diff options
Diffstat (limited to 'drivers/pci/controller')
125 files changed, 49769 insertions, 13291 deletions
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 6671946dbf66..c254d2b8bf17 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -3,139 +3,72 @@ menu "PCI controller drivers" depends on PCI -config PCI_MVEBU - bool "Marvell EBU PCIe controller" - depends on ARCH_MVEBU || ARCH_DOVE || COMPILE_TEST - depends on MVEBU_MBUS - depends on ARM - depends on OF - select PCI_BRIDGE_EMUL +config PCI_HOST_COMMON + tristate + select PCI_ECAM config PCI_AARDVARK - bool "Aardvark PCIe controller" + tristate "Aardvark PCIe controller" depends on (ARCH_MVEBU && ARM64) || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + 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 3700 SoC. -menu "Cadence PCIe controllers support" - -config PCIE_CADENCE - bool - -config PCIE_CADENCE_HOST - bool "Cadence PCIe host controller" - depends on OF - depends on PCI - select IRQ_DOMAIN - select PCIE_CADENCE - help - Say Y here if you want to support the Cadence PCIe controller in host - mode. This PCIe controller may be embedded into many different vendors - SoCs. - -config PCIE_CADENCE_EP - bool "Cadence PCIe endpoint controller" - depends on OF - depends on PCI_ENDPOINT - select PCIE_CADENCE - help - Say Y here if you want to support the Cadence PCIe controller in - endpoint mode. This PCIe controller may be embedded into many - different vendors SoCs. - -endmenu - -config PCIE_XILINX_NWL - bool "NWL PCIe Core" - depends on ARCH_ZYNQMP || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN - help - Say 'Y' here if you want kernel support for Xilinx - NWL PCIe controller. The controller can act as Root Port - or End Point. The current option selection will only - support root port enabling. - -config PCI_FTPCI100 - bool "Faraday Technology FTPCI100 PCI controller" - depends on OF - default ARCH_GEMINI - -config PCI_TEGRA - bool "NVIDIA Tegra PCIe controller" - depends on ARCH_TEGRA || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN - help - Say Y here if you want support for the PCIe host controller found - on NVIDIA Tegra SoCs. - -config PCI_RCAR_GEN2 - bool "Renesas R-Car Gen2 Internal PCI controller" - depends on ARCH_RENESAS || COMPILE_TEST - depends on ARM +config PCIE_ALTERA + tristate "Altera PCIe controller" + depends on ARM || NIOS2 || ARM64 || 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. + Say Y here if you want to enable PCIe controller support on Altera + FPGA. -config PCIE_RCAR - bool "Renesas R-Car PCIe controller" - depends on ARCH_RENESAS || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN +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 controller support on R-Car SoCs. + Say Y here if you want PCIe MSI support for the Altera FPGA. + This MSI driver supports Altera MSI to GIC controller IP. -config PCI_HOST_COMMON - bool - select PCI_ECAM +config PCIE_APPLE_MSI_DOORBELL_ADDR + hex + default 0xfffff000 + depends on PCIE_APPLE -config PCI_HOST_GENERIC - bool "Generic PCI host controller" +config PCIE_APPLE + tristate "Apple PCIe controller" + depends on ARCH_APPLE || COMPILE_TEST depends on OF + depends on PCI_MSI select PCI_HOST_COMMON - select IRQ_DOMAIN - help - Say Y here if you want to support a simple generic PCI host - controller, such as the one emulated by kvmtool. - -config PCIE_XILINX - bool "Xilinx AXI PCIe host bridge support" - depends on OF || COMPILE_TEST - help - Say 'Y' here if you want kernel to support the Xilinx AXI PCIe - Host Bridge driver. - -config PCI_XGENE - bool "X-Gene PCIe controller" - depends on ARM64 || COMPILE_TEST - depends on OF || (ACPI && PCI_QUIRKS) + select IRQ_MSI_LIB help - Say Y here if you want internal PCI support on APM X-Gene SoC. - There are 5 internal PCIe ports available. Each port is GEN3 capable - and have varied lanes from x1 to x8. + Say Y here if you want to enable PCIe controller support on Apple + system-on-chips, like the Apple M1. This is required for the USB + type-A ports, Ethernet, Wi-Fi, and Bluetooth. -config PCI_XGENE_MSI - bool "X-Gene v1 PCIe MSI feature" - depends on PCI_XGENE - depends on PCI_MSI_IRQ_DOMAIN - default y - help - Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC. - This MSI driver supports 5 PCIe ports on the APM X-Gene v1 SoC. - -config PCI_V3_SEMI - bool "V3 Semiconductor PCI controller" - depends on OF - depends on ARM || COMPILE_TEST - default ARCH_INTEGRATOR_AP + If unsure, say Y if you have an Apple Silicon system. config PCI_VERSATILE bool "ARM Versatile PB PCI controller" - depends on ARCH_VERSATILE + depends on ARCH_VERSATILE || COMPILE_TEST + +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 + Broadcom STB based SoCs, like the Raspberry Pi 4. config PCIE_IPROC tristate @@ -155,7 +88,7 @@ config PCIE_IPROC_PLATFORM through the generic platform bus interface config PCIE_IPROC_BCMA - tristate "Broadcom iProc PCIe BCMA bus driver" + tristate "Broadcom iProc BCMA PCIe controller" depends on ARM && (ARCH_BCM_IPROC || COMPILE_TEST) select PCIE_IPROC select BCMA @@ -167,27 +100,13 @@ config PCIE_IPROC_BCMA config PCIE_IPROC_MSI bool "Broadcom iProc PCIe MSI support" depends on PCIE_IPROC_PLATFORM || PCIE_IPROC_BCMA - depends on PCI_MSI_IRQ_DOMAIN + 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 PCIe controller -config PCIE_ALTERA - bool "Altera PCIe controller" - depends on ARM || NIOS2 || COMPILE_TEST - help - Say Y here if you want to enable PCIe controller support on Altera - FPGA. - -config PCIE_ALTERA_MSI - bool "Altera PCIe MSI feature" - depends on PCIE_ALTERA - depends on PCI_MSI_IRQ_DOMAIN - help - Say Y here if you want PCIe MSI support for the Altera FPGA. - This MSI driver supports Altera MSI to GIC controller IP. - config PCI_HOST_THUNDER_PEM bool "Cavium Thunder PCIe controller to off-chip devices" depends on ARM64 || COMPILE_TEST @@ -204,15 +123,166 @@ config PCI_HOST_THUNDER_ECAM help Say Y here if you want ECAM support for CN88XX-Pass-1.x Cavium Thunder SoCs. +config PCI_FTPCI100 + bool "Faraday Technology FTPCI100 PCI controller" + depends on OF + default ARCH_GEMINI + +config PCI_HOST_GENERIC + tristate "Generic PCI host controller" + depends on OF + select PCI_HOST_COMMON + select IRQ_DOMAIN + help + Say Y here if you want to support a simple generic PCI host + controller, such as the one emulated by kvmtool. + +config PCIE_HISI_ERR + depends on ACPI_APEI_GHES && (ARM64 || COMPILE_TEST) + bool "HiSilicon HIP PCIe controller error handling driver" + help + Say Y here if you want error handling support + for the PCIe controller's errors on HiSilicon HIP SoCs + +config PCI_IXP4XX + bool "Intel IXP4xx PCI controller" + depends on OF + depends on ARCH_IXP4XX || COMPILE_TEST + default ARCH_IXP4XX + help + Say Y here if you want support for the PCI host controller found + in the Intel IXP4xx XScale-based network processor SoC. + +config 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, + and devices attached to them, to be removed from the default + PCI domain and placed within the VMD domain. This provides + more bus resources than are otherwise possible with a + single domain. If you know your system provides one of these and + has devices attached to it, say Y; if you are not sure, say N. + + To compile this driver as a module, choose M here: the + module will be called vmd. + +config PCI_LOONGSON + bool "LOONGSON PCIe controller" + depends on MACH_LOONGSON64 || COMPILE_TEST + depends on OF || ACPI + depends on PCI_QUIRKS + default MACH_LOONGSON64 + help + Say Y here if you want to enable PCI controller support on + Loongson systems. + +config PCI_MVEBU + tristate "Marvell EBU PCIe controller" + depends on ARCH_MVEBU || ARCH_DOVE || COMPILE_TEST + depends on MVEBU_MBUS + depends on ARM + depends on OF + select PCI_BRIDGE_EMUL + help + Add support for Marvell EBU PCIe controller. This PCIe controller + is used on 32-bit Marvell ARM SoCs: Dove, Kirkwood, Armada 370, + Armada XP, Armada 375, Armada 38x and Armada 39x. + +config PCIE_MEDIATEK + tristate "MediaTek PCIe controller" + 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. + +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, + and support up to 256 MSI interrupt numbers for + multi-function devices. + + Say Y here if you want to enable Gen3 PCIe controller support on + MediaTek SoCs. + +config PCIE_MT7621 + tristate "MediaTek MT7621 PCIe controller" + depends on SOC_MT7621 || COMPILE_TEST + select PHY_MT7621_PCI + default SOC_MT7621 + help + This selects a driver for the MediaTek MT7621 PCIe Controller. + +config PCI_HYPERV_INTERFACE + tristate "Microsoft Hyper-V PCI Interface" + depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI + help + The Hyper-V PCI Interface is a helper driver that allows other + drivers to have a common interface with the Hyper-V PCI frontend + driver. + +config PCI_TEGRA + bool "NVIDIA Tegra PCIe controller" + depends on ARCH_TEGRA || COMPILE_TEST + depends on PCI_MSI + select IRQ_MSI_LIB + help + Say Y here if you want support for the PCIe host controller found + on NVIDIA Tegra SoCs. + +config PCIE_RCAR_HOST + bool "Renesas R-Car PCIe controller (host mode)" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PCI_MSI + select IRQ_MSI_LIB + help + Say Y here if you want PCIe controller support on R-Car SoCs in host + mode. + +config PCIE_RCAR_EP + bool "Renesas R-Car PCIe controller (endpoint mode)" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PCI_ENDPOINT + help + Say Y here if you want PCIe controller support on R-Car SoCs in + endpoint mode. + +config PCI_RCAR_GEN2 + bool "Renesas R-Car Gen2 Internal PCI controller" + depends on (ARCH_RENESAS && ARM) || COMPILE_TEST + help + Say Y here if you want internal PCI support on R-Car Gen2 SoC. + 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 depends on PCI config PCIE_ROCKCHIP_HOST - tristate "Rockchip PCIe host controller" + tristate "Rockchip PCIe controller (host mode)" depends on ARCH_ROCKCHIP || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select MFD_SYSCON select PCIE_ROCKCHIP help @@ -221,7 +291,7 @@ config PCIE_ROCKCHIP_HOST 4 slots. config PCIE_ROCKCHIP_EP - bool "Rockchip PCIe endpoint controller" + bool "Rockchip PCIe controller (endpoint mode)" depends on ARCH_ROCKCHIP || COMPILE_TEST depends on OF depends on PCI_ENDPOINT @@ -232,53 +302,73 @@ config PCIE_ROCKCHIP_EP endpoint mode on Rockchip SoC. There is 1 internal PCIe port available to support GEN2 with 4 slots. -config PCIE_MEDIATEK - tristate "MediaTek PCIe controller" - depends on ARCH_MEDIATEK || COMPILE_TEST +config PCI_V3_SEMI + bool "V3 Semiconductor PCI controller" depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on ARM || COMPILE_TEST + default ARCH_INTEGRATOR_AP + +config PCI_XGENE + bool "X-Gene PCIe controller" + depends on ARM64 || COMPILE_TEST + depends on OF || (ACPI && PCI_QUIRKS) help - Say Y here if you want to enable PCIe controller support on - MediaTek SoCs. + Say Y here if you want internal PCI support on APM X-Gene SoC. + There are 5 internal PCIe ports available. Each port is GEN3 capable + and have varied lanes from x1 to x8. -config PCIE_MOBIVEIL - bool "Mobiveil AXI PCIe controller" - depends on ARCH_ZYNQMP || COMPILE_TEST +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. + This MSI driver supports 5 PCIe ports on the APM X-Gene v1 SoC. + +config PCIE_XILINX + bool "Xilinx AXI PCIe controller" depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI + select IRQ_MSI_LIB help - Say Y here if you want to enable support for the Mobiveil AXI PCIe - Soft IP. It has up to 8 outbound and inbound windows - for address translation and it is a PCIe Gen4 IP. + Say 'Y' here if you want kernel to support the Xilinx AXI PCIe + Host Bridge driver. -config PCIE_TANGO_SMP8759 - bool "Tango SMP8759 PCIe controller (DANGEROUS)" - depends on ARCH_TANGO && PCI_MSI && OF - depends on BROKEN +config PCIE_XILINX_DMA_PL + bool "Xilinx DMA PL PCIe host bridge support" + depends on ARCH_ZYNQMP || COMPILE_TEST + depends on PCI_MSI select PCI_HOST_COMMON + select IRQ_MSI_LIB help - Say Y here to enable PCIe controller support for Sigma Designs - Tango SMP8759-based systems. - - Note: The SMP8759 controller multiplexes PCI config and MMIO - accesses, and Linux doesn't provide a way to serialize them. - This can lead to data corruption if drivers perform concurrent - config and MMIO accesses. + 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 + Root Port. If your system provides Xilinx PCIe host controller + bridge DMA as Soft IP say 'Y'; if you are not sure, say 'N'. -config VMD - depends on PCI_MSI && X86_64 && SRCU - tristate "Intel Volume Management Device Driver" - ---help--- - Adds support for the Intel Volume Management Device (VMD). VMD is a - secondary PCI host bridge that allows PCI Express root ports, - and devices attached to them, to be removed from the default - PCI domain and placed within the VMD domain. This provides - more bus resources than are otherwise possible with a - single domain. If you know your system provides one of these and - has devices attached to it, say Y; if you are not sure, say N. +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 + or End Point. The current option selection will only + support root port enabling. - To compile this driver as a module, choose M here: the - module will be called vmd. +config PCIE_XILINX_CPM + bool "Xilinx Versal CPM PCI controller" + depends on ARCH_ZYNQMP || COMPILE_TEST + select PCI_HOST_COMMON + help + Say 'Y' here if you want kernel support for the + Xilinx Versal CPM host bridge. +source "drivers/pci/controller/cadence/Kconfig" source "drivers/pci/controller/dwc/Kconfig" +source "drivers/pci/controller/mobiveil/Kconfig" +source "drivers/pci/controller/plda/Kconfig" endmenu diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile index d56a507495c5..229929a945c2 100644 --- a/drivers/pci/controller/Makefile +++ b/drivers/pci/controller/Makefile @@ -1,19 +1,26 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_PCIE_CADENCE) += pcie-cadence.o -obj-$(CONFIG_PCIE_CADENCE_HOST) += pcie-cadence-host.o -obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep.o +obj-$(CONFIG_PCIE_CADENCE) += cadence/ obj-$(CONFIG_PCI_FTPCI100) += pci-ftpci100.o +obj-$(CONFIG_PCI_IXP4XX) += pci-ixp4xx.o obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o +obj-$(CONFIG_PCI_HYPERV_INTERFACE) += pci-hyperv-intf.o obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o obj-$(CONFIG_PCI_AARDVARK) += pci-aardvark.o obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o -obj-$(CONFIG_PCIE_RCAR) += pcie-rcar.o +obj-$(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-$(CONFIG_PCI_HOST_THUNDER_ECAM) += pci-thunder-ecam.o +obj-$(CONFIG_PCI_HOST_THUNDER_PEM) += pci-thunder-pem.o obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o obj-$(CONFIG_PCIE_XILINX_NWL) += pcie-xilinx-nwl.o +obj-$(CONFIG_PCIE_XILINX_CPM) += pcie-xilinx-cpm.o +obj-$(CONFIG_PCIE_XILINX_DMA_PL) += pcie-xilinx-dma-pl.o obj-$(CONFIG_PCI_V3_SEMI) += pci-v3-semi.o +obj-$(CONFIG_PCI_XGENE) += pci-xgene.o obj-$(CONFIG_PCI_XGENE_MSI) += pci-xgene-msi.o obj-$(CONFIG_PCI_VERSATILE) += pci-versatile.o obj-$(CONFIG_PCIE_IPROC) += pcie-iproc.o @@ -26,11 +33,18 @@ obj-$(CONFIG_PCIE_ROCKCHIP) += pcie-rockchip.o obj-$(CONFIG_PCIE_ROCKCHIP_EP) += pcie-rockchip-ep.o obj-$(CONFIG_PCIE_ROCKCHIP_HOST) += pcie-rockchip-host.o obj-$(CONFIG_PCIE_MEDIATEK) += pcie-mediatek.o -obj-$(CONFIG_PCIE_MOBIVEIL) += pcie-mobiveil.o -obj-$(CONFIG_PCIE_TANGO_SMP8759) += pcie-tango.o +obj-$(CONFIG_PCIE_MEDIATEK_GEN3) += pcie-mediatek-gen3.o obj-$(CONFIG_VMD) += vmd.o +obj-$(CONFIG_PCIE_BRCMSTB) += pcie-brcmstb.o +obj-$(CONFIG_PCI_LOONGSON) += pci-loongson.o +obj-$(CONFIG_PCIE_HISI_ERR) += pcie-hisi-error.o +obj-$(CONFIG_PCIE_APPLE) += pcie-apple.o +obj-$(CONFIG_PCIE_MT7621) += pcie-mt7621.o + # pcie-hisi.o quirks are needed even without CONFIG_PCIE_DW obj-y += dwc/ +obj-y += mobiveil/ +obj-y += plda/ # The following drivers are for devices that use the generic ACPI @@ -43,8 +57,10 @@ obj-y += dwc/ # ARM64 and use internal ifdefs to only build the pieces we need # depending on whether ACPI, the DT driver, or both are enabled. -ifdef CONFIG_PCI +ifdef CONFIG_ACPI +ifdef CONFIG_PCI_QUIRKS obj-$(CONFIG_ARM64) += pci-thunder-ecam.o obj-$(CONFIG_ARM64) += pci-thunder-pem.o obj-$(CONFIG_ARM64) += pci-xgene.o endif +endif diff --git a/drivers/pci/controller/cadence/Kconfig b/drivers/pci/controller/cadence/Kconfig new file mode 100644 index 000000000000..9e651d545973 --- /dev/null +++ b/drivers/pci/controller/cadence/Kconfig @@ -0,0 +1,95 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Cadence-based PCIe controllers" + depends on PCI + +config PCIE_CADENCE + tristate + +config PCIE_CADENCE_HOST + tristate + depends on OF + select IRQ_DOMAIN + select PCIE_CADENCE + +config PCIE_CADENCE_EP + tristate + depends on OF + depends on PCI_ENDPOINT + select PCIE_CADENCE + +config PCIE_CADENCE_PLAT + tristate + +config PCIE_CADENCE_PLAT_HOST + tristate "Cadence platform PCIe controller (host mode)" + depends on OF + select PCIE_CADENCE_HOST + select PCIE_CADENCE_PLAT + help + Say Y here if you want to support the Cadence PCIe platform controller in + host mode. This PCIe controller may be embedded into many different + vendors SoCs. + +config PCIE_CADENCE_PLAT_EP + tristate "Cadence platform PCIe controller (endpoint mode)" + depends on OF + depends on PCI_ENDPOINT + select PCIE_CADENCE_EP + select PCIE_CADENCE_PLAT + help + Say Y here if you want to support the Cadence PCIe platform controller in + endpoint mode. This PCIe controller may be embedded into many + different vendors SoCs. + +config PCI_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 + tristate + select PCIE_CADENCE_HOST if PCI_J721E_HOST != n + select PCIE_CADENCE_EP if PCI_J721E_EP != n + +config PCI_J721E_HOST + tristate "TI J721E PCIe controller (host mode)" + depends on ARCH_K3 || COMPILE_TEST + depends on OF + select PCI_J721E + help + Say Y here if you want to support the TI J721E PCIe platform + controller in host mode. TI J721E PCIe controller uses Cadence PCIe + core. + +config PCI_J721E_EP + tristate "TI J721E PCIe controller (endpoint mode)" + depends on ARCH_K3 || COMPILE_TEST + depends on OF + depends on PCI_ENDPOINT + select PCI_J721E + help + Say Y here if you want to support the TI J721E PCIe platform + controller in endpoint mode. TI J721E PCIe controller uses Cadence PCIe + core. + +endmenu diff --git a/drivers/pci/controller/cadence/Makefile b/drivers/pci/controller/cadence/Makefile new file mode 100644 index 000000000000..b8ec1cecfaa8 --- /dev/null +++ b/drivers/pci/controller/cadence/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +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 new file mode 100644 index 000000000000..ecd1b0312400 --- /dev/null +++ b/drivers/pci/controller/cadence/pci-j721e.c @@ -0,0 +1,772 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * pci-j721e - PCIe controller driver for TI's J721E SoCs + * + * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com + * Author: Kishon Vijay Abraham I <kishon@ti.com> + */ + +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/container_of.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/io.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> + +#include "../../pci.h" +#include "pcie-cadence.h" + +#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) +#define J7200_LINK_DOWN BIT(10) + +#define J721E_PCIE_USER_CMD_STATUS 0x4 +#define LINK_TRAINING_ENABLE BIT(0) + +#define J721E_PCIE_USER_LINKSTATUS 0x14 +#define LINK_STATUS GENMASK(1, 0) + +enum link_status { + NO_RECEIVERS_DETECTED, + LINK_TRAINING_IN_PROGRESS, + LINK_UP_DL_IN_PROGRESS, + LINK_UP_DL_COMPLETED, +}; + +#define J721E_MODE_RC BIT(7) +#define LANE_COUNT(n) ((n) << 8) + +#define ACSPCIE_PAD_DISABLE_MASK GENMASK(1, 0) +#define GENERATION_SEL_MASK GENMASK(1, 0) + +struct j721e_pcie { + struct cdns_pcie *cdns_pcie; + struct clk *refclk; + u32 mode; + u32 num_lanes; + u32 max_lanes; + struct gpio_desc *reset_gpio; + void __iomem *user_cfg_base; + void __iomem *intd_cfg_base; + u32 linkdown_irq_regfield; +}; + +enum j721e_pcie_mode { + PCI_MODE_RC, + PCI_MODE_EP, +}; + +struct j721e_pcie_data { + enum j721e_pcie_mode mode; + unsigned int quirk_retrain_flag:1; + unsigned int quirk_detect_quiet_flag:1; + unsigned int quirk_disable_flr:1; + u32 linkdown_irq_regfield; + unsigned int byte_access_allowed:1; + unsigned int max_lanes; +}; + +static inline u32 j721e_pcie_user_readl(struct j721e_pcie *pcie, u32 offset) +{ + return readl(pcie->user_cfg_base + offset); +} + +static inline void j721e_pcie_user_writel(struct j721e_pcie *pcie, u32 offset, + u32 value) +{ + writel(value, pcie->user_cfg_base + offset); +} + +static inline u32 j721e_pcie_intd_readl(struct j721e_pcie *pcie, u32 offset) +{ + return readl(pcie->intd_cfg_base + offset); +} + +static inline void j721e_pcie_intd_writel(struct j721e_pcie *pcie, u32 offset, + u32 value) +{ + writel(value, pcie->intd_cfg_base + offset); +} + +static irqreturn_t j721e_pcie_link_irq_handler(int irq, void *priv) +{ + struct j721e_pcie *pcie = priv; + struct device *dev = pcie->cdns_pcie->dev; + u32 reg; + + reg = j721e_pcie_intd_readl(pcie, STATUS_REG_SYS_2); + if (!(reg & pcie->linkdown_irq_regfield)) + return IRQ_NONE; + + dev_err(dev, "LINK DOWN!\n"); + + j721e_pcie_intd_writel(pcie, STATUS_CLR_REG_SYS_2, pcie->linkdown_irq_regfield); + return IRQ_HANDLED; +} + +static void j721e_pcie_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; + + reg = j721e_pcie_intd_readl(pcie, ENABLE_REG_SYS_2); + reg |= pcie->linkdown_irq_regfield; + j721e_pcie_intd_writel(pcie, ENABLE_REG_SYS_2, reg); +} + +static int j721e_pcie_start_link(struct cdns_pcie *cdns_pcie) +{ + struct j721e_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 reg; + + reg = j721e_pcie_user_readl(pcie, J721E_PCIE_USER_CMD_STATUS); + reg |= LINK_TRAINING_ENABLE; + j721e_pcie_user_writel(pcie, J721E_PCIE_USER_CMD_STATUS, reg); + + return 0; +} + +static void j721e_pcie_stop_link(struct cdns_pcie *cdns_pcie) +{ + struct j721e_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 reg; + + reg = j721e_pcie_user_readl(pcie, J721E_PCIE_USER_CMD_STATUS); + reg &= ~LINK_TRAINING_ENABLE; + j721e_pcie_user_writel(pcie, J721E_PCIE_USER_CMD_STATUS, reg); +} + +static bool j721e_pcie_link_up(struct cdns_pcie *cdns_pcie) +{ + struct j721e_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 reg; + + reg = j721e_pcie_user_readl(pcie, J721E_PCIE_USER_LINKSTATUS); + return (reg & LINK_STATUS) == LINK_UP_DL_COMPLETED; +} + +static const struct cdns_pcie_ops j721e_pcie_ops = { + .start_link = j721e_pcie_start_link, + .stop_link = j721e_pcie_stop_link, + .link_up = j721e_pcie_link_up, +}; + +static int j721e_pcie_set_mode(struct j721e_pcie *pcie, struct regmap *syscon, + unsigned int offset) +{ + struct device *dev = pcie->cdns_pcie->dev; + u32 mask = J721E_MODE_RC; + u32 mode = pcie->mode; + u32 val = 0; + int ret = 0; + + if (mode == PCI_MODE_RC) + val = J721E_MODE_RC; + + ret = regmap_update_bits(syscon, offset, mask, val); + if (ret) + dev_err(dev, "failed to set pcie mode\n"); + + return ret; +} + +static int j721e_pcie_set_link_speed(struct j721e_pcie *pcie, + struct regmap *syscon, unsigned int offset) +{ + struct device *dev = pcie->cdns_pcie->dev; + struct device_node *np = dev->of_node; + int link_speed; + u32 val = 0; + int ret; + + link_speed = of_pci_get_max_link_speed(np); + if (link_speed < 2) + link_speed = 2; + + val = link_speed - 1; + ret = regmap_update_bits(syscon, offset, GENERATION_SEL_MASK, val); + if (ret) + dev_err(dev, "failed to set link speed\n"); + + return ret; +} + +static int j721e_pcie_set_lane_count(struct j721e_pcie *pcie, + struct regmap *syscon, unsigned int offset) +{ + struct device *dev = pcie->cdns_pcie->dev; + u32 lanes = pcie->num_lanes; + u32 mask = BIT(8); + u32 val = 0; + int ret; + + if (pcie->max_lanes == 4) + mask = GENMASK(9, 8); + + val = LANE_COUNT(lanes - 1); + ret = regmap_update_bits(syscon, offset, mask, val); + if (ret) + dev_err(dev, "failed to set link count\n"); + + return ret; +} + +static int j721e_enable_acspcie_refclk(struct j721e_pcie *pcie, + struct regmap *syscon) +{ + struct device *dev = pcie->cdns_pcie->dev; + struct device_node *node = dev->of_node; + u32 mask = ACSPCIE_PAD_DISABLE_MASK; + struct of_phandle_args args; + u32 val; + int ret; + + ret = of_parse_phandle_with_fixed_args(node, + "ti,syscon-acspcie-proxy-ctrl", + 1, 0, &args); + if (ret) { + dev_err(dev, + "ti,syscon-acspcie-proxy-ctrl has invalid arguments\n"); + return ret; + } + + /* Clear PAD IO disable bits to enable refclk output */ + val = ~(args.args[0]); + ret = regmap_update_bits(syscon, 0, mask, val); + if (ret) { + dev_err(dev, "failed to enable ACSPCIE refclk: %d\n", ret); + return ret; + } + + return 0; +} + +static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie) +{ + struct device *dev = pcie->cdns_pcie->dev; + struct device_node *node = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; + struct regmap *syscon; + int ret; + + syscon = syscon_regmap_lookup_by_phandle(node, "ti,syscon-pcie-ctrl"); + if (IS_ERR(syscon)) { + dev_err(dev, "Unable to get ti,syscon-pcie-ctrl regmap\n"); + return PTR_ERR(syscon); + } + + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(node, "ti,syscon-pcie-ctrl", 1, + 0, &args); + if (!ret) + offset = args.args[0]; + + /* + * 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"); + return ret; + } + + ret = j721e_pcie_set_link_speed(pcie, syscon, offset); + if (ret < 0) { + dev_err(dev, "Failed to set link speed\n"); + return ret; + } + + ret = j721e_pcie_set_lane_count(pcie, syscon, offset); + if (ret < 0) { + dev_err(dev, "Failed to set num-lanes\n"); + return ret; + } + + 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"); + if (!syscon) + return 0; + + return j721e_enable_acspcie_refclk(pcie, syscon); +} + +static int cdns_ti_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *value) +{ + if (pci_is_root_bus(bus)) + return pci_generic_config_read32(bus, devfn, where, size, + value); + + return pci_generic_config_read(bus, devfn, where, size, value); +} + +static int cdns_ti_pcie_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 value) +{ + if (pci_is_root_bus(bus)) + return pci_generic_config_write32(bus, devfn, where, size, + value); + + return pci_generic_config_write(bus, devfn, where, size, value); +} + +static struct pci_ops cdns_ti_pcie_host_ops = { + .map_bus = cdns_pci_map_bus, + .read = cdns_ti_pcie_config_read, + .write = cdns_ti_pcie_config_write, +}; + +static const struct j721e_pcie_data j721e_pcie_rc_data = { + .mode = PCI_MODE_RC, + .quirk_retrain_flag = true, + .byte_access_allowed = false, + .linkdown_irq_regfield = LINK_DOWN, + .max_lanes = 2, +}; + +static const struct j721e_pcie_data j721e_pcie_ep_data = { + .mode = PCI_MODE_EP, + .linkdown_irq_regfield = LINK_DOWN, + .max_lanes = 2, +}; + +static const struct j721e_pcie_data j7200_pcie_rc_data = { + .mode = PCI_MODE_RC, + .quirk_detect_quiet_flag = true, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .byte_access_allowed = true, + .max_lanes = 2, +}; + +static const struct j721e_pcie_data j7200_pcie_ep_data = { + .mode = PCI_MODE_EP, + .quirk_detect_quiet_flag = true, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .quirk_disable_flr = true, + .max_lanes = 2, +}; + +static const struct j721e_pcie_data am64_pcie_rc_data = { + .mode = PCI_MODE_RC, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .byte_access_allowed = true, + .max_lanes = 1, +}; + +static const struct j721e_pcie_data am64_pcie_ep_data = { + .mode = PCI_MODE_EP, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .max_lanes = 1, +}; + +static const struct j721e_pcie_data j784s4_pcie_rc_data = { + .mode = PCI_MODE_RC, + .quirk_retrain_flag = true, + .byte_access_allowed = false, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .max_lanes = 4, +}; + +static const struct j721e_pcie_data j784s4_pcie_ep_data = { + .mode = PCI_MODE_EP, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .max_lanes = 4, +}; + +static const struct j721e_pcie_data j722s_pcie_rc_data = { + .mode = PCI_MODE_RC, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .byte_access_allowed = true, + .max_lanes = 1, +}; + +static const struct of_device_id of_j721e_pcie_match[] = { + { + .compatible = "ti,j721e-pcie-host", + .data = &j721e_pcie_rc_data, + }, + { + .compatible = "ti,j721e-pcie-ep", + .data = &j721e_pcie_ep_data, + }, + { + .compatible = "ti,j7200-pcie-host", + .data = &j7200_pcie_rc_data, + }, + { + .compatible = "ti,j7200-pcie-ep", + .data = &j7200_pcie_ep_data, + }, + { + .compatible = "ti,am64-pcie-host", + .data = &am64_pcie_rc_data, + }, + { + .compatible = "ti,am64-pcie-ep", + .data = &am64_pcie_ep_data, + }, + { + .compatible = "ti,j784s4-pcie-host", + .data = &j784s4_pcie_rc_data, + }, + { + .compatible = "ti,j784s4-pcie-ep", + .data = &j784s4_pcie_ep_data, + }, + { + .compatible = "ti,j722s-pcie-host", + .data = &j722s_pcie_rc_data, + }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_j721e_pcie_match); + +static int j721e_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + struct pci_host_bridge *bridge; + const struct j721e_pcie_data *data; + struct cdns_pcie *cdns_pcie; + struct j721e_pcie *pcie; + struct cdns_pcie_rc *rc = NULL; + struct cdns_pcie_ep *ep = NULL; + void __iomem *base; + u32 num_lanes; + u32 mode; + int ret; + int irq; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + mode = (u32)data->mode; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + switch (mode) { + case PCI_MODE_RC: + if (!IS_ENABLED(CONFIG_PCI_J721E_HOST)) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); + if (!bridge) + return -ENOMEM; + + if (!data->byte_access_allowed) + bridge->ops = &cdns_ti_pcie_host_ops; + rc = pci_host_bridge_priv(bridge); + rc->quirk_retrain_flag = data->quirk_retrain_flag; + rc->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; + + cdns_pcie = &rc->pcie; + cdns_pcie->dev = dev; + cdns_pcie->ops = &j721e_pcie_ops; + pcie->cdns_pcie = cdns_pcie; + break; + case PCI_MODE_EP: + if (!IS_ENABLED(CONFIG_PCI_J721E_EP)) + return -ENODEV; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; + ep->quirk_disable_flr = data->quirk_disable_flr; + + cdns_pcie = &ep->pcie; + cdns_pcie->dev = dev; + cdns_pcie->ops = &j721e_pcie_ops; + pcie->cdns_pcie = cdns_pcie; + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + return 0; + } + + pcie->mode = mode; + pcie->linkdown_irq_regfield = data->linkdown_irq_regfield; + + base = devm_platform_ioremap_resource_byname(pdev, "intd_cfg"); + if (IS_ERR(base)) + return PTR_ERR(base); + pcie->intd_cfg_base = base; + + base = devm_platform_ioremap_resource_byname(pdev, "user_cfg"); + if (IS_ERR(base)) + return PTR_ERR(base); + pcie->user_cfg_base = base; + + ret = of_property_read_u32(node, "num-lanes", &num_lanes); + if (ret || num_lanes > data->max_lanes) { + dev_warn(dev, "num-lanes property not provided or invalid, setting num-lanes to 1\n"); + num_lanes = 1; + } + + pcie->num_lanes = num_lanes; + pcie->max_lanes = data->max_lanes; + + if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48))) + return -EINVAL; + + irq = platform_get_irq_byname(pdev, "link_state"); + if (irq < 0) + return irq; + + dev_set_drvdata(dev, pcie); + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err_probe(dev, ret, "pm_runtime_get_sync failed\n"); + goto err_get_sync; + } + + ret = j721e_pcie_ctrl_init(pcie); + if (ret < 0) { + dev_err_probe(dev, ret, "j721e_pcie_ctrl_init failed\n"); + goto err_get_sync; + } + + ret = devm_request_irq(dev, irq, j721e_pcie_link_irq_handler, 0, + "j721e-pcie-link-down-irq", pcie); + if (ret < 0) { + dev_err_probe(dev, ret, "failed to request link state IRQ %d\n", irq); + goto err_get_sync; + } + + j721e_pcie_config_link_irq(pcie); + + switch (mode) { + case PCI_MODE_RC: + 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; + } + + ret = cdns_pcie_init_phy(dev, cdns_pcie); + if (ret) { + dev_err_probe(dev, ret, "Failed to init phy\n"); + goto err_get_sync; + } + + 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; + } + + /* + * Section 2.2 of the PCI Express Card Electromechanical + * Specification (Revision 5.1) mandates that the deassertion + * of the PERST# signal should be delayed by 100 ms (TPVPERL). + * This shall ensure that the power and the reference clock + * are stable. + */ + if (pcie->reset_gpio) { + msleep(PCIE_T_PVPERL_MS); + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + } + + ret = cdns_pcie_host_setup(rc); + if (ret < 0) + goto err_pcie_setup; + + break; + case PCI_MODE_EP: + ret = cdns_pcie_init_phy(dev, cdns_pcie); + if (ret) { + dev_err_probe(dev, ret, "Failed to init phy\n"); + goto err_get_sync; + } + + ret = cdns_pcie_ep_setup(ep); + if (ret < 0) + goto err_pcie_setup; + + break; + } + + return 0; + +err_pcie_setup: + cdns_pcie_disable_phy(cdns_pcie); + +err_get_sync: + pm_runtime_put(dev); + pm_runtime_disable(dev); + + return ret; +} + +static void j721e_pcie_remove(struct platform_device *pdev) +{ + struct j721e_pcie *pcie = platform_get_drvdata(pdev); + struct cdns_pcie *cdns_pcie = pcie->cdns_pcie; + struct device *dev = &pdev->dev; + struct cdns_pcie_ep *ep; + struct cdns_pcie_rc *rc; + + if (pcie->mode == PCI_MODE_RC) { + rc = container_of(cdns_pcie, struct cdns_pcie_rc, pcie); + cdns_pcie_host_disable(rc); + } else { + ep = container_of(cdns_pcie, struct cdns_pcie_ep, pcie); + cdns_pcie_ep_disable(ep); + } + + gpiod_set_value_cansleep(pcie->reset_gpio, 0); + + cdns_pcie_disable_phy(cdns_pcie); + j721e_pcie_disable_link_irq(pcie); + pm_runtime_put(dev); + pm_runtime_disable(dev); +} + +static int j721e_pcie_suspend_noirq(struct device *dev) +{ + struct j721e_pcie *pcie = dev_get_drvdata(dev); + + if (pcie->mode == PCI_MODE_RC) { + gpiod_set_value_cansleep(pcie->reset_gpio, 0); + clk_disable_unprepare(pcie->refclk); + } + + cdns_pcie_disable_phy(pcie->cdns_pcie); + + return 0; +} + +static int j721e_pcie_resume_noirq(struct device *dev) +{ + struct j721e_pcie *pcie = dev_get_drvdata(dev); + struct cdns_pcie *cdns_pcie = pcie->cdns_pcie; + int ret; + + ret = j721e_pcie_ctrl_init(pcie); + if (ret < 0) + return ret; + + j721e_pcie_config_link_irq(pcie); + + /* + * This is not called explicitly in the probe, it is called by + * cdns_pcie_init_phy(). + */ + ret = cdns_pcie_enable_phy(pcie->cdns_pcie); + if (ret < 0) + return ret; + + if (pcie->mode == PCI_MODE_RC) { + struct cdns_pcie_rc *rc = cdns_pcie_to_rc(cdns_pcie); + + ret = clk_prepare_enable(pcie->refclk); + if (ret < 0) + return ret; + + /* + * Section 2.2 of the PCI Express Card Electromechanical + * Specification (Revision 5.1) mandates that the deassertion + * of the PERST# signal should be delayed by 100 ms (TPVPERL). + * This shall ensure that the power and the reference clock + * are stable. + */ + if (pcie->reset_gpio) { + msleep(PCIE_T_PVPERL_MS); + 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; + } + + /* + * Reset internal status of BARs to force reinitialization in + * cdns_pcie_host_init(). + */ + 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; + } + } + + return 0; +} + +static DEFINE_NOIRQ_DEV_PM_OPS(j721e_pcie_pm_ops, + j721e_pcie_suspend_noirq, + j721e_pcie_resume_noirq); + +static struct platform_driver j721e_pcie_driver = { + .probe = j721e_pcie_probe, + .remove = j721e_pcie_remove, + .driver = { + .name = "j721e-pcie", + .of_match_table = of_j721e_pcie_match, + .suppress_bind_attrs = true, + .pm = pm_sleep_ptr(&j721e_pcie_pm_ops), + }, +}; +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 new file mode 100644 index 000000000000..c0e1194a936b --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c @@ -0,0 +1,775 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Cadence +// Cadence PCIe endpoint controller driver. +// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + +#include <linux/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 +#define CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY 0x3 + +static u8 cdns_pcie_get_fn_from_vfn(struct cdns_pcie *pcie, u8 fn, u8 vfn) +{ + u32 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); + + return fn; +} + +static int cdns_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_header *hdr) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + 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; + } else if (vfn == 1) { + reg = cap + PCI_SRIOV_VF_DID; + cdns_pcie_ep_fn_writew(pcie, fn, reg, hdr->deviceid); + return 0; + } + + cdns_pcie_ep_fn_writew(pcie, fn, PCI_DEVICE_ID, hdr->deviceid); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_REVISION_ID, hdr->revid); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_CLASS_PROG, hdr->progif_code); + cdns_pcie_ep_fn_writew(pcie, fn, PCI_CLASS_DEVICE, + hdr->subclass_code | hdr->baseclass_code << 8); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_CACHE_LINE_SIZE, + hdr->cache_line_size); + cdns_pcie_ep_fn_writew(pcie, fn, PCI_SUBSYSTEM_ID, hdr->subsys_id); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_INTERRUPT_PIN, hdr->interrupt_pin); + + /* + * Vendor ID can only be modified from function 0, all other functions + * use the same vendor ID as function 0. + */ + if (fn == 0) { + /* Update the vendor IDs. */ + u32 id = CDNS_PCIE_LM_ID_VENDOR(hdr->vendorid) | + CDNS_PCIE_LM_ID_SUBSYS(hdr->subsys_vendor_id); + + cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id); + } + + return 0; +} + +static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie_epf *epf = &ep->epf[fn]; + struct cdns_pcie *pcie = &ep->pcie; + dma_addr_t bar_phys = epf_bar->phys_addr; + enum pci_barno bar = epf_bar->barno; + int flags = epf_bar->flags; + u32 addr0, addr1, reg, cfg, b, aperture, ctrl; + u64 sz; + + /* BAR size is 2^(aperture + 7) */ + sz = max_t(size_t, epf_bar->size, CDNS_PCIE_EP_MIN_APERTURE); + /* + * roundup_pow_of_two() returns an unsigned long, which is not suited + * for 64bit values. + */ + sz = 1ULL << fls64(sz - 1); + aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */ + + if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) { + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_IO_32BITS; + } else { + bool is_prefetch = !!(flags & PCI_BASE_ADDRESS_MEM_PREFETCH); + bool is_64bits = !!(flags & PCI_BASE_ADDRESS_MEM_TYPE_64); + + if (is_64bits && (bar & 1)) + return -EINVAL; + + if (is_64bits && is_prefetch) + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_64BITS; + else if (is_prefetch) + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_32BITS; + else if (is_64bits) + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_64BITS; + else + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_32BITS; + } + + addr0 = lower_32_bits(bar_phys); + addr1 = upper_32_bits(bar_phys); + + if (vfn == 1) + reg = CDNS_PCIE_LM_EP_VFUNC_BAR_CFG(bar, fn); + else + reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG(bar, fn); + b = (bar < BAR_4) ? bar : bar - BAR_4; + + if (vfn == 0 || vfn == 1) { + cfg = cdns_pcie_readl(pcie, reg); + cfg &= ~(CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | + CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); + cfg |= (CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE(b, aperture) | + CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl)); + cdns_pcie_writel(pcie, reg, cfg); + } + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar), + addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar), + addr1); + + if (vfn > 0) + epf = &epf->epf[vfn - 1]; + epf->epf_bar[bar] = epf_bar; + + return 0; +} + +static void cdns_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie_epf *epf = &ep->epf[fn]; + struct cdns_pcie *pcie = &ep->pcie; + enum pci_barno bar = epf_bar->barno; + u32 reg, cfg, b, ctrl; + + if (vfn == 1) + reg = CDNS_PCIE_LM_EP_VFUNC_BAR_CFG(bar, fn); + else + reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG(bar, fn); + b = (bar < BAR_4) ? bar : bar - BAR_4; + + if (vfn == 0 || vfn == 1) { + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED; + cfg = cdns_pcie_readl(pcie, reg); + cfg &= ~(CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | + CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); + cfg |= CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl); + cdns_pcie_writel(pcie, reg, cfg); + } + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar), 0); + + if (vfn > 0) + epf = &epf->epf[vfn - 1]; + epf->epf_bar[bar] = NULL; +} + +static int cdns_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u64 pci_addr, size_t size) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 r; + + r = find_first_zero_bit(&ep->ob_region_map, BITS_PER_LONG); + if (r >= ep->max_regions - 1) { + dev_err(&epc->dev, "no free outbound region\n"); + return -EINVAL; + } + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + cdns_pcie_set_outbound_region(pcie, 0, fn, r, false, addr, pci_addr, size); + + set_bit(r, &ep->ob_region_map); + ep->ob_addr[r] = addr; + + return 0; +} + +static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 r; + + for (r = 0; r < ep->max_regions - 1; r++) + if (ep->ob_addr[r] == addr) + break; + + if (r == ep->max_regions - 1) + return; + + cdns_pcie_reset_outbound_region(pcie, r); + + ep->ob_addr[r] = 0; + clear_bit(r, &ep->ob_region_map); +} + +static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 nr_irqs) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + 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); + + /* + * Set the Multiple Message Capable bitfield into the Message Control + * register. + */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + flags = (flags & ~PCI_MSI_FLAGS_QMASK) | (mmc << 1); + flags |= PCI_MSI_FLAGS_64BIT; + flags &= ~PCI_MSI_FLAGS_MASKBIT; + cdns_pcie_ep_fn_writew(pcie, fn, cap + PCI_MSI_FLAGS, flags); + + return 0; +} + +static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + 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. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + if (!(flags & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + /* + * Get the Multiple Message Enable bitfield from the Message Control + * register. + */ + mme = FIELD_GET(PCI_MSI_FLAGS_QSIZE, flags); + + 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 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; + val = cdns_pcie_ep_fn_readw(pcie, func_no, reg); + if (!(val & PCI_MSIX_FLAGS_ENABLE)) + return -EINVAL; + + val &= PCI_MSIX_FLAGS_QSIZE; + + return val + 1; +} + +static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, + 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 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 |= nr_irqs - 1; /* encoded as N-1 */ + cdns_pcie_ep_fn_writew(pcie, fn, reg, val); + + /* Set MSI-X BAR and offset */ + reg = cap + PCI_MSIX_TABLE; + val = offset | bir; + cdns_pcie_ep_fn_writel(pcie, fn, reg, val); + + /* Set PBA BAR and offset. BAR must match MSI-X BAR */ + reg = cap + PCI_MSIX_PBA; + val = (offset + (nr_irqs * PCI_MSIX_ENTRY_SIZE)) | bir; + cdns_pcie_ep_fn_writel(pcie, fn, reg, val); + + return 0; +} + +static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx, + bool is_asserted) +{ + struct cdns_pcie *pcie = &ep->pcie; + unsigned long flags; + u32 offset; + u16 status; + u8 msg_code; + + intx &= 3; + + /* Set the outbound region if needed. */ + if (unlikely(ep->irq_pci_addr != CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY || + ep->irq_pci_fn != fn)) { + /* First region was reserved for IRQ writes. */ + cdns_pcie_set_outbound_region_for_normal_msg(pcie, 0, fn, 0, + ep->irq_phys_addr); + ep->irq_pci_addr = CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY; + ep->irq_pci_fn = fn; + } + + if (is_asserted) { + ep->irq_pending |= BIT(intx); + msg_code = PCIE_MSG_CODE_ASSERT_INTA + intx; + } else { + ep->irq_pending &= ~BIT(intx); + msg_code = PCIE_MSG_CODE_DEASSERT_INTA + intx; + } + + spin_lock_irqsave(&ep->lock, flags); + status = cdns_pcie_ep_fn_readw(pcie, fn, PCI_STATUS); + if (((status & PCI_STATUS_INTERRUPT) != 0) ^ (ep->irq_pending != 0)) { + status ^= PCI_STATUS_INTERRUPT; + cdns_pcie_ep_fn_writew(pcie, fn, PCI_STATUS, status); + } + spin_unlock_irqrestore(&ep->lock, flags); + + offset = CDNS_PCIE_NORMAL_MSG_ROUTING(PCIE_MSG_TYPE_R_LOCAL) | + CDNS_PCIE_NORMAL_MSG_CODE(msg_code); + writel(0, ep->irq_cpu_addr + offset); +} + +static int cdns_pcie_ep_send_intx_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, + u8 intx) +{ + u16 cmd; + + cmd = cdns_pcie_ep_fn_readw(&ep->pcie, fn, PCI_COMMAND); + if (cmd & PCI_COMMAND_INTX_DISABLE) + return -EINVAL; + + cdns_pcie_ep_assert_intx(ep, fn, intx, true); + /* + * The mdelay() value was taken from dra7xx_pcie_raise_intx_irq() + */ + mdelay(1); + cdns_pcie_ep_assert_intx(ep, fn, intx, false); + return 0; +} + +static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, + u8 interrupt_num) +{ + struct cdns_pcie *pcie = &ep->pcie; + u16 flags, mme, data, data_mask; + 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. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + if (!(flags & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + /* Get the number of enabled MSIs */ + mme = FIELD_GET(PCI_MSI_FLAGS_QSIZE, flags); + msi_count = 1 << mme; + if (!interrupt_num || interrupt_num > msi_count) + return -EINVAL; + + /* Compute the data value to be written. */ + data_mask = msi_count - 1; + data = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_DATA_64); + data = (data & ~data_mask) | ((interrupt_num - 1) & data_mask); + + /* Get the PCI address where to write the data into. */ + pci_addr = cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_HI); + pci_addr <<= 32; + pci_addr |= cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_LO); + pci_addr &= GENMASK_ULL(63, 2); + + /* Set the outbound region if needed. */ + if (unlikely(ep->irq_pci_addr != (pci_addr & ~pci_addr_mask) || + ep->irq_pci_fn != fn)) { + /* First region was reserved for IRQ writes. */ + cdns_pcie_set_outbound_region(pcie, 0, fn, 0, + false, + ep->irq_phys_addr, + pci_addr & ~pci_addr_mask, + pci_addr_mask + 1); + ep->irq_pci_addr = (pci_addr & ~pci_addr_mask); + ep->irq_pci_fn = fn; + } + writel(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask)); + + return 0; +} + +static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u8 interrupt_num, + u32 entry_size, u32 *msi_data, + u32 *msi_addr_offset) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u64 pci_addr, pci_addr_mask = 0xff; + u16 flags, mme, data, data_mask; + 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. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + if (!(flags & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + /* Get the number of enabled MSIs */ + mme = FIELD_GET(PCI_MSI_FLAGS_QSIZE, flags); + msi_count = 1 << mme; + if (!interrupt_num || interrupt_num > msi_count) + return -EINVAL; + + /* Compute the data value to be written. */ + data_mask = msi_count - 1; + data = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_DATA_64); + data = data & ~data_mask; + + /* Get the PCI address where to write the data into. */ + pci_addr = cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_HI); + pci_addr <<= 32; + pci_addr |= cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_LO); + pci_addr &= GENMASK_ULL(63, 2); + + for (i = 0; i < interrupt_num; i++) { + ret = cdns_pcie_ep_map_addr(epc, fn, vfn, addr, + pci_addr & ~pci_addr_mask, + entry_size); + if (ret) + return ret; + addr = addr + entry_size; + } + + *msi_data = data; + *msi_addr_offset = pci_addr & pci_addr_mask; + + return 0; +} + +static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, + u16 interrupt_num) +{ + u32 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; + + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSIX); + epf = &ep->epf[fn]; + if (vfn > 0) + epf = &epf->epf[vfn - 1]; + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + + /* Check whether the MSI-X feature has been enabled by the PCI host. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSIX_FLAGS); + if (!(flags & PCI_MSIX_FLAGS_ENABLE)) + return -EINVAL; + + reg = cap + PCI_MSIX_TABLE; + tbl_offset = cdns_pcie_ep_fn_readl(pcie, fn, reg); + bir = FIELD_GET(PCI_MSIX_TABLE_BIR, tbl_offset); + tbl_offset &= PCI_MSIX_TABLE_OFFSET; + + msix_tbl = epf->epf_bar[bir]->addr + tbl_offset; + msg_addr = msix_tbl[(interrupt_num - 1)].msg_addr; + msg_data = msix_tbl[(interrupt_num - 1)].msg_data; + + /* Set the outbound region if needed. */ + if (ep->irq_pci_addr != (msg_addr & ~pci_addr_mask) || + ep->irq_pci_fn != fn) { + /* First region was reserved for IRQ writes. */ + cdns_pcie_set_outbound_region(pcie, 0, fn, 0, + false, + ep->irq_phys_addr, + msg_addr & ~pci_addr_mask, + pci_addr_mask + 1); + ep->irq_pci_addr = (msg_addr & ~pci_addr_mask); + ep->irq_pci_fn = fn; + } + writel(msg_data, ep->irq_cpu_addr + (msg_addr & pci_addr_mask)); + + return 0; +} + +static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, + unsigned int type, u16 interrupt_num) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + struct device *dev = pcie->dev; + + switch (type) { + case PCI_IRQ_INTX: + if (vfn > 0) { + dev_err(dev, "Cannot raise INTX interrupts for VF\n"); + return -EINVAL; + } + return cdns_pcie_ep_send_intx_irq(ep, fn, vfn, 0); + + case PCI_IRQ_MSI: + return cdns_pcie_ep_send_msi_irq(ep, fn, vfn, interrupt_num); + + case PCI_IRQ_MSIX: + return cdns_pcie_ep_send_msix_irq(ep, fn, vfn, interrupt_num); + + default: + break; + } + + return -EINVAL; +} + +static int cdns_pcie_ep_start(struct pci_epc *epc) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + struct device *dev = pcie->dev; + int max_epfs = sizeof(epc->function_num_map) * 8; + int ret, 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. + */ + cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, epc->function_num_map); + + /* + * Next function field in ARI_CAP_AND_CTR register for last function + * should be 0. Clear Next Function Number field for the last + * function used. + */ + last_fn = find_last_bit(&epc->function_num_map, BITS_PER_LONG); + reg = CDNS_PCIE_CORE_PF_I_ARI_CAP_AND_CTRL(last_fn); + value = cdns_pcie_readl(pcie, reg); + value &= ~CDNS_PCIE_ARI_CAP_NFN_MASK; + cdns_pcie_writel(pcie, reg, value); + + if (ep->quirk_disable_flr) { + for (epf = 0; epf < max_epfs; epf++) { + if (!(epc->function_num_map & BIT(epf))) + continue; + + value = cdns_pcie_ep_fn_readl(pcie, epf, + cap + PCI_EXP_DEVCAP); + value &= ~PCI_EXP_DEVCAP_FLR; + cdns_pcie_ep_fn_writel(pcie, epf, + cap + PCI_EXP_DEVCAP, value); + } + } + + ret = cdns_pcie_start_link(pcie); + if (ret) { + dev_err(dev, "Failed to start link\n"); + return ret; + } + + return 0; +} + +static const struct pci_epc_features cdns_pcie_epc_vf_features = { + .msi_capable = true, + .msix_capable = true, + .align = 65536, +}; + +static const struct pci_epc_features cdns_pcie_epc_features = { + .msi_capable = true, + .msix_capable = true, + .align = 256, +}; + +static const struct pci_epc_features* +cdns_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + if (!vfunc_no) + return &cdns_pcie_epc_features; + + return &cdns_pcie_epc_vf_features; +} + +static const struct pci_epc_ops cdns_pcie_epc_ops = { + .write_header = cdns_pcie_ep_write_header, + .set_bar = cdns_pcie_ep_set_bar, + .clear_bar = cdns_pcie_ep_clear_bar, + .map_addr = cdns_pcie_ep_map_addr, + .unmap_addr = cdns_pcie_ep_unmap_addr, + .set_msi = cdns_pcie_ep_set_msi, + .get_msi = cdns_pcie_ep_get_msi, + .set_msix = cdns_pcie_ep_set_msix, + .get_msix = cdns_pcie_ep_get_msix, + .raise_irq = cdns_pcie_ep_raise_irq, + .map_msi_irq = cdns_pcie_ep_map_msi_irq, + .start = cdns_pcie_ep_start, + .get_features = cdns_pcie_ep_get_features, +}; + +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) +{ + struct device *dev = ep->pcie.dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *np = dev->of_node; + struct cdns_pcie *pcie = &ep->pcie; + struct cdns_pcie_epf *epf; + struct resource *res; + struct pci_epc *epc; + int ret; + int i; + + pcie->is_rc = false; + + pcie->reg_base = devm_platform_ioremap_resource_byname(pdev, "reg"); + if (IS_ERR(pcie->reg_base)) { + dev_err(dev, "missing \"reg\"\n"); + return PTR_ERR(pcie->reg_base); + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mem"); + if (!res) { + dev_err(dev, "missing \"mem\"\n"); + return -EINVAL; + } + pcie->mem_res = res; + + ep->max_regions = CDNS_PCIE_MAX_OB; + of_property_read_u32(np, "cdns,max-outbound-regions", &ep->max_regions); + + ep->ob_addr = devm_kcalloc(dev, + ep->max_regions, sizeof(*ep->ob_addr), + GFP_KERNEL); + if (!ep->ob_addr) + return -ENOMEM; + + /* Disable all but function 0 (anyway BIT(0) is hardwired to 1). */ + cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, BIT(0)); + + epc = devm_pci_epc_create(dev, &cdns_pcie_epc_ops); + if (IS_ERR(epc)) { + dev_err(dev, "failed to create epc device\n"); + return PTR_ERR(epc); + } + + epc_set_drvdata(epc, ep); + + if (of_property_read_u8(np, "max-functions", &epc->max_functions) < 0) + epc->max_functions = 1; + + ep->epf = devm_kcalloc(dev, epc->max_functions, sizeof(*ep->epf), + GFP_KERNEL); + if (!ep->epf) + return -ENOMEM; + + epc->max_vfs = devm_kcalloc(dev, epc->max_functions, + sizeof(*epc->max_vfs), GFP_KERNEL); + if (!epc->max_vfs) + return -ENOMEM; + + ret = of_property_read_u8_array(np, "max-virtual-functions", + epc->max_vfs, epc->max_functions); + if (ret == 0) { + for (i = 0; i < epc->max_functions; i++) { + epf = &ep->epf[i]; + if (epc->max_vfs[i] == 0) + continue; + epf->epf = devm_kcalloc(dev, epc->max_vfs[i], + sizeof(*ep->epf), GFP_KERNEL); + if (!epf->epf) + return -ENOMEM; + } + } + + ret = pci_epc_mem_init(epc, pcie->mem_res->start, + resource_size(pcie->mem_res), PAGE_SIZE); + if (ret < 0) { + dev_err(dev, "failed to initialize the memory space\n"); + return ret; + } + + ep->irq_cpu_addr = pci_epc_mem_alloc_addr(epc, &ep->irq_phys_addr, + SZ_128K); + if (!ep->irq_cpu_addr) { + dev_err(dev, "failed to reserve memory space for MSI\n"); + ret = -ENOMEM; + goto free_epc_mem; + } + ep->irq_pci_addr = CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE; + /* Reserve region 0 for IRQs */ + set_bit(0, &ep->ob_region_map); + + if (ep->quirk_detect_quiet_flag) + cdns_pcie_detect_quiet_min_delay_set(&ep->pcie); + + spin_lock_init(&ep->lock); + + pci_epc_init_notify(epc); + + return 0; + + free_epc_mem: + pci_epc_mem_exit(epc); + + return ret; +} +EXPORT_SYMBOL_GPL(cdns_pcie_ep_setup); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe endpoint controller driver"); +MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@free-electrons.com>"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-host-common.c b/drivers/pci/controller/cadence/pcie-cadence-host-common.c new file mode 100644 index 000000000000..15415d7f35ee --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host-common.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence PCIe host controller library. + * + * Copyright (c) 2017 Cadence + * Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + */ +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/list_sort.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/platform_device.h> + +#include "pcie-cadence.h" +#include "pcie-cadence-host-common.h" + +#define LINK_RETRAIN_TIMEOUT HZ + +u64 bar_max_size[] = { + [RP_BAR0] = _ULL(128 * SZ_2G), + [RP_BAR1] = SZ_2G, + [RP_NO_BAR] = _BITULL(63), +}; +EXPORT_SYMBOL_GPL(bar_max_size); + +int cdns_pcie_host_training_complete(struct cdns_pcie *pcie) +{ + u32 pcie_cap_off = CDNS_PCIE_RP_CAP_OFFSET; + unsigned long end_jiffies; + u16 lnk_stat; + + /* Wait for link training to complete. Exit after timeout. */ + end_jiffies = jiffies + LINK_RETRAIN_TIMEOUT; + do { + lnk_stat = cdns_pcie_rp_readw(pcie, pcie_cap_off + PCI_EXP_LNKSTA); + if (!(lnk_stat & PCI_EXP_LNKSTA_LT)) + break; + usleep_range(0, 1000); + } while (time_before(jiffies, end_jiffies)); + + if (!(lnk_stat & PCI_EXP_LNKSTA_LT)) + return 0; + + return -ETIMEDOUT; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_training_complete); + +int cdns_pcie_host_wait_for_link(struct cdns_pcie *pcie, + cdns_pcie_linkup_func pcie_link_up) +{ + struct device *dev = pcie->dev; + int retries; + + /* Check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (pcie_link_up(pcie)) { + dev_info(dev, "Link up\n"); + return 0; + } + usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + } + + return -ETIMEDOUT; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_wait_for_link); + +int cdns_pcie_retrain(struct cdns_pcie *pcie, + cdns_pcie_linkup_func pcie_link_up) +{ + u32 lnk_cap_sls, pcie_cap_off = CDNS_PCIE_RP_CAP_OFFSET; + u16 lnk_stat, lnk_ctl; + int ret = 0; + + /* + * Set retrain bit if current speed is 2.5 GB/s, + * but the PCIe root port support is > 2.5 GB/s. + */ + + lnk_cap_sls = cdns_pcie_readl(pcie, (CDNS_PCIE_RP_BASE + pcie_cap_off + + PCI_EXP_LNKCAP)); + if ((lnk_cap_sls & PCI_EXP_LNKCAP_SLS) <= PCI_EXP_LNKCAP_SLS_2_5GB) + return ret; + + lnk_stat = cdns_pcie_rp_readw(pcie, pcie_cap_off + PCI_EXP_LNKSTA); + if ((lnk_stat & PCI_EXP_LNKSTA_CLS) == PCI_EXP_LNKSTA_CLS_2_5GB) { + lnk_ctl = cdns_pcie_rp_readw(pcie, + pcie_cap_off + PCI_EXP_LNKCTL); + lnk_ctl |= PCI_EXP_LNKCTL_RL; + cdns_pcie_rp_writew(pcie, pcie_cap_off + PCI_EXP_LNKCTL, + lnk_ctl); + + ret = cdns_pcie_host_training_complete(pcie); + if (ret) + return ret; + + ret = cdns_pcie_host_wait_for_link(pcie, pcie_link_up); + } + return ret; +} +EXPORT_SYMBOL_GPL(cdns_pcie_retrain); + +int cdns_pcie_host_start_link(struct cdns_pcie_rc *rc, + cdns_pcie_linkup_func pcie_link_up) +{ + struct cdns_pcie *pcie = &rc->pcie; + int ret; + + ret = cdns_pcie_host_wait_for_link(pcie, pcie_link_up); + + /* + * Retrain link for Gen2 training defect + * if quirk flag is set. + */ + if (!ret && rc->quirk_retrain_flag) + ret = cdns_pcie_retrain(pcie, pcie_link_up); + + return ret; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_start_link); + +enum cdns_pcie_rp_bar +cdns_pcie_host_find_min_bar(struct cdns_pcie_rc *rc, u64 size) +{ + enum cdns_pcie_rp_bar bar, sel_bar; + + sel_bar = RP_BAR_UNDEFINED; + for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) { + if (!rc->avail_ib_bar[bar]) + continue; + + if (size <= bar_max_size[bar]) { + if (sel_bar == RP_BAR_UNDEFINED) { + sel_bar = bar; + continue; + } + + if (bar_max_size[bar] < bar_max_size[sel_bar]) + sel_bar = bar; + } + } + + return sel_bar; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_find_min_bar); + +enum cdns_pcie_rp_bar +cdns_pcie_host_find_max_bar(struct cdns_pcie_rc *rc, u64 size) +{ + enum cdns_pcie_rp_bar bar, sel_bar; + + sel_bar = RP_BAR_UNDEFINED; + for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) { + if (!rc->avail_ib_bar[bar]) + continue; + + if (size >= bar_max_size[bar]) { + if (sel_bar == RP_BAR_UNDEFINED) { + sel_bar = bar; + continue; + } + + if (bar_max_size[bar] > bar_max_size[sel_bar]) + sel_bar = bar; + } + } + + return sel_bar; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_find_max_bar); + +int cdns_pcie_host_dma_ranges_cmp(void *priv, const struct list_head *a, + const struct list_head *b) +{ + struct resource_entry *entry1, *entry2; + + entry1 = container_of(a, struct resource_entry, node); + entry2 = container_of(b, struct resource_entry, node); + + return resource_size(entry2->res) - resource_size(entry1->res); +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_dma_ranges_cmp); + +int cdns_pcie_host_bar_config(struct cdns_pcie_rc *rc, + struct resource_entry *entry, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = pcie->dev; + u64 cpu_addr, size, winsize; + enum cdns_pcie_rp_bar bar; + unsigned long flags; + int ret; + + cpu_addr = entry->res->start; + flags = entry->res->flags; + size = resource_size(entry->res); + + while (size > 0) { + /* + * Try to find a minimum BAR whose size is greater than + * or equal to the remaining resource_entry size. This will + * fail if the size of each of the available BARs is less than + * the remaining resource_entry size. + * + * If a minimum BAR is found, IB ATU will be configured and + * exited. + */ + bar = cdns_pcie_host_find_min_bar(rc, size); + if (bar != RP_BAR_UNDEFINED) { + ret = pci_host_ib_config(rc, bar, cpu_addr, size, flags); + if (ret) + dev_err(dev, "IB BAR: %d config failed\n", bar); + return ret; + } + + /* + * If the control reaches here, it would mean the remaining + * resource_entry size cannot be fitted in a single BAR. So we + * find a maximum BAR whose size is less than or equal to the + * remaining resource_entry size and split the resource entry + * so that part of resource entry is fitted inside the maximum + * BAR. The remaining size would be fitted during the next + * iteration of the loop. + * + * If a maximum BAR is not found, there is no way we can fit + * this resource_entry, so we error out. + */ + bar = cdns_pcie_host_find_max_bar(rc, size); + if (bar == RP_BAR_UNDEFINED) { + dev_err(dev, "No free BAR to map cpu_addr %llx\n", + cpu_addr); + return -EINVAL; + } + + winsize = bar_max_size[bar]; + ret = pci_host_ib_config(rc, bar, cpu_addr, winsize, flags); + if (ret) { + dev_err(dev, "IB BAR: %d config failed\n", bar); + return ret; + } + + size -= winsize; + cpu_addr += winsize; + } + + return 0; +} + +int cdns_pcie_host_map_dma_ranges(struct cdns_pcie_rc *rc, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = pcie->dev; + struct device_node *np = dev->of_node; + struct pci_host_bridge *bridge; + struct resource_entry *entry; + u32 no_bar_nbits = 32; + int err; + + bridge = pci_host_bridge_from_priv(rc); + if (!bridge) + return -ENOMEM; + + if (list_empty(&bridge->dma_ranges)) { + of_property_read_u32(np, "cdns,no-bar-match-nbits", + &no_bar_nbits); + err = pci_host_ib_config(rc, RP_NO_BAR, 0x0, (u64)1 << no_bar_nbits, 0); + if (err) + dev_err(dev, "IB BAR: %d config failed\n", RP_NO_BAR); + return err; + } + + list_sort(NULL, &bridge->dma_ranges, cdns_pcie_host_dma_ranges_cmp); + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + err = cdns_pcie_host_bar_config(rc, entry, pci_host_ib_config); + if (err) { + dev_err(dev, "Fail to configure IB using dma-ranges\n"); + return err; + } + } + + return 0; +} + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe host controller driver"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-host-common.h b/drivers/pci/controller/cadence/pcie-cadence-host-common.h new file mode 100644 index 000000000000..fe7d4202a8b6 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host-common.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Cadence PCIe Host controller driver. + * + * Copyright (c) 2017 Cadence + * Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + */ +#ifndef _PCIE_CADENCE_HOST_COMMON_H +#define _PCIE_CADENCE_HOST_COMMON_H + +#include <linux/kernel.h> +#include <linux/pci.h> + +extern u64 bar_max_size[]; + +typedef int (*cdns_pcie_host_bar_ib_cfg)(struct cdns_pcie_rc *, + enum cdns_pcie_rp_bar, + u64, + u64, + unsigned long); +typedef bool (*cdns_pcie_linkup_func)(struct cdns_pcie *); + +int cdns_pcie_host_training_complete(struct cdns_pcie *pcie); +int cdns_pcie_host_wait_for_link(struct cdns_pcie *pcie, + cdns_pcie_linkup_func pcie_link_up); +int cdns_pcie_retrain(struct cdns_pcie *pcie, cdns_pcie_linkup_func pcie_linkup_func); +int cdns_pcie_host_start_link(struct cdns_pcie_rc *rc, + cdns_pcie_linkup_func pcie_link_up); +enum cdns_pcie_rp_bar +cdns_pcie_host_find_min_bar(struct cdns_pcie_rc *rc, u64 size); +enum cdns_pcie_rp_bar +cdns_pcie_host_find_max_bar(struct cdns_pcie_rc *rc, u64 size); +int cdns_pcie_host_dma_ranges_cmp(void *priv, const struct list_head *a, + const struct list_head *b); +int cdns_pcie_host_bar_ib_config(struct cdns_pcie_rc *rc, + enum cdns_pcie_rp_bar bar, + u64 cpu_addr, + u64 size, + unsigned long flags); +int cdns_pcie_host_bar_config(struct cdns_pcie_rc *rc, + struct resource_entry *entry, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config); +int cdns_pcie_host_map_dma_ranges(struct cdns_pcie_rc *rc, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config); + +#endif /* _PCIE_CADENCE_HOST_COMMON_H */ diff --git a/drivers/pci/controller/cadence/pcie-cadence-host-hpa.c b/drivers/pci/controller/cadence/pcie-cadence-host-hpa.c new file mode 100644 index 000000000000..0f540bed58e8 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host-hpa.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence PCIe host controller driver. + * + * Copyright (c) 2024, Cadence Design Systems + * Author: Manikandan K Pillai <mpillai@cadence.com> + */ +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/list_sort.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_irq.h> +#include <linux/platform_device.h> + +#include "pcie-cadence.h" +#include "pcie-cadence-host-common.h" + +static u8 bar_aperture_mask[] = { + [RP_BAR0] = 0x3F, + [RP_BAR1] = 0x3F, +}; + +void __iomem *cdns_pci_hpa_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct pci_host_bridge *bridge = pci_find_host_bridge(bus); + struct cdns_pcie_rc *rc = pci_host_bridge_priv(bridge); + struct cdns_pcie *pcie = &rc->pcie; + unsigned int busn = bus->number; + u32 addr0, desc0, desc1, ctrl0; + u32 regval; + + if (pci_is_root_bus(bus)) { + /* + * Only the root port (devfn == 0) is connected to this bus. + * All other PCI devices are behind some bridge hence on another + * bus. + */ + if (devfn) + return NULL; + + return pcie->reg_base + (where & 0xfff); + } + + /* Clear AXI link-down status */ + regval = cdns_pcie_hpa_readl(pcie, REG_BANK_AXI_SLAVE, CDNS_PCIE_HPA_AT_LINKDOWN); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, CDNS_PCIE_HPA_AT_LINKDOWN, + (regval & ~GENMASK(0, 0))); + + /* Update Output registers for AXI region 0 */ + addr0 = CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_NBITS(12) | + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) | + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_BUS(busn); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0(0), addr0); + + desc1 = cdns_pcie_hpa_readl(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(0)); + desc1 &= ~CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN_MASK; + desc1 |= CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN(0); + ctrl0 = CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_BUS | + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_DEV_FN; + + if (busn == bridge->busnr + 1) + desc0 = CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_CONF_TYPE0; + else + desc0 = CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_CONF_TYPE1; + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC0(0), desc0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(0), desc1); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0(0), ctrl0); + + return rc->cfg_base + (where & 0xfff); +} + +static struct pci_ops cdns_pcie_hpa_host_ops = { + .map_bus = cdns_pci_hpa_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static void cdns_pcie_hpa_host_enable_ptm_response(struct cdns_pcie *pcie) +{ + u32 val; + + val = cdns_pcie_hpa_readl(pcie, REG_BANK_IP_REG, CDNS_PCIE_HPA_LM_PTM_CTRL); + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_REG, CDNS_PCIE_HPA_LM_PTM_CTRL, + val | CDNS_PCIE_HPA_LM_PTM_CTRL_PTMRSEN); +} + +static int cdns_pcie_hpa_host_bar_ib_config(struct cdns_pcie_rc *rc, + enum cdns_pcie_rp_bar bar, + u64 cpu_addr, u64 size, + unsigned long flags) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 addr0, addr1, aperture, value; + + if (!rc->avail_ib_bar[bar]) + return -ENODEV; + + rc->avail_ib_bar[bar] = false; + + aperture = ilog2(size); + if (bar == RP_NO_BAR) { + addr0 = CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0_NBITS(aperture) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + } else { + addr0 = lower_32_bits(cpu_addr); + addr1 = upper_32_bits(cpu_addr); + } + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_MASTER, + CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0(bar), addr0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_MASTER, + CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR1(bar), addr1); + + if (bar == RP_NO_BAR) + bar = (enum cdns_pcie_rp_bar)BAR_0; + + value = cdns_pcie_hpa_readl(pcie, REG_BANK_IP_CFG_CTRL_REG, CDNS_PCIE_HPA_LM_RC_BAR_CFG); + value &= ~(HPA_LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar) | + HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar) | + HPA_LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar) | + HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar) | + HPA_LM_RC_BAR_CFG_APERTURE(bar, bar_aperture_mask[bar] + 7)); + if (size + cpu_addr >= SZ_4G) { + value |= HPA_LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar); + if ((flags & IORESOURCE_PREFETCH)) + value |= HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar); + } else { + value |= HPA_LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar); + if ((flags & IORESOURCE_PREFETCH)) + value |= HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar); + } + + value |= HPA_LM_RC_BAR_CFG_APERTURE(bar, aperture); + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_CFG_CTRL_REG, CDNS_PCIE_HPA_LM_RC_BAR_CFG, value); + + return 0; +} + +static int cdns_pcie_hpa_host_init_root_port(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 value, ctrl; + + /* + * Set the root port BAR configuration register: + * - disable both BAR0 and BAR1 + * - enable Prefetchable Memory Base and Limit registers in type 1 + * config space (64 bits) + * - enable IO Base and Limit registers in type 1 config + * space (32 bits) + */ + + ctrl = CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_DISABLED; + value = CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_CTRL(ctrl) | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_CTRL(ctrl) | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_IO_ENABLE | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_IO_32BITS; + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_CFG_CTRL_REG, + CDNS_PCIE_HPA_LM_RC_BAR_CFG, value); + + if (rc->vendor_id != 0xffff) + cdns_pcie_hpa_rp_writew(pcie, PCI_VENDOR_ID, rc->vendor_id); + + if (rc->device_id != 0xffff) + cdns_pcie_hpa_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id); + + cdns_pcie_hpa_rp_writeb(pcie, PCI_CLASS_REVISION, 0); + cdns_pcie_hpa_rp_writeb(pcie, PCI_CLASS_PROG, 0); + cdns_pcie_hpa_rp_writew(pcie, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_PCI); + + /* Enable bus mastering */ + value = cdns_pcie_hpa_readl(pcie, REG_BANK_RP, PCI_COMMAND); + value |= (PCI_COMMAND_MEMORY | PCI_COMMAND_IO | PCI_COMMAND_MASTER); + cdns_pcie_hpa_writel(pcie, REG_BANK_RP, PCI_COMMAND, value); + return 0; +} + +static void cdns_pcie_hpa_create_region_for_cfg(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rc); + struct resource *cfg_res = rc->cfg_res; + struct resource_entry *entry; + u64 cpu_addr = cfg_res->start; + u32 addr0, addr1, desc1; + int busnr = 0; + + entry = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (entry) + busnr = entry->res->start; + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_TAG_MANAGEMENT, 0x01000000); + /* + * Reserve region 0 for PCI configure space accesses: + * OB_REGION_PCI_ADDR0 and OB_REGION_DESC0 are updated dynamically by + * cdns_pci_map_bus(), other region registers are set here once for all + */ + desc1 = CDNS_PCIE_HPA_AT_OB_REGION_DESC1_BUS(busnr); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR1(0), 0x0); + /* Type-1 CFG */ + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC0(0), 0x05000000); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(0), desc1); + + addr0 = CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0_NBITS(12) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0(0), addr0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR1(0), addr1); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0(0), 0x06000000); +} + +static int cdns_pcie_hpa_host_init_address_translation(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rc); + struct resource_entry *entry; + int r = 0, busnr = 0; + + if (!rc->ecam_supported) + cdns_pcie_hpa_create_region_for_cfg(rc); + + entry = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (entry) + busnr = entry->res->start; + + r++; + if (pcie->msg_res) { + cdns_pcie_hpa_set_outbound_region_for_normal_msg(pcie, busnr, 0, r, + pcie->msg_res->start); + + r++; + } + resource_list_for_each_entry(entry, &bridge->windows) { + struct resource *res = entry->res; + u64 pci_addr = res->start - entry->offset; + + if (resource_type(res) == IORESOURCE_IO) + cdns_pcie_hpa_set_outbound_region(pcie, busnr, 0, r, + true, + pci_pio_to_address(res->start), + pci_addr, + resource_size(res)); + else + cdns_pcie_hpa_set_outbound_region(pcie, busnr, 0, r, + false, + res->start, + pci_addr, + resource_size(res)); + + r++; + } + + if (rc->no_inbound_map) + return 0; + else + return cdns_pcie_host_map_dma_ranges(rc, cdns_pcie_hpa_host_bar_ib_config); +} + +static int cdns_pcie_hpa_host_init(struct cdns_pcie_rc *rc) +{ + int err; + + err = cdns_pcie_hpa_host_init_root_port(rc); + if (err) + return err; + + return cdns_pcie_hpa_host_init_address_translation(rc); +} + +int cdns_pcie_hpa_host_link_setup(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = rc->pcie.dev; + int ret; + + if (rc->quirk_detect_quiet_flag) + cdns_pcie_hpa_detect_quiet_min_delay_set(&rc->pcie); + + cdns_pcie_hpa_host_enable_ptm_response(pcie); + + ret = cdns_pcie_start_link(pcie); + if (ret) { + dev_err(dev, "Failed to start link\n"); + return ret; + } + + ret = cdns_pcie_host_wait_for_link(pcie, cdns_pcie_hpa_link_up); + if (ret) + dev_dbg(dev, "PCIe link never came up\n"); + + return ret; +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_host_link_setup); + +int cdns_pcie_hpa_host_setup(struct cdns_pcie_rc *rc) +{ + struct device *dev = rc->pcie.dev; + struct platform_device *pdev = to_platform_device(dev); + struct pci_host_bridge *bridge; + enum cdns_pcie_rp_bar bar; + struct cdns_pcie *pcie; + struct resource *res; + int ret; + + bridge = pci_host_bridge_from_priv(rc); + if (!bridge) + return -ENOMEM; + + pcie = &rc->pcie; + pcie->is_rc = true; + + if (!pcie->reg_base) { + pcie->reg_base = devm_platform_ioremap_resource_byname(pdev, "reg"); + if (IS_ERR(pcie->reg_base)) { + dev_err(dev, "missing \"reg\"\n"); + return PTR_ERR(pcie->reg_base); + } + } + + /* ECAM config space is remapped at glue layer */ + if (!rc->cfg_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + rc->cfg_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(rc->cfg_base)) + return PTR_ERR(rc->cfg_base); + rc->cfg_res = res; + } + + /* Put EROM Bar aperture to 0 */ + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_CFG_CTRL_REG, CDNS_PCIE_EROM, 0x0); + + ret = cdns_pcie_hpa_host_link_setup(rc); + if (ret) + return ret; + + for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) + rc->avail_ib_bar[bar] = true; + + ret = cdns_pcie_hpa_host_init(rc); + if (ret) + return ret; + + if (!bridge->ops) + bridge->ops = &cdns_pcie_hpa_host_ops; + + return pci_host_probe(bridge); +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_host_setup); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe host controller driver"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c new file mode 100644 index 000000000000..db3154c1eccb --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host.c @@ -0,0 +1,425 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Cadence +// Cadence PCIe host controller driver. +// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/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" +#include "pcie-cadence-host-common.h" + +static u8 bar_aperture_mask[] = { + [RP_BAR0] = 0x1F, + [RP_BAR1] = 0xF, +}; + +void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct pci_host_bridge *bridge = pci_find_host_bridge(bus); + struct cdns_pcie_rc *rc = pci_host_bridge_priv(bridge); + struct cdns_pcie *pcie = &rc->pcie; + unsigned int busn = bus->number; + u32 addr0, desc0; + + if (pci_is_root_bus(bus)) { + /* + * Only the root port (devfn == 0) is connected to this bus. + * All other PCI devices are behind some bridge hence on another + * bus. + */ + if (devfn) + return NULL; + + return pcie->reg_base + (where & 0xfff); + } + /* Check that the link is up */ + if (!(cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE) & 0x1)) + return NULL; + /* Clear AXI link-down status */ + cdns_pcie_writel(pcie, CDNS_PCIE_AT_LINKDOWN, 0x0); + + /* Update Output registers for AXI region 0. */ + addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(12) | + CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) | + CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_BUS(busn); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR0(0), addr0); + + /* Configuration Type 0 or Type 1 access. */ + desc0 = CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID | + CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(0); + /* + * The bus number was already set once for all in desc1 by + * cdns_pcie_host_init_address_translation(). + */ + if (busn == bridge->busnr + 1) + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE0; + else + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE1; + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC0(0), desc0); + + return rc->cfg_base + (where & 0xfff); +} +EXPORT_SYMBOL_GPL(cdns_pci_map_bus); + +static struct pci_ops cdns_pcie_host_ops = { + .map_bus = cdns_pci_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static void cdns_pcie_host_disable_ptm_response(struct cdns_pcie *pcie) +{ + u32 val; + + val = cdns_pcie_readl(pcie, CDNS_PCIE_LM_PTM_CTRL); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_PTM_CTRL, val & ~CDNS_PCIE_LM_TPM_CTRL_PTMRSEN); +} + +static void cdns_pcie_host_enable_ptm_response(struct cdns_pcie *pcie) +{ + u32 val; + + val = cdns_pcie_readl(pcie, CDNS_PCIE_LM_PTM_CTRL); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_PTM_CTRL, val | CDNS_PCIE_LM_TPM_CTRL_PTMRSEN); +} + +static void cdns_pcie_host_deinit_root_port(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 value, ctrl; + + 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) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 value, ctrl; + u32 id; + + /* + * Set the root complex BAR configuration register: + * - disable both BAR0 and BAR1. + * - enable Prefetchable Memory Base and Limit registers in type 1 + * config space (64 bits). + * - enable IO Base and Limit registers in type 1 config + * space (32 bits). + */ + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED; + value = CDNS_PCIE_LM_RC_BAR_CFG_BAR0_CTRL(ctrl) | + CDNS_PCIE_LM_RC_BAR_CFG_BAR1_CTRL(ctrl) | + CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE | + CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS | + CDNS_PCIE_LM_RC_BAR_CFG_IO_ENABLE | + CDNS_PCIE_LM_RC_BAR_CFG_IO_32BITS; + cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); + + /* Set root port configuration space */ + if (rc->vendor_id != 0xffff) { + id = CDNS_PCIE_LM_ID_VENDOR(rc->vendor_id) | + CDNS_PCIE_LM_ID_SUBSYS(rc->vendor_id); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id); + } + + if (rc->device_id != 0xffff) + cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id); + + cdns_pcie_rp_writeb(pcie, PCI_CLASS_REVISION, 0); + cdns_pcie_rp_writeb(pcie, PCI_CLASS_PROG, 0); + cdns_pcie_rp_writew(pcie, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_PCI); + + return 0; +} + +int cdns_pcie_host_bar_ib_config(struct cdns_pcie_rc *rc, + enum cdns_pcie_rp_bar bar, + u64 cpu_addr, + u64 size, + unsigned long flags) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 addr0, addr1, aperture, value; + + if (!rc->avail_ib_bar[bar]) + return -EBUSY; + + rc->avail_ib_bar[bar] = false; + + aperture = ilog2(size); + addr0 = CDNS_PCIE_AT_IB_RP_BAR_ADDR0_NBITS(aperture) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR0(bar), addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar), addr1); + + if (bar == RP_NO_BAR) + return 0; + + value = cdns_pcie_readl(pcie, CDNS_PCIE_LM_RC_BAR_CFG); + value &= ~(LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar) | + LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar) | + LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar) | + LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar) | + LM_RC_BAR_CFG_APERTURE(bar, bar_aperture_mask[bar] + 2)); + if (size + cpu_addr >= SZ_4G) { + if (!(flags & IORESOURCE_PREFETCH)) + value |= LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar); + value |= LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar); + } else { + if (!(flags & IORESOURCE_PREFETCH)) + value |= LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar); + value |= LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar); + } + + value |= LM_RC_BAR_CFG_APERTURE(bar, aperture); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); + + return 0; +} + +static void cdns_pcie_host_unmap_dma_ranges(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + enum cdns_pcie_rp_bar bar; + u32 value; + + /* 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]) + continue; + + 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); + + if (bar == RP_NO_BAR) + continue; + + 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); + } +} + +static void cdns_pcie_host_deinit_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; + + cdns_pcie_host_unmap_dma_ranges(rc); + + /* + * Reset outbound region 0 which was reserved for configuration space + * accesses. + */ + cdns_pcie_reset_outbound_region(pcie, 0); + + /* Reset rest of the outbound regions */ + r = 1; + resource_list_for_each_entry(entry, &bridge->windows) { + cdns_pcie_reset_outbound_region(pcie, r); + r++; + } +} + +static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rc); + struct resource *cfg_res = rc->cfg_res; + struct resource_entry *entry; + u64 cpu_addr = cfg_res->start; + u32 addr0, addr1, desc1; + int r, busnr = 0; + + entry = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (entry) + busnr = entry->res->start; + + /* + * Reserve region 0 for PCI configure space accesses: + * OB_REGION_PCI_ADDR0 and OB_REGION_DESC0 are updated dynamically by + * cdns_pci_map_bus(), other region registers are set here once for all. + */ + addr1 = 0; /* Should be programmed to zero. */ + desc1 = CDNS_PCIE_AT_OB_REGION_DESC1_BUS(busnr); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR1(0), addr1); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC1(0), desc1); + + if (pcie->ops && pcie->ops->cpu_addr_fixup) + cpu_addr = pcie->ops->cpu_addr_fixup(pcie, cpu_addr); + + addr0 = CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS(12) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(0), addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(0), addr1); + + r = 1; + resource_list_for_each_entry(entry, &bridge->windows) { + struct resource *res = entry->res; + u64 pci_addr = res->start - entry->offset; + + if (resource_type(res) == IORESOURCE_IO) + cdns_pcie_set_outbound_region(pcie, busnr, 0, r, + true, + pci_pio_to_address(res->start), + pci_addr, + resource_size(res)); + else + cdns_pcie_set_outbound_region(pcie, busnr, 0, r, + false, + res->start, + pci_addr, + resource_size(res)); + + r++; + } + + return cdns_pcie_host_map_dma_ranges(rc, 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) +{ + int err; + + err = cdns_pcie_host_init_root_port(rc); + if (err) + return err; + + 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) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = rc->pcie.dev; + int ret; + + if (rc->quirk_detect_quiet_flag) + cdns_pcie_detect_quiet_min_delay_set(&rc->pcie); + + cdns_pcie_host_enable_ptm_response(pcie); + + ret = cdns_pcie_start_link(pcie); + if (ret) { + dev_err(dev, "Failed to start link\n"); + return ret; + } + + ret = cdns_pcie_host_start_link(rc, 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) +{ + struct device *dev = rc->pcie.dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *np = dev->of_node; + struct pci_host_bridge *bridge; + enum cdns_pcie_rp_bar bar; + struct cdns_pcie *pcie; + struct resource *res; + int ret; + + bridge = pci_host_bridge_from_priv(rc); + if (!bridge) + return -ENOMEM; + + pcie = &rc->pcie; + pcie->is_rc = true; + + rc->vendor_id = 0xffff; + of_property_read_u32(np, "vendor-id", &rc->vendor_id); + + rc->device_id = 0xffff; + of_property_read_u32(np, "device-id", &rc->device_id); + + pcie->reg_base = devm_platform_ioremap_resource_byname(pdev, "reg"); + if (IS_ERR(pcie->reg_base)) { + dev_err(dev, "missing \"reg\"\n"); + return PTR_ERR(pcie->reg_base); + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + rc->cfg_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(rc->cfg_base)) + return PTR_ERR(rc->cfg_base); + rc->cfg_res = res; + + ret = cdns_pcie_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_host_init(rc); + if (ret) + return ret; + + if (!bridge->ops) + bridge->ops = &cdns_pcie_host_ops; + + 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/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence-lga-regs.h index ae6bf2a2b3d3..857b2140c5d2 100644 --- a/drivers/pci/controller/pcie-cadence.h +++ b/drivers/pci/controller/cadence/pcie-cadence-lga-regs.h @@ -1,18 +1,21 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2017 Cadence -// Cadence PCIe controller driver. -// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> +/* 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 -#ifndef _PCIE_CADENCE_H -#define _PCIE_CADENCE_H +#include <linux/bitfield.h> -#include <linux/kernel.h> -#include <linux/pci.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 - */ +/* Local Management Registers */ #define CDNS_PCIE_LM_BASE 0x00100000 /* Vendor ID Register */ @@ -26,25 +29,33 @@ #define CDNS_PCIE_LM_ID_SUBSYS(sub) \ (((sub) << CDNS_PCIE_LM_ID_SUBSYS_SHIFT) & CDNS_PCIE_LM_ID_SUBSYS_MASK) -/* Root Port Requestor ID Register */ -#define CDNS_PCIE_LM_RP_RID (CDNS_PCIE_LM_BASE + 0x0228) +/* 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 (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) \ @@ -55,7 +66,7 @@ (((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) +#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) @@ -87,6 +98,24 @@ #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) @@ -94,21 +123,24 @@ #define CDNS_PCIE_EP_FUNC_BASE(fn) (((fn) << 12) & GENMASK(19, 12)) #define CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET 0x90 +#define CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET 0xB0 +#define CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET 0xC0 +#define CDNS_PCIE_EP_FUNC_SRIOV_CAP_OFFSET 0x200 -/* - * Root Port Registers (PCI configuration space for the root port function) - */ -#define CDNS_PCIE_RP_BASE 0x00200000 +/* 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 - */ +/* 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) + (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) @@ -121,18 +153,18 @@ /* 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) + (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) + (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 +#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) @@ -141,21 +173,21 @@ /* Region r Outbound PCIe Descriptor Register 1 */ #define CDNS_PCIE_AT_OB_REGION_DESC1(r) \ - (CDNS_PCIE_AT_BASE + 0x000c + ((r) & 0x1f) * 0x0020) + (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) + (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) + (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) \ @@ -169,11 +201,16 @@ /* AXI link down register */ #define CDNS_PCIE_AT_LINKDOWN (CDNS_PCIE_AT_BASE + 0x0824) -enum cdns_pcie_rp_bar { - RP_BAR0, - RP_BAR1, - RP_NO_BAR -}; +/* 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) \ @@ -188,135 +225,6 @@ enum cdns_pcie_rp_bar { #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) - -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 - 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 - * @is_rc: tell whether the PCIe controller mode is Root Complex or Endpoint. - * @bus: In Root Complex mode, the bus number - */ -struct cdns_pcie { - void __iomem *reg_base; - struct resource *mem_res; - bool is_rc; - u8 bus; - int phy_count; - struct phy **phy; - struct device_link **link; -}; - -/* Register access */ -static inline void cdns_pcie_writeb(struct cdns_pcie *pcie, u32 reg, u8 value) -{ - writeb(value, pcie->reg_base + reg); -} - -static inline void cdns_pcie_writew(struct cdns_pcie *pcie, u32 reg, u16 value) -{ - writew(value, pcie->reg_base + reg); -} - -static inline void cdns_pcie_writel(struct cdns_pcie *pcie, u32 reg, u32 value) -{ - writel(value, pcie->reg_base + reg); -} - -static inline u32 cdns_pcie_readl(struct cdns_pcie *pcie, u32 reg) -{ - return readl(pcie->reg_base + reg); -} - -/* Root Port register access */ -static inline void cdns_pcie_rp_writeb(struct cdns_pcie *pcie, - u32 reg, u8 value) -{ - writeb(value, pcie->reg_base + CDNS_PCIE_RP_BASE + reg); -} - -static inline void cdns_pcie_rp_writew(struct cdns_pcie *pcie, - u32 reg, u16 value) -{ - writew(value, pcie->reg_base + CDNS_PCIE_RP_BASE + reg); -} - -/* Endpoint Function register access */ -static inline void cdns_pcie_ep_fn_writeb(struct cdns_pcie *pcie, u8 fn, - u32 reg, u8 value) -{ - writeb(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); -} - -static inline void cdns_pcie_ep_fn_writew(struct cdns_pcie *pcie, u8 fn, - u32 reg, u16 value) -{ - writew(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); -} - -static inline void cdns_pcie_ep_fn_writel(struct cdns_pcie *pcie, u8 fn, - u32 reg, u32 value) -{ - writel(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); -} - -static inline u8 cdns_pcie_ep_fn_readb(struct cdns_pcie *pcie, u8 fn, u32 reg) -{ - return readb(pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); -} - -static inline u16 cdns_pcie_ep_fn_readw(struct cdns_pcie *pcie, u8 fn, u32 reg) -{ - return readw(pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); -} - -static inline u32 cdns_pcie_ep_fn_readl(struct cdns_pcie *pcie, u8 fn, u32 reg) -{ - return readl(pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); -} - -void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 fn, - u32 r, bool is_io, - u64 cpu_addr, u64 pci_addr, size_t size); - -void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, u8 fn, - u32 r, u64 cpu_addr); - -void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r); -void cdns_pcie_disable_phy(struct cdns_pcie *pcie); -int cdns_pcie_enable_phy(struct cdns_pcie *pcie); -int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie); -extern const struct dev_pm_ops cdns_pcie_pm_ops; +#define CDNS_PCIE_MSG_NO_DATA BIT(16) -#endif /* _PCIE_CADENCE_H */ +#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 new file mode 100644 index 000000000000..b067a3296dd3 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-plat.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence PCIe platform driver. + * + * Copyright (c) 2019, Cadence Design Systems + * Author: Tom Joseph <tjoseph@cadence.com> + */ +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include "pcie-cadence.h" + +#define CDNS_PLAT_CPU_TO_BUS_ADDR 0x0FFFFFFF + +/** + * struct cdns_plat_pcie - private data for this PCIe platform driver + * @pcie: Cadence PCIe controller + */ +struct cdns_plat_pcie { + struct cdns_pcie *pcie; +}; + +static const struct of_device_id cdns_plat_pcie_of_match[]; + +static u64 cdns_plat_cpu_addr_fixup(struct cdns_pcie *pcie, u64 cpu_addr) +{ + return cpu_addr & CDNS_PLAT_CPU_TO_BUS_ADDR; +} + +static const struct cdns_pcie_ops cdns_plat_ops = { + .cpu_addr_fixup = cdns_plat_cpu_addr_fixup, +}; + +static int cdns_plat_pcie_probe(struct platform_device *pdev) +{ + const struct cdns_plat_pcie_of_data *data; + struct cdns_plat_pcie *cdns_plat_pcie; + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct cdns_pcie_ep *ep; + struct cdns_pcie_rc *rc; + int phy_count; + bool is_rc; + int ret; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + is_rc = data->is_rc; + + pr_debug(" Started %s with is_rc: %d\n", __func__, is_rc); + cdns_plat_pcie = devm_kzalloc(dev, sizeof(*cdns_plat_pcie), GFP_KERNEL); + if (!cdns_plat_pcie) + return -ENOMEM; + + platform_set_drvdata(pdev, cdns_plat_pcie); + if (is_rc) { + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_PLAT_HOST)) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); + if (!bridge) + return -ENOMEM; + + rc = pci_host_bridge_priv(bridge); + rc->pcie.dev = dev; + rc->pcie.ops = &cdns_plat_ops; + cdns_plat_pcie->pcie = &rc->pcie; + + ret = cdns_pcie_init_phy(dev, cdns_plat_pcie->pcie); + if (ret) { + dev_err(dev, "failed to init phy\n"); + return ret; + } + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync() failed\n"); + goto err_get_sync; + } + + ret = cdns_pcie_host_setup(rc); + if (ret) + goto err_init; + } else { + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_PLAT_EP)) + return -ENODEV; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->pcie.dev = dev; + ep->pcie.ops = &cdns_plat_ops; + cdns_plat_pcie->pcie = &ep->pcie; + + ret = cdns_pcie_init_phy(dev, cdns_plat_pcie->pcie); + if (ret) { + dev_err(dev, "failed to init phy\n"); + return ret; + } + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync() failed\n"); + goto err_get_sync; + } + + ret = cdns_pcie_ep_setup(ep); + if (ret) + goto err_init; + } + + return 0; + + err_init: + err_get_sync: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + cdns_pcie_disable_phy(cdns_plat_pcie->pcie); + phy_count = cdns_plat_pcie->pcie->phy_count; + while (phy_count--) + device_link_del(cdns_plat_pcie->pcie->link[phy_count]); + + return 0; +} + +static void cdns_plat_pcie_shutdown(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cdns_pcie *pcie = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_put_sync(dev); + if (ret < 0) + dev_dbg(dev, "pm_runtime_put_sync failed\n"); + + pm_runtime_disable(dev); + + cdns_pcie_disable_phy(pcie); +} + +static const struct cdns_plat_pcie_of_data cdns_plat_pcie_host_of_data = { + .is_rc = true, +}; + +static const struct cdns_plat_pcie_of_data cdns_plat_pcie_ep_of_data = { + .is_rc = false, +}; + +static const struct of_device_id cdns_plat_pcie_of_match[] = { + { + .compatible = "cdns,cdns-pcie-host", + .data = &cdns_plat_pcie_host_of_data, + }, + { + .compatible = "cdns,cdns-pcie-ep", + .data = &cdns_plat_pcie_ep_of_data, + }, + {}, +}; + +static struct platform_driver cdns_plat_pcie_driver = { + .driver = { + .name = "cdns-pcie", + .of_match_table = cdns_plat_pcie_of_match, + .pm = &cdns_pcie_pm_ops, + }, + .probe = cdns_plat_pcie_probe, + .shutdown = cdns_plat_pcie_shutdown, +}; +module_platform_driver(cdns_plat_pcie_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe controller platform driver"); diff --git a/drivers/pci/controller/pcie-cadence.c b/drivers/pci/controller/cadence/pcie-cadence.c index cd795f6fc1e2..e6f1a4ac0fb7 100644 --- a/drivers/pci/controller/pcie-cadence.c +++ b/drivers/pci/controller/cadence/pcie-cadence.c @@ -4,10 +4,54 @@ // 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" -void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 fn, +u8 cdns_pcie_find_capability(struct cdns_pcie *pcie, u8 cap) +{ + return PCI_FIND_NEXT_CAP(cdns_pcie_read_cfg, PCI_CAPABILITY_LIST, + cap, pcie); +} +EXPORT_SYMBOL_GPL(cdns_pcie_find_capability); + +u16 cdns_pcie_find_ext_capability(struct cdns_pcie *pcie, u8 cap) +{ + return PCI_FIND_NEXT_EXT_CAP(cdns_pcie_read_cfg, 0, cap, pcie); +} +EXPORT_SYMBOL_GPL(cdns_pcie_find_ext_capability); + +bool cdns_pcie_linkup(struct cdns_pcie *pcie) +{ + u32 pl_reg_val; + + pl_reg_val = cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE); + if (pl_reg_val & GENMASK(0, 0)) + return true; + return false; +} +EXPORT_SYMBOL_GPL(cdns_pcie_linkup); + +void cdns_pcie_detect_quiet_min_delay_set(struct cdns_pcie *pcie) +{ + u32 delay = 0x3; + u32 ltssm_control_cap; + + /* + * Set the LTSSM Detect Quiet state min. delay to 2ms. + */ + ltssm_control_cap = cdns_pcie_readl(pcie, CDNS_PCIE_LTSSM_CONTROL_CAP); + ltssm_control_cap = ((ltssm_control_cap & + ~CDNS_PCIE_DETECT_QUIET_MIN_DELAY_MASK) | + CDNS_PCIE_DETECT_QUIET_MIN_DELAY(delay)); + + cdns_pcie_writel(pcie, CDNS_PCIE_LTSSM_CONTROL_CAP, ltssm_control_cap); +} +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, u64 cpu_addr, u64 pci_addr, size_t size) { @@ -60,7 +104,7 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 fn, /* The device and function numbers are always 0. */ desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID | CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(0); - desc1 |= CDNS_PCIE_AT_OB_REGION_DESC1_BUS(pcie->bus); + desc1 |= CDNS_PCIE_AT_OB_REGION_DESC1_BUS(busnr); } else { /* * Use captured values for bus and device numbers but still @@ -73,7 +117,9 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 fn, cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC1(r), desc1); /* Set the CPU address */ - cpu_addr -= pcie->mem_res->start; + 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) | (lower_32_bits(cpu_addr) & GENMASK(31, 8)); addr1 = upper_32_bits(cpu_addr); @@ -81,8 +127,10 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, 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 fn, +void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, + u8 busnr, u8 fn, u32 r, u64 cpu_addr) { u32 addr0, addr1, desc0, desc1; @@ -94,13 +142,15 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, u8 fn, if (pcie->is_rc) { desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID | CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(0); - desc1 |= CDNS_PCIE_AT_OB_REGION_DESC1_BUS(pcie->bus); + desc1 |= CDNS_PCIE_AT_OB_REGION_DESC1_BUS(busnr); } else { desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(fn); } /* Set the CPU address */ - cpu_addr -= pcie->mem_res->start; + 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) | (lower_32_bits(cpu_addr) & GENMASK(31, 8)); addr1 = upper_32_bits(cpu_addr); @@ -112,6 +162,7 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, 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_for_normal_msg); void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r) { @@ -124,6 +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) { @@ -134,6 +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) { @@ -162,6 +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) { @@ -175,7 +229,7 @@ int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie) phy_count = of_property_count_strings(np, "phy-names"); if (phy_count < 1) { - dev_err(dev, "no phy-names. PHY will not be initialized\n"); + dev_info(dev, "no \"phy-names\" property found; PHY will not be initialized\n"); pcie->phy_count = 0; return 0; } @@ -221,8 +275,8 @@ err_phy: return ret; } +EXPORT_SYMBOL_GPL(cdns_pcie_init_phy); -#ifdef CONFIG_PM_SLEEP static int cdns_pcie_suspend_noirq(struct device *dev) { struct cdns_pcie *pcie = dev_get_drvdata(dev); @@ -239,15 +293,19 @@ static int cdns_pcie_resume_noirq(struct device *dev) ret = cdns_pcie_enable_phy(pcie); if (ret) { - dev_err(dev, "failed to enable phy\n"); + dev_err(dev, "failed to enable PHY\n"); return ret; } return 0; } -#endif const struct dev_pm_ops cdns_pcie_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(cdns_pcie_suspend_noirq, - cdns_pcie_resume_noirq) + 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 new file mode 100644 index 000000000000..443033c607d7 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence.h @@ -0,0 +1,523 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2017 Cadence +// Cadence PCIe controller driver. +// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + +#ifndef _PCIE_CADENCE_H +#define _PCIE_CADENCE_H + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/pci-epf.h> +#include <linux/phy/phy.h> +#include "pcie-cadence-lga-regs.h" +#include "pcie-cadence-hpa-regs.h" + +enum cdns_pcie_rp_bar { + RP_BAR_UNDEFINED = -1, + RP_BAR0, + RP_BAR1, + RP_NO_BAR +}; + +struct cdns_pcie_rp_ib_bar { + u64 size; + bool free; +}; + +struct cdns_pcie; +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); + 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 + * @phy: list of pointers to specific PHY control blocks + * @link: list of pointers to corresponding device link representations + * @ops: Platform-specific ops to control various inputs from Cadence PCIe + * wrapper + * @cdns_pcie_reg_offsets: Register bank offsets for different SoC + */ +struct cdns_pcie { + 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; +}; + +/** + * struct cdns_pcie_rc - private data for this PCIe Root Complex driver + * @pcie: Cadence PCIe controller + * @cfg_res: start/end offsets in the physical system memory to map PCI + * configuration space accesses + * @cfg_base: IO mapped window to access the PCI configuration space of a + * single function at a time + * @vendor_id: PCI vendor ID + * @device_id: PCI device ID + * @avail_ib_bar: Status of RP_BAR0, RP_BAR1 and RP_NO_BAR if it's free or + * available + * @quirk_retrain_flag: Retrain link as quirk for PCIe Gen2 + * @quirk_detect_quiet_flag: LTSSM Detect Quiet min delay set as quirk + * @ecam_supported: Whether the ECAM is supported + * @no_inbound_map: Whether inbound mapping is supported + */ +struct cdns_pcie_rc { + struct cdns_pcie pcie; + struct resource *cfg_res; + void __iomem *cfg_base; + u32 vendor_id; + u32 device_id; + bool avail_ib_bar[CDNS_PCIE_RP_MAX_IB]; + unsigned int quirk_retrain_flag:1; + unsigned int quirk_detect_quiet_flag:1; + unsigned int ecam_supported:1; + unsigned int no_inbound_map:1; +}; + +/** + * struct cdns_pcie_epf - Structure to hold info about endpoint function + * @epf: Info about virtual functions attached to the physical function + * @epf_bar: reference to the pci_epf_bar for the six Base Address Registers + */ +struct cdns_pcie_epf { + struct cdns_pcie_epf *epf; + struct pci_epf_bar *epf_bar[PCI_STD_NUM_BARS]; +}; + +/** + * struct cdns_pcie_ep - private data for this PCIe endpoint controller driver + * @pcie: Cadence PCIe controller + * @max_regions: maximum number of regions supported by hardware + * @ob_region_map: bitmask of mapped outbound regions + * @ob_addr: base addresses in the AXI bus where the outbound regions start + * @irq_phys_addr: base address on the AXI bus where the MSI/INTX IRQ + * dedicated outbound regions is mapped. + * @irq_cpu_addr: base address in the CPU space where a write access triggers + * the sending of a memory write (MSI) / normal message (INTX + * IRQ) TLP through the PCIe bus. + * @irq_pci_addr: used to save the current mapping of the MSI/INTX IRQ + * dedicated outbound region. + * @irq_pci_fn: the latest PCI function that has updated the mapping of + * the MSI/INTX IRQ dedicated outbound region. + * @irq_pending: bitmask of asserted INTX IRQs. + * @lock: spin lock to disable interrupts while modifying PCIe controller + * registers fields (RMW) accessible by both remote RC and EP to + * minimize time between read and write + * @epf: Structure to hold info about endpoint function + * @quirk_detect_quiet_flag: LTSSM Detect Quiet min delay set as quirk + * @quirk_disable_flr: Disable FLR (Function Level Reset) quirk flag + */ +struct cdns_pcie_ep { + struct cdns_pcie pcie; + u32 max_regions; + unsigned long ob_region_map; + phys_addr_t *ob_addr; + phys_addr_t irq_phys_addr; + void __iomem *irq_cpu_addr; + u64 irq_pci_addr; + u8 irq_pci_fn; + u8 irq_pending; + /* protect writing to PCI_STATUS while raising INTX interrupts */ + spinlock_t lock; + struct cdns_pcie_epf *epf; + unsigned int quirk_detect_quiet_flag:1; + 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) +{ + writel(value, pcie->reg_base + reg); +} + +static inline u32 cdns_pcie_readl(struct cdns_pcie *pcie, u32 reg) +{ + return readl(pcie->reg_base + reg); +} + +static inline 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); + unsigned int offset = (unsigned long)addr & 0x3; + u32 val = readl(aligned_addr); + + if (!IS_ALIGNED((uintptr_t)addr, size)) { + pr_warn("Address %p and size %d are not aligned\n", addr, size); + return 0; + } + + if (size > 2) + return val; + + return (val >> (8 * offset)) & ((1 << (size * 8)) - 1); +} + +static inline void cdns_pcie_write_sz(void __iomem *addr, int size, u32 value) +{ + void __iomem *aligned_addr = PTR_ALIGN_DOWN(addr, 0x4); + unsigned int offset = (unsigned long)addr & 0x3; + u32 mask; + u32 val; + + if (!IS_ALIGNED((uintptr_t)addr, size)) { + pr_warn("Address %p and size %d are not aligned\n", addr, size); + return; + } + + if (size > 2) { + writel(value, addr); + return; + } + + mask = ~(((1 << (size * 8)) - 1) << (offset * 8)); + val = readl(aligned_addr) & mask; + val |= value << (offset * 8); + writel(val, aligned_addr); +} + +/* Root Port register access */ +static inline void cdns_pcie_rp_writeb(struct cdns_pcie *pcie, + u32 reg, u8 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_RP_BASE + reg; + + cdns_pcie_write_sz(addr, 0x1, value); +} + +static inline void cdns_pcie_rp_writew(struct cdns_pcie *pcie, + u32 reg, u16 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_RP_BASE + reg; + + cdns_pcie_write_sz(addr, 0x2, value); +} + +static inline u16 cdns_pcie_rp_readw(struct cdns_pcie *pcie, u32 reg) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_RP_BASE + reg; + + return cdns_pcie_read_sz(addr, 0x2); +} + +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) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg; + + cdns_pcie_write_sz(addr, 0x1, value); +} + +static inline void cdns_pcie_ep_fn_writew(struct cdns_pcie *pcie, u8 fn, + u32 reg, u16 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg; + + cdns_pcie_write_sz(addr, 0x2, value); +} + +static inline void cdns_pcie_ep_fn_writel(struct cdns_pcie *pcie, u8 fn, + u32 reg, u32 value) +{ + writel(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); +} + +static inline u16 cdns_pcie_ep_fn_readw(struct cdns_pcie *pcie, u8 fn, u32 reg) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg; + + return cdns_pcie_read_sz(addr, 0x2); +} + +static inline u32 cdns_pcie_ep_fn_readl(struct cdns_pcie *pcie, u8 fn, u32 reg) +{ + return readl(pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); +} + +static inline int cdns_pcie_start_link(struct cdns_pcie *pcie) +{ + if (pcie->ops && pcie->ops->start_link) + return pcie->ops->start_link(pcie); + + return 0; +} + +static inline void cdns_pcie_stop_link(struct cdns_pcie *pcie) +{ + if (pcie->ops && pcie->ops->stop_link) + pcie->ops->stop_link(pcie); +} + +static inline bool cdns_pcie_link_up(struct cdns_pcie *pcie) +{ + if (pcie->ops && pcie->ops->link_up) + return pcie->ops->link_up(pcie); + + return true; +} + +#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) +{ + return 0; +} + +static inline int cdns_pcie_host_init(struct cdns_pcie_rc *rc) +{ + return 0; +} + +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) +{ + return NULL; +} +#endif + +#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, + u32 r, bool is_io, + u64 cpu_addr, u64 pci_addr, size_t size); + +void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, + u8 busnr, u8 fn, + u32 r, u64 cpu_addr); + +void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r); +void cdns_pcie_disable_phy(struct cdns_pcie *pcie); +int cdns_pcie_enable_phy(struct cdns_pcie *pcie); +int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie); +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 548c58223868..519b59422b47 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -1,61 +1,277 @@ # SPDX-License-Identifier: GPL-2.0 -menu "DesignWare PCI Core Support" +menu "DesignWare-based PCIe controllers" depends on PCI config PCIE_DW bool +config PCIE_DW_DEBUGFS + bool "DesignWare PCIe debugfs entries" + depends on DEBUG_FS + depends on PCIE_DW_HOST || PCIE_DW_EP + help + Say Y here to enable debugfs entries for the PCIe controller. These + entries provide various debug features related to the controller and + expose the RAS DES capabilities such as Silicon Debug, Error Injection + and Statistical Counters. + config PCIE_DW_HOST - bool - depends on PCI_MSI_IRQ_DOMAIN - select PCIE_DW + bool + select PCIE_DW + select IRQ_MSI_LIB + select PCI_HOST_COMMON config PCIE_DW_EP bool - depends on PCI_ENDPOINT select PCIE_DW -config PCI_DRA7XX +config PCIE_AL + bool "Amazon Annapurna Labs PCIe controller" + depends on OF && (ARM64 || COMPILE_TEST) + depends on PCI_MSI + select PCIE_DW_HOST + select PCI_ECAM + help + Say Y here to enable support of the Amazon's Annapurna Labs PCIe + controller IP on Amazon SoCs. The PCIe controller uses the DesignWare + core plus Annapurna Labs proprietary hardware wrappers. This is + required only for DT-based platforms. ACPI platforms with the + Annapurna Labs PCIe controller don't need to enable this. + +config PCIE_AMD_MDB + bool "AMD MDB Versal2 PCIe controller" + depends on OF && (ARM64 || COMPILE_TEST) + depends on PCI_MSI + select PCIE_DW_HOST + help + Say Y here if you want to enable PCIe controller support on AMD + Versal2 SoCs. The AMD MDB Versal2 PCIe controller is based on + DesignWare IP and therefore the driver re-uses the DesignWare + core functions to implement the driver. + +config PCI_MESON + tristate "Amlogic Meson PCIe controller" + default m if ARCH_MESON + depends on PCI_MSI + select PCIE_DW_HOST + help + Say Y here if you want to enable PCI controller support on Amlogic + SoCs. The PCI controller on Amlogic is based on DesignWare hardware + and therefore the driver re-uses the DesignWare core functions to + implement the driver. + +config PCIE_ARTPEC6 bool -config PCI_DRA7XX_HOST - bool "TI DRA7xx PCIe controller Host Mode" - depends on SOC_DRA7XX || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN - depends on OF && HAS_IOMEM && TI_PIPE3 +config PCIE_ARTPEC6_HOST + bool "Axis ARTPEC-6 PCIe controller (host mode)" + depends on MACH_ARTPEC6 || COMPILE_TEST + depends on PCI_MSI select PCIE_DW_HOST - select PCI_DRA7XX - default y + select PCIE_ARTPEC6 help - Enables support for the PCIe controller in the DRA7xx SoC to work in - host mode. There are two instances of PCIe controller in DRA7xx. - This controller can work either as EP or RC. In order to enable - host-specific features PCI_DRA7XX_HOST must be selected and in order - to enable device-specific features PCI_DRA7XX_EP must be selected. - This uses the DesignWare core. + Enables support for the PCIe controller in the ARTPEC-6 SoC to work in + host mode. This uses the DesignWare core. -config PCI_DRA7XX_EP - bool "TI DRA7xx PCIe controller Endpoint Mode" - depends on SOC_DRA7XX || COMPILE_TEST +config PCIE_ARTPEC6_EP + bool "Axis ARTPEC-6 PCIe controller (endpoint mode)" + depends on MACH_ARTPEC6 || COMPILE_TEST depends on PCI_ENDPOINT - depends on OF && HAS_IOMEM && TI_PIPE3 select PCIE_DW_EP - select PCI_DRA7XX + select PCIE_ARTPEC6 help - Enables support for the PCIe controller in the DRA7xx SoC to work in - endpoint mode. There are two instances of PCIe controller in DRA7xx. - This controller can work either as EP or RC. In order to enable - host-specific features PCI_DRA7XX_HOST must be selected and in order - to enable device-specific features PCI_DRA7XX_EP must be selected. - This uses the DesignWare core. + Enables support for the PCIe controller in the ARTPEC-6 SoC to work in + endpoint mode. This uses the DesignWare core. + +config PCIE_BT1 + tristate "Baikal-T1 PCIe controller" + depends on MIPS_BAIKAL_T1 || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + help + Enables support for the PCIe controller in the Baikal-T1 SoC to work + in host mode. It's based on the Synopsys DWC PCIe v4.60a IP-core. + +config PCI_IMX6 + bool + +config PCI_IMX6_HOST + bool "Freescale i.MX6/7/8 PCIe controller (host mode)" + depends on ARCH_MXC || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + select PCI_IMX6 + help + Enables support for the PCIe controller in the i.MX SoCs to + work in Root Complex mode. The PCI controller on i.MX is based + on DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. + +config PCI_IMX6_EP + bool "Freescale i.MX6/7/8 PCIe controller (endpoint mode)" + depends on ARCH_MXC || COMPILE_TEST + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCI_IMX6 + help + Enables support for the PCIe controller in the i.MX SoCs to + work in endpoint mode. The PCI controller on i.MX is based + on DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. + +config PCI_LAYERSCAPE + bool "Freescale Layerscape PCIe controller (host mode)" + depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) + depends on PCI_MSI + select PCIE_DW_HOST + select MFD_SYSCON + help + Say Y here if you want to enable PCIe controller support on Layerscape + SoCs to work in Host mode. + This controller can work either as EP or RC. The RCW[HOST_AGT_PEX] + determines which PCIe controller works in EP mode and which PCIe + controller works in RC mode. + +config PCI_LAYERSCAPE_EP + bool "Freescale Layerscape PCIe controller (endpoint mode)" + depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) + depends on PCI_ENDPOINT + select PCIE_DW_EP + help + Say Y here if you want to enable PCIe controller support on Layerscape + SoCs to work in Endpoint mode. + This controller can work either as EP or RC. The RCW[HOST_AGT_PEX] + determines which PCIe controller works in EP mode and which PCIe + controller works in RC mode. + +config PCI_HISI + depends on OF && (ARM64 || COMPILE_TEST) + bool "HiSilicon Hip05 and Hip06 SoCs PCIe controller" + depends on PCI_MSI + select PCIE_DW_HOST + select PCI_HOST_COMMON + help + Say Y here if you want PCIe controller support on HiSilicon + Hip05 and Hip06 SoCs + +config PCIE_KIRIN + depends on OF && (ARM64 || COMPILE_TEST) + tristate "HiSilicon Kirin PCIe controller" + depends on PCI_MSI + select PCIE_DW_HOST + select REGMAP_MMIO + help + Say Y here if you want PCIe controller support + on HiSilicon Kirin series SoCs. + +config PCIE_HISI_STB + bool "HiSilicon STB PCIe controller" + depends on ARCH_HISI || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + help + Say Y here if you want PCIe controller support on HiSilicon STB SoCs + +config PCIE_INTEL_GW + bool "Intel Gateway PCIe controller " + depends on OF && (X86 || COMPILE_TEST) + depends on PCI_MSI + select PCIE_DW_HOST + help + Say 'Y' here to enable PCIe Host controller support on Intel + Gateway SoCs. + The PCIe controller uses the DesignWare core plus Intel-specific + hardware wrappers. + +config PCIE_KEEMBAY + bool + +config PCIE_KEEMBAY_HOST + bool "Intel Keem Bay PCIe controller (host mode)" + depends on ARCH_KEEMBAY || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + select PCIE_KEEMBAY + help + Say 'Y' here to enable support for the PCIe controller in Keem Bay + to work in host mode. + The PCIe controller is based on DesignWare Hardware and uses + DesignWare core functions. + +config PCIE_KEEMBAY_EP + bool "Intel Keem Bay PCIe controller (endpoint mode)" + depends on ARCH_KEEMBAY || COMPILE_TEST + depends on PCI_MSI + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCIE_KEEMBAY + help + Say 'Y' here to enable support for the PCIe controller in Keem Bay + to work in endpoint mode. + The PCIe controller is based on DesignWare Hardware and uses + DesignWare core functions. + +config PCIE_ARMADA_8K + bool "Marvell Armada-8K PCIe controller" + depends on ARCH_MVEBU || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + help + Say Y here if you want to enable PCIe controller support on + Armada-8K SoCs. The PCIe controller on Armada-8K is based on + DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. + +config PCIE_TEGRA194 + tristate + +config PCIE_TEGRA194_HOST + tristate "NVIDIA Tegra194 (and later) PCIe controller (host mode)" + depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + select PHY_TEGRA194_P2U + select PCIE_TEGRA194 + help + Enables support for the PCIe controller in the NVIDIA Tegra194 SoC to + work in host mode. There are two instances of PCIe controllers in + Tegra194. This controller can work either as EP or RC. In order to + enable host-specific features PCIE_TEGRA194_HOST must be selected and + in order to enable device-specific features PCIE_TEGRA194_EP must be + selected. This uses the DesignWare core. + +config PCIE_TEGRA194_EP + tristate "NVIDIA Tegra194 (and later) PCIe controller (endpoint mode)" + depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PHY_TEGRA194_P2U + select PCIE_TEGRA194 + help + Enables support for the PCIe controller in the NVIDIA Tegra194 SoC to + work in endpoint mode. There are two instances of PCIe controllers in + Tegra194. This controller can work either as EP or RC. In order to + enable host-specific features PCIE_TEGRA194_HOST must be selected and + in order to enable device-specific features PCIE_TEGRA194_EP must be + selected. This uses the DesignWare core. + +config PCIE_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 config PCIE_DW_PLAT_HOST - bool "Platform bus based DesignWare PCIe Controller - Host mode" - depends on PCI && PCI_MSI_IRQ_DOMAIN + bool "Platform bus based DesignWare PCIe controller (host mode)" + depends on PCI_MSI select PCIE_DW_HOST select PCIE_DW_PLAT help @@ -68,8 +284,8 @@ config PCIE_DW_PLAT_HOST selected. config PCIE_DW_PLAT_EP - bool "Platform bus based DesignWare PCIe Controller - Endpoint mode" - depends on PCI && PCI_MSI_IRQ_DOMAIN + bool "Platform bus based DesignWare PCIe controller (endpoint mode)" + depends on PCI && PCI_MSI depends on PCI_ENDPOINT select PCIE_DW_EP select PCIE_DW_PLAT @@ -82,135 +298,254 @@ config PCIE_DW_PLAT_EP order to enable device-specific features PCI_DW_PLAT_EP must be selected. -config PCI_EXYNOS - bool "Samsung Exynos PCIe controller" - depends on SOC_EXYNOS5440 || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN +config PCIE_QCOM_COMMON + bool + +config PCIE_QCOM + bool "Qualcomm PCIe controller (host mode)" + depends on OF && (ARCH_QCOM || COMPILE_TEST) + depends on PCI_MSI 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 + hardware wrappers. -config PCI_IMX6 - bool "Freescale i.MX6/7 PCIe controller" - depends on SOC_IMX6Q || SOC_IMX7D || (ARM && COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN +config PCIE_QCOM_EP + tristate "Qualcomm PCIe controller (endpoint mode)" + depends on OF && (ARCH_QCOM || COMPILE_TEST) + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCIE_QCOM_COMMON + help + Say Y here to enable support for the PCIe controllers on Qualcomm SoCs + to work in endpoint mode. The PCIe controller uses the DesignWare core + plus Qualcomm-specific hardware wrappers. + +config PCIE_RCAR_GEN4 + tristate + +config PCIE_RCAR_GEN4_HOST + tristate "Renesas R-Car Gen4 PCIe controller (host mode)" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PCI_MSI select PCIE_DW_HOST + select PCIE_RCAR_GEN4 + help + Say Y here if you want PCIe controller (host mode) on R-Car Gen4 SoCs. + To compile this driver as a module, choose M here: the module will be + called pcie-rcar-gen4.ko. This uses the DesignWare core. -config PCIE_SPEAR13XX - bool "STMicroelectronics SPEAr PCIe controller" - depends on ARCH_SPEAR13XX || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN +config PCIE_RCAR_GEN4_EP + tristate "Renesas R-Car Gen4 PCIe controller (endpoint mode)" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCIE_RCAR_GEN4 + help + Say Y here if you want PCIe controller (endpoint mode) on R-Car Gen4 + SoCs. To compile this driver as a module, choose M here: the module + will be called pcie-rcar-gen4.ko. This uses the DesignWare core. + +config PCIE_ROCKCHIP_DW + bool + +config PCIE_ROCKCHIP_DW_HOST + bool "Rockchip DesignWare PCIe controller (host mode)" + depends on PCI_MSI + depends on ARCH_ROCKCHIP || COMPILE_TEST + depends on OF select PCIE_DW_HOST + select PCIE_ROCKCHIP_DW help - Say Y here if you want PCIe support on SPEAr13XX SoCs. + Enables support for the DesignWare PCIe controller in the + Rockchip SoC (except RK3399) to work in host mode. -config PCI_KEYSTONE - bool "TI Keystone PCIe controller" - depends on ARCH_KEYSTONE || (ARM && COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN +config PCIE_ROCKCHIP_DW_EP + bool "Rockchip DesignWare PCIe controller (endpoint mode)" + depends on ARCH_ROCKCHIP || COMPILE_TEST + depends on OF + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCIE_ROCKCHIP_DW + help + Enables support for the DesignWare PCIe controller in the + Rockchip SoC (except RK3399) to work in endpoint mode. + +config PCI_EXYNOS + tristate "Samsung Exynos PCIe controller" + depends on ARCH_EXYNOS || COMPILE_TEST + depends on PCI_MSI select PCIE_DW_HOST help - Say Y here if you want to enable PCI controller support on Keystone - SoCs. The PCI controller on Keystone is based on DesignWare hardware - and therefore the driver re-uses the DesignWare core functions to - implement the driver. + Enables support for the PCIe controller in the Samsung Exynos SoCs + to work in host mode. The PCI controller is based on the DesignWare + hardware and therefore the driver re-uses the DesignWare core + functions to implement the driver. -config PCI_LAYERSCAPE - bool "Freescale Layerscape PCIe controller" - depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN - select MFD_SYSCON +config PCIE_FU740 + bool "SiFive FU740 PCIe controller" + depends on PCI_MSI + depends on ARCH_SIFIVE || COMPILE_TEST select PCIE_DW_HOST help - Say Y here if you want PCIe controller support on Layerscape SoCs. + Say Y here if you want PCIe controller support for the SiFive + FU740. -config PCI_HISI - depends on OF && (ARM64 || COMPILE_TEST) - bool "HiSilicon Hip05 and Hip06 SoCs PCIe controllers" - depends on PCI_MSI_IRQ_DOMAIN +config PCIE_UNIPHIER + bool "Socionext UniPhier PCIe controller (host mode)" + depends on ARCH_UNIPHIER || COMPILE_TEST + depends on OF && HAS_IOMEM + depends on PCI_MSI select PCIE_DW_HOST - select PCI_HOST_COMMON help - Say Y here if you want PCIe controller support on HiSilicon - Hip05 and Hip06 SoCs + Say Y here if you want PCIe host controller support on UniPhier SoCs. + This driver supports LD20 and PXs3 SoCs. -config PCIE_QCOM - bool "Qualcomm PCIe controller" - depends on OF && (ARCH_QCOM || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN +config PCIE_UNIPHIER_EP + bool "Socionext UniPhier PCIe controller (endpoint mode)" + depends on ARCH_UNIPHIER || COMPILE_TEST + depends on OF && HAS_IOMEM + depends on PCI_ENDPOINT + select PCIE_DW_EP + help + Say Y here if you want PCIe endpoint controller support on + UniPhier SoCs. This driver supports Pro5 SoC. + +config PCIE_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 to enable PCIe controller support on Qualcomm SoCs. The - PCIe controller uses the DesignWare core plus Qualcomm-specific - hardware wrappers. + Say Y here if you want PCIe host controller support on + Sophgo SoCs. -config PCIE_ARMADA_8K - bool "Marvell Armada-8K PCIe controller" - depends on ARCH_MVEBU || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN +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 - Say Y here if you want to enable PCIe controller support on - Armada-8K SoCs. The PCIe controller on Armada-8K is based on - DesignWare hardware and therefore the driver re-uses the - DesignWare core functions to implement the driver. + 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_ARTPEC6 - bool +config PCIE_SPEAR13XX + bool "STMicroelectronics SPEAr PCIe controller" + depends on ARCH_SPEAR13XX || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + help + Say Y here if you want PCIe support on SPEAr13XX SoCs. -config PCIE_ARTPEC6_HOST - bool "Axis ARTPEC-6 PCIe controller Host Mode" - depends on MACH_ARTPEC6 || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN +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 - select PCIE_ARTPEC6 help - Enables support for the PCIe controller in the ARTPEC-6 SoC to work in - host mode. This uses the DesignWare core. + Enables Root Complex (RC) support for the DesignWare core based PCIe + controller found in STM32MP25 SoC. -config PCIE_ARTPEC6_EP - bool "Axis ARTPEC-6 PCIe controller Endpoint Mode" - depends on MACH_ARTPEC6 || COMPILE_TEST + 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 - select PCIE_ARTPEC6 help - Enables support for the PCIe controller in the ARTPEC-6 SoC to work in - endpoint mode. This uses the DesignWare core. + Enables Endpoint (EP) support for the DesignWare core based PCIe + controller found in STM32MP25 SoC. -config PCIE_KIRIN - depends on OF && (ARM64 || COMPILE_TEST) - bool "HiSilicon Kirin series SoCs PCIe controllers" - depends on PCI_MSI_IRQ_DOMAIN + This driver can also be built as a module. If so, the module + will be called pcie-stm32-ep. + +config PCI_DRA7XX + tristate + +config PCI_DRA7XX_HOST + tristate "TI DRA7xx PCIe controller (host mode)" + depends on SOC_DRA7XX || COMPILE_TEST + depends on OF && HAS_IOMEM && TI_PIPE3 + depends on PCI_MSI select PCIE_DW_HOST + select PCI_DRA7XX + default y if SOC_DRA7XX help - Say Y here if you want PCIe controller support - on HiSilicon Kirin series SoCs. + Enables support for the PCIe controller in the DRA7xx SoC to work in + host mode. There are two instances of PCIe controller in DRA7xx. + This controller can work either as EP or RC. In order to enable + host-specific features PCI_DRA7XX_HOST must be selected and in order + to enable device-specific features PCI_DRA7XX_EP must be selected. + This uses the DesignWare core. -config PCIE_HISI_STB - bool "HiSilicon STB SoCs PCIe controllers" - depends on ARCH_HISI || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN - select PCIE_DW_HOST +config PCI_DRA7XX_EP + tristate "TI DRA7xx PCIe controller (endpoint mode)" + depends on SOC_DRA7XX || COMPILE_TEST + depends on OF && HAS_IOMEM && TI_PIPE3 + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCI_DRA7XX help - Say Y here if you want PCIe controller support on HiSilicon STB SoCs + Enables support for the PCIe controller in the DRA7xx SoC to work in + endpoint mode. There are two instances of PCIe controller in DRA7xx. + This controller can work either as EP or RC. In order to enable + host-specific features PCI_DRA7XX_HOST must be selected and in order + to enable device-specific features PCI_DRA7XX_EP must be selected. + This uses the DesignWare core. -config PCI_MESON - bool "MESON PCIe controller" - depends on PCI_MSI_IRQ_DOMAIN +# 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 + 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 if ARM + select PCI_KEYSTONE_TRISTATE if !ARM help - Say Y here if you want to enable PCI controller support on Amlogic - SoCs. The PCI controller on Amlogic is based on DesignWare hardware - and therefore the driver re-uses the DesignWare core functions to - implement the driver. + Enables support for the PCIe controller in the Keystone SoC to + work in host mode. The PCI controller on Keystone is based on + DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. -config PCIE_UNIPHIER - bool "Socionext UniPhier PCIe controllers" - depends on ARCH_UNIPHIER || COMPILE_TEST - depends on OF && HAS_IOMEM - depends on PCI_MSI_IRQ_DOMAIN +config PCI_KEYSTONE_EP + 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 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 + on DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. + +config PCIE_VISCONTI_HOST + bool "Toshiba Visconti PCIe controller" + depends on ARCH_VISCONTI || COMPILE_TEST + depends on PCI_MSI select PCIE_DW_HOST help - Say Y here if you want PCIe controller support on UniPhier SoCs. - This driver supports LD20 and PXs3 SoCs. + Say Y here if you want PCIe controller support on Toshiba Visconti SoC. + This driver supports TMPV7708 SoC. endmenu diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile index 7bcdcdf5024e..67ba59c02038 100644 --- a/drivers/pci/controller/dwc/Makefile +++ b/drivers/pci/controller/dwc/Makefile @@ -1,21 +1,43 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_PCIE_DW) += pcie-designware.o +obj-$(CONFIG_PCIE_DW_DEBUGFS) += pcie-designware-debugfs.o obj-$(CONFIG_PCIE_DW_HOST) += pcie-designware-host.o obj-$(CONFIG_PCIE_DW_EP) += pcie-designware-ep.o obj-$(CONFIG_PCIE_DW_PLAT) += pcie-designware-plat.o +obj-$(CONFIG_PCIE_AMD_MDB) += pcie-amd-mdb.o +obj-$(CONFIG_PCIE_BT1) += pcie-bt1.o obj-$(CONFIG_PCI_DRA7XX) += pci-dra7xx.o obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o +obj-$(CONFIG_PCIE_FU740) += pcie-fu740.o obj-$(CONFIG_PCI_IMX6) += pci-imx6.o +obj-$(CONFIG_PCIE_NXP_S32G) += pcie-nxp-s32g.o obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o +# ARM32 platforms use hook_fault_code() and cannot support loadable module. obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone.o +# On non-ARM32 platforms, loadable module can be supported. +obj-$(CONFIG_PCI_KEYSTONE_TRISTATE) += pci-keystone.o obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o +obj-$(CONFIG_PCI_LAYERSCAPE_EP) += pci-layerscape-ep.o +obj-$(CONFIG_PCIE_QCOM_COMMON) += pcie-qcom-common.o obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o +obj-$(CONFIG_PCIE_QCOM_EP) += pcie-qcom-ep.o obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o +obj-$(CONFIG_PCIE_ROCKCHIP_DW) += pcie-dw-rockchip.o +obj-$(CONFIG_PCIE_SOPHGO_DW) += pcie-sophgo.o +obj-$(CONFIG_PCIE_INTEL_GW) += pcie-intel-gw.o +obj-$(CONFIG_PCIE_KEEMBAY) += pcie-keembay.o obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o obj-$(CONFIG_PCI_MESON) += pci-meson.o +obj-$(CONFIG_PCIE_TEGRA194) += pcie-tegra194.o obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o +obj-$(CONFIG_PCIE_UNIPHIER_EP) += pcie-uniphier-ep.o +obj-$(CONFIG_PCIE_VISCONTI_HOST) += pcie-visconti.o +obj-$(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-$(CONFIG_PCIE_STM32_EP) += pcie-stm32-ep.o # The following drivers are for devices that use the generic ACPI # pci_root.c driver but don't support standard ECAM config access. @@ -27,6 +49,13 @@ obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o # ARM64 and use internal ifdefs to only build the pieces we need # depending on whether ACPI, the DT driver, or both are enabled. -ifdef CONFIG_PCI +obj-$(CONFIG_PCIE_AL) += pcie-al.o +obj-$(CONFIG_PCI_HISI) += pcie-hisi.o + +ifdef CONFIG_ACPI +ifdef CONFIG_PCI_QUIRKS +obj-$(CONFIG_ARM64) += pcie-al.o obj-$(CONFIG_ARM64) += pcie-hisi.o +obj-$(CONFIG_ARM64) += pcie-tegra194-acpi.o +endif endif diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index a32d6dde7a57..01cfd9aeb0b8 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -2,21 +2,22 @@ /* * pcie-dra7xx - PCIe controller driver for TI DRA7xx SoCs * - * Copyright (C) 2013-2014 Texas Instruments Incorporated - http://www.ti.com + * Copyright (C) 2013-2014 Texas Instruments Incorporated - https://www.ti.com * * Authors: Kishon Vijay Abraham I <kishon@ti.com> */ +#include <linux/clk.h> #include <linux/delay.h> #include <linux/device.h> #include <linux/err.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/kernel.h> -#include <linux/init.h> -#include <linux/of_device.h> -#include <linux/of_gpio.h> +#include <linux/module.h> +#include <linux/of.h> #include <linux/of_pci.h> #include <linux/pci.h> #include <linux/phy/phy.h> @@ -26,6 +27,7 @@ #include <linux/types.h> #include <linux/mfd/syscon.h> #include <linux/regmap.h> +#include <linux/gpio/consumer.h> #include "../../pci.h" #include "pcie-designware.h" @@ -72,8 +74,6 @@ #define LINK_UP BIT(16) #define DRA7XX_CPU_TO_BUS_ADDR 0x0FFFFFFF -#define EXP_CAP_ID_OFFSET 0x70 - #define PCIECTRL_TI_CONF_INTX_ASSERT 0x0124 #define PCIECTRL_TI_CONF_INTX_DEASSERT 0x0128 @@ -81,18 +81,23 @@ #define MSI_REQ_GRANT BIT(0) #define MSI_VECTOR_SHIFT 7 +#define PCIE_1LANE_2LANE_SELECTION BIT(13) +#define PCIE_B1C0_MODE_SEL BIT(2) +#define PCIE_B0_B1_TSYNCEN BIT(0) + struct dra7xx_pcie { struct dw_pcie *pci; void __iomem *base; /* DT ti_conf */ int phy_count; /* DT phy-names count */ struct phy **phy; - int link_gen; struct irq_domain *irq_domain; + struct clk *clk; enum dw_pcie_device_mode mode; }; struct dra7xx_pcie_of_data { enum dw_pcie_device_mode mode; + u32 b1co_mode_sel_mask; }; #define to_dra7xx_pcie(x) dev_get_drvdata((x)->dev) @@ -108,17 +113,17 @@ static inline void dra7xx_pcie_writel(struct dra7xx_pcie *pcie, u32 offset, writel(value, pcie->base + offset); } -static u64 dra7xx_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 pci_addr) +static u64 dra7xx_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 cpu_addr) { - return pci_addr & DRA7XX_CPU_TO_BUS_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) @@ -136,33 +141,12 @@ static int dra7xx_pcie_establish_link(struct dw_pcie *pci) struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); struct device *dev = pci->dev; u32 reg; - u32 exp_cap_off = EXP_CAP_ID_OFFSET; if (dw_pcie_link_up(pci)) { dev_err(dev, "link is already up\n"); return 0; } - if (dra7xx->link_gen == 1) { - dw_pcie_read(pci->dbi_base + exp_cap_off + PCI_EXP_LNKCAP, - 4, ®); - if ((reg & PCI_EXP_LNKCAP_SLS) != PCI_EXP_LNKCAP_SLS_2_5GB) { - reg &= ~((u32)PCI_EXP_LNKCAP_SLS); - reg |= PCI_EXP_LNKCAP_SLS_2_5GB; - dw_pcie_write(pci->dbi_base + exp_cap_off + - PCI_EXP_LNKCAP, 4, reg); - } - - dw_pcie_read(pci->dbi_base + exp_cap_off + PCI_EXP_LNKCTL2, - 2, ®); - if ((reg & PCI_EXP_LNKCAP_SLS) != PCI_EXP_LNKCAP_SLS_2_5GB) { - reg &= ~((u32)PCI_EXP_LNKCAP_SLS); - reg |= PCI_EXP_LNKCAP_SLS_2_5GB; - dw_pcie_write(pci->dbi_base + exp_cap_off + - PCI_EXP_LNKCTL2, 2, reg); - } - } - reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD); reg |= LTSSM_EN; dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg); @@ -194,25 +178,16 @@ static void dra7xx_pcie_enable_interrupts(struct dra7xx_pcie *dra7xx) dra7xx_pcie_enable_msi_interrupts(dra7xx); } -static int dra7xx_pcie_host_init(struct pcie_port *pp) +static int dra7xx_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); - dw_pcie_setup_rc(pp); - - dra7xx_pcie_establish_link(pci); - dw_pcie_wait_for_link(pci); - dw_pcie_msi_init(pp); dra7xx_pcie_enable_interrupts(dra7xx); return 0; } -static const struct dw_pcie_host_ops dra7xx_pcie_host_ops = { - .host_init = dra7xx_pcie_host_init, -}; - static int dra7xx_pcie_intx_map(struct irq_domain *domain, unsigned int irq, irq_hw_number_t hwirq) { @@ -227,58 +202,87 @@ static const struct irq_domain_ops intx_domain_ops = { .xlate = pci_irqd_intx_xlate, }; -static int dra7xx_pcie_init_irq_domain(struct pcie_port *pp) +static int dra7xx_pcie_handle_msi(struct dw_pcie_rp *pp, int index) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct device *dev = pci->dev; - struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); - struct device_node *node = dev->of_node; - struct device_node *pcie_intc_node = of_get_next_child(node, NULL); + unsigned long val; + int pos; - if (!pcie_intc_node) { - dev_err(dev, "No PCIe Intc node found\n"); - return -ENODEV; - } + val = dw_pcie_readl_dbi(pci, PCIE_MSI_INTR0_STATUS + + (index * MSI_REG_CTRL_BLOCK_SIZE)); + if (!val) + return 0; - dra7xx->irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, - &intx_domain_ops, pp); - if (!dra7xx->irq_domain) { - dev_err(dev, "Failed to get a INTx IRQ domain\n"); - return -ENODEV; + pos = find_first_bit(&val, MAX_MSI_IRQS_PER_CTRL); + while (pos != MAX_MSI_IRQS_PER_CTRL) { + generic_handle_domain_irq(pp->irq_domain, + (index * MAX_MSI_IRQS_PER_CTRL) + pos); + pos++; + pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, pos); } - return 0; + return 1; } -static irqreturn_t dra7xx_pcie_msi_irq_handler(int irq, void *arg) +static void dra7xx_pcie_handle_msi_irq(struct dw_pcie_rp *pp) { - struct dra7xx_pcie *dra7xx = arg; - struct dw_pcie *pci = dra7xx->pci; - struct pcie_port *pp = &pci->pp; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + int ret, i, count, num_ctrls; + + num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + + /** + * Need to make sure all MSI status bits read 0 before exiting. + * Else, new MSI IRQs are not registered by the wrapper. Have an + * upperbound for the loop and exit the IRQ in case of IRQ flood + * to avoid locking up system in interrupt context. + */ + count = 0; + do { + ret = 0; + + for (i = 0; i < num_ctrls; i++) + ret |= dra7xx_pcie_handle_msi(pp, i); + count++; + } while (ret && count <= 1000); + + if (count > 1000) + dev_warn_ratelimited(pci->dev, + "Too many MSI IRQs to handle\n"); +} + +static void dra7xx_pcie_msi_irq_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct dra7xx_pcie *dra7xx; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; unsigned long reg; - u32 virq, bit; + u32 bit; + + chained_irq_enter(chip, desc); + + pp = irq_desc_get_handler_data(desc); + pci = to_dw_pcie_from_pp(pp); + dra7xx = to_dra7xx_pcie(pci); reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI); + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI, reg); switch (reg) { case MSI: - dw_handle_msi_irq(pp); + dra7xx_pcie_handle_msi_irq(pp); break; case INTA: case INTB: case INTC: case INTD: - for_each_set_bit(bit, ®, PCI_NUM_INTX) { - virq = irq_find_mapping(dra7xx->irq_domain, bit); - if (virq) - generic_handle_irq(virq); - } + for_each_set_bit(bit, ®, PCI_NUM_INTX) + generic_handle_domain_irq(dra7xx->irq_domain, bit); break; } - dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI, reg); - - return IRQ_HANDLED; + chained_irq_exit(chip, desc); } static irqreturn_t dra7xx_pcie_irq_handler(int irq, void *arg) @@ -340,19 +344,49 @@ static irqreturn_t dra7xx_pcie_irq_handler(int irq, void *arg) return IRQ_HANDLED; } +static int dra7xx_pcie_init_irq_domain(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node = of_get_next_child(node, NULL); + + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -ENODEV; + } + + irq_set_chained_handler_and_data(pp->irq, dra7xx_pcie_msi_irq_handler, + pp); + dra7xx->irq_domain = irq_domain_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"); + return -ENODEV; + } + + return 0; +} + +static const struct dw_pcie_host_ops dra7xx_pcie_host_ops = { + .init = dra7xx_pcie_host_init, +}; + static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); dra7xx_pcie_enable_wrapper_interrupts(dra7xx); } -static void dra7xx_pcie_raise_legacy_irq(struct dra7xx_pcie *dra7xx) +static void dra7xx_pcie_raise_intx_irq(struct dra7xx_pcie *dra7xx) { dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_INTX_ASSERT, 0x1); mdelay(1); @@ -370,16 +404,16 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx, } static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u16 interrupt_num) + unsigned int type, u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); switch (type) { - case PCI_EPC_IRQ_LEGACY: - dra7xx_pcie_raise_legacy_irq(dra7xx); + case PCI_IRQ_INTX: + dra7xx_pcie_raise_intx_irq(dra7xx); break; - case PCI_EPC_IRQ_MSI: + case PCI_IRQ_MSI: dra7xx_pcie_raise_msi_irq(dra7xx, interrupt_num); break; default: @@ -389,78 +423,81 @@ static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } -static struct dw_pcie_ep_ops pcie_ep_ops = { - .ep_init = dra7xx_pcie_ep_init, +static const struct pci_epc_features dra7xx_pcie_epc_features = { + .linkup_notifier = true, + .msi_capable = true, +}; + +static const struct pci_epc_features* +dra7xx_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &dra7xx_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .init = dra7xx_pcie_ep_init, .raise_irq = dra7xx_pcie_raise_irq, + .get_features = dra7xx_pcie_get_features, }; -static int __init dra7xx_add_pcie_ep(struct dra7xx_pcie *dra7xx, - struct platform_device *pdev) +static int dra7xx_add_pcie_ep(struct dra7xx_pcie *dra7xx, + struct platform_device *pdev) { int ret; struct dw_pcie_ep *ep; - struct resource *res; struct device *dev = &pdev->dev; struct dw_pcie *pci = dra7xx->pci; ep = &pci->ep; ep->ops = &pcie_ep_ops; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ep_dbics"); - pci->dbi_base = devm_ioremap_resource(dev, res); + pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "ep_dbics"); if (IS_ERR(pci->dbi_base)) return PTR_ERR(pci->dbi_base); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ep_dbics2"); - pci->dbi_base2 = devm_ioremap_resource(dev, res); + pci->dbi_base2 = + devm_platform_ioremap_resource_byname(pdev, "ep_dbics2"); if (IS_ERR(pci->dbi_base2)) return PTR_ERR(pci->dbi_base2); - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space"); - if (!res) - return -EINVAL; - - ep->phys_base = res->start; - ep->addr_size = resource_size(res); - ret = dw_pcie_ep_init(ep); if (ret) { dev_err(dev, "failed to initialize endpoint\n"); return ret; } + ret = dw_pcie_ep_init_registers(ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(ep); + return ret; + } + + pci_epc_init_notify(ep->epc); + return 0; } -static int __init dra7xx_add_pcie_port(struct dra7xx_pcie *dra7xx, - struct platform_device *pdev) +static int dra7xx_add_pcie_port(struct dra7xx_pcie *dra7xx, + struct platform_device *pdev) { int ret; struct dw_pcie *pci = dra7xx->pci; - struct pcie_port *pp = &pci->pp; + struct dw_pcie_rp *pp = &pci->pp; struct device *dev = pci->dev; - struct resource *res; pp->irq = platform_get_irq(pdev, 1); - if (pp->irq < 0) { - dev_err(dev, "missing IRQ resource\n"); + if (pp->irq < 0) return pp->irq; - } - ret = devm_request_irq(dev, pp->irq, dra7xx_pcie_msi_irq_handler, - IRQF_SHARED | IRQF_NO_THREAD, - "dra7-pcie-msi", dra7xx); - if (ret) { - dev_err(dev, "failed to request irq\n"); - return ret; - } + /* MSI IRQ is muxed */ + pp->msi_irq[0] = -ENODEV; ret = dra7xx_pcie_init_irq_domain(pp); if (ret < 0) return ret; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rc_dbics"); - pci->dbi_base = devm_ioremap_resource(dev, res); + pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "rc_dbics"); if (IS_ERR(pci->dbi_base)) return PTR_ERR(pci->dbi_base); @@ -499,6 +536,10 @@ static int dra7xx_pcie_enable_phy(struct dra7xx_pcie *dra7xx) int i; for (i = 0; i < phy_count; i++) { + ret = phy_set_mode(dra7xx->phy[i], PHY_MODE_PCIE); + if (ret < 0) + goto err_phy; + ret = phy_init(dra7xx->phy[i]); if (ret < 0) goto err_phy; @@ -529,6 +570,26 @@ static const struct dra7xx_pcie_of_data dra7xx_pcie_ep_of_data = { .mode = DW_PCIE_EP_TYPE, }; +static const struct dra7xx_pcie_of_data dra746_pcie_rc_of_data = { + .b1co_mode_sel_mask = BIT(2), + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra726_pcie_rc_of_data = { + .b1co_mode_sel_mask = GENMASK(3, 2), + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra746_pcie_ep_of_data = { + .b1co_mode_sel_mask = BIT(2), + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra726_pcie_ep_of_data = { + .b1co_mode_sel_mask = GENMASK(3, 2), + .mode = DW_PCIE_EP_TYPE, +}; + static const struct of_device_id of_dra7xx_pcie_match[] = { { .compatible = "ti,dra7-pcie", @@ -538,8 +599,25 @@ static const struct of_device_id of_dra7xx_pcie_match[] = { .compatible = "ti,dra7-pcie-ep", .data = &dra7xx_pcie_ep_of_data, }, + { + .compatible = "ti,dra746-pcie-rc", + .data = &dra746_pcie_rc_of_data, + }, + { + .compatible = "ti,dra726-pcie-rc", + .data = &dra726_pcie_rc_of_data, + }, + { + .compatible = "ti,dra746-pcie-ep", + .data = &dra746_pcie_ep_of_data, + }, + { + .compatible = "ti,dra726-pcie-ep", + .data = &dra726_pcie_ep_of_data, + }, {}, }; +MODULE_DEVICE_TABLE(of, of_dra7xx_pcie_match); /* * dra7xx_pcie_unaligned_memaccess: workaround for AM572x/AM571x Errata i870 @@ -556,34 +634,47 @@ static int dra7xx_pcie_unaligned_memaccess(struct device *dev) { int ret; struct device_node *np = dev->of_node; - struct of_phandle_args args; + unsigned int args[2]; struct regmap *regmap; - regmap = syscon_regmap_lookup_by_phandle(np, - "ti,syscon-unaligned-access"); + regmap = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-unaligned-access", + 2, args); if (IS_ERR(regmap)) { dev_dbg(dev, "can't get ti,syscon-unaligned-access\n"); return -EINVAL; } - ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-unaligned-access", - 2, 0, &args); - if (ret) { - dev_err(dev, "failed to parse ti,syscon-unaligned-access\n"); - return ret; - } - - ret = regmap_update_bits(regmap, args.args[0], args.args[1], - args.args[1]); + ret = regmap_update_bits(regmap, args[0], args[1], args[1]); if (ret) dev_err(dev, "failed to enable unaligned access\n"); - of_node_put(args.np); - return ret; } -static int __init dra7xx_pcie_probe(struct platform_device *pdev) +static int dra7xx_pcie_configure_two_lane(struct device *dev, + u32 b1co_mode_sel_mask) +{ + struct device_node *np = dev->of_node; + struct regmap *pcie_syscon; + unsigned int pcie_reg; + u32 mask; + u32 val; + + pcie_syscon = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-lane-sel", + 1, &pcie_reg); + if (IS_ERR(pcie_syscon)) { + dev_err(dev, "unable to get ti,syscon-lane-sel\n"); + return -EINVAL; + } + + mask = b1co_mode_sel_mask | PCIE_B0_B1_TSYNCEN; + val = PCIE_B1C0_MODE_SEL | PCIE_B0_B1_TSYNCEN; + regmap_update_bits(pcie_syscon, pcie_reg, mask, val); + + return 0; +} + +static int dra7xx_pcie_probe(struct platform_device *pdev) { u32 reg; int ret; @@ -593,23 +684,22 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) struct phy **phy; struct device_link **link; void __iomem *base; - struct resource *res; struct dw_pcie *pci; struct dra7xx_pcie *dra7xx; struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; char name[10]; struct gpio_desc *reset; - const struct of_device_id *match; const struct dra7xx_pcie_of_data *data; enum dw_pcie_device_mode mode; + u32 b1co_mode_sel_mask; - match = of_match_device(of_match_ptr(of_dra7xx_pcie_match), dev); - if (!match) + data = of_device_get_match_data(dev); + if (!data) return -EINVAL; - data = (struct dra7xx_pcie_of_data *)match->data; mode = (enum dw_pcie_device_mode)data->mode; + b1co_mode_sel_mask = data->b1co_mode_sel_mask; dra7xx = devm_kzalloc(dev, sizeof(*dra7xx), GFP_KERNEL); if (!dra7xx) @@ -623,15 +713,12 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) pci->ops = &dw_pcie_ops; irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "missing IRQ resource: %d\n", irq); + if (irq < 0) return irq; - } - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ti_conf"); - base = devm_ioremap_nocache(dev, res->start, resource_size(res)); - if (!base) - return -ENOMEM; + base = devm_platform_ioremap_resource_byname(pdev, "ti_conf"); + if (IS_ERR(base)) + return PTR_ERR(base); phy_count = of_property_count_strings(np, "phy-names"); if (phy_count < 0) { @@ -647,6 +734,15 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) if (!link) return -ENOMEM; + dra7xx->clk = devm_clk_get_optional(dev, NULL); + if (IS_ERR(dra7xx->clk)) + return dev_err_probe(dev, PTR_ERR(dra7xx->clk), + "clock request failed"); + + ret = clk_prepare_enable(dra7xx->clk); + if (ret) + return ret; + for (i = 0; i < phy_count; i++) { snprintf(name, sizeof(name), "pcie-phy%d", i); phy[i] = devm_phy_get(dev, name); @@ -665,6 +761,12 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) dra7xx->pci = pci; dra7xx->phy_count = phy_count; + if (phy_count == 2) { + ret = dra7xx_pcie_configure_two_lane(dev, b1co_mode_sel_mask); + if (ret < 0) + dra7xx->phy_count = 1; /* Fallback to x1 lane mode */ + } + ret = dra7xx_pcie_enable_phy(dra7xx); if (ret) { dev_err(dev, "failed to enable phy\n"); @@ -691,10 +793,6 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) reg &= ~LTSSM_EN; dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg); - dra7xx->link_gen = of_pci_get_max_link_speed(np); - if (dra7xx->link_gen < 0 || dra7xx->link_gen > 2) - dra7xx->link_gen = 2; - switch (mode) { case DW_PCIE_RC_TYPE: if (!IS_ENABLED(CONFIG_PCI_DRA7XX_HOST)) { @@ -735,19 +833,25 @@ static int __init dra7xx_pcie_probe(struct platform_device *pdev) } dra7xx->mode = mode; - ret = devm_request_irq(dev, irq, dra7xx_pcie_irq_handler, - IRQF_SHARED, "dra7xx-pcie-main", dra7xx); + ret = devm_request_threaded_irq(dev, irq, NULL, dra7xx_pcie_irq_handler, + IRQF_SHARED | IRQF_ONESHOT, + "dra7xx-pcie-main", dra7xx); if (ret) { dev_err(dev, "failed to request irq\n"); - goto err_gpio; + goto err_deinit; } return 0; -err_gpio: - pm_runtime_put(dev); +err_deinit: + if (dra7xx->mode == DW_PCIE_RC_TYPE) + dw_pcie_host_deinit(&dra7xx->pci->pp); + else + dw_pcie_ep_deinit(&dra7xx->pci->ep); +err_gpio: err_get_sync: + pm_runtime_put(dev); pm_runtime_disable(dev); dra7xx_pcie_disable_phy(dra7xx); @@ -758,7 +862,6 @@ err_link: return ret; } -#ifdef CONFIG_PM_SLEEP static int dra7xx_pcie_suspend(struct device *dev) { struct dra7xx_pcie *dra7xx = dev_get_drvdata(dev); @@ -815,7 +918,6 @@ static int dra7xx_pcie_resume_noirq(struct device *dev) return 0; } -#endif static void dra7xx_pcie_shutdown(struct platform_device *pdev) { @@ -831,15 +933,18 @@ static void dra7xx_pcie_shutdown(struct platform_device *pdev) pm_runtime_disable(dev); dra7xx_pcie_disable_phy(dra7xx); + + clk_disable_unprepare(dra7xx->clk); } static const struct dev_pm_ops dra7xx_pcie_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(dra7xx_pcie_suspend, dra7xx_pcie_resume) - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(dra7xx_pcie_suspend_noirq, - dra7xx_pcie_resume_noirq) + SYSTEM_SLEEP_PM_OPS(dra7xx_pcie_suspend, dra7xx_pcie_resume) + NOIRQ_SYSTEM_SLEEP_PM_OPS(dra7xx_pcie_suspend_noirq, + dra7xx_pcie_resume_noirq) }; static struct platform_driver dra7xx_pcie_driver = { + .probe = dra7xx_pcie_probe, .driver = { .name = "dra7-pcie", .of_match_table = of_dra7xx_pcie_match, @@ -848,4 +953,8 @@ static struct platform_driver dra7xx_pcie_driver = { }, .shutdown = dra7xx_pcie_shutdown, }; -builtin_platform_driver_probe(dra7xx_pcie_driver, dra7xx_pcie_probe); +module_platform_driver(dra7xx_pcie_driver); + +MODULE_AUTHOR("Kishon Vijay Abraham I <kishon@ti.com>"); +MODULE_DESCRIPTION("PCIe controller driver for TI DRA7xx SoCs"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index cee5f2f590e2..0bb7d4f5d784 100644 --- a/drivers/pci/controller/dwc/pci-exynos.c +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -1,27 +1,25 @@ // SPDX-License-Identifier: GPL-2.0 /* - * PCIe host controller driver for Samsung EXYNOS SoCs + * PCIe host controller driver for Samsung Exynos SoCs * - * Copyright (C) 2013 Samsung Electronics Co., Ltd. - * http://www.samsung.com + * Copyright (C) 2013-2020 Samsung Electronics Co., Ltd. + * https://www.samsung.com * * Author: Jingoo Han <jg1.han@samsung.com> + * Jaehoon Chung <jh80.chung@samsung.com> */ #include <linux/clk.h> #include <linux/delay.h> -#include <linux/gpio.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/init.h> -#include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/phy/phy.h> -#include <linux/resource.h> -#include <linux/signal.h> -#include <linux/types.h> +#include <linux/regulator/consumer.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> #include "pcie-designware.h" @@ -37,128 +35,27 @@ #define PCIE_IRQ_SPECIAL 0x008 #define PCIE_IRQ_EN_PULSE 0x00c #define PCIE_IRQ_EN_LEVEL 0x010 -#define IRQ_MSI_ENABLE BIT(2) #define PCIE_IRQ_EN_SPECIAL 0x014 -#define PCIE_PWR_RESET 0x018 +#define PCIE_SW_WAKE 0x018 +#define PCIE_BUS_EN BIT(1) #define PCIE_CORE_RESET 0x01c #define PCIE_CORE_RESET_ENABLE BIT(0) #define PCIE_STICKY_RESET 0x020 #define PCIE_NONSTICKY_RESET 0x024 #define PCIE_APP_INIT_RESET 0x028 #define PCIE_APP_LTSSM_ENABLE 0x02c -#define PCIE_ELBI_RDLH_LINKUP 0x064 +#define PCIE_ELBI_RDLH_LINKUP 0x074 +#define PCIE_ELBI_XMLH_LINKUP BIT(4) #define PCIE_ELBI_LTSSM_ENABLE 0x1 #define PCIE_ELBI_SLV_AWMISC 0x11c #define PCIE_ELBI_SLV_ARMISC 0x120 #define PCIE_ELBI_SLV_DBI_ENABLE BIT(21) -struct exynos_pcie_mem_res { - void __iomem *elbi_base; /* DT 0th resource: PCIe CTRL */ -}; - -struct exynos_pcie_clk_res { - struct clk *clk; - struct clk *bus_clk; -}; - struct exynos_pcie { - struct dw_pcie *pci; - struct exynos_pcie_mem_res *mem_res; - struct exynos_pcie_clk_res *clk_res; - const struct exynos_pcie_ops *ops; - int reset_gpio; - + struct dw_pcie pci; + struct clk_bulk_data *clks; struct phy *phy; -}; - -struct exynos_pcie_ops { - int (*get_mem_resources)(struct platform_device *pdev, - struct exynos_pcie *ep); - int (*get_clk_resources)(struct exynos_pcie *ep); - int (*init_clk_resources)(struct exynos_pcie *ep); - void (*deinit_clk_resources)(struct exynos_pcie *ep); -}; - -static int exynos5440_pcie_get_mem_resources(struct platform_device *pdev, - struct exynos_pcie *ep) -{ - struct dw_pcie *pci = ep->pci; - struct device *dev = pci->dev; - struct resource *res; - - ep->mem_res = devm_kzalloc(dev, sizeof(*ep->mem_res), GFP_KERNEL); - if (!ep->mem_res) - return -ENOMEM; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ep->mem_res->elbi_base = devm_ioremap_resource(dev, res); - if (IS_ERR(ep->mem_res->elbi_base)) - return PTR_ERR(ep->mem_res->elbi_base); - - return 0; -} - -static int exynos5440_pcie_get_clk_resources(struct exynos_pcie *ep) -{ - struct dw_pcie *pci = ep->pci; - struct device *dev = pci->dev; - - ep->clk_res = devm_kzalloc(dev, sizeof(*ep->clk_res), GFP_KERNEL); - if (!ep->clk_res) - return -ENOMEM; - - ep->clk_res->clk = devm_clk_get(dev, "pcie"); - if (IS_ERR(ep->clk_res->clk)) { - dev_err(dev, "Failed to get pcie rc clock\n"); - return PTR_ERR(ep->clk_res->clk); - } - - ep->clk_res->bus_clk = devm_clk_get(dev, "pcie_bus"); - if (IS_ERR(ep->clk_res->bus_clk)) { - dev_err(dev, "Failed to get pcie bus clock\n"); - return PTR_ERR(ep->clk_res->bus_clk); - } - - return 0; -} - -static int exynos5440_pcie_init_clk_resources(struct exynos_pcie *ep) -{ - struct dw_pcie *pci = ep->pci; - struct device *dev = pci->dev; - int ret; - - ret = clk_prepare_enable(ep->clk_res->clk); - if (ret) { - dev_err(dev, "cannot enable pcie rc clock"); - return ret; - } - - ret = clk_prepare_enable(ep->clk_res->bus_clk); - if (ret) { - dev_err(dev, "cannot enable pcie bus clock"); - goto err_bus_clk; - } - - return 0; - -err_bus_clk: - clk_disable_unprepare(ep->clk_res->clk); - - return ret; -} - -static void exynos5440_pcie_deinit_clk_resources(struct exynos_pcie *ep) -{ - clk_disable_unprepare(ep->clk_res->bus_clk); - clk_disable_unprepare(ep->clk_res->clk); -} - -static const struct exynos_pcie_ops exynos5440_pcie_ops = { - .get_mem_resources = exynos5440_pcie_get_mem_resources, - .get_clk_resources = exynos5440_pcie_get_clk_resources, - .init_clk_resources = exynos5440_pcie_init_clk_resources, - .deinit_clk_resources = exynos5440_pcie_deinit_clk_resources, + struct regulator_bulk_data supplies[2]; }; static void exynos_pcie_writel(void __iomem *base, u32 val, u32 reg) @@ -173,117 +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->mem_res->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->mem_res->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->mem_res->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->mem_res->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->mem_res->elbi_base, PCIE_CORE_RESET); + val = exynos_pcie_readl(pci->elbi_base, PCIE_CORE_RESET); val &= ~PCIE_CORE_RESET_ENABLE; - exynos_pcie_writel(ep->mem_res->elbi_base, val, PCIE_CORE_RESET); - exynos_pcie_writel(ep->mem_res->elbi_base, 0, PCIE_PWR_RESET); - exynos_pcie_writel(ep->mem_res->elbi_base, 0, PCIE_STICKY_RESET); - exynos_pcie_writel(ep->mem_res->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->mem_res->elbi_base, PCIE_CORE_RESET); + val = exynos_pcie_readl(pci->elbi_base, PCIE_CORE_RESET); val |= PCIE_CORE_RESET_ENABLE; - exynos_pcie_writel(ep->mem_res->elbi_base, val, PCIE_CORE_RESET); - exynos_pcie_writel(ep->mem_res->elbi_base, 1, PCIE_STICKY_RESET); - exynos_pcie_writel(ep->mem_res->elbi_base, 1, PCIE_NONSTICKY_RESET); - exynos_pcie_writel(ep->mem_res->elbi_base, 1, PCIE_APP_INIT_RESET); - exynos_pcie_writel(ep->mem_res->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 void exynos_pcie_assert_reset(struct exynos_pcie *ep) +static int exynos_pcie_start_link(struct dw_pcie *pci) { - struct dw_pcie *pci = ep->pci; - struct device *dev = pci->dev; - - if (ep->reset_gpio >= 0) - devm_gpio_request_one(dev, ep->reset_gpio, - GPIOF_OUT_INIT_HIGH, "RESET"); -} - -static int exynos_pcie_establish_link(struct exynos_pcie *ep) -{ - struct dw_pcie *pci = ep->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = pci->dev; - - if (dw_pcie_link_up(pci)) { - dev_err(dev, "Link already up\n"); - return 0; - } - - exynos_pcie_assert_core_reset(ep); - - phy_reset(ep->phy); + u32 val; - exynos_pcie_writel(ep->mem_res->elbi_base, 1, - PCIE_PWR_RESET); - - phy_power_on(ep->phy); - phy_init(ep->phy); - - exynos_pcie_deassert_core_reset(ep); - dw_pcie_setup_rc(pp); - exynos_pcie_assert_reset(ep); + val = exynos_pcie_readl(pci->elbi_base, PCIE_SW_WAKE); + val &= ~PCIE_BUS_EN; + exynos_pcie_writel(pci->elbi_base, val, PCIE_SW_WAKE); /* assert LTSSM enable */ - exynos_pcie_writel(ep->mem_res->elbi_base, PCIE_ELBI_LTSSM_ENABLE, + exynos_pcie_writel(pci->elbi_base, PCIE_ELBI_LTSSM_ENABLE, PCIE_APP_LTSSM_ENABLE); - - /* check if the link is up or not */ - if (!dw_pcie_wait_for_link(pci)) - return 0; - - phy_power_off(ep->phy); - return -ETIMEDOUT; + return 0; } static void exynos_pcie_clear_irq_pulse(struct exynos_pcie *ep) { - u32 val; + struct dw_pcie *pci = &ep->pci; - val = exynos_pcie_readl(ep->mem_res->elbi_base, PCIE_IRQ_PULSE); - exynos_pcie_writel(ep->mem_res->elbi_base, val, PCIE_IRQ_PULSE); -} + u32 val = exynos_pcie_readl(pci->elbi_base, PCIE_IRQ_PULSE); -static void exynos_pcie_enable_irq_pulse(struct exynos_pcie *ep) -{ - u32 val; - - /* enable INTX interrupt */ - val = IRQ_INTA_ASSERT | IRQ_INTB_ASSERT | - IRQ_INTC_ASSERT | IRQ_INTD_ASSERT; - exynos_pcie_writel(ep->mem_res->elbi_base, val, PCIE_IRQ_EN_PULSE); + exynos_pcie_writel(pci->elbi_base, val, PCIE_IRQ_PULSE); } static irqreturn_t exynos_pcie_irq_handler(int irq, void *arg) @@ -294,26 +152,16 @@ static irqreturn_t exynos_pcie_irq_handler(int irq, void *arg) return IRQ_HANDLED; } -static void exynos_pcie_msi_init(struct exynos_pcie *ep) +static void exynos_pcie_enable_irq_pulse(struct exynos_pcie *ep) { - struct dw_pcie *pci = ep->pci; - struct pcie_port *pp = &pci->pp; - u32 val; - - dw_pcie_msi_init(pp); + struct dw_pcie *pci = &ep->pci; - /* enable MSI interrupt */ - val = exynos_pcie_readl(ep->mem_res->elbi_base, PCIE_IRQ_EN_LEVEL); - val |= IRQ_MSI_ENABLE; - exynos_pcie_writel(ep->mem_res->elbi_base, val, PCIE_IRQ_EN_LEVEL); -} - -static void exynos_pcie_enable_interrupts(struct exynos_pcie *ep) -{ - exynos_pcie_enable_irq_pulse(ep); + u32 val = IRQ_INTA_ASSERT | IRQ_INTB_ASSERT | + IRQ_INTC_ASSERT | IRQ_INTD_ASSERT; - if (IS_ENABLED(CONFIG_PCI_MSI)) - exynos_pcie_msi_init(ep); + 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, @@ -338,90 +186,85 @@ static void exynos_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, exynos_pcie_sideband_dbi_w_mode(ep, false); } -static int exynos_pcie_rd_own_conf(struct pcie_port *pp, int where, int size, - u32 *val) +static int exynos_pcie_rd_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct exynos_pcie *ep = to_exynos_pcie(pci); - int ret; + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); - exynos_pcie_sideband_dbi_r_mode(ep, true); - ret = dw_pcie_read(pci->dbi_base + where, size, val); - exynos_pcie_sideband_dbi_r_mode(ep, false); - return ret; + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + *val = dw_pcie_read_dbi(pci, where, size); + return PCIBIOS_SUCCESSFUL; } -static int exynos_pcie_wr_own_conf(struct pcie_port *pp, int where, int size, - u32 val) +static int exynos_pcie_wr_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct exynos_pcie *ep = to_exynos_pcie(pci); - int ret; + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); - exynos_pcie_sideband_dbi_w_mode(ep, true); - ret = dw_pcie_write(pci->dbi_base + where, size, val); - exynos_pcie_sideband_dbi_w_mode(ep, false); - return ret; + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + dw_pcie_write_dbi(pci, where, size, val); + return PCIBIOS_SUCCESSFUL; } -static int exynos_pcie_link_up(struct dw_pcie *pci) -{ - struct exynos_pcie *ep = to_exynos_pcie(pci); - u32 val; +static struct pci_ops exynos_pci_ops = { + .read = exynos_pcie_rd_own_conf, + .write = exynos_pcie_wr_own_conf, +}; - val = exynos_pcie_readl(ep->mem_res->elbi_base, PCIE_ELBI_RDLH_LINKUP); - if (val == PCIE_ELBI_LTSSM_ENABLE) - return 1; +static bool exynos_pcie_link_up(struct dw_pcie *pci) +{ + u32 val = exynos_pcie_readl(pci->elbi_base, PCIE_ELBI_RDLH_LINKUP); - return 0; + return val & PCIE_ELBI_XMLH_LINKUP; } -static int exynos_pcie_host_init(struct pcie_port *pp) +static int exynos_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct exynos_pcie *ep = to_exynos_pcie(pci); - exynos_pcie_establish_link(ep); - exynos_pcie_enable_interrupts(ep); + pp->bridge->ops = &exynos_pci_ops; + + exynos_pcie_assert_core_reset(ep); + + phy_init(ep->phy); + phy_power_on(ep->phy); + + exynos_pcie_deassert_core_reset(ep); + exynos_pcie_enable_irq_pulse(ep); return 0; } static const struct dw_pcie_host_ops exynos_pcie_host_ops = { - .rd_own_conf = exynos_pcie_rd_own_conf, - .wr_own_conf = exynos_pcie_wr_own_conf, - .host_init = exynos_pcie_host_init, + .init = exynos_pcie_host_init, }; -static int __init exynos_add_pcie_port(struct exynos_pcie *ep, +static int exynos_add_pcie_port(struct exynos_pcie *ep, struct platform_device *pdev) { - struct dw_pcie *pci = ep->pci; - struct pcie_port *pp = &pci->pp; + struct dw_pcie *pci = &ep->pci; + struct dw_pcie_rp *pp = &pci->pp; struct device *dev = &pdev->dev; int ret; - pp->irq = platform_get_irq(pdev, 1); - if (pp->irq < 0) { - dev_err(dev, "failed to get irq\n"); + pp->irq = platform_get_irq(pdev, 0); + if (pp->irq < 0) return pp->irq; - } + ret = devm_request_irq(dev, pp->irq, exynos_pcie_irq_handler, - IRQF_SHARED, "exynos-pcie", ep); + IRQF_SHARED, "exynos-pcie", ep); if (ret) { dev_err(dev, "failed to request irq\n"); return ret; } - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq(pdev, 0); - if (pp->msi_irq < 0) { - dev_err(dev, "failed to get msi irq\n"); - return pp->msi_irq; - } - } - pp->ops = &exynos_pcie_host_ops; + pp->msi_irq[0] = -ENODEV; ret = dw_pcie_host_init(pp); if (ret) { @@ -436,12 +279,12 @@ static const struct dw_pcie_ops dw_pcie_ops = { .read_dbi = exynos_pcie_read_dbi, .write_dbi = exynos_pcie_write_dbi, .link_up = exynos_pcie_link_up, + .start_link = exynos_pcie_start_link, }; -static int __init exynos_pcie_probe(struct platform_device *pdev) +static int exynos_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct dw_pcie *pci; struct exynos_pcie *ep; struct device_node *np = dev->of_node; int ret; @@ -450,42 +293,27 @@ static int __init exynos_pcie_probe(struct platform_device *pdev) if (!ep) return -ENOMEM; - pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); - if (!pci) - return -ENOMEM; - - pci->dev = dev; - pci->ops = &dw_pcie_ops; - - ep->pci = pci; - ep->ops = (const struct exynos_pcie_ops *) - of_device_get_match_data(dev); - - ep->reset_gpio = of_get_named_gpio(np, "reset-gpio", 0); + ep->pci.dev = dev; + ep->pci.ops = &dw_pcie_ops; ep->phy = devm_of_phy_get(dev, np, NULL); - if (IS_ERR(ep->phy)) { - if (PTR_ERR(ep->phy) == -EPROBE_DEFER) - return PTR_ERR(ep->phy); + if (IS_ERR(ep->phy)) + return PTR_ERR(ep->phy); - ep->phy = NULL; - } + ret = devm_clk_bulk_get_all_enabled(dev, &ep->clks); + if (ret < 0) + return ret; - if (ep->ops && ep->ops->get_mem_resources) { - ret = ep->ops->get_mem_resources(pdev, ep); - if (ret) - return ret; - } + ep->supplies[0].supply = "vdd18"; + ep->supplies[1].supply = "vdd10"; + ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ep->supplies), + ep->supplies); + if (ret) + return ret; - if (ep->ops && ep->ops->get_clk_resources && - ep->ops->init_clk_resources) { - ret = ep->ops->get_clk_resources(ep); - if (ret) - return ret; - ret = ep->ops->init_clk_resources(ep); - if (ret) - return ret; - } + ret = regulator_bulk_enable(ARRAY_SIZE(ep->supplies), ep->supplies); + if (ret) + return ret; platform_set_drvdata(pdev, ep); @@ -497,42 +325,72 @@ static int __init exynos_pcie_probe(struct platform_device *pdev) fail_probe: phy_exit(ep->phy); + regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies); - if (ep->ops && ep->ops->deinit_clk_resources) - ep->ops->deinit_clk_resources(ep); return ret; } -static int __exit exynos_pcie_remove(struct platform_device *pdev) +static void exynos_pcie_remove(struct platform_device *pdev) { struct exynos_pcie *ep = platform_get_drvdata(pdev); - if (ep->ops && ep->ops->deinit_clk_resources) - ep->ops->deinit_clk_resources(ep); + dw_pcie_host_deinit(&ep->pci.pp); + exynos_pcie_assert_core_reset(ep); + phy_power_off(ep->phy); + phy_exit(ep->phy); + regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies); +} + +static int exynos_pcie_suspend_noirq(struct device *dev) +{ + struct exynos_pcie *ep = dev_get_drvdata(dev); + + exynos_pcie_assert_core_reset(ep); + phy_power_off(ep->phy); + phy_exit(ep->phy); + regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies); return 0; } +static int exynos_pcie_resume_noirq(struct device *dev) +{ + struct exynos_pcie *ep = dev_get_drvdata(dev); + struct dw_pcie *pci = &ep->pci; + struct dw_pcie_rp *pp = &pci->pp; + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(ep->supplies), ep->supplies); + if (ret) + return ret; + + /* exynos_pcie_host_init controls ep->phy */ + exynos_pcie_host_init(pp); + dw_pcie_setup_rc(pp); + exynos_pcie_start_link(pci); + return dw_pcie_wait_for_link(pci); +} + +static const struct dev_pm_ops exynos_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(exynos_pcie_suspend_noirq, + exynos_pcie_resume_noirq) +}; + static const struct of_device_id exynos_pcie_of_match[] = { - { - .compatible = "samsung,exynos5440-pcie", - .data = &exynos5440_pcie_ops - }, - {}, + { .compatible = "samsung,exynos5433-pcie", }, + { }, }; static struct platform_driver exynos_pcie_driver = { - .remove = __exit_p(exynos_pcie_remove), + .probe = exynos_pcie_probe, + .remove = exynos_pcie_remove, .driver = { .name = "exynos-pcie", .of_match_table = exynos_pcie_of_match, + .pm = &exynos_pcie_pm_ops, }, }; - -/* Exynos PCIe driver does not allow module unload */ - -static int __init exynos_pcie_init(void) -{ - return platform_driver_probe(&exynos_pcie_driver, exynos_pcie_probe); -} -subsys_initcall(exynos_pcie_init); +module_platform_driver(exynos_pcie_driver); +MODULE_DESCRIPTION("Samsung Exynos PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); +MODULE_DEVICE_TABLE(of, exynos_pcie_of_match); diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 52e47dac028f..4668fc9648bf 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -3,21 +3,22 @@ * PCIe host controller driver for Freescale i.MX6 SoCs * * Copyright (C) 2013 Kosagi - * http://www.kosagi.com + * https://www.kosagi.com * * Author: Sean Cross <xobs@kosagi.com> */ +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/delay.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/kernel.h> #include <linux/mfd/syscon.h> #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> #include <linux/mfd/syscon/imx7-iomuxc-gpr.h> #include <linux/module.h> -#include <linux/of_gpio.h> -#include <linux/of_device.h> +#include <linux/of.h> +#include <linux/of_address.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/regmap.h> @@ -27,110 +28,284 @@ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/reset.h> +#include <linux/phy/pcie.h> +#include <linux/phy/phy.h> #include <linux/pm_domain.h> #include <linux/pm_runtime.h> +#include "../../pci.h" #include "pcie-designware.h" -#define to_imx6_pcie(x) dev_get_drvdata((x)->dev) +#define IMX8MQ_GPR_PCIE_REF_USE_PAD BIT(9) +#define IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN BIT(10) +#define IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE BIT(11) +#define IMX8MQ_GPR_PCIE_VREG_BYPASS BIT(12) +#define IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE GENMASK(11, 8) -enum imx6_pcie_variants { +#define IMX95_PCIE_PHY_GEN_CTRL 0x0 +#define IMX95_PCIE_REF_USE_PAD BIT(17) + +#define IMX95_PCIE_PHY_MPLLA_CTRL 0x10 +#define IMX95_PCIE_PHY_MPLL_STATE BIT(30) + +#define IMX95_PCIE_SS_RW_REG_0 0xf0 +#define IMX95_PCIE_REF_CLKEN BIT(23) +#define IMX95_PCIE_PHY_CR_PARA_SEL BIT(9) +#define IMX95_PCIE_SS_RW_REG_1 0xf4 +#define IMX95_PCIE_SYS_AUX_PWR_DET BIT(31) + +#define IMX95_PE0_GEN_CTRL_1 0x1050 +#define IMX95_PCIE_DEVICE_TYPE GENMASK(3, 0) + +#define IMX95_PE0_GEN_CTRL_3 0x1058 +#define IMX95_PCIE_LTSSM_EN BIT(0) + +#define IMX95_PE0_LUT_ACSCTRL 0x1008 +#define IMX95_PEO_LUT_RWA BIT(16) +#define IMX95_PE0_LUT_ENLOC GENMASK(4, 0) + +#define IMX95_PE0_LUT_DATA1 0x100c +#define IMX95_PE0_LUT_VLD BIT(31) +#define IMX95_PE0_LUT_DAC_ID GENMASK(10, 8) +#define IMX95_PE0_LUT_STREAM_ID GENMASK(5, 0) + +#define IMX95_PE0_LUT_DATA2 0x1010 +#define IMX95_PE0_LUT_REQID GENMASK(31, 16) +#define IMX95_PE0_LUT_MASK GENMASK(15, 0) + +#define IMX95_SID_MASK GENMASK(5, 0) +#define IMX95_MAX_LUT 32 + +#define IMX95_PCIE_RST_CTRL 0x3010 +#define IMX95_PCIE_COLD_RST BIT(0) + +#define to_imx_pcie(x) dev_get_drvdata((x)->dev) + +enum imx_pcie_variants { IMX6Q, IMX6SX, IMX6QP, IMX7D, + IMX8MQ, + IMX8MM, + IMX8MP, + IMX8Q, + IMX95, + IMX8MQ_EP, + IMX8MM_EP, + IMX8MP_EP, + IMX8Q_EP, + IMX95_EP, +}; + +#define IMX_PCIE_FLAG_IMX_PHY BIT(0) +#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) +#define IMX_PCIE_FLAG_HAS_PHY_RESET BIT(5) +#define IMX_PCIE_FLAG_HAS_SERDES BIT(6) +#define IMX_PCIE_FLAG_SUPPORT_64BIT BIT(7) +#define IMX_PCIE_FLAG_CPU_ADDR_FIXUP BIT(8) +/* + * Because of ERR005723 (PCIe does not support L2 power down) we need to + * workaround suspend resume on some devices which are affected by this errata. + */ +#define IMX_PCIE_FLAG_BROKEN_SUSPEND BIT(9) +#define IMX_PCIE_FLAG_HAS_LUT BIT(10) +#define IMX_PCIE_FLAG_8GT_ECN_ERR051586 BIT(11) + +#define imx_check_flag(pci, val) (pci->drvdata->flags & val) + +#define IMX_PCIE_MAX_INSTANCES 2 + +struct imx_pcie; + +struct imx_pcie_drvdata { + enum imx_pcie_variants variant; + enum dw_pcie_device_mode mode; + u32 flags; + int dbi_length; + const char *gpr; + const u32 ltssm_off; + const u32 ltssm_mask; + const u32 mode_off[IMX_PCIE_MAX_INSTANCES]; + const u32 mode_mask[IMX_PCIE_MAX_INSTANCES]; + const struct pci_epc_features *epc_features; + int (*init_phy)(struct imx_pcie *pcie); + int (*enable_ref_clk)(struct imx_pcie *pcie, bool enable); + int (*core_reset)(struct imx_pcie *pcie, bool assert); + int (*wait_pll_lock)(struct imx_pcie *pcie); + const struct dw_pcie_host_ops *ops; +}; + +struct imx_lut_data { + u32 data1; + u32 data2; }; -struct imx6_pcie { +struct imx_pcie { struct dw_pcie *pci; - int reset_gpio; - bool gpio_active_high; - struct clk *pcie_bus; - struct clk *pcie_phy; - struct clk *pcie_inbound_axi; - struct clk *pcie; + struct gpio_desc *reset_gpiod; + struct clk_bulk_data *clks; + int num_clks; struct regmap *iomuxc_gpr; + u16 msi_ctrl; + u32 controller_id; struct reset_control *pciephy_reset; struct reset_control *apps_reset; - struct reset_control *turnoff_reset; - enum imx6_pcie_variants variant; u32 tx_deemph_gen1; u32 tx_deemph_gen2_3p5db; u32 tx_deemph_gen2_6db; u32 tx_swing_full; u32 tx_swing_low; - int link_gen; struct regulator *vpcie; + struct regulator *vph; + void __iomem *phy_base; + /* LUT data for pcie */ + struct imx_lut_data luts[IMX95_MAX_LUT]; /* power domain for pcie */ struct device *pd_pcie; /* power domain for pcie phy */ struct device *pd_pcie_phy; + struct phy *phy; + const struct imx_pcie_drvdata *drvdata; + + /* Ensure that only one device's LUT is configured at any given time */ + struct mutex lock; }; /* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */ -#define PHY_PLL_LOCK_WAIT_MAX_RETRIES 2000 -#define PHY_PLL_LOCK_WAIT_USLEEP_MIN 50 #define PHY_PLL_LOCK_WAIT_USLEEP_MAX 200 - -/* PCIe Root Complex registers (memory-mapped) */ -#define PCIE_RC_IMX6_MSI_CAP 0x50 -#define PCIE_RC_LCR 0x7c -#define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN1 0x1 -#define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2 0x2 -#define PCIE_RC_LCR_MAX_LINK_SPEEDS_MASK 0xf - -#define PCIE_RC_LCSR 0x80 +#define PHY_PLL_LOCK_WAIT_TIMEOUT (2000 * PHY_PLL_LOCK_WAIT_USLEEP_MAX) /* PCIe Port Logic registers (memory-mapped) */ #define PL_OFFSET 0x700 -#define PCIE_PL_PFLR (PL_OFFSET + 0x08) -#define PCIE_PL_PFLR_LINK_STATE_MASK (0x3f << 16) -#define PCIE_PL_PFLR_FORCE_LINK (1 << 15) -#define PCIE_PHY_DEBUG_R0 (PL_OFFSET + 0x28) -#define PCIE_PHY_DEBUG_R1 (PL_OFFSET + 0x2c) #define PCIE_PHY_CTRL (PL_OFFSET + 0x114) -#define PCIE_PHY_CTRL_DATA_LOC 0 -#define PCIE_PHY_CTRL_CAP_ADR_LOC 16 -#define PCIE_PHY_CTRL_CAP_DAT_LOC 17 -#define PCIE_PHY_CTRL_WR_LOC 18 -#define PCIE_PHY_CTRL_RD_LOC 19 +#define PCIE_PHY_CTRL_DATA(x) FIELD_PREP(GENMASK(15, 0), (x)) +#define PCIE_PHY_CTRL_CAP_ADR BIT(16) +#define PCIE_PHY_CTRL_CAP_DAT BIT(17) +#define PCIE_PHY_CTRL_WR BIT(18) +#define PCIE_PHY_CTRL_RD BIT(19) #define PCIE_PHY_STAT (PL_OFFSET + 0x110) -#define PCIE_PHY_STAT_ACK_LOC 16 - -#define PCIE_LINK_WIDTH_SPEED_CONTROL 0x80C -#define PORT_LOGIC_SPEED_CHANGE (0x1 << 17) +#define PCIE_PHY_STAT_ACK BIT(16) /* PHY registers (not memory-mapped) */ #define PCIE_PHY_ATEOVRD 0x10 -#define PCIE_PHY_ATEOVRD_EN (0x1 << 2) +#define PCIE_PHY_ATEOVRD_EN BIT(2) #define PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT 0 #define PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK 0x1 #define PCIE_PHY_MPLL_OVRD_IN_LO 0x11 #define PCIE_PHY_MPLL_MULTIPLIER_SHIFT 2 #define PCIE_PHY_MPLL_MULTIPLIER_MASK 0x7f -#define PCIE_PHY_MPLL_MULTIPLIER_OVRD (0x1 << 9) +#define PCIE_PHY_MPLL_MULTIPLIER_OVRD BIT(9) #define PCIE_PHY_RX_ASIC_OUT 0x100D #define PCIE_PHY_RX_ASIC_OUT_VALID (1 << 0) +/* iMX7 PCIe PHY registers */ +#define PCIE_PHY_CMN_REG4 0x14 +/* These are probably the bits that *aren't* DCC_FB_EN */ +#define PCIE_PHY_CMN_REG4_DCC_FB_EN 0x29 + +#define PCIE_PHY_CMN_REG15 0x54 +#define PCIE_PHY_CMN_REG15_DLY_4 BIT(2) +#define PCIE_PHY_CMN_REG15_PLL_PD BIT(5) +#define PCIE_PHY_CMN_REG15_OVRD_PLL_PD BIT(7) + +#define PCIE_PHY_CMN_REG24 0x90 +#define PCIE_PHY_CMN_REG24_RX_EQ BIT(6) +#define PCIE_PHY_CMN_REG24_RX_EQ_SEL BIT(3) + +#define PCIE_PHY_CMN_REG26 0x98 +#define PCIE_PHY_CMN_REG26_ATT_MODE 0xBC + #define PHY_RX_OVRD_IN_LO 0x1005 -#define PHY_RX_OVRD_IN_LO_RX_DATA_EN (1 << 5) -#define PHY_RX_OVRD_IN_LO_RX_PLL_EN (1 << 3) +#define PHY_RX_OVRD_IN_LO_RX_DATA_EN BIT(5) +#define PHY_RX_OVRD_IN_LO_RX_PLL_EN BIT(3) -static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, int exp_val) +static unsigned int imx_pcie_grp_offset(const struct imx_pcie *imx_pcie) { - struct dw_pcie *pci = imx6_pcie->pci; - u32 val; + WARN_ON(imx_pcie->drvdata->variant != IMX8MQ && + imx_pcie->drvdata->variant != IMX8MQ_EP && + imx_pcie->drvdata->variant != IMX8MM && + imx_pcie->drvdata->variant != IMX8MM_EP && + imx_pcie->drvdata->variant != IMX8MP && + imx_pcie->drvdata->variant != IMX8MP_EP); + return imx_pcie->controller_id == 1 ? IOMUXC_GPR16 : IOMUXC_GPR14; +} + +static int imx95_pcie_init_phy(struct imx_pcie *imx_pcie) +{ + /* + * ERR051624: The Controller Without Vaux Cannot Exit L23 Ready + * Through Beacon or PERST# De-assertion + * + * When the auxiliary power is not available, the controller + * cannot exit from L23 Ready with beacon or PERST# de-assertion + * when main power is not removed. + * + * Workaround: Set SS_RW_REG_1[SYS_AUX_PWR_DET] to 1. + */ + regmap_set_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_1, + IMX95_PCIE_SYS_AUX_PWR_DET); + + regmap_update_bits(imx_pcie->iomuxc_gpr, + IMX95_PCIE_SS_RW_REG_0, + IMX95_PCIE_PHY_CR_PARA_SEL, + 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, + IMX95_PCIE_REF_CLKEN, + IMX95_PCIE_REF_CLKEN); + + return 0; +} + +static void imx_pcie_configure_type(struct imx_pcie *imx_pcie) +{ + const struct imx_pcie_drvdata *drvdata = imx_pcie->drvdata; + unsigned int mask, val, mode, id; + + if (drvdata->mode == DW_PCIE_EP_TYPE) + mode = PCI_EXP_TYPE_ENDPOINT; + else + mode = PCI_EXP_TYPE_ROOT_PORT; + + id = imx_pcie->controller_id; + + /* If mode_mask is 0, generic PHY driver is used to set the mode */ + if (!drvdata->mode_mask[0]) + return; + + /* If mode_mask[id] is 0, each controller has its individual GPR */ + if (!drvdata->mode_mask[id]) + id = 0; + + mask = drvdata->mode_mask[id]; + val = mode << (ffs(mask) - 1); + + regmap_update_bits(imx_pcie->iomuxc_gpr, drvdata->mode_off[id], mask, val); +} + +static int pcie_phy_poll_ack(struct imx_pcie *imx_pcie, bool exp_val) +{ + struct dw_pcie *pci = imx_pcie->pci; + bool val; u32 max_iterations = 10; u32 wait_counter = 0; do { - val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT); - val = (val >> PCIE_PHY_STAT_ACK_LOC) & 0x1; + val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT) & + PCIE_PHY_STAT_ACK; wait_counter++; if (val == exp_val) @@ -142,103 +317,102 @@ static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, int exp_val) return -ETIMEDOUT; } -static int pcie_phy_wait_ack(struct imx6_pcie *imx6_pcie, int addr) +static int pcie_phy_wait_ack(struct imx_pcie *imx_pcie, int addr) { - struct dw_pcie *pci = imx6_pcie->pci; + struct dw_pcie *pci = imx_pcie->pci; u32 val; int ret; - val = addr << PCIE_PHY_CTRL_DATA_LOC; + val = PCIE_PHY_CTRL_DATA(addr); dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val); - val |= (0x1 << PCIE_PHY_CTRL_CAP_ADR_LOC); + val |= PCIE_PHY_CTRL_CAP_ADR; dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val); - ret = pcie_phy_poll_ack(imx6_pcie, 1); + ret = pcie_phy_poll_ack(imx_pcie, true); if (ret) return ret; - val = addr << PCIE_PHY_CTRL_DATA_LOC; + val = PCIE_PHY_CTRL_DATA(addr); dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val); - return pcie_phy_poll_ack(imx6_pcie, 0); + return pcie_phy_poll_ack(imx_pcie, false); } /* Read from the 16-bit PCIe PHY control registers (not memory-mapped) */ -static int pcie_phy_read(struct imx6_pcie *imx6_pcie, int addr, int *data) +static int pcie_phy_read(struct imx_pcie *imx_pcie, int addr, u16 *data) { - struct dw_pcie *pci = imx6_pcie->pci; - u32 val, phy_ctl; + struct dw_pcie *pci = imx_pcie->pci; + u32 phy_ctl; int ret; - ret = pcie_phy_wait_ack(imx6_pcie, addr); + ret = pcie_phy_wait_ack(imx_pcie, addr); if (ret) return ret; /* assert Read signal */ - phy_ctl = 0x1 << PCIE_PHY_CTRL_RD_LOC; + phy_ctl = PCIE_PHY_CTRL_RD; dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, phy_ctl); - ret = pcie_phy_poll_ack(imx6_pcie, 1); + ret = pcie_phy_poll_ack(imx_pcie, true); if (ret) return ret; - val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT); - *data = val & 0xffff; + *data = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT); /* deassert Read signal */ dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, 0x00); - return pcie_phy_poll_ack(imx6_pcie, 0); + return pcie_phy_poll_ack(imx_pcie, false); } -static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, int data) +static int pcie_phy_write(struct imx_pcie *imx_pcie, int addr, u16 data) { - struct dw_pcie *pci = imx6_pcie->pci; + struct dw_pcie *pci = imx_pcie->pci; u32 var; int ret; /* write addr */ /* cap addr */ - ret = pcie_phy_wait_ack(imx6_pcie, addr); + ret = pcie_phy_wait_ack(imx_pcie, addr); if (ret) return ret; - var = data << PCIE_PHY_CTRL_DATA_LOC; + var = PCIE_PHY_CTRL_DATA(data); dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); /* capture data */ - var |= (0x1 << PCIE_PHY_CTRL_CAP_DAT_LOC); + var |= PCIE_PHY_CTRL_CAP_DAT; dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); - ret = pcie_phy_poll_ack(imx6_pcie, 1); + ret = pcie_phy_poll_ack(imx_pcie, true); if (ret) return ret; /* deassert cap data */ - var = data << PCIE_PHY_CTRL_DATA_LOC; + var = PCIE_PHY_CTRL_DATA(data); dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); /* wait for ack de-assertion */ - ret = pcie_phy_poll_ack(imx6_pcie, 0); + ret = pcie_phy_poll_ack(imx_pcie, false); if (ret) return ret; /* assert wr signal */ - var = 0x1 << PCIE_PHY_CTRL_WR_LOC; + var = PCIE_PHY_CTRL_WR; dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); /* wait for ack */ - ret = pcie_phy_poll_ack(imx6_pcie, 1); + ret = pcie_phy_poll_ack(imx_pcie, true); if (ret) return ret; /* deassert wr signal */ - var = data << PCIE_PHY_CTRL_DATA_LOC; + var = PCIE_PHY_CTRL_DATA(data); dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); /* wait for ack de-assertion */ - ret = pcie_phy_poll_ack(imx6_pcie, 0); + ret = pcie_phy_poll_ack(imx_pcie, false); if (ret) return ret; @@ -247,23 +421,166 @@ static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, int data) return 0; } -static void imx6_pcie_reset_phy(struct imx6_pcie *imx6_pcie) +static int imx8mq_pcie_init_phy(struct imx_pcie *imx_pcie) { - u32 tmp; + /* TODO: This code assumes external oscillator is being used */ + regmap_update_bits(imx_pcie->iomuxc_gpr, + imx_pcie_grp_offset(imx_pcie), + IMX8MQ_GPR_PCIE_REF_USE_PAD, + IMX8MQ_GPR_PCIE_REF_USE_PAD); + /* + * Per the datasheet, the PCIE_VPH is suggested to be 1.8V. If the + * PCIE_VPH is supplied by 3.3V, the VREG_BYPASS should be cleared + * to zero. + */ + if (imx_pcie->vph && regulator_get_voltage(imx_pcie->vph) > 3000000) + regmap_update_bits(imx_pcie->iomuxc_gpr, + imx_pcie_grp_offset(imx_pcie), + IMX8MQ_GPR_PCIE_VREG_BYPASS, + 0); + + return 0; +} + +static int imx_pcie_init_phy(struct imx_pcie *imx_pcie) +{ + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6Q_GPR12_PCIE_CTL_2, 0 << 10); + + /* configure constant input signal to the pcie ctrl and phy */ + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6Q_GPR12_LOS_LEVEL, 9 << 4); + + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_DEEMPH_GEN1, + imx_pcie->tx_deemph_gen1 << 0); + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB, + imx_pcie->tx_deemph_gen2_3p5db << 6); + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB, + imx_pcie->tx_deemph_gen2_6db << 12); + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_SWING_FULL, + imx_pcie->tx_swing_full << 18); + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_SWING_LOW, + imx_pcie->tx_swing_low << 25); + return 0; +} + +static int imx6sx_pcie_init_phy(struct imx_pcie *imx_pcie) +{ + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_RX_EQ_MASK, IMX6SX_GPR12_PCIE_RX_EQ_2); + + return imx_pcie_init_phy(imx_pcie); +} + +static void imx7d_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, + IOMUXC_GPR22, val, + val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED, + PHY_PLL_LOCK_WAIT_USLEEP_MAX, + PHY_PLL_LOCK_WAIT_TIMEOUT)) + dev_err(dev, "PCIe PLL lock timeout\n"); +} + +static int 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; + } - pcie_phy_read(imx6_pcie, PHY_RX_OVRD_IN_LO, &tmp); + return 0; +} + +static int imx_setup_phy_mpll(struct imx_pcie *imx_pcie) +{ + unsigned long phy_rate = 0; + int mult, div; + u16 val; + int i; + struct clk_bulk_data *clks = imx_pcie->clks; + + if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_IMX_PHY)) + return 0; + + for (i = 0; i < imx_pcie->num_clks; i++) + if (strncmp(clks[i].id, "pcie_phy", 8) == 0) + phy_rate = clk_get_rate(clks[i].clk); + + switch (phy_rate) { + case 125000000: + /* + * The default settings of the MPLL are for a 125MHz input + * clock, so no need to reconfigure anything in that case. + */ + return 0; + case 100000000: + mult = 25; + div = 0; + break; + case 200000000: + mult = 25; + div = 1; + break; + default: + dev_err(imx_pcie->pci->dev, + "Unsupported PHY reference clock rate %lu\n", phy_rate); + return -EINVAL; + } + + pcie_phy_read(imx_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, &val); + val &= ~(PCIE_PHY_MPLL_MULTIPLIER_MASK << + PCIE_PHY_MPLL_MULTIPLIER_SHIFT); + val |= mult << PCIE_PHY_MPLL_MULTIPLIER_SHIFT; + val |= PCIE_PHY_MPLL_MULTIPLIER_OVRD; + pcie_phy_write(imx_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, val); + + pcie_phy_read(imx_pcie, PCIE_PHY_ATEOVRD, &val); + val &= ~(PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK << + PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT); + val |= div << PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT; + val |= PCIE_PHY_ATEOVRD_EN; + pcie_phy_write(imx_pcie, PCIE_PHY_ATEOVRD, val); + + return 0; +} + +static void imx_pcie_reset_phy(struct imx_pcie *imx_pcie) +{ + u16 tmp; + + if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_IMX_PHY)) + return; + + pcie_phy_read(imx_pcie, PHY_RX_OVRD_IN_LO, &tmp); tmp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN | PHY_RX_OVRD_IN_LO_RX_PLL_EN); - pcie_phy_write(imx6_pcie, PHY_RX_OVRD_IN_LO, tmp); + pcie_phy_write(imx_pcie, PHY_RX_OVRD_IN_LO, tmp); usleep_range(2000, 3000); - pcie_phy_read(imx6_pcie, PHY_RX_OVRD_IN_LO, &tmp); + pcie_phy_read(imx_pcie, PHY_RX_OVRD_IN_LO, &tmp); tmp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN | PHY_RX_OVRD_IN_LO_RX_PLL_EN); - pcie_phy_write(imx6_pcie, PHY_RX_OVRD_IN_LO, tmp); + pcie_phy_write(imx_pcie, PHY_RX_OVRD_IN_LO, tmp); } +#ifdef CONFIG_ARM /* Added for PCI abort handling */ static int imx6q_pcie_abort_handler(unsigned long addr, unsigned int fsr, struct pt_regs *regs) @@ -297,333 +614,281 @@ static int imx6q_pcie_abort_handler(unsigned long addr, return 1; } +#endif -static int imx6_pcie_attach_pd(struct device *dev) +static int imx_pcie_attach_pd(struct device *dev) { - struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + struct imx_pcie *imx_pcie = dev_get_drvdata(dev); struct device_link *link; /* Do nothing when in a single power domain */ if (dev->pm_domain) return 0; - imx6_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie"); - if (IS_ERR(imx6_pcie->pd_pcie)) - return PTR_ERR(imx6_pcie->pd_pcie); - link = device_link_add(dev, imx6_pcie->pd_pcie, + imx_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie"); + if (IS_ERR(imx_pcie->pd_pcie)) + return PTR_ERR(imx_pcie->pd_pcie); + /* Do nothing when power domain missing */ + if (!imx_pcie->pd_pcie) + return 0; + link = device_link_add(dev, imx_pcie->pd_pcie, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); if (!link) { - dev_err(dev, "Failed to add device_link to pcie pd.\n"); + dev_err(dev, "Failed to add device_link to pcie pd\n"); return -EINVAL; } - imx6_pcie->pd_pcie_phy = dev_pm_domain_attach_by_name(dev, "pcie_phy"); - if (IS_ERR(imx6_pcie->pd_pcie_phy)) - return PTR_ERR(imx6_pcie->pd_pcie_phy); + imx_pcie->pd_pcie_phy = dev_pm_domain_attach_by_name(dev, "pcie_phy"); + if (IS_ERR(imx_pcie->pd_pcie_phy)) + return PTR_ERR(imx_pcie->pd_pcie_phy); - device_link_add(dev, imx6_pcie->pd_pcie_phy, + link = device_link_add(dev, imx_pcie->pd_pcie_phy, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (IS_ERR(link)) { - dev_err(dev, "Failed to add device_link to pcie_phy pd: %ld\n", PTR_ERR(link)); - return PTR_ERR(link); + if (!link) { + dev_err(dev, "Failed to add device_link to pcie_phy pd\n"); + return -EINVAL; } return 0; } -static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie) +static int imx6sx_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { - struct device *dev = imx6_pcie->pci->dev; - - switch (imx6_pcie->variant) { - case IMX7D: - reset_control_assert(imx6_pcie->pciephy_reset); - reset_control_assert(imx6_pcie->apps_reset); - break; - case IMX6SX: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_TEST_POWERDOWN, - IMX6SX_GPR12_PCIE_TEST_POWERDOWN); - /* Force PCIe PHY reset */ - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5, - IMX6SX_GPR5_PCIE_BTNRST_RESET, - IMX6SX_GPR5_PCIE_BTNRST_RESET); - break; - case IMX6QP: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, - IMX6Q_GPR1_PCIE_SW_RST, - IMX6Q_GPR1_PCIE_SW_RST); - break; - case IMX6Q: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, - IMX6Q_GPR1_PCIE_TEST_PD, 1 << 18); - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, - IMX6Q_GPR1_PCIE_REF_CLK_EN, 0 << 16); - break; - } - - if (imx6_pcie->vpcie && regulator_is_enabled(imx6_pcie->vpcie) > 0) { - int ret = regulator_disable(imx6_pcie->vpcie); - - if (ret) - dev_err(dev, "failed to disable vpcie regulator: %d\n", - ret); - } + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_TEST_POWERDOWN, + enable ? 0 : IMX6SX_GPR12_PCIE_TEST_POWERDOWN); + return 0; } -static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie) +static int imx6q_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { - struct dw_pcie *pci = imx6_pcie->pci; - struct device *dev = pci->dev; - int ret = 0; - - switch (imx6_pcie->variant) { - case IMX6SX: - ret = clk_prepare_enable(imx6_pcie->pcie_inbound_axi); - if (ret) { - dev_err(dev, "unable to enable pcie_axi clock\n"); - break; - } - - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_TEST_POWERDOWN, 0); - break; - case IMX6QP: /* FALLTHROUGH */ - case IMX6Q: + if (enable) { /* power up core phy and enable ref clock */ - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, - IMX6Q_GPR1_PCIE_TEST_PD, 0 << 18); + regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_TEST_PD); /* - * the async reset input need ref clock to sync internally, + * The async reset input need ref clock to sync internally, * when the ref clock comes after reset, internal synced * reset time is too short, cannot meet the requirement. - * add one ~10us delay here. + * Add a ~10us delay here. */ - udelay(10); - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, - IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16); - break; - case IMX7D: - break; + usleep_range(10, 100); + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_REF_CLK_EN); + } else { + regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_REF_CLK_EN); + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_TEST_PD); } - return ret; + return 0; } -static void imx7d_pcie_wait_for_phy_pll_lock(struct imx6_pcie *imx6_pcie) +static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { - u32 val; - unsigned int retries; - struct device *dev = imx6_pcie->pci->dev; - - for (retries = 0; retries < PHY_PLL_LOCK_WAIT_MAX_RETRIES; retries++) { - regmap_read(imx6_pcie->iomuxc_gpr, IOMUXC_GPR22, &val); - - if (val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED) - return; - - usleep_range(PHY_PLL_LOCK_WAIT_USLEEP_MIN, - PHY_PLL_LOCK_WAIT_USLEEP_MAX); - } + int offset = imx_pcie_grp_offset(imx_pcie); + + regmap_update_bits(imx_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE, + enable ? 0 : IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE); + regmap_update_bits(imx_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN, + enable ? IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN : 0); + return 0; +} - dev_err(dev, "PCIe PLL lock timeout\n"); +static int imx7d_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) +{ + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, + enable ? 0 : IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); + return 0; } -static void imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie) +static int imx_pcie_clk_enable(struct imx_pcie *imx_pcie) { - struct dw_pcie *pci = imx6_pcie->pci; + struct dw_pcie *pci = imx_pcie->pci; struct device *dev = pci->dev; int ret; - if (imx6_pcie->vpcie && !regulator_is_enabled(imx6_pcie->vpcie)) { - ret = regulator_enable(imx6_pcie->vpcie); + ret = clk_bulk_prepare_enable(imx_pcie->num_clks, imx_pcie->clks); + if (ret) + return ret; + + if (imx_pcie->drvdata->enable_ref_clk) { + ret = imx_pcie->drvdata->enable_ref_clk(imx_pcie, true); if (ret) { - dev_err(dev, "failed to enable vpcie regulator: %d\n", - ret); - return; + dev_err(dev, "Failed to enable PCIe REFCLK\n"); + goto err_ref_clk; } } - ret = clk_prepare_enable(imx6_pcie->pcie_phy); - if (ret) { - dev_err(dev, "unable to enable pcie_phy clock\n"); - goto err_pcie_phy; - } - - ret = clk_prepare_enable(imx6_pcie->pcie_bus); - if (ret) { - dev_err(dev, "unable to enable pcie_bus clock\n"); - goto err_pcie_bus; - } + /* allow the clocks to stabilize */ + usleep_range(200, 500); + return 0; - ret = clk_prepare_enable(imx6_pcie->pcie); - if (ret) { - dev_err(dev, "unable to enable pcie clock\n"); - goto err_pcie; - } +err_ref_clk: + clk_bulk_disable_unprepare(imx_pcie->num_clks, imx_pcie->clks); - ret = imx6_pcie_enable_ref_clk(imx6_pcie); - if (ret) { - dev_err(dev, "unable to enable pcie ref clock\n"); - goto err_ref_clk; - } + return ret; +} - /* allow the clocks to stabilize */ - usleep_range(200, 500); +static void imx_pcie_clk_disable(struct imx_pcie *imx_pcie) +{ + if (imx_pcie->drvdata->enable_ref_clk) + imx_pcie->drvdata->enable_ref_clk(imx_pcie, false); + clk_bulk_disable_unprepare(imx_pcie->num_clks, imx_pcie->clks); +} - /* Some boards don't have PCIe reset GPIO. */ - if (gpio_is_valid(imx6_pcie->reset_gpio)) { - gpio_set_value_cansleep(imx6_pcie->reset_gpio, - imx6_pcie->gpio_active_high); - msleep(100); - gpio_set_value_cansleep(imx6_pcie->reset_gpio, - !imx6_pcie->gpio_active_high); - } +static int imx6sx_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) +{ + if (assert) + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_TEST_POWERDOWN); - switch (imx6_pcie->variant) { - case IMX7D: - reset_control_deassert(imx6_pcie->pciephy_reset); - imx7d_pcie_wait_for_phy_pll_lock(imx6_pcie); - break; - case IMX6SX: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5, - IMX6SX_GPR5_PCIE_BTNRST_RESET, 0); - break; - case IMX6QP: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, - IMX6Q_GPR1_PCIE_SW_RST, 0); + /* Force PCIe PHY reset */ + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR5, IMX6SX_GPR5_PCIE_BTNRST_RESET, + assert ? IMX6SX_GPR5_PCIE_BTNRST_RESET : 0); + return 0; +} +static int imx6qp_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) +{ + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_SW_RST, + assert ? IMX6Q_GPR1_PCIE_SW_RST : 0); + if (!assert) usleep_range(200, 500); - break; - case IMX6Q: /* Nothing to do */ - break; - } - return; + return 0; +} -err_ref_clk: - clk_disable_unprepare(imx6_pcie->pcie); -err_pcie: - clk_disable_unprepare(imx6_pcie->pcie_bus); -err_pcie_bus: - clk_disable_unprepare(imx6_pcie->pcie_phy); -err_pcie_phy: - if (imx6_pcie->vpcie && regulator_is_enabled(imx6_pcie->vpcie) > 0) { - ret = regulator_disable(imx6_pcie->vpcie); - if (ret) - dev_err(dev, "failed to disable vpcie regulator: %d\n", - ret); - } +static int imx6q_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) +{ + if (!assert) + return 0; + + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_TEST_PD); + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_REF_CLK_EN); + + return 0; } -static void imx6_pcie_init_phy(struct imx6_pcie *imx6_pcie) +static int imx7d_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) { - switch (imx6_pcie->variant) { - case IMX7D: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0); - break; - case IMX6SX: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_RX_EQ_MASK, - IMX6SX_GPR12_PCIE_RX_EQ_2); - /* FALLTHROUGH */ - default: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6Q_GPR12_PCIE_CTL_2, 0 << 10); + struct dw_pcie *pci = imx_pcie->pci; + struct device *dev = pci->dev; - /* configure constant input signal to the pcie ctrl and phy */ - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6Q_GPR12_LOS_LEVEL, 9 << 4); - - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, - IMX6Q_GPR8_TX_DEEMPH_GEN1, - imx6_pcie->tx_deemph_gen1 << 0); - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, - IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB, - imx6_pcie->tx_deemph_gen2_3p5db << 6); - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, - IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB, - imx6_pcie->tx_deemph_gen2_6db << 12); - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, - IMX6Q_GPR8_TX_SWING_FULL, - imx6_pcie->tx_swing_full << 18); - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, - IMX6Q_GPR8_TX_SWING_LOW, - imx6_pcie->tx_swing_low << 25); - break; - } + if (assert) + return 0; + + /* + * Workaround for ERR010728 (IMX7DS_2N09P, Rev. 1.1, 4/2023): + * + * PCIe: PLL may fail to lock under corner conditions. + * + * Initial VCO oscillation may fail under corner conditions such as + * cold temperature which will cause the PCIe PLL fail to lock in the + * initialization phase. + * + * The Duty-cycle Corrector calibration must be disabled. + * + * 1. De-assert the G_RST signal by clearing + * SRC_PCIEPHY_RCR[PCIEPHY_G_RST]. + * 2. De-assert DCC_FB_EN by writing data “0x29” to the register + * address 0x306d0014 (PCIE_PHY_CMN_REG4). + * 3. Assert RX_EQS, RX_EQ_SEL by writing data “0x48” to the register + * address 0x306d0090 (PCIE_PHY_CMN_REG24). + * 4. Assert ATT_MODE by writing data “0xbc” to the register + * address 0x306d0098 (PCIE_PHY_CMN_REG26). + * 5. De-assert the CMN_RST signal by clearing register bit + * SRC_PCIEPHY_RCR[PCIEPHY_BTN] + */ - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6Q_GPR12_DEVICE_TYPE, PCI_EXP_TYPE_ROOT_PORT << 12); + if (likely(imx_pcie->phy_base)) { + /* De-assert DCC_FB_EN */ + writel(PCIE_PHY_CMN_REG4_DCC_FB_EN, imx_pcie->phy_base + PCIE_PHY_CMN_REG4); + /* Assert RX_EQS and RX_EQS_SEL */ + writel(PCIE_PHY_CMN_REG24_RX_EQ_SEL | PCIE_PHY_CMN_REG24_RX_EQ, + imx_pcie->phy_base + PCIE_PHY_CMN_REG24); + /* Assert ATT_MODE */ + writel(PCIE_PHY_CMN_REG26_ATT_MODE, imx_pcie->phy_base + PCIE_PHY_CMN_REG26); + } else { + dev_warn(dev, "Unable to apply ERR010728 workaround. DT missing fsl,imx7d-pcie-phy phandle ?\n"); + } + imx7d_pcie_wait_for_phy_pll_lock(imx_pcie); + return 0; } -static int imx6_setup_phy_mpll(struct imx6_pcie *imx6_pcie) +static int imx95_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) { - unsigned long phy_rate = clk_get_rate(imx6_pcie->pcie_phy); - int mult, div; u32 val; - switch (phy_rate) { - case 125000000: + if (assert) { /* - * The default settings of the MPLL are for a 125MHz input - * clock, so no need to reconfigure anything in that case. + * 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. */ - return 0; - case 100000000: - mult = 25; - div = 0; - break; - case 200000000: - mult = 25; - div = 1; - break; - default: - dev_err(imx6_pcie->pci->dev, - "Unsupported PHY reference clock rate %lu\n", phy_rate); - return -EINVAL; + 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); } - pcie_phy_read(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, &val); - val &= ~(PCIE_PHY_MPLL_MULTIPLIER_MASK << - PCIE_PHY_MPLL_MULTIPLIER_SHIFT); - val |= mult << PCIE_PHY_MPLL_MULTIPLIER_SHIFT; - val |= PCIE_PHY_MPLL_MULTIPLIER_OVRD; - pcie_phy_write(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, val); + return 0; +} - pcie_phy_read(imx6_pcie, PCIE_PHY_ATEOVRD, &val); - val &= ~(PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK << - PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT); - val |= div << PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT; - val |= PCIE_PHY_ATEOVRD_EN; - pcie_phy_write(imx6_pcie, PCIE_PHY_ATEOVRD, val); +static void imx_pcie_assert_core_reset(struct imx_pcie *imx_pcie) +{ + reset_control_assert(imx_pcie->pciephy_reset); - return 0; + if (imx_pcie->drvdata->core_reset) + imx_pcie->drvdata->core_reset(imx_pcie, true); + + /* Some boards don't have PCIe reset GPIO. */ + gpiod_set_value_cansleep(imx_pcie->reset_gpiod, 1); } -static int imx6_pcie_wait_for_link(struct imx6_pcie *imx6_pcie) +static int imx_pcie_deassert_core_reset(struct imx_pcie *imx_pcie) { - struct dw_pcie *pci = imx6_pcie->pci; - struct device *dev = pci->dev; + reset_control_deassert(imx_pcie->pciephy_reset); - /* check if the link is up or not */ - if (!dw_pcie_wait_for_link(pci)) - return 0; + if (imx_pcie->drvdata->core_reset) + imx_pcie->drvdata->core_reset(imx_pcie, false); - dev_dbg(dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n", - dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R0), - dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R1)); - return -ETIMEDOUT; + /* Some boards don't have PCIe reset GPIO. */ + if (imx_pcie->reset_gpiod) { + msleep(100); + gpiod_set_value_cansleep(imx_pcie->reset_gpiod, 0); + /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ + msleep(100); + } + + return 0; } -static int imx6_pcie_wait_for_speed_change(struct imx6_pcie *imx6_pcie) +static int imx_pcie_wait_for_speed_change(struct imx_pcie *imx_pcie) { - struct dw_pcie *pci = imx6_pcie->pci; + struct dw_pcie *pci = imx_pcie->pci; struct device *dev = pci->dev; u32 tmp; unsigned int retries; @@ -637,57 +902,78 @@ static int imx6_pcie_wait_for_speed_change(struct imx6_pcie *imx6_pcie) } dev_err(dev, "Speed change timeout\n"); - return -EINVAL; + return -ETIMEDOUT; } -static void imx6_pcie_ltssm_enable(struct device *dev) +static void imx_pcie_ltssm_enable(struct device *dev) { - struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); - - switch (imx6_pcie->variant) { - case IMX6Q: - case IMX6SX: - case IMX6QP: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6Q_GPR12_PCIE_CTL_2, - IMX6Q_GPR12_PCIE_CTL_2); - break; - case IMX7D: - reset_control_deassert(imx6_pcie->apps_reset); - break; - } + struct imx_pcie *imx_pcie = dev_get_drvdata(dev); + const struct imx_pcie_drvdata *drvdata = imx_pcie->drvdata; + u8 offset = dw_pcie_find_capability(imx_pcie->pci, PCI_CAP_ID_EXP); + u32 tmp; + + tmp = dw_pcie_readl_dbi(imx_pcie->pci, offset + PCI_EXP_LNKCAP); + phy_set_speed(imx_pcie->phy, FIELD_GET(PCI_EXP_LNKCAP_SLS, tmp)); + if (drvdata->ltssm_mask) + regmap_update_bits(imx_pcie->iomuxc_gpr, drvdata->ltssm_off, drvdata->ltssm_mask, + drvdata->ltssm_mask); + + reset_control_deassert(imx_pcie->apps_reset); +} + +static void imx_pcie_ltssm_disable(struct device *dev) +{ + struct imx_pcie *imx_pcie = dev_get_drvdata(dev); + const struct imx_pcie_drvdata *drvdata = imx_pcie->drvdata; + + phy_set_speed(imx_pcie->phy, 0); + if (drvdata->ltssm_mask) + regmap_update_bits(imx_pcie->iomuxc_gpr, drvdata->ltssm_off, + drvdata->ltssm_mask, 0); + + reset_control_assert(imx_pcie->apps_reset); } -static int imx6_pcie_establish_link(struct imx6_pcie *imx6_pcie) +static int imx_pcie_start_link(struct dw_pcie *pci) { - struct dw_pcie *pci = imx6_pcie->pci; + struct imx_pcie *imx_pcie = to_imx_pcie(pci); struct device *dev = pci->dev; + u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); 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 * bus will not be detected at all. This happens with PCIe switches. */ - tmp = dw_pcie_readl_dbi(pci, PCIE_RC_LCR); - tmp &= ~PCIE_RC_LCR_MAX_LINK_SPEEDS_MASK; - tmp |= PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN1; - dw_pcie_writel_dbi(pci, PCIE_RC_LCR, tmp); + dw_pcie_dbi_ro_wr_en(pci); + tmp = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= PCI_EXP_LNKCAP_SLS_2_5GB; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, tmp); + dw_pcie_dbi_ro_wr_dis(pci); /* Start LTSSM. */ - imx6_pcie_ltssm_enable(dev); + imx_pcie_ltssm_enable(dev); - ret = imx6_pcie_wait_for_link(imx6_pcie); - 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; - if (imx6_pcie->link_gen == 2) { - /* Allow Gen2 mode after the link is up. */ - tmp = dw_pcie_readl_dbi(pci, PCIE_RC_LCR); - tmp &= ~PCIE_RC_LCR_MAX_LINK_SPEEDS_MASK; - tmp |= PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2; - dw_pcie_writel_dbi(pci, PCIE_RC_LCR, tmp); + /* Allow faster modes after the link is up */ + dw_pcie_dbi_ro_wr_en(pci); + tmp = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= pci->max_link_speed; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, tmp); /* * Start Directed Speed Change so the best possible @@ -696,233 +982,631 @@ static int imx6_pcie_establish_link(struct imx6_pcie *imx6_pcie) tmp = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); tmp |= PORT_LOGIC_SPEED_CHANGE; dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp); + dw_pcie_dbi_ro_wr_dis(pci); - if (imx6_pcie->variant != IMX7D) { - /* - * On i.MX7, DIRECT_SPEED_CHANGE behaves differently - * from i.MX6 family when no link speed transition - * occurs and we go Gen1 -> yep, Gen1. The difference - * is that, in such case, it will not be cleared by HW - * which will cause the following code to report false - * failure. - */ - - ret = imx6_pcie_wait_for_speed_change(imx6_pcie); - if (ret) { - dev_err(dev, "Failed to bring link up!\n"); - goto err_reset_phy; - } - } - - /* Make sure link training is finished as well! */ - ret = imx6_pcie_wait_for_link(imx6_pcie); + 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: Gen2 disabled\n"); + dev_info(dev, "Link: Only Gen1 is enabled\n"); } - tmp = dw_pcie_readl_dbi(pci, PCIE_RC_LCSR); - dev_info(dev, "Link up, Gen%i\n", (tmp >> 16) & 0xf); return 0; err_reset_phy: dev_dbg(dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n", - dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R0), - dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R1)); - imx6_pcie_reset_phy(imx6_pcie); - return ret; + dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0), + dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1)); + imx_pcie_reset_phy(imx_pcie); + return 0; } -static int imx6_pcie_host_init(struct pcie_port *pp) +static void imx_pcie_stop_link(struct dw_pcie *pci) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci); + struct device *dev = pci->dev; - imx6_pcie_assert_core_reset(imx6_pcie); - imx6_pcie_init_phy(imx6_pcie); - imx6_pcie_deassert_core_reset(imx6_pcie); - imx6_setup_phy_mpll(imx6_pcie); - dw_pcie_setup_rc(pp); - imx6_pcie_establish_link(imx6_pcie); + /* Turn off PCIe LTSSM */ + imx_pcie_ltssm_disable(dev); +} - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(pp); +static int imx_pcie_add_lut(struct imx_pcie *imx_pcie, u16 rid, u8 sid) +{ + struct dw_pcie *pci = imx_pcie->pci; + struct device *dev = pci->dev; + u32 data1, data2; + int free = -1; + int i; + + if (sid >= 64) { + dev_err(dev, "Invalid SID for index %d\n", sid); + return -EINVAL; + } + + guard(mutex)(&imx_pcie->lock); + + /* + * Iterate through all LUT entries to check for duplicate RID and + * identify the first available entry. Configure this available entry + * immediately after verification to avoid rescanning it. + */ + for (i = 0; i < IMX95_MAX_LUT; i++) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, &data1); + + if (!(data1 & IMX95_PE0_LUT_VLD)) { + if (free < 0) + free = i; + continue; + } + + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2); + + /* Do not add duplicate RID */ + if (rid == FIELD_GET(IMX95_PE0_LUT_REQID, data2)) { + dev_warn(dev, "Existing LUT entry available for RID (%d)", rid); + return 0; + } + } + + if (free < 0) { + dev_err(dev, "LUT entry is not available\n"); + return -ENOSPC; + } + + data1 = FIELD_PREP(IMX95_PE0_LUT_DAC_ID, 0); + data1 |= FIELD_PREP(IMX95_PE0_LUT_STREAM_ID, sid); + data1 |= IMX95_PE0_LUT_VLD; + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, data1); + + if (imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE) + data2 = 0x7; /* In the EP mode, only 'Device ID' is required */ + else + data2 = IMX95_PE0_LUT_MASK; /* Match all bits of RID */ + data2 |= FIELD_PREP(IMX95_PE0_LUT_REQID, rid); + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, data2); + + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL, free); return 0; } -static const struct dw_pcie_host_ops imx6_pcie_host_ops = { - .host_init = imx6_pcie_host_init, -}; +static void imx_pcie_remove_lut(struct imx_pcie *imx_pcie, u16 rid) +{ + u32 data2; + int i; + + guard(mutex)(&imx_pcie->lock); + + for (i = 0; i < IMX95_MAX_LUT; i++) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2); + if (FIELD_GET(IMX95_PE0_LUT_REQID, data2) == rid) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_DATA1, 0); + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_DATA2, 0); + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, i); + + break; + } + } +} -static int imx6_add_pcie_port(struct imx6_pcie *imx6_pcie, - struct platform_device *pdev) +static int imx_pcie_add_lut_by_rid(struct imx_pcie *imx_pcie, u32 rid) { - struct dw_pcie *pci = imx6_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = &pdev->dev; + struct device *dev = imx_pcie->pci->dev; + struct device_node *target; + u32 sid_i, sid_m; + int err_i, err_m; + u32 sid = 0; + + target = NULL; + err_i = of_map_id(dev->of_node, rid, "iommu-map", "iommu-map-mask", + &target, &sid_i); + if (target) { + of_node_put(target); + } else { + /* + * "target == NULL && err_i == 0" means RID out of map range. + * Use 1:1 map RID to streamID. Hardware can't support this + * because the streamID is only 6 bits + */ + err_i = -EINVAL; + } + + target = NULL; + err_m = of_map_id(dev->of_node, rid, "msi-map", "msi-map-mask", + &target, &sid_m); + + /* + * err_m target + * 0 NULL RID out of range. Use 1:1 map RID to + * streamID, Current hardware can't + * support it, so return -EINVAL. + * != 0 NULL msi-map does not exist, use built-in MSI + * 0 != NULL Get correct streamID from RID + * != 0 != NULL Invalid combination + */ + if (!err_m && !target) + return -EINVAL; + else if (target) + of_node_put(target); /* Find streamID map entry for RID in msi-map */ + + /* + * msi-map iommu-map + * N N DWC MSI Ctrl + * Y Y ITS + SMMU, require the same SID + * Y N ITS + * N Y DWC MSI Ctrl + SMMU + */ + if (err_i && err_m) + return 0; + + if (!err_i && !err_m) { + /* + * Glue Layer + * <==========> + * ┌─────┐ ┌──────────┐ + * │ LUT │ 6-bit streamID │ │ + * │ │─────────────────►│ MSI │ + * └─────┘ 2-bit ctrl ID │ │ + * ┌───────────►│ │ + * (i.MX95) │ │ │ + * 00 PCIe0 │ │ │ + * 01 ENETC │ │ │ + * 10 PCIe1 │ │ │ + * │ └──────────┘ + * The MSI glue layer auto adds 2 bits controller ID ahead of + * streamID, so mask these 2 bits to get streamID. The + * IOMMU glue layer doesn't do that. + */ + if (sid_i != (sid_m & IMX95_SID_MASK)) { + dev_err(dev, "iommu-map and msi-map entries mismatch!\n"); + return -EINVAL; + } + } + + if (!err_i) + sid = sid_i; + else if (!err_m) + sid = sid_m & IMX95_SID_MASK; + + return imx_pcie_add_lut(imx_pcie, rid, sid); +} + +static int imx_pcie_enable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) +{ + struct imx_pcie *imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata)); + + return imx_pcie_add_lut_by_rid(imx_pcie, pci_dev_id(pdev)); +} + +static void imx_pcie_disable_device(struct pci_host_bridge *bridge, + struct pci_dev *pdev) +{ + struct imx_pcie *imx_pcie; + + imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata)); + imx_pcie_remove_lut(imx_pcie, pci_dev_id(pdev)); +} + +static int imx_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct imx_pcie *imx_pcie = to_imx_pcie(pci); int ret; - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq_byname(pdev, "msi"); - if (pp->msi_irq <= 0) { - dev_err(dev, "failed to get MSI irq\n"); - return -ENODEV; + if (imx_pcie->vpcie) { + ret = regulator_enable(imx_pcie->vpcie); + if (ret) { + dev_err(dev, "failed to enable vpcie regulator: %d\n", + ret); + return ret; } } - pp->ops = &imx6_pcie_host_ops; + if (pp->bridge && imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT)) { + pp->bridge->enable_device = imx_pcie_enable_device; + pp->bridge->disable_device = imx_pcie_disable_device; + } + + imx_pcie_assert_core_reset(imx_pcie); - ret = dw_pcie_host_init(pp); + if (imx_pcie->drvdata->init_phy) + imx_pcie->drvdata->init_phy(imx_pcie); + + imx_pcie_configure_type(imx_pcie); + + ret = imx_pcie_clk_enable(imx_pcie); if (ret) { - dev_err(dev, "failed to initialize host\n"); - return ret; + dev_err(dev, "unable to enable pcie clocks: %d\n", ret); + goto err_reg_disable; } + if (imx_pcie->phy) { + ret = phy_init(imx_pcie->phy); + if (ret) { + dev_err(dev, "pcie PHY power up failed\n"); + goto err_clk_disable; + } + + ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE, + imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE ? + PHY_MODE_PCIE_EP : PHY_MODE_PCIE_RC); + if (ret) { + dev_err(dev, "unable to set PCIe PHY mode\n"); + goto err_phy_exit; + } + + ret = phy_power_on(imx_pcie->phy); + if (ret) { + dev_err(dev, "waiting for PHY ready timeout!\n"); + goto err_phy_exit; + } + } + + /* 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; + +err_phy_off: + phy_power_off(imx_pcie->phy); +err_phy_exit: + phy_exit(imx_pcie->phy); +err_clk_disable: + imx_pcie_clk_disable(imx_pcie); +err_reg_disable: + if (imx_pcie->vpcie) + regulator_disable(imx_pcie->vpcie); + return ret; +} + +static void imx_pcie_host_exit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx_pcie *imx_pcie = to_imx_pcie(pci); + + if (imx_pcie->phy) { + if (phy_power_off(imx_pcie->phy)) + dev_err(pci->dev, "unable to power off PHY\n"); + phy_exit(imx_pcie->phy); + } + imx_pcie_clk_disable(imx_pcie); + + if (imx_pcie->vpcie) + 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); + } +} + +/* + * In old DWC implementations, PCIE_ATU_INHIBIT_PAYLOAD in iATU Ctrl2 + * register is reserved, so the generic DWC implementation of sending the + * PME_Turn_Off message using a dummy MMIO write cannot be used. + */ +static void imx_pcie_pme_turn_off(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx_pcie *imx_pcie = to_imx_pcie(pci); + + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF); + regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF); + + usleep_range(PCIE_PME_TO_L2_TIMEOUT_US/10, PCIE_PME_TO_L2_TIMEOUT_US); } +static const struct dw_pcie_host_ops imx_pcie_host_ops = { + .init = imx_pcie_host_init, + .deinit = imx_pcie_host_exit, + .pme_turn_off = imx_pcie_pme_turn_off, +}; + +static const struct dw_pcie_host_ops imx_pcie_host_dw_pme_ops = { + .init = imx_pcie_host_init, + .deinit = imx_pcie_host_exit, + .post_init = imx_pcie_host_post_init, +}; + static const struct dw_pcie_ops dw_pcie_ops = { - /* No special ops needed, but pcie-designware still expects this struct */ + .start_link = imx_pcie_start_link, + .stop_link = imx_pcie_stop_link, }; -#ifdef CONFIG_PM_SLEEP -static void imx6_pcie_ltssm_disable(struct device *dev) +static void imx_pcie_ep_init(struct dw_pcie_ep *ep) { - struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + enum pci_barno bar; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - switch (imx6_pcie->variant) { - case IMX6SX: - case IMX6QP: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6Q_GPR12_PCIE_CTL_2, 0); - break; - case IMX7D: - reset_control_assert(imx6_pcie->apps_reset); - break; + for (bar = BAR_0; bar <= BAR_5; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static int imx_pcie_ep_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); + case PCI_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); default: - dev_err(dev, "ltssm_disable not supported\n"); + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + return -EINVAL; } + + return 0; +} + +static const struct pci_epc_features imx8m_pcie_epc_features = { + .msi_capable = true, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = SZ_256, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + .align = SZ_64K, +}; + +static const struct pci_epc_features imx8q_pcie_epc_features = { + .msi_capable = true, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + .align = SZ_64K, +}; + +/* + * | Default | Default | Default | BAR Sizing + * BAR# | Enable? | Type | Size | Scheme + * ======================================================= + * BAR0 | Enable | 64-bit | 1 MB | Programmable Size + * BAR1 | Disable | 32-bit | 64 KB | Fixed Size + * (BAR1 should be disabled if BAR0 is 64-bit) + * BAR2 | Enable | 32-bit | 1 MB | Programmable Size + * BAR3 | Enable | 32-bit | 64 KB | Programmable Size + * BAR4 | Enable | 32-bit | 1 MB | Programmable Size + * BAR5 | Enable | 32-bit | 64 KB | Programmable Size + */ +static const struct pci_epc_features imx95_pcie_epc_features = { + .msi_capable = true, + .bar[BAR_1] = { .type = BAR_FIXED, .fixed_size = SZ_64K, }, + .align = SZ_4K, +}; + +static const struct pci_epc_features* +imx_pcie_ep_get_features(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct imx_pcie *imx_pcie = to_imx_pcie(pci); + + return imx_pcie->drvdata->epc_features; } -static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie) +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .init = imx_pcie_ep_init, + .raise_irq = imx_pcie_ep_raise_irq, + .get_features = imx_pcie_ep_get_features, +}; + +static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, + struct platform_device *pdev) { - struct device *dev = imx6_pcie->pci->dev; + int ret; + struct dw_pcie_ep *ep; + struct dw_pcie *pci = imx_pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = pci->dev; + + imx_pcie_host_init(pp); + ep = &pci->ep; + ep->ops = &pcie_ep_ops; + + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_SUPPORT_64BIT)) + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - /* Some variants have a turnoff reset in DT */ - if (imx6_pcie->turnoff_reset) { - reset_control_assert(imx6_pcie->turnoff_reset); - reset_control_deassert(imx6_pcie->turnoff_reset); - goto pm_turnoff_sleep; + ep->page_size = imx_pcie->drvdata->epc_features->align; + + ret = dw_pcie_ep_init(ep); + if (ret) { + dev_err(dev, "failed to initialize endpoint\n"); + return ret; } + imx_pcie_host_post_init(pp); - /* Others poke directly at IOMUXC registers */ - switch (imx6_pcie->variant) { - case IMX6SX: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_PM_TURN_OFF, - IMX6SX_GPR12_PCIE_PM_TURN_OFF); - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_PM_TURN_OFF, 0); - break; - default: - dev_err(dev, "PME_Turn_Off not implemented\n"); - return; + ret = dw_pcie_ep_init_registers(ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(ep); + return ret; } - /* - * Components with an upstream port must respond to - * PME_Turn_Off with PME_TO_Ack but we can't check. - * - * The standard recommends a 1-10ms timeout after which to - * proceed anyway as if acks were received. - */ -pm_turnoff_sleep: - usleep_range(1000, 10000); + pci_epc_init_notify(ep->epc); + + return 0; } -static void imx6_pcie_clk_disable(struct imx6_pcie *imx6_pcie) +static void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save) { - clk_disable_unprepare(imx6_pcie->pcie); - clk_disable_unprepare(imx6_pcie->pcie_phy); - clk_disable_unprepare(imx6_pcie->pcie_bus); + u8 offset; + u16 val; + struct dw_pcie *pci = imx_pcie->pci; - switch (imx6_pcie->variant) { - case IMX6SX: - clk_disable_unprepare(imx6_pcie->pcie_inbound_axi); - break; - case IMX7D: - regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, - IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); - break; - default: - break; + if (pci_msi_enabled()) { + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_MSI); + if (save) { + val = dw_pcie_readw_dbi(pci, offset + PCI_MSI_FLAGS); + imx_pcie->msi_ctrl = val; + } else { + dw_pcie_dbi_ro_wr_en(pci); + val = imx_pcie->msi_ctrl; + dw_pcie_writew_dbi(pci, offset + PCI_MSI_FLAGS, val); + dw_pcie_dbi_ro_wr_dis(pci); + } } } -static inline bool imx6_pcie_supports_suspend(struct imx6_pcie *imx6_pcie) +static void imx_pcie_lut_save(struct imx_pcie *imx_pcie) { - return (imx6_pcie->variant == IMX7D || - imx6_pcie->variant == IMX6SX); + 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 imx6_pcie_suspend_noirq(struct device *dev) +static int imx_pcie_suspend_noirq(struct device *dev) { - struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + struct imx_pcie *imx_pcie = dev_get_drvdata(dev); - if (!imx6_pcie_supports_suspend(imx6_pcie)) + if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND)) return 0; - imx6_pcie_pm_turnoff(imx6_pcie); - imx6_pcie_clk_disable(imx6_pcie); - imx6_pcie_ltssm_disable(dev); + 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 + * set the PCIE_TEST_PD flag. However, we can also disable the + * clock which saves some power. + */ + imx_pcie_assert_core_reset(imx_pcie); + imx_pcie->drvdata->enable_ref_clk(imx_pcie, false); + } else { + return dw_pcie_suspend_noirq(imx_pcie->pci); + } return 0; } -static int imx6_pcie_resume_noirq(struct device *dev) +static int imx_pcie_resume_noirq(struct device *dev) { int ret; - struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); - struct pcie_port *pp = &imx6_pcie->pci->pp; + struct imx_pcie *imx_pcie = dev_get_drvdata(dev); - if (!imx6_pcie_supports_suspend(imx6_pcie)) + if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND)) return 0; - imx6_pcie_assert_core_reset(imx6_pcie); - imx6_pcie_init_phy(imx6_pcie); - imx6_pcie_deassert_core_reset(imx6_pcie); - dw_pcie_setup_rc(pp); + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_BROKEN_SUSPEND)) { + ret = imx_pcie->drvdata->enable_ref_clk(imx_pcie, true); + if (ret) + return ret; + ret = imx_pcie_deassert_core_reset(imx_pcie); + if (ret) + return ret; - ret = imx6_pcie_establish_link(imx6_pcie); - if (ret < 0) - dev_info(dev, "pcie link is down after resume.\n"); + /* + * Using PCIE_TEST_PD seems to disable MSI and powers down the + * root complex. This is why we have to setup the rc again and + * why we have to restore the MSI register. + */ + ret = dw_pcie_setup_rc(&imx_pcie->pci->pp); + if (ret) + return ret; + } else { + ret = dw_pcie_resume_noirq(imx_pcie->pci); + if (ret) + return ret; + } + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT)) + imx_pcie_lut_restore(imx_pcie); + imx_pcie_msi_save_restore(imx_pcie, false); return 0; } -#endif -static const struct dev_pm_ops imx6_pcie_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx6_pcie_suspend_noirq, - imx6_pcie_resume_noirq) +static const struct dev_pm_ops imx_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(imx_pcie_suspend_noirq, + imx_pcie_resume_noirq) }; -static int imx6_pcie_probe(struct platform_device *pdev) +static int imx_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct dw_pcie *pci; - struct imx6_pcie *imx6_pcie; - struct resource *dbi_base; + struct imx_pcie *imx_pcie; + struct device_node *np; struct device_node *node = dev->of_node; - int ret; + int ret, domain; u16 val; - imx6_pcie = devm_kzalloc(dev, sizeof(*imx6_pcie), GFP_KERNEL); - if (!imx6_pcie) + imx_pcie = devm_kzalloc(dev, sizeof(*imx_pcie), GFP_KERNEL); + if (!imx_pcie) return -ENOMEM; pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); @@ -932,179 +1616,434 @@ static int imx6_pcie_probe(struct platform_device *pdev) pci->dev = dev; pci->ops = &dw_pcie_ops; - imx6_pcie->pci = pci; - imx6_pcie->variant = - (enum imx6_pcie_variants)of_device_get_match_data(dev); + imx_pcie->pci = pci; + imx_pcie->drvdata = of_device_get_match_data(dev); - dbi_base = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pci->dbi_base = devm_ioremap_resource(dev, dbi_base); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); + mutex_init(&imx_pcie->lock); - /* Fetch GPIOs */ - imx6_pcie->reset_gpio = of_get_named_gpio(node, "reset-gpio", 0); - imx6_pcie->gpio_active_high = of_property_read_bool(node, - "reset-gpio-active-high"); - if (gpio_is_valid(imx6_pcie->reset_gpio)) { - ret = devm_gpio_request_one(dev, imx6_pcie->reset_gpio, - imx6_pcie->gpio_active_high ? - GPIOF_OUT_INIT_HIGH : - GPIOF_OUT_INIT_LOW, - "PCIe reset"); + if (imx_pcie->drvdata->ops) + pci->pp.ops = imx_pcie->drvdata->ops; + else + pci->pp.ops = &imx_pcie_host_dw_pme_ops; + + /* Find the PHY if one is defined, only imx7d uses it */ + np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0); + if (np) { + struct resource res; + + ret = of_address_to_resource(np, 0, &res); if (ret) { - dev_err(dev, "unable to get reset gpio\n"); + dev_err(dev, "Unable to map PCIe PHY\n"); return ret; } - } else if (imx6_pcie->reset_gpio == -EPROBE_DEFER) { - return imx6_pcie->reset_gpio; + imx_pcie->phy_base = devm_ioremap_resource(dev, &res); + if (IS_ERR(imx_pcie->phy_base)) + return PTR_ERR(imx_pcie->phy_base); } + /* Fetch GPIOs */ + imx_pcie->reset_gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(imx_pcie->reset_gpiod)) + return dev_err_probe(dev, PTR_ERR(imx_pcie->reset_gpiod), + "unable to get reset gpio\n"); + gpiod_set_consumer_name(imx_pcie->reset_gpiod, "PCIe reset"); + /* Fetch clocks */ - imx6_pcie->pcie_phy = devm_clk_get(dev, "pcie_phy"); - if (IS_ERR(imx6_pcie->pcie_phy)) { - dev_err(dev, "pcie_phy clock source missing or invalid\n"); - return PTR_ERR(imx6_pcie->pcie_phy); + imx_pcie->num_clks = devm_clk_bulk_get_all(dev, &imx_pcie->clks); + if (imx_pcie->num_clks < 0) + return dev_err_probe(dev, imx_pcie->num_clks, + "failed to get clocks\n"); + + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_PHYDRV)) { + imx_pcie->phy = devm_phy_get(dev, "pcie-phy"); + if (IS_ERR(imx_pcie->phy)) + return dev_err_probe(dev, PTR_ERR(imx_pcie->phy), + "failed to get pcie phy\n"); } - imx6_pcie->pcie_bus = devm_clk_get(dev, "pcie_bus"); - if (IS_ERR(imx6_pcie->pcie_bus)) { - dev_err(dev, "pcie_bus clock source missing or invalid\n"); - return PTR_ERR(imx6_pcie->pcie_bus); + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_APP_RESET)) { + imx_pcie->apps_reset = devm_reset_control_get_exclusive(dev, "apps"); + if (IS_ERR(imx_pcie->apps_reset)) + return dev_err_probe(dev, PTR_ERR(imx_pcie->apps_reset), + "failed to get pcie apps reset control\n"); } - imx6_pcie->pcie = devm_clk_get(dev, "pcie"); - if (IS_ERR(imx6_pcie->pcie)) { - dev_err(dev, "pcie clock source missing or invalid\n"); - return PTR_ERR(imx6_pcie->pcie); + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_PHY_RESET)) { + imx_pcie->pciephy_reset = devm_reset_control_get_exclusive(dev, "pciephy"); + if (IS_ERR(imx_pcie->pciephy_reset)) + return dev_err_probe(dev, PTR_ERR(imx_pcie->pciephy_reset), + "Failed to get PCIEPHY reset control\n"); } - switch (imx6_pcie->variant) { - case IMX6SX: - imx6_pcie->pcie_inbound_axi = devm_clk_get(dev, - "pcie_inbound_axi"); - if (IS_ERR(imx6_pcie->pcie_inbound_axi)) { - dev_err(dev, "pcie_inbound_axi clock missing or invalid\n"); - return PTR_ERR(imx6_pcie->pcie_inbound_axi); - } - break; - case IMX7D: - imx6_pcie->pciephy_reset = devm_reset_control_get_exclusive(dev, - "pciephy"); - if (IS_ERR(imx6_pcie->pciephy_reset)) { - dev_err(dev, "Failed to get PCIEPHY reset control\n"); - return PTR_ERR(imx6_pcie->pciephy_reset); - } + switch (imx_pcie->drvdata->variant) { + case IMX8MQ: + case IMX8MQ_EP: + domain = of_get_pci_domain_nr(node); + if (domain < 0 || domain > 1) + return dev_err_probe(dev, -ENODEV, "no \"linux,pci-domain\" property in devicetree\n"); - imx6_pcie->apps_reset = devm_reset_control_get_exclusive(dev, - "apps"); - if (IS_ERR(imx6_pcie->apps_reset)) { - dev_err(dev, "Failed to get PCIE APPS reset control\n"); - return PTR_ERR(imx6_pcie->apps_reset); - } + imx_pcie->controller_id = domain; break; default: break; } - /* Grab turnoff reset */ - imx6_pcie->turnoff_reset = devm_reset_control_get_optional_exclusive(dev, "turnoff"); - if (IS_ERR(imx6_pcie->turnoff_reset)) { - dev_err(dev, "Failed to get TURNOFF reset control\n"); - return PTR_ERR(imx6_pcie->turnoff_reset); + if (imx_pcie->drvdata->gpr) { + /* Grab GPR config register range */ + imx_pcie->iomuxc_gpr = + syscon_regmap_lookup_by_compatible(imx_pcie->drvdata->gpr); + if (IS_ERR(imx_pcie->iomuxc_gpr)) + return dev_err_probe(dev, PTR_ERR(imx_pcie->iomuxc_gpr), + "unable to find iomuxc registers\n"); } - /* Grab GPR config register range */ - imx6_pcie->iomuxc_gpr = - syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr"); - if (IS_ERR(imx6_pcie->iomuxc_gpr)) { - dev_err(dev, "unable to find iomuxc registers\n"); - return PTR_ERR(imx6_pcie->iomuxc_gpr); + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_SERDES)) { + void __iomem *off = devm_platform_ioremap_resource_byname(pdev, "app"); + + if (IS_ERR(off)) + return dev_err_probe(dev, PTR_ERR(off), + "unable to find serdes registers\n"); + + static const struct regmap_config regmap_config = { + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, + }; + + imx_pcie->iomuxc_gpr = devm_regmap_init_mmio(dev, off, ®map_config); + if (IS_ERR(imx_pcie->iomuxc_gpr)) + return dev_err_probe(dev, PTR_ERR(imx_pcie->iomuxc_gpr), + "unable to find iomuxc registers\n"); } /* Grab PCIe PHY Tx Settings */ if (of_property_read_u32(node, "fsl,tx-deemph-gen1", - &imx6_pcie->tx_deemph_gen1)) - imx6_pcie->tx_deemph_gen1 = 0; + &imx_pcie->tx_deemph_gen1)) + imx_pcie->tx_deemph_gen1 = 0; if (of_property_read_u32(node, "fsl,tx-deemph-gen2-3p5db", - &imx6_pcie->tx_deemph_gen2_3p5db)) - imx6_pcie->tx_deemph_gen2_3p5db = 0; + &imx_pcie->tx_deemph_gen2_3p5db)) + imx_pcie->tx_deemph_gen2_3p5db = 0; if (of_property_read_u32(node, "fsl,tx-deemph-gen2-6db", - &imx6_pcie->tx_deemph_gen2_6db)) - imx6_pcie->tx_deemph_gen2_6db = 20; + &imx_pcie->tx_deemph_gen2_6db)) + imx_pcie->tx_deemph_gen2_6db = 20; if (of_property_read_u32(node, "fsl,tx-swing-full", - &imx6_pcie->tx_swing_full)) - imx6_pcie->tx_swing_full = 127; + &imx_pcie->tx_swing_full)) + imx_pcie->tx_swing_full = 127; if (of_property_read_u32(node, "fsl,tx-swing-low", - &imx6_pcie->tx_swing_low)) - imx6_pcie->tx_swing_low = 127; + &imx_pcie->tx_swing_low)) + imx_pcie->tx_swing_low = 127; /* Limit link speed */ - ret = of_property_read_u32(node, "fsl,max-link-speed", - &imx6_pcie->link_gen); - if (ret) - imx6_pcie->link_gen = 1; + pci->max_link_speed = 1; + of_property_read_u32(node, "fsl,max-link-speed", &pci->max_link_speed); + + ret = devm_regulator_get_enable_optional(&pdev->dev, "vpcie3v3aux"); + if (ret < 0 && ret != -ENODEV) + return dev_err_probe(dev, ret, "failed to enable Vaux supply\n"); + + imx_pcie->vpcie = devm_regulator_get_optional(&pdev->dev, "vpcie"); + if (IS_ERR(imx_pcie->vpcie)) { + if (PTR_ERR(imx_pcie->vpcie) != -ENODEV) + return PTR_ERR(imx_pcie->vpcie); + imx_pcie->vpcie = NULL; + } - imx6_pcie->vpcie = devm_regulator_get_optional(&pdev->dev, "vpcie"); - if (IS_ERR(imx6_pcie->vpcie)) { - if (PTR_ERR(imx6_pcie->vpcie) == -EPROBE_DEFER) - return -EPROBE_DEFER; - imx6_pcie->vpcie = NULL; + imx_pcie->vph = devm_regulator_get_optional(&pdev->dev, "vph"); + if (IS_ERR(imx_pcie->vph)) { + if (PTR_ERR(imx_pcie->vph) != -ENODEV) + return PTR_ERR(imx_pcie->vph); + imx_pcie->vph = NULL; } - platform_set_drvdata(pdev, imx6_pcie); + platform_set_drvdata(pdev, imx_pcie); - ret = imx6_pcie_attach_pd(dev); + ret = imx_pcie_attach_pd(dev); if (ret) return ret; - ret = imx6_add_pcie_port(imx6_pcie, pdev); - if (ret < 0) - return ret; + pci->use_parent_dt_ranges = true; + if (imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE) { + ret = imx_add_pcie_ep(imx_pcie, pdev); + if (ret < 0) + return ret; - if (pci_msi_enabled()) { - val = dw_pcie_readw_dbi(pci, PCIE_RC_IMX6_MSI_CAP + - PCI_MSI_FLAGS); - val |= PCI_MSI_FLAGS_ENABLE; - dw_pcie_writew_dbi(pci, PCIE_RC_IMX6_MSI_CAP + PCI_MSI_FLAGS, - val); + /* + * FIXME: Only single Device (EPF) is supported due to the + * Endpoint framework limitation. + */ + imx_pcie_add_lut_by_rid(imx_pcie, 0); + } else { + pci->pp.use_atu_msg = true; + ret = dw_pcie_host_init(&pci->pp); + if (ret < 0) + return ret; + + if (pci_msi_enabled()) { + u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_MSI); + + val = dw_pcie_readw_dbi(pci, offset + PCI_MSI_FLAGS); + val |= PCI_MSI_FLAGS_ENABLE; + dw_pcie_writew_dbi(pci, offset + PCI_MSI_FLAGS, val); + } } return 0; } -static void imx6_pcie_shutdown(struct platform_device *pdev) +static void imx_pcie_shutdown(struct platform_device *pdev) { - struct imx6_pcie *imx6_pcie = platform_get_drvdata(pdev); + struct imx_pcie *imx_pcie = platform_get_drvdata(pdev); /* bring down link, so bootloader gets clean state in case of reboot */ - imx6_pcie_assert_core_reset(imx6_pcie); + imx_pcie_assert_core_reset(imx_pcie); } -static const struct of_device_id imx6_pcie_of_match[] = { - { .compatible = "fsl,imx6q-pcie", .data = (void *)IMX6Q, }, - { .compatible = "fsl,imx6sx-pcie", .data = (void *)IMX6SX, }, - { .compatible = "fsl,imx6qp-pcie", .data = (void *)IMX6QP, }, - { .compatible = "fsl,imx7d-pcie", .data = (void *)IMX7D, }, +static const struct imx_pcie_drvdata drvdata[] = { + [IMX6Q] = { + .variant = IMX6Q, + .flags = IMX_PCIE_FLAG_IMX_PHY | + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND | + IMX_PCIE_FLAG_BROKEN_SUSPEND | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, + .dbi_length = 0x200, + .gpr = "fsl,imx6q-iomuxc-gpr", + .ltssm_off = IOMUXC_GPR12, + .ltssm_mask = IMX6Q_GPR12_PCIE_CTL_2, + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .init_phy = imx_pcie_init_phy, + .enable_ref_clk = imx6q_pcie_enable_ref_clk, + .core_reset = imx6q_pcie_core_reset, + }, + [IMX6SX] = { + .variant = IMX6SX, + .flags = IMX_PCIE_FLAG_IMX_PHY | + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, + .gpr = "fsl,imx6q-iomuxc-gpr", + .ltssm_off = IOMUXC_GPR12, + .ltssm_mask = IMX6Q_GPR12_PCIE_CTL_2, + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .init_phy = imx6sx_pcie_init_phy, + .enable_ref_clk = imx6sx_pcie_enable_ref_clk, + .core_reset = imx6sx_pcie_core_reset, + .ops = &imx_pcie_host_ops, + }, + [IMX6QP] = { + .variant = IMX6QP, + .flags = IMX_PCIE_FLAG_IMX_PHY | + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, + .dbi_length = 0x200, + .gpr = "fsl,imx6q-iomuxc-gpr", + .ltssm_off = IOMUXC_GPR12, + .ltssm_mask = IMX6Q_GPR12_PCIE_CTL_2, + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .init_phy = imx_pcie_init_phy, + .enable_ref_clk = imx6q_pcie_enable_ref_clk, + .core_reset = imx6qp_pcie_core_reset, + .ops = &imx_pcie_host_ops, + }, + [IMX7D] = { + .variant = IMX7D, + .flags = IMX_PCIE_FLAG_SUPPORTS_SUSPEND | + IMX_PCIE_FLAG_HAS_APP_RESET | + IMX_PCIE_FLAG_HAS_PHY_RESET, + .gpr = "fsl,imx7d-iomuxc-gpr", + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .enable_ref_clk = imx7d_pcie_enable_ref_clk, + .core_reset = imx7d_pcie_core_reset, + }, + [IMX8MQ] = { + .variant = IMX8MQ, + .flags = IMX_PCIE_FLAG_HAS_APP_RESET | + IMX_PCIE_FLAG_HAS_PHY_RESET | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, + .gpr = "fsl,imx8mq-iomuxc-gpr", + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .mode_off[1] = IOMUXC_GPR12, + .mode_mask[1] = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE, + .init_phy = imx8mq_pcie_init_phy, + .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + }, + [IMX8MM] = { + .variant = IMX8MM, + .flags = IMX_PCIE_FLAG_SUPPORTS_SUSPEND | + IMX_PCIE_FLAG_HAS_PHYDRV | + IMX_PCIE_FLAG_HAS_APP_RESET, + .gpr = "fsl,imx8mm-iomuxc-gpr", + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + }, + [IMX8MP] = { + .variant = IMX8MP, + .flags = IMX_PCIE_FLAG_SUPPORTS_SUSPEND | + IMX_PCIE_FLAG_HAS_PHYDRV | + IMX_PCIE_FLAG_HAS_APP_RESET, + .gpr = "fsl,imx8mp-iomuxc-gpr", + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + }, + [IMX8Q] = { + .variant = IMX8Q, + .flags = IMX_PCIE_FLAG_HAS_PHYDRV | + IMX_PCIE_FLAG_CPU_ADDR_FIXUP | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, + }, + [IMX95] = { + .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, + }, + [IMX8MQ_EP] = { + .variant = IMX8MQ_EP, + .flags = IMX_PCIE_FLAG_HAS_APP_RESET | + IMX_PCIE_FLAG_HAS_PHY_RESET, + .mode = DW_PCIE_EP_TYPE, + .gpr = "fsl,imx8mq-iomuxc-gpr", + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .mode_off[1] = IOMUXC_GPR12, + .mode_mask[1] = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE, + .epc_features = &imx8q_pcie_epc_features, + .init_phy = imx8mq_pcie_init_phy, + .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + }, + [IMX8MM_EP] = { + .variant = IMX8MM_EP, + .flags = IMX_PCIE_FLAG_HAS_APP_RESET | + IMX_PCIE_FLAG_HAS_PHYDRV, + .mode = DW_PCIE_EP_TYPE, + .gpr = "fsl,imx8mm-iomuxc-gpr", + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .epc_features = &imx8m_pcie_epc_features, + .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + }, + [IMX8MP_EP] = { + .variant = IMX8MP_EP, + .flags = IMX_PCIE_FLAG_HAS_APP_RESET | + IMX_PCIE_FLAG_HAS_PHYDRV, + .mode = DW_PCIE_EP_TYPE, + .gpr = "fsl,imx8mp-iomuxc-gpr", + .mode_off[0] = IOMUXC_GPR12, + .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, + .epc_features = &imx8m_pcie_epc_features, + .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + }, + [IMX8Q_EP] = { + .variant = IMX8Q_EP, + .flags = IMX_PCIE_FLAG_HAS_PHYDRV, + .mode = DW_PCIE_EP_TYPE, + .epc_features = &imx8q_pcie_epc_features, + }, + [IMX95_EP] = { + .variant = IMX95_EP, + .flags = IMX_PCIE_FLAG_HAS_SERDES | + IMX_PCIE_FLAG_8GT_ECN_ERR051586 | + IMX_PCIE_FLAG_SUPPORT_64BIT, + .ltssm_off = IMX95_PE0_GEN_CTRL_3, + .ltssm_mask = IMX95_PCIE_LTSSM_EN, + .mode_off[0] = IMX95_PE0_GEN_CTRL_1, + .mode_mask[0] = IMX95_PCIE_DEVICE_TYPE, + .init_phy = imx95_pcie_init_phy, + .core_reset = imx95_pcie_core_reset, + .wait_pll_lock = imx95_pcie_wait_for_phy_pll_lock, + .epc_features = &imx95_pcie_epc_features, + .mode = DW_PCIE_EP_TYPE, + }, +}; + +static const struct of_device_id imx_pcie_of_match[] = { + { .compatible = "fsl,imx6q-pcie", .data = &drvdata[IMX6Q], }, + { .compatible = "fsl,imx6sx-pcie", .data = &drvdata[IMX6SX], }, + { .compatible = "fsl,imx6qp-pcie", .data = &drvdata[IMX6QP], }, + { .compatible = "fsl,imx7d-pcie", .data = &drvdata[IMX7D], }, + { .compatible = "fsl,imx8mq-pcie", .data = &drvdata[IMX8MQ], }, + { .compatible = "fsl,imx8mm-pcie", .data = &drvdata[IMX8MM], }, + { .compatible = "fsl,imx8mp-pcie", .data = &drvdata[IMX8MP], }, + { .compatible = "fsl,imx8q-pcie", .data = &drvdata[IMX8Q], }, + { .compatible = "fsl,imx95-pcie", .data = &drvdata[IMX95], }, + { .compatible = "fsl,imx8mq-pcie-ep", .data = &drvdata[IMX8MQ_EP], }, + { .compatible = "fsl,imx8mm-pcie-ep", .data = &drvdata[IMX8MM_EP], }, + { .compatible = "fsl,imx8mp-pcie-ep", .data = &drvdata[IMX8MP_EP], }, + { .compatible = "fsl,imx8q-pcie-ep", .data = &drvdata[IMX8Q_EP], }, + { .compatible = "fsl,imx95-pcie-ep", .data = &drvdata[IMX95_EP], }, {}, }; -static struct platform_driver imx6_pcie_driver = { +static struct platform_driver imx_pcie_driver = { .driver = { .name = "imx6q-pcie", - .of_match_table = imx6_pcie_of_match, + .of_match_table = imx_pcie_of_match, .suppress_bind_attrs = true, - .pm = &imx6_pcie_pm_ops, + .pm = &imx_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, - .probe = imx6_pcie_probe, - .shutdown = imx6_pcie_shutdown, + .probe = imx_pcie_probe, + .shutdown = imx_pcie_shutdown, }; -static int __init imx6_pcie_init(void) +static void imx_pcie_quirk(struct pci_dev *dev) { + struct pci_bus *bus = dev->bus; + struct dw_pcie_rp *pp = bus->sysdata; + + /* Bus parent is the PCI bridge, its parent is this platform driver */ + if (!bus->dev.parent || !bus->dev.parent->parent) + return; + + /* Make sure we only quirk devices associated with this driver */ + if (bus->dev.parent->parent->driver != &imx_pcie_driver.driver) + return; + + if (pci_is_root_bus(bus)) { + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx_pcie *imx_pcie = to_imx_pcie(pci); + + /* + * Limit config length to avoid the kernel reading beyond + * the register set and causing an abort on i.MX 6Quad + */ + if (imx_pcie->drvdata->dbi_length) { + dev->cfg_size = imx_pcie->drvdata->dbi_length; + dev_info(&dev->dev, "Limiting cfg_size to %d\n", + dev->cfg_size); + } + } +} +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_SYNOPSYS, 0xabcd, + PCI_CLASS_BRIDGE_PCI, 8, imx_pcie_quirk); + +static int __init imx_pcie_init(void) +{ +#ifdef CONFIG_ARM + struct device_node *np; + + np = of_find_matching_node(NULL, imx_pcie_of_match); + if (!np) + return -ENODEV; + of_node_put(np); + /* * Since probe() can be deferred we need to make sure that * hook_fault_code is not called after __init memory is freed @@ -1114,7 +2053,8 @@ static int __init imx6_pcie_init(void) */ hook_fault_code(8, imx6q_pcie_abort_handler, SIGBUS, 0, "external abort on non-linefetch"); +#endif - return platform_driver_register(&imx6_pcie_driver); + return platform_driver_register(&imx_pcie_driver); } -device_initcall(imx6_pcie_init); +device_initcall(imx_pcie_init); diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index 14f2b0b4ed5e..f86d9111f863 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -3,7 +3,7 @@ * PCIe host controller driver for Texas Instruments Keystone SoCs * * Copyright (C) 2013-2014 Texas Instruments., Ltd. - * http://www.ti.com + * https://www.ti.com * * Author: Murali Karicheri <m-karicheri2@ti.com> * Implementation based on pci-exynos.c and pcie-designware.c @@ -11,11 +11,13 @@ #include <linux/clk.h> #include <linux/delay.h> +#include <linux/gpio/consumer.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/mfd/syscon.h> +#include <linux/module.h> #include <linux/msi.h> #include <linux/of.h> #include <linux/of_irq.h> @@ -26,12 +28,18 @@ #include <linux/resource.h> #include <linux/signal.h> +#include "../../pci.h" #include "pcie-designware.h" #define PCIE_VENDORID_MASK 0xffff #define PCIE_DEVICEID_SHIFT 16 /* Application registers */ +#define PID 0x000 +#define RTL GENMASK(15, 11) +#define RTL_SHIFT 11 +#define AM6_PCI_PG1_RTL_VER 0x15 + #define CMD_STATUS 0x004 #define LTSSM_EN_VAL BIT(0) #define OB_XLAT_EN_VAL BIT(1) @@ -44,28 +52,34 @@ #define CFG_TYPE1 BIT(24) #define OB_SIZE 0x030 -#define SPACE0_REMOTE_CFG_OFFSET 0x1000 #define OB_OFFSET_INDEX(n) (0x200 + (8 * (n))) #define OB_OFFSET_HI(n) (0x204 + (8 * (n))) #define OB_ENABLEN BIT(0) #define OB_WIN_SIZE 8 /* 8MB */ +#define PCIE_LEGACY_IRQ_ENABLE_SET(n) (0x188 + (0x10 * ((n) - 1))) +#define PCIE_LEGACY_IRQ_ENABLE_CLR(n) (0x18c + (0x10 * ((n) - 1))) +#define PCIE_EP_IRQ_SET 0x64 +#define PCIE_EP_IRQ_CLR 0x68 +#define INT_ENABLE BIT(0) + /* IRQ register defines */ #define IRQ_EOI 0x050 -#define IRQ_STATUS 0x184 -#define IRQ_ENABLE_SET 0x188 -#define IRQ_ENABLE_CLR 0x18c #define MSI_IRQ 0x054 -#define MSI0_IRQ_STATUS 0x104 -#define MSI0_IRQ_ENABLE_SET 0x108 -#define MSI0_IRQ_ENABLE_CLR 0x10c -#define IRQ_STATUS 0x184 +#define MSI_IRQ_STATUS(n) (0x104 + ((n) << 4)) +#define MSI_IRQ_ENABLE_SET(n) (0x108 + ((n) << 4)) +#define MSI_IRQ_ENABLE_CLR(n) (0x10c + ((n) << 4)) #define MSI_IRQ_OFFSET 4 +#define IRQ_STATUS(n) (0x184 + ((n) << 4)) +#define IRQ_ENABLE_SET(n) (0x188 + ((n) << 4)) +#define INTx_EN BIT(0) + #define ERR_IRQ_STATUS 0x1c4 #define ERR_IRQ_ENABLE_SET 0x1c8 #define ERR_AER BIT(5) /* ECRC error */ +#define AM6_ERR_AER BIT(4) /* AM6 ECRC error */ #define ERR_AXI BIT(4) /* AXI tag lookup fatal error */ #define ERR_CORR BIT(3) /* Correctable error */ #define ERR_NONFATAL BIT(2) /* Non-fatal error */ @@ -74,55 +88,58 @@ #define ERR_IRQ_ALL (ERR_AER | ERR_AXI | ERR_CORR | \ ERR_NONFATAL | ERR_FATAL | ERR_SYS) -#define MAX_MSI_HOST_IRQS 8 /* PCIE controller device IDs */ #define PCIE_RC_K2HK 0xb008 #define PCIE_RC_K2E 0xb009 #define PCIE_RC_K2L 0xb00a #define PCIE_RC_K2G 0xb00b +#define KS_PCIE_DEV_TYPE_MASK (0x3 << 1) +#define KS_PCIE_DEV_TYPE(mode) ((mode) << 1) + +#define EP 0x0 +#define LEG_EP 0x1 +#define RC 0x2 + +#define KS_PCIE_SYSCLOCKOUTEN BIT(0) + +#define AM654_PCIE_DEV_TYPE_MASK 0x3 +#define AM654_WIN_SIZE SZ_64K + +#define APP_ADDR_SPACE_0 (16 * SZ_1K) + #define to_keystone_pcie(x) dev_get_drvdata((x)->dev) +#define PCI_DEVICE_ID_TI_AM654X 0xb00c + +struct ks_pcie_of_data { + enum dw_pcie_device_mode mode; + const struct dw_pcie_host_ops *host_ops; + const struct dw_pcie_ep_ops *ep_ops; + u32 version; +}; + struct keystone_pcie { struct dw_pcie *pci; /* PCI Device ID */ u32 device_id; - int num_legacy_host_irqs; - int legacy_host_irqs[PCI_NUM_INTX]; - struct device_node *legacy_intc_np; + int intx_host_irqs[PCI_NUM_INTX]; - int num_msi_host_irqs; - int msi_host_irqs[MAX_MSI_HOST_IRQS]; + int msi_host_irq; int num_lanes; u32 num_viewport; struct phy **phy; struct device_link **link; struct device_node *msi_intc_np; - struct irq_domain *legacy_irq_domain; + struct irq_domain *intx_irq_domain; struct device_node *np; - int error_irq; - /* Application register space */ void __iomem *va_app_base; /* DT 1st resource */ struct resource app; + bool is_am6; }; -static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset, - u32 *bit_pos) -{ - *reg_offset = offset % 8; - *bit_pos = offset >> 3; -} - -static phys_addr_t ks_pcie_get_msi_addr(struct pcie_port *pp) -{ - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); - - return ks_pcie->app.start + MSI_IRQ; -} - static u32 ks_pcie_app_readl(struct keystone_pcie *ks_pcie, u32 offset) { return readl(ks_pcie->va_app_base + offset); @@ -134,95 +151,179 @@ static void ks_pcie_app_writel(struct keystone_pcie *ks_pcie, u32 offset, writel(val, ks_pcie->va_app_base + offset); } -static void ks_pcie_handle_msi_irq(struct keystone_pcie *ks_pcie, int offset) +static void ks_pcie_msi_irq_ack(struct irq_data *data) { - struct dw_pcie *pci = ks_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = pci->dev; - u32 pending, vector; - int src, virq; + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); + struct keystone_pcie *ks_pcie; + u32 irq = data->hwirq; + struct dw_pcie *pci; + u32 reg_offset; + u32 bit_pos; - pending = ks_pcie_app_readl(ks_pcie, MSI0_IRQ_STATUS + (offset << 4)); + pci = to_dw_pcie_from_pp(pp); + ks_pcie = to_keystone_pcie(pci); - /* - * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit - * shows 1, 9, 17, 25 and so forth - */ - for (src = 0; src < 4; src++) { - if (BIT(src) & pending) { - vector = offset + (src << 3); - virq = irq_linear_revmap(pp->irq_domain, vector); - dev_dbg(dev, "irq: bit %d, vector %d, virq %d\n", - src, vector, virq); - generic_handle_irq(virq); - } - } + reg_offset = irq % 8; + bit_pos = irq >> 3; + + ks_pcie_app_writel(ks_pcie, MSI_IRQ_STATUS(reg_offset), + BIT(bit_pos)); + ks_pcie_app_writel(ks_pcie, IRQ_EOI, reg_offset + MSI_IRQ_OFFSET); } -static void ks_pcie_msi_irq_ack(int irq, struct pcie_port *pp) +static void ks_pcie_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { - u32 reg_offset, bit_pos; + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); struct keystone_pcie *ks_pcie; struct dw_pcie *pci; + u64 msi_target; pci = to_dw_pcie_from_pp(pp); ks_pcie = to_keystone_pcie(pci); - update_reg_offset_bit_pos(irq, ®_offset, &bit_pos); - ks_pcie_app_writel(ks_pcie, MSI0_IRQ_STATUS + (reg_offset << 4), - BIT(bit_pos)); - ks_pcie_app_writel(ks_pcie, IRQ_EOI, reg_offset + MSI_IRQ_OFFSET); + msi_target = ks_pcie->app.start + MSI_IRQ; + msg->address_lo = lower_32_bits(msi_target); + msg->address_hi = upper_32_bits(msi_target); + msg->data = data->hwirq; + + dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); } -static void ks_pcie_msi_set_irq(struct pcie_port *pp, int irq) +static void ks_pcie_msi_mask(struct irq_data *data) { - u32 reg_offset, bit_pos; - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); + struct keystone_pcie *ks_pcie; + u32 irq = data->hwirq; + struct dw_pcie *pci; + unsigned long flags; + u32 reg_offset; + u32 bit_pos; + + raw_spin_lock_irqsave(&pp->lock, flags); - update_reg_offset_bit_pos(irq, ®_offset, &bit_pos); - ks_pcie_app_writel(ks_pcie, MSI0_IRQ_ENABLE_SET + (reg_offset << 4), + pci = to_dw_pcie_from_pp(pp); + ks_pcie = to_keystone_pcie(pci); + + reg_offset = irq % 8; + bit_pos = irq >> 3; + + ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_CLR(reg_offset), BIT(bit_pos)); + + raw_spin_unlock_irqrestore(&pp->lock, flags); } -static void ks_pcie_msi_clear_irq(struct pcie_port *pp, int irq) +static void ks_pcie_msi_unmask(struct irq_data *data) { - u32 reg_offset, bit_pos; - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); + struct keystone_pcie *ks_pcie; + u32 irq = data->hwirq; + struct dw_pcie *pci; + unsigned long flags; + u32 reg_offset; + u32 bit_pos; + + raw_spin_lock_irqsave(&pp->lock, flags); - update_reg_offset_bit_pos(irq, ®_offset, &bit_pos); - ks_pcie_app_writel(ks_pcie, MSI0_IRQ_ENABLE_CLR + (reg_offset << 4), + pci = to_dw_pcie_from_pp(pp); + ks_pcie = to_keystone_pcie(pci); + + reg_offset = irq % 8; + bit_pos = irq >> 3; + + ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_SET(reg_offset), BIT(bit_pos)); + + raw_spin_unlock_irqrestore(&pp->lock, flags); } -static int ks_pcie_msi_host_init(struct pcie_port *pp) +static struct irq_chip ks_pcie_msi_irq_chip = { + .name = "KEYSTONE-PCI-MSI", + .irq_ack = ks_pcie_msi_irq_ack, + .irq_compose_msi_msg = ks_pcie_compose_msi_msg, + .irq_mask = ks_pcie_msi_mask, + .irq_unmask = ks_pcie_msi_unmask, +}; + +/** + * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask registers + * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone + * PCIe host controller driver information. + * + * Since modification of dbi_cs2 involves different clock domain, read the + * status back to ensure the transition is complete. + */ +static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie) { - return dw_pcie_allocate_domains(pp); + u32 val; + + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + val |= DBI_CS2; + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); + + do { + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + } while (!(val & DBI_CS2)); } -static void ks_pcie_enable_legacy_irqs(struct keystone_pcie *ks_pcie) +/** + * ks_pcie_clear_dbi_mode() - Disable DBI mode + * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone + * PCIe host controller driver information. + * + * Since modification of dbi_cs2 involves different clock domain, read the + * status back to ensure the transition is complete. + */ +static void ks_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie) { - int i; + u32 val; - for (i = 0; i < PCI_NUM_INTX; i++) - ks_pcie_app_writel(ks_pcie, IRQ_ENABLE_SET + (i << 4), 0x1); + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + val &= ~DBI_CS2; + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); + + do { + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + } while (val & DBI_CS2); } -static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie, - int offset) +static int ks_pcie_msi_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); + + /* Configure and set up BAR0 */ + ks_pcie_set_dbi_mode(ks_pcie); + + /* Enable BAR0 */ + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1); + + ks_pcie_clear_dbi_mode(ks_pcie); + + /* + * For BAR0, just setting bus address for inbound writes (MSI) should + * be sufficient. Use physical address to avoid any conflicts. + */ + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start); + + pp->msi_irq_chip = &ks_pcie_msi_irq_chip; + return dw_pcie_allocate_domains(pp); +} + +static void ks_pcie_handle_intx_irq(struct keystone_pcie *ks_pcie, + int offset) { struct dw_pcie *pci = ks_pcie->pci; struct device *dev = pci->dev; u32 pending; - int virq; - pending = ks_pcie_app_readl(ks_pcie, IRQ_STATUS + (offset << 4)); + pending = ks_pcie_app_readl(ks_pcie, IRQ_STATUS(offset)); if (BIT(0) & pending) { - virq = irq_linear_revmap(ks_pcie->legacy_irq_domain, offset); - dev_dbg(dev, ": irq: irq_offset %d, virq %d\n", offset, virq); - generic_handle_irq(virq); + dev_dbg(dev, ": irq: irq_offset %d", offset); + generic_handle_domain_irq(ks_pcie->intx_irq_domain, offset); } /* EOI the INTx interrupt */ @@ -255,10 +356,10 @@ static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie) if (reg & ERR_CORR) dev_dbg(dev, "Correctable Error\n"); - if (reg & ERR_AXI) + if (!ks_pcie->is_am6 && (reg & ERR_AXI)) dev_err(dev, "AXI tag lookup fatal Error\n"); - if (reg & ERR_AER) + if (reg & ERR_AER || (ks_pcie->is_am6 && (reg & AM6_ERR_AER))) dev_err(dev, "ECRC Error\n"); ks_pcie_app_writel(ks_pcie, ERR_IRQ_STATUS, reg); @@ -266,96 +367,68 @@ static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie) return IRQ_HANDLED; } -static void ks_pcie_ack_legacy_irq(struct irq_data *d) +static void ks_pcie_ack_intx_irq(struct irq_data *d) { } -static void ks_pcie_mask_legacy_irq(struct irq_data *d) +static void ks_pcie_mask_intx_irq(struct irq_data *d) { } -static void ks_pcie_unmask_legacy_irq(struct irq_data *d) +static void ks_pcie_unmask_intx_irq(struct irq_data *d) { } -static struct irq_chip ks_pcie_legacy_irq_chip = { - .name = "Keystone-PCI-Legacy-IRQ", - .irq_ack = ks_pcie_ack_legacy_irq, - .irq_mask = ks_pcie_mask_legacy_irq, - .irq_unmask = ks_pcie_unmask_legacy_irq, +static struct irq_chip ks_pcie_intx_irq_chip = { + .name = "Keystone-PCI-INTX-IRQ", + .irq_ack = ks_pcie_ack_intx_irq, + .irq_mask = ks_pcie_mask_intx_irq, + .irq_unmask = ks_pcie_unmask_intx_irq, }; -static int ks_pcie_init_legacy_irq_map(struct irq_domain *d, - unsigned int irq, - irq_hw_number_t hw_irq) +static int ks_pcie_init_intx_irq_map(struct irq_domain *d, + unsigned int irq, irq_hw_number_t hw_irq) { - irq_set_chip_and_handler(irq, &ks_pcie_legacy_irq_chip, + irq_set_chip_and_handler(irq, &ks_pcie_intx_irq_chip, handle_level_irq); irq_set_chip_data(irq, d->host_data); return 0; } -static const struct irq_domain_ops ks_pcie_legacy_irq_domain_ops = { - .map = ks_pcie_init_legacy_irq_map, +static const struct irq_domain_ops ks_pcie_intx_irq_domain_ops = { + .map = ks_pcie_init_intx_irq_map, .xlate = irq_domain_xlate_onetwocell, }; -/** - * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask - * registers - * - * Since modification of dbi_cs2 involves different clock domain, read the - * status back to ensure the transition is complete. - */ -static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie) -{ - u32 val; - - val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); - val |= DBI_CS2; - ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); - - do { - val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); - } while (!(val & DBI_CS2)); -} - -/** - * ks_pcie_clear_dbi_mode() - Disable DBI mode - * - * Since modification of dbi_cs2 involves different clock domain, read the - * status back to ensure the transition is complete. - */ -static void ks_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie) -{ - u32 val; - - val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); - val &= ~DBI_CS2; - ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); - - do { - val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); - } while (val & DBI_CS2); -} - -static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie) +static int ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie) { u32 val; u32 num_viewport = ks_pcie->num_viewport; struct dw_pcie *pci = ks_pcie->pci; - struct pcie_port *pp = &pci->pp; - u64 start = pp->mem->start; - u64 end = pp->mem->end; + struct dw_pcie_rp *pp = &pci->pp; + struct resource_entry *entry; + struct resource *mem; + u64 start, end; int i; + entry = resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM); + if (!entry) + return -ENODEV; + + mem = entry->res; + start = mem->start; + end = mem->end; + /* Disable BARs for inbound access */ ks_pcie_set_dbi_mode(ks_pcie); dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0); ks_pcie_clear_dbi_mode(ks_pcie); + if (ks_pcie->is_am6) + return 0; + val = ilog2(OB_WIN_SIZE); ks_pcie_app_writel(ks_pcie, OB_SIZE, val); @@ -365,162 +438,113 @@ static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie) lower_32_bits(start) | OB_ENABLEN); ks_pcie_app_writel(ks_pcie, OB_OFFSET_HI(i), upper_32_bits(start)); - start += OB_WIN_SIZE; + start += OB_WIN_SIZE * SZ_1M; } val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); val |= OB_XLAT_EN_VAL; ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); -} -static int ks_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus, - unsigned int devfn, int where, int size, - u32 *val) -{ - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); - u32 reg; - - reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) | - CFG_FUNC(PCI_FUNC(devfn)); - if (bus->parent->number != pp->root_bus_nr) - reg |= CFG_TYPE1; - ks_pcie_app_writel(ks_pcie, CFG_SETUP, reg); - - return dw_pcie_read(pp->va_cfg0_base + where, size, val); + return 0; } -static int ks_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus, - unsigned int devfn, int where, int size, - u32 val) +static void __iomem *ks_pcie_other_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) { + struct dw_pcie_rp *pp = bus->sysdata; struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); u32 reg; + /* + * Checking whether the link is up here is a last line of defense + * against platforms that forward errors on the system bus as + * SError upon PCI configuration transactions issued when the link + * is down. This check is racy by definition and does not stop + * the system from triggering an SError if the link goes down + * after this check is performed. + */ + if (!dw_pcie_link_up(pci)) + return NULL; + reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) | CFG_FUNC(PCI_FUNC(devfn)); - if (bus->parent->number != pp->root_bus_nr) + if (!pci_is_root_bus(bus->parent)) reg |= CFG_TYPE1; ks_pcie_app_writel(ks_pcie, CFG_SETUP, reg); - return dw_pcie_write(pp->va_cfg0_base + where, size, val); + return pp->va_cfg0_base + where; } -/** - * ks_pcie_v3_65_scan_bus() - keystone scan_bus post initialization - * - * This sets BAR0 to enable inbound access for MSI_IRQ register - */ -static void ks_pcie_v3_65_scan_bus(struct pcie_port *pp) -{ - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); - - /* Configure and set up BAR0 */ - ks_pcie_set_dbi_mode(ks_pcie); - - /* Enable BAR0 */ - dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1); - dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1); - - ks_pcie_clear_dbi_mode(ks_pcie); +static struct pci_ops ks_child_pcie_ops = { + .map_bus = ks_pcie_other_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; - /* - * For BAR0, just setting bus address for inbound writes (MSI) should - * be sufficient. Use physical address to avoid any conflicts. - */ - dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start); -} +static struct pci_ops ks_pcie_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; /** * ks_pcie_link_up() - Check if link up + * @pci: A pointer to the dw_pcie structure which holds the DesignWare PCIe host + * controller driver information. */ -static int ks_pcie_link_up(struct dw_pcie *pci) +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_initiate_link_train(struct keystone_pcie *ks_pcie) +static void ks_pcie_stop_link(struct dw_pcie *pci) { + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); u32 val; /* Disable Link training */ val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); val &= ~LTSSM_EN_VAL; - ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val); - - /* Initiate Link Training */ - val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); - ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val); + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); } -/** - * ks_pcie_dw_host_init() - initialize host for v3_65 dw hardware - * - * Ioremap the register resources, initialize legacy irq domain - * and call dw_pcie_v3_65_host_init() API to initialize the Keystone - * PCI host controller. - */ -static int __init ks_pcie_dw_host_init(struct keystone_pcie *ks_pcie) +static int ks_pcie_start_link(struct dw_pcie *pci) { - struct dw_pcie *pci = ks_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = pci->dev; - struct platform_device *pdev = to_platform_device(dev); - struct resource *res; - - /* Index 0 is the config reg. space address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pci->dbi_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); - - /* - * We set these same and is used in pcie rd/wr_other_conf - * functions - */ - pp->va_cfg0_base = pci->dbi_base + SPACE0_REMOTE_CFG_OFFSET; - pp->va_cfg1_base = pp->va_cfg0_base; - - /* Index 1 is the application reg. space address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - ks_pcie->va_app_base = devm_ioremap_resource(dev, res); - if (IS_ERR(ks_pcie->va_app_base)) - return PTR_ERR(ks_pcie->va_app_base); - - ks_pcie->app = *res; + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + u32 val; - /* Create legacy IRQ domain */ - ks_pcie->legacy_irq_domain = - irq_domain_add_linear(ks_pcie->legacy_intc_np, - PCI_NUM_INTX, - &ks_pcie_legacy_irq_domain_ops, - NULL); - if (!ks_pcie->legacy_irq_domain) { - dev_err(dev, "Failed to add irq domain for legacy irqs\n"); - return -EINVAL; - } + /* Initiate Link Training */ + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val); - return dw_pcie_host_init(pp); + return 0; } static void ks_pcie_quirk(struct pci_dev *dev) { struct pci_bus *bus = dev->bus; + struct keystone_pcie *ks_pcie; + struct device *bridge_dev; struct pci_dev *bridge; + u32 val; + static const struct pci_device_id rc_pci_devids[] = { { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK), - .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, }, + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2E), - .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, }, + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L), - .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, }, + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2G), + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, + { 0, }, + }; + static const struct pci_device_id am6_pci_devids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_AM654X), .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, }, { 0, }, }; @@ -545,41 +569,49 @@ static void ks_pcie_quirk(struct pci_dev *dev) */ if (pci_match_id(rc_pci_devids, bridge)) { if (pcie_get_readrq(dev) > 256) { - dev_info(&dev->dev, "limiting MRRS to 256\n"); + dev_info(&dev->dev, "limiting MRRS to 256 bytes\n"); pcie_set_readrq(dev, 256); } } -} -DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, ks_pcie_quirk); -static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie) -{ - struct dw_pcie *pci = ks_pcie->pci; - struct device *dev = pci->dev; - - if (dw_pcie_link_up(pci)) { - dev_info(dev, "Link already up\n"); - return 0; + /* + * Memory transactions fail with PCI controller in AM654 PG1.0 + * when MRRS is set to more than 128 bytes. Force the MRRS to + * 128 bytes in all downstream devices. + */ + if (pci_match_id(am6_pci_devids, bridge)) { + bridge_dev = pci_get_host_bridge_device(dev); + if (!bridge_dev || !bridge_dev->parent) + return; + + ks_pcie = dev_get_drvdata(bridge_dev->parent); + if (!ks_pcie) + return; + + val = ks_pcie_app_readl(ks_pcie, PID); + val &= RTL; + val >>= RTL_SHIFT; + if (val != AM6_PCI_PG1_RTL_VER) + return; + + if (pcie_get_readrq(dev) > 128) { + dev_info(&dev->dev, "limiting MRRS to 128 bytes\n"); + pcie_set_readrq(dev, 128); + } } - - ks_pcie_initiate_link_train(ks_pcie); - - /* check if the link is up or not */ - if (!dw_pcie_wait_for_link(pci)) - return 0; - - dev_err(dev, "phy link never came up\n"); - return -ETIMEDOUT; } +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, ks_pcie_quirk); static void ks_pcie_msi_irq_handler(struct irq_desc *desc) { - unsigned int irq = irq_desc_get_irq(desc); + unsigned int irq = desc->irq_data.hwirq; struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc); - u32 offset = irq - ks_pcie->msi_host_irqs[0]; + u32 offset = irq - ks_pcie->msi_host_irq; struct dw_pcie *pci = ks_pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; struct device *dev = pci->dev; struct irq_chip *chip = irq_desc_get_chip(desc); + u32 vector, reg, pos; dev_dbg(dev, "%s, irq %d\n", __func__, irq); @@ -589,28 +621,41 @@ static void ks_pcie_msi_irq_handler(struct irq_desc *desc) * ack operation. */ chained_irq_enter(chip, desc); - ks_pcie_handle_msi_irq(ks_pcie, offset); + + reg = ks_pcie_app_readl(ks_pcie, MSI_IRQ_STATUS(offset)); + /* + * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit + * shows 1, 9, 17, 25 and so forth + */ + for (pos = 0; pos < 4; pos++) { + if (!(reg & BIT(pos))) + continue; + + vector = offset + (pos << 3); + dev_dbg(dev, "irq: bit %d, vector %d\n", pos, vector); + generic_handle_domain_irq(pp->irq_domain, vector); + } + chained_irq_exit(chip, desc); } /** - * ks_pcie_legacy_irq_handler() - Handle legacy interrupt - * @irq: IRQ line for legacy interrupts + * ks_pcie_intx_irq_handler() - Handle INTX interrupt * @desc: Pointer to irq descriptor * - * Traverse through pending legacy interrupts and invoke handler for each. Also + * Traverse through pending INTX interrupts and invoke handler for each. Also * takes care of interrupt controller level mask/ack operation. */ -static void ks_pcie_legacy_irq_handler(struct irq_desc *desc) +static void ks_pcie_intx_irq_handler(struct irq_desc *desc) { unsigned int irq = irq_desc_get_irq(desc); struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc); struct dw_pcie *pci = ks_pcie->pci; struct device *dev = pci->dev; - u32 irq_offset = irq - ks_pcie->legacy_host_irqs[0]; + u32 irq_offset = irq - ks_pcie->intx_host_irqs[0]; struct irq_chip *chip = irq_desc_get_chip(desc); - dev_dbg(dev, ": Handling legacy irq %d\n", irq); + dev_dbg(dev, ": Handling INTX irq %d\n", irq); /* * The chained irq handler installation would have replaced normal @@ -618,114 +663,122 @@ static void ks_pcie_legacy_irq_handler(struct irq_desc *desc) * ack operation. */ chained_irq_enter(chip, desc); - ks_pcie_handle_legacy_irq(ks_pcie, irq_offset); + ks_pcie_handle_intx_irq(ks_pcie, irq_offset); chained_irq_exit(chip, desc); } -static int ks_pcie_get_irq_controller_info(struct keystone_pcie *ks_pcie, - char *controller, int *num_irqs) +static int ks_pcie_config_msi_irq(struct keystone_pcie *ks_pcie) { - int temp, max_host_irqs, legacy = 1, *host_irqs; struct device *dev = ks_pcie->pci->dev; - struct device_node *np_pcie = dev->of_node, **np_temp; - - if (!strcmp(controller, "msi-interrupt-controller")) - legacy = 0; - - if (legacy) { - np_temp = &ks_pcie->legacy_intc_np; - max_host_irqs = PCI_NUM_INTX; - host_irqs = &ks_pcie->legacy_host_irqs[0]; - } else { - np_temp = &ks_pcie->msi_intc_np; - max_host_irqs = MAX_MSI_HOST_IRQS; - host_irqs = &ks_pcie->msi_host_irqs[0]; - } + struct device_node *np = ks_pcie->np; + struct device_node *intc_np; + struct irq_data *irq_data; + int irq_count, irq, ret, i; - /* interrupt controller is in a child node */ - *np_temp = of_get_child_by_name(np_pcie, controller); - if (!(*np_temp)) { - dev_err(dev, "Node for %s is absent\n", controller); - return -EINVAL; - } + if (!IS_ENABLED(CONFIG_PCI_MSI)) + return 0; - temp = of_irq_count(*np_temp); - if (!temp) { - dev_err(dev, "No IRQ entries in %s\n", controller); - of_node_put(*np_temp); + intc_np = of_get_child_by_name(np, "msi-interrupt-controller"); + if (!intc_np) { + if (ks_pcie->is_am6) + return 0; + dev_warn(dev, "msi-interrupt-controller node is absent\n"); return -EINVAL; } - if (temp > max_host_irqs) - dev_warn(dev, "Too many %s interrupts defined %u\n", - (legacy ? "legacy" : "MSI"), temp); - - /* - * support upto max_host_irqs. In dt from index 0 to 3 (legacy) or 0 to - * 7 (MSI) - */ - for (temp = 0; temp < max_host_irqs; temp++) { - host_irqs[temp] = irq_of_parse_and_map(*np_temp, temp); - if (!host_irqs[temp]) - break; + irq_count = of_irq_count(intc_np); + if (!irq_count) { + dev_err(dev, "No IRQ entries in msi-interrupt-controller\n"); + ret = -EINVAL; + goto err; } - of_node_put(*np_temp); + for (i = 0; i < irq_count; i++) { + irq = irq_of_parse_and_map(intc_np, i); + if (!irq) { + ret = -EINVAL; + goto err; + } - if (temp) { - *num_irqs = temp; - return 0; + if (!ks_pcie->msi_host_irq) { + irq_data = irq_get_irq_data(irq); + if (!irq_data) { + ret = -EINVAL; + goto err; + } + ks_pcie->msi_host_irq = irq_data->hwirq; + } + + irq_set_chained_handler_and_data(irq, ks_pcie_msi_irq_handler, + ks_pcie); } - return -EINVAL; + of_node_put(intc_np); + return 0; + +err: + of_node_put(intc_np); + return ret; } -static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie) +static int ks_pcie_config_intx_irq(struct keystone_pcie *ks_pcie) { - int i; - - /* Legacy IRQ */ - for (i = 0; i < ks_pcie->num_legacy_host_irqs; i++) { - irq_set_chained_handler_and_data(ks_pcie->legacy_host_irqs[i], - ks_pcie_legacy_irq_handler, - ks_pcie); - } - ks_pcie_enable_legacy_irqs(ks_pcie); - - /* MSI IRQ */ - if (IS_ENABLED(CONFIG_PCI_MSI)) { - for (i = 0; i < ks_pcie->num_msi_host_irqs; i++) { - irq_set_chained_handler_and_data(ks_pcie->msi_host_irqs[i], - ks_pcie_msi_irq_handler, - ks_pcie); - } + struct device *dev = ks_pcie->pci->dev; + struct irq_domain *intx_irq_domain; + struct device_node *np = ks_pcie->np; + struct device_node *intc_np; + int irq_count, irq, ret = 0, i; + + intc_np = of_get_child_by_name(np, "legacy-interrupt-controller"); + if (!intc_np) { + /* + * Since INTX interrupts are modeled as edge-interrupts in + * AM6, keep it disabled for now. + */ + if (ks_pcie->is_am6) + return 0; + dev_warn(dev, "legacy-interrupt-controller node is absent\n"); + return -EINVAL; } - if (ks_pcie->error_irq > 0) - ks_pcie_enable_error_irq(ks_pcie); -} + irq_count = of_irq_count(intc_np); + if (!irq_count) { + dev_err(dev, "No IRQ entries in legacy-interrupt-controller\n"); + ret = -EINVAL; + goto err; + } -/* - * When a PCI device does not exist during config cycles, keystone host gets a - * bus error instead of returning 0xffffffff. This handler always returns 0 - * for this kind of faults. - */ -static int ks_pcie_fault(unsigned long addr, unsigned int fsr, - struct pt_regs *regs) -{ - unsigned long instr = *(unsigned long *) instruction_pointer(regs); + for (i = 0; i < irq_count; i++) { + irq = irq_of_parse_and_map(intc_np, i); + if (!irq) { + ret = -EINVAL; + goto err; + } + ks_pcie->intx_host_irqs[i] = irq; - if ((instr & 0x0e100090) == 0x00100090) { - int reg = (instr >> 12) & 15; + irq_set_chained_handler_and_data(irq, + ks_pcie_intx_irq_handler, + ks_pcie); + } - regs->uregs[reg] = -1; - regs->ARM_pc += 4; + 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"); + ret = -EINVAL; + goto err; } + ks_pcie->intx_irq_domain = intx_irq_domain; - return 0; + for (i = 0; i < PCI_NUM_INTX; i++) + ks_pcie_app_writel(ks_pcie, IRQ_ENABLE_SET(i), INTx_EN); + +err: + of_node_put(intc_np); + return ret; } -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; @@ -733,32 +786,53 @@ static int __init ks_pcie_init_id(struct keystone_pcie *ks_pcie) struct dw_pcie *pci = ks_pcie->pci; struct device *dev = pci->dev; struct device_node *np = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; devctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-id"); if (IS_ERR(devctrl_regs)) return PTR_ERR(devctrl_regs); - ret = regmap_read(devctrl_regs, 0, &id); + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-pcie-id", 1, 0, &args); + if (!ret) + offset = args.args[0]; + + ret = regmap_read(devctrl_regs, offset, &id); if (ret) return ret; + dw_pcie_dbi_ro_wr_en(pci); dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, id & PCIE_VENDORID_MASK); dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, id >> PCIE_DEVICEID_SHIFT); + dw_pcie_dbi_ro_wr_dis(pci); return 0; } -static int __init ks_pcie_host_init(struct pcie_port *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); int ret; - dw_pcie_setup_rc(pp); + pp->bridge->ops = &ks_pcie_ops; + if (!ks_pcie->is_am6) + pp->bridge->child_ops = &ks_child_pcie_ops; + + ret = ks_pcie_config_intx_irq(ks_pcie); + if (ret) + return ret; + + ret = ks_pcie_config_msi_irq(ks_pcie); + if (ret) + return ret; + + ks_pcie_stop_link(pci); + ret = ks_pcie_setup_rc_app_regs(ks_pcie); + if (ret) + return ret; - ks_pcie_establish_link(ks_pcie); - ks_pcie_setup_rc_app_regs(ks_pcie); - ks_pcie_setup_interrupts(ks_pcie); writew(PCI_IO_RANGE_TYPE_32 | (PCI_IO_RANGE_TYPE_32 << 8), pci->dbi_base + PCI_IO_BASE); @@ -766,26 +840,16 @@ static int __init ks_pcie_host_init(struct pcie_port *pp) if (ret < 0) return ret; - /* - * 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"); - return 0; } static const struct dw_pcie_host_ops ks_pcie_host_ops = { - .rd_other_conf = ks_pcie_rd_other_conf, - .wr_other_conf = ks_pcie_wr_other_conf, - .host_init = ks_pcie_host_init, - .msi_set_irq = ks_pcie_msi_set_irq, - .msi_clear_irq = ks_pcie_msi_clear_irq, - .get_msi_addr = ks_pcie_get_msi_addr, - .msi_host_init = ks_pcie_msi_host_init, - .msi_irq_ack = ks_pcie_msi_irq_ack, - .scan_bus = ks_pcie_v3_65_scan_bus, + .init = ks_pcie_host_init, + .msi_init = ks_pcie_msi_host_init, +}; + +static const struct dw_pcie_host_ops ks_pcie_am654_host_ops = { + .init = ks_pcie_host_init, }; static irqreturn_t ks_pcie_err_irq_handler(int irq, void *priv) @@ -795,65 +859,98 @@ static irqreturn_t ks_pcie_err_irq_handler(int irq, void *priv) return ks_pcie_handle_error_irq(ks_pcie); } -static int __init ks_pcie_add_pcie_port(struct keystone_pcie *ks_pcie, - struct platform_device *pdev) +static void ks_pcie_am654_write_dbi2(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + + ks_pcie_set_dbi_mode(ks_pcie); + dw_pcie_write(base + reg, size, val); + ks_pcie_clear_dbi_mode(ks_pcie); +} + +static const struct dw_pcie_ops ks_pcie_dw_pcie_ops = { + .start_link = ks_pcie_start_link, + .stop_link = ks_pcie_stop_link, + .link_up = ks_pcie_link_up, + .write_dbi2 = ks_pcie_am654_write_dbi2, +}; + +static void ks_pcie_am654_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + int flags; + + ep->page_size = AM654_WIN_SIZE; + flags = PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_32; + dw_pcie_writel_dbi2(pci, PCI_BASE_ADDRESS_0, APP_ADDR_SPACE_0 - 1); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, flags); +} + +static void ks_pcie_am654_raise_intx_irq(struct keystone_pcie *ks_pcie) { struct dw_pcie *pci = ks_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = &pdev->dev; - int ret; + u8 int_pin; - ret = ks_pcie_get_irq_controller_info(ks_pcie, - "legacy-interrupt-controller", - &ks_pcie->num_legacy_host_irqs); - if (ret) - return ret; + int_pin = dw_pcie_readb_dbi(pci, PCI_INTERRUPT_PIN); + if (int_pin == 0 || int_pin > 4) + return; - if (IS_ENABLED(CONFIG_PCI_MSI)) { - ret = ks_pcie_get_irq_controller_info(ks_pcie, - "msi-interrupt-controller", - &ks_pcie->num_msi_host_irqs); - if (ret) - return ret; - } + ks_pcie_app_writel(ks_pcie, PCIE_LEGACY_IRQ_ENABLE_SET(int_pin), + INT_ENABLE); + ks_pcie_app_writel(ks_pcie, PCIE_EP_IRQ_SET, INT_ENABLE); + mdelay(1); + ks_pcie_app_writel(ks_pcie, PCIE_EP_IRQ_CLR, INT_ENABLE); + ks_pcie_app_writel(ks_pcie, PCIE_LEGACY_IRQ_ENABLE_CLR(int_pin), + INT_ENABLE); +} - /* - * Index 0 is the platform interrupt for error interrupt - * from RC. This is optional. - */ - ks_pcie->error_irq = irq_of_parse_and_map(ks_pcie->np, 0); - if (ks_pcie->error_irq <= 0) - dev_info(dev, "no error IRQ defined\n"); - else { - ret = request_irq(ks_pcie->error_irq, ks_pcie_err_irq_handler, - IRQF_SHARED, "pcie-error-irq", ks_pcie); - if (ret < 0) { - dev_err(dev, "failed to request error IRQ %d\n", - ks_pcie->error_irq); - return ret; - } - } +static int ks_pcie_am654_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); + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); - pp->ops = &ks_pcie_host_ops; - ret = ks_pcie_dw_host_init(ks_pcie); - if (ret) { - dev_err(dev, "failed to initialize host\n"); - return ret; + switch (type) { + case PCI_IRQ_INTX: + ks_pcie_am654_raise_intx_irq(ks_pcie); + break; + case PCI_IRQ_MSI: + dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + break; + case PCI_IRQ_MSIX: + dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); + break; + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + return -EINVAL; } return 0; } -static const struct of_device_id ks_pcie_of_match[] = { - { - .type = "pci", - .compatible = "ti,keystone-pcie", - }, - { }, +static const struct pci_epc_features ks_pcie_am654_epc_features = { + .msi_capable = true, + .msix_capable = true, + .bar[BAR_0] = { .type = BAR_RESERVED, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .type = BAR_RESIZABLE, }, + .bar[BAR_3] = { .type = BAR_FIXED, .fixed_size = SZ_64K, }, + .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256, }, + .bar[BAR_5] = { .type = BAR_RESIZABLE, }, + .align = SZ_64K, }; -static const struct dw_pcie_ops ks_pcie_dw_pcie_ops = { - .link_up = ks_pcie_link_up, +static const struct pci_epc_features* +ks_pcie_am654_get_features(struct dw_pcie_ep *ep) +{ + return &ks_pcie_am654_epc_features; +} + +static const struct dw_pcie_ep_ops ks_pcie_am654_ep_ops = { + .init = ks_pcie_am654_ep_init, + .raise_irq = ks_pcie_am654_raise_irq, + .get_features = &ks_pcie_am654_get_features, }; static void ks_pcie_disable_phy(struct keystone_pcie *ks_pcie) @@ -873,6 +970,10 @@ static int ks_pcie_enable_phy(struct keystone_pcie *ks_pcie) int num_lanes = ks_pcie->num_lanes; for (i = 0; i < num_lanes; i++) { + ret = phy_reset(ks_pcie->phy[i]); + if (ret < 0) + goto err_phy; + ret = phy_init(ks_pcie->phy[i]); if (ret < 0) goto err_phy; @@ -895,20 +996,148 @@ err_phy: return ret; } -static int __init ks_pcie_probe(struct platform_device *pdev) +static int ks_pcie_set_mode(struct device *dev) +{ + struct device_node *np = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; + struct regmap *syscon; + u32 val; + u32 mask; + int ret = 0; + + syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-mode"); + if (IS_ERR(syscon)) + return 0; + + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-pcie-mode", 1, 0, &args); + if (!ret) + offset = args.args[0]; + + mask = KS_PCIE_DEV_TYPE_MASK | KS_PCIE_SYSCLOCKOUTEN; + val = KS_PCIE_DEV_TYPE(RC) | KS_PCIE_SYSCLOCKOUTEN; + + ret = regmap_update_bits(syscon, offset, mask, val); + if (ret) { + dev_err(dev, "failed to set pcie mode\n"); + return ret; + } + + return 0; +} + +static int ks_pcie_am654_set_mode(struct device *dev, + enum dw_pcie_device_mode mode) { + struct device_node *np = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; + struct regmap *syscon; + u32 val; + u32 mask; + int ret = 0; + + syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-mode"); + if (IS_ERR(syscon)) + return 0; + + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-pcie-mode", 1, 0, &args); + if (!ret) + offset = args.args[0]; + + mask = AM654_PCIE_DEV_TYPE_MASK; + + switch (mode) { + case DW_PCIE_RC_TYPE: + val = RC; + break; + case DW_PCIE_EP_TYPE: + val = EP; + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + return -EINVAL; + } + + ret = regmap_update_bits(syscon, offset, mask, val); + if (ret) { + dev_err(dev, "failed to set pcie mode\n"); + return ret; + } + + return 0; +} + +static const struct ks_pcie_of_data ks_pcie_rc_of_data = { + .host_ops = &ks_pcie_host_ops, + .mode = DW_PCIE_RC_TYPE, + .version = DW_PCIE_VER_365A, +}; + +static const struct ks_pcie_of_data ks_pcie_am654_rc_of_data = { + .host_ops = &ks_pcie_am654_host_ops, + .mode = DW_PCIE_RC_TYPE, + .version = DW_PCIE_VER_490A, +}; + +static const struct ks_pcie_of_data ks_pcie_am654_ep_of_data = { + .ep_ops = &ks_pcie_am654_ep_ops, + .mode = DW_PCIE_EP_TYPE, + .version = DW_PCIE_VER_490A, +}; + +static const struct of_device_id ks_pcie_of_match[] = { + { + .type = "pci", + .data = &ks_pcie_rc_of_data, + .compatible = "ti,keystone-pcie", + }, + { + .data = &ks_pcie_am654_rc_of_data, + .compatible = "ti,am654-pcie-rc", + }, + { + .data = &ks_pcie_am654_ep_of_data, + .compatible = "ti,am654-pcie-ep", + }, + { }, +}; +MODULE_DEVICE_TABLE(of, ks_pcie_of_match); + +static int ks_pcie_probe(struct platform_device *pdev) +{ + const struct dw_pcie_host_ops *host_ops; + const struct dw_pcie_ep_ops *ep_ops; struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; + const struct ks_pcie_of_data *data; + enum dw_pcie_device_mode mode; struct dw_pcie *pci; struct keystone_pcie *ks_pcie; struct device_link **link; + struct gpio_desc *gpiod; + struct resource *res; + void __iomem *base; u32 num_viewport; struct phy **phy; u32 num_lanes; char name[10]; + u32 version; int ret; + int irq; int i; + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + version = data->version; + host_ops = data->host_ops; + ep_ops = data->ep_ops; + mode = data->mode; + ks_pcie = devm_kzalloc(dev, sizeof(*ks_pcie), GFP_KERNEL); if (!ks_pcie) return -ENOMEM; @@ -917,12 +1146,36 @@ static int __init ks_pcie_probe(struct platform_device *pdev) if (!pci) return -ENOMEM; + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "app"); + ks_pcie->va_app_base = devm_ioremap_resource(dev, res); + if (IS_ERR(ks_pcie->va_app_base)) + return PTR_ERR(ks_pcie->va_app_base); + + ks_pcie->app = *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbics"); + base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + if (of_device_is_compatible(np, "ti,am654-pcie-rc")) + ks_pcie->is_am6 = true; + + pci->dbi_base = base; + pci->dbi_base2 = base; pci->dev = dev; pci->ops = &ks_pcie_dw_pcie_ops; + pci->version = version; - ret = of_property_read_u32(np, "num-viewport", &num_viewport); + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + 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, "unable to read *num-viewport* property\n"); + dev_err(dev, "failed to request error IRQ %d\n", + irq); return ret; } @@ -930,11 +1183,11 @@ static int __init 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; @@ -960,10 +1213,27 @@ static int __init ks_pcie_probe(struct platform_device *pdev) ks_pcie->pci = pci; ks_pcie->link = link; ks_pcie->num_lanes = num_lanes; - ks_pcie->num_viewport = num_viewport; ks_pcie->phy = phy; + gpiod = devm_gpiod_get_optional(dev, "reset", + GPIOD_OUT_LOW); + if (IS_ERR(gpiod)) { + ret = PTR_ERR(gpiod); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get reset GPIO\n"); + goto err_link; + } + + /* Obtain references to the PHYs */ + for (i = 0; i < num_lanes; i++) + phy_pm_runtime_get_sync(ks_pcie->phy[i]); + ret = ks_pcie_enable_phy(ks_pcie); + + /* Release references to the PHYs */ + for (i = 0; i < num_lanes; i++) + phy_pm_runtime_put_sync(ks_pcie->phy[i]); + if (ret) { dev_err(dev, "failed to enable phy\n"); goto err_link; @@ -977,12 +1247,77 @@ static int __init ks_pcie_probe(struct platform_device *pdev) goto err_get_sync; } - ret = ks_pcie_add_pcie_port(ks_pcie, pdev); + if (dw_pcie_ver_is_ge(pci, 480A)) + ret = ks_pcie_am654_set_mode(dev, mode); + else + ret = ks_pcie_set_mode(dev); if (ret < 0) goto err_get_sync; + switch (mode) { + case DW_PCIE_RC_TYPE: + if (!IS_ENABLED(CONFIG_PCI_KEYSTONE_HOST)) { + ret = -ENODEV; + goto err_get_sync; + } + + ret = of_property_read_u32(np, "num-viewport", &num_viewport); + if (ret < 0) { + dev_err(dev, "unable to read *num-viewport* property\n"); + goto err_get_sync; + } + + /* + * "Power Sequencing and Reset Signal Timings" table in + * PCI EXPRESS CARD ELECTROMECHANICAL SPECIFICATION, REV. 2.0 + * indicates PERST# should be deasserted after minimum of 100us + * once REFCLK is stable. The REFCLK to the connector in RC + * mode is selected while enabling the PHY. So deassert PERST# + * after 100 us. + */ + if (gpiod) { + usleep_range(100, 200); + gpiod_set_value_cansleep(gpiod, 1); + } + + ks_pcie->num_viewport = num_viewport; + pci->pp.ops = host_ops; + ret = dw_pcie_host_init(&pci->pp); + if (ret < 0) + goto err_get_sync; + break; + case DW_PCIE_EP_TYPE: + if (!IS_ENABLED(CONFIG_PCI_KEYSTONE_EP)) { + ret = -ENODEV; + goto err_get_sync; + } + + pci->ep.ops = ep_ops; + ret = dw_pcie_ep_init(&pci->ep); + if (ret < 0) + goto err_get_sync; + + ret = dw_pcie_ep_init_registers(&pci->ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + goto err_ep_init; + } + + pci_epc_init_notify(pci->ep.epc); + + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + ret = -EINVAL; + goto err_get_sync; + } + + ks_pcie_enable_error_irq(ks_pcie); + return 0; +err_ep_init: + dw_pcie_ep_deinit(&pci->ep); err_get_sync: pm_runtime_put(dev); pm_runtime_disable(dev); @@ -995,7 +1330,7 @@ err_link: return ret; } -static int __exit ks_pcie_remove(struct platform_device *pdev) +static void ks_pcie_remove(struct platform_device *pdev) { struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev); struct device_link **link = ks_pcie->link; @@ -1007,16 +1342,55 @@ static int __exit ks_pcie_remove(struct platform_device *pdev) ks_pcie_disable_phy(ks_pcie); while (num_lanes--) device_link_del(link[num_lanes]); - - return 0; } -static struct platform_driver ks_pcie_driver __refdata = { +static struct platform_driver ks_pcie_driver = { .probe = ks_pcie_probe, - .remove = __exit_p(ks_pcie_remove), + .remove = ks_pcie_remove, .driver = { .name = "keystone-pcie", - .of_match_table = of_match_ptr(ks_pcie_of_match), + .of_match_table = ks_pcie_of_match, }, }; + +#ifdef CONFIG_ARM +/* + * When a PCI device does not exist during config cycles, keystone host + * gets a bus error instead of returning 0xffffffff (PCI_ERROR_RESPONSE). + * This handler always returns 0 for this kind of fault. + */ +static int ks_pcie_fault(unsigned long addr, unsigned int fsr, + struct pt_regs *regs) +{ + unsigned long instr = *(unsigned long *)instruction_pointer(regs); + + if ((instr & 0x0e100090) == 0x00100090) { + int reg = (instr >> 12) & 15; + + regs->uregs[reg] = -1; + regs->ARM_pc += 4; + } + + return 0; +} + +static int __init ks_pcie_init(void) +{ + /* + * PCIe access errors that result into OCP errors are caught by ARM as + * "External aborts" + */ + if (of_find_matching_node(NULL, ks_pcie_of_match)) + hook_fault_code(17, ks_pcie_fault, SIGBUS, 0, + "Asynchronous external abort"); + + return platform_driver_register(&ks_pcie_driver); +} +device_initcall(ks_pcie_init); +#else builtin_platform_driver(ks_pcie_driver); +#endif + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("PCIe controller driver for Texas Instruments Keystone SoCs"); +MODULE_AUTHOR("Murali Karicheri <m-karicheri2@ti.com>"); diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c new file mode 100644 index 000000000000..a4a800699f89 --- /dev/null +++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c @@ -0,0 +1,301 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe controller EP driver for Freescale Layerscape SoCs + * + * Copyright (C) 2018 NXP Semiconductor. + * + * Author: Xiaowei Bao <xiaowei.bao@nxp.com> + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> + +#include "pcie-designware.h" + +#define PEX_PF0_CONFIG 0xC0014 +#define PEX_PF0_CFG_READY BIT(0) + +/* PEX PFa PCIE PME and message interrupt registers*/ +#define PEX_PF0_PME_MES_DR 0xC0020 +#define PEX_PF0_PME_MES_DR_LUD BIT(7) +#define PEX_PF0_PME_MES_DR_LDD BIT(9) +#define PEX_PF0_PME_MES_DR_HRD BIT(10) + +#define PEX_PF0_PME_MES_IER 0xC0028 +#define PEX_PF0_PME_MES_IER_LUDIE BIT(7) +#define PEX_PF0_PME_MES_IER_LDDIE BIT(9) +#define PEX_PF0_PME_MES_IER_HRDIE BIT(10) + +#define to_ls_pcie_ep(x) dev_get_drvdata((x)->dev) + +struct ls_pcie_ep_drvdata { + u32 func_offset; + const struct dw_pcie_ep_ops *ops; + const struct dw_pcie_ops *dw_pcie_ops; +}; + +struct ls_pcie_ep { + struct dw_pcie *pci; + struct pci_epc_features *ls_epc; + const struct ls_pcie_ep_drvdata *drvdata; + int irq; + u32 lnkcap; + bool big_endian; +}; + +static u32 ls_pcie_pf_lut_readl(struct ls_pcie_ep *pcie, u32 offset) +{ + struct dw_pcie *pci = pcie->pci; + + if (pcie->big_endian) + return ioread32be(pci->dbi_base + offset); + else + return ioread32(pci->dbi_base + offset); +} + +static void ls_pcie_pf_lut_writel(struct ls_pcie_ep *pcie, u32 offset, u32 value) +{ + struct dw_pcie *pci = pcie->pci; + + if (pcie->big_endian) + iowrite32be(value, pci->dbi_base + offset); + else + iowrite32(value, pci->dbi_base + offset); +} + +static irqreturn_t ls_pcie_ep_event_handler(int irq, void *dev_id) +{ + struct ls_pcie_ep *pcie = dev_id; + struct dw_pcie *pci = pcie->pci; + u32 val, cfg; + u8 offset; + + val = ls_pcie_pf_lut_readl(pcie, PEX_PF0_PME_MES_DR); + ls_pcie_pf_lut_writel(pcie, PEX_PF0_PME_MES_DR, val); + + if (!val) + return IRQ_NONE; + + if (val & PEX_PF0_PME_MES_DR_LUD) { + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + /* + * The values of the Maximum Link Width and Supported Link + * Speed from the Link Capabilities Register will be lost + * during link down or hot reset. Restore initial value + * that configured by the Reset Configuration Word (RCW). + */ + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, pcie->lnkcap); + dw_pcie_dbi_ro_wr_dis(pci); + + cfg = ls_pcie_pf_lut_readl(pcie, PEX_PF0_CONFIG); + cfg |= PEX_PF0_CFG_READY; + ls_pcie_pf_lut_writel(pcie, PEX_PF0_CONFIG, cfg); + dw_pcie_ep_linkup(&pci->ep); + + dev_dbg(pci->dev, "Link up\n"); + } else if (val & PEX_PF0_PME_MES_DR_LDD) { + dev_dbg(pci->dev, "Link down\n"); + dw_pcie_ep_linkdown(&pci->ep); + } else if (val & PEX_PF0_PME_MES_DR_HRD) { + dev_dbg(pci->dev, "Hot reset\n"); + } + + return IRQ_HANDLED; +} + +static int ls_pcie_ep_interrupt_init(struct ls_pcie_ep *pcie, + struct platform_device *pdev) +{ + u32 val; + int ret; + + pcie->irq = platform_get_irq_byname(pdev, "pme"); + if (pcie->irq < 0) + return pcie->irq; + + ret = devm_request_irq(&pdev->dev, pcie->irq, ls_pcie_ep_event_handler, + IRQF_SHARED, pdev->name, pcie); + if (ret) { + dev_err(&pdev->dev, "Can't register PCIe IRQ\n"); + return ret; + } + + /* Enable interrupts */ + val = ls_pcie_pf_lut_readl(pcie, PEX_PF0_PME_MES_IER); + val |= PEX_PF0_PME_MES_IER_LDDIE | PEX_PF0_PME_MES_IER_HRDIE | + PEX_PF0_PME_MES_IER_LUDIE; + ls_pcie_pf_lut_writel(pcie, PEX_PF0_PME_MES_IER, val); + + return 0; +} + +static const struct pci_epc_features* +ls_pcie_ep_get_features(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci); + + return pcie->ls_epc; +} + +static void ls_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci); + struct dw_pcie_ep_func *ep_func; + enum pci_barno bar; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, 0); + if (!ep_func) + return; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + dw_pcie_ep_reset_bar(pci, bar); + + pcie->ls_epc->msi_capable = ep_func->msi_cap ? true : false; + pcie->ls_epc->msix_capable = ep_func->msix_cap ? true : false; +} + +static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + 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); + case PCI_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq_doorbell(ep, func_no, + interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + return -EINVAL; + } +} + +static unsigned int ls_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep, u8 func_no) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci); + + WARN_ON(func_no && !pcie->drvdata->func_offset); + return pcie->drvdata->func_offset * func_no; +} + +static const struct dw_pcie_ep_ops ls_pcie_ep_ops = { + .init = ls_pcie_ep_init, + .raise_irq = ls_pcie_ep_raise_irq, + .get_features = ls_pcie_ep_get_features, + .get_dbi_offset = ls_pcie_ep_get_dbi_offset, +}; + +static const struct ls_pcie_ep_drvdata ls1_ep_drvdata = { + .ops = &ls_pcie_ep_ops, +}; + +static const struct ls_pcie_ep_drvdata ls2_ep_drvdata = { + .func_offset = 0x20000, + .ops = &ls_pcie_ep_ops, +}; + +static const struct ls_pcie_ep_drvdata lx2_ep_drvdata = { + .func_offset = 0x8000, + .ops = &ls_pcie_ep_ops, +}; + +static const struct of_device_id ls_pcie_ep_of_match[] = { + { .compatible = "fsl,ls1028a-pcie-ep", .data = &ls1_ep_drvdata }, + { .compatible = "fsl,ls1046a-pcie-ep", .data = &ls1_ep_drvdata }, + { .compatible = "fsl,ls1088a-pcie-ep", .data = &ls2_ep_drvdata }, + { .compatible = "fsl,ls2088a-pcie-ep", .data = &ls2_ep_drvdata }, + { .compatible = "fsl,lx2160ar2-pcie-ep", .data = &lx2_ep_drvdata }, + { }, +}; + +static int __init ls_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct ls_pcie_ep *pcie; + struct pci_epc_features *ls_epc; + struct resource *dbi_base; + u8 offset; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + ls_epc = devm_kzalloc(dev, sizeof(*ls_epc), GFP_KERNEL); + if (!ls_epc) + return -ENOMEM; + + pcie->drvdata = of_device_get_match_data(dev); + + pci->dev = dev; + pci->ops = pcie->drvdata->dw_pcie_ops; + + ls_epc->bar[BAR_2].only_64bit = true; + ls_epc->bar[BAR_3].type = BAR_RESERVED; + ls_epc->bar[BAR_4].only_64bit = true; + ls_epc->bar[BAR_5].type = BAR_RESERVED; + ls_epc->linkup_notifier = true; + + pcie->pci = pci; + pcie->ls_epc = ls_epc; + + dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + + pci->ep.ops = &ls_pcie_ep_ops; + + pcie->big_endian = of_property_read_bool(dev->of_node, "big-endian"); + + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + + platform_set_drvdata(pdev, pcie); + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + pcie->lnkcap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + + ret = dw_pcie_ep_init(&pci->ep); + if (ret) + return ret; + + ret = dw_pcie_ep_init_registers(&pci->ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(&pci->ep); + return ret; + } + + pci_epc_init_notify(pci->ep.epc); + + return ls_pcie_ep_interrupt_init(pcie, pdev); +} + +static struct platform_driver ls_pcie_ep_driver = { + .driver = { + .name = "layerscape-pcie-ep", + .of_match_table = ls_pcie_ep_of_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver_probe(ls_pcie_ep_driver, ls_pcie_ep_probe); diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c index ce45bde29bf8..a44b5c256d6e 100644 --- a/drivers/pci/controller/dwc/pci-layerscape.c +++ b/drivers/pci/controller/dwc/pci-layerscape.c @@ -3,16 +3,18 @@ * PCIe host controller driver for Freescale Layerscape SoCs * * Copyright (C) 2014 Freescale Semiconductor. + * Copyright 2021 NXP * * Author: Minghuan Lian <Minghuan.Lian@freescale.com> */ +#include <linux/delay.h> #include <linux/kernel.h> #include <linux/interrupt.h> #include <linux/init.h> +#include <linux/iopoll.h> #include <linux/of_pci.h> #include <linux/of_platform.h> -#include <linux/of_irq.h> #include <linux/of_address.h> #include <linux/pci.h> #include <linux/platform_device.h> @@ -20,37 +22,54 @@ #include <linux/mfd/syscon.h> #include <linux/regmap.h> +#include "../../pci.h" #include "pcie-designware.h" -/* PEX1/2 Misc Ports Status Register */ -#define SCFG_PEXMSCPORTSR(pex_idx) (0x94 + (pex_idx) * 4) -#define LTSSM_STATE_SHIFT 20 -#define LTSSM_STATE_MASK 0x3f -#define LTSSM_PCIE_L0 0x11 /* L0 state */ - /* PEX Internal Configuration Registers */ #define PCIE_STRFMR1 0x71c /* Symbol Timer & Filter Mask Register1 */ #define PCIE_ABSERR 0x8d0 /* Bridge Slave Error Response Register */ #define PCIE_ABSERR_SETTING 0x9401 /* Forward error of non-posted request */ +/* PF Message Command Register */ +#define LS_PCIE_PF_MCR 0x2c +#define PF_MCR_PTOMR BIT(0) +#define PF_MCR_EXL2S BIT(1) + +/* LS1021A PEXn PM Write Control Register */ +#define SCFG_PEXPMWRCR(idx) (0x5c + (idx) * 0x64) +#define PMXMTTURNOFF BIT(31) +#define SCFG_PEXSFTRSTCR 0x190 +#define PEXSR(idx) BIT(idx) + +/* LS1043A PEX PME control register */ +#define SCFG_PEXPMECR 0x144 +#define PEXPME(idx) BIT(31 - (idx) * 4) + +/* LS1043A PEX LUT debug register */ +#define LS_PCIE_LDBG 0x7fc +#define LDBG_SR BIT(30) +#define LDBG_WE BIT(31) + #define PCIE_IATU_NUM 6 struct ls_pcie_drvdata { - u32 lut_offset; - u32 ltssm_shift; - u32 lut_dbg; + const u32 pf_lut_off; const struct dw_pcie_host_ops *ops; - const struct dw_pcie_ops *dw_pcie_ops; + int (*exit_from_l2)(struct dw_pcie_rp *pp); + bool scfg_support; + bool pm_support; }; struct ls_pcie { struct dw_pcie *pci; - void __iomem *lut; - struct regmap *scfg; const struct ls_pcie_drvdata *drvdata; + void __iomem *pf_lut_base; + struct regmap *scfg; int index; + bool big_endian; }; +#define ls_pcie_pf_lut_readl_addr(addr) ls_pcie_pf_lut_readl(pcie, addr) #define to_ls_pcie(x) dev_get_drvdata((x)->dev) static bool ls_pcie_is_bridge(struct ls_pcie *pcie) @@ -59,7 +78,7 @@ static bool ls_pcie_is_bridge(struct ls_pcie *pcie) u32 header_type; header_type = ioread8(pci->dbi_base + PCI_HEADER_TYPE); - header_type &= 0x7f; + header_type &= PCI_HEADER_TYPE_MASK; return header_type == PCI_HEADER_TYPE_BRIDGE; } @@ -83,65 +102,83 @@ static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie) iowrite32(val, pci->dbi_base + PCIE_STRFMR1); } -static void ls_pcie_disable_outbound_atus(struct ls_pcie *pcie) +/* Forward error response of outbound non-posted requests */ +static void ls_pcie_fix_error_response(struct ls_pcie *pcie) { - int i; + struct dw_pcie *pci = pcie->pci; - for (i = 0; i < PCIE_IATU_NUM; i++) - dw_pcie_disable_atu(pcie->pci, i, DW_PCIE_REGION_OUTBOUND); + iowrite32(PCIE_ABSERR_SETTING, pci->dbi_base + PCIE_ABSERR); } -static int ls1021_pcie_link_up(struct dw_pcie *pci) +static u32 ls_pcie_pf_lut_readl(struct ls_pcie *pcie, u32 off) { - u32 state; - struct ls_pcie *pcie = to_ls_pcie(pci); - - if (!pcie->scfg) - return 0; - - regmap_read(pcie->scfg, SCFG_PEXMSCPORTSR(pcie->index), &state); - state = (state >> LTSSM_STATE_SHIFT) & LTSSM_STATE_MASK; + if (pcie->big_endian) + return ioread32be(pcie->pf_lut_base + off); - if (state < LTSSM_PCIE_L0) - return 0; + return ioread32(pcie->pf_lut_base + off); +} - return 1; +static void ls_pcie_pf_lut_writel(struct ls_pcie *pcie, u32 off, u32 val) +{ + if (pcie->big_endian) + iowrite32be(val, pcie->pf_lut_base + off); + else + iowrite32(val, pcie->pf_lut_base + off); } -static int ls_pcie_link_up(struct dw_pcie *pci) +static void ls_pcie_send_turnoff_msg(struct dw_pcie_rp *pp) { + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct ls_pcie *pcie = to_ls_pcie(pci); - u32 state; - - state = (ioread32(pcie->lut + pcie->drvdata->lut_dbg) >> - pcie->drvdata->ltssm_shift) & - LTSSM_STATE_MASK; + u32 val; + int ret; - if (state < LTSSM_PCIE_L0) - return 0; + val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_PF_MCR); + val |= PF_MCR_PTOMR; + ls_pcie_pf_lut_writel(pcie, LS_PCIE_PF_MCR, val); - return 1; + ret = readx_poll_timeout(ls_pcie_pf_lut_readl_addr, LS_PCIE_PF_MCR, + val, !(val & PF_MCR_PTOMR), + PCIE_PME_TO_L2_TIMEOUT_US/10, + PCIE_PME_TO_L2_TIMEOUT_US); + if (ret) + dev_err(pcie->pci->dev, "PME_Turn_off timeout\n"); } -/* Forward error response of outbound non-posted requests */ -static void ls_pcie_fix_error_response(struct ls_pcie *pcie) +static int ls_pcie_exit_from_l2(struct dw_pcie_rp *pp) { - struct dw_pcie *pci = pcie->pci; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct ls_pcie *pcie = to_ls_pcie(pci); + u32 val; + int ret; - iowrite32(PCIE_ABSERR_SETTING, pci->dbi_base + PCIE_ABSERR); + /* + * Set PF_MCR_EXL2S bit in LS_PCIE_PF_MCR register for the link + * to exit L2 state. + */ + val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_PF_MCR); + val |= PF_MCR_EXL2S; + ls_pcie_pf_lut_writel(pcie, LS_PCIE_PF_MCR, val); + + /* + * L2 exit timeout of 10ms is not defined in the specifications, + * it was chosen based on empirical observations. + */ + ret = readx_poll_timeout(ls_pcie_pf_lut_readl_addr, LS_PCIE_PF_MCR, + val, !(val & PF_MCR_EXL2S), + 1000, + 10000); + if (ret) + dev_err(pcie->pci->dev, "L2 exit timeout\n"); + + return ret; } -static int ls_pcie_host_init(struct pcie_port *pp) +static int ls_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct ls_pcie *pcie = to_ls_pcie(pci); - /* - * Disable outbound windows configured by the bootloader to avoid - * one transaction hitting multiple outbound windows. - * dw_pcie_setup_rc() will reconfigure the outbound windows. - */ - ls_pcie_disable_outbound_atus(pcie); ls_pcie_fix_error_response(pcie); dw_pcie_dbi_ro_wr_en(pci); @@ -150,152 +187,148 @@ static int ls_pcie_host_init(struct pcie_port *pp) ls_pcie_drop_msg_tlp(pcie); - dw_pcie_setup_rc(pp); + return 0; +} + +static void scfg_pcie_send_turnoff_msg(struct regmap *scfg, u32 reg, u32 mask) +{ + /* Send PME_Turn_Off message */ + regmap_write_bits(scfg, reg, mask, mask); + + /* + * There is no specific register to check for PME_To_Ack from endpoint. + * So on the safe side, wait for PCIE_PME_TO_L2_TIMEOUT_US. + */ + mdelay(PCIE_PME_TO_L2_TIMEOUT_US/1000); + + /* + * Layerscape hardware reference manual recommends clearing the PMXMTTURNOFF bit + * to complete the PME_Turn_Off handshake. + */ + regmap_write_bits(scfg, reg, mask, 0); +} + +static void ls1021a_pcie_send_turnoff_msg(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct ls_pcie *pcie = to_ls_pcie(pci); + + scfg_pcie_send_turnoff_msg(pcie->scfg, SCFG_PEXPMWRCR(pcie->index), PMXMTTURNOFF); +} + +static int scfg_pcie_exit_from_l2(struct regmap *scfg, u32 reg, u32 mask) +{ + /* Reset the PEX wrapper to bring the link out of L2 */ + regmap_write_bits(scfg, reg, mask, mask); + regmap_write_bits(scfg, reg, mask, 0); return 0; } -static int ls1021_pcie_host_init(struct pcie_port *pp) +static int ls1021a_pcie_exit_from_l2(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct ls_pcie *pcie = to_ls_pcie(pci); - struct device *dev = pci->dev; - u32 index[2]; - int ret; - pcie->scfg = syscon_regmap_lookup_by_phandle(dev->of_node, - "fsl,pcie-scfg"); - if (IS_ERR(pcie->scfg)) { - ret = PTR_ERR(pcie->scfg); - dev_err(dev, "No syscfg phandle specified\n"); - pcie->scfg = NULL; - return ret; - } + return scfg_pcie_exit_from_l2(pcie->scfg, SCFG_PEXSFTRSTCR, PEXSR(pcie->index)); +} - if (of_property_read_u32_array(dev->of_node, - "fsl,pcie-scfg", index, 2)) { - pcie->scfg = NULL; - return -EINVAL; - } - pcie->index = index[1]; +static void ls1043a_pcie_send_turnoff_msg(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct ls_pcie *pcie = to_ls_pcie(pci); - return ls_pcie_host_init(pp); + scfg_pcie_send_turnoff_msg(pcie->scfg, SCFG_PEXPMECR, PEXPME(pcie->index)); } -static int ls_pcie_msi_host_init(struct pcie_port *pp) +static int ls1043a_pcie_exit_from_l2(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct device *dev = pci->dev; - struct device_node *np = dev->of_node; - struct device_node *msi_node; + struct ls_pcie *pcie = to_ls_pcie(pci); + u32 val; /* - * The MSI domain is set by the generic of_msi_configure(). This - * .msi_host_init() function keeps us from doing the default MSI - * domain setup in dw_pcie_host_init() and also enforces the - * requirement that "msi-parent" exists. + * Reset the PEX wrapper to bring the link out of L2. + * LDBG_WE: allows the user to have write access to the PEXDBG[SR] for both setting and + * clearing the soft reset on the PEX module. + * LDBG_SR: When SR is set to 1, the PEX module enters soft reset. */ - msi_node = of_parse_phandle(np, "msi-parent", 0); - if (!msi_node) { - dev_err(dev, "failed to find msi-parent\n"); - return -EINVAL; - } + val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG); + val |= LDBG_WE; + ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val); - return 0; -} + val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG); + val |= LDBG_SR; + ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val); -static const struct dw_pcie_host_ops ls1021_pcie_host_ops = { - .host_init = ls1021_pcie_host_init, - .msi_host_init = ls_pcie_msi_host_init, -}; + val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG); + val &= ~LDBG_SR; + ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val); -static const struct dw_pcie_host_ops ls_pcie_host_ops = { - .host_init = ls_pcie_host_init, - .msi_host_init = ls_pcie_msi_host_init, -}; + val = ls_pcie_pf_lut_readl(pcie, LS_PCIE_LDBG); + val &= ~LDBG_WE; + ls_pcie_pf_lut_writel(pcie, LS_PCIE_LDBG, val); -static const struct dw_pcie_ops dw_ls1021_pcie_ops = { - .link_up = ls1021_pcie_link_up, -}; + return 0; +} -static const struct dw_pcie_ops dw_ls_pcie_ops = { - .link_up = ls_pcie_link_up, +static const struct dw_pcie_host_ops ls_pcie_host_ops = { + .init = ls_pcie_host_init, + .pme_turn_off = ls_pcie_send_turnoff_msg, }; -static const struct ls_pcie_drvdata ls1021_drvdata = { - .ops = &ls1021_pcie_host_ops, - .dw_pcie_ops = &dw_ls1021_pcie_ops, +static const struct dw_pcie_host_ops ls1021a_pcie_host_ops = { + .init = ls_pcie_host_init, + .pme_turn_off = ls1021a_pcie_send_turnoff_msg, }; -static const struct ls_pcie_drvdata ls1043_drvdata = { - .lut_offset = 0x10000, - .ltssm_shift = 24, - .lut_dbg = 0x7fc, - .ops = &ls_pcie_host_ops, - .dw_pcie_ops = &dw_ls_pcie_ops, +static const struct ls_pcie_drvdata ls1021a_drvdata = { + .pm_support = true, + .scfg_support = true, + .ops = &ls1021a_pcie_host_ops, + .exit_from_l2 = ls1021a_pcie_exit_from_l2, }; -static const struct ls_pcie_drvdata ls1046_drvdata = { - .lut_offset = 0x80000, - .ltssm_shift = 24, - .lut_dbg = 0x407fc, - .ops = &ls_pcie_host_ops, - .dw_pcie_ops = &dw_ls_pcie_ops, +static const struct dw_pcie_host_ops ls1043a_pcie_host_ops = { + .init = ls_pcie_host_init, + .pme_turn_off = ls1043a_pcie_send_turnoff_msg, }; -static const struct ls_pcie_drvdata ls2080_drvdata = { - .lut_offset = 0x80000, - .ltssm_shift = 0, - .lut_dbg = 0x7fc, - .ops = &ls_pcie_host_ops, - .dw_pcie_ops = &dw_ls_pcie_ops, +static const struct ls_pcie_drvdata ls1043a_drvdata = { + .pf_lut_off = 0x10000, + .pm_support = true, + .scfg_support = true, + .ops = &ls1043a_pcie_host_ops, + .exit_from_l2 = ls1043a_pcie_exit_from_l2, }; -static const struct ls_pcie_drvdata ls2088_drvdata = { - .lut_offset = 0x80000, - .ltssm_shift = 0, - .lut_dbg = 0x407fc, +static const struct ls_pcie_drvdata layerscape_drvdata = { + .pf_lut_off = 0xc0000, + .pm_support = true, .ops = &ls_pcie_host_ops, - .dw_pcie_ops = &dw_ls_pcie_ops, + .exit_from_l2 = ls_pcie_exit_from_l2, }; static const struct of_device_id ls_pcie_of_match[] = { - { .compatible = "fsl,ls1012a-pcie", .data = &ls1046_drvdata }, - { .compatible = "fsl,ls1021a-pcie", .data = &ls1021_drvdata }, - { .compatible = "fsl,ls1043a-pcie", .data = &ls1043_drvdata }, - { .compatible = "fsl,ls1046a-pcie", .data = &ls1046_drvdata }, - { .compatible = "fsl,ls2080a-pcie", .data = &ls2080_drvdata }, - { .compatible = "fsl,ls2085a-pcie", .data = &ls2080_drvdata }, - { .compatible = "fsl,ls2088a-pcie", .data = &ls2088_drvdata }, - { .compatible = "fsl,ls1088a-pcie", .data = &ls2088_drvdata }, + { .compatible = "fsl,ls1012a-pcie", .data = &layerscape_drvdata }, + { .compatible = "fsl,ls1021a-pcie", .data = &ls1021a_drvdata }, + { .compatible = "fsl,ls1028a-pcie", .data = &layerscape_drvdata }, + { .compatible = "fsl,ls1043a-pcie", .data = &ls1043a_drvdata }, + { .compatible = "fsl,ls1046a-pcie", .data = &layerscape_drvdata }, + { .compatible = "fsl,ls2080a-pcie", .data = &layerscape_drvdata }, + { .compatible = "fsl,ls2085a-pcie", .data = &layerscape_drvdata }, + { .compatible = "fsl,ls2088a-pcie", .data = &layerscape_drvdata }, + { .compatible = "fsl,ls1088a-pcie", .data = &layerscape_drvdata }, { }, }; -static int __init ls_add_pcie_port(struct ls_pcie *pcie) -{ - struct dw_pcie *pci = pcie->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = pci->dev; - int ret; - - pp->ops = pcie->drvdata->ops; - - ret = dw_pcie_host_init(pp); - if (ret) { - dev_err(dev, "failed to initialize host\n"); - return ret; - } - - return 0; -} - -static int __init ls_pcie_probe(struct platform_device *pdev) +static int ls_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct dw_pcie *pci; struct ls_pcie *pcie; struct resource *dbi_base; - int ret; + u32 index[2]; pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) @@ -308,34 +341,75 @@ static int __init ls_pcie_probe(struct platform_device *pdev) pcie->drvdata = of_device_get_match_data(dev); pci->dev = dev; - pci->ops = pcie->drvdata->dw_pcie_ops; - pcie->pci = pci; + pci->pp.ops = pcie->drvdata->ops; dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base); if (IS_ERR(pci->dbi_base)) return PTR_ERR(pci->dbi_base); - pcie->lut = pci->dbi_base + pcie->drvdata->lut_offset; + pcie->big_endian = of_property_read_bool(dev->of_node, "big-endian"); + + pcie->pf_lut_base = pci->dbi_base + pcie->drvdata->pf_lut_off; + + if (pcie->drvdata->scfg_support) { + pcie->scfg = + syscon_regmap_lookup_by_phandle_args(dev->of_node, + "fsl,pcie-scfg", 1, + index); + if (IS_ERR(pcie->scfg)) { + dev_err(dev, "No syscfg phandle specified\n"); + return PTR_ERR(pcie->scfg); + } + + pcie->index = index[1]; + } if (!ls_pcie_is_bridge(pcie)) return -ENODEV; platform_set_drvdata(pdev, pcie); - ret = ls_add_pcie_port(pcie); - if (ret < 0) + return dw_pcie_host_init(&pci->pp); +} + +static int ls_pcie_suspend_noirq(struct device *dev) +{ + struct ls_pcie *pcie = dev_get_drvdata(dev); + + if (!pcie->drvdata->pm_support) + return 0; + + return dw_pcie_suspend_noirq(pcie->pci); +} + +static int ls_pcie_resume_noirq(struct device *dev) +{ + struct ls_pcie *pcie = dev_get_drvdata(dev); + int ret; + + if (!pcie->drvdata->pm_support) + return 0; + + ret = pcie->drvdata->exit_from_l2(&pcie->pci->pp); + if (ret) return ret; - return 0; + return dw_pcie_resume_noirq(pcie->pci); } +static const struct dev_pm_ops ls_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(ls_pcie_suspend_noirq, ls_pcie_resume_noirq) +}; + static struct platform_driver ls_pcie_driver = { + .probe = ls_pcie_probe, .driver = { .name = "layerscape-pcie", .of_match_table = ls_pcie_of_match, .suppress_bind_attrs = true, + .pm = &ls_pcie_pm_ops, }, }; -builtin_platform_driver_probe(ls_pcie_driver, ls_pcie_probe); +builtin_platform_driver(ls_pcie_driver); diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c index e35e9eaa50ee..54b6a4196f17 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -9,44 +9,20 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> -#include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/reset.h> #include <linux/resource.h> #include <linux/types.h> +#include <linux/phy/phy.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> #include "pcie-designware.h" #define to_meson_pcie(x) dev_get_drvdata((x)->dev) -/* External local bus interface registers */ -#define PLR_OFFSET 0x700 -#define PCIE_PORT_LINK_CTRL_OFF (PLR_OFFSET + 0x10) -#define FAST_LINK_MODE BIT(7) -#define LINK_CAPABLE_MASK GENMASK(21, 16) -#define LINK_CAPABLE_X1 BIT(16) - -#define PCIE_GEN2_CTRL_OFF (PLR_OFFSET + 0x10c) -#define NUM_OF_LANES_MASK GENMASK(12, 8) -#define NUM_OF_LANES_X1 BIT(8) -#define DIRECT_SPEED_CHANGE BIT(17) - -#define TYPE1_HDR_OFFSET 0x0 -#define PCIE_STATUS_COMMAND (TYPE1_HDR_OFFSET + 0x04) -#define PCI_IO_EN BIT(0) -#define PCI_MEM_SPACE_EN BIT(1) -#define PCI_BUS_MASTER_EN BIT(2) - -#define PCIE_BASE_ADDR0 (TYPE1_HDR_OFFSET + 0x10) -#define PCIE_BASE_ADDR1 (TYPE1_HDR_OFFSET + 0x14) - -#define PCIE_CAP_OFFSET 0x70 -#define PCIE_DEV_CTRL_DEV_STUS (PCIE_CAP_OFFSET + 0x08) -#define PCIE_CAP_MAX_PAYLOAD_MASK GENMASK(7, 5) #define PCIE_CAP_MAX_PAYLOAD_SIZE(x) ((x) << 5) -#define PCIE_CAP_MAX_READ_REQ_MASK GENMASK(14, 12) #define PCIE_CAP_MAX_READ_REQ_SIZE(x) ((x) << 12) /* PCIe specific config registers */ @@ -65,7 +41,6 @@ #define PORT_CLK_RATE 100000000UL #define MAX_PAYLOAD_SIZE 256 #define MAX_READ_REQ_SIZE 256 -#define MESON_PCIE_PHY_POWERUP 0x1c #define PCIE_RESET_DELAY 500 #define PCIE_SHARED_RESET 1 #define PCIE_NORMAL_RESET 0 @@ -77,31 +52,24 @@ enum pcie_data_rate { PCIE_GEN4 }; -struct meson_pcie_mem_res { - void __iomem *elbi_base; - void __iomem *cfg_base; - void __iomem *phy_base; -}; - struct meson_pcie_clk_res { struct clk *clk; - struct clk *mipi_gate; struct clk *port_clk; struct clk *general_clk; }; struct meson_pcie_rc_reset { - struct reset_control *phy; struct reset_control *port; struct reset_control *apb; }; struct meson_pcie { struct dw_pcie pci; - struct meson_pcie_mem_res mem_res; + void __iomem *cfg_base; struct meson_pcie_clk_res clk_res; struct meson_pcie_rc_reset mrst; struct gpio_desc *reset_gpio; + struct phy *phy; }; static struct reset_control *meson_pcie_get_reset(struct meson_pcie *mp, @@ -123,11 +91,6 @@ static int meson_pcie_get_resets(struct meson_pcie *mp) { struct meson_pcie_rc_reset *mrst = &mp->mrst; - mrst->phy = meson_pcie_get_reset(mp, "phy", PCIE_SHARED_RESET); - if (IS_ERR(mrst->phy)) - return PTR_ERR(mrst->phy); - reset_control_deassert(mrst->phy); - mrst->port = meson_pcie_get_reset(mp, "port", PCIE_NORMAL_RESET); if (IS_ERR(mrst->port)) return PTR_ERR(mrst->port); @@ -141,66 +104,65 @@ static int meson_pcie_get_resets(struct meson_pcie *mp) return 0; } -static void __iomem *meson_pcie_get_mem(struct platform_device *pdev, - struct meson_pcie *mp, - const char *id) -{ - struct device *dev = mp->pci.dev; - struct resource *res; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, id); - - return devm_ioremap_resource(dev, res); -} - -static void __iomem *meson_pcie_get_mem_shared(struct platform_device *pdev, - struct meson_pcie *mp, - const char *id) +static int meson_pcie_get_mems(struct platform_device *pdev, + struct meson_pcie *mp) { - struct device *dev = mp->pci.dev; + struct dw_pcie *pci = &mp->pci; struct resource *res; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, id); - if (!res) { - dev_err(dev, "No REG resource %s\n", id); - return ERR_PTR(-ENXIO); + /* + * 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; } - return devm_ioremap(dev, res->start, resource_size(res)); + mp->cfg_base = devm_platform_ioremap_resource_byname(pdev, "cfg"); + if (IS_ERR(mp->cfg_base)) + return PTR_ERR(mp->cfg_base); + + return 0; } -static int meson_pcie_get_mems(struct platform_device *pdev, - struct meson_pcie *mp) +static int meson_pcie_power_on(struct meson_pcie *mp) { - mp->mem_res.elbi_base = meson_pcie_get_mem(pdev, mp, "elbi"); - if (IS_ERR(mp->mem_res.elbi_base)) - return PTR_ERR(mp->mem_res.elbi_base); + int ret = 0; - mp->mem_res.cfg_base = meson_pcie_get_mem(pdev, mp, "cfg"); - if (IS_ERR(mp->mem_res.cfg_base)) - return PTR_ERR(mp->mem_res.cfg_base); + ret = phy_init(mp->phy); + if (ret) + return ret; - /* Meson SoC has two PCI controllers use same phy register*/ - mp->mem_res.phy_base = meson_pcie_get_mem_shared(pdev, mp, "phy"); - if (IS_ERR(mp->mem_res.phy_base)) - return PTR_ERR(mp->mem_res.phy_base); + ret = phy_power_on(mp->phy); + if (ret) { + phy_exit(mp->phy); + return ret; + } return 0; } -static void meson_pcie_power_on(struct meson_pcie *mp) +static void meson_pcie_power_off(struct meson_pcie *mp) { - writel(MESON_PCIE_PHY_POWERUP, mp->mem_res.phy_base); + phy_power_off(mp->phy); + phy_exit(mp->phy); } -static void meson_pcie_reset(struct meson_pcie *mp) +static int meson_pcie_reset(struct meson_pcie *mp) { struct meson_pcie_rc_reset *mrst = &mp->mrst; + int ret = 0; - reset_control_assert(mrst->phy); - udelay(PCIE_RESET_DELAY); - reset_control_deassert(mrst->phy); - udelay(PCIE_RESET_DELAY); + ret = phy_reset(mp->phy); + if (ret) + return ret; reset_control_assert(mrst->port); reset_control_assert(mrst->apb); @@ -208,6 +170,15 @@ static void meson_pcie_reset(struct meson_pcie *mp) reset_control_deassert(mrst->port); reset_control_deassert(mrst->apb); udelay(PCIE_RESET_DELAY); + + return 0; +} + +static inline void meson_pcie_disable_clock(void *data) +{ + struct clk *clk = data; + + clk_disable_unprepare(clk); } static inline struct clk *meson_pcie_probe_clock(struct device *dev, @@ -234,9 +205,7 @@ static inline struct clk *meson_pcie_probe_clock(struct device *dev, return ERR_PTR(ret); } - devm_add_action_or_reset(dev, - (void (*) (void *))clk_disable_unprepare, - clk); + devm_add_action_or_reset(dev, meson_pcie_disable_clock, clk); return clk; } @@ -250,74 +219,41 @@ static int meson_pcie_probe_clocks(struct meson_pcie *mp) if (IS_ERR(res->port_clk)) return PTR_ERR(res->port_clk); - res->mipi_gate = meson_pcie_probe_clock(dev, "pcie_mipi_en", 0); - if (IS_ERR(res->mipi_gate)) - return PTR_ERR(res->mipi_gate); - - res->general_clk = meson_pcie_probe_clock(dev, "pcie_general", 0); + res->general_clk = meson_pcie_probe_clock(dev, "general", 0); if (IS_ERR(res->general_clk)) return PTR_ERR(res->general_clk); - res->clk = meson_pcie_probe_clock(dev, "pcie", 0); + res->clk = meson_pcie_probe_clock(dev, "pclk", 0); if (IS_ERR(res->clk)) return PTR_ERR(res->clk); return 0; } -static inline void meson_elb_writel(struct meson_pcie *mp, u32 val, u32 reg) -{ - writel(val, mp->mem_res.elbi_base + reg); -} - -static inline u32 meson_elb_readl(struct meson_pcie *mp, u32 reg) -{ - return readl(mp->mem_res.elbi_base + reg); -} - static inline u32 meson_cfg_readl(struct meson_pcie *mp, u32 reg) { - return readl(mp->mem_res.cfg_base + reg); + return readl(mp->cfg_base + reg); } static inline void meson_cfg_writel(struct meson_pcie *mp, u32 val, u32 reg) { - writel(val, mp->mem_res.cfg_base + reg); + writel(val, mp->cfg_base + reg); } static void meson_pcie_assert_reset(struct meson_pcie *mp) { - gpiod_set_value_cansleep(mp->reset_gpio, 0); - udelay(500); gpiod_set_value_cansleep(mp->reset_gpio, 1); + udelay(500); + gpiod_set_value_cansleep(mp->reset_gpio, 0); } -static void meson_pcie_init_dw(struct meson_pcie *mp) +static void meson_pcie_ltssm_enable(struct meson_pcie *mp) { u32 val; val = meson_cfg_readl(mp, PCIE_CFG0); val |= APP_LTSSM_ENABLE; meson_cfg_writel(mp, val, PCIE_CFG0); - - val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF); - val &= ~LINK_CAPABLE_MASK; - meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF); - - val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF); - val |= LINK_CAPABLE_X1 | FAST_LINK_MODE; - meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF); - - val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF); - val &= ~NUM_OF_LANES_MASK; - meson_elb_writel(mp, val, PCIE_GEN2_CTRL_OFF); - - val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF); - val |= NUM_OF_LANES_X1 | DIRECT_SPEED_CHANGE; - meson_elb_writel(mp, val, PCIE_GEN2_CTRL_OFF); - - meson_elb_writel(mp, 0x0, PCIE_BASE_ADDR0); - meson_elb_writel(mp, 0x0, PCIE_BASE_ADDR1); } static int meson_size_to_payload(struct meson_pcie *mp, int size) @@ -339,69 +275,52 @@ static int meson_size_to_payload(struct meson_pcie *mp, int size) static void meson_set_max_payload(struct meson_pcie *mp, int size) { + struct dw_pcie *pci = &mp->pci; u32 val; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); int max_payload_size = meson_size_to_payload(mp, size); - val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); - val &= ~PCIE_CAP_MAX_PAYLOAD_MASK; - meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); + val &= ~PCI_EXP_DEVCTL_PAYLOAD; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); - val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); val |= PCIE_CAP_MAX_PAYLOAD_SIZE(max_payload_size); - meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); } static void meson_set_max_rd_req_size(struct meson_pcie *mp, int size) { + struct dw_pcie *pci = &mp->pci; u32 val; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); int max_rd_req_size = meson_size_to_payload(mp, size); - val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); - val &= ~PCIE_CAP_MAX_READ_REQ_MASK; - meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); + val &= ~PCI_EXP_DEVCTL_READRQ; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); - val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); val |= PCIE_CAP_MAX_READ_REQ_SIZE(max_rd_req_size); - meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); } -static inline void meson_enable_memory_space(struct meson_pcie *mp) +static int meson_pcie_start_link(struct dw_pcie *pci) { - /* Set the RC Bus Master, Memory Space and I/O Space enables */ - meson_elb_writel(mp, PCI_IO_EN | PCI_MEM_SPACE_EN | PCI_BUS_MASTER_EN, - PCIE_STATUS_COMMAND); -} - -static int meson_pcie_establish_link(struct meson_pcie *mp) -{ - struct dw_pcie *pci = &mp->pci; - struct pcie_port *pp = &pci->pp; - - meson_pcie_init_dw(mp); - meson_set_max_payload(mp, MAX_PAYLOAD_SIZE); - meson_set_max_rd_req_size(mp, MAX_READ_REQ_SIZE); - - dw_pcie_setup_rc(pp); - meson_enable_memory_space(mp); + struct meson_pcie *mp = to_meson_pcie(pci); + meson_pcie_ltssm_enable(mp); meson_pcie_assert_reset(mp); - return dw_pcie_wait_for_link(pci); -} - -static void meson_pcie_enable_interrupts(struct meson_pcie *mp) -{ - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(&mp->pci.pp); + return 0; } -static int meson_pcie_rd_own_conf(struct pcie_port *pp, int where, int size, - u32 *val) +static int meson_pcie_rd_own_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 *val) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); int ret; - ret = dw_pcie_read(pci->dbi_base + where, size, val); + ret = pci_generic_config_read(bus, devfn, where, size, val); if (ret != PCIBIOS_SUCCESSFUL) return ret; @@ -410,27 +329,25 @@ static int meson_pcie_rd_own_conf(struct pcie_port *pp, int where, int size, * cannot program the PCI_CLASS_DEVICE register, so we must fabricate * the return value in the config accessors. */ - if (where == PCI_CLASS_REVISION && size == 4) - *val = (PCI_CLASS_BRIDGE_PCI << 16) | (*val & 0xffff); - else if (where == PCI_CLASS_DEVICE && size == 2) - *val = PCI_CLASS_BRIDGE_PCI; - else if (where == PCI_CLASS_DEVICE && size == 1) - *val = PCI_CLASS_BRIDGE_PCI & 0xff; - else if (where == PCI_CLASS_DEVICE + 1 && size == 1) - *val = (PCI_CLASS_BRIDGE_PCI >> 8) & 0xff; + if ((where & ~3) == PCI_CLASS_REVISION) { + if (size <= 2) + *val = (*val & ((1 << (size * 8)) - 1)) << (8 * (where & 3)); + *val &= ~0xffffff00; + *val |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + } return PCIBIOS_SUCCESSFUL; } -static int meson_pcie_wr_own_conf(struct pcie_port *pp, int where, - int size, u32 val) -{ - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - - return dw_pcie_write(pci->dbi_base + where, size, val); -} +static struct pci_ops meson_pci_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = meson_pcie_rd_own_conf, + .write = pci_generic_config_write, +}; -static int meson_pcie_link_up(struct dw_pcie *pci) +static bool meson_pcie_link_up(struct dw_pcie *pci) { struct meson_pcie *mp = to_meson_pcie(pci); struct device *dev = pci->dev; @@ -458,7 +375,7 @@ static int meson_pcie_link_up(struct dw_pcie *pci) dev_dbg(dev, "speed_okay\n"); if (smlh_up && rdlh_up && ltssm_up && speed_okay) - return 1; + return true; cnt++; @@ -466,60 +383,29 @@ static int meson_pcie_link_up(struct dw_pcie *pci) } while (cnt < WAIT_LINKUP_TIMEOUT); dev_err(dev, "error: wait linkup timeout\n"); - return 0; + return false; } -static int meson_pcie_host_init(struct pcie_port *pp) +static int meson_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct meson_pcie *mp = to_meson_pcie(pci); - int ret; - ret = meson_pcie_establish_link(mp); - if (ret) - return ret; + pp->bridge->ops = &meson_pci_ops; - meson_pcie_enable_interrupts(mp); + meson_set_max_payload(mp, MAX_PAYLOAD_SIZE); + meson_set_max_rd_req_size(mp, MAX_READ_REQ_SIZE); return 0; } static const struct dw_pcie_host_ops meson_pcie_host_ops = { - .rd_own_conf = meson_pcie_rd_own_conf, - .wr_own_conf = meson_pcie_wr_own_conf, - .host_init = meson_pcie_host_init, + .init = meson_pcie_host_init, }; -static int meson_add_pcie_port(struct meson_pcie *mp, - struct platform_device *pdev) -{ - struct dw_pcie *pci = &mp->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = &pdev->dev; - int ret; - - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq(pdev, 0); - if (pp->msi_irq < 0) { - dev_err(dev, "failed to get MSI IRQ\n"); - return pp->msi_irq; - } - } - - pp->ops = &meson_pcie_host_ops; - pci->dbi_base = mp->mem_res.elbi_base; - - ret = dw_pcie_host_init(pp); - if (ret) { - dev_err(dev, "failed to initialize host\n"); - return ret; - } - - return 0; -} - static const struct dw_pcie_ops dw_pcie_ops = { .link_up = meson_pcie_link_up, + .start_link = meson_pcie_start_link, }; static int meson_pcie_probe(struct platform_device *pdev) @@ -536,6 +422,14 @@ static int meson_pcie_probe(struct platform_device *pdev) pci = &mp->pci; pci->dev = dev; pci->ops = &dw_pcie_ops; + pci->pp.ops = &meson_pcie_host_ops; + pci->num_lanes = 1; + + mp->phy = devm_phy_get(dev, "pcie"); + if (IS_ERR(mp->phy)) { + dev_err(dev, "get phy failed, %ld\n", PTR_ERR(mp->phy)); + return PTR_ERR(mp->phy); + } mp->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); if (IS_ERR(mp->reset_gpio)) { @@ -555,32 +449,49 @@ static int meson_pcie_probe(struct platform_device *pdev) return ret; } - meson_pcie_power_on(mp); - meson_pcie_reset(mp); + ret = meson_pcie_power_on(mp); + if (ret) { + dev_err(dev, "phy power on failed, %d\n", ret); + return ret; + } + + ret = meson_pcie_reset(mp); + if (ret) { + dev_err(dev, "reset failed, %d\n", ret); + goto err_phy; + } ret = meson_pcie_probe_clocks(mp); if (ret) { dev_err(dev, "init clock resources failed, %d\n", ret); - return ret; + goto err_phy; } platform_set_drvdata(pdev, mp); - ret = meson_add_pcie_port(mp, pdev); + ret = dw_pcie_host_init(&pci->pp); if (ret < 0) { dev_err(dev, "Add PCIe port failed, %d\n", ret); - return ret; + goto err_phy; } return 0; + +err_phy: + meson_pcie_power_off(mp); + return ret; } static const struct of_device_id meson_pcie_of_match[] = { { .compatible = "amlogic,axg-pcie", }, + { + .compatible = "amlogic,g12a-pcie", + }, {}, }; +MODULE_DEVICE_TABLE(of, meson_pcie_of_match); static struct platform_driver meson_pcie_driver = { .probe = meson_pcie_probe, @@ -590,4 +501,8 @@ static struct platform_driver meson_pcie_driver = { }, }; -builtin_platform_driver(meson_pcie_driver); +module_platform_driver(meson_pcie_driver); + +MODULE_AUTHOR("Yue Wang <yue.wang@amlogic.com>"); +MODULE_DESCRIPTION("Amlogic PCIe Controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c new file mode 100644 index 000000000000..345c281c74fe --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-al.c @@ -0,0 +1,391 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Amazon's Annapurna Labs IP (used in chips + * such as Graviton and Alpine) + * + * Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * Author: Jonathan Chocron <jonnyc@amazon.com> + */ + +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/pci-acpi.h> +#include "../../pci.h" + +#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) + +struct al_pcie_acpi { + void __iomem *dbi_base; +}; + +static void __iomem *al_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct al_pcie_acpi *pcie = cfg->priv; + void __iomem *dbi_base = pcie->dbi_base; + + if (bus->number == cfg->busr.start) { + /* + * The DW PCIe core doesn't filter out transactions to other + * devices/functions on the root bus num, so we do this here. + */ + if (PCI_SLOT(devfn) > 0) + return NULL; + else + return dbi_base + where; + } + + return pci_ecam_map_bus(bus, devfn, where); +} + +static int al_pcie_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct acpi_device *adev = to_acpi_device(dev); + struct acpi_pci_root *root = acpi_driver_data(adev); + struct al_pcie_acpi *al_pcie; + struct resource *res; + int ret; + + al_pcie = devm_kzalloc(dev, sizeof(*al_pcie), GFP_KERNEL); + if (!al_pcie) + return -ENOMEM; + + res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL); + if (!res) + return -ENOMEM; + + ret = acpi_get_rc_resources(dev, "AMZN0001", root->segment, res); + if (ret) { + dev_err(dev, "can't get rc dbi base address for SEG %d\n", + root->segment); + return ret; + } + + dev_dbg(dev, "Root port dbi res: %pR\n", res); + + al_pcie->dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(al_pcie->dbi_base)) + return PTR_ERR(al_pcie->dbi_base); + + cfg->priv = al_pcie; + + return 0; +} + +const struct pci_ecam_ops al_pcie_ops = { + .init = al_pcie_init, + .pci_ops = { + .map_bus = al_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +#endif /* defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) */ + +#ifdef CONFIG_PCIE_AL + +#include <linux/of_pci.h> +#include "pcie-designware.h" + +#define AL_PCIE_REV_ID_2 2 +#define AL_PCIE_REV_ID_3 3 +#define AL_PCIE_REV_ID_4 4 + +#define AXI_BASE_OFFSET 0x0 + +#define DEVICE_ID_OFFSET 0x16c + +#define DEVICE_REV_ID 0x0 +#define DEVICE_REV_ID_DEV_ID_MASK GENMASK(31, 16) + +#define DEVICE_REV_ID_DEV_ID_X4 0 +#define DEVICE_REV_ID_DEV_ID_X8 2 +#define DEVICE_REV_ID_DEV_ID_X16 4 + +#define OB_CTRL_REV1_2_OFFSET 0x0040 +#define OB_CTRL_REV3_5_OFFSET 0x0030 + +#define CFG_TARGET_BUS 0x0 +#define CFG_TARGET_BUS_MASK_MASK GENMASK(7, 0) +#define CFG_TARGET_BUS_BUSNUM_MASK GENMASK(15, 8) + +#define CFG_CONTROL 0x4 +#define CFG_CONTROL_SUBBUS_MASK GENMASK(15, 8) +#define CFG_CONTROL_SEC_BUS_MASK GENMASK(23, 16) + +struct al_pcie_reg_offsets { + unsigned int ob_ctrl; +}; + +struct al_pcie_target_bus_cfg { + u8 reg_val; + u8 reg_mask; + u8 ecam_mask; +}; + +struct al_pcie { + struct dw_pcie *pci; + void __iomem *controller_base; /* base of PCIe unit (not DW core) */ + struct device *dev; + resource_size_t ecam_size; + unsigned int controller_rev_id; + struct al_pcie_reg_offsets reg_offsets; + struct al_pcie_target_bus_cfg target_bus_cfg; +}; + +#define to_al_pcie(x) dev_get_drvdata((x)->dev) + +static inline u32 al_pcie_controller_readl(struct al_pcie *pcie, u32 offset) +{ + return readl_relaxed(pcie->controller_base + offset); +} + +static inline void al_pcie_controller_writel(struct al_pcie *pcie, u32 offset, + u32 val) +{ + writel_relaxed(val, pcie->controller_base + offset); +} + +static int al_pcie_rev_id_get(struct al_pcie *pcie, unsigned int *rev_id) +{ + u32 dev_rev_id_val; + u32 dev_id_val; + + dev_rev_id_val = al_pcie_controller_readl(pcie, AXI_BASE_OFFSET + + DEVICE_ID_OFFSET + + DEVICE_REV_ID); + dev_id_val = FIELD_GET(DEVICE_REV_ID_DEV_ID_MASK, dev_rev_id_val); + + switch (dev_id_val) { + case DEVICE_REV_ID_DEV_ID_X4: + *rev_id = AL_PCIE_REV_ID_2; + break; + case DEVICE_REV_ID_DEV_ID_X8: + *rev_id = AL_PCIE_REV_ID_3; + break; + case DEVICE_REV_ID_DEV_ID_X16: + *rev_id = AL_PCIE_REV_ID_4; + break; + default: + dev_err(pcie->dev, "Unsupported dev_id_val (0x%x)\n", + dev_id_val); + return -EINVAL; + } + + dev_dbg(pcie->dev, "dev_id_val: 0x%x\n", dev_id_val); + + return 0; +} + +static int al_pcie_reg_offsets_set(struct al_pcie *pcie) +{ + switch (pcie->controller_rev_id) { + case AL_PCIE_REV_ID_2: + pcie->reg_offsets.ob_ctrl = OB_CTRL_REV1_2_OFFSET; + break; + case AL_PCIE_REV_ID_3: + case AL_PCIE_REV_ID_4: + pcie->reg_offsets.ob_ctrl = OB_CTRL_REV3_5_OFFSET; + break; + default: + dev_err(pcie->dev, "Unsupported controller rev_id: 0x%x\n", + pcie->controller_rev_id); + return -EINVAL; + } + + return 0; +} + +static inline void al_pcie_target_bus_set(struct al_pcie *pcie, + u8 target_bus, + u8 mask_target_bus) +{ + u32 reg; + + reg = FIELD_PREP(CFG_TARGET_BUS_MASK_MASK, mask_target_bus) | + FIELD_PREP(CFG_TARGET_BUS_BUSNUM_MASK, target_bus); + + al_pcie_controller_writel(pcie, AXI_BASE_OFFSET + + pcie->reg_offsets.ob_ctrl + CFG_TARGET_BUS, + reg); +} + +static void __iomem *al_pcie_conf_addr_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct al_pcie *pcie = to_al_pcie(to_dw_pcie_from_pp(pp)); + unsigned int busnr = bus->number; + struct al_pcie_target_bus_cfg *target_bus_cfg = &pcie->target_bus_cfg; + unsigned int busnr_ecam = busnr & target_bus_cfg->ecam_mask; + unsigned int busnr_reg = busnr & target_bus_cfg->reg_mask; + + if (busnr_reg != target_bus_cfg->reg_val) { + dev_dbg(pcie->pci->dev, "Changing target bus busnum val from 0x%x to 0x%x\n", + target_bus_cfg->reg_val, busnr_reg); + target_bus_cfg->reg_val = busnr_reg; + al_pcie_target_bus_set(pcie, + target_bus_cfg->reg_val, + target_bus_cfg->reg_mask); + } + + return pp->va_cfg0_base + PCIE_ECAM_OFFSET(busnr_ecam, devfn, where); +} + +static struct pci_ops al_child_pci_ops = { + .map_bus = al_pcie_conf_addr_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static int al_pcie_config_prepare(struct al_pcie *pcie) +{ + struct al_pcie_target_bus_cfg *target_bus_cfg; + struct dw_pcie_rp *pp = &pcie->pci->pp; + unsigned int ecam_bus_mask; + struct resource_entry *ft; + u32 cfg_control_offset; + struct resource *bus; + u8 subordinate_bus; + u8 secondary_bus; + u32 cfg_control; + u32 reg; + + ft = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS); + if (!ft) + return -ENODEV; + + bus = ft->res; + target_bus_cfg = &pcie->target_bus_cfg; + + ecam_bus_mask = (pcie->ecam_size >> PCIE_ECAM_BUS_SHIFT) - 1; + if (ecam_bus_mask > 255) { + dev_warn(pcie->dev, "ECAM window size is larger than 256MB. Cutting off at 256\n"); + ecam_bus_mask = 255; + } + + /* This portion is taken from the transaction address */ + target_bus_cfg->ecam_mask = ecam_bus_mask; + /* This portion is taken from the cfg_target_bus reg */ + target_bus_cfg->reg_mask = ~target_bus_cfg->ecam_mask; + target_bus_cfg->reg_val = bus->start & target_bus_cfg->reg_mask; + + al_pcie_target_bus_set(pcie, target_bus_cfg->reg_val, + target_bus_cfg->reg_mask); + + secondary_bus = bus->start + 1; + subordinate_bus = bus->end; + + /* Set the valid values of secondary and subordinate buses */ + cfg_control_offset = AXI_BASE_OFFSET + pcie->reg_offsets.ob_ctrl + + CFG_CONTROL; + + cfg_control = al_pcie_controller_readl(pcie, cfg_control_offset); + + reg = cfg_control & + ~(CFG_CONTROL_SEC_BUS_MASK | CFG_CONTROL_SUBBUS_MASK); + + reg |= FIELD_PREP(CFG_CONTROL_SUBBUS_MASK, subordinate_bus) | + FIELD_PREP(CFG_CONTROL_SEC_BUS_MASK, secondary_bus); + + al_pcie_controller_writel(pcie, cfg_control_offset, reg); + + return 0; +} + +static int al_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct al_pcie *pcie = to_al_pcie(pci); + int rc; + + pp->bridge->child_ops = &al_child_pci_ops; + + rc = al_pcie_rev_id_get(pcie, &pcie->controller_rev_id); + if (rc) + return rc; + + rc = al_pcie_reg_offsets_set(pcie); + if (rc) + return rc; + + rc = al_pcie_config_prepare(pcie); + if (rc) + return rc; + + return 0; +} + +static const struct dw_pcie_host_ops al_pcie_host_ops = { + .init = al_pcie_host_init, +}; + +static int al_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *controller_res; + struct resource *ecam_res; + struct al_pcie *al_pcie; + struct dw_pcie *pci; + + al_pcie = devm_kzalloc(dev, sizeof(*al_pcie), GFP_KERNEL); + if (!al_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->pp.ops = &al_pcie_host_ops; + + al_pcie->pci = pci; + al_pcie->dev = dev; + + ecam_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); + if (!ecam_res) { + dev_err(dev, "couldn't find 'config' reg in DT\n"); + return -ENOENT; + } + al_pcie->ecam_size = resource_size(ecam_res); + pci->pp.native_ecam = true; + + controller_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "controller"); + al_pcie->controller_base = devm_ioremap_resource(dev, controller_res); + if (IS_ERR(al_pcie->controller_base)) { + dev_err(dev, "couldn't remap controller base %pR\n", + controller_res); + return PTR_ERR(al_pcie->controller_base); + } + + dev_dbg(dev, "From DT: controller_base: %pR\n", controller_res); + + platform_set_drvdata(pdev, al_pcie); + + return dw_pcie_host_init(&pci->pp); +} + +static const struct of_device_id al_pcie_of_match[] = { + { .compatible = "amazon,al-alpine-v2-pcie", + }, + { .compatible = "amazon,al-alpine-v3-pcie", + }, + {}, +}; + +static struct platform_driver al_pcie_driver = { + .driver = { + .name = "al-pcie", + .of_match_table = al_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = al_pcie_probe, +}; +builtin_platform_driver(al_pcie_driver); + +#endif /* CONFIG_PCIE_AL*/ diff --git a/drivers/pci/controller/dwc/pcie-amd-mdb.c b/drivers/pci/controller/dwc/pcie-amd-mdb.c new file mode 100644 index 000000000000..3c6e837465bb --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-amd-mdb.c @@ -0,0 +1,526 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for AMD MDB PCIe Bridge + * + * Copyright (C) 2024-2025, Advanced Micro Devices, Inc. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/interrupt.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_device.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/types.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +#define AMD_MDB_TLP_IR_STATUS_MISC 0x4C0 +#define AMD_MDB_TLP_IR_MASK_MISC 0x4C4 +#define AMD_MDB_TLP_IR_ENABLE_MISC 0x4C8 +#define AMD_MDB_TLP_IR_DISABLE_MISC 0x4CC + +#define AMD_MDB_TLP_PCIE_INTX_MASK GENMASK(23, 16) + +#define AMD_MDB_PCIE_INTR_INTX_ASSERT(x) BIT((x) * 2) + +/* Interrupt registers definitions. */ +#define AMD_MDB_PCIE_INTR_CMPL_TIMEOUT 15 +#define AMD_MDB_PCIE_INTR_INTX 16 +#define AMD_MDB_PCIE_INTR_PM_PME_RCVD 24 +#define AMD_MDB_PCIE_INTR_PME_TO_ACK_RCVD 25 +#define AMD_MDB_PCIE_INTR_MISC_CORRECTABLE 26 +#define AMD_MDB_PCIE_INTR_NONFATAL 27 +#define AMD_MDB_PCIE_INTR_FATAL 28 + +#define IMR(x) BIT(AMD_MDB_PCIE_INTR_ ##x) +#define AMD_MDB_PCIE_IMR_ALL_MASK \ + ( \ + IMR(CMPL_TIMEOUT) | \ + IMR(PM_PME_RCVD) | \ + IMR(PME_TO_ACK_RCVD) | \ + IMR(MISC_CORRECTABLE) | \ + IMR(NONFATAL) | \ + IMR(FATAL) | \ + AMD_MDB_TLP_PCIE_INTX_MASK \ + ) + +/** + * struct amd_mdb_pcie - PCIe port information + * @pci: DesignWare PCIe controller structure + * @slcr: MDB System Level Control and Status Register (SLCR) base + * @intx_domain: INTx IRQ domain pointer + * @mdb_domain: MDB IRQ domain pointer + * @perst_gpio: GPIO descriptor for PERST# signal handling + * @intx_irq: INTx IRQ interrupt number + */ +struct amd_mdb_pcie { + struct dw_pcie pci; + void __iomem *slcr; + struct irq_domain *intx_domain; + struct irq_domain *mdb_domain; + struct gpio_desc *perst_gpio; + int intx_irq; +}; + +static const struct dw_pcie_host_ops amd_mdb_pcie_host_ops = { +}; + +static void amd_mdb_intx_irq_mask(struct irq_data *data) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(data); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = FIELD_PREP(AMD_MDB_TLP_PCIE_INTX_MASK, + AMD_MDB_PCIE_INTR_INTX_ASSERT(data->hwirq)); + + /* + * Writing '1' to a bit in AMD_MDB_TLP_IR_DISABLE_MISC disables that + * interrupt, writing '0' has no effect. + */ + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_DISABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void amd_mdb_intx_irq_unmask(struct irq_data *data) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(data); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = FIELD_PREP(AMD_MDB_TLP_PCIE_INTX_MASK, + AMD_MDB_PCIE_INTR_INTX_ASSERT(data->hwirq)); + + /* + * Writing '1' to a bit in AMD_MDB_TLP_IR_ENABLE_MISC enables that + * interrupt, writing '0' has no effect. + */ + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_ENABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip amd_mdb_intx_irq_chip = { + .name = "AMD MDB INTx", + .irq_mask = amd_mdb_intx_irq_mask, + .irq_unmask = amd_mdb_intx_irq_unmask, +}; + +/** + * amd_mdb_pcie_intx_map - Set the handler for the INTx and mark IRQ as valid + * @domain: IRQ domain + * @irq: Virtual IRQ number + * @hwirq: Hardware interrupt number + * + * Return: Always returns '0'. + */ +static int amd_mdb_pcie_intx_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &amd_mdb_intx_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + + return 0; +} + +/* INTx IRQ domain operations. */ +static const struct irq_domain_ops amd_intx_domain_ops = { + .map = amd_mdb_pcie_intx_map, +}; + +static irqreturn_t dw_pcie_rp_intx(int irq, void *args) +{ + struct amd_mdb_pcie *pcie = args; + unsigned long val; + int i, int_status; + + val = readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + int_status = FIELD_GET(AMD_MDB_TLP_PCIE_INTX_MASK, val); + + for (i = 0; i < PCI_NUM_INTX; i++) { + if (int_status & AMD_MDB_PCIE_INTR_INTX_ASSERT(i)) + generic_handle_domain_irq(pcie->intx_domain, i); + } + + return IRQ_HANDLED; +} + +#define _IC(x, s)[AMD_MDB_PCIE_INTR_ ## x] = { __stringify(x), s } + +static const struct { + const char *sym; + const char *str; +} intr_cause[32] = { + _IC(CMPL_TIMEOUT, "Completion timeout"), + _IC(PM_PME_RCVD, "PM_PME message received"), + _IC(PME_TO_ACK_RCVD, "PME_TO_ACK message received"), + _IC(MISC_CORRECTABLE, "Correctable error message"), + _IC(NONFATAL, "Non fatal error message"), + _IC(FATAL, "Fatal error message"), +}; + +static void amd_mdb_event_irq_mask(struct irq_data *d) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = BIT(d->hwirq); + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_DISABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void amd_mdb_event_irq_unmask(struct irq_data *d) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = BIT(d->hwirq); + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_ENABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip amd_mdb_event_irq_chip = { + .name = "AMD MDB RC-Event", + .irq_mask = amd_mdb_event_irq_mask, + .irq_unmask = amd_mdb_event_irq_unmask, +}; + +static int amd_mdb_pcie_event_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &amd_mdb_event_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + + return 0; +} + +static const struct irq_domain_ops event_domain_ops = { + .map = amd_mdb_pcie_event_map, +}; + +static irqreturn_t amd_mdb_pcie_event(int irq, void *args) +{ + struct amd_mdb_pcie *pcie = args; + unsigned long val; + int i; + + val = readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + val &= ~readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_MASK_MISC); + for_each_set_bit(i, &val, 32) + generic_handle_domain_irq(pcie->mdb_domain, i); + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + + return IRQ_HANDLED; +} + +static void amd_mdb_pcie_free_irq_domains(struct amd_mdb_pcie *pcie) +{ + if (pcie->intx_domain) { + irq_domain_remove(pcie->intx_domain); + pcie->intx_domain = NULL; + } + + if (pcie->mdb_domain) { + irq_domain_remove(pcie->mdb_domain); + pcie->mdb_domain = NULL; + } +} + +static int amd_mdb_pcie_init_port(struct amd_mdb_pcie *pcie) +{ + unsigned long val; + + /* Disable all TLP interrupts. */ + writel_relaxed(AMD_MDB_PCIE_IMR_ALL_MASK, + pcie->slcr + AMD_MDB_TLP_IR_DISABLE_MISC); + + /* Clear pending TLP interrupts. */ + val = readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + val &= AMD_MDB_PCIE_IMR_ALL_MASK; + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + + /* Enable all TLP interrupts. */ + writel_relaxed(AMD_MDB_PCIE_IMR_ALL_MASK, + pcie->slcr + AMD_MDB_TLP_IR_ENABLE_MISC); + + return 0; +} + +/** + * amd_mdb_pcie_init_irq_domains - Initialize IRQ domain + * @pcie: PCIe port information + * @pdev: Platform device + * + * Return: Returns '0' on success and error value on failure. + */ +static int amd_mdb_pcie_init_irq_domains(struct amd_mdb_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + int err; + + pcie_intc_node = of_get_child_by_name(node, "interrupt-controller"); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -ENODEV; + } + + pcie->mdb_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), 32, + &event_domain_ops, pcie); + if (!pcie->mdb_domain) { + err = -ENOMEM; + dev_err(dev, "Failed to add MDB domain\n"); + goto out; + } + + irq_domain_update_bus_token(pcie->mdb_domain, DOMAIN_BUS_NEXUS); + + pcie->intx_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), + PCI_NUM_INTX, &amd_intx_domain_ops, pcie); + if (!pcie->intx_domain) { + err = -ENOMEM; + dev_err(dev, "Failed to add INTx domain\n"); + goto mdb_out; + } + + of_node_put(pcie_intc_node); + irq_domain_update_bus_token(pcie->intx_domain, DOMAIN_BUS_WIRED); + + raw_spin_lock_init(&pp->lock); + + return 0; +mdb_out: + amd_mdb_pcie_free_irq_domains(pcie); +out: + of_node_put(pcie_intc_node); + return err; +} + +static irqreturn_t amd_mdb_pcie_intr_handler(int irq, void *args) +{ + struct amd_mdb_pcie *pcie = args; + struct device *dev; + struct irq_data *d; + + dev = pcie->pci.dev; + + /* + * In the future, error reporting will be hooked to the AER subsystem. + * Currently, the driver prints a warning message to the user. + */ + d = irq_domain_get_irq_data(pcie->mdb_domain, irq); + if (intr_cause[d->hwirq].str) + dev_warn(dev, "%s\n", intr_cause[d->hwirq].str); + else + dev_warn_once(dev, "Unknown IRQ %ld\n", d->hwirq); + + return IRQ_HANDLED; +} + +static int amd_mdb_setup_irq(struct amd_mdb_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + int i, irq, err; + + amd_mdb_pcie_init_port(pcie); + + pp->irq = platform_get_irq(pdev, 0); + if (pp->irq < 0) + return pp->irq; + + for (i = 0; i < ARRAY_SIZE(intr_cause); i++) { + if (!intr_cause[i].str) + continue; + + irq = irq_create_mapping(pcie->mdb_domain, i); + if (!irq) { + dev_err(dev, "Failed to map MDB domain interrupt\n"); + return -ENOMEM; + } + + err = devm_request_irq(dev, irq, amd_mdb_pcie_intr_handler, + IRQF_NO_THREAD, intr_cause[i].sym, pcie); + if (err) { + dev_err(dev, "Failed to request IRQ %d, err=%d\n", + irq, err); + return err; + } + } + + pcie->intx_irq = irq_create_mapping(pcie->mdb_domain, + AMD_MDB_PCIE_INTR_INTX); + if (!pcie->intx_irq) { + dev_err(dev, "Failed to map INTx interrupt\n"); + return -ENXIO; + } + + err = devm_request_irq(dev, pcie->intx_irq, dw_pcie_rp_intx, + IRQF_NO_THREAD, NULL, pcie); + if (err) { + dev_err(dev, "Failed to request INTx IRQ %d, err=%d\n", + irq, err); + return err; + } + + /* Plug the main event handler. */ + err = devm_request_irq(dev, pp->irq, amd_mdb_pcie_event, IRQF_NO_THREAD, + "amd_mdb pcie_irq", pcie); + if (err) { + dev_err(dev, "Failed to request event IRQ %d, err=%d\n", + pp->irq, err); + return err; + } + + return 0; +} + +static int amd_mdb_parse_pcie_port(struct amd_mdb_pcie *pcie) +{ + struct device *dev = pcie->pci.dev; + struct device_node *pcie_port_node __maybe_unused; + + /* + * This platform currently supports only one Root Port, so the loop + * will execute only once. + * TODO: Enhance the driver to handle multiple Root Ports in the future. + */ + for_each_child_of_node_with_prefix(dev->of_node, pcie_port_node, "pcie") { + pcie->perst_gpio = devm_fwnode_gpiod_get(dev, of_fwnode_handle(pcie_port_node), + "reset", GPIOD_OUT_HIGH, NULL); + if (IS_ERR(pcie->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(pcie->perst_gpio), + "Failed to request reset GPIO\n"); + return 0; + } + + return -ENODEV; +} + +static int amd_mdb_add_pcie_port(struct amd_mdb_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + int err; + + pcie->slcr = devm_platform_ioremap_resource_byname(pdev, "slcr"); + if (IS_ERR(pcie->slcr)) + return PTR_ERR(pcie->slcr); + + err = amd_mdb_pcie_init_irq_domains(pcie, pdev); + if (err) + return err; + + err = amd_mdb_setup_irq(pcie, pdev); + if (err) { + dev_err(dev, "Failed to set up interrupts, err=%d\n", err); + goto out; + } + + pp->ops = &amd_mdb_pcie_host_ops; + + if (pcie->perst_gpio) { + mdelay(PCIE_T_PVPERL_MS); + gpiod_set_value_cansleep(pcie->perst_gpio, 0); + mdelay(PCIE_RESET_CONFIG_WAIT_MS); + } + + err = dw_pcie_host_init(pp); + if (err) { + dev_err(dev, "Failed to initialize host, err=%d\n", err); + goto out; + } + + return 0; + +out: + amd_mdb_pcie_free_irq_domains(pcie); + return err; +} + +static int amd_mdb_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct amd_mdb_pcie *pcie; + struct dw_pcie *pci; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = &pcie->pci; + pci->dev = dev; + + platform_set_drvdata(pdev, pcie); + + ret = amd_mdb_parse_pcie_port(pcie); + /* + * If amd_mdb_parse_pcie_port returns -ENODEV, it indicates that the + * PCIe Bridge node was not found in the device tree. This is not + * considered a fatal error and will trigger a fallback where the + * reset GPIO is acquired directly from the PCIe Host Bridge node. + */ + if (ret) { + if (ret != -ENODEV) + return ret; + + pcie->perst_gpio = devm_gpiod_get_optional(dev, "reset", + GPIOD_OUT_HIGH); + if (IS_ERR(pcie->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(pcie->perst_gpio), + "Failed to request reset GPIO\n"); + } + + return amd_mdb_add_pcie_port(pcie, pdev); +} + +static const struct of_device_id amd_mdb_pcie_of_match[] = { + { + .compatible = "amd,versal2-mdb-host", + }, + {}, +}; + +static struct platform_driver amd_mdb_pcie_driver = { + .driver = { + .name = "amd-mdb-pcie", + .of_match_table = amd_mdb_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = amd_mdb_pcie_probe, +}; + +builtin_platform_driver(amd_mdb_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c index b171b6bc15c8..c2650fd0d458 100644 --- a/drivers/pci/controller/dwc/pcie-armada8k.c +++ b/drivers/pci/controller/dwc/pcie-armada8k.c @@ -21,16 +21,17 @@ #include <linux/platform_device.h> #include <linux/resource.h> #include <linux/of_pci.h> -#include <linux/of_irq.h> -#include <linux/gpio/consumer.h> #include "pcie-designware.h" +#define ARMADA8K_PCIE_MAX_LANES PCIE_LNK_X4 + struct armada8k_pcie { struct dw_pcie *pci; struct clk *clk; struct clk *clk_reg; - struct gpio_desc *reset_gpio; + struct phy *phy[ARMADA8K_PCIE_MAX_LANES]; + unsigned int phy_count; }; #define PCIE_VENDOR_REGS_OFFSET 0x8000 @@ -57,7 +58,7 @@ struct armada8k_pcie { #define PCIE_ARUSER_REG (PCIE_VENDOR_REGS_OFFSET + 0x5C) #define PCIE_AWUSER_REG (PCIE_VENDOR_REGS_OFFSET + 0x60) /* - * AR/AW Cache defauls: Normal memory, Write-Back, Read / Write + * AR/AW Cache defaults: Normal memory, Write-Back, Read / Write * allocate */ #define ARCACHE_DEFAULT_VALUE 0x3511 @@ -69,7 +70,76 @@ struct armada8k_pcie { #define to_armada8k_pcie(x) dev_get_drvdata((x)->dev) -static int armada8k_pcie_link_up(struct dw_pcie *pci) +static void armada8k_pcie_disable_phys(struct armada8k_pcie *pcie) +{ + int i; + + for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) { + phy_power_off(pcie->phy[i]); + phy_exit(pcie->phy[i]); + } +} + +static int armada8k_pcie_enable_phys(struct armada8k_pcie *pcie) +{ + int ret; + int i; + + for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) { + ret = phy_init(pcie->phy[i]); + if (ret) + return ret; + + ret = phy_set_mode_ext(pcie->phy[i], PHY_MODE_PCIE, + pcie->phy_count); + if (ret) { + phy_exit(pcie->phy[i]); + return ret; + } + + ret = phy_power_on(pcie->phy[i]); + if (ret) { + phy_exit(pcie->phy[i]); + return ret; + } + } + + return 0; +} + +static int armada8k_pcie_setup_phys(struct armada8k_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + struct device_node *node = dev->of_node; + int ret = 0; + int i; + + for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) { + pcie->phy[i] = devm_of_phy_get_by_index(dev, node, i); + if (IS_ERR(pcie->phy[i])) { + if (PTR_ERR(pcie->phy[i]) != -ENODEV) + return PTR_ERR(pcie->phy[i]); + + pcie->phy[i] = NULL; + continue; + } + + pcie->phy_count++; + } + + /* Old bindings miss the PHY handle, so just warn if there is no PHY */ + if (!pcie->phy_count) + dev_warn(dev, "No available PHY\n"); + + ret = armada8k_pcie_enable_phys(pcie); + if (ret) + dev_err(dev, "Failed to initialize PHY(s) (%d)\n", ret); + + return ret; +} + +static 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; @@ -77,16 +147,28 @@ 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 false; +} + +static int armada8k_pcie_start_link(struct dw_pcie *pci) +{ + u32 reg; + + /* Start LTSSM */ + reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_CONTROL_REG); + reg |= PCIE_APP_LTSSM_EN; + dw_pcie_writel_dbi(pci, PCIE_GLOBAL_CONTROL_REG, reg); + return 0; } -static void armada8k_pcie_establish_link(struct armada8k_pcie *pcie) +static int armada8k_pcie_host_init(struct dw_pcie_rp *pp) { - struct dw_pcie *pci = pcie->pci; u32 reg; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); if (!dw_pcie_link_up(pci)) { /* Disable LTSSM state machine to enable configuration */ @@ -122,32 +204,6 @@ static void armada8k_pcie_establish_link(struct armada8k_pcie *pcie) PCIE_INT_C_ASSERT_MASK | PCIE_INT_D_ASSERT_MASK; dw_pcie_writel_dbi(pci, PCIE_GLOBAL_INT_MASK1_REG, reg); - if (!dw_pcie_link_up(pci)) { - /* Configuration done. Start LTSSM */ - reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_CONTROL_REG); - reg |= PCIE_APP_LTSSM_EN; - dw_pcie_writel_dbi(pci, PCIE_GLOBAL_CONTROL_REG, reg); - } - - /* Wait until the link becomes active again */ - if (dw_pcie_wait_for_link(pci)) - dev_err(pci->dev, "Link not up after reconfiguration\n"); -} - -static int armada8k_pcie_host_init(struct pcie_port *pp) -{ - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct armada8k_pcie *pcie = to_armada8k_pcie(pci); - - if (pcie->reset_gpio) { - /* assert and then deassert the reset signal */ - gpiod_set_value_cansleep(pcie->reset_gpio, 1); - msleep(100); - gpiod_set_value_cansleep(pcie->reset_gpio, 0); - } - dw_pcie_setup_rc(pp); - armada8k_pcie_establish_link(pcie); - return 0; } @@ -169,24 +225,22 @@ static irqreturn_t armada8k_pcie_irq_handler(int irq, void *arg) } static const struct dw_pcie_host_ops armada8k_pcie_host_ops = { - .host_init = armada8k_pcie_host_init, + .init = armada8k_pcie_host_init, }; static int armada8k_add_pcie_port(struct armada8k_pcie *pcie, struct platform_device *pdev) { struct dw_pcie *pci = pcie->pci; - struct pcie_port *pp = &pci->pp; + struct dw_pcie_rp *pp = &pci->pp; struct device *dev = &pdev->dev; int ret; pp->ops = &armada8k_pcie_host_ops; pp->irq = platform_get_irq(pdev, 0); - if (pp->irq < 0) { - dev_err(dev, "failed to get irq for port\n"); + if (pp->irq < 0) return pp->irq; - } ret = devm_request_irq(dev, pp->irq, armada8k_pcie_irq_handler, IRQF_SHARED, "armada8k-pcie", pcie); @@ -206,6 +260,7 @@ static int armada8k_add_pcie_port(struct armada8k_pcie *pcie, static const struct dw_pcie_ops dw_pcie_ops = { .link_up = armada8k_pcie_link_up, + .start_link = armada8k_pcie_start_link, }; static int armada8k_pcie_probe(struct platform_device *pdev) @@ -252,27 +307,24 @@ static int armada8k_pcie_probe(struct platform_device *pdev) base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl"); pci->dbi_base = devm_pci_remap_cfg_resource(dev, base); if (IS_ERR(pci->dbi_base)) { - dev_err(dev, "couldn't remap regs base %p\n", base); ret = PTR_ERR(pci->dbi_base); goto fail_clkreg; } - /* Get reset gpio signal and hold asserted (logically high) */ - pcie->reset_gpio = devm_gpiod_get_optional(dev, "reset", - GPIOD_OUT_HIGH); - if (IS_ERR(pcie->reset_gpio)) { - ret = PTR_ERR(pcie->reset_gpio); + ret = armada8k_pcie_setup_phys(pcie); + if (ret) goto fail_clkreg; - } platform_set_drvdata(pdev, pcie); ret = armada8k_add_pcie_port(pcie, pdev); if (ret) - goto fail_clkreg; + goto disable_phy; return 0; +disable_phy: + armada8k_pcie_disable_phys(pcie); fail_clkreg: clk_disable_unprepare(pcie->clk_reg); fail: @@ -290,7 +342,7 @@ static struct platform_driver armada8k_pcie_driver = { .probe = armada8k_pcie_probe, .driver = { .name = "armada8k-pcie", - .of_match_table = of_match_ptr(armada8k_pcie_of_match), + .of_match_table = armada8k_pcie_of_match, .suppress_bind_attrs = true, }, }; diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c index dba83abfe764..f4a136ee2daf 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -10,7 +10,7 @@ #include <linux/delay.h> #include <linux/kernel.h> #include <linux/init.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/resource.h> @@ -44,16 +44,6 @@ struct artpec_pcie_of_data { static const struct of_device_id artpec6_pcie_of_match[]; -/* PCIe Port Logic registers (memory-mapped) */ -#define PL_OFFSET 0x700 - -#define ACK_F_ASPM_CTRL_OFF (PL_OFFSET + 0xc) -#define ACK_N_FTS_MASK GENMASK(15, 8) -#define ACK_N_FTS(x) (((x) << 8) & ACK_N_FTS_MASK) - -#define FAST_TRAINING_SEQ_MASK GENMASK(7, 0) -#define FAST_TRAINING_SEQ(x) (((x) << 0) & FAST_TRAINING_SEQ_MASK) - /* ARTPEC-6 specific registers */ #define PCIECFG 0x18 #define PCIECFG_DBG_OEN BIT(24) @@ -104,21 +94,21 @@ static void artpec6_pcie_writel(struct artpec6_pcie *artpec6_pcie, u32 offset, u regmap_write(artpec6_pcie->regmap, offset, val); } -static u64 artpec6_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 pci_addr) +static u64 artpec6_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 cpu_addr) { struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci); - struct pcie_port *pp = &pci->pp; + struct dw_pcie_rp *pp = &pci->pp; struct dw_pcie_ep *ep = &pci->ep; switch (artpec6_pcie->mode) { case DW_PCIE_RC_TYPE: - return pci_addr - pp->cfg0_base; + return cpu_addr - pp->cfg0_base; case DW_PCIE_EP_TYPE: - return pci_addr - ep->phys_base; + return cpu_addr - ep->phys_base; default: dev_err(pci->dev, "UNKNOWN device type\n"); } - return pci_addr; + return cpu_addr; } static int artpec6_pcie_establish_link(struct dw_pcie *pci) @@ -292,33 +282,6 @@ static void artpec6_pcie_init_phy(struct artpec6_pcie *artpec6_pcie) } } -static void artpec6_pcie_set_nfts(struct artpec6_pcie *artpec6_pcie) -{ - struct dw_pcie *pci = artpec6_pcie->pci; - u32 val; - - if (artpec6_pcie->variant != ARTPEC7) - return; - - /* - * Increase the N_FTS (Number of Fast Training Sequences) - * to be transmitted when transitioning from L0s to L0. - */ - val = dw_pcie_readl_dbi(pci, ACK_F_ASPM_CTRL_OFF); - val &= ~ACK_N_FTS_MASK; - val |= ACK_N_FTS(180); - dw_pcie_writel_dbi(pci, ACK_F_ASPM_CTRL_OFF, val); - - /* - * Set the Number of Fast Training Sequences that the core - * advertises as its N_FTS during Gen2 or Gen3 link training. - */ - val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); - val &= ~FAST_TRAINING_SEQ_MASK; - val |= FAST_TRAINING_SEQ(180); - dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); -} - static void artpec6_pcie_assert_core_reset(struct artpec6_pcie *artpec6_pcie) { u32 val; @@ -352,64 +315,27 @@ static void artpec6_pcie_deassert_core_reset(struct artpec6_pcie *artpec6_pcie) usleep_range(100, 200); } -static void artpec6_pcie_enable_interrupts(struct artpec6_pcie *artpec6_pcie) -{ - struct dw_pcie *pci = artpec6_pcie->pci; - struct pcie_port *pp = &pci->pp; - - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(pp); -} - -static int artpec6_pcie_host_init(struct pcie_port *pp) +static int artpec6_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci); + if (artpec6_pcie->variant == ARTPEC7) { + pci->n_fts[0] = 180; + pci->n_fts[1] = 180; + } artpec6_pcie_assert_core_reset(artpec6_pcie); artpec6_pcie_init_phy(artpec6_pcie); artpec6_pcie_deassert_core_reset(artpec6_pcie); artpec6_pcie_wait_for_phy(artpec6_pcie); - artpec6_pcie_set_nfts(artpec6_pcie); - dw_pcie_setup_rc(pp); - artpec6_pcie_establish_link(pci); - dw_pcie_wait_for_link(pci); - artpec6_pcie_enable_interrupts(artpec6_pcie); return 0; } static const struct dw_pcie_host_ops artpec6_pcie_host_ops = { - .host_init = artpec6_pcie_host_init, + .init = artpec6_pcie_host_init, }; -static int artpec6_add_pcie_port(struct artpec6_pcie *artpec6_pcie, - struct platform_device *pdev) -{ - struct dw_pcie *pci = artpec6_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = pci->dev; - int ret; - - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq_byname(pdev, "msi"); - if (pp->msi_irq < 0) { - dev_err(dev, "failed to get MSI irq\n"); - return pp->msi_irq; - } - } - - pp->ops = &artpec6_pcie_host_ops; - - ret = dw_pcie_host_init(pp); - if (ret) { - dev_err(dev, "failed to initialize host\n"); - return ret; - } - - return 0; -} - static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); @@ -420,22 +346,21 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep) artpec6_pcie_init_phy(artpec6_pcie); artpec6_pcie_deassert_core_reset(artpec6_pcie); artpec6_pcie_wait_for_phy(artpec6_pcie); - artpec6_pcie_set_nfts(artpec6_pcie); - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); } static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u16 interrupt_num) + unsigned int type, u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); switch (type) { - case PCI_EPC_IRQ_LEGACY: - dev_err(pci->dev, "EP cannot trigger legacy IRQs\n"); + case PCI_IRQ_INTX: + dev_err(pci->dev, "EP cannot trigger INTx IRQs\n"); return -EINVAL; - case PCI_EPC_IRQ_MSI: + 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"); @@ -444,62 +369,37 @@ static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } -static struct dw_pcie_ep_ops pcie_ep_ops = { - .ep_init = artpec6_pcie_ep_init, - .raise_irq = artpec6_pcie_raise_irq, +static const struct pci_epc_features artpec6_pcie_epc_features = { + .msi_capable = true, }; -static int artpec6_add_pcie_ep(struct artpec6_pcie *artpec6_pcie, - struct platform_device *pdev) +static const struct pci_epc_features * +artpec6_pcie_get_features(struct dw_pcie_ep *ep) { - int ret; - struct dw_pcie_ep *ep; - struct resource *res; - struct device *dev = &pdev->dev; - struct dw_pcie *pci = artpec6_pcie->pci; - - ep = &pci->ep; - ep->ops = &pcie_ep_ops; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi2"); - pci->dbi_base2 = devm_ioremap_resource(dev, res); - if (IS_ERR(pci->dbi_base2)) - return PTR_ERR(pci->dbi_base2); - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space"); - if (!res) - return -EINVAL; - - ep->phys_base = res->start; - ep->addr_size = resource_size(res); - - ret = dw_pcie_ep_init(ep); - if (ret) { - dev_err(dev, "failed to initialize endpoint\n"); - return ret; - } - - return 0; + return &artpec6_pcie_epc_features; } +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .init = artpec6_pcie_ep_init, + .raise_irq = artpec6_pcie_raise_irq, + .get_features = artpec6_pcie_get_features, +}; + static int artpec6_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct dw_pcie *pci; struct artpec6_pcie *artpec6_pcie; - struct resource *dbi_base; - struct resource *phy_base; int ret; - const struct of_device_id *match; const struct artpec_pcie_of_data *data; enum artpec_pcie_variants variant; enum dw_pcie_device_mode mode; + u32 val; - match = of_match_device(artpec6_pcie_of_match, dev); - if (!match) + data = of_device_get_match_data(dev); + if (!data) return -EINVAL; - data = (struct artpec_pcie_of_data *)match->data; variant = (enum artpec_pcie_variants)data->variant; mode = (enum dw_pcie_device_mode)data->mode; @@ -518,13 +418,8 @@ static int artpec6_pcie_probe(struct platform_device *pdev) artpec6_pcie->variant = variant; artpec6_pcie->mode = mode; - dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); - pci->dbi_base = devm_ioremap_resource(dev, dbi_base); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); - - phy_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "phy"); - artpec6_pcie->phy_base = devm_ioremap_resource(dev, phy_base); + artpec6_pcie->phy_base = + devm_platform_ioremap_resource_byname(pdev, "phy"); if (IS_ERR(artpec6_pcie->phy_base)) return PTR_ERR(artpec6_pcie->phy_base); @@ -541,24 +436,36 @@ static int artpec6_pcie_probe(struct platform_device *pdev) if (!IS_ENABLED(CONFIG_PCIE_ARTPEC6_HOST)) return -ENODEV; - ret = artpec6_add_pcie_port(artpec6_pcie, pdev); + pci->pp.ops = &artpec6_pcie_host_ops; + + ret = dw_pcie_host_init(&pci->pp); if (ret < 0) return ret; break; - case DW_PCIE_EP_TYPE: { - u32 val; - + case DW_PCIE_EP_TYPE: if (!IS_ENABLED(CONFIG_PCIE_ARTPEC6_EP)) return -ENODEV; val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); val &= ~PCIECFG_DEVICE_TYPE_MASK; artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); - ret = artpec6_add_pcie_ep(artpec6_pcie, pdev); - if (ret < 0) + + pci->ep.ops = &pcie_ep_ops; + + ret = dw_pcie_ep_init(&pci->ep); + if (ret) + return ret; + + ret = dw_pcie_ep_init_registers(&pci->ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(&pci->ep); return ret; + } + + pci_epc_init_notify(pci->ep.epc); + break; - } default: dev_err(dev, "INVALID device type %d\n", artpec6_pcie->mode); } diff --git a/drivers/pci/controller/dwc/pcie-bt1.c b/drivers/pci/controller/dwc/pcie-bt1.c new file mode 100644 index 000000000000..1340edc18d12 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-bt1.c @@ -0,0 +1,645 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 BAIKAL ELECTRONICS, JSC + * + * Authors: + * Vadim Vlasov <Vadim.Vlasov@baikalelectronics.ru> + * Serge Semin <Sergey.Semin@baikalelectronics.ru> + * + * Baikal-T1 PCIe controller driver + */ + +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +/* Baikal-T1 System CCU control registers */ +#define BT1_CCU_PCIE_CLKC 0x140 +#define BT1_CCU_PCIE_REQ_PCS_CLK BIT(16) +#define BT1_CCU_PCIE_REQ_MAC_CLK BIT(17) +#define BT1_CCU_PCIE_REQ_PIPE_CLK BIT(18) + +#define BT1_CCU_PCIE_RSTC 0x144 +#define BT1_CCU_PCIE_REQ_LINK_RST BIT(13) +#define BT1_CCU_PCIE_REQ_SMLH_RST BIT(14) +#define BT1_CCU_PCIE_REQ_PHY_RST BIT(16) +#define BT1_CCU_PCIE_REQ_CORE_RST BIT(24) +#define BT1_CCU_PCIE_REQ_STICKY_RST BIT(26) +#define BT1_CCU_PCIE_REQ_NSTICKY_RST BIT(27) + +#define BT1_CCU_PCIE_PMSC 0x148 +#define BT1_CCU_PCIE_LTSSM_STATE_MASK GENMASK(5, 0) +#define BT1_CCU_PCIE_LTSSM_DET_QUIET 0x00 +#define BT1_CCU_PCIE_LTSSM_DET_ACT 0x01 +#define BT1_CCU_PCIE_LTSSM_POLL_ACT 0x02 +#define BT1_CCU_PCIE_LTSSM_POLL_COMP 0x03 +#define BT1_CCU_PCIE_LTSSM_POLL_CONF 0x04 +#define BT1_CCU_PCIE_LTSSM_PRE_DET_QUIET 0x05 +#define BT1_CCU_PCIE_LTSSM_DET_WAIT 0x06 +#define BT1_CCU_PCIE_LTSSM_CFG_LNKWD_START 0x07 +#define BT1_CCU_PCIE_LTSSM_CFG_LNKWD_ACEPT 0x08 +#define BT1_CCU_PCIE_LTSSM_CFG_LNNUM_WAIT 0x09 +#define BT1_CCU_PCIE_LTSSM_CFG_LNNUM_ACEPT 0x0a +#define BT1_CCU_PCIE_LTSSM_CFG_COMPLETE 0x0b +#define BT1_CCU_PCIE_LTSSM_CFG_IDLE 0x0c +#define BT1_CCU_PCIE_LTSSM_RCVR_LOCK 0x0d +#define BT1_CCU_PCIE_LTSSM_RCVR_SPEED 0x0e +#define BT1_CCU_PCIE_LTSSM_RCVR_RCVRCFG 0x0f +#define BT1_CCU_PCIE_LTSSM_RCVR_IDLE 0x10 +#define BT1_CCU_PCIE_LTSSM_L0 0x11 +#define BT1_CCU_PCIE_LTSSM_L0S 0x12 +#define BT1_CCU_PCIE_LTSSM_L123_SEND_IDLE 0x13 +#define BT1_CCU_PCIE_LTSSM_L1_IDLE 0x14 +#define BT1_CCU_PCIE_LTSSM_L2_IDLE 0x15 +#define BT1_CCU_PCIE_LTSSM_L2_WAKE 0x16 +#define BT1_CCU_PCIE_LTSSM_DIS_ENTRY 0x17 +#define BT1_CCU_PCIE_LTSSM_DIS_IDLE 0x18 +#define BT1_CCU_PCIE_LTSSM_DISABLE 0x19 +#define BT1_CCU_PCIE_LTSSM_LPBK_ENTRY 0x1a +#define BT1_CCU_PCIE_LTSSM_LPBK_ACTIVE 0x1b +#define BT1_CCU_PCIE_LTSSM_LPBK_EXIT 0x1c +#define BT1_CCU_PCIE_LTSSM_LPBK_EXIT_TOUT 0x1d +#define BT1_CCU_PCIE_LTSSM_HOT_RST_ENTRY 0x1e +#define BT1_CCU_PCIE_LTSSM_HOT_RST 0x1f +#define BT1_CCU_PCIE_LTSSM_RCVR_EQ0 0x20 +#define BT1_CCU_PCIE_LTSSM_RCVR_EQ1 0x21 +#define BT1_CCU_PCIE_LTSSM_RCVR_EQ2 0x22 +#define BT1_CCU_PCIE_LTSSM_RCVR_EQ3 0x23 +#define BT1_CCU_PCIE_SMLH_LINKUP BIT(6) +#define BT1_CCU_PCIE_RDLH_LINKUP BIT(7) +#define BT1_CCU_PCIE_PM_LINKSTATE_L0S BIT(8) +#define BT1_CCU_PCIE_PM_LINKSTATE_L1 BIT(9) +#define BT1_CCU_PCIE_PM_LINKSTATE_L2 BIT(10) +#define BT1_CCU_PCIE_L1_PENDING BIT(12) +#define BT1_CCU_PCIE_REQ_EXIT_L1 BIT(14) +#define BT1_CCU_PCIE_LTSSM_RCVR_EQ BIT(15) +#define BT1_CCU_PCIE_PM_DSTAT_MASK GENMASK(18, 16) +#define BT1_CCU_PCIE_PM_PME_EN BIT(20) +#define BT1_CCU_PCIE_PM_PME_STATUS BIT(21) +#define BT1_CCU_PCIE_AUX_PM_EN BIT(22) +#define BT1_CCU_PCIE_AUX_PWR_DET BIT(23) +#define BT1_CCU_PCIE_WAKE_DET BIT(24) +#define BT1_CCU_PCIE_TURNOFF_REQ BIT(30) +#define BT1_CCU_PCIE_TURNOFF_ACK BIT(31) + +#define BT1_CCU_PCIE_GENC 0x14c +#define BT1_CCU_PCIE_LTSSM_EN BIT(1) +#define BT1_CCU_PCIE_DBI2_MODE BIT(2) +#define BT1_CCU_PCIE_MGMT_EN BIT(3) +#define BT1_CCU_PCIE_RXLANE_FLIP_EN BIT(16) +#define BT1_CCU_PCIE_TXLANE_FLIP_EN BIT(17) +#define BT1_CCU_PCIE_SLV_XFER_PEND BIT(24) +#define BT1_CCU_PCIE_RCV_XFER_PEND BIT(25) +#define BT1_CCU_PCIE_DBI_XFER_PEND BIT(26) +#define BT1_CCU_PCIE_DMA_XFER_PEND BIT(27) + +#define BT1_CCU_PCIE_LTSSM_LINKUP(_pmsc) \ +({ \ + int __state = FIELD_GET(BT1_CCU_PCIE_LTSSM_STATE_MASK, _pmsc); \ + __state >= BT1_CCU_PCIE_LTSSM_L0 && __state <= BT1_CCU_PCIE_LTSSM_L2_WAKE; \ +}) + +/* Baikal-T1 PCIe specific control registers */ +#define BT1_PCIE_AXI2MGM_LANENUM 0xd04 +#define BT1_PCIE_AXI2MGM_LANESEL_MASK GENMASK(3, 0) + +#define BT1_PCIE_AXI2MGM_ADDRCTL 0xd08 +#define BT1_PCIE_AXI2MGM_PHYREG_ADDR_MASK GENMASK(20, 0) +#define BT1_PCIE_AXI2MGM_READ_FLAG BIT(29) +#define BT1_PCIE_AXI2MGM_DONE BIT(30) +#define BT1_PCIE_AXI2MGM_BUSY BIT(31) + +#define BT1_PCIE_AXI2MGM_WRITEDATA 0xd0c +#define BT1_PCIE_AXI2MGM_WDATA GENMASK(15, 0) + +#define BT1_PCIE_AXI2MGM_READDATA 0xd10 +#define BT1_PCIE_AXI2MGM_RDATA GENMASK(15, 0) + +/* Generic Baikal-T1 PCIe interface resources */ +#define BT1_PCIE_NUM_APP_CLKS ARRAY_SIZE(bt1_pcie_app_clks) +#define BT1_PCIE_NUM_CORE_CLKS ARRAY_SIZE(bt1_pcie_core_clks) +#define BT1_PCIE_NUM_APP_RSTS ARRAY_SIZE(bt1_pcie_app_rsts) +#define BT1_PCIE_NUM_CORE_RSTS ARRAY_SIZE(bt1_pcie_core_rsts) + +/* PCIe bus setup delays and timeouts */ +#define BT1_PCIE_RST_DELAY_MS 100 +#define BT1_PCIE_RUN_DELAY_US 100 +#define BT1_PCIE_REQ_DELAY_US 1 +#define BT1_PCIE_REQ_TIMEOUT_US 1000 +#define BT1_PCIE_LNK_DELAY_US 1000 +#define BT1_PCIE_LNK_TIMEOUT_US 1000000 + +static const enum dw_pcie_app_clk bt1_pcie_app_clks[] = { + DW_PCIE_DBI_CLK, DW_PCIE_MSTR_CLK, DW_PCIE_SLV_CLK, +}; + +static const enum dw_pcie_core_clk bt1_pcie_core_clks[] = { + DW_PCIE_REF_CLK, +}; + +static const enum dw_pcie_app_rst bt1_pcie_app_rsts[] = { + DW_PCIE_MSTR_RST, DW_PCIE_SLV_RST, +}; + +static const enum dw_pcie_core_rst bt1_pcie_core_rsts[] = { + DW_PCIE_NON_STICKY_RST, DW_PCIE_STICKY_RST, DW_PCIE_CORE_RST, + DW_PCIE_PIPE_RST, DW_PCIE_PHY_RST, DW_PCIE_HOT_RST, DW_PCIE_PWR_RST, +}; + +struct bt1_pcie { + struct dw_pcie dw; + struct platform_device *pdev; + struct regmap *sys_regs; +}; +#define to_bt1_pcie(_dw) container_of(_dw, struct bt1_pcie, dw) + +/* + * Baikal-T1 MMIO space must be read/written by the dword-aligned + * instructions. Note the methods are optimized to have the dword operations + * performed with minimum overhead as the most frequently used ones. + */ +static int bt1_pcie_read_mmio(void __iomem *addr, int size, u32 *val) +{ + unsigned int ofs = (uintptr_t)addr & 0x3; + + if (!IS_ALIGNED((uintptr_t)addr, size)) + return -EINVAL; + + *val = readl(addr - ofs) >> ofs * BITS_PER_BYTE; + if (size == 4) { + return 0; + } else if (size == 2) { + *val &= 0xffff; + return 0; + } else if (size == 1) { + *val &= 0xff; + return 0; + } + + return -EINVAL; +} + +static int bt1_pcie_write_mmio(void __iomem *addr, int size, u32 val) +{ + unsigned int ofs = (uintptr_t)addr & 0x3; + u32 tmp, mask; + + if (!IS_ALIGNED((uintptr_t)addr, size)) + return -EINVAL; + + if (size == 4) { + writel(val, addr); + return 0; + } else if (size == 2 || size == 1) { + mask = GENMASK(size * BITS_PER_BYTE - 1, 0); + tmp = readl(addr - ofs) & ~(mask << ofs * BITS_PER_BYTE); + tmp |= (val & mask) << ofs * BITS_PER_BYTE; + writel(tmp, addr - ofs); + return 0; + } + + return -EINVAL; +} + +static u32 bt1_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg, + size_t size) +{ + int ret; + u32 val; + + ret = bt1_pcie_read_mmio(base + reg, size, &val); + if (ret) { + dev_err(pci->dev, "Read DBI address failed\n"); + return ~0U; + } + + return val; +} + +static void bt1_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg, + size_t size, u32 val) +{ + int ret; + + ret = bt1_pcie_write_mmio(base + reg, size, val); + if (ret) + dev_err(pci->dev, "Write DBI address failed\n"); +} + +static void bt1_pcie_write_dbi2(struct dw_pcie *pci, void __iomem *base, u32 reg, + size_t size, u32 val) +{ + struct bt1_pcie *btpci = to_bt1_pcie(pci); + int ret; + + regmap_update_bits(btpci->sys_regs, BT1_CCU_PCIE_GENC, + BT1_CCU_PCIE_DBI2_MODE, BT1_CCU_PCIE_DBI2_MODE); + + ret = bt1_pcie_write_mmio(base + reg, size, val); + if (ret) + dev_err(pci->dev, "Write DBI2 address failed\n"); + + regmap_update_bits(btpci->sys_regs, BT1_CCU_PCIE_GENC, + BT1_CCU_PCIE_DBI2_MODE, 0); +} + +static int bt1_pcie_start_link(struct dw_pcie *pci) +{ + struct bt1_pcie *btpci = to_bt1_pcie(pci); + u32 val; + int ret; + + /* + * Enable LTSSM and make sure it was able to establish both PHY and + * data links. This procedure shall work fine to reach 2.5 GT/s speed. + */ + regmap_update_bits(btpci->sys_regs, BT1_CCU_PCIE_GENC, + BT1_CCU_PCIE_LTSSM_EN, BT1_CCU_PCIE_LTSSM_EN); + + ret = regmap_read_poll_timeout(btpci->sys_regs, BT1_CCU_PCIE_PMSC, val, + (val & BT1_CCU_PCIE_SMLH_LINKUP), + BT1_PCIE_LNK_DELAY_US, BT1_PCIE_LNK_TIMEOUT_US); + if (ret) { + dev_err(pci->dev, "LTSSM failed to set PHY link up\n"); + return ret; + } + + ret = regmap_read_poll_timeout(btpci->sys_regs, BT1_CCU_PCIE_PMSC, val, + (val & BT1_CCU_PCIE_RDLH_LINKUP), + BT1_PCIE_LNK_DELAY_US, BT1_PCIE_LNK_TIMEOUT_US); + if (ret) { + dev_err(pci->dev, "LTSSM failed to set data link up\n"); + return ret; + } + + /* + * Activate direct speed change after the link is established in an + * attempt to reach a higher bus performance (up to Gen.3 - 8.0 GT/s). + * This is required at least to get 8.0 GT/s speed. + */ + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + + ret = regmap_read_poll_timeout(btpci->sys_regs, BT1_CCU_PCIE_PMSC, val, + BT1_CCU_PCIE_LTSSM_LINKUP(val), + BT1_PCIE_LNK_DELAY_US, BT1_PCIE_LNK_TIMEOUT_US); + if (ret) + dev_err(pci->dev, "LTSSM failed to get into L0 state\n"); + + return ret; +} + +static void bt1_pcie_stop_link(struct dw_pcie *pci) +{ + struct bt1_pcie *btpci = to_bt1_pcie(pci); + + regmap_update_bits(btpci->sys_regs, BT1_CCU_PCIE_GENC, + BT1_CCU_PCIE_LTSSM_EN, 0); +} + +static const struct dw_pcie_ops bt1_pcie_ops = { + .read_dbi = bt1_pcie_read_dbi, + .write_dbi = bt1_pcie_write_dbi, + .write_dbi2 = bt1_pcie_write_dbi2, + .start_link = bt1_pcie_start_link, + .stop_link = bt1_pcie_stop_link, +}; + +static struct pci_ops bt1_pci_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, +}; + +static int bt1_pcie_get_resources(struct bt1_pcie *btpci) +{ + struct device *dev = btpci->dw.dev; + int i; + + /* DBI access is supposed to be performed by the dword-aligned IOs */ + btpci->dw.pp.bridge->ops = &bt1_pci_ops; + + /* These CSRs are in MMIO so we won't check the regmap-methods status */ + btpci->sys_regs = + syscon_regmap_lookup_by_phandle(dev->of_node, "baikal,bt1-syscon"); + if (IS_ERR(btpci->sys_regs)) + return dev_err_probe(dev, PTR_ERR(btpci->sys_regs), + "Failed to get syscon\n"); + + /* Make sure all the required resources have been specified */ + for (i = 0; i < BT1_PCIE_NUM_APP_CLKS; i++) { + if (!btpci->dw.app_clks[bt1_pcie_app_clks[i]].clk) { + dev_err(dev, "App clocks set is incomplete\n"); + return -ENOENT; + } + } + + for (i = 0; i < BT1_PCIE_NUM_CORE_CLKS; i++) { + if (!btpci->dw.core_clks[bt1_pcie_core_clks[i]].clk) { + dev_err(dev, "Core clocks set is incomplete\n"); + return -ENOENT; + } + } + + for (i = 0; i < BT1_PCIE_NUM_APP_RSTS; i++) { + if (!btpci->dw.app_rsts[bt1_pcie_app_rsts[i]].rstc) { + dev_err(dev, "App resets set is incomplete\n"); + return -ENOENT; + } + } + + for (i = 0; i < BT1_PCIE_NUM_CORE_RSTS; i++) { + if (!btpci->dw.core_rsts[bt1_pcie_core_rsts[i]].rstc) { + dev_err(dev, "Core resets set is incomplete\n"); + return -ENOENT; + } + } + + return 0; +} + +static void bt1_pcie_full_stop_bus(struct bt1_pcie *btpci, bool init) +{ + struct device *dev = btpci->dw.dev; + struct dw_pcie *pci = &btpci->dw; + int ret; + + /* Disable LTSSM for sure */ + regmap_update_bits(btpci->sys_regs, BT1_CCU_PCIE_GENC, + BT1_CCU_PCIE_LTSSM_EN, 0); + + /* + * Application reset controls are trigger-based so assert the core + * resets only. + */ + ret = reset_control_bulk_assert(DW_PCIE_NUM_CORE_RSTS, pci->core_rsts); + if (ret) + dev_err(dev, "Failed to assert core resets\n"); + + /* + * Clocks are disabled by default at least in accordance with the clk + * enable counter value on init stage. + */ + if (!init) { + clk_bulk_disable_unprepare(DW_PCIE_NUM_CORE_CLKS, pci->core_clks); + + clk_bulk_disable_unprepare(DW_PCIE_NUM_APP_CLKS, pci->app_clks); + } + + /* The peripheral devices are unavailable anyway so reset them too */ + gpiod_set_value_cansleep(pci->pe_rst, 1); + + /* Make sure all the resets are settled */ + msleep(BT1_PCIE_RST_DELAY_MS); +} + +/* + * Implements the cold reset procedure in accordance with the reference manual + * and available PM signals. + */ +static int bt1_pcie_cold_start_bus(struct bt1_pcie *btpci) +{ + struct device *dev = btpci->dw.dev; + struct dw_pcie *pci = &btpci->dw; + u32 val; + int ret; + + /* First get out of the Power/Hot reset state */ + ret = reset_control_deassert(pci->core_rsts[DW_PCIE_PWR_RST].rstc); + if (ret) { + dev_err(dev, "Failed to deassert PHY reset\n"); + return ret; + } + + ret = reset_control_deassert(pci->core_rsts[DW_PCIE_HOT_RST].rstc); + if (ret) { + dev_err(dev, "Failed to deassert hot reset\n"); + goto err_assert_pwr_rst; + } + + /* Wait for the PM-core to stop requesting the PHY reset */ + ret = regmap_read_poll_timeout(btpci->sys_regs, BT1_CCU_PCIE_RSTC, val, + !(val & BT1_CCU_PCIE_REQ_PHY_RST), + BT1_PCIE_REQ_DELAY_US, BT1_PCIE_REQ_TIMEOUT_US); + if (ret) { + dev_err(dev, "Timed out waiting for PM to stop PHY resetting\n"); + goto err_assert_hot_rst; + } + + ret = reset_control_deassert(pci->core_rsts[DW_PCIE_PHY_RST].rstc); + if (ret) { + dev_err(dev, "Failed to deassert PHY reset\n"); + goto err_assert_hot_rst; + } + + /* Clocks can be now enabled, but the ref one is crucial at this stage */ + ret = clk_bulk_prepare_enable(DW_PCIE_NUM_APP_CLKS, pci->app_clks); + if (ret) { + dev_err(dev, "Failed to enable app clocks\n"); + goto err_assert_phy_rst; + } + + ret = clk_bulk_prepare_enable(DW_PCIE_NUM_CORE_CLKS, pci->core_clks); + if (ret) { + dev_err(dev, "Failed to enable ref clocks\n"); + goto err_disable_app_clk; + } + + /* Wait for the PM to stop requesting the controller core reset */ + ret = regmap_read_poll_timeout(btpci->sys_regs, BT1_CCU_PCIE_RSTC, val, + !(val & BT1_CCU_PCIE_REQ_CORE_RST), + BT1_PCIE_REQ_DELAY_US, BT1_PCIE_REQ_TIMEOUT_US); + if (ret) { + dev_err(dev, "Timed out waiting for PM to stop core resetting\n"); + goto err_disable_core_clk; + } + + /* PCS-PIPE interface and controller core can be now activated */ + ret = reset_control_deassert(pci->core_rsts[DW_PCIE_PIPE_RST].rstc); + if (ret) { + dev_err(dev, "Failed to deassert PIPE reset\n"); + goto err_disable_core_clk; + } + + ret = reset_control_deassert(pci->core_rsts[DW_PCIE_CORE_RST].rstc); + if (ret) { + dev_err(dev, "Failed to deassert core reset\n"); + goto err_assert_pipe_rst; + } + + /* It's recommended to reset the core and application logic together */ + ret = reset_control_bulk_reset(DW_PCIE_NUM_APP_RSTS, pci->app_rsts); + if (ret) { + dev_err(dev, "Failed to reset app domain\n"); + goto err_assert_core_rst; + } + + /* Sticky/Non-sticky CSR flags can be now unreset too */ + ret = reset_control_deassert(pci->core_rsts[DW_PCIE_STICKY_RST].rstc); + if (ret) { + dev_err(dev, "Failed to deassert sticky reset\n"); + goto err_assert_core_rst; + } + + ret = reset_control_deassert(pci->core_rsts[DW_PCIE_NON_STICKY_RST].rstc); + if (ret) { + dev_err(dev, "Failed to deassert non-sticky reset\n"); + goto err_assert_sticky_rst; + } + + /* Activate the PCIe bus peripheral devices */ + gpiod_set_value_cansleep(pci->pe_rst, 0); + + /* Make sure the state is settled (LTSSM is still disabled though) */ + usleep_range(BT1_PCIE_RUN_DELAY_US, BT1_PCIE_RUN_DELAY_US + 100); + + return 0; + +err_assert_sticky_rst: + reset_control_assert(pci->core_rsts[DW_PCIE_STICKY_RST].rstc); + +err_assert_core_rst: + reset_control_assert(pci->core_rsts[DW_PCIE_CORE_RST].rstc); + +err_assert_pipe_rst: + reset_control_assert(pci->core_rsts[DW_PCIE_PIPE_RST].rstc); + +err_disable_core_clk: + clk_bulk_disable_unprepare(DW_PCIE_NUM_CORE_CLKS, pci->core_clks); + +err_disable_app_clk: + clk_bulk_disable_unprepare(DW_PCIE_NUM_APP_CLKS, pci->app_clks); + +err_assert_phy_rst: + reset_control_assert(pci->core_rsts[DW_PCIE_PHY_RST].rstc); + +err_assert_hot_rst: + reset_control_assert(pci->core_rsts[DW_PCIE_HOT_RST].rstc); + +err_assert_pwr_rst: + reset_control_assert(pci->core_rsts[DW_PCIE_PWR_RST].rstc); + + return ret; +} + +static int bt1_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct bt1_pcie *btpci = to_bt1_pcie(pci); + int ret; + + ret = bt1_pcie_get_resources(btpci); + if (ret) + return ret; + + bt1_pcie_full_stop_bus(btpci, true); + + return bt1_pcie_cold_start_bus(btpci); +} + +static void bt1_pcie_host_deinit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct bt1_pcie *btpci = to_bt1_pcie(pci); + + bt1_pcie_full_stop_bus(btpci, false); +} + +static const struct dw_pcie_host_ops bt1_pcie_host_ops = { + .init = bt1_pcie_host_init, + .deinit = bt1_pcie_host_deinit, +}; + +static struct bt1_pcie *bt1_pcie_create_data(struct platform_device *pdev) +{ + struct bt1_pcie *btpci; + + btpci = devm_kzalloc(&pdev->dev, sizeof(*btpci), GFP_KERNEL); + if (!btpci) + return ERR_PTR(-ENOMEM); + + btpci->pdev = pdev; + + platform_set_drvdata(pdev, btpci); + + return btpci; +} + +static int bt1_pcie_add_port(struct bt1_pcie *btpci) +{ + struct device *dev = &btpci->pdev->dev; + int ret; + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (ret) + return ret; + + btpci->dw.version = DW_PCIE_VER_460A; + btpci->dw.dev = dev; + btpci->dw.ops = &bt1_pcie_ops; + + btpci->dw.pp.num_vectors = MAX_MSI_IRQS; + btpci->dw.pp.ops = &bt1_pcie_host_ops; + + dw_pcie_cap_set(&btpci->dw, REQ_RES); + + ret = dw_pcie_host_init(&btpci->dw.pp); + + return dev_err_probe(dev, ret, "Failed to initialize DWC PCIe host\n"); +} + +static void bt1_pcie_del_port(struct bt1_pcie *btpci) +{ + dw_pcie_host_deinit(&btpci->dw.pp); +} + +static int bt1_pcie_probe(struct platform_device *pdev) +{ + struct bt1_pcie *btpci; + + btpci = bt1_pcie_create_data(pdev); + if (IS_ERR(btpci)) + return PTR_ERR(btpci); + + return bt1_pcie_add_port(btpci); +} + +static void bt1_pcie_remove(struct platform_device *pdev) +{ + struct bt1_pcie *btpci = platform_get_drvdata(pdev); + + bt1_pcie_del_port(btpci); +} + +static const struct of_device_id bt1_pcie_of_match[] = { + { .compatible = "baikal,bt1-pcie" }, + {}, +}; +MODULE_DEVICE_TABLE(of, bt1_pcie_of_match); + +static struct platform_driver bt1_pcie_driver = { + .probe = bt1_pcie_probe, + .remove = bt1_pcie_remove, + .driver = { + .name = "bt1-pcie", + .of_match_table = bt1_pcie_of_match, + }, +}; +module_platform_driver(bt1_pcie_driver); + +MODULE_AUTHOR("Serge Semin <Sergey.Semin@baikalelectronics.ru>"); +MODULE_DESCRIPTION("Baikal-T1 PCIe driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/dwc/pcie-designware-debugfs.c b/drivers/pci/controller/dwc/pcie-designware-debugfs.c new file mode 100644 index 000000000000..0fbf86c0b97e --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-designware-debugfs.c @@ -0,0 +1,927 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Synopsys DesignWare PCIe controller debugfs driver + * + * Copyright (C) 2025 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * Author: Shradha Todi <shradha.t@samsung.com> + */ + +#include <linux/debugfs.h> + +#include "pcie-designware.h" + +#define SD_STATUS_L1LANE_REG 0xb0 +#define PIPE_RXVALID BIT(18) +#define PIPE_DETECT_LANE BIT(17) +#define LANE_SELECT GENMASK(3, 0) + +#define ERR_INJ0_OFF 0x34 +#define EINJ_VAL_DIFF GENMASK(28, 16) +#define EINJ_VC_NUM GENMASK(14, 12) +#define EINJ_TYPE_SHIFT 8 +#define EINJ0_TYPE GENMASK(11, 8) +#define EINJ1_TYPE BIT(8) +#define EINJ2_TYPE GENMASK(9, 8) +#define EINJ3_TYPE GENMASK(10, 8) +#define EINJ4_TYPE GENMASK(10, 8) +#define EINJ5_TYPE BIT(8) +#define EINJ_COUNT GENMASK(7, 0) + +#define ERR_INJ_ENABLE_REG 0x30 + +#define RAS_DES_EVENT_COUNTER_DATA_REG 0xc + +#define RAS_DES_EVENT_COUNTER_CTRL_REG 0x8 +#define EVENT_COUNTER_GROUP_SELECT GENMASK(27, 24) +#define EVENT_COUNTER_EVENT_SELECT GENMASK(23, 16) +#define EVENT_COUNTER_LANE_SELECT GENMASK(11, 8) +#define EVENT_COUNTER_STATUS BIT(7) +#define EVENT_COUNTER_ENABLE GENMASK(4, 2) +#define PER_EVENT_ON 0x3 +#define PER_EVENT_OFF 0x1 + +#define DWC_DEBUGFS_BUF_MAX 128 + +/** + * struct dwc_pcie_rasdes_info - Stores controller common information + * @ras_cap_offset: RAS DES vendor specific extended capability offset + * @reg_event_lock: Mutex used for RAS DES shadow event registers + * + * Any parameter constant to all files of the debugfs hierarchy for a single + * controller will be stored in this struct. It is allocated and assigned to + * controller specific struct dw_pcie during initialization. + */ +struct dwc_pcie_rasdes_info { + u32 ras_cap_offset; + struct mutex reg_event_lock; +}; + +/** + * struct dwc_pcie_rasdes_priv - Stores file specific private data information + * @pci: Reference to the dw_pcie structure + * @idx: Index of specific file related information in array of structs + * + * All debugfs files will have this struct as its private data. + */ +struct dwc_pcie_rasdes_priv { + struct dw_pcie *pci; + int idx; +}; + +/** + * struct dwc_pcie_err_inj - Store details about each error injection + * supported by DWC RAS DES + * @name: Name of the error that can be injected + * @err_inj_group: Group number to which the error belongs. The value + * can range from 0 to 5 + * @err_inj_type: Each group can have multiple types of error + */ +struct dwc_pcie_err_inj { + const char *name; + u32 err_inj_group; + u32 err_inj_type; +}; + +static const struct dwc_pcie_err_inj err_inj_list[] = { + {"tx_lcrc", 0x0, 0x0}, + {"b16_crc_dllp", 0x0, 0x1}, + {"b16_crc_upd_fc", 0x0, 0x2}, + {"tx_ecrc", 0x0, 0x3}, + {"fcrc_tlp", 0x0, 0x4}, + {"parity_tsos", 0x0, 0x5}, + {"parity_skpos", 0x0, 0x6}, + {"rx_lcrc", 0x0, 0x8}, + {"rx_ecrc", 0x0, 0xb}, + {"tlp_err_seq", 0x1, 0x0}, + {"ack_nak_dllp_seq", 0x1, 0x1}, + {"ack_nak_dllp", 0x2, 0x0}, + {"upd_fc_dllp", 0x2, 0x1}, + {"nak_dllp", 0x2, 0x2}, + {"inv_sync_hdr_sym", 0x3, 0x0}, + {"com_pad_ts1", 0x3, 0x1}, + {"com_pad_ts2", 0x3, 0x2}, + {"com_fts", 0x3, 0x3}, + {"com_idl", 0x3, 0x4}, + {"end_edb", 0x3, 0x5}, + {"stp_sdp", 0x3, 0x6}, + {"com_skp", 0x3, 0x7}, + {"posted_tlp_hdr", 0x4, 0x0}, + {"non_post_tlp_hdr", 0x4, 0x1}, + {"cmpl_tlp_hdr", 0x4, 0x2}, + {"posted_tlp_data", 0x4, 0x4}, + {"non_post_tlp_data", 0x4, 0x5}, + {"cmpl_tlp_data", 0x4, 0x6}, + {"duplicate_tlp", 0x5, 0x0}, + {"nullified_tlp", 0x5, 0x1}, +}; + +static const u32 err_inj_type_mask[] = { + EINJ0_TYPE, + EINJ1_TYPE, + EINJ2_TYPE, + EINJ3_TYPE, + EINJ4_TYPE, + EINJ5_TYPE, +}; + +/** + * struct dwc_pcie_event_counter - Store details about each event counter + * supported in DWC RAS DES + * @name: Name of the error counter + * @group_no: Group number that the event belongs to. The value can range + * from 0 to 4 + * @event_no: Event number of the particular event. The value ranges are: + * Group 0: 0 - 10 + * Group 1: 5 - 13 + * Group 2: 0 - 7 + * Group 3: 0 - 5 + * Group 4: 0 - 1 + */ +struct dwc_pcie_event_counter { + const char *name; + u32 group_no; + u32 event_no; +}; + +static const struct dwc_pcie_event_counter event_list[] = { + {"ebuf_overflow", 0x0, 0x0}, + {"ebuf_underrun", 0x0, 0x1}, + {"decode_err", 0x0, 0x2}, + {"running_disparity_err", 0x0, 0x3}, + {"skp_os_parity_err", 0x0, 0x4}, + {"sync_header_err", 0x0, 0x5}, + {"rx_valid_deassertion", 0x0, 0x6}, + {"ctl_skp_os_parity_err", 0x0, 0x7}, + {"retimer_parity_err_1st", 0x0, 0x8}, + {"retimer_parity_err_2nd", 0x0, 0x9}, + {"margin_crc_parity_err", 0x0, 0xA}, + {"detect_ei_infer", 0x1, 0x5}, + {"receiver_err", 0x1, 0x6}, + {"rx_recovery_req", 0x1, 0x7}, + {"n_fts_timeout", 0x1, 0x8}, + {"framing_err", 0x1, 0x9}, + {"deskew_err", 0x1, 0xa}, + {"framing_err_in_l0", 0x1, 0xc}, + {"deskew_uncompleted_err", 0x1, 0xd}, + {"bad_tlp", 0x2, 0x0}, + {"lcrc_err", 0x2, 0x1}, + {"bad_dllp", 0x2, 0x2}, + {"replay_num_rollover", 0x2, 0x3}, + {"replay_timeout", 0x2, 0x4}, + {"rx_nak_dllp", 0x2, 0x5}, + {"tx_nak_dllp", 0x2, 0x6}, + {"retry_tlp", 0x2, 0x7}, + {"fc_timeout", 0x3, 0x0}, + {"poisoned_tlp", 0x3, 0x1}, + {"ecrc_error", 0x3, 0x2}, + {"unsupported_request", 0x3, 0x3}, + {"completer_abort", 0x3, 0x4}, + {"completion_timeout", 0x3, 0x5}, + {"ebuf_skp_add", 0x4, 0x0}, + {"ebuf_skp_del", 0x4, 0x1}, +}; + +static ssize_t lane_detect_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dw_pcie *pci = file->private_data; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG); + val = FIELD_GET(PIPE_DETECT_LANE, val); + if (val) + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Lane Detected\n"); + else + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Lane Undetected\n"); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t lane_detect_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dw_pcie *pci = file->private_data; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 lane, val; + + val = kstrtou32_from_user(buf, count, 0, &lane); + if (val) + return val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG); + val &= ~(LANE_SELECT); + val |= FIELD_PREP(LANE_SELECT, lane); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG, val); + + return count; +} + +static ssize_t rx_valid_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dw_pcie *pci = file->private_data; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG); + val = FIELD_GET(PIPE_RXVALID, val); + if (val) + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "RX Valid\n"); + else + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "RX Invalid\n"); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t rx_valid_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + return lane_detect_write(file, buf, count, ppos); +} + +static ssize_t err_inj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 val, counter, vc_num, err_group, type_mask; + int val_diff = 0; + char *kern_buf; + + err_group = err_inj_list[pdata->idx].err_inj_group; + type_mask = err_inj_type_mask[err_group]; + + kern_buf = memdup_user_nul(buf, count); + if (IS_ERR(kern_buf)) + return PTR_ERR(kern_buf); + + if (err_group == 4) { + val = sscanf(kern_buf, "%u %d %u", &counter, &val_diff, &vc_num); + if ((val != 3) || (val_diff < -4095 || val_diff > 4095)) { + kfree(kern_buf); + return -EINVAL; + } + } else if (err_group == 1) { + val = sscanf(kern_buf, "%u %d", &counter, &val_diff); + if ((val != 2) || (val_diff < -4095 || val_diff > 4095)) { + kfree(kern_buf); + return -EINVAL; + } + } else { + val = kstrtou32(kern_buf, 0, &counter); + if (val) { + kfree(kern_buf); + return val; + } + } + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + ERR_INJ0_OFF + (0x4 * err_group)); + val &= ~(type_mask | EINJ_COUNT); + val |= ((err_inj_list[pdata->idx].err_inj_type << EINJ_TYPE_SHIFT) & type_mask); + val |= FIELD_PREP(EINJ_COUNT, counter); + + if (err_group == 1 || err_group == 4) { + val &= ~(EINJ_VAL_DIFF); + val |= FIELD_PREP(EINJ_VAL_DIFF, val_diff); + } + if (err_group == 4) { + val &= ~(EINJ_VC_NUM); + val |= FIELD_PREP(EINJ_VC_NUM, vc_num); + } + + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + ERR_INJ0_OFF + (0x4 * err_group), val); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + ERR_INJ_ENABLE_REG, (0x1 << err_group)); + + kfree(kern_buf); + return count; +} + +static void set_event_number(struct dwc_pcie_rasdes_priv *pdata, + struct dw_pcie *pci, struct dwc_pcie_rasdes_info *rinfo) +{ + u32 val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + val &= ~EVENT_COUNTER_ENABLE; + val &= ~(EVENT_COUNTER_GROUP_SELECT | EVENT_COUNTER_EVENT_SELECT); + val |= FIELD_PREP(EVENT_COUNTER_GROUP_SELECT, event_list[pdata->idx].group_no); + val |= FIELD_PREP(EVENT_COUNTER_EVENT_SELECT, event_list[pdata->idx].event_no); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG, val); +} + +static ssize_t counter_enable_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + mutex_unlock(&rinfo->reg_event_lock); + val = FIELD_GET(EVENT_COUNTER_STATUS, val); + if (val) + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Counter Enabled\n"); + else + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Counter Disabled\n"); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t counter_enable_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 val, enable; + + val = kstrtou32_from_user(buf, count, 0, &enable); + if (val) + return val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + if (enable) + val |= FIELD_PREP(EVENT_COUNTER_ENABLE, PER_EVENT_ON); + else + val |= FIELD_PREP(EVENT_COUNTER_ENABLE, PER_EVENT_OFF); + + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG, val); + + /* + * While enabling the counter, always read the status back to check if + * it is enabled or not. Return error if it is not enabled to let the + * users know that the counter is not supported on the platform. + */ + if (enable) { + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + + RAS_DES_EVENT_COUNTER_CTRL_REG); + if (!FIELD_GET(EVENT_COUNTER_STATUS, val)) { + mutex_unlock(&rinfo->reg_event_lock); + return -EOPNOTSUPP; + } + } + + mutex_unlock(&rinfo->reg_event_lock); + + return count; +} + +static ssize_t counter_lane_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + mutex_unlock(&rinfo->reg_event_lock); + val = FIELD_GET(EVENT_COUNTER_LANE_SELECT, val); + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Lane: %d\n", val); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t counter_lane_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 val, lane; + + val = kstrtou32_from_user(buf, count, 0, &lane); + if (val) + return val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + val &= ~(EVENT_COUNTER_LANE_SELECT); + val |= FIELD_PREP(EVENT_COUNTER_LANE_SELECT, lane); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG, val); + mutex_unlock(&rinfo->reg_event_lock); + + return count; +} + +static ssize_t counter_value_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_DATA_REG); + mutex_unlock(&rinfo->reg_event_lock); + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Counter value: %d\n", val); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static const char *ltssm_status_string(enum dw_pcie_ltssm ltssm) +{ + const char *str; + + switch (ltssm) { +#define DW_PCIE_LTSSM_NAME(n) case n: str = #n; break + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DETECT_QUIET); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DETECT_ACT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_POLL_ACTIVE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_POLL_COMPLIANCE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_POLL_CONFIG); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_PRE_DETECT_QUIET); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DETECT_WAIT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LINKWD_START); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LINKWD_ACEPT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LANENUM_WAI); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LANENUM_ACEPT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_COMPLETE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_LOCK); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_SPEED); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_RCVRCFG); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L0); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L0S); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L123_SEND_EIDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L1_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L2_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L2_WAKE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DISABLED_ENTRY); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DISABLED_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DISABLED); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_ENTRY); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_ACTIVE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_EXIT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_EXIT_TIMEOUT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_HOT_RESET_ENTRY); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_HOT_RESET); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ0); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ1); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ2); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ3); + default: + str = "DW_PCIE_LTSSM_UNKNOWN"; + break; + } + + return str + strlen("DW_PCIE_LTSSM_"); +} + +static int ltssm_status_show(struct seq_file *s, void *v) +{ + struct dw_pcie *pci = s->private; + enum dw_pcie_ltssm val; + + val = dw_pcie_get_ltssm(pci); + seq_printf(s, "%s (0x%02x)\n", ltssm_status_string(val), val); + + return 0; +} + +static int ltssm_status_open(struct inode *inode, struct file *file) +{ + return single_open(file, ltssm_status_show, inode->i_private); +} + +#define dwc_debugfs_create(name) \ +debugfs_create_file(#name, 0644, rasdes_debug, pci, \ + &dbg_ ## name ## _fops) + +#define DWC_DEBUGFS_FOPS(name) \ +static const struct file_operations dbg_ ## name ## _fops = { \ + .open = simple_open, \ + .read = name ## _read, \ + .write = name ## _write \ +} + +DWC_DEBUGFS_FOPS(lane_detect); +DWC_DEBUGFS_FOPS(rx_valid); + +static const struct file_operations dwc_pcie_err_inj_ops = { + .open = simple_open, + .write = err_inj_write, +}; + +static const struct file_operations dwc_pcie_counter_enable_ops = { + .open = simple_open, + .read = counter_enable_read, + .write = counter_enable_write, +}; + +static const struct file_operations dwc_pcie_counter_lane_ops = { + .open = simple_open, + .read = counter_lane_read, + .write = counter_lane_write, +}; + +static const struct file_operations dwc_pcie_counter_value_ops = { + .open = simple_open, + .read = counter_value_read, +}; + +static const struct file_operations dwc_pcie_ltssm_status_ops = { + .open = ltssm_status_open, + .read = seq_read, +}; + +static void dwc_pcie_rasdes_debugfs_deinit(struct dw_pcie *pci) +{ + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + + mutex_destroy(&rinfo->reg_event_lock); +} + +static int dwc_pcie_rasdes_debugfs_init(struct dw_pcie *pci, struct dentry *dir) +{ + struct dentry *rasdes_debug, *rasdes_err_inj; + struct dentry *rasdes_event_counter, *rasdes_events; + struct dwc_pcie_rasdes_info *rasdes_info; + struct dwc_pcie_rasdes_priv *priv_tmp; + struct device *dev = pci->dev; + int ras_cap, i, ret; + + /* + * If a given SoC has no RAS DES capability, the following call is + * bound to return an error, breaking some existing platforms. So, + * return 0 here, as this is not necessarily an error. + */ + ras_cap = dw_pcie_find_rasdes_capability(pci); + if (!ras_cap) { + dev_dbg(dev, "no RAS DES capability available\n"); + return 0; + } + + rasdes_info = devm_kzalloc(dev, sizeof(*rasdes_info), GFP_KERNEL); + if (!rasdes_info) + return -ENOMEM; + + /* Create subdirectories for Debug, Error Injection, Statistics. */ + rasdes_debug = debugfs_create_dir("rasdes_debug", dir); + rasdes_err_inj = debugfs_create_dir("rasdes_err_inj", dir); + rasdes_event_counter = debugfs_create_dir("rasdes_event_counter", dir); + + mutex_init(&rasdes_info->reg_event_lock); + rasdes_info->ras_cap_offset = ras_cap; + pci->debugfs->rasdes_info = rasdes_info; + + /* Create debugfs files for Debug subdirectory. */ + dwc_debugfs_create(lane_detect); + dwc_debugfs_create(rx_valid); + + /* Create debugfs files for Error Injection subdirectory. */ + for (i = 0; i < ARRAY_SIZE(err_inj_list); i++) { + priv_tmp = devm_kzalloc(dev, sizeof(*priv_tmp), GFP_KERNEL); + if (!priv_tmp) { + ret = -ENOMEM; + goto err_deinit; + } + + priv_tmp->idx = i; + priv_tmp->pci = pci; + debugfs_create_file(err_inj_list[i].name, 0200, rasdes_err_inj, priv_tmp, + &dwc_pcie_err_inj_ops); + } + + /* Create debugfs files for Statistical Counter subdirectory. */ + for (i = 0; i < ARRAY_SIZE(event_list); i++) { + priv_tmp = devm_kzalloc(dev, sizeof(*priv_tmp), GFP_KERNEL); + if (!priv_tmp) { + ret = -ENOMEM; + goto err_deinit; + } + + priv_tmp->idx = i; + priv_tmp->pci = pci; + rasdes_events = debugfs_create_dir(event_list[i].name, rasdes_event_counter); + if (event_list[i].group_no == 0 || event_list[i].group_no == 4) { + debugfs_create_file("lane_select", 0644, rasdes_events, + priv_tmp, &dwc_pcie_counter_lane_ops); + } + debugfs_create_file("counter_value", 0444, rasdes_events, priv_tmp, + &dwc_pcie_counter_value_ops); + debugfs_create_file("counter_enable", 0644, rasdes_events, priv_tmp, + &dwc_pcie_counter_enable_ops); + } + + return 0; + +err_deinit: + dwc_pcie_rasdes_debugfs_deinit(pci); + return ret; +} + +static void dwc_pcie_ltssm_debugfs_init(struct dw_pcie *pci, struct dentry *dir) +{ + debugfs_create_file("ltssm_status", 0444, dir, pci, + &dwc_pcie_ltssm_status_ops); +} + +static int dw_pcie_ptm_check_capability(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + pci->ptm_vsec_offset = dw_pcie_find_ptm_capability(pci); + + return pci->ptm_vsec_offset; +} + +static int dw_pcie_ptm_context_update_write(void *drvdata, u8 mode) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + if (mode == PCIE_PTM_CONTEXT_UPDATE_AUTO) { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val |= PTM_REQ_AUTO_UPDATE_ENABLED; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } else if (mode == PCIE_PTM_CONTEXT_UPDATE_MANUAL) { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val &= ~PTM_REQ_AUTO_UPDATE_ENABLED; + val |= PTM_REQ_START_UPDATE; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } else { + return -EINVAL; + } + + return 0; +} + +static int dw_pcie_ptm_context_update_read(void *drvdata, u8 *mode) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + if (FIELD_GET(PTM_REQ_AUTO_UPDATE_ENABLED, val)) + *mode = PCIE_PTM_CONTEXT_UPDATE_AUTO; + else + /* + * PTM_REQ_START_UPDATE is a self clearing register bit. So if + * PTM_REQ_AUTO_UPDATE_ENABLED is not set, then it implies that + * manual update is used. + */ + *mode = PCIE_PTM_CONTEXT_UPDATE_MANUAL; + + return 0; +} + +static int dw_pcie_ptm_context_valid_write(void *drvdata, bool valid) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + if (valid) { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val |= PTM_RES_CCONTEXT_VALID; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } else { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val &= ~PTM_RES_CCONTEXT_VALID; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } + + return 0; +} + +static int dw_pcie_ptm_context_valid_read(void *drvdata, bool *valid) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + *valid = !!FIELD_GET(PTM_RES_CCONTEXT_VALID, val); + + return 0; +} + +static int dw_pcie_ptm_local_clock_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_master_clock_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t1_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t2_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t3_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t4_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static bool dw_pcie_ptm_context_update_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static bool dw_pcie_ptm_context_valid_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_RC_TYPE; +} + +static bool dw_pcie_ptm_local_clock_visible(void *drvdata) +{ + /* PTM local clock is always visible */ + return true; +} + +static bool dw_pcie_ptm_master_clock_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static bool dw_pcie_ptm_t1_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static bool dw_pcie_ptm_t2_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_RC_TYPE; +} + +static bool dw_pcie_ptm_t3_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_RC_TYPE; +} + +static bool dw_pcie_ptm_t4_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static const struct pcie_ptm_ops dw_pcie_ptm_ops = { + .check_capability = dw_pcie_ptm_check_capability, + .context_update_write = dw_pcie_ptm_context_update_write, + .context_update_read = dw_pcie_ptm_context_update_read, + .context_valid_write = dw_pcie_ptm_context_valid_write, + .context_valid_read = dw_pcie_ptm_context_valid_read, + .local_clock_read = dw_pcie_ptm_local_clock_read, + .master_clock_read = dw_pcie_ptm_master_clock_read, + .t1_read = dw_pcie_ptm_t1_read, + .t2_read = dw_pcie_ptm_t2_read, + .t3_read = dw_pcie_ptm_t3_read, + .t4_read = dw_pcie_ptm_t4_read, + .context_update_visible = dw_pcie_ptm_context_update_visible, + .context_valid_visible = dw_pcie_ptm_context_valid_visible, + .local_clock_visible = dw_pcie_ptm_local_clock_visible, + .master_clock_visible = dw_pcie_ptm_master_clock_visible, + .t1_visible = dw_pcie_ptm_t1_visible, + .t2_visible = dw_pcie_ptm_t2_visible, + .t3_visible = dw_pcie_ptm_t3_visible, + .t4_visible = dw_pcie_ptm_t4_visible, +}; + +void dwc_pcie_debugfs_deinit(struct dw_pcie *pci) +{ + if (!pci->debugfs) + return; + + pcie_ptm_destroy_debugfs(pci->ptm_debugfs); + dwc_pcie_rasdes_debugfs_deinit(pci); + debugfs_remove_recursive(pci->debugfs->debug_dir); +} + +void dwc_pcie_debugfs_init(struct dw_pcie *pci, enum dw_pcie_device_mode mode) +{ + char dirname[DWC_DEBUGFS_BUF_MAX]; + struct device *dev = pci->dev; + struct debugfs_info *debugfs; + struct dentry *dir; + int err; + + /* Create main directory for each platform driver. */ + snprintf(dirname, DWC_DEBUGFS_BUF_MAX, "dwc_pcie_%s", dev_name(dev)); + dir = debugfs_create_dir(dirname, NULL); + debugfs = devm_kzalloc(dev, sizeof(*debugfs), GFP_KERNEL); + if (!debugfs) + return; + + debugfs->debug_dir = dir; + pci->debugfs = debugfs; + err = dwc_pcie_rasdes_debugfs_init(pci, dir); + if (err) + dev_err(dev, "failed to initialize RAS DES debugfs, err=%d\n", + err); + + dwc_pcie_ltssm_debugfs_init(pci, dir); + + pci->mode = mode; + pci->ptm_debugfs = pcie_ptm_create_debugfs(pci->dev, pci, + &dw_pcie_ptm_ops); +} diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index a543c45c7224..19571ac2b961 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -1,207 +1,430 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * Synopsys DesignWare PCIe Endpoint controller driver * * Copyright (C) 2017 Texas Instruments * Author: Kishon Vijay Abraham I <kishon@ti.com> */ +#include <linux/align.h> +#include <linux/bitfield.h> #include <linux/of.h> +#include <linux/platform_device.h> #include "pcie-designware.h" #include <linux/pci-epc.h> #include <linux/pci-epf.h> -void dw_pcie_ep_linkup(struct dw_pcie_ep *ep) +/** + * dw_pcie_ep_get_func_from_ep - Get the struct dw_pcie_ep_func corresponding to + * the endpoint function + * @ep: DWC EP device + * @func_no: Function number of the endpoint device + * + * Return: struct dw_pcie_ep_func if success, NULL otherwise. + */ +struct dw_pcie_ep_func * +dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no) { - struct pci_epc *epc = ep->epc; + struct dw_pcie_ep_func *ep_func; - pci_epc_linkup(epc); + list_for_each_entry(ep_func, &ep->func_list, list) { + if (ep_func->func_no == func_no) + return ep_func; + } + + return NULL; } -static void __dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar, - int flags) +static void __dw_pcie_ep_reset_bar(struct dw_pcie *pci, u8 func_no, + enum pci_barno bar, int flags) { + struct dw_pcie_ep *ep = &pci->ep; u32 reg; reg = PCI_BASE_ADDRESS_0 + (4 * bar); dw_pcie_dbi_ro_wr_en(pci); - dw_pcie_writel_dbi2(pci, reg, 0x0); - dw_pcie_writel_dbi(pci, reg, 0x0); + dw_pcie_ep_writel_dbi2(ep, func_no, reg, 0x0); + dw_pcie_ep_writel_dbi(ep, func_no, reg, 0x0); if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { - dw_pcie_writel_dbi2(pci, reg + 4, 0x0); - dw_pcie_writel_dbi(pci, reg + 4, 0x0); + dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, 0x0); + dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0x0); } dw_pcie_dbi_ro_wr_dis(pci); } +/** + * dw_pcie_ep_reset_bar - Reset endpoint BAR + * @pci: DWC PCI device + * @bar: BAR number of the endpoint + */ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) { - __dw_pcie_ep_reset_bar(pci, bar, 0); + u8 func_no, funcs; + + funcs = pci->ep.epc->max_functions; + + for (func_no = 0; func_no < funcs; func_no++) + __dw_pcie_ep_reset_bar(pci, func_no, bar, 0); } +EXPORT_SYMBOL_GPL(dw_pcie_ep_reset_bar); -static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie *pci, u8 cap_ptr, - u8 cap) +static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap) { - u8 cap_id, next_cap_ptr; - u16 reg; + return PCI_FIND_NEXT_CAP(dw_pcie_ep_read_cfg, PCI_CAPABILITY_LIST, + cap, ep, func_no); +} - reg = dw_pcie_readw_dbi(pci, cap_ptr); - next_cap_ptr = (reg & 0xff00) >> 8; - cap_id = (reg & 0x00ff); +/** + * dw_pcie_ep_hide_ext_capability - Hide a capability from the linked list + * @pci: DWC PCI device + * @prev_cap: Capability preceding the capability that should be hidden + * @cap: Capability that should be hidden + * + * Return: 0 if success, errno otherwise. + */ +int dw_pcie_ep_hide_ext_capability(struct dw_pcie *pci, u8 prev_cap, u8 cap) +{ + u16 prev_cap_offset, cap_offset; + u32 prev_cap_header, cap_header; - if (!next_cap_ptr || cap_id > PCI_CAP_ID_MAX) - return 0; + prev_cap_offset = dw_pcie_find_ext_capability(pci, prev_cap); + if (!prev_cap_offset) + return -EINVAL; - if (cap_id == cap) - return cap_ptr; + 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); - return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap); -} + /* cap must immediately follow prev_cap. */ + if (PCI_EXT_CAP_ID(cap_header) != cap) + return -EINVAL; -static u8 dw_pcie_ep_find_capability(struct dw_pcie *pci, u8 cap) -{ - u8 next_cap_ptr; - u16 reg; + /* Clear next ptr. */ + prev_cap_header &= ~GENMASK(31, 20); - reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST); - next_cap_ptr = (reg & 0x00ff); + /* Set next ptr to next ptr of cap. */ + prev_cap_header |= cap_header & GENMASK(31, 20); - if (!next_cap_ptr) - return 0; + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, prev_cap_offset, prev_cap_header); + dw_pcie_dbi_ro_wr_dis(pci); - return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap); + return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_hide_ext_capability); -static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, +static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_header *hdr) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); dw_pcie_dbi_ro_wr_en(pci); - dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, hdr->vendorid); - dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, hdr->deviceid); - dw_pcie_writeb_dbi(pci, PCI_REVISION_ID, hdr->revid); - dw_pcie_writeb_dbi(pci, PCI_CLASS_PROG, hdr->progif_code); - dw_pcie_writew_dbi(pci, PCI_CLASS_DEVICE, - hdr->subclass_code | hdr->baseclass_code << 8); - dw_pcie_writeb_dbi(pci, PCI_CACHE_LINE_SIZE, - hdr->cache_line_size); - dw_pcie_writew_dbi(pci, PCI_SUBSYSTEM_VENDOR_ID, - hdr->subsys_vendor_id); - dw_pcie_writew_dbi(pci, PCI_SUBSYSTEM_ID, hdr->subsys_id); - dw_pcie_writeb_dbi(pci, PCI_INTERRUPT_PIN, - hdr->interrupt_pin); + dw_pcie_ep_writew_dbi(ep, func_no, PCI_VENDOR_ID, hdr->vendorid); + dw_pcie_ep_writew_dbi(ep, func_no, PCI_DEVICE_ID, hdr->deviceid); + dw_pcie_ep_writeb_dbi(ep, func_no, PCI_REVISION_ID, hdr->revid); + dw_pcie_ep_writeb_dbi(ep, func_no, PCI_CLASS_PROG, hdr->progif_code); + dw_pcie_ep_writew_dbi(ep, func_no, PCI_CLASS_DEVICE, + hdr->subclass_code | hdr->baseclass_code << 8); + dw_pcie_ep_writeb_dbi(ep, func_no, PCI_CACHE_LINE_SIZE, + hdr->cache_line_size); + dw_pcie_ep_writew_dbi(ep, func_no, PCI_SUBSYSTEM_VENDOR_ID, + hdr->subsys_vendor_id); + dw_pcie_ep_writew_dbi(ep, func_no, PCI_SUBSYSTEM_ID, hdr->subsys_id); + dw_pcie_ep_writeb_dbi(ep, func_no, PCI_INTERRUPT_PIN, + hdr->interrupt_pin); dw_pcie_dbi_ro_wr_dis(pci); return 0; } -static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, enum pci_barno bar, - dma_addr_t cpu_addr, - enum dw_pcie_as_type as_type) +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) { int ret; u32 free_win; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - free_win = find_first_zero_bit(ep->ib_window_map, ep->num_ib_windows); - if (free_win >= ep->num_ib_windows) { + if (!ep->bar_to_atu[bar]) + free_win = find_first_zero_bit(ep->ib_window_map, pci->num_ib_windows); + else + free_win = ep->bar_to_atu[bar] - 1; + + if (free_win >= pci->num_ib_windows) { dev_err(pci->dev, "No free inbound window\n"); return -EINVAL; } - ret = dw_pcie_prog_inbound_atu(pci, free_win, bar, cpu_addr, - as_type); + ret = dw_pcie_prog_ep_inbound_atu(pci, func_no, free_win, type, + parent_bus_addr, bar, size); if (ret < 0) { dev_err(pci->dev, "Failed to program IB window\n"); return ret; } - ep->bar_to_atu[bar] = free_win; + /* + * Always increment free_win before assignment, since value 0 is used to identify + * unallocated mapping. + */ + ep->bar_to_atu[bar] = free_win + 1; set_bit(free_win, ep->ib_window_map); return 0; } -static int dw_pcie_ep_outbound_atu(struct dw_pcie_ep *ep, phys_addr_t phys_addr, - u64 pci_addr, size_t size) +static int dw_pcie_ep_outbound_atu(struct dw_pcie_ep *ep, + struct dw_pcie_ob_atu_cfg *atu) { - u32 free_win; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 free_win; + int ret; - free_win = find_first_zero_bit(ep->ob_window_map, ep->num_ob_windows); - if (free_win >= ep->num_ob_windows) { + free_win = find_first_zero_bit(ep->ob_window_map, pci->num_ob_windows); + if (free_win >= pci->num_ob_windows) { dev_err(pci->dev, "No free outbound window\n"); return -EINVAL; } - dw_pcie_prog_outbound_atu(pci, free_win, PCIE_ATU_TYPE_MEM, - phys_addr, pci_addr, size); + atu->index = free_win; + ret = dw_pcie_prog_outbound_atu(pci, atu); + if (ret) + return ret; set_bit(free_win, ep->ob_window_map); - ep->outbound_addr[free_win] = phys_addr; + ep->outbound_addr[free_win] = atu->parent_bus_addr; return 0; } -static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, +static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar = epf_bar->barno; - u32 atu_index = ep->bar_to_atu[bar]; + u32 atu_index = ep->bar_to_atu[bar] - 1; + + if (!ep->bar_to_atu[bar]) + return; - __dw_pcie_ep_reset_bar(pci, bar, epf_bar->flags); + __dw_pcie_ep_reset_bar(pci, func_no, bar, epf_bar->flags); - dw_pcie_disable_atu(pci, atu_index, DW_PCIE_REGION_INBOUND); + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, atu_index); clear_bit(atu_index, ep->ib_window_map); + ep->epf_bar[bar] = NULL; + ep->bar_to_atu[bar] = 0; } -static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, - struct pci_epf_bar *epf_bar) +static unsigned int dw_pcie_ep_get_rebar_offset(struct dw_pcie *pci, + enum pci_barno bar) +{ + u32 reg, bar_index; + unsigned int offset, nbars; + int i; + + offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR); + if (!offset) + return offset; + + reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, reg); + + for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) { + reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + bar_index = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, reg); + if (bar_index == bar) + return offset; + } + + return 0; +} + +static int dw_pcie_ep_set_bar_resizable(struct dw_pcie_ep *ep, u8 func_no, + struct pci_epf_bar *epf_bar) { - int ret; - struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar = epf_bar->barno; size_t size = epf_bar->size; int flags = epf_bar->flags; - enum dw_pcie_as_type as_type; u32 reg = PCI_BASE_ADDRESS_0 + (4 * bar); + unsigned int rebar_offset; + u32 rebar_cap, rebar_ctrl; + int ret; - if (!(flags & PCI_BASE_ADDRESS_SPACE)) - as_type = DW_PCIE_AS_MEM; - else - as_type = DW_PCIE_AS_IO; + rebar_offset = dw_pcie_ep_get_rebar_offset(pci, bar); + if (!rebar_offset) + return -EINVAL; - ret = dw_pcie_ep_inbound_atu(ep, bar, epf_bar->phys_addr, as_type); + ret = pci_epc_bar_size_to_rebar_cap(size, &rebar_cap); if (ret) return ret; dw_pcie_dbi_ro_wr_en(pci); - dw_pcie_writel_dbi2(pci, reg, lower_32_bits(size - 1)); - dw_pcie_writel_dbi(pci, reg, flags); + /* + * A BAR mask should not be written for a resizable BAR. The BAR mask + * is automatically derived by the controller every time the "selected + * size" bits are updated, see "Figure 3-26 Resizable BAR Example for + * 32-bit Memory BAR0" in DWC EP databook 5.96a. We simply need to write + * BIT(0) to set the BAR enable bit. + */ + dw_pcie_ep_writel_dbi2(ep, func_no, reg, BIT(0)); + dw_pcie_ep_writel_dbi(ep, func_no, reg, flags); if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { - dw_pcie_writel_dbi2(pci, reg + 4, upper_32_bits(size - 1)); - dw_pcie_writel_dbi(pci, reg + 4, 0); + dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, 0); + dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0); } + /* + * Bits 31:0 in PCI_REBAR_CAP define "supported sizes" bits for sizes + * 1 MB to 128 TB. Bits 31:16 in PCI_REBAR_CTRL define "supported sizes" + * bits for sizes 256 TB to 8 EB. Disallow sizes 256 TB to 8 EB. + */ + rebar_ctrl = dw_pcie_readl_dbi(pci, rebar_offset + PCI_REBAR_CTRL); + rebar_ctrl &= ~GENMASK(31, 16); + dw_pcie_writel_dbi(pci, rebar_offset + PCI_REBAR_CTRL, rebar_ctrl); + + /* + * The "selected size" (bits 13:8) in PCI_REBAR_CTRL are automatically + * updated when writing PCI_REBAR_CAP, see "Figure 3-26 Resizable BAR + * Example for 32-bit Memory BAR0" in DWC EP databook 5.96a. + */ + dw_pcie_writel_dbi(pci, rebar_offset + PCI_REBAR_CAP, rebar_cap); + dw_pcie_dbi_ro_wr_dis(pci); return 0; } +static int dw_pcie_ep_set_bar_programmable(struct dw_pcie_ep *ep, u8 func_no, + struct pci_epf_bar *epf_bar) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar = epf_bar->barno; + size_t size = epf_bar->size; + int flags = epf_bar->flags; + u32 reg = PCI_BASE_ADDRESS_0 + (4 * bar); + + dw_pcie_dbi_ro_wr_en(pci); + + dw_pcie_ep_writel_dbi2(ep, func_no, reg, lower_32_bits(size - 1)); + dw_pcie_ep_writel_dbi(ep, func_no, reg, flags); + + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { + dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, upper_32_bits(size - 1)); + dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0); + } + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static enum pci_epc_bar_type dw_pcie_ep_get_bar_type(struct dw_pcie_ep *ep, + enum pci_barno bar) +{ + const struct pci_epc_features *epc_features; + + if (!ep->ops->get_features) + return BAR_PROGRAMMABLE; + + epc_features = ep->ops->get_features(ep); + + return epc_features->bar[bar].type; +} + +static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + struct pci_epf_bar *epf_bar) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar = epf_bar->barno; + size_t size = epf_bar->size; + enum pci_epc_bar_type bar_type; + int flags = epf_bar->flags; + int ret, type; + + /* + * DWC does not allow BAR pairs to overlap, e.g. you cannot combine BARs + * 1 and 2 to form a 64-bit BAR. + */ + if ((flags & PCI_BASE_ADDRESS_MEM_TYPE_64) && (bar & 1)) + return -EINVAL; + + /* + * Certain EPF drivers dynamically change the physical address of a BAR + * (i.e. they call set_bar() twice, without ever calling clear_bar(), as + * calling clear_bar() would clear the BAR's PCI address assigned by the + * host). + */ + if (ep->epf_bar[bar]) { + /* + * We can only dynamically change a BAR if the new BAR size and + * BAR flags do not differ from the existing configuration. + */ + if (ep->epf_bar[bar]->barno != bar || + ep->epf_bar[bar]->size != size || + ep->epf_bar[bar]->flags != flags) + return -EINVAL; + + /* + * When dynamically changing a BAR, skip writing the BAR reg, as + * that would clear the BAR's PCI address assigned by the host. + */ + goto config_atu; + } + + bar_type = dw_pcie_ep_get_bar_type(ep, bar); + switch (bar_type) { + case BAR_FIXED: + /* + * There is no need to write a BAR mask for a fixed BAR (except + * to write 1 to the LSB of the BAR mask register, to enable the + * BAR). Write the BAR mask regardless. (The fixed bits in the + * BAR mask register will be read-only anyway.) + */ + fallthrough; + case BAR_PROGRAMMABLE: + ret = dw_pcie_ep_set_bar_programmable(ep, func_no, epf_bar); + break; + case BAR_RESIZABLE: + ret = dw_pcie_ep_set_bar_resizable(ep, func_no, epf_bar); + break; + default: + ret = -EINVAL; + dev_err(pci->dev, "Invalid BAR type\n"); + break; + } + + if (ret) + return ret; + +config_atu: + if (!(flags & PCI_BASE_ADDRESS_SPACE)) + type = PCIE_ATU_TYPE_MEM; + else + type = PCIE_ATU_TYPE_IO; + + ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar, + size); + if (ret) + return ret; + + ep->epf_bar[bar] = epf_bar; + + return 0; +} + static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, u32 *atu_index) { u32 index; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - for (index = 0; index < ep->num_ob_windows; index++) { + for_each_set_bit(index, ep->ob_window_map, pci->num_ob_windows) { if (ep->outbound_addr[index] != addr) continue; *atu_index = index; @@ -211,7 +434,21 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, return -EINVAL; } -static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, +static u64 dw_pcie_ep_align_addr(struct pci_epc *epc, u64 pci_addr, + size_t *pci_size, size_t *offset) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u64 mask = pci->region_align - 1; + size_t ofst = pci_addr & mask; + + *pci_size = ALIGN(ofst + *pci_size, epc->mem->window.page_size); + *offset = ofst; + + return pci_addr & ~mask; +} + +static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t addr) { int ret; @@ -219,23 +456,30 @@ static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - ret = dw_pcie_find_index(ep, addr, &atu_index); + ret = dw_pcie_find_index(ep, addr - pci->parent_bus_offset, + &atu_index); if (ret < 0) return; - dw_pcie_disable_atu(pci, atu_index, DW_PCIE_REGION_OUTBOUND); + ep->outbound_addr[atu_index] = 0; + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, atu_index); clear_bit(atu_index, ep->ob_window_map); } -static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, - phys_addr_t addr, - u64 pci_addr, size_t size) +static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + phys_addr_t addr, u64 pci_addr, size_t size) { int ret; struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - - ret = dw_pcie_ep_outbound_atu(ep, addr, pci_addr, size); + struct dw_pcie_ob_atu_cfg atu = { 0 }; + + atu.func_no = func_no; + atu.type = PCIE_ATU_TYPE_MEM; + atu.parent_bus_addr = addr - pci->parent_bus_offset; + atu.pci_addr = pci_addr; + atu.size = size; + ret = dw_pcie_ep_outbound_atu(ep, &atu); if (ret) { dev_err(pci->dev, "Failed to enable address\n"); return ret; @@ -244,86 +488,105 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, return 0; } -static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no) +static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); - struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; u32 val, reg; - if (!ep->msi_cap) + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msi_cap) return -EINVAL; - reg = ep->msi_cap + PCI_MSI_FLAGS; - val = dw_pcie_readw_dbi(pci, reg); + reg = ep_func->msi_cap + PCI_MSI_FLAGS; + val = dw_pcie_ep_readw_dbi(ep, func_no, reg); if (!(val & PCI_MSI_FLAGS_ENABLE)) return -EINVAL; - val = (val & PCI_MSI_FLAGS_QSIZE) >> 4; + 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 interrupts) +static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + 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; - if (!ep->msi_cap) + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msi_cap) return -EINVAL; - reg = ep->msi_cap + PCI_MSI_FLAGS; - val = dw_pcie_readw_dbi(pci, reg); + reg = ep_func->msi_cap + PCI_MSI_FLAGS; + val = dw_pcie_ep_readw_dbi(ep, func_no, reg); val &= ~PCI_MSI_FLAGS_QMASK; - val |= (interrupts << 1) & PCI_MSI_FLAGS_QMASK; + val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, mmc); dw_pcie_dbi_ro_wr_en(pci); - dw_pcie_writew_dbi(pci, reg, val); + dw_pcie_ep_writew_dbi(ep, func_no, reg, val); dw_pcie_dbi_ro_wr_dis(pci); return 0; } -static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no) +static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); - struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; u32 val, reg; - if (!ep->msix_cap) + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) return -EINVAL; - reg = ep->msix_cap + PCI_MSIX_FLAGS; - val = dw_pcie_readw_dbi(pci, reg); + reg = ep_func->msix_cap + PCI_MSIX_FLAGS; + val = dw_pcie_ep_readw_dbi(ep, func_no, reg); if (!(val & PCI_MSIX_FLAGS_ENABLE)) return -EINVAL; val &= PCI_MSIX_FLAGS_QSIZE; - return val; + return val + 1; } -static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts) +static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + 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); + struct dw_pcie_ep_func *ep_func; u32 val, reg; - if (!ep->msix_cap) + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) return -EINVAL; - reg = ep->msix_cap + PCI_MSIX_FLAGS; - val = dw_pcie_readw_dbi(pci, reg); - val &= ~PCI_MSIX_FLAGS_QSIZE; - val |= interrupts; dw_pcie_dbi_ro_wr_en(pci); + + reg = ep_func->msix_cap + PCI_MSIX_FLAGS; + val = dw_pcie_ep_readw_dbi(ep, func_no, reg); + val &= ~PCI_MSIX_FLAGS_QSIZE; + val |= nr_irqs - 1; /* encoded as N-1 */ dw_pcie_writew_dbi(pci, reg, val); + + reg = ep_func->msix_cap + PCI_MSIX_TABLE; + val = offset | bir; + dw_pcie_ep_writel_dbi(ep, func_no, reg, val); + + reg = ep_func->msix_cap + PCI_MSIX_PBA; + 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); return 0; } -static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, - enum pci_epc_irq_type type, u16 interrupt_num) +static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + unsigned int type, u16 interrupt_num) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); @@ -338,10 +601,7 @@ 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); - if (!pci->ops->stop_link) - return; - - pci->ops->stop_link(pci); + dw_pcie_stop_link(pci); } static int dw_pcie_ep_start(struct pci_epc *epc) @@ -349,16 +609,25 @@ static int dw_pcie_ep_start(struct pci_epc *epc) struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - if (!pci->ops->start_link) - return -EINVAL; + return dw_pcie_start_link(pci); +} - return pci->ops->start_link(pci); +static const struct pci_epc_features* +dw_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + + if (!ep->ops->get_features) + return NULL; + + return ep->ops->get_features(ep); } static const struct pci_epc_ops epc_ops = { .write_header = dw_pcie_ep_write_header, .set_bar = dw_pcie_ep_set_bar, .clear_bar = dw_pcie_ep_clear_bar, + .align_addr = dw_pcie_ep_align_addr, .map_addr = dw_pcie_ep_map_addr, .unmap_addr = dw_pcie_ep_unmap_addr, .set_msi = dw_pcie_ep_set_msi, @@ -368,185 +637,456 @@ static const struct pci_epc_ops epc_ops = { .raise_irq = dw_pcie_ep_raise_irq, .start = dw_pcie_ep_start, .stop = dw_pcie_ep_stop, + .get_features = dw_pcie_ep_get_features, }; -int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no) +/** + * dw_pcie_ep_raise_intx_irq - Raise INTx IRQ to the host + * @ep: DWC EP device + * @func_no: Function number of the endpoint + * + * Return: 0 if success, errno otherwise. + */ +int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct device *dev = pci->dev; - dev_err(dev, "EP cannot trigger legacy IRQs\n"); + dev_err(dev, "EP cannot raise INTX IRQs\n"); return -EINVAL; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_intx_irq); +/** + * dw_pcie_ep_raise_msi_irq - Raise MSI IRQ to the host + * @ep: DWC EP device + * @func_no: Function number of the endpoint + * @interrupt_num: Interrupt number to be raised + * + * Return: 0 if success, errno otherwise. + */ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u8 interrupt_num) { - struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 msg_addr_lower, msg_addr_upper, reg; + struct dw_pcie_ep_func *ep_func; struct pci_epc *epc = ep->epc; + size_t map_size = sizeof(u32); + size_t offset; u16 msg_ctrl, msg_data; - u32 msg_addr_lower, msg_addr_upper, reg; - u64 msg_addr; bool has_upper; + u64 msg_addr; int ret; - if (!ep->msi_cap) + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msi_cap) return -EINVAL; /* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */ - reg = ep->msi_cap + PCI_MSI_FLAGS; - msg_ctrl = dw_pcie_readw_dbi(pci, reg); + reg = ep_func->msi_cap + PCI_MSI_FLAGS; + msg_ctrl = dw_pcie_ep_readw_dbi(ep, func_no, reg); has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT); - reg = ep->msi_cap + PCI_MSI_ADDRESS_LO; - msg_addr_lower = dw_pcie_readl_dbi(pci, reg); + reg = ep_func->msi_cap + PCI_MSI_ADDRESS_LO; + msg_addr_lower = dw_pcie_ep_readl_dbi(ep, func_no, reg); if (has_upper) { - reg = ep->msi_cap + PCI_MSI_ADDRESS_HI; - msg_addr_upper = dw_pcie_readl_dbi(pci, reg); - reg = ep->msi_cap + PCI_MSI_DATA_64; - msg_data = dw_pcie_readw_dbi(pci, reg); + reg = ep_func->msi_cap + PCI_MSI_ADDRESS_HI; + msg_addr_upper = dw_pcie_ep_readl_dbi(ep, func_no, reg); + reg = ep_func->msi_cap + PCI_MSI_DATA_64; + msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg); } else { msg_addr_upper = 0; - reg = ep->msi_cap + PCI_MSI_DATA_32; - msg_data = dw_pcie_readw_dbi(pci, reg); + reg = ep_func->msi_cap + PCI_MSI_DATA_32; + msg_data = dw_pcie_ep_readw_dbi(ep, func_no, reg); } - msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower; - ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr, - epc->mem->page_size); + 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); + writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset); + + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); + + return 0; +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_msi_irq); + +/** + * dw_pcie_ep_raise_msix_irq_doorbell - Raise MSI-X to the host using Doorbell + * method + * @ep: DWC EP device + * @func_no: Function number of the endpoint device + * @interrupt_num: Interrupt number to be raised + * + * Return: 0 if success, errno otherwise. + */ +int dw_pcie_ep_raise_msix_irq_doorbell(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; + u32 msg_data; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) + return -EINVAL; + + msg_data = (func_no << PCIE_MSIX_DOORBELL_PF_SHIFT) | + (interrupt_num - 1); - dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys); + dw_pcie_writel_dbi(pci, PCIE_MSIX_DOORBELL, msg_data); return 0; } +/** + * dw_pcie_ep_raise_msix_irq - Raise MSI-X to the host + * @ep: DWC EP device + * @func_no: Function number of the endpoint device + * @interrupt_num: Interrupt number to be raised + * + * Return: 0 if success, errno otherwise. + */ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, - u16 interrupt_num) + u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct pci_epf_msix_tbl *msix_tbl; + struct dw_pcie_ep_func *ep_func; struct pci_epc *epc = ep->epc; - u16 tbl_offset, bir; - u32 bar_addr_upper, bar_addr_lower; - u32 msg_addr_upper, msg_addr_lower; + size_t map_size = sizeof(u32); + size_t offset; u32 reg, msg_data, vec_ctrl; - u64 tbl_addr, msg_addr, reg_u64; - void __iomem *msix_tbl; + u32 tbl_offset; + u64 msg_addr; int ret; + u8 bir; - reg = ep->msix_cap + PCI_MSIX_TABLE; - tbl_offset = dw_pcie_readl_dbi(pci, reg); - bir = (tbl_offset & PCI_MSIX_TABLE_BIR); - tbl_offset &= PCI_MSIX_TABLE_OFFSET; - - reg = PCI_BASE_ADDRESS_0 + (4 * bir); - bar_addr_upper = 0; - bar_addr_lower = dw_pcie_readl_dbi(pci, reg); - reg_u64 = (bar_addr_lower & PCI_BASE_ADDRESS_MEM_TYPE_MASK); - if (reg_u64 == PCI_BASE_ADDRESS_MEM_TYPE_64) - bar_addr_upper = dw_pcie_readl_dbi(pci, reg + 4); - - tbl_addr = ((u64) bar_addr_upper) << 32 | bar_addr_lower; - tbl_addr += (tbl_offset + ((interrupt_num - 1) * PCI_MSIX_ENTRY_SIZE)); - tbl_addr &= PCI_BASE_ADDRESS_MEM_MASK; - - msix_tbl = ioremap_nocache(ep->phys_base + tbl_addr, - PCI_MSIX_ENTRY_SIZE); - if (!msix_tbl) + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) return -EINVAL; - msg_addr_lower = readl(msix_tbl + PCI_MSIX_ENTRY_LOWER_ADDR); - msg_addr_upper = readl(msix_tbl + PCI_MSIX_ENTRY_UPPER_ADDR); - msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower; - msg_data = readl(msix_tbl + PCI_MSIX_ENTRY_DATA); - vec_ctrl = readl(msix_tbl + PCI_MSIX_ENTRY_VECTOR_CTRL); + reg = ep_func->msix_cap + PCI_MSIX_TABLE; + tbl_offset = dw_pcie_ep_readl_dbi(ep, func_no, reg); + bir = FIELD_GET(PCI_MSIX_TABLE_BIR, tbl_offset); + tbl_offset &= PCI_MSIX_TABLE_OFFSET; - iounmap(msix_tbl); + msix_tbl = ep->epf_bar[bir]->addr + tbl_offset; + msg_addr = msix_tbl[(interrupt_num - 1)].msg_addr; + msg_data = msix_tbl[(interrupt_num - 1)].msg_data; + vec_ctrl = msix_tbl[(interrupt_num - 1)].vector_ctrl; - if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT) + if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT) { + dev_dbg(pci->dev, "MSI-X entry ctrl set\n"); return -EPERM; + } - ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr, - epc->mem->page_size); + msg_addr = dw_pcie_ep_align_addr(epc, msg_addr, &map_size, &offset); + ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, + map_size); if (ret) return ret; - writel(msg_data, ep->msi_mem); + writel(msg_data, ep->msi_mem + offset); - dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys); + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_msix_irq); + +/** + * dw_pcie_ep_cleanup - Cleanup DWC EP resources after fundamental reset + * @ep: DWC EP device + * + * Cleans up the DWC EP specific resources like eDMA etc... after fundamental + * reset like PERST#. Note that this API is only applicable for drivers + * supporting PERST# or any other methods of fundamental reset. + */ +void dw_pcie_ep_cleanup(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + dwc_pcie_debugfs_deinit(pci); + dw_pcie_edma_remove(pci); +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_cleanup); -void dw_pcie_ep_exit(struct dw_pcie_ep *ep) +/** + * dw_pcie_ep_deinit - Deinitialize the endpoint device + * @ep: DWC EP device + * + * Deinitialize the endpoint device. EPC device is not destroyed since that will + * be taken care by Devres. + */ +void dw_pcie_ep_deinit(struct dw_pcie_ep *ep) { struct pci_epc *epc = ep->epc; + dw_pcie_ep_cleanup(ep); + pci_epc_mem_free_addr(epc, ep->msi_mem_phys, ep->msi_mem, - epc->mem->page_size); + epc->mem->window.page_size); pci_epc_mem_exit(epc); } +EXPORT_SYMBOL_GPL(dw_pcie_ep_deinit); -int dw_pcie_ep_init(struct dw_pcie_ep *ep) +static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci) +{ + struct dw_pcie_ep *ep = &pci->ep; + unsigned int offset; + unsigned int nbars; + enum pci_barno bar; + u32 reg, i, val; + + offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR); + + dw_pcie_dbi_ro_wr_en(pci); + + if (offset) { + reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, reg); + + /* + * PCIe r6.0, sec 7.8.6.2 require us to support at least one + * size in the range from 1 MB to 512 GB. Advertise support + * for 1 MB BAR size only. + * + * For a BAR that has been configured via dw_pcie_ep_set_bar(), + * advertise support for only that size instead. + */ + for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) { + /* + * While the RESBAR_CAP_REG_* fields are sticky, the + * RESBAR_CTRL_REG_BAR_SIZE field is non-sticky (it is + * sticky in certain versions of DWC PCIe, but not all). + * + * RESBAR_CTRL_REG_BAR_SIZE is updated automatically by + * the controller when RESBAR_CAP_REG is written, which + * is why RESBAR_CAP_REG is written here. + */ + val = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + bar = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, val); + if (ep->epf_bar[bar]) + pci_epc_bar_size_to_rebar_cap(ep->epf_bar[bar]->size, &val); + else + val = BIT(4); + + dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, val); + } + } + + dw_pcie_setup(pci); + dw_pcie_dbi_ro_wr_dis(pci); +} + +/** + * dw_pcie_ep_init_registers - Initialize DWC EP specific registers + * @ep: DWC EP device + * + * Initialize the registers (CSRs) specific to DWC EP. This API should be called + * only when the endpoint receives an active refclk (either from host or + * generated locally). + */ +int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep) { - int ret; - void *addr; - struct pci_epc *epc; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; struct device *dev = pci->dev; - struct device_node *np = dev->of_node; + struct pci_epc *epc = ep->epc; + u32 ptm_cap_base, reg; + u8 hdr_type; + u8 func_no; + void *addr; + int ret; - if (!pci->dbi_base || !pci->dbi_base2) { - dev_err(dev, "dbi_base/dbi_base2 is not populated\n"); - return -EINVAL; - } - if (pci->iatu_unroll_enabled && !pci->atu_base) { - dev_err(dev, "atu_base is not populated\n"); - return -EINVAL; + hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE) & + PCI_HEADER_TYPE_MASK; + if (hdr_type != PCI_HEADER_TYPE_NORMAL) { + dev_err(pci->dev, + "PCIe controller is not set to EP mode (hdr_type:0x%x)!\n", + hdr_type); + return -EIO; } - ret = of_property_read_u32(np, "num-ib-windows", &ep->num_ib_windows); - if (ret < 0) { - dev_err(dev, "Unable to read *num-ib-windows* property\n"); + dw_pcie_version_detect(pci); + + dw_pcie_iatu_detect(pci); + + ret = dw_pcie_edma_detect(pci); + if (ret) return ret; + + ret = -ENOMEM; + if (!ep->ib_window_map) { + ep->ib_window_map = devm_bitmap_zalloc(dev, pci->num_ib_windows, + GFP_KERNEL); + if (!ep->ib_window_map) + goto err_remove_edma; } - if (ep->num_ib_windows > MAX_IATU_IN) { - dev_err(dev, "Invalid *num-ib-windows*\n"); - return -EINVAL; + + if (!ep->ob_window_map) { + ep->ob_window_map = devm_bitmap_zalloc(dev, pci->num_ob_windows, + GFP_KERNEL); + if (!ep->ob_window_map) + goto err_remove_edma; } - ret = of_property_read_u32(np, "num-ob-windows", &ep->num_ob_windows); - if (ret < 0) { - dev_err(dev, "Unable to read *num-ob-windows* property\n"); - return ret; + if (!ep->outbound_addr) { + addr = devm_kcalloc(dev, pci->num_ob_windows, sizeof(phys_addr_t), + GFP_KERNEL); + if (!addr) + goto err_remove_edma; + ep->outbound_addr = addr; } - if (ep->num_ob_windows > MAX_IATU_OUT) { - dev_err(dev, "Invalid *num-ob-windows*\n"); - return -EINVAL; + + for (func_no = 0; func_no < epc->max_functions; func_no++) { + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (ep_func) + continue; + + ep_func = devm_kzalloc(dev, sizeof(*ep_func), GFP_KERNEL); + if (!ep_func) + goto err_remove_edma; + + ep_func->func_no = func_no; + ep_func->msi_cap = dw_pcie_ep_find_capability(ep, func_no, + PCI_CAP_ID_MSI); + ep_func->msix_cap = dw_pcie_ep_find_capability(ep, func_no, + PCI_CAP_ID_MSIX); + + list_add_tail(&ep_func->list, &ep->func_list); } - ep->ib_window_map = devm_kcalloc(dev, - BITS_TO_LONGS(ep->num_ib_windows), - sizeof(long), - GFP_KERNEL); - if (!ep->ib_window_map) - return -ENOMEM; - - ep->ob_window_map = devm_kcalloc(dev, - BITS_TO_LONGS(ep->num_ob_windows), - sizeof(long), - GFP_KERNEL); - if (!ep->ob_window_map) - return -ENOMEM; - - addr = devm_kcalloc(dev, ep->num_ob_windows, sizeof(phys_addr_t), - GFP_KERNEL); - if (!addr) - return -ENOMEM; - ep->outbound_addr = addr; + if (ep->ops->init) + ep->ops->init(ep); + + ptm_cap_base = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_PTM); + + /* + * PTM responder capability can be disabled only after disabling + * PTM root capability. + */ + if (ptm_cap_base) { + dw_pcie_dbi_ro_wr_en(pci); + reg = dw_pcie_readl_dbi(pci, ptm_cap_base + PCI_PTM_CAP); + reg &= ~PCI_PTM_CAP_ROOT; + dw_pcie_writel_dbi(pci, ptm_cap_base + PCI_PTM_CAP, reg); + + reg = dw_pcie_readl_dbi(pci, ptm_cap_base + PCI_PTM_CAP); + reg &= ~(PCI_PTM_CAP_RES | PCI_PTM_GRANULARITY_MASK); + dw_pcie_writel_dbi(pci, ptm_cap_base + PCI_PTM_CAP, reg); + dw_pcie_dbi_ro_wr_dis(pci); + } + + dw_pcie_ep_init_non_sticky_registers(pci); + + dwc_pcie_debugfs_init(pci, DW_PCIE_EP_TYPE); + + return 0; + +err_remove_edma: + dw_pcie_edma_remove(pci); + + return ret; +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_init_registers); + +/** + * dw_pcie_ep_linkup - Notify EPF drivers about Link Up event + * @ep: DWC EP device + */ +void dw_pcie_ep_linkup(struct dw_pcie_ep *ep) +{ + struct pci_epc *epc = ep->epc; + + pci_epc_linkup(epc); +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_linkup); + +/** + * dw_pcie_ep_linkdown - Notify EPF drivers about Link Down event + * @ep: DWC EP device + * + * Non-sticky registers are also initialized before sending the notification to + * the EPF drivers. This is needed since the registers need to be initialized + * before the link comes back again. + */ +void dw_pcie_ep_linkdown(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct pci_epc *epc = ep->epc; + + /* + * Initialize the non-sticky DWC registers as they would've reset post + * Link Down. This is specifically needed for drivers not supporting + * PERST# as they have no way to reinitialize the registers before the + * link comes back again. + */ + dw_pcie_ep_init_non_sticky_registers(pci); + + pci_epc_linkdown(epc); +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_linkdown); + +static int dw_pcie_ep_get_resources(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *np = dev->of_node; + struct pci_epc *epc = ep->epc; + struct resource *res; + int ret; + + ret = dw_pcie_get_resources(pci); + if (ret) + return ret; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space"); + if (!res) + return -EINVAL; + + ep->phys_base = res->start; + ep->addr_size = resource_size(res); + + /* + * artpec6_pcie_cpu_addr_fixup() uses ep->phys_base, so call + * dw_pcie_parent_bus_offset() after setting ep->phys_base. + */ + pci->parent_bus_offset = dw_pcie_parent_bus_offset(pci, "addr_space", + ep->phys_base); + + ret = of_property_read_u8(np, "max-functions", &epc->max_functions); + if (ret < 0) + epc->max_functions = 1; + + return 0; +} + +/** + * dw_pcie_ep_init - Initialize the endpoint device + * @ep: DWC EP device + * + * Initialize the endpoint device. Allocate resources and create the EPC + * device with the endpoint framework. + * + * Return: 0 if success, errno otherwise. + */ +int dw_pcie_ep_init(struct dw_pcie_ep *ep) +{ + int ret; + struct pci_epc *epc; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + + INIT_LIST_HEAD(&ep->func_list); epc = devm_pci_epc_create(dev, &epc_ops); if (IS_ERR(epc)) { @@ -557,31 +1097,33 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) ep->epc = epc; epc_set_drvdata(epc, ep); - if (ep->ops->ep_init) - ep->ops->ep_init(ep); + ret = dw_pcie_ep_get_resources(ep); + if (ret) + return ret; - ret = of_property_read_u8(np, "max-functions", &epc->max_functions); - if (ret < 0) - epc->max_functions = 1; + if (ep->ops->pre_init) + ep->ops->pre_init(ep); - ret = __pci_epc_mem_init(epc, ep->phys_base, ep->addr_size, - ep->page_size); + ret = pci_epc_mem_init(epc, ep->phys_base, ep->addr_size, + ep->page_size); if (ret < 0) { dev_err(dev, "Failed to initialize address space\n"); return ret; } ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys, - epc->mem->page_size); + epc->mem->window.page_size); if (!ep->msi_mem) { + ret = -ENOMEM; dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n"); - return -ENOMEM; + goto err_exit_epc_mem; } - ep->msi_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSI); - ep->msix_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSIX); + return 0; - dw_pcie_setup(pci); +err_exit_epc_mem: + pci_epc_mem_exit(epc); - return 0; + return ret; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_init); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 721d60a5d9e4..372207c33a85 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -3,13 +3,17 @@ * Synopsys DesignWare PCIe host controller driver * * Copyright (C) 2013 Samsung Electronics Co., Ltd. - * http://www.samsung.com + * https://www.samsung.com * * 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> #include <linux/of_pci.h> #include <linux/pci_regs.h> @@ -19,86 +23,53 @@ #include "pcie-designware.h" static struct pci_ops dw_pcie_ops; - -static int dw_pcie_rd_own_conf(struct pcie_port *pp, int where, int size, - u32 *val) -{ - struct dw_pcie *pci; - - if (pp->ops->rd_own_conf) - return pp->ops->rd_own_conf(pp, where, size, val); - - pci = to_dw_pcie_from_pp(pp); - return dw_pcie_read(pci->dbi_base + where, size, val); -} - -static int dw_pcie_wr_own_conf(struct pcie_port *pp, int where, int size, - u32 val) -{ - struct dw_pcie *pci; - - if (pp->ops->wr_own_conf) - return pp->ops->wr_own_conf(pp, where, size, val); - - pci = to_dw_pcie_from_pp(pp); - return dw_pcie_write(pci->dbi_base + where, size, val); -} - -static void dw_msi_ack_irq(struct irq_data *d) -{ - irq_chip_ack_parent(d); -} - -static void dw_msi_mask_irq(struct irq_data *d) -{ - pci_msi_mask_irq(d); - irq_chip_mask_parent(d); -} - -static void dw_msi_unmask_irq(struct irq_data *d) -{ - pci_msi_unmask_irq(d); - irq_chip_unmask_parent(d); -} - -static struct irq_chip dw_pcie_msi_irq_chip = { - .name = "PCI-MSI", - .irq_ack = dw_msi_ack_irq, - .irq_mask = dw_msi_mask_irq, - .irq_unmask = dw_msi_unmask_irq, -}; - -static struct msi_domain_info dw_pcie_msi_domain_info = { - .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI), - .chip = &dw_pcie_msi_irq_chip, +static struct pci_ops dw_pcie_ecam_ops; +static struct pci_ops dw_child_pcie_ops; + +#define DW_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) +#define DW_PCIE_MSI_FLAGS_SUPPORTED (MSI_FLAG_MULTI_PCI_MSI | \ + MSI_FLAG_PCI_MSIX | \ + MSI_GENERIC_FLAGS_MASK) + +#define IS_256MB_ALIGNED(x) IS_ALIGNED(x, SZ_256M) + +static const struct msi_parent_ops dw_pcie_msi_parent_ops = { + .required_flags = DW_PCIE_MSI_FLAGS_REQUIRED, + .supported_flags = DW_PCIE_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "DW-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; /* MSI int handler */ -irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) +irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp) { - int i, pos, irq; - u32 val, num_ctrls; + int i, pos; + unsigned long val; + u32 status, num_ctrls; irqreturn_t ret = IRQ_NONE; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; for (i = 0; i < num_ctrls; i++) { - dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_STATUS + - (i * MSI_REG_CTRL_BLOCK_SIZE), - 4, &val); - if (!val) + status = dw_pcie_readl_dbi(pci, PCIE_MSI_INTR0_STATUS + + (i * MSI_REG_CTRL_BLOCK_SIZE)); + if (!status) continue; ret = IRQ_HANDLED; + val = status; pos = 0; - while ((pos = find_next_bit((unsigned long *) &val, - MAX_MSI_IRQS_PER_CTRL, + while ((pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, pos)) != MAX_MSI_IRQS_PER_CTRL) { - irq = irq_find_mapping(pp->irq_domain, - (i * MAX_MSI_IRQS_PER_CTRL) + - pos); - generic_handle_irq(irq); + generic_handle_domain_irq(pp->irq_domain, + (i * MAX_MSI_IRQS_PER_CTRL) + + pos); pos++; } } @@ -110,7 +81,7 @@ irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) static void dw_chained_msi_isr(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); - struct pcie_port *pp; + struct dw_pcie_rp *pp; chained_irq_enter(chip, desc); @@ -120,106 +91,78 @@ static void dw_chained_msi_isr(struct irq_desc *desc) chained_irq_exit(chip, desc); } -static void dw_pci_setup_msi_msg(struct irq_data *data, struct msi_msg *msg) +static void dw_pci_setup_msi_msg(struct irq_data *d, struct msi_msg *msg) { - struct pcie_port *pp = irq_data_get_irq_chip_data(data); + 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; - if (pp->ops->get_msi_addr) - msi_target = pp->ops->get_msi_addr(pp); - else - msi_target = (u64)pp->msi_data; + msi_target = (u64)pp->msi_data; msg->address_lo = lower_32_bits(msi_target); msg->address_hi = upper_32_bits(msi_target); - if (pp->ops->get_msi_data) - msg->data = pp->ops->get_msi_data(pp, data->hwirq); - else - msg->data = data->hwirq; + msg->data = d->hwirq; dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n", - (int)data->hwirq, msg->address_hi, msg->address_lo); -} - -static int dw_pci_msi_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) -{ - return -EINVAL; + (int)d->hwirq, msg->address_hi, msg->address_lo); } -static void dw_pci_bottom_mask(struct irq_data *data) +static void dw_pci_bottom_mask(struct irq_data *d) { - struct pcie_port *pp = irq_data_get_irq_chip_data(data); + 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); - if (pp->ops->msi_clear_irq) { - pp->ops->msi_clear_irq(pp, data->hwirq); - } else { - ctrl = data->hwirq / MAX_MSI_IRQS_PER_CTRL; - res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; - bit = data->hwirq % MAX_MSI_IRQS_PER_CTRL; + 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_status[ctrl] &= ~(1 << bit); - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + res, 4, - ~pp->irq_status[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 *data) +static void dw_pci_bottom_unmask(struct irq_data *d) { - struct pcie_port *pp = irq_data_get_irq_chip_data(data); + 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); - if (pp->ops->msi_set_irq) { - pp->ops->msi_set_irq(pp, data->hwirq); - } else { - ctrl = data->hwirq / MAX_MSI_IRQS_PER_CTRL; - res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; - bit = data->hwirq % MAX_MSI_IRQS_PER_CTRL; + 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_status[ctrl] |= 1 << bit; - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + res, 4, - ~pp->irq_status[ctrl]); - } + pp->irq_mask[ctrl] &= ~BIT(bit); + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK + res, pp->irq_mask[ctrl]); raw_spin_unlock_irqrestore(&pp->lock, flags); } static void dw_pci_bottom_ack(struct irq_data *d) { - struct pcie_port *pp = irq_data_get_irq_chip_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; ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL; res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL; - raw_spin_lock_irqsave(&pp->lock, flags); - - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_STATUS + res, 4, 1 << bit); - - if (pp->ops->msi_irq_ack) - pp->ops->msi_irq_ack(d->hwirq, pp); - - raw_spin_unlock_irqrestore(&pp->lock, flags); + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_STATUS + res, BIT(bit)); } static struct irq_chip dw_pci_msi_bottom_irq_chip = { .name = "DWPCI-MSI", .irq_ack = dw_pci_bottom_ack, .irq_compose_msi_msg = dw_pci_setup_msi_msg, - .irq_set_affinity = dw_pci_msi_set_affinity, .irq_mask = dw_pci_bottom_mask, .irq_unmask = dw_pci_bottom_unmask, }; @@ -228,7 +171,7 @@ static int dw_pcie_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *args) { - struct pcie_port *pp = domain->host_data; + struct dw_pcie_rp *pp = domain->host_data; unsigned long flags; u32 i; int bit; @@ -245,7 +188,7 @@ static int dw_pcie_irq_domain_alloc(struct irq_domain *domain, for (i = 0; i < nr_irqs; i++) irq_domain_set_info(domain, virq + i, bit + i, - &dw_pci_msi_bottom_irq_chip, + pp->msi_irq_chip, pp, handle_edge_irq, NULL, NULL); @@ -255,13 +198,13 @@ static int dw_pcie_irq_domain_alloc(struct irq_domain *domain, static void dw_pcie_irq_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { - struct irq_data *data = irq_domain_get_irq_data(domain, virq); - struct pcie_port *pp = irq_data_get_irq_chip_data(data); + 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, data->hwirq, + bitmap_release_region(pp->msi_irq_in_use, d->hwirq, order_base_2(nr_irqs)); raw_spin_unlock_irqrestore(&pp->lock, flags); @@ -272,419 +215,867 @@ static const struct irq_domain_ops dw_pcie_msi_domain_ops = { .free = dw_pcie_irq_domain_free, }; -int dw_pcie_allocate_domains(struct pcie_port *pp) +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; } - 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); -void dw_pcie_free_msi(struct pcie_port *pp) +void dw_pcie_free_msi(struct dw_pcie_rp *pp) { - irq_set_chained_handler(pp->msi_irq, NULL); - irq_set_handler_data(pp->msi_irq, NULL); + u32 ctrl; + + for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) { + if (pp->msi_irq[ctrl] > 0) + irq_set_chained_handler_and_data(pp->msi_irq[ctrl], + NULL, NULL); + } - irq_domain_remove(pp->msi_domain); irq_domain_remove(pp->irq_domain); } +EXPORT_SYMBOL_GPL(dw_pcie_free_msi); -void dw_pcie_msi_init(struct pcie_port *pp) +void dw_pcie_msi_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct device *dev = pci->dev; - struct page *page; - u64 msi_target; + u64 msi_target = (u64)pp->msi_data; + u32 ctrl, num_ctrls; - page = alloc_page(GFP_KERNEL); - pp->msi_data = dma_map_page(dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); - if (dma_mapping_error(dev, pp->msi_data)) { - dev_err(dev, "Failed to map MSI data\n"); - __free_page(page); + if (!pci_msi_enabled() || !pp->has_msi_ctrl) return; + + num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + + /* Initialize IRQ Status array */ + for (ctrl = 0; ctrl < num_ctrls; ctrl++) { + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK + + (ctrl * MSI_REG_CTRL_BLOCK_SIZE), + pp->irq_mask[ctrl]); + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_ENABLE + + (ctrl * MSI_REG_CTRL_BLOCK_SIZE), + ~0); } - msi_target = (u64)pp->msi_data; /* Program the msi_data */ - dw_pcie_wr_own_conf(pp, PCIE_MSI_ADDR_LO, 4, - lower_32_bits(msi_target)); - dw_pcie_wr_own_conf(pp, PCIE_MSI_ADDR_HI, 4, - upper_32_bits(msi_target)); + 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); -int dw_pcie_host_init(struct pcie_port *pp) +static int dw_pcie_parse_split_msi_irq(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct device *dev = pci->dev; - struct device_node *np = dev->of_node; struct platform_device *pdev = to_platform_device(dev); - struct resource_entry *win, *tmp; - struct pci_bus *bus, *child; - struct pci_host_bridge *bridge; - struct resource *cfg_res; + u32 ctrl, max_vectors; + int irq; + + /* Parse any "msiX" IRQs described in the devicetree */ + for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) { + char msi_name[] = "msiX"; + + msi_name[3] = '0' + ctrl; + irq = platform_get_irq_byname_optional(pdev, msi_name); + if (irq == -ENXIO) + break; + if (irq < 0) + return dev_err_probe(dev, irq, + "Failed to parse MSI IRQ '%s'\n", + msi_name); + + pp->msi_irq[ctrl] = irq; + } + + /* If no "msiX" IRQs, caller should fallback to "msi" IRQ */ + if (ctrl == 0) + return -ENXIO; + + max_vectors = ctrl * MAX_MSI_IRQS_PER_CTRL; + if (pp->num_vectors > max_vectors) { + dev_warn(dev, "Exceeding number of MSI vectors, limiting to %u\n", + max_vectors); + pp->num_vectors = max_vectors; + } + if (!pp->num_vectors) + pp->num_vectors = max_vectors; + + return 0; +} + +int dw_pcie_msi_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + u64 *msi_vaddr = NULL; int ret; + u32 ctrl, num_ctrls; - raw_spin_lock_init(&pci->pp.lock); + for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) + pp->irq_mask[ctrl] = ~0; - cfg_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); - if (cfg_res) { - pp->cfg0_size = resource_size(cfg_res) >> 1; - pp->cfg1_size = resource_size(cfg_res) >> 1; - pp->cfg0_base = cfg_res->start; - pp->cfg1_base = cfg_res->start + pp->cfg0_size; - } else if (!pp->va_cfg0_base) { - dev_err(dev, "Missing *config* reg space\n"); + if (!pp->msi_irq[0]) { + ret = dw_pcie_parse_split_msi_irq(pp); + if (ret < 0 && ret != -ENXIO) + return ret; } - bridge = pci_alloc_host_bridge(0); - if (!bridge) - return -ENOMEM; + if (!pp->num_vectors) + pp->num_vectors = MSI_DEF_NUM_VECTORS; + num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + + if (!pp->msi_irq[0]) { + pp->msi_irq[0] = platform_get_irq_byname_optional(pdev, "msi"); + if (pp->msi_irq[0] < 0) { + pp->msi_irq[0] = platform_get_irq(pdev, 0); + if (pp->msi_irq[0] < 0) + return pp->msi_irq[0]; + } + } + + dev_dbg(dev, "Using %d MSI vectors\n", pp->num_vectors); - ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, - &bridge->windows, &pp->io_base); + pp->msi_irq_chip = &dw_pci_msi_bottom_irq_chip; + + ret = dw_pcie_allocate_domains(pp); if (ret) return ret; - ret = devm_request_pci_bus_resources(dev, &bridge->windows); - if (ret) - goto error; - - /* Get the I/O and memory ranges from DT */ - resource_list_for_each_entry_safe(win, tmp, &bridge->windows) { - switch (resource_type(win->res)) { - case IORESOURCE_IO: - ret = devm_pci_remap_iospace(dev, win->res, - pp->io_base); - if (ret) { - dev_warn(dev, "Error %d: failed to map resource %pR\n", - ret, win->res); - resource_list_destroy_entry(win); - } else { - pp->io = win->res; - pp->io->name = "I/O"; - pp->io_size = resource_size(pp->io); - pp->io_bus_addr = pp->io->start - win->offset; - } - break; - case IORESOURCE_MEM: - pp->mem = win->res; - pp->mem->name = "MEM"; - pp->mem_size = resource_size(pp->mem); - pp->mem_bus_addr = pp->mem->start - win->offset; - break; - case 0: - pp->cfg = win->res; - pp->cfg0_size = resource_size(pp->cfg) >> 1; - pp->cfg1_size = resource_size(pp->cfg) >> 1; - pp->cfg0_base = pp->cfg->start; - pp->cfg1_base = pp->cfg->start + pp->cfg0_size; - break; - case IORESOURCE_BUS: - pp->busn = win->res; - break; - } + for (ctrl = 0; ctrl < num_ctrls; ctrl++) { + if (pp->msi_irq[ctrl] > 0) + irq_set_chained_handler_and_data(pp->msi_irq[ctrl], + dw_chained_msi_isr, pp); } - if (!pci->dbi_base) { - pci->dbi_base = devm_pci_remap_cfgspace(dev, - pp->cfg->start, - resource_size(pp->cfg)); - if (!pci->dbi_base) { - dev_err(dev, "Error with ioremap\n"); - ret = -ENOMEM; - goto error; + /* + * Even though the iMSI-RX Module supports 64-bit addresses some + * peripheral PCIe devices may lack 64-bit message support. In + * 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. + */ + ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); + if (!ret) + msi_vaddr = dmam_alloc_coherent(dev, sizeof(u64), &pp->msi_data, + GFP_KERNEL); + + if (!msi_vaddr) { + dev_warn(dev, "Failed to allocate 32-bit MSI address\n"); + dma_set_coherent_mask(dev, DMA_BIT_MASK(64)); + msi_vaddr = dmam_alloc_coherent(dev, sizeof(u64), &pp->msi_data, + GFP_KERNEL); + if (!msi_vaddr) { + dev_err(dev, "Failed to allocate MSI address\n"); + dw_pcie_free_msi(pp); + return -ENOMEM; } } - pp->mem_base = pp->mem->start; + return 0; +} +EXPORT_SYMBOL_GPL(dw_pcie_msi_host_init); - if (!pp->va_cfg0_base) { - pp->va_cfg0_base = devm_pci_remap_cfgspace(dev, - pp->cfg0_base, pp->cfg0_size); - if (!pp->va_cfg0_base) { - dev_err(dev, "Error with ioremap in function\n"); - ret = -ENOMEM; - goto error; - } +static void dw_pcie_host_request_msg_tlp_res(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct resource_entry *win; + struct resource *res; + + win = resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM); + if (win) { + res = devm_kzalloc(pci->dev, sizeof(*res), GFP_KERNEL); + if (!res) + return; + + /* + * Allocate MSG TLP region of size 'region_align' at the end of + * the host bridge window. + */ + res->start = win->res->end - pci->region_align + 1; + res->end = win->res->end; + res->name = "msg"; + res->flags = win->res->flags | IORESOURCE_BUSY; + + if (!devm_request_resource(pci->dev, win->res, res)) + pp->msg_res = res; } +} - if (!pp->va_cfg1_base) { - pp->va_cfg1_base = devm_pci_remap_cfgspace(dev, - pp->cfg1_base, - pp->cfg1_size); - if (!pp->va_cfg1_base) { - dev_err(dev, "Error with ioremap\n"); - ret = -ENOMEM; - goto error; - } +static int dw_pcie_config_ecam_iatu(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dw_pcie_ob_atu_cfg atu = {0}; + resource_size_t bus_range_max; + struct resource_entry *bus; + int ret; + + bus = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS); + + /* + * Root bus under the host bridge doesn't require any iATU configuration + * as DBI region will be used to access root bus config space. + * Immediate bus under Root Bus, needs type 0 iATU configuration and + * remaining buses need type 1 iATU configuration. + */ + atu.index = 0; + atu.type = PCIE_ATU_TYPE_CFG0; + atu.parent_bus_addr = pp->cfg0_base + SZ_1M; + /* 1MiB is to cover 1 (bus) * 32 (devices) * 8 (functions) */ + atu.size = SZ_1M; + atu.ctrl2 = PCIE_ATU_CFG_SHIFT_MODE_ENABLE; + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) + return ret; + + bus_range_max = resource_size(bus->res); + + if (bus_range_max < 2) + return 0; + + /* Configure remaining buses in type 1 iATU configuration */ + atu.index = 1; + atu.type = PCIE_ATU_TYPE_CFG1; + atu.parent_bus_addr = pp->cfg0_base + SZ_2M; + atu.size = (SZ_1M * bus_range_max) - SZ_2M; + atu.ctrl2 = PCIE_ATU_CFG_SHIFT_MODE_ENABLE; + + return dw_pcie_prog_outbound_atu(pci, &atu); +} + +static int dw_pcie_create_ecam_window(struct dw_pcie_rp *pp, struct resource *res) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct resource_entry *bus; + + bus = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS); + if (!bus) + return -ENODEV; + + pp->cfg = pci_ecam_create(dev, res, bus->res, &pci_generic_ecam_ops); + if (IS_ERR(pp->cfg)) + return PTR_ERR(pp->cfg); + + return 0; +} + +static bool dw_pcie_ecam_enabled(struct dw_pcie_rp *pp, struct resource *config_res) +{ + struct resource *bus_range; + u64 nr_buses; + + /* Vendor glue drivers may implement their own ECAM mechanism */ + if (pp->native_ecam) + return false; + + /* + * PCIe spec r6.0, sec 7.2.2 mandates the base address used for ECAM to + * be aligned on a 2^(n+20) byte boundary, where n is the number of bits + * used for representing 'bus' in BDF. Since the DWC cores always use 8 + * bits for representing 'bus', the base address has to be aligned to + * 2^28 byte boundary, which is 256 MiB. + */ + if (!IS_256MB_ALIGNED(config_res->start)) + return false; + + bus_range = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS)->res; + if (!bus_range) + return false; + + nr_buses = resource_size(config_res) >> PCIE_ECAM_BUS_SHIFT; + + return nr_buses >= resource_size(bus_range); +} + +static int dw_pcie_host_get_resources(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource_entry *win; + struct resource *res; + int ret; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); + if (!res) { + dev_err(dev, "Missing \"config\" reg space\n"); + return -ENODEV; + } + + pp->cfg0_size = resource_size(res); + pp->cfg0_base = res->start; + + pp->ecam_enabled = dw_pcie_ecam_enabled(pp, res); + if (pp->ecam_enabled) { + ret = dw_pcie_create_ecam_window(pp, res); + if (ret) + return ret; + + pp->bridge->ops = &dw_pcie_ecam_ops; + pp->bridge->sysdata = pp->cfg; + pp->cfg->priv = pp; + } else { + pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pp->va_cfg0_base)) + return PTR_ERR(pp->va_cfg0_base); + + /* 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; } - ret = of_property_read_u32(np, "num-viewport", &pci->num_viewport); + /* Get the I/O range from DT */ + win = resource_list_first_type(&pp->bridge->windows, IORESOURCE_IO); + if (win) { + pp->io_size = resource_size(win->res); + pp->io_bus_addr = win->res->start - win->offset; + pp->io_base = pci_pio_to_address(win->res->start); + } + + /* + * visconti_pcie_cpu_addr_fixup() uses pp->io_base, so we have to + * call dw_pcie_parent_bus_offset() after setting pp->io_base. + */ + pci->parent_bus_offset = dw_pcie_parent_bus_offset(pci, "config", + pp->cfg0_base); + return 0; +} + +int dw_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct device_node *np = dev->of_node; + struct pci_host_bridge *bridge; + int ret; + + raw_spin_lock_init(&pp->lock); + + bridge = devm_pci_alloc_host_bridge(dev, 0); + if (!bridge) + return -ENOMEM; + + pp->bridge = bridge; + + ret = dw_pcie_host_get_resources(pp); if (ret) - pci->num_viewport = 2; + return ret; + + if (pp->ops->init) { + ret = pp->ops->init(pp); + if (ret) + goto err_free_ecam; + } + + if (pci_msi_enabled()) { + pp->has_msi_ctrl = !(pp->ops->msi_init || + of_property_present(np, "msi-parent") || + of_property_present(np, "msi-map")); - if (IS_ENABLED(CONFIG_PCI_MSI)) { /* - * If a specific SoC driver needs to change the - * default number of vectors, it needs to implement - * the set_num_vectors callback. + * For the has_msi_ctrl case the default assignment is handled + * in the dw_pcie_msi_host_init(). */ - if (!pp->ops->set_num_vectors) { + if (!pp->has_msi_ctrl && !pp->num_vectors) { pp->num_vectors = MSI_DEF_NUM_VECTORS; - } else { - pp->ops->set_num_vectors(pp); - - if (pp->num_vectors > MAX_MSI_IRQS || - pp->num_vectors == 0) { - dev_err(dev, - "Invalid number of vectors\n"); - goto error; - } + } else if (pp->num_vectors > MAX_MSI_IRQS) { + dev_err(dev, "Invalid number of vectors\n"); + ret = -EINVAL; + goto err_deinit_host; } - if (!pp->ops->msi_host_init) { - ret = dw_pcie_allocate_domains(pp); - if (ret) - goto error; - - if (pp->msi_irq) - irq_set_chained_handler_and_data(pp->msi_irq, - dw_chained_msi_isr, - pp); - } else { - ret = pp->ops->msi_host_init(pp); + if (pp->ops->msi_init) { + ret = pp->ops->msi_init(pp); + if (ret < 0) + goto err_deinit_host; + } else if (pp->has_msi_ctrl) { + ret = dw_pcie_msi_host_init(pp); if (ret < 0) - goto error; + goto err_deinit_host; } } - if (pp->ops->host_init) { - ret = pp->ops->host_init(pp); - if (ret) - goto error; + dw_pcie_version_detect(pci); + + dw_pcie_iatu_detect(pci); + + if (pci->num_lanes < 1) + pci->num_lanes = dw_pcie_link_get_max_link_width(pci); + + ret = of_pci_get_equalization_presets(dev, &pp->presets, pci->num_lanes); + if (ret) + goto err_free_msi; + + if (pp->ecam_enabled) { + ret = dw_pcie_config_ecam_iatu(pp); + if (ret) { + dev_err(dev, "Failed to configure iATU in ECAM mode\n"); + goto err_free_msi; + } } - pp->root_bus_nr = pp->busn->start; + /* + * Allocate the resource for MSG TLP before programming the iATU + * outbound window in dw_pcie_setup_rc(). Since the allocation depends + * on the value of 'region_align', this has to be done after + * dw_pcie_iatu_detect(). + * + * Glue drivers need to set 'use_atu_msg' before dw_pcie_host_init() to + * make use of the generic MSG TLP implementation. + */ + if (pp->use_atu_msg) + dw_pcie_host_request_msg_tlp_res(pp); - bridge->dev.parent = dev; - bridge->sysdata = pp; - bridge->busnr = pp->root_bus_nr; - bridge->ops = &dw_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; + ret = dw_pcie_edma_detect(pci); + if (ret) + goto err_free_msi; - ret = pci_scan_root_bus_bridge(bridge); + ret = dw_pcie_setup_rc(pp); if (ret) - goto error; + goto err_remove_edma; - bus = bridge->bus; + if (!dw_pcie_link_up(pci)) { + ret = dw_pcie_start_link(pci); + if (ret) + goto err_remove_edma; + } - if (pp->ops->scan_bus) - pp->ops->scan_bus(pp); + /* + * Note: Skip the link up delay only when a Link Up IRQ is present. + * If there is no Link Up IRQ, we should not bypass the delay + * because that would require users to manually rescan for devices. + */ + if (!pp->use_linkup_irq) + /* Ignore errors, the link may come up later */ + dw_pcie_wait_for_link(pci); + + ret = pci_host_probe(bridge); + if (ret) + goto err_stop_link; - pci_bus_size_bridges(bus); - pci_bus_assign_resources(bus); + if (pp->ops->post_init) + pp->ops->post_init(pp); - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); + dwc_pcie_debugfs_init(pci, DW_PCIE_RC_TYPE); - pci_bus_add_devices(bus); return 0; -error: - pci_free_host_bridge(bridge); +err_stop_link: + dw_pcie_stop_link(pci); + +err_remove_edma: + dw_pcie_edma_remove(pci); + +err_free_msi: + if (pp->has_msi_ctrl) + 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); -static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus, - u32 devfn, int where, int size, u32 *val) +void dw_pcie_host_deinit(struct dw_pcie_rp *pp) { - int ret, type; - u32 busdev, cfg_size; - u64 cpu_addr; - void __iomem *va_cfg_base; struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - if (pp->ops->rd_other_conf) - return pp->ops->rd_other_conf(pp, bus, devfn, where, size, val); + dwc_pcie_debugfs_deinit(pci); - busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) | - PCIE_ATU_FUNC(PCI_FUNC(devfn)); + pci_stop_root_bus(pp->bridge->bus); + pci_remove_root_bus(pp->bridge->bus); - if (bus->parent->number == pp->root_bus_nr) { - type = PCIE_ATU_TYPE_CFG0; - cpu_addr = pp->cfg0_base; - cfg_size = pp->cfg0_size; - va_cfg_base = pp->va_cfg0_base; - } else { - type = PCIE_ATU_TYPE_CFG1; - cpu_addr = pp->cfg1_base; - cfg_size = pp->cfg1_size; - va_cfg_base = pp->va_cfg1_base; - } + dw_pcie_stop_link(pci); - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1, - type, cpu_addr, - busdev, cfg_size); - ret = dw_pcie_read(va_cfg_base + where, size, val); - if (pci->num_viewport <= 2) - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1, - PCIE_ATU_TYPE_IO, pp->io_base, - pp->io_bus_addr, pp->io_size); + dw_pcie_edma_remove(pci); - return ret; + if (pp->has_msi_ctrl) + 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); -static int dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus, - u32 devfn, int where, int size, u32 val) +static void __iomem *dw_pcie_other_conf_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) { - int ret, type; - u32 busdev, cfg_size; - u64 cpu_addr; - void __iomem *va_cfg_base; + struct dw_pcie_rp *pp = bus->sysdata; struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dw_pcie_ob_atu_cfg atu = { 0 }; + int type, ret; + u32 busdev; - if (pp->ops->wr_other_conf) - return pp->ops->wr_other_conf(pp, bus, devfn, where, size, val); + /* + * Checking whether the link is up here is a last line of defense + * against platforms that forward errors on the system bus as + * SError upon PCI configuration transactions issued when the link + * is down. This check is racy by definition and does not stop + * the system from triggering an SError if the link goes down + * after this check is performed. + */ + if (!dw_pcie_link_up(pci)) + return NULL; busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) | PCIE_ATU_FUNC(PCI_FUNC(devfn)); - if (bus->parent->number == pp->root_bus_nr) { + if (pci_is_root_bus(bus->parent)) type = PCIE_ATU_TYPE_CFG0; - cpu_addr = pp->cfg0_base; - cfg_size = pp->cfg0_size; - va_cfg_base = pp->va_cfg0_base; - } else { + else type = PCIE_ATU_TYPE_CFG1; - cpu_addr = pp->cfg1_base; - cfg_size = pp->cfg1_size; - va_cfg_base = pp->va_cfg1_base; - } - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1, - type, cpu_addr, - busdev, cfg_size); - ret = dw_pcie_write(va_cfg_base + where, size, val); - if (pci->num_viewport <= 2) - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1, - PCIE_ATU_TYPE_IO, pp->io_base, - pp->io_bus_addr, pp->io_size); + atu.type = type; + atu.parent_bus_addr = pp->cfg0_base - pci->parent_bus_offset; + atu.pci_addr = busdev; + atu.size = pp->cfg0_size; - return ret; + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) + return NULL; + + return pp->va_cfg0_base + where; } -static int dw_pcie_valid_device(struct pcie_port *pp, struct pci_bus *bus, - int dev) +static int dw_pcie_rd_other_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) { + struct dw_pcie_rp *pp = bus->sysdata; struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dw_pcie_ob_atu_cfg atu = { 0 }; + int ret; - /* If there is no link, then there is no device */ - if (bus->number != pp->root_bus_nr) { - if (!dw_pcie_link_up(pci)) - return 0; - } + ret = pci_generic_config_read(bus, devfn, where, size, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; - /* Access only one slot on each root port */ - if (bus->number == pp->root_bus_nr && dev > 0) - return 0; + if (pp->cfg0_io_shared) { + atu.type = PCIE_ATU_TYPE_IO; + atu.parent_bus_addr = pp->io_base - pci->parent_bus_offset; + atu.pci_addr = pp->io_bus_addr; + atu.size = pp->io_size; - return 1; + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) + return PCIBIOS_SET_FAILED; + } + + return PCIBIOS_SUCCESSFUL; } -static int dw_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, - int size, u32 *val) +static int dw_pcie_wr_other_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) { - struct pcie_port *pp = bus->sysdata; + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dw_pcie_ob_atu_cfg atu = { 0 }; + int ret; + + ret = pci_generic_config_write(bus, devfn, where, size, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (pp->cfg0_io_shared) { + atu.type = PCIE_ATU_TYPE_IO; + atu.parent_bus_addr = pp->io_base - pci->parent_bus_offset; + atu.pci_addr = pp->io_bus_addr; + atu.size = pp->io_size; - if (!dw_pcie_valid_device(pp, bus, PCI_SLOT(devfn))) { - *val = 0xffffffff; - return PCIBIOS_DEVICE_NOT_FOUND; + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) + return PCIBIOS_SET_FAILED; } - if (bus->number == pp->root_bus_nr) - return dw_pcie_rd_own_conf(pp, where, size, val); + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops dw_child_pcie_ops = { + .map_bus = dw_pcie_other_conf_map_bus, + .read = dw_pcie_rd_other_conf, + .write = dw_pcie_wr_other_conf, +}; - return dw_pcie_rd_other_conf(pp, bus, devfn, where, size, val); +void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, int where) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + if (PCI_SLOT(devfn) > 0) + return NULL; + + return pci->dbi_base + where; } +EXPORT_SYMBOL_GPL(dw_pcie_own_conf_map_bus); -static int dw_pcie_wr_conf(struct pci_bus *bus, u32 devfn, - int where, int size, u32 val) +static void __iomem *dw_pcie_ecam_conf_map_bus(struct pci_bus *bus, unsigned int devfn, int where) { - struct pcie_port *pp = bus->sysdata; + 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 (!dw_pcie_valid_device(pp, bus, PCI_SLOT(devfn))) - return PCIBIOS_DEVICE_NOT_FOUND; + if (busn > 0) + return pci_ecam_map_bus(bus, devfn, where); - if (bus->number == pp->root_bus_nr) - return dw_pcie_wr_own_conf(pp, where, size, val); + if (PCI_SLOT(devfn) > 0) + return NULL; - return dw_pcie_wr_other_conf(pp, bus, devfn, where, size, val); + return pci->dbi_base + where; +} + +static int dw_pcie_op_assert_perst(struct pci_bus *bus, bool assert) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + return dw_pcie_assert_perst(pci, assert); } static struct pci_ops dw_pcie_ops = { - .read = dw_pcie_rd_conf, - .write = dw_pcie_wr_conf, + .map_bus = dw_pcie_own_conf_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + .assert_perst = dw_pcie_op_assert_perst, +}; + +static struct pci_ops dw_pcie_ecam_ops = { + .map_bus = dw_pcie_ecam_conf_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; -static u8 dw_pcie_iatu_unroll_enabled(struct dw_pcie *pci) +static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) { - u32 val; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dw_pcie_ob_atu_cfg atu = { 0 }; + struct resource_entry *entry; + int i, ret; + + /* Note the very first outbound ATU is used for CFG IOs */ + if (!pci->num_ob_windows) { + dev_err(pci->dev, "No outbound iATU found\n"); + return -EINVAL; + } - val = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT); - if (val == 0xffffffff) - return 1; + /* + * Ensure all out/inbound windows are disabled before proceeding with + * the MEM/IO (dma-)ranges setups. + */ + for (i = 0; i < pci->num_ob_windows; i++) + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, i); + + for (i = 0; i < pci->num_ib_windows; i++) + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, i); + + i = 0; + resource_list_for_each_entry(entry, &pp->bridge->windows) { + if (resource_type(entry->res) != IORESOURCE_MEM) + continue; + + if (pci->num_ob_windows <= ++i) + break; + + 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) - + resource_size(pp->msg_res); + else + atu.size = resource_size(entry->res); + + 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; + } + } + + if (pp->io_size) { + if (pci->num_ob_windows > ++i) { + atu.index = i; + atu.type = PCIE_ATU_TYPE_IO; + atu.parent_bus_addr = pp->io_base - pci->parent_bus_offset; + atu.pci_addr = pp->io_bus_addr; + atu.size = pp->io_size; + + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) { + dev_err(pci->dev, "Failed to set IO range %pr\n", + entry->res); + return ret; + } + } else { + pp->cfg0_io_shared = true; + } + } + + if (pci->num_ob_windows <= i) + dev_warn(pci->dev, "Ranges exceed outbound iATU size (%d)\n", + pci->num_ob_windows); + + pp->msg_atu_index = i; + + i = 0; + resource_list_for_each_entry(entry, &pp->bridge->dma_ranges) { + if (resource_type(entry->res) != IORESOURCE_MEM) + continue; + + if (pci->num_ib_windows <= i) + break; + + 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; + } + } + + if (pci->num_ib_windows <= i) + dev_warn(pci->dev, "Dma-ranges exceed inbound iATU size (%u)\n", + pci->num_ib_windows); return 0; } -void dw_pcie_setup_rc(struct pcie_port *pp) +static void dw_pcie_program_presets(struct dw_pcie_rp *pp, enum pci_bus_speed speed) { - u32 val, ctrl, num_ctrls; 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; + } - dw_pcie_setup(pci); + if (presets[0] == PCI_EQ_RESV) + return; - num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + cap = dw_pcie_find_ext_capability(pci, cap_id); + if (!cap) + return; - /* Initialize IRQ Status array */ - for (ctrl = 0; ctrl < num_ctrls; ctrl++) { - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + - (ctrl * MSI_REG_CTRL_BLOCK_SIZE), - 4, ~0); - dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + - (ctrl * MSI_REG_CTRL_BLOCK_SIZE), - 4, ~0); - pp->irq_status[ctrl] = 0; - } + /* + * 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; + int ret; + + /* + * Enable DBI read-only registers for writing/updating configuration. + * Write permission gets disabled towards the end of this function. + */ + dw_pcie_dbi_ro_wr_en(pci); + + dw_pcie_setup(pci); + + dw_pcie_msi_init(pp); /* Setup RC BARs */ dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0x00000004); dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0x00000000); /* Setup interrupt pins */ - dw_pcie_dbi_ro_wr_en(pci); val = dw_pcie_readl_dbi(pci, PCI_INTERRUPT_LINE); val &= 0xffff00ff; val |= 0x00000100; dw_pcie_writel_dbi(pci, PCI_INTERRUPT_LINE, val); - dw_pcie_dbi_ro_wr_dis(pci); /* Setup bus numbers */ val = dw_pcie_readl_dbi(pci, PCI_PRIMARY_BUS); @@ -699,39 +1090,147 @@ void dw_pcie_setup_rc(struct pcie_port *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 ->rd_other_conf, it means the platform - * uses its own address translation component rather than ATU, so - * we should not program the ATU here. + * 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->ops->rd_other_conf) { - /* Get iATU unroll support */ - pci->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pci); - dev_dbg(pci->dev, "iATU unroll: %s\n", - pci->iatu_unroll_enabled ? "enabled" : "disabled"); - - if (pci->iatu_unroll_enabled && !pci->atu_base) - pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET; - - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0, - PCIE_ATU_TYPE_MEM, pp->mem_base, - pp->mem_bus_addr, pp->mem_size); - if (pci->num_viewport > 2) - dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX2, - PCIE_ATU_TYPE_IO, pp->io_base, - pp->io_bus_addr, pp->io_size); + if (pp->bridge->child_ops == &dw_child_pcie_ops) { + ret = dw_pcie_iatu_setup(pp); + if (ret) + return ret; } - dw_pcie_wr_own_conf(pp, PCI_BASE_ADDRESS_0, 4, 0); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); - /* Enable write permission for the DBI read-only register */ - dw_pcie_dbi_ro_wr_en(pci); /* Program correct class for RC */ - dw_pcie_wr_own_conf(pp, PCI_CLASS_DEVICE, 2, PCI_CLASS_BRIDGE_PCI); - /* Better disable write permission right after the update */ - dw_pcie_dbi_ro_wr_dis(pci); + dw_pcie_writew_dbi(pci, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_PCI); - dw_pcie_rd_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, &val); + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); val |= PORT_LOGIC_SPEED_CHANGE; - dw_pcie_wr_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, val); + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} +EXPORT_SYMBOL_GPL(dw_pcie_setup_rc); + +static int dw_pcie_pme_turn_off(struct dw_pcie *pci) +{ + struct dw_pcie_ob_atu_cfg atu = { 0 }; + void __iomem *mem; + int ret; + + if (pci->num_ob_windows <= pci->pp.msg_atu_index) + return -ENOSPC; + + if (!pci->pp.msg_res) + return -ENOSPC; + + atu.code = PCIE_MSG_CODE_PME_TURN_OFF; + atu.routing = PCIE_MSG_TYPE_R_BC; + atu.type = PCIE_ATU_TYPE_MSG; + atu.size = resource_size(pci->pp.msg_res); + atu.index = pci->pp.msg_atu_index; + + atu.parent_bus_addr = pci->pp.msg_res->start - pci->parent_bus_offset; + + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) + return ret; + + mem = ioremap(pci->pp.msg_res->start, pci->region_align); + if (!mem) + return -ENOMEM; + + /* A dummy write is converted to a Msg TLP */ + writel(0, mem); + + iounmap(mem); + + return 0; +} + +int dw_pcie_suspend_noirq(struct dw_pcie *pci) +{ + u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; + int ret; + + /* + * If L1SS is supported, then do not put the link into L2 as some + * devices such as NVMe expect low resume latency. + */ + if (dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKCTL) & PCI_EXP_LNKCTL_ASPM_L1) + return 0; + + if (pci->pp.ops->pme_turn_off) { + pci->pp.ops->pme_turn_off(&pci->pp); + } else { + ret = dw_pcie_pme_turn_off(pci); + if (ret) + return ret; + } + + ret = read_poll_timeout(dw_pcie_get_ltssm, val, + val == DW_PCIE_LTSSM_L2_IDLE || + val <= DW_PCIE_LTSSM_DETECT_WAIT, + PCIE_PME_TO_L2_TIMEOUT_US/10, + PCIE_PME_TO_L2_TIMEOUT_US, false, pci); + if (ret) { + /* Only log message when LTSSM isn't in DETECT or POLL */ + dev_err(pci->dev, "Timeout waiting for L2 entry! LTSSM: 0x%x\n", val); + return ret; + } + + /* + * Per PCIe r6.0, sec 5.3.3.2.1, software should wait at least + * 100ns after L2/L3 Ready before turning off refclock and + * main power. This is harmless when no endpoint is connected. + */ + udelay(1); + + dw_pcie_stop_link(pci); + if (pci->pp.ops->deinit) + pci->pp.ops->deinit(&pci->pp); + + pci->suspended = true; + + return ret; +} +EXPORT_SYMBOL_GPL(dw_pcie_suspend_noirq); + +int dw_pcie_resume_noirq(struct dw_pcie *pci) +{ + int ret; + + if (!pci->suspended) + return 0; + + pci->suspended = false; + + if (pci->pp.ops->init) { + ret = pci->pp.ops->init(&pci->pp); + if (ret) { + dev_err(pci->dev, "Host init failed: %d\n", ret); + return ret; + } + } + + dw_pcie_setup_rc(&pci->pp); + + ret = dw_pcie_start_link(pci); + if (ret) + return ret; + + ret = dw_pcie_wait_for_link(pci); + if (ret) + return ret; + + 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 c12bf794d69c..12f41886c65d 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -12,20 +12,16 @@ #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/init.h> -#include <linux/of_device.h> -#include <linux/of_gpio.h> +#include <linux/of.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/resource.h> -#include <linux/signal.h> #include <linux/types.h> -#include <linux/regmap.h> #include "pcie-designware.h" struct dw_plat_pcie { struct dw_pcie *pci; - struct regmap *regmap; enum dw_pcie_device_mode mode; }; @@ -33,65 +29,29 @@ struct dw_plat_pcie_of_data { enum dw_pcie_device_mode mode; }; -static const struct of_device_id dw_plat_pcie_of_match[]; - -static int dw_plat_pcie_host_init(struct pcie_port *pp) -{ - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - - dw_pcie_setup_rc(pp); - dw_pcie_wait_for_link(pci); - - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(pp); - - return 0; -} - -static void dw_plat_set_num_vectors(struct pcie_port *pp) -{ - pp->num_vectors = MAX_MSI_IRQS; -} - static const struct dw_pcie_host_ops dw_plat_pcie_host_ops = { - .host_init = dw_plat_pcie_host_init, - .set_num_vectors = dw_plat_set_num_vectors, -}; - -static int dw_plat_pcie_establish_link(struct dw_pcie *pci) -{ - return 0; -} - -static const struct dw_pcie_ops dw_pcie_ops = { - .start_link = dw_plat_pcie_establish_link, }; static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - struct pci_epc *epc = ep->epc; enum pci_barno bar; - for (bar = BAR_0; bar <= BAR_5; bar++) + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); - - epc->features |= EPC_FEATURE_NO_LINKUP_NOTIFIER; - epc->features |= EPC_FEATURE_MSIX_AVAILABLE; } static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, - u16 interrupt_num) + unsigned int type, u16 interrupt_num) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); switch (type) { - case PCI_EPC_IRQ_LEGACY: - return dw_pcie_ep_raise_legacy_irq(ep, func_no); - case PCI_EPC_IRQ_MSI: + 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); - case PCI_EPC_IRQ_MSIX: + case PCI_IRQ_MSIX: return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); default: dev_err(pci->dev, "UNKNOWN IRQ type\n"); @@ -100,16 +60,28 @@ static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } -static struct dw_pcie_ep_ops pcie_ep_ops = { - .ep_init = dw_plat_pcie_ep_init, +static const struct pci_epc_features dw_plat_pcie_epc_features = { + .msi_capable = true, + .msix_capable = true, +}; + +static const struct pci_epc_features* +dw_plat_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &dw_plat_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .init = dw_plat_pcie_ep_init, .raise_irq = dw_plat_pcie_ep_raise_irq, + .get_features = dw_plat_pcie_get_features, }; static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie, struct platform_device *pdev) { struct dw_pcie *pci = dw_plat_pcie->pci; - struct pcie_port *pp = &pci->pp; + struct dw_pcie_rp *pp = &pci->pp; struct device *dev = &pdev->dev; int ret; @@ -117,12 +89,7 @@ static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie, if (pp->irq < 0) return pp->irq; - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq(pdev, 0); - if (pp->msi_irq < 0) - return pp->msi_irq; - } - + pp->num_vectors = MAX_MSI_IRQS; pp->ops = &dw_plat_pcie_host_ops; ret = dw_pcie_host_init(pp); @@ -134,54 +101,19 @@ static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie, return 0; } -static int dw_plat_add_pcie_ep(struct dw_plat_pcie *dw_plat_pcie, - struct platform_device *pdev) -{ - int ret; - struct dw_pcie_ep *ep; - struct resource *res; - struct device *dev = &pdev->dev; - struct dw_pcie *pci = dw_plat_pcie->pci; - - ep = &pci->ep; - ep->ops = &pcie_ep_ops; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi2"); - pci->dbi_base2 = devm_ioremap_resource(dev, res); - if (IS_ERR(pci->dbi_base2)) - return PTR_ERR(pci->dbi_base2); - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space"); - if (!res) - return -EINVAL; - - ep->phys_base = res->start; - ep->addr_size = resource_size(res); - - ret = dw_pcie_ep_init(ep); - if (ret) { - dev_err(dev, "Failed to initialize endpoint\n"); - return ret; - } - return 0; -} - static int dw_plat_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct dw_plat_pcie *dw_plat_pcie; struct dw_pcie *pci; - struct resource *res; /* Resource from DT */ int ret; - const struct of_device_id *match; const struct dw_plat_pcie_of_data *data; enum dw_pcie_device_mode mode; - match = of_match_device(dw_plat_pcie_of_match, dev); - if (!match) + data = of_device_get_match_data(dev); + if (!data) return -EINVAL; - data = (struct dw_plat_pcie_of_data *)match->data; mode = (enum dw_pcie_device_mode)data->mode; dw_plat_pcie = devm_kzalloc(dev, sizeof(*dw_plat_pcie), GFP_KERNEL); @@ -193,19 +125,10 @@ static int dw_plat_pcie_probe(struct platform_device *pdev) return -ENOMEM; pci->dev = dev; - pci->ops = &dw_pcie_ops; dw_plat_pcie->pci = pci; dw_plat_pcie->mode = mode; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); - if (!res) - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - - pci->dbi_base = devm_ioremap_resource(dev, res); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); - platform_set_drvdata(pdev, dw_plat_pcie); switch (dw_plat_pcie->mode) { @@ -214,22 +137,32 @@ static int dw_plat_pcie_probe(struct platform_device *pdev) return -ENODEV; ret = dw_plat_add_pcie_port(dw_plat_pcie, pdev); - if (ret < 0) - return ret; break; case DW_PCIE_EP_TYPE: if (!IS_ENABLED(CONFIG_PCIE_DW_PLAT_EP)) return -ENODEV; - ret = dw_plat_add_pcie_ep(dw_plat_pcie, pdev); - if (ret < 0) + pci->ep.ops = &pcie_ep_ops; + ret = dw_pcie_ep_init(&pci->ep); + if (ret) return ret; + + ret = dw_pcie_ep_init_registers(&pci->ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(&pci->ep); + } + + pci_epc_init_notify(pci->ep.epc); + break; default: dev_err(dev, "INVALID device type %d\n", dw_plat_pcie->mode); + ret = -EINVAL; + break; } - return 0; + return ret; } static const struct dw_plat_pcie_of_data dw_plat_pcie_rc_of_data = { diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 93ef8c31fb39..75fc8b767fcc 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -3,26 +3,293 @@ * Synopsys DesignWare PCIe host controller driver * * Copyright (C) 2013 Samsung Electronics Co., Ltd. - * http://www.samsung.com + * https://www.samsung.com * * Author: Jingoo Han <jg1.han@samsung.com> */ +#include <linux/align.h> +#include <linux/bitops.h> +#include <linux/clk.h> #include <linux/delay.h> +#include <linux/dma/edma.h> +#include <linux/gpio/consumer.h> +#include <linux/ioport.h> #include <linux/of.h> +#include <linux/of_address.h> +#include <linux/pcie-dwc.h> +#include <linux/platform_device.h> +#include <linux/sizes.h> #include <linux/types.h> +#include "../../pci.h" #include "pcie-designware.h" -/* PCIe Port Logic registers */ -#define PLR_OFFSET 0x700 -#define PCIE_PHY_DEBUG_R1 (PLR_OFFSET + 0x2c) -#define PCIE_PHY_DEBUG_R1_LINK_UP (0x1 << 4) -#define PCIE_PHY_DEBUG_R1_LINK_IN_TRAINING (0x1 << 29) +static const char * const dw_pcie_app_clks[DW_PCIE_NUM_APP_CLKS] = { + [DW_PCIE_DBI_CLK] = "dbi", + [DW_PCIE_MSTR_CLK] = "mstr", + [DW_PCIE_SLV_CLK] = "slv", +}; + +static const char * const dw_pcie_core_clks[DW_PCIE_NUM_CORE_CLKS] = { + [DW_PCIE_PIPE_CLK] = "pipe", + [DW_PCIE_CORE_CLK] = "core", + [DW_PCIE_AUX_CLK] = "aux", + [DW_PCIE_REF_CLK] = "ref", +}; + +static const char * const dw_pcie_app_rsts[DW_PCIE_NUM_APP_RSTS] = { + [DW_PCIE_DBI_RST] = "dbi", + [DW_PCIE_MSTR_RST] = "mstr", + [DW_PCIE_SLV_RST] = "slv", +}; + +static const char * const dw_pcie_core_rsts[DW_PCIE_NUM_CORE_RSTS] = { + [DW_PCIE_NON_STICKY_RST] = "non-sticky", + [DW_PCIE_STICKY_RST] = "sticky", + [DW_PCIE_CORE_RST] = "core", + [DW_PCIE_PIPE_RST] = "pipe", + [DW_PCIE_PHY_RST] = "phy", + [DW_PCIE_HOT_RST] = "hot", + [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; + + for (i = 0; i < DW_PCIE_NUM_APP_CLKS; i++) + pci->app_clks[i].id = dw_pcie_app_clks[i]; + + for (i = 0; i < DW_PCIE_NUM_CORE_CLKS; i++) + pci->core_clks[i].id = dw_pcie_core_clks[i]; + + ret = devm_clk_bulk_get_optional(pci->dev, DW_PCIE_NUM_APP_CLKS, + pci->app_clks); + if (ret) + return ret; + + return devm_clk_bulk_get_optional(pci->dev, DW_PCIE_NUM_CORE_CLKS, + pci->core_clks); +} + +static int dw_pcie_get_resets(struct dw_pcie *pci) +{ + int i, ret; + + for (i = 0; i < DW_PCIE_NUM_APP_RSTS; i++) + pci->app_rsts[i].id = dw_pcie_app_rsts[i]; + + for (i = 0; i < DW_PCIE_NUM_CORE_RSTS; i++) + pci->core_rsts[i].id = dw_pcie_core_rsts[i]; + + ret = devm_reset_control_bulk_get_optional_shared(pci->dev, + DW_PCIE_NUM_APP_RSTS, + pci->app_rsts); + if (ret) + return ret; + + ret = devm_reset_control_bulk_get_optional_exclusive(pci->dev, + DW_PCIE_NUM_CORE_RSTS, + pci->core_rsts); + if (ret) + return ret; + + pci->pe_rst = devm_gpiod_get_optional(pci->dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(pci->pe_rst)) + return PTR_ERR(pci->pe_rst); + + return 0; +} + +int dw_pcie_get_resources(struct dw_pcie *pci) +{ + struct platform_device *pdev = to_platform_device(pci->dev); + struct device_node *np = dev_of_node(pci->dev); + struct resource *res; + int ret; + + if (!pci->dbi_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + pci->dbi_base = devm_pci_remap_cfg_resource(pci->dev, res); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + pci->dbi_phys_addr = res->start; + } + + /* DBI2 is mainly useful for the endpoint controller */ + if (!pci->dbi_base2) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi2"); + if (res) { + pci->dbi_base2 = devm_pci_remap_cfg_resource(pci->dev, res); + if (IS_ERR(pci->dbi_base2)) + return PTR_ERR(pci->dbi_base2); + } else { + pci->dbi_base2 = pci->dbi_base + SZ_4K; + } + } + + /* For non-unrolled iATU/eDMA platforms this range will be ignored */ + if (!pci->atu_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "atu"); + if (res) { + pci->atu_size = resource_size(res); + pci->atu_base = devm_ioremap_resource(pci->dev, res); + if (IS_ERR(pci->atu_base)) + return PTR_ERR(pci->atu_base); + pci->atu_phys_addr = res->start; + } else { + pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET; + } + } + + /* Set a default value suitable for at most 8 in and 8 out windows */ + if (!pci->atu_size) + pci->atu_size = SZ_4K; + + /* eDMA region can be mapped to a custom base address */ + if (!pci->edma.reg_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dma"); + if (res) { + pci->edma.reg_base = devm_ioremap_resource(pci->dev, res); + if (IS_ERR(pci->edma.reg_base)) + return PTR_ERR(pci->edma.reg_base); + } else if (pci->atu_size >= 2 * DEFAULT_DBI_DMA_OFFSET) { + pci->edma.reg_base = pci->atu_base + DEFAULT_DBI_DMA_OFFSET; + } + } + + /* 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); + if (ret) + return ret; + + ret = dw_pcie_get_resets(pci); + if (ret) + return ret; + } + + if (pci->max_link_speed < 1) + pci->max_link_speed = of_pci_get_max_link_speed(np); + + of_property_read_u32(np, "num-lanes", &pci->num_lanes); + + if (of_property_read_bool(np, "snps,enable-cdm-check")) + dw_pcie_cap_set(pci, CDM_CHECK); + + return 0; +} + +void dw_pcie_version_detect(struct dw_pcie *pci) +{ + u32 ver; + + /* The content of the CSR is zero on DWC PCIe older than v4.70a */ + ver = dw_pcie_readl_dbi(pci, PCIE_VERSION_NUMBER); + if (!ver) + return; + + if (pci->version && pci->version != ver) + dev_warn(pci->dev, "Versions don't match (%08x != %08x)\n", + pci->version, ver); + else + pci->version = ver; + + ver = dw_pcie_readl_dbi(pci, PCIE_VERSION_TYPE); + + if (pci->type && pci->type != ver) + dev_warn(pci->dev, "Types don't match (%08x != %08x)\n", + pci->type, ver); + else + pci->type = ver; +} + +u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap) +{ + return PCI_FIND_NEXT_CAP(dw_pcie_read_cfg, PCI_CAPABILITY_LIST, cap, + pci); +} +EXPORT_SYMBOL_GPL(dw_pcie_find_capability); + +u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap) +{ + return PCI_FIND_NEXT_EXT_CAP(dw_pcie_read_cfg, 0, cap, pci); +} +EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability); + +static u16 __dw_pcie_find_vsec_capability(struct dw_pcie *pci, u16 vendor_id, + u16 vsec_id) +{ + u16 vsec = 0; + u32 header; + + if (vendor_id != dw_pcie_readw_dbi(pci, PCI_VENDOR_ID)) + return 0; + + while ((vsec = PCI_FIND_NEXT_EXT_CAP(dw_pcie_read_cfg, vsec, + PCI_EXT_CAP_ID_VNDR, pci))) { + header = dw_pcie_readl_dbi(pci, vsec + PCI_VNDR_HEADER); + if (PCI_VNDR_HEADER_ID(header) == vsec_id) + return vsec; + } + + return 0; +} + +static u16 dw_pcie_find_vsec_capability(struct dw_pcie *pci, + const struct dwc_pcie_vsec_id *vsec_ids) +{ + const struct dwc_pcie_vsec_id *vid; + u16 vsec; + u32 header; + + for (vid = vsec_ids; vid->vendor_id; vid++) { + vsec = __dw_pcie_find_vsec_capability(pci, vid->vendor_id, + vid->vsec_id); + if (vsec) { + header = dw_pcie_readl_dbi(pci, vsec + PCI_VNDR_HEADER); + if (PCI_VNDR_HEADER_REV(header) == vid->vsec_rev) + return vsec; + } + } + + return 0; +} + +u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci) +{ + return dw_pcie_find_vsec_capability(pci, dwc_pcie_rasdes_vsec_ids); +} +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 ((uintptr_t)addr & (size - 1)) { + if (!IS_ALIGNED((uintptr_t)addr, size)) { *val = 0; return PCIBIOS_BAD_REGISTER_NUMBER; } @@ -40,10 +307,11 @@ int dw_pcie_read(void __iomem *addr, int size, u32 *val) return PCIBIOS_SUCCESSFUL; } +EXPORT_SYMBOL_GPL(dw_pcie_read); int dw_pcie_write(void __iomem *addr, int size, u32 val) { - if ((uintptr_t)addr & (size - 1)) + if (!IS_ALIGNED((uintptr_t)addr, size)) return PCIBIOS_BAD_REGISTER_NUMBER; if (size == 4) @@ -57,338 +325,882 @@ int dw_pcie_write(void __iomem *addr, int size, u32 val) return PCIBIOS_SUCCESSFUL; } +EXPORT_SYMBOL_GPL(dw_pcie_write); -u32 __dw_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg, - size_t size) +u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size) { int ret; u32 val; - if (pci->ops->read_dbi) - return pci->ops->read_dbi(pci, base, reg, size); + if (pci->ops && pci->ops->read_dbi) + return pci->ops->read_dbi(pci, pci->dbi_base, reg, size); - ret = dw_pcie_read(base + reg, size, &val); + ret = dw_pcie_read(pci->dbi_base + reg, size, &val); if (ret) dev_err(pci->dev, "Read DBI address failed\n"); return val; } +EXPORT_SYMBOL_GPL(dw_pcie_read_dbi); -void __dw_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg, - size_t size, u32 val) +void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val) { int ret; - if (pci->ops->write_dbi) { - pci->ops->write_dbi(pci, base, reg, size, val); + if (pci->ops && pci->ops->write_dbi) { + pci->ops->write_dbi(pci, pci->dbi_base, reg, size, val); return; } - ret = dw_pcie_write(base + reg, size, val); + ret = dw_pcie_write(pci->dbi_base + reg, size, val); if (ret) dev_err(pci->dev, "Write DBI address failed\n"); } +EXPORT_SYMBOL_GPL(dw_pcie_write_dbi); -static u32 dw_pcie_readl_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg) +void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val) { - u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index); + int ret; + + if (pci->ops && pci->ops->write_dbi2) { + pci->ops->write_dbi2(pci, pci->dbi_base2, reg, size, val); + return; + } - return dw_pcie_readl_atu(pci, offset + reg); + ret = dw_pcie_write(pci->dbi_base2 + reg, size, val); + if (ret) + dev_err(pci->dev, "write DBI address failed\n"); } +EXPORT_SYMBOL_GPL(dw_pcie_write_dbi2); -static void dw_pcie_writel_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg, - u32 val) +static inline void __iomem *dw_pcie_select_atu(struct dw_pcie *pci, u32 dir, + u32 index) { - u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index); + if (dw_pcie_cap_is(pci, IATU_UNROLL)) + return pci->atu_base + PCIE_ATU_UNROLL_BASE(dir, index); - dw_pcie_writel_atu(pci, offset + reg, val); + dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, dir | index); + return pci->atu_base; } -static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, int index, - int type, u64 cpu_addr, - u64 pci_addr, u32 size) +static u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 dir, u32 index, u32 reg) { - u32 retries, val; + void __iomem *base; + int ret; + u32 val; + + base = dw_pcie_select_atu(pci, dir, index); + + if (pci->ops && pci->ops->read_dbi) + return pci->ops->read_dbi(pci, base, reg, 4); - dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_LOWER_BASE, - lower_32_bits(cpu_addr)); - dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_UPPER_BASE, - upper_32_bits(cpu_addr)); - dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_LIMIT, - lower_32_bits(cpu_addr + size - 1)); - dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_LOWER_TARGET, - lower_32_bits(pci_addr)); - dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_UPPER_TARGET, - upper_32_bits(pci_addr)); - dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL1, - type); - dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2, - PCIE_ATU_ENABLE); + ret = dw_pcie_read(base + reg, 4, &val); + if (ret) + dev_err(pci->dev, "Read ATU address failed\n"); + + return val; +} + +static void dw_pcie_writel_atu(struct dw_pcie *pci, u32 dir, u32 index, + u32 reg, u32 val) +{ + void __iomem *base; + int ret; + + base = dw_pcie_select_atu(pci, dir, index); + + if (pci->ops && pci->ops->write_dbi) { + pci->ops->write_dbi(pci, base, reg, 4, val); + return; + } + + ret = dw_pcie_write(base + reg, 4, val); + if (ret) + dev_err(pci->dev, "Write ATU address failed\n"); +} + +static inline u32 dw_pcie_readl_atu_ob(struct dw_pcie *pci, u32 index, u32 reg) +{ + return dw_pcie_readl_atu(pci, PCIE_ATU_REGION_DIR_OB, index, reg); +} + +static inline void dw_pcie_writel_atu_ob(struct dw_pcie *pci, u32 index, u32 reg, + u32 val) +{ + dw_pcie_writel_atu(pci, PCIE_ATU_REGION_DIR_OB, index, reg, val); +} +static inline u32 dw_pcie_enable_ecrc(u32 val) +{ /* - * Make sure ATU enable takes effect before any subsequent config - * and I/O accesses. + * DesignWare core version 4.90A has a design issue where the 'TD' + * bit in the Control register-1 of the ATU outbound region acts + * like an override for the ECRC setting, i.e., the presence of TLP + * Digest (ECRC) in the outgoing TLPs is solely determined by this + * bit. This is contrary to the PCIe spec which says that the + * enablement of the ECRC is solely determined by the AER + * registers. + * + * Because of this, even when the ECRC is enabled through AER + * registers, the transactions going through ATU won't have TLP + * Digest as there is no way the PCI core AER code could program + * the TD bit which is specific to the DesignWare core. + * + * The best way to handle this scenario is to program the TD bit + * always. It affects only the traffic from root port to downstream + * devices. + * + * At this point, + * When ECRC is enabled in AER registers, everything works normally + * When ECRC is NOT enabled in AER registers, then, + * on Root Port:- TLP Digest (DWord size) gets appended to each packet + * even through it is not required. Since downstream + * TLPs are mostly for configuration accesses and BAR + * accesses, they are not in critical path and won't + * have much negative effect on the performance. + * on End Point:- TLP Digest is received for some/all the packets coming + * from the root port. TLP Digest is ignored because, + * as per the PCIe Spec r5.0 v1.0 section 2.2.3 + * "TLP Digest Rules", when an endpoint receives TLP + * Digest when its ECRC check functionality is disabled + * in AER registers, received TLP Digest is just ignored. + * Since there is no issue or error reported either side, best way to + * handle the scenario is to program TD bit by default. */ - for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) { - val = dw_pcie_readl_ob_unroll(pci, index, - PCIE_ATU_UNR_REGION_CTRL2); - if (val & PCIE_ATU_ENABLE) - return; - mdelay(LINK_WAIT_IATU); - } - dev_err(pci->dev, "Outbound iATU is not being enabled\n"); + return val | PCIE_ATU_TD; } -void dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type, - u64 cpu_addr, u64 pci_addr, u32 size) +int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, + const struct dw_pcie_ob_atu_cfg *atu) { + u64 parent_bus_addr = atu->parent_bus_addr; u32 retries, val; + u64 limit_addr; - if (pci->ops->cpu_addr_fixup) - cpu_addr = pci->ops->cpu_addr_fixup(pci, cpu_addr); + limit_addr = parent_bus_addr + atu->size - 1; - if (pci->iatu_unroll_enabled) { - dw_pcie_prog_outbound_atu_unroll(pci, index, type, cpu_addr, - pci_addr, size); - return; + if ((limit_addr & ~pci->region_limit) != (parent_bus_addr & ~pci->region_limit) || + !IS_ALIGNED(parent_bus_addr, pci->region_align) || + !IS_ALIGNED(atu->pci_addr, pci->region_align) || !atu->size) { + return -EINVAL; } - dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, - PCIE_ATU_REGION_OUTBOUND | index); - dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_BASE, - lower_32_bits(cpu_addr)); - dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_BASE, - upper_32_bits(cpu_addr)); - dw_pcie_writel_dbi(pci, PCIE_ATU_LIMIT, - lower_32_bits(cpu_addr + size - 1)); - dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_TARGET, - lower_32_bits(pci_addr)); - dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_TARGET, - upper_32_bits(pci_addr)); - dw_pcie_writel_dbi(pci, PCIE_ATU_CR1, type); - dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, PCIE_ATU_ENABLE); + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LOWER_BASE, + lower_32_bits(parent_bus_addr)); + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_UPPER_BASE, + upper_32_bits(parent_bus_addr)); + + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LIMIT, + lower_32_bits(limit_addr)); + if (dw_pcie_ver_is_ge(pci, 460A)) + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_UPPER_LIMIT, + upper_32_bits(limit_addr)); + + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LOWER_TARGET, + lower_32_bits(atu->pci_addr)); + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_UPPER_TARGET, + upper_32_bits(atu->pci_addr)); + + val = atu->type | atu->routing | PCIE_ATU_FUNC_NUM(atu->func_no); + if (upper_32_bits(limit_addr) > upper_32_bits(parent_bus_addr) && + dw_pcie_ver_is_ge(pci, 460A)) + val |= PCIE_ATU_INCREASE_REGION_SIZE; + if (dw_pcie_ver_is(pci, 490A)) + val = dw_pcie_enable_ecrc(val); + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_REGION_CTRL1, val); + + val = PCIE_ATU_ENABLE | atu->ctrl2; + if (atu->type == PCIE_ATU_TYPE_MSG) { + /* The data-less messages only for now */ + val |= PCIE_ATU_INHIBIT_PAYLOAD | atu->code; + } + dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_REGION_CTRL2, val); /* * Make sure ATU enable takes effect before any subsequent config * and I/O accesses. */ for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) { - val = dw_pcie_readl_dbi(pci, PCIE_ATU_CR2); + val = dw_pcie_readl_atu_ob(pci, atu->index, PCIE_ATU_REGION_CTRL2); if (val & PCIE_ATU_ENABLE) - return; + return 0; mdelay(LINK_WAIT_IATU); } + dev_err(pci->dev, "Outbound iATU is not being enabled\n"); + + return -ETIMEDOUT; } -static u32 dw_pcie_readl_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg) +static inline u32 dw_pcie_readl_atu_ib(struct dw_pcie *pci, u32 index, u32 reg) { - u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index); - - return dw_pcie_readl_atu(pci, offset + reg); + return dw_pcie_readl_atu(pci, PCIE_ATU_REGION_DIR_IB, index, reg); } -static void dw_pcie_writel_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg, - u32 val) +static inline void dw_pcie_writel_atu_ib(struct dw_pcie *pci, u32 index, u32 reg, + u32 val) { - u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index); - - dw_pcie_writel_atu(pci, offset + reg, val); + dw_pcie_writel_atu(pci, PCIE_ATU_REGION_DIR_IB, index, reg, val); } -static int dw_pcie_prog_inbound_atu_unroll(struct dw_pcie *pci, int index, - int bar, u64 cpu_addr, - enum dw_pcie_as_type as_type) +int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, + u64 parent_bus_addr, u64 pci_addr, u64 size) { - int type; + u64 limit_addr = pci_addr + size - 1; u32 retries, val; - dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_LOWER_TARGET, - lower_32_bits(cpu_addr)); - dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_UPPER_TARGET, - upper_32_bits(cpu_addr)); - - switch (as_type) { - case DW_PCIE_AS_MEM: - type = PCIE_ATU_TYPE_MEM; - break; - case DW_PCIE_AS_IO: - type = PCIE_ATU_TYPE_IO; - break; - default: + 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) { return -EINVAL; } - dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL1, type); - dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2, - PCIE_ATU_ENABLE | - PCIE_ATU_BAR_MODE_ENABLE | (bar << 8)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_BASE, + lower_32_bits(pci_addr)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_BASE, + upper_32_bits(pci_addr)); + + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LIMIT, + lower_32_bits(limit_addr)); + if (dw_pcie_ver_is_ge(pci, 460A)) + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_LIMIT, + upper_32_bits(limit_addr)); + + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET, + lower_32_bits(parent_bus_addr)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET, + upper_32_bits(parent_bus_addr)); + + val = type; + if (upper_32_bits(limit_addr) > upper_32_bits(pci_addr) && + dw_pcie_ver_is_ge(pci, 460A)) + val |= PCIE_ATU_INCREASE_REGION_SIZE; + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL1, val); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2, PCIE_ATU_ENABLE); /* * Make sure ATU enable takes effect before any subsequent config * and I/O accesses. */ for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) { - val = dw_pcie_readl_ib_unroll(pci, index, - PCIE_ATU_UNR_REGION_CTRL2); + val = dw_pcie_readl_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2); if (val & PCIE_ATU_ENABLE) return 0; mdelay(LINK_WAIT_IATU); } + dev_err(pci->dev, "Inbound iATU is not being enabled\n"); - return -EBUSY; + return -ETIMEDOUT; } -int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int bar, - u64 cpu_addr, enum dw_pcie_as_type as_type) +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) { - int type; u32 retries, val; - if (pci->iatu_unroll_enabled) - return dw_pcie_prog_inbound_atu_unroll(pci, index, bar, - cpu_addr, as_type); - - dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, PCIE_ATU_REGION_INBOUND | - index); - dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_TARGET, lower_32_bits(cpu_addr)); - dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_TARGET, upper_32_bits(cpu_addr)); - - switch (as_type) { - case DW_PCIE_AS_MEM: - type = PCIE_ATU_TYPE_MEM; - break; - case DW_PCIE_AS_IO: - type = PCIE_ATU_TYPE_IO; - break; - default: + if (!IS_ALIGNED(parent_bus_addr, pci->region_align) || + !IS_ALIGNED(parent_bus_addr, size)) return -EINVAL; - } - dw_pcie_writel_dbi(pci, PCIE_ATU_CR1, type); - dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, PCIE_ATU_ENABLE - | PCIE_ATU_BAR_MODE_ENABLE | (bar << 8)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET, + lower_32_bits(parent_bus_addr)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET, + upper_32_bits(parent_bus_addr)); + + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL1, type | + PCIE_ATU_FUNC_NUM(func_no)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2, + PCIE_ATU_ENABLE | PCIE_ATU_FUNC_NUM_MATCH_EN | + PCIE_ATU_BAR_MODE_ENABLE | (bar << 8)); /* * Make sure ATU enable takes effect before any subsequent config * and I/O accesses. */ for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) { - val = dw_pcie_readl_dbi(pci, PCIE_ATU_CR2); + val = dw_pcie_readl_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2); if (val & PCIE_ATU_ENABLE) return 0; mdelay(LINK_WAIT_IATU); } + dev_err(pci->dev, "Inbound iATU is not being enabled\n"); - return -EBUSY; + return -ETIMEDOUT; } -void dw_pcie_disable_atu(struct dw_pcie *pci, int index, - enum dw_pcie_region_type type) +void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index) { - int region; - - switch (type) { - case DW_PCIE_REGION_INBOUND: - region = PCIE_ATU_REGION_INBOUND; - break; - case DW_PCIE_REGION_OUTBOUND: - region = PCIE_ATU_REGION_OUTBOUND; - break; - default: - return; - } - - dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, region | index); - dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, ~PCIE_ATU_ENABLE); + dw_pcie_writel_atu(pci, dir, index, PCIE_ATU_REGION_CTRL2, 0); } int dw_pcie_wait_for_link(struct dw_pcie *pci) { + u32 offset, val; int retries; /* Check if the link is up or not */ - for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { - if (dw_pcie_link_up(pci)) { - dev_info(pci->dev, "Link up\n"); - return 0; - } - usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + for (retries = 0; retries < PCIE_LINK_WAIT_MAX_RETRIES; retries++) { + if (dw_pcie_link_up(pci)) + break; + + msleep(PCIE_LINK_WAIT_SLEEP_MS); } - dev_err(pci->dev, "Phy link never came up\n"); + if (retries >= PCIE_LINK_WAIT_MAX_RETRIES) { + dev_info(pci->dev, "Phy link never came up\n"); + return -ETIMEDOUT; + } - 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); + + dev_info(pci->dev, "PCIe Gen.%u x%u link up\n", + FIELD_GET(PCI_EXP_LNKSTA_CLS, val), + FIELD_GET(PCI_EXP_LNKSTA_NLW, val)); + + return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_wait_for_link); -int dw_pcie_link_up(struct dw_pcie *pci) +bool dw_pcie_link_up(struct dw_pcie *pci) { u32 val; - if (pci->ops->link_up) + if (pci->ops && pci->ops->link_up) return pci->ops->link_up(pci); - val = readl(pci->dbi_base + PCIE_PHY_DEBUG_R1); - return ((val & PCIE_PHY_DEBUG_R1_LINK_UP) && - (!(val & PCIE_PHY_DEBUG_R1_LINK_IN_TRAINING))); + val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1); + return ((val & PCIE_PORT_DEBUG1_LINK_UP) && + (!(val & PCIE_PORT_DEBUG1_LINK_IN_TRAINING))); } +EXPORT_SYMBOL_GPL(dw_pcie_link_up); -void dw_pcie_setup(struct dw_pcie *pci) +void dw_pcie_upconfig_setup(struct dw_pcie *pci) { - int ret; u32 val; - u32 lanes; - struct device *dev = pci->dev; - struct device_node *np = dev->of_node; - ret = of_property_read_u32(np, "num-lanes", &lanes); - if (ret) - lanes = 0; + val = dw_pcie_readl_dbi(pci, PCIE_PORT_MULTI_LANE_CTRL); + val |= PORT_MLTI_UPCFG_SUPPORT; + dw_pcie_writel_dbi(pci, PCIE_PORT_MULTI_LANE_CTRL, val); +} +EXPORT_SYMBOL_GPL(dw_pcie_upconfig_setup); - /* Set the number of lanes */ - val = dw_pcie_readl_dbi(pci, PCIE_PORT_LINK_CONTROL); - val &= ~PORT_LINK_MODE_MASK; - switch (lanes) { - case 1: - val |= PORT_LINK_MODE_1_LANES; +static void dw_pcie_link_set_max_speed(struct dw_pcie *pci) +{ + u32 cap, ctrl2, link_speed; + u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + cap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + + /* + * Even if the platform doesn't want to limit the maximum link speed, + * just cache the hardware default value so that the vendor drivers can + * use it to do any link specific configuration. + */ + if (pci->max_link_speed < 1) { + pci->max_link_speed = FIELD_GET(PCI_EXP_LNKCAP_SLS, cap); + return; + } + + ctrl2 = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCTL2); + ctrl2 &= ~PCI_EXP_LNKCTL2_TLS; + + switch (pcie_link_speed[pci->max_link_speed]) { + case PCIE_SPEED_2_5GT: + link_speed = PCI_EXP_LNKCTL2_TLS_2_5GT; break; - case 2: - val |= PORT_LINK_MODE_2_LANES; + case PCIE_SPEED_5_0GT: + link_speed = PCI_EXP_LNKCTL2_TLS_5_0GT; break; - case 4: - val |= PORT_LINK_MODE_4_LANES; + case PCIE_SPEED_8_0GT: + link_speed = PCI_EXP_LNKCTL2_TLS_8_0GT; break; - case 8: - val |= PORT_LINK_MODE_8_LANES; + case PCIE_SPEED_16_0GT: + link_speed = PCI_EXP_LNKCTL2_TLS_16_0GT; break; default: - dev_err(pci->dev, "num-lanes %u: invalid value\n", lanes); - return; + /* Use hardware capability */ + link_speed = FIELD_GET(PCI_EXP_LNKCAP_SLS, cap); + ctrl2 &= ~PCI_EXP_LNKCTL2_HASD; + break; } - dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val); + + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCTL2, ctrl2 | link_speed); + + cap &= ~((u32)PCI_EXP_LNKCAP_SLS); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, cap | link_speed); + +} + +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; + u8 cap; + + if (!num_lanes) + return; + + /* Set the number of lanes */ + plc = dw_pcie_readl_dbi(pci, PCIE_PORT_LINK_CONTROL); + plc &= ~PORT_LINK_FAST_LINK_MODE; + plc &= ~PORT_LINK_MODE_MASK; /* Set link width speed control register */ - val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); - val &= ~PORT_LOGIC_LINK_WIDTH_MASK; - switch (lanes) { + 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: - val |= PORT_LOGIC_LINK_WIDTH_1_LANES; + plc |= PORT_LINK_MODE_1_LANES; break; case 2: - val |= PORT_LOGIC_LINK_WIDTH_2_LANES; + plc |= PORT_LINK_MODE_2_LANES; break; case 4: - val |= PORT_LOGIC_LINK_WIDTH_4_LANES; + plc |= PORT_LINK_MODE_4_LANES; break; case 8: - val |= PORT_LOGIC_LINK_WIDTH_8_LANES; + plc |= PORT_LINK_MODE_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); + return; + } + dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, plc); + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, lwsc); + + cap = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + lnkcap = dw_pcie_readl_dbi(pci, cap + PCI_EXP_LNKCAP); + lnkcap &= ~PCI_EXP_LNKCAP_MLW; + lnkcap |= FIELD_PREP(PCI_EXP_LNKCAP_MLW, num_lanes); + dw_pcie_writel_dbi(pci, cap + PCI_EXP_LNKCAP, lnkcap); +} + +void dw_pcie_iatu_detect(struct dw_pcie *pci) +{ + int max_region, ob, ib; + u32 val, min, dir; + u64 max; + + val = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT); + if (val == 0xFFFFFFFF) { + dw_pcie_cap_set(pci, IATU_UNROLL); + + max_region = min((int)pci->atu_size / 512, 256); + } else { + pci->atu_base = pci->dbi_base + PCIE_ATU_VIEWPORT_BASE; + pci->atu_size = PCIE_ATU_VIEWPORT_SIZE; + + dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, 0xFF); + max_region = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT) + 1; + } + + for (ob = 0; ob < max_region; ob++) { + dw_pcie_writel_atu_ob(pci, ob, PCIE_ATU_LOWER_TARGET, 0x11110000); + val = dw_pcie_readl_atu_ob(pci, ob, PCIE_ATU_LOWER_TARGET); + if (val != 0x11110000) + break; + } + + for (ib = 0; ib < max_region; ib++) { + dw_pcie_writel_atu_ib(pci, ib, PCIE_ATU_LOWER_TARGET, 0x11110000); + val = dw_pcie_readl_atu_ib(pci, ib, PCIE_ATU_LOWER_TARGET); + if (val != 0x11110000) + break; + } + + if (ob) { + dir = PCIE_ATU_REGION_DIR_OB; + } else if (ib) { + dir = PCIE_ATU_REGION_DIR_IB; + } else { + dev_err(pci->dev, "No iATU regions found\n"); + return; + } + + dw_pcie_writel_atu(pci, dir, 0, PCIE_ATU_LIMIT, 0x0); + min = dw_pcie_readl_atu(pci, dir, 0, PCIE_ATU_LIMIT); + + if (dw_pcie_ver_is_ge(pci, 460A)) { + dw_pcie_writel_atu(pci, dir, 0, PCIE_ATU_UPPER_LIMIT, 0xFFFFFFFF); + max = dw_pcie_readl_atu(pci, dir, 0, PCIE_ATU_UPPER_LIMIT); + } else { + max = 0; } - dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + + pci->num_ob_windows = ob; + pci->num_ib_windows = ib; + pci->region_align = 1 << fls(min); + pci->region_limit = (max << 32) | (SZ_4G - 1); + + dev_info(pci->dev, "iATU: unroll %s, %u ob, %u ib, align %uK, limit %lluG\n", + dw_pcie_cap_is(pci, IATU_UNROLL) ? "T" : "F", + pci->num_ob_windows, pci->num_ib_windows, + pci->region_align / SZ_1K, (pci->region_limit + 1) / SZ_1G); +} + +static u32 dw_pcie_readl_dma(struct dw_pcie *pci, u32 reg) +{ + u32 val = 0; + int ret; + + if (pci->ops && pci->ops->read_dbi) + return pci->ops->read_dbi(pci, pci->edma.reg_base, reg, 4); + + ret = dw_pcie_read(pci->edma.reg_base + reg, 4, &val); + if (ret) + dev_err(pci->dev, "Read DMA address failed\n"); + + return val; +} + +static int dw_pcie_edma_irq_vector(struct device *dev, unsigned int nr) +{ + struct platform_device *pdev = to_platform_device(dev); + char name[6]; + int ret; + + if (nr >= EDMA_MAX_WR_CH + EDMA_MAX_RD_CH) + return -EINVAL; + + ret = platform_get_irq_byname_optional(pdev, "dma"); + if (ret > 0) + return ret; + + snprintf(name, sizeof(name), "dma%u", nr); + + return platform_get_irq_byname_optional(pdev, name); +} + +static struct dw_edma_plat_ops dw_pcie_edma_ops = { + .irq_vector = dw_pcie_edma_irq_vector, +}; + +static void dw_pcie_edma_init_data(struct dw_pcie *pci) +{ + pci->edma.dev = pci->dev; + + if (!pci->edma.ops) + pci->edma.ops = &dw_pcie_edma_ops; + + pci->edma.flags |= DW_EDMA_CHIP_LOCAL; +} + +static int dw_pcie_edma_find_mf(struct dw_pcie *pci) +{ + u32 val; + + /* + * Bail out finding the mapping format if it is already set by the glue + * driver. Also ensure that the edma.reg_base is pointing to a valid + * memory region. + */ + if (pci->edma.mf != EDMA_MF_EDMA_LEGACY) + return pci->edma.reg_base ? 0 : -ENODEV; + + /* + * Indirect eDMA CSRs access has been completely removed since v5.40a + * thus no space is now reserved for the eDMA channels viewport and + * former DMA CTRL register is no longer fixed to FFs. + */ + if (dw_pcie_ver_is_ge(pci, 540A)) + val = 0xFFFFFFFF; + else + val = dw_pcie_readl_dbi(pci, PCIE_DMA_VIEWPORT_BASE + PCIE_DMA_CTRL); + + if (val == 0xFFFFFFFF && pci->edma.reg_base) { + pci->edma.mf = EDMA_MF_EDMA_UNROLL; + } else if (val != 0xFFFFFFFF) { + pci->edma.mf = EDMA_MF_EDMA_LEGACY; + + pci->edma.reg_base = pci->dbi_base + PCIE_DMA_VIEWPORT_BASE; + } else { + return -ENODEV; + } + + return 0; +} + +static int dw_pcie_edma_find_channels(struct dw_pcie *pci) +{ + u32 val; + + /* + * Autodetect the read/write channels count only for non-HDMA platforms. + * HDMA platforms with native CSR mapping doesn't support autodetect, + * so the glue drivers should've passed the valid count already. If not, + * the below sanity check will catch it. + */ + if (pci->edma.mf != EDMA_MF_HDMA_NATIVE) { + val = dw_pcie_readl_dma(pci, PCIE_DMA_CTRL); + + pci->edma.ll_wr_cnt = FIELD_GET(PCIE_DMA_NUM_WR_CHAN, val); + pci->edma.ll_rd_cnt = FIELD_GET(PCIE_DMA_NUM_RD_CHAN, val); + } + + /* Sanity check the channels count if the mapping was incorrect */ + if (!pci->edma.ll_wr_cnt || pci->edma.ll_wr_cnt > EDMA_MAX_WR_CH || + !pci->edma.ll_rd_cnt || pci->edma.ll_rd_cnt > EDMA_MAX_RD_CH) + return -EINVAL; + + return 0; +} + +static int dw_pcie_edma_find_chip(struct dw_pcie *pci) +{ + int ret; + + dw_pcie_edma_init_data(pci); + + ret = dw_pcie_edma_find_mf(pci); + if (ret) + return ret; + + return dw_pcie_edma_find_channels(pci); +} + +static int dw_pcie_edma_irq_verify(struct dw_pcie *pci) +{ + struct platform_device *pdev = to_platform_device(pci->dev); + u16 ch_cnt = pci->edma.ll_wr_cnt + pci->edma.ll_rd_cnt; + char name[15]; + int ret; + + if (pci->edma.nr_irqs > 1) + return pci->edma.nr_irqs != ch_cnt ? -EINVAL : 0; + + ret = platform_get_irq_byname_optional(pdev, "dma"); + if (ret > 0) { + pci->edma.nr_irqs = 1; + return 0; + } + + for (; pci->edma.nr_irqs < ch_cnt; pci->edma.nr_irqs++) { + snprintf(name, sizeof(name), "dma%d", pci->edma.nr_irqs); + + ret = platform_get_irq_byname_optional(pdev, name); + if (ret <= 0) + return -EINVAL; + } + + return 0; +} + +static int dw_pcie_edma_ll_alloc(struct dw_pcie *pci) +{ + struct dw_edma_region *ll; + dma_addr_t paddr; + int i; + + for (i = 0; i < pci->edma.ll_wr_cnt; i++) { + ll = &pci->edma.ll_region_wr[i]; + ll->sz = DMA_LLP_MEM_SIZE; + ll->vaddr.mem = dmam_alloc_coherent(pci->dev, ll->sz, + &paddr, GFP_KERNEL); + if (!ll->vaddr.mem) + return -ENOMEM; + + ll->paddr = paddr; + } + + for (i = 0; i < pci->edma.ll_rd_cnt; i++) { + ll = &pci->edma.ll_region_rd[i]; + ll->sz = DMA_LLP_MEM_SIZE; + ll->vaddr.mem = dmam_alloc_coherent(pci->dev, ll->sz, + &paddr, GFP_KERNEL); + if (!ll->vaddr.mem) + return -ENOMEM; + + ll->paddr = paddr; + } + + return 0; +} + +int dw_pcie_edma_detect(struct dw_pcie *pci) +{ + int ret; + + /* Don't fail if no eDMA was found (for the backward compatibility) */ + ret = dw_pcie_edma_find_chip(pci); + if (ret) + return 0; + + /* Don't fail on the IRQs verification (for the backward compatibility) */ + ret = dw_pcie_edma_irq_verify(pci); + if (ret) { + dev_err(pci->dev, "Invalid eDMA IRQs found\n"); + return 0; + } + + ret = dw_pcie_edma_ll_alloc(pci); + if (ret) { + dev_err(pci->dev, "Couldn't allocate LLP memory\n"); + return ret; + } + + /* Don't fail if the DW eDMA driver can't find the device */ + ret = dw_edma_probe(&pci->edma); + if (ret && ret != -ENODEV) { + dev_err(pci->dev, "Couldn't register eDMA device\n"); + return ret; + } + + dev_info(pci->dev, "eDMA: unroll %s, %hu wr, %hu rd\n", + pci->edma.mf == EDMA_MF_EDMA_UNROLL ? "T" : "F", + pci->edma.ll_wr_cnt, pci->edma.ll_rd_cnt); + + return 0; +} + +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; + + dw_pcie_link_set_max_speed(pci); + + /* Configure Gen1 N_FTS */ + if (pci->n_fts[0]) { + val = dw_pcie_readl_dbi(pci, PCIE_PORT_AFR); + val &= ~(PORT_AFR_N_FTS_MASK | PORT_AFR_CC_N_FTS_MASK); + val |= PORT_AFR_N_FTS(pci->n_fts[0]); + val |= PORT_AFR_CC_N_FTS(pci->n_fts[0]); + dw_pcie_writel_dbi(pci, PCIE_PORT_AFR, val); + } + + /* Configure Gen2+ N_FTS */ + if (pci->n_fts[1]) { + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val &= ~PORT_LOGIC_N_FTS_MASK; + val |= pci->n_fts[1]; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + } + + if (dw_pcie_cap_is(pci, CDM_CHECK)) { + val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS); + val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS | + PCIE_PL_CHK_REG_CHK_REG_START; + dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val); + } + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_LINK_CONTROL); + val &= ~PORT_LINK_FAST_LINK_MODE; + val |= PORT_LINK_DLL_LINK_EN; + dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val); + + dw_pcie_link_set_max_link_width(pci, pci->num_lanes); +} + +resource_size_t dw_pcie_parent_bus_offset(struct dw_pcie *pci, + const char *reg_name, + resource_size_t cpu_phys_addr) +{ + struct device *dev = pci->dev; + struct device_node *np = dev->of_node; + int index; + u64 reg_addr, fixup_addr; + u64 (*fixup)(struct dw_pcie *pcie, u64 cpu_addr); + + /* Look up reg_name address on parent bus */ + index = of_property_match_string(np, "reg-names", reg_name); + + if (index < 0) { + dev_err(dev, "No %s in devicetree \"reg\" property\n", reg_name); + return 0; + } + + of_property_read_reg(np, index, ®_addr, NULL); + + fixup = pci->ops ? pci->ops->cpu_addr_fixup : NULL; + if (fixup) { + fixup_addr = fixup(pci, cpu_phys_addr); + if (reg_addr == fixup_addr) { + dev_info(dev, "%s reg[%d] %#010llx == %#010llx == fixup(cpu %#010llx); %ps is redundant with this devicetree\n", + reg_name, index, reg_addr, fixup_addr, + (unsigned long long) cpu_phys_addr, fixup); + } else { + dev_warn(dev, "%s reg[%d] %#010llx != %#010llx == fixup(cpu %#010llx); devicetree is broken\n", + reg_name, index, reg_addr, fixup_addr, + (unsigned long long) cpu_phys_addr); + reg_addr = fixup_addr; + } + + return cpu_phys_addr - reg_addr; + } + + if (pci->use_parent_dt_ranges) { + + /* + * This platform once had a fixup, presumably because it + * translates between CPU and PCI controller addresses. + * Log a note if devicetree didn't describe a translation. + */ + if (reg_addr == cpu_phys_addr) + dev_info(dev, "%s reg[%d] %#010llx == cpu %#010llx\n; no fixup was ever needed for this devicetree\n", + reg_name, index, reg_addr, + (unsigned long long) cpu_phys_addr); + } else { + if (reg_addr != cpu_phys_addr) { + dev_warn(dev, "%s reg[%d] %#010llx != cpu %#010llx; no fixup and devicetree \"ranges\" is broken, assuming no translation\n", + reg_name, index, reg_addr, + (unsigned long long) cpu_phys_addr); + return 0; + } + } + + return cpu_phys_addr - reg_addr; } diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 9943d8c68335..31685951a080 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -3,7 +3,7 @@ * Synopsys DesignWare PCIe host controller driver * * Copyright (C) 2013 Samsung Electronics Co., Ltd. - * http://www.samsung.com + * https://www.samsung.com * * Author: Jingoo Han <jg1.han@samsung.com> */ @@ -11,42 +11,107 @@ #ifndef _PCIE_DESIGNWARE_H #define _PCIE_DESIGNWARE_H +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/clk.h> #include <linux/dma-mapping.h> +#include <linux/dma/edma.h> +#include <linux/gpio/consumer.h> #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> -/* 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 +#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 +#define DW_PCIE_VER_470A 0x3437302a +#define DW_PCIE_VER_480A 0x3438302a +#define DW_PCIE_VER_490A 0x3439302a +#define DW_PCIE_VER_520A 0x3532302a +#define DW_PCIE_VER_540A 0x3534302a + +#define __dw_pcie_ver_cmp(_pci, _ver, _op) \ + ((_pci)->version _op DW_PCIE_VER_ ## _ver) + +#define dw_pcie_ver_is(_pci, _ver) __dw_pcie_ver_cmp(_pci, _ver, ==) + +#define dw_pcie_ver_is_ge(_pci, _ver) __dw_pcie_ver_cmp(_pci, _ver, >=) + +#define dw_pcie_ver_type_is(_pci, _ver, _type) \ + (__dw_pcie_ver_cmp(_pci, _ver, ==) && \ + __dw_pcie_ver_cmp(_pci, TYPE_ ## _type, ==)) + +#define dw_pcie_ver_type_is_ge(_pci, _ver, _type) \ + (__dw_pcie_ver_cmp(_pci, _ver, ==) && \ + __dw_pcie_ver_cmp(_pci, TYPE_ ## _type, >=)) + +/* DWC PCIe controller capabilities */ +#define DW_PCIE_CAP_REQ_RES 0 +#define DW_PCIE_CAP_IATU_UNROLL 1 +#define DW_PCIE_CAP_CDM_CHECK 2 + +#define dw_pcie_cap_is(_pci, _cap) \ + test_bit(DW_PCIE_CAP_ ## _cap, &(_pci)->caps) + +#define dw_pcie_cap_set(_pci, _cap) \ + set_bit(DW_PCIE_CAP_ ## _cap, &(_pci)->caps) /* Parameters for the waiting for iATU enabled routine */ #define LINK_WAIT_MAX_IATU_RETRIES 5 #define LINK_WAIT_IATU 9 /* Synopsys-specific PCIe configuration registers */ +#define PCIE_PORT_FORCE 0x708 +#define PORT_FORCE_DO_DESKEW_FOR_SRIS BIT(23) + +#define PCIE_PORT_AFR 0x70C +#define PORT_AFR_N_FTS_MASK GENMASK(15, 8) +#define PORT_AFR_N_FTS(n) FIELD_PREP(PORT_AFR_N_FTS_MASK, n) +#define PORT_AFR_CC_N_FTS_MASK GENMASK(23, 16) +#define PORT_AFR_CC_N_FTS(n) FIELD_PREP(PORT_AFR_CC_N_FTS_MASK, n) +#define PORT_AFR_ENTER_ASPM BIT(30) +#define PORT_AFR_L0S_ENTRANCE_LAT_SHIFT 24 +#define PORT_AFR_L0S_ENTRANCE_LAT_MASK GENMASK(26, 24) +#define PORT_AFR_L1_ENTRANCE_LAT_SHIFT 27 +#define PORT_AFR_L1_ENTRANCE_LAT_MASK GENMASK(29, 27) + #define PCIE_PORT_LINK_CONTROL 0x710 -#define PORT_LINK_MODE_MASK (0x3f << 16) -#define PORT_LINK_MODE_1_LANES (0x1 << 16) -#define PORT_LINK_MODE_2_LANES (0x3 << 16) -#define PORT_LINK_MODE_4_LANES (0x7 << 16) -#define PORT_LINK_MODE_8_LANES (0xf << 16) +#define PORT_LINK_DLL_LINK_EN BIT(5) +#define PORT_LINK_FAST_LINK_MODE BIT(7) +#define PORT_LINK_MODE_MASK GENMASK(21, 16) +#define PORT_LINK_MODE(n) FIELD_PREP(PORT_LINK_MODE_MASK, n) +#define PORT_LINK_MODE_1_LANES PORT_LINK_MODE(0x1) +#define PORT_LINK_MODE_2_LANES PORT_LINK_MODE(0x3) +#define PORT_LINK_MODE_4_LANES PORT_LINK_MODE(0x7) +#define PORT_LINK_MODE_8_LANES PORT_LINK_MODE(0xf) +#define 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) +#define PCIE_PORT_DEBUG1_LINK_IN_TRAINING BIT(29) #define PCIE_LINK_WIDTH_SPEED_CONTROL 0x80C -#define PORT_LOGIC_SPEED_CHANGE (0x1 << 17) -#define PORT_LOGIC_LINK_WIDTH_MASK (0x1f << 8) -#define PORT_LOGIC_LINK_WIDTH_1_LANES (0x1 << 8) -#define PORT_LOGIC_LINK_WIDTH_2_LANES (0x2 << 8) -#define PORT_LOGIC_LINK_WIDTH_4_LANES (0x4 << 8) -#define PORT_LOGIC_LINK_WIDTH_8_LANES (0x8 << 8) +#define PORT_LOGIC_N_FTS_MASK GENMASK(7, 0) +#define PORT_LOGIC_SPEED_CHANGE BIT(17) +#define PORT_LOGIC_LINK_WIDTH_MASK GENMASK(12, 8) +#define PORT_LOGIC_LINK_WIDTH(n) FIELD_PREP(PORT_LOGIC_LINK_WIDTH_MASK, n) +#define PORT_LOGIC_LINK_WIDTH_1_LANES PORT_LOGIC_LINK_WIDTH(0x1) +#define PORT_LOGIC_LINK_WIDTH_2_LANES PORT_LOGIC_LINK_WIDTH(0x2) +#define PORT_LOGIC_LINK_WIDTH_4_LANES PORT_LOGIC_LINK_WIDTH(0x4) +#define PORT_LOGIC_LINK_WIDTH_8_LANES PORT_LOGIC_LINK_WIDTH(0x8) #define PCIE_MSI_ADDR_LO 0x820 #define PCIE_MSI_ADDR_HI 0x824 @@ -54,33 +119,124 @@ #define PCIE_MSI_INTR0_MASK 0x82C #define PCIE_MSI_INTR0_STATUS 0x830 +#define GEN3_RELATED_OFF 0x890 +#define GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL BIT(0) +#define GEN3_RELATED_OFF_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_EQ_CONTROL_OFF 0x8A8 +#define GEN3_EQ_CONTROL_OFF_FB_MODE GENMASK(3, 0) +#define GEN3_EQ_CONTROL_OFF_PHASE23_EXIT_MODE BIT(4) +#define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC GENMASK(23, 8) +#define GEN3_EQ_CONTROL_OFF_FOM_INC_INITIAL_EVAL BIT(24) + +#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_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) + +#define PCIE_VERSION_NUMBER 0x8F8 +#define PCIE_VERSION_TYPE 0x8FC + +/* + * iATU inbound and outbound windows CSRs. Before the IP-core v4.80a each + * iATU region CSRs had been indirectly accessible by means of the dedicated + * viewport selector. The iATU/eDMA CSRs space was re-designed in DWC PCIe + * v4.80a in a way so the viewport was unrolled into the directly accessible + * iATU/eDMA CSRs space. + */ #define PCIE_ATU_VIEWPORT 0x900 -#define PCIE_ATU_REGION_INBOUND (0x1 << 31) -#define PCIE_ATU_REGION_OUTBOUND (0x0 << 31) -#define PCIE_ATU_REGION_INDEX2 (0x2 << 0) -#define PCIE_ATU_REGION_INDEX1 (0x1 << 0) -#define PCIE_ATU_REGION_INDEX0 (0x0 << 0) -#define PCIE_ATU_CR1 0x904 -#define PCIE_ATU_TYPE_MEM (0x0 << 0) -#define PCIE_ATU_TYPE_IO (0x2 << 0) -#define PCIE_ATU_TYPE_CFG0 (0x4 << 0) -#define PCIE_ATU_TYPE_CFG1 (0x5 << 0) -#define PCIE_ATU_CR2 0x908 -#define PCIE_ATU_ENABLE (0x1 << 31) -#define PCIE_ATU_BAR_MODE_ENABLE (0x1 << 30) -#define PCIE_ATU_LOWER_BASE 0x90C -#define PCIE_ATU_UPPER_BASE 0x910 -#define PCIE_ATU_LIMIT 0x914 -#define PCIE_ATU_LOWER_TARGET 0x918 -#define PCIE_ATU_BUS(x) (((x) & 0xff) << 24) -#define PCIE_ATU_DEV(x) (((x) & 0x1f) << 19) -#define PCIE_ATU_FUNC(x) (((x) & 0x7) << 16) -#define PCIE_ATU_UPPER_TARGET 0x91C +#define PCIE_ATU_REGION_DIR_IB BIT(31) +#define PCIE_ATU_REGION_DIR_OB 0 +#define PCIE_ATU_VIEWPORT_BASE 0x904 +#define PCIE_ATU_UNROLL_BASE(dir, index) \ + (((index) << 9) | ((dir == PCIE_ATU_REGION_DIR_IB) ? BIT(8) : 0)) +#define PCIE_ATU_VIEWPORT_SIZE 0x2C +#define PCIE_ATU_REGION_CTRL1 0x000 +#define PCIE_ATU_INCREASE_REGION_SIZE BIT(13) +#define PCIE_ATU_TYPE_MEM 0x0 +#define PCIE_ATU_TYPE_IO 0x2 +#define PCIE_ATU_TYPE_CFG0 0x4 +#define PCIE_ATU_TYPE_CFG1 0x5 +#define PCIE_ATU_TYPE_MSG 0x10 +#define PCIE_ATU_TD BIT(8) +#define PCIE_ATU_FUNC_NUM(pf) ((pf) << 20) +#define PCIE_ATU_REGION_CTRL2 0x004 +#define PCIE_ATU_ENABLE BIT(31) +#define PCIE_ATU_BAR_MODE_ENABLE BIT(30) +#define PCIE_ATU_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 +#define PCIE_ATU_UPPER_BASE 0x00C +#define PCIE_ATU_LIMIT 0x010 +#define PCIE_ATU_LOWER_TARGET 0x014 +#define PCIE_ATU_BUS(x) FIELD_PREP(GENMASK(31, 24), x) +#define PCIE_ATU_DEV(x) FIELD_PREP(GENMASK(23, 19), x) +#define PCIE_ATU_FUNC(x) FIELD_PREP(GENMASK(18, 16), x) +#define PCIE_ATU_UPPER_TARGET 0x018 +#define PCIE_ATU_UPPER_LIMIT 0x020 #define PCIE_MISC_CONTROL_1_OFF 0x8BC -#define PCIE_DBI_RO_WR_EN (0x1 << 0) +#define PCIE_DBI_RO_WR_EN BIT(0) + +#define PCIE_MSIX_DOORBELL 0x948 +#define PCIE_MSIX_DOORBELL_PF_SHIFT 24 /* + * eDMA CSRs. DW PCIe IP-core v4.70a and older had the eDMA registers accessible + * over the Port Logic registers space. Afterwards the unrolled mapping was + * introduced so eDMA and iATU could be accessed via a dedicated registers + * space. + */ +#define PCIE_DMA_VIEWPORT_BASE 0x970 +#define PCIE_DMA_UNROLL_BASE 0x80000 +#define PCIE_DMA_CTRL 0x008 +#define PCIE_DMA_NUM_WR_CHAN GENMASK(3, 0) +#define PCIE_DMA_NUM_RD_CHAN GENMASK(19, 16) + +#define PCIE_PL_CHK_REG_CONTROL_STATUS 0xB20 +#define PCIE_PL_CHK_REG_CHK_REG_START BIT(0) +#define PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS BIT(1) +#define PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR BIT(16) +#define PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR BIT(17) +#define PCIE_PL_CHK_REG_CHK_REG_COMPLETE BIT(18) + +#define PCIE_PL_CHK_REG_ERR_ADDR 0xB28 + +/* + * 16.0 GT/s (Gen 4) lane margining register definitions + */ +#define GEN4_LANE_MARGINING_1_OFF 0xB80 +#define MARGINING_MAX_VOLTAGE_OFFSET GENMASK(29, 24) +#define MARGINING_NUM_VOLTAGE_STEPS GENMASK(22, 16) +#define MARGINING_MAX_TIMING_OFFSET GENMASK(13, 8) +#define MARGINING_NUM_TIMING_STEPS GENMASK(5, 0) + +#define GEN4_LANE_MARGINING_2_OFF 0xB84 +#define MARGINING_IND_ERROR_SAMPLER BIT(28) +#define MARGINING_SAMPLE_REPORTING_METHOD BIT(27) +#define MARGINING_IND_LEFT_RIGHT_TIMING BIT(26) +#define MARGINING_IND_UP_DOWN_VOLTAGE BIT(25) +#define MARGINING_VOLTAGE_SUPPORTED BIT(24) +#define MARGINING_MAXLANES GENMASK(20, 16) +#define MARGINING_SAMPLE_RATE_TIMING GENMASK(13, 8) +#define MARGINING_SAMPLE_RATE_VOLTAGE GENMASK(5, 0) +/* * iATU Unroll-specific register definitions * From 4.80 core version the address translation will be made by unroll */ @@ -88,9 +244,44 @@ #define PCIE_ATU_UNR_REGION_CTRL2 0x04 #define PCIE_ATU_UNR_LOWER_BASE 0x08 #define PCIE_ATU_UNR_UPPER_BASE 0x0C -#define PCIE_ATU_UNR_LIMIT 0x10 +#define PCIE_ATU_UNR_LOWER_LIMIT 0x10 #define PCIE_ATU_UNR_LOWER_TARGET 0x14 #define PCIE_ATU_UNR_UPPER_TARGET 0x18 +#define PCIE_ATU_UNR_UPPER_LIMIT 0x20 + +/* + * RAS-DES register definitions + */ +#define PCIE_RAS_DES_EVENT_COUNTER_CONTROL 0x8 +#define EVENT_COUNTER_ALL_CLEAR 0x3 +#define EVENT_COUNTER_ENABLE_ALL 0x7 +#define EVENT_COUNTER_ENABLE_SHIFT 2 +#define EVENT_COUNTER_EVENT_SEL_MASK GENMASK(7, 0) +#define EVENT_COUNTER_EVENT_SEL_SHIFT 16 +#define EVENT_COUNTER_EVENT_Tx_L0S 0x2 +#define EVENT_COUNTER_EVENT_Rx_L0S 0x3 +#define EVENT_COUNTER_EVENT_L1 0x5 +#define EVENT_COUNTER_EVENT_L1_1 0x7 +#define EVENT_COUNTER_EVENT_L1_2 0x8 +#define EVENT_COUNTER_GROUP_SEL_SHIFT 24 +#define EVENT_COUNTER_GROUP_5 0x5 + +#define PCIE_RAS_DES_EVENT_COUNTER_DATA 0xc + +/* 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 @@ -99,13 +290,7 @@ * this offset, if atu_base not set. */ #define DEFAULT_DBI_ATU_OFFSET (0x3 << 20) - -/* Register address builder */ -#define PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(region) \ - ((region) << 9) - -#define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region) \ - (((region) << 9) | (0x1 << 8)) +#define DEFAULT_DBI_DMA_OFFSET PCIE_DMA_UNROLL_BASE #define MAX_MSI_IRQS 256 #define MAX_MSI_IRQS_PER_CTRL 32 @@ -117,16 +302,13 @@ #define MAX_IATU_IN 256 #define MAX_IATU_OUT 256 -struct pcie_port; +/* Default eDMA LLP memory size */ +#define DMA_LLP_MEM_SIZE PAGE_SIZE + struct dw_pcie; +struct dw_pcie_rp; struct dw_pcie_ep; -enum dw_pcie_region_type { - DW_PCIE_REGION_UNKNOWN, - DW_PCIE_REGION_INBOUND, - DW_PCIE_REGION_OUTBOUND, -}; - enum dw_pcie_device_mode { DW_PCIE_UNKNOWN_TYPE, DW_PCIE_EP_TYPE, @@ -134,82 +316,169 @@ enum dw_pcie_device_mode { DW_PCIE_RC_TYPE, }; +enum dw_pcie_app_clk { + DW_PCIE_DBI_CLK, + DW_PCIE_MSTR_CLK, + DW_PCIE_SLV_CLK, + DW_PCIE_NUM_APP_CLKS +}; + +enum dw_pcie_core_clk { + DW_PCIE_PIPE_CLK, + DW_PCIE_CORE_CLK, + DW_PCIE_AUX_CLK, + DW_PCIE_REF_CLK, + DW_PCIE_NUM_CORE_CLKS +}; + +enum dw_pcie_app_rst { + DW_PCIE_DBI_RST, + DW_PCIE_MSTR_RST, + DW_PCIE_SLV_RST, + DW_PCIE_NUM_APP_RSTS +}; + +enum dw_pcie_core_rst { + DW_PCIE_NON_STICKY_RST, + DW_PCIE_STICKY_RST, + DW_PCIE_CORE_RST, + DW_PCIE_PIPE_RST, + DW_PCIE_PHY_RST, + DW_PCIE_HOT_RST, + DW_PCIE_PWR_RST, + DW_PCIE_NUM_CORE_RSTS +}; + +enum dw_pcie_ltssm { + /* Need to align with PCIE_PORT_DEBUG0 bits 0:5 */ + DW_PCIE_LTSSM_DETECT_QUIET = 0x0, + DW_PCIE_LTSSM_DETECT_ACT = 0x1, + DW_PCIE_LTSSM_POLL_ACTIVE = 0x2, + DW_PCIE_LTSSM_POLL_COMPLIANCE = 0x3, + DW_PCIE_LTSSM_POLL_CONFIG = 0x4, + DW_PCIE_LTSSM_PRE_DETECT_QUIET = 0x5, + DW_PCIE_LTSSM_DETECT_WAIT = 0x6, + DW_PCIE_LTSSM_CFG_LINKWD_START = 0x7, + DW_PCIE_LTSSM_CFG_LINKWD_ACEPT = 0x8, + DW_PCIE_LTSSM_CFG_LANENUM_WAI = 0x9, + DW_PCIE_LTSSM_CFG_LANENUM_ACEPT = 0xa, + DW_PCIE_LTSSM_CFG_COMPLETE = 0xb, + DW_PCIE_LTSSM_CFG_IDLE = 0xc, + DW_PCIE_LTSSM_RCVRY_LOCK = 0xd, + DW_PCIE_LTSSM_RCVRY_SPEED = 0xe, + DW_PCIE_LTSSM_RCVRY_RCVRCFG = 0xf, + DW_PCIE_LTSSM_RCVRY_IDLE = 0x10, + DW_PCIE_LTSSM_L0 = 0x11, + DW_PCIE_LTSSM_L0S = 0x12, + DW_PCIE_LTSSM_L123_SEND_EIDLE = 0x13, + DW_PCIE_LTSSM_L1_IDLE = 0x14, + DW_PCIE_LTSSM_L2_IDLE = 0x15, + DW_PCIE_LTSSM_L2_WAKE = 0x16, + DW_PCIE_LTSSM_DISABLED_ENTRY = 0x17, + DW_PCIE_LTSSM_DISABLED_IDLE = 0x18, + DW_PCIE_LTSSM_DISABLED = 0x19, + DW_PCIE_LTSSM_LPBK_ENTRY = 0x1a, + DW_PCIE_LTSSM_LPBK_ACTIVE = 0x1b, + DW_PCIE_LTSSM_LPBK_EXIT = 0x1c, + DW_PCIE_LTSSM_LPBK_EXIT_TIMEOUT = 0x1d, + DW_PCIE_LTSSM_HOT_RESET_ENTRY = 0x1e, + DW_PCIE_LTSSM_HOT_RESET = 0x1f, + DW_PCIE_LTSSM_RCVRY_EQ0 = 0x20, + DW_PCIE_LTSSM_RCVRY_EQ1 = 0x21, + DW_PCIE_LTSSM_RCVRY_EQ2 = 0x22, + DW_PCIE_LTSSM_RCVRY_EQ3 = 0x23, + + DW_PCIE_LTSSM_UNKNOWN = 0xFFFFFFFF, +}; + +struct dw_pcie_ob_atu_cfg { + int index; + int type; + u8 func_no; + u8 code; + u8 routing; + u32 ctrl2; + u64 parent_bus_addr; + u64 pci_addr; + u64 size; +}; + struct dw_pcie_host_ops { - int (*rd_own_conf)(struct pcie_port *pp, int where, int size, u32 *val); - int (*wr_own_conf)(struct pcie_port *pp, int where, int size, u32 val); - int (*rd_other_conf)(struct pcie_port *pp, struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 *val); - int (*wr_other_conf)(struct pcie_port *pp, struct pci_bus *bus, - unsigned int devfn, int where, int size, u32 val); - int (*host_init)(struct pcie_port *pp); - void (*msi_set_irq)(struct pcie_port *pp, int irq); - void (*msi_clear_irq)(struct pcie_port *pp, int irq); - phys_addr_t (*get_msi_addr)(struct pcie_port *pp); - u32 (*get_msi_data)(struct pcie_port *pp, int pos); - void (*scan_bus)(struct pcie_port *pp); - void (*set_num_vectors)(struct pcie_port *pp); - int (*msi_host_init)(struct pcie_port *pp); - void (*msi_irq_ack)(int irq, struct pcie_port *pp); + int (*init)(struct dw_pcie_rp *pp); + void (*deinit)(struct dw_pcie_rp *pp); + void (*post_init)(struct dw_pcie_rp *pp); + int (*msi_init)(struct dw_pcie_rp *pp); + void (*pme_turn_off)(struct dw_pcie_rp *pp); }; -struct pcie_port { - u8 root_bus_nr; +struct dw_pcie_rp { + bool has_msi_ctrl:1; + bool cfg0_io_shared:1; u64 cfg0_base; void __iomem *va_cfg0_base; u32 cfg0_size; - u64 cfg1_base; - void __iomem *va_cfg1_base; - u32 cfg1_size; resource_size_t io_base; phys_addr_t io_bus_addr; u32 io_size; - u64 mem_base; - phys_addr_t mem_bus_addr; - u32 mem_size; - struct resource *cfg; - struct resource *io; - struct resource *mem; - struct resource *busn; int irq; const struct dw_pcie_host_ops *ops; - int msi_irq; + int msi_irq[MAX_MSI_CTRLS]; struct irq_domain *irq_domain; - struct irq_domain *msi_domain; dma_addr_t msi_data; + struct irq_chip *msi_irq_chip; u32 num_vectors; - u32 irq_status[MAX_MSI_CTRLS]; + u32 irq_mask[MAX_MSI_CTRLS]; + struct pci_host_bridge *bridge; raw_spinlock_t lock; DECLARE_BITMAP(msi_irq_in_use, MAX_MSI_IRQS); -}; - -enum dw_pcie_as_type { - DW_PCIE_AS_UNKNOWN, - DW_PCIE_AS_MEM, - DW_PCIE_AS_IO, + bool use_atu_msg; + int msg_atu_index; + struct resource *msg_res; + bool use_linkup_irq; + struct pci_eq_presets presets; + struct pci_config_window *cfg; + bool ecam_enabled; + bool native_ecam; }; struct dw_pcie_ep_ops { - void (*ep_init)(struct dw_pcie_ep *ep); + void (*pre_init)(struct dw_pcie_ep *ep); + void (*init)(struct dw_pcie_ep *ep); int (*raise_irq)(struct dw_pcie_ep *ep, u8 func_no, - enum pci_epc_irq_type type, u16 interrupt_num); + unsigned int type, u16 interrupt_num); + const struct pci_epc_features* (*get_features)(struct dw_pcie_ep *ep); + /* + * Provide a method to implement the different func config space + * access for different platform, if different func have different + * offset, return the offset of func. if use write a register way + * return a 0, and implement code in callback function of platform + * driver. + */ + unsigned int (*get_dbi_offset)(struct dw_pcie_ep *ep, u8 func_no); + unsigned int (*get_dbi2_offset)(struct dw_pcie_ep *ep, u8 func_no); +}; + +struct dw_pcie_ep_func { + struct list_head list; + u8 func_no; + u8 msi_cap; /* MSI capability offset */ + u8 msix_cap; /* MSI-X capability offset */ }; struct dw_pcie_ep { struct pci_epc *epc; - struct dw_pcie_ep_ops *ops; + struct list_head func_list; + const struct dw_pcie_ep_ops *ops; phys_addr_t phys_base; size_t addr_size; size_t page_size; - u8 bar_to_atu[6]; + u8 bar_to_atu[PCI_STD_NUM_BARS]; phys_addr_t *outbound_addr; unsigned long *ib_window_map; unsigned long *ob_window_map; - u32 num_ib_windows; - u32 num_ob_windows; void __iomem *msi_mem; phys_addr_t msi_mem_phys; - u8 msi_cap; /* MSI capability offset */ - u8 msix_cap; /* MSI-X capability offset */ + struct pci_epf_bar *epf_bar[PCI_STD_NUM_BARS]; }; struct dw_pcie_ops { @@ -218,22 +487,68 @@ struct dw_pcie_ops { size_t size); void (*write_dbi)(struct dw_pcie *pcie, void __iomem *base, u32 reg, size_t size, u32 val); - int (*link_up)(struct dw_pcie *pcie); + void (*write_dbi2)(struct dw_pcie *pcie, void __iomem *base, u32 reg, + size_t size, u32 val); + bool (*link_up)(struct dw_pcie *pcie); + enum dw_pcie_ltssm (*get_ltssm)(struct dw_pcie *pcie); int (*start_link)(struct dw_pcie *pcie); void (*stop_link)(struct dw_pcie *pcie); + int (*assert_perst)(struct dw_pcie *pcie, bool assert); +}; + +struct debugfs_info { + struct dentry *debug_dir; + void *rasdes_info; }; struct dw_pcie { struct device *dev; void __iomem *dbi_base; + resource_size_t dbi_phys_addr; void __iomem *dbi_base2; - /* Used when iatu_unroll_enabled is true */ void __iomem *atu_base; - u32 num_viewport; - u8 iatu_unroll_enabled; - struct pcie_port pp; + void __iomem *elbi_base; + resource_size_t atu_phys_addr; + size_t atu_size; + resource_size_t parent_bus_offset; + u32 num_ib_windows; + u32 num_ob_windows; + u32 region_align; + u64 region_limit; + struct dw_pcie_rp pp; struct dw_pcie_ep ep; const struct dw_pcie_ops *ops; + u32 version; + u32 type; + unsigned long caps; + int num_lanes; + int max_link_speed; + u8 n_fts[2]; + struct dw_edma_chip edma; + bool l1ss_support; /* L1 PM Substates support */ + struct clk_bulk_data app_clks[DW_PCIE_NUM_APP_CLKS]; + struct clk_bulk_data core_clks[DW_PCIE_NUM_CORE_CLKS]; + struct reset_control_bulk_data app_rsts[DW_PCIE_NUM_APP_RSTS]; + struct reset_control_bulk_data core_rsts[DW_PCIE_NUM_CORE_RSTS]; + struct gpio_desc *pe_rst; + bool suspended; + struct debugfs_info *debugfs; + enum dw_pcie_device_mode mode; + u16 ptm_vsec_offset; + struct pci_ptm_debugfs *ptm_debugfs; + + /* + * If iATU input addresses are offset from CPU physical addresses, + * we previously required .cpu_addr_fixup() to convert them. We + * now rely on the devicetree instead. If .cpu_addr_fixup() + * exists, we compare its results with devicetree. + * + * If .cpu_addr_fixup() does not exist, we assume the offset is + * zero and warn if devicetree claims otherwise. If we know all + * devicetrees correctly describe the offset, set + * use_parent_dt_ranges to true to avoid this warning. + */ + bool use_parent_dt_ranges; }; #define to_dw_pcie_from_pp(port) container_of((port), struct dw_pcie, pp) @@ -241,72 +556,210 @@ struct dw_pcie { #define to_dw_pcie_from_ep(endpoint) \ container_of((endpoint), struct dw_pcie, ep) +int dw_pcie_get_resources(struct dw_pcie *pci); + +void dw_pcie_version_detect(struct dw_pcie *pci); + +u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap); +u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap); +u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci); +u16 dw_pcie_find_ptm_capability(struct dw_pcie *pci); + int dw_pcie_read(void __iomem *addr, int size, u32 *val); int dw_pcie_write(void __iomem *addr, int size, u32 val); -u32 __dw_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg, - size_t size); -void __dw_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg, - size_t size, u32 val); -int dw_pcie_link_up(struct dw_pcie *pci); +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); +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); -void dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, - int type, u64 cpu_addr, u64 pci_addr, - u32 size); -int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int bar, - u64 cpu_addr, enum dw_pcie_as_type as_type); -void dw_pcie_disable_atu(struct dw_pcie *pci, int index, - enum dw_pcie_region_type type); +int dw_pcie_link_get_max_link_width(struct dw_pcie *pci); +int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, + const struct dw_pcie_ob_atu_cfg *atu); +int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, + u64 parent_bus_addr, u64 pci_addr, u64 size); +int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, + int type, u64 parent_bus_addr, + u8 bar, size_t size); +void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index); +void dw_pcie_hide_unsupported_l1ss(struct dw_pcie *pci); void dw_pcie_setup(struct dw_pcie *pci); +void dw_pcie_iatu_detect(struct dw_pcie *pci); +int dw_pcie_edma_detect(struct dw_pcie *pci); +void dw_pcie_edma_remove(struct dw_pcie *pci); +resource_size_t dw_pcie_parent_bus_offset(struct dw_pcie *pci, + const char *reg_name, + resource_size_t cpu_phy_addr); static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val) { - __dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x4, val); + dw_pcie_write_dbi(pci, reg, 0x4, val); } static inline u32 dw_pcie_readl_dbi(struct dw_pcie *pci, u32 reg) { - return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x4); + return dw_pcie_read_dbi(pci, reg, 0x4); } static inline void dw_pcie_writew_dbi(struct dw_pcie *pci, u32 reg, u16 val) { - __dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x2, val); + dw_pcie_write_dbi(pci, reg, 0x2, val); } static inline u16 dw_pcie_readw_dbi(struct dw_pcie *pci, u32 reg) { - return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x2); + return dw_pcie_read_dbi(pci, reg, 0x2); } static inline void dw_pcie_writeb_dbi(struct dw_pcie *pci, u32 reg, u8 val) { - __dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x1, val); + dw_pcie_write_dbi(pci, reg, 0x1, val); } static inline u8 dw_pcie_readb_dbi(struct dw_pcie *pci, u32 reg) { - return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x1); + return dw_pcie_read_dbi(pci, reg, 0x1); } static inline void dw_pcie_writel_dbi2(struct dw_pcie *pci, u32 reg, u32 val) { - __dw_pcie_write_dbi(pci, pci->dbi_base2, reg, 0x4, 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) +{ + unsigned int dbi_offset = 0; + + if (ep->ops->get_dbi_offset) + dbi_offset = ep->ops->get_dbi_offset(ep, func_no); + + return dbi_offset; +} + +static inline u32 dw_pcie_ep_read_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg, size_t size) +{ + unsigned int offset = dw_pcie_ep_get_dbi_offset(ep, func_no); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + return dw_pcie_read_dbi(pci, offset + reg, size); +} + +static inline void dw_pcie_ep_write_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg, size_t size, u32 val) +{ + unsigned int offset = dw_pcie_ep_get_dbi_offset(ep, func_no); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + dw_pcie_write_dbi(pci, offset + reg, size, val); +} + +static inline void dw_pcie_ep_writel_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg, u32 val) +{ + dw_pcie_ep_write_dbi(ep, func_no, reg, 0x4, val); +} + +static inline u32 dw_pcie_ep_readl_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg) +{ + return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x4); +} + +static inline void dw_pcie_ep_writew_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg, u16 val) +{ + dw_pcie_ep_write_dbi(ep, func_no, reg, 0x2, val); +} + +static inline u16 dw_pcie_ep_readw_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg) +{ + return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x2); +} + +static inline void dw_pcie_ep_writeb_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg, u8 val) +{ + dw_pcie_ep_write_dbi(ep, func_no, reg, 0x1, val); } -static inline u32 dw_pcie_readl_dbi2(struct dw_pcie *pci, u32 reg) +static inline u8 dw_pcie_ep_readb_dbi(struct dw_pcie_ep *ep, u8 func_no, + u32 reg) { - return __dw_pcie_read_dbi(pci, pci->dbi_base2, reg, 0x4); + return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x1); } -static inline void dw_pcie_writel_atu(struct dw_pcie *pci, u32 reg, u32 val) +static inline int dw_pcie_ep_read_cfg_byte(struct dw_pcie_ep *ep, u8 func_no, + int where, u8 *val) { - __dw_pcie_write_dbi(pci, pci->atu_base, reg, 0x4, val); + *val = dw_pcie_ep_readb_dbi(ep, func_no, where); + return PCIBIOS_SUCCESSFUL; } -static inline u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 reg) +static inline int dw_pcie_ep_read_cfg_word(struct dw_pcie_ep *ep, u8 func_no, + int where, u16 *val) { - return __dw_pcie_read_dbi(pci, pci->atu_base, reg, 0x4); + *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) +{ + unsigned int dbi2_offset = 0; + + if (ep->ops->get_dbi2_offset) + dbi2_offset = ep->ops->get_dbi2_offset(ep, func_no); + else if (ep->ops->get_dbi_offset) /* for backward compatibility */ + dbi2_offset = ep->ops->get_dbi_offset(ep, func_no); + + return dbi2_offset; +} + +static inline void dw_pcie_ep_write_dbi2(struct dw_pcie_ep *ep, u8 func_no, + u32 reg, size_t size, u32 val) +{ + unsigned int offset = dw_pcie_ep_get_dbi2_offset(ep, func_no); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + dw_pcie_write_dbi2(pci, offset + reg, size, val); +} + +static inline void dw_pcie_ep_writel_dbi2(struct dw_pcie_ep *ep, u8 func_no, + u32 reg, u32 val) +{ + dw_pcie_ep_write_dbi2(ep, func_no, reg, 0x4, val); } static inline void dw_pcie_dbi_ro_wr_en(struct dw_pcie *pci) @@ -331,67 +784,152 @@ static inline void dw_pcie_dbi_ro_wr_dis(struct dw_pcie *pci) dw_pcie_writel_dbi(pci, reg, val); } +static inline int dw_pcie_start_link(struct dw_pcie *pci) +{ + if (pci->ops && pci->ops->start_link) + return pci->ops->start_link(pci); + + return 0; +} + +static inline void dw_pcie_stop_link(struct dw_pcie *pci) +{ + if (pci->ops && pci->ops->stop_link) + pci->ops->stop_link(pci); +} + +static inline int dw_pcie_assert_perst(struct dw_pcie *pci, bool assert) +{ + if (pci->ops && pci->ops->assert_perst) + return pci->ops->assert_perst(pci, assert); + + return 0; +} + +static inline enum dw_pcie_ltssm dw_pcie_get_ltssm(struct dw_pcie *pci) +{ + u32 val; + + if (pci->ops && pci->ops->get_ltssm) + return pci->ops->get_ltssm(pci); + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0); + + return (enum dw_pcie_ltssm)FIELD_GET(PORT_LOGIC_LTSSM_STATE_MASK, val); +} + #ifdef CONFIG_PCIE_DW_HOST -irqreturn_t dw_handle_msi_irq(struct pcie_port *pp); -void dw_pcie_msi_init(struct pcie_port *pp); -void dw_pcie_free_msi(struct pcie_port *pp); -void dw_pcie_setup_rc(struct pcie_port *pp); -int dw_pcie_host_init(struct pcie_port *pp); -int dw_pcie_allocate_domains(struct pcie_port *pp); +int dw_pcie_suspend_noirq(struct dw_pcie *pci); +int dw_pcie_resume_noirq(struct dw_pcie *pci); +irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp); +void dw_pcie_msi_init(struct dw_pcie_rp *pp); +int dw_pcie_msi_host_init(struct dw_pcie_rp *pp); +void dw_pcie_free_msi(struct dw_pcie_rp *pp); +int dw_pcie_setup_rc(struct dw_pcie_rp *pp); +int dw_pcie_host_init(struct dw_pcie_rp *pp); +void dw_pcie_host_deinit(struct dw_pcie_rp *pp); +int dw_pcie_allocate_domains(struct dw_pcie_rp *pp); +void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, + int where); #else -static inline irqreturn_t dw_handle_msi_irq(struct pcie_port *pp) +static inline int dw_pcie_suspend_noirq(struct dw_pcie *pci) { - return IRQ_NONE; + return 0; } -static inline void dw_pcie_msi_init(struct pcie_port *pp) +static inline int dw_pcie_resume_noirq(struct dw_pcie *pci) { + return 0; } -static inline void dw_pcie_free_msi(struct pcie_port *pp) +static inline irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp) { + return IRQ_NONE; } -static inline void dw_pcie_setup_rc(struct pcie_port *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 -ENODEV; } -static inline int dw_pcie_host_init(struct pcie_port *pp) +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; } -static inline int dw_pcie_allocate_domains(struct pcie_port *pp) +static inline int dw_pcie_host_init(struct dw_pcie_rp *pp) { return 0; } + +static inline void dw_pcie_host_deinit(struct dw_pcie_rp *pp) +{ +} + +static inline int dw_pcie_allocate_domains(struct dw_pcie_rp *pp) +{ + return 0; +} +static inline void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, + unsigned int devfn, + int where) +{ + return NULL; +} #endif #ifdef CONFIG_PCIE_DW_EP void dw_pcie_ep_linkup(struct dw_pcie_ep *ep); +void dw_pcie_ep_linkdown(struct dw_pcie_ep *ep); int dw_pcie_ep_init(struct dw_pcie_ep *ep); -void dw_pcie_ep_exit(struct dw_pcie_ep *ep); -int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no); +int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep); +void dw_pcie_ep_deinit(struct dw_pcie_ep *ep); +void dw_pcie_ep_cleanup(struct dw_pcie_ep *ep); +int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no); int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u8 interrupt_num); int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, u16 interrupt_num); +int dw_pcie_ep_raise_msix_irq_doorbell(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num); void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar); +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 static inline void dw_pcie_ep_linkup(struct dw_pcie_ep *ep) { } +static inline void dw_pcie_ep_linkdown(struct dw_pcie_ep *ep) +{ +} + static inline int dw_pcie_ep_init(struct dw_pcie_ep *ep) { return 0; } -static inline void dw_pcie_ep_exit(struct dw_pcie_ep *ep) +static inline int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep) +{ + return 0; +} + +static inline void dw_pcie_ep_deinit(struct dw_pcie_ep *ep) { } -static inline int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no) +static inline void dw_pcie_ep_cleanup(struct dw_pcie_ep *ep) +{ +} + +static inline int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no) { return 0; } @@ -408,8 +946,41 @@ static inline int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } +static inline int dw_pcie_ep_raise_msix_irq_doorbell(struct dw_pcie_ep *ep, + u8 func_no, + u16 interrupt_num) +{ + return 0; +} + static inline void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) { } + +static inline int dw_pcie_ep_hide_ext_capability(struct dw_pcie *pci, + u8 prev_cap, u8 cap) +{ + return 0; +} + +static inline struct dw_pcie_ep_func * +dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no) +{ + return NULL; +} #endif + +#ifdef CONFIG_PCIE_DW_DEBUGFS +void dwc_pcie_debugfs_init(struct dw_pcie *pci, enum dw_pcie_device_mode mode); +void dwc_pcie_debugfs_deinit(struct dw_pcie *pci); +#else +static inline void dwc_pcie_debugfs_init(struct dw_pcie *pci, + enum dw_pcie_device_mode mode) +{ +} +static inline void dwc_pcie_debugfs_deinit(struct dw_pcie *pci) +{ +} +#endif + #endif /* _PCIE_DESIGNWARE_H */ diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c new file mode 100644 index 000000000000..f8605fe61a41 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -0,0 +1,777 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Rockchip SoCs. + * + * Copyright (C) 2021 Rockchip Electronics Co., Ltd. + * http://www.rock-chips.com + * + * Author: Simon Xue <xxm@rock-chips.com> + */ + +#include <linux/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> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_irq.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +/* + * The upper 16 bits of PCIE_CLIENT_CONFIG are a write + * mask for the lower 16 bits. + */ + +#define to_rockchip_pcie(x) dev_get_drvdata((x)->dev) + +/* 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_INTR_MASK GENMASK(7, 0) +#define PCIE_INTR_CLAMP(_x) ((BIT((_x)) & PCIE_INTR_MASK)) +#define PCIE_INTR_LEGACY_MASK(x) (PCIE_INTR_CLAMP((x)) | \ + (PCIE_INTR_CLAMP((x)) << 16)) +#define PCIE_INTR_LEGACY_UNMASK(x) (PCIE_INTR_CLAMP((x)) << 16) + +/* Interrupt Mask Register Related to Miscellaneous Operation */ +#define PCIE_CLIENT_INTR_MASK_MISC 0x24 + +/* Power Management Control Register */ +#define PCIE_CLIENT_POWER_CON 0x2c +#define PCIE_CLKREQ_READY FIELD_PREP_WM16(BIT(0), 1) +#define PCIE_CLKREQ_NOT_READY FIELD_PREP_WM16(BIT(0), 0) +#define PCIE_CLKREQ_PULL_DOWN FIELD_PREP_WM16(GENMASK(13, 12), 1) + +/* Hot Reset Control Register */ +#define PCIE_CLIENT_HOT_RESET_CTRL 0x180 +#define PCIE_LTSSM_APP_DLY2_EN BIT(1) +#define PCIE_LTSSM_APP_DLY2_DONE BIT(3) +#define PCIE_LTSSM_ENABLE_ENHANCE BIT(4) + +/* LTSSM Status Register */ +#define PCIE_CLIENT_LTSSM_STATUS 0x300 +#define PCIE_LINKUP 0x3 +#define PCIE_LINKUP_MASK GENMASK(17, 16) +#define PCIE_LTSSM_STATUS_MASK GENMASK(5, 0) + +struct rockchip_pcie { + struct dw_pcie pci; + void __iomem *apb_base; + struct phy *phy; + struct clk_bulk_data *clks; + unsigned int clk_cnt; + struct reset_control *rst; + struct gpio_desc *rst_gpio; + struct irq_domain *irq_domain; + const struct rockchip_pcie_of_data *data; + bool supports_clkreq; +}; + +struct rockchip_pcie_of_data { + enum dw_pcie_device_mode mode; + const struct pci_epc_features *epc_features; +}; + +static int rockchip_pcie_readl_apb(struct rockchip_pcie *rockchip, u32 reg) +{ + return readl_relaxed(rockchip->apb_base + reg); +} + +static void rockchip_pcie_writel_apb(struct rockchip_pcie *rockchip, u32 val, + u32 reg) +{ + writel_relaxed(val, rockchip->apb_base + reg); +} + +static void rockchip_pcie_intx_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc); + unsigned long reg, hwirq; + + chained_irq_enter(chip, desc); + + reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_LEGACY); + + for_each_set_bit(hwirq, ®, 4) + generic_handle_domain_irq(rockchip->irq_domain, hwirq); + + chained_irq_exit(chip, desc); +} + +static void rockchip_intx_mask(struct irq_data *data) +{ + rockchip_pcie_writel_apb(irq_data_get_irq_chip_data(data), + 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), + PCIE_INTR_LEGACY_UNMASK(data->hwirq), + PCIE_CLIENT_INTR_MASK_LEGACY); +}; + +static struct irq_chip rockchip_intx_irq_chip = { + .name = "INTx", + .irq_mask = rockchip_intx_mask, + .irq_unmask = rockchip_intx_unmask, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, +}; + +static int rockchip_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &rockchip_intx_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = rockchip_pcie_intx_map, +}; + +static int rockchip_pcie_init_irq_domain(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->pci.dev; + struct device_node *intc; + + intc = of_get_child_by_name(dev->of_node, "legacy-interrupt-controller"); + if (!intc) { + dev_err(dev, "missing child interrupt-controller node\n"); + return -EINVAL; + } + + rockchip->irq_domain = irq_domain_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"); + return -EINVAL; + } + + return 0; +} + +static u32 rockchip_pcie_get_ltssm(struct rockchip_pcie *rockchip) +{ + return rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_LTSSM_STATUS); +} + +static void rockchip_pcie_enable_ltssm(struct rockchip_pcie *rockchip) +{ + rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_ENABLE_LTSSM, + 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_CON); +} + +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); + + return FIELD_GET(PCIE_LINKUP_MASK, val) == PCIE_LINKUP; +} + +/* + * See e.g. section '11.6.6.4 L1 Substate' in the RK3588 TRM V1.0 for the steps + * needed to support L1 substates. Currently, just enable L1 substates for RC + * mode if CLKREQ# is properly connected and supports-clkreq is present in DT. + * For EP mode, there are more things should be done to actually save power in + * L1 substates, so disable L1 substates until there is proper support. + */ +static void rockchip_pcie_configure_l1ss(struct dw_pcie *pci) +{ + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + + /* 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) +{ + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + + /* Reset device */ + gpiod_set_value_cansleep(rockchip->rst_gpio, 0); + + rockchip_pcie_enable_ltssm(rockchip); + + /* + * PCIe requires the refclk to be stable for 100µs prior to releasing + * PERST. See table 2-4 in section 2.6.2 AC Specifications of the PCI + * Express Card Electromechanical Specification, 1.1. However, we don't + * know if the refclk is coming from RC's PHY or external OSC. If it's + * from RC, so enabling LTSSM is the just right place to release #PERST. + * We need more extra time as before, rather than setting just + * 100us as we don't know how long should the device need to reset. + */ + msleep(PCIE_T_PVPERL_MS); + gpiod_set_value_cansleep(rockchip->rst_gpio, 1); + + return 0; +} + +static void rockchip_pcie_stop_link(struct dw_pcie *pci) +{ + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + + rockchip_pcie_disable_ltssm(rockchip); +} + +static int rockchip_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + struct device *dev = rockchip->pci.dev; + int irq, ret; + + irq = of_irq_get_byname(dev->of_node, "legacy"); + if (irq < 0) + return irq; + + ret = rockchip_pcie_init_irq_domain(rockchip); + if (ret < 0) + dev_err(dev, "failed to init irq domain\n"); + + irq_set_chained_handler_and_data(irq, rockchip_pcie_intx_handler, + rockchip); + + rockchip_pcie_configure_l1ss(pci); + rockchip_pcie_enable_l0s(pci); + + return 0; +} + +static const struct dw_pcie_host_ops rockchip_pcie_host_ops = { + .init = rockchip_pcie_host_init, +}; + +/* + * ATS does not work on RK3588 when running in EP mode. + * + * After the host has enabled ATS on the EP side, it will send an IOTLB + * invalidation request to the EP side. However, the RK3588 will never send + * a completion back and eventually the host will print an IOTLB_INV_TIMEOUT + * error, and the EP will not be operational. If we hide the ATS capability, + * things work as expected. + */ +static void rockchip_pcie_ep_hide_broken_ats_cap_rk3588(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + + /* Only hide the ATS capability for RK3588 running in EP mode. */ + if (!of_device_is_compatible(dev->of_node, "rockchip,rk3588-pcie-ep")) + return; + + if (dw_pcie_ep_hide_ext_capability(pci, PCI_EXT_CAP_ID_SECPCI, + PCI_EXT_CAP_ID_ATS)) + dev_err(dev, "failed to hide ATS capability\n"); +} + +static void rockchip_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + rockchip_pcie_enable_l0s(pci); + rockchip_pcie_ep_hide_broken_ats_cap_rk3588(ep); + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + dw_pcie_ep_reset_bar(pci, bar); +}; + +static int rockchip_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); + case PCI_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + } + + return 0; +} + +static const struct pci_epc_features rockchip_pcie_epc_features_rk3568 = { + .linkup_notifier = true, + .msi_capable = true, + .msix_capable = true, + .align = SZ_64K, + .bar[BAR_0] = { .type = BAR_RESIZABLE, }, + .bar[BAR_1] = { .type = BAR_RESIZABLE, }, + .bar[BAR_2] = { .type = BAR_RESIZABLE, }, + .bar[BAR_3] = { .type = BAR_RESIZABLE, }, + .bar[BAR_4] = { .type = BAR_RESIZABLE, }, + .bar[BAR_5] = { .type = BAR_RESIZABLE, }, +}; + +/* + * BAR4 on rk3588 exposes the ATU Port Logic Structure to the host regardless of + * iATU settings for BAR4. This means that BAR4 cannot be used by an EPF driver, + * so mark it as RESERVED. (rockchip_pcie_ep_init() will disable all BARs by + * default.) If the host could write to BAR4, the iATU settings (for all other + * BARs) would be overwritten, resulting in (all other BARs) no longer working. + */ +static const struct pci_epc_features rockchip_pcie_epc_features_rk3588 = { + .linkup_notifier = true, + .msi_capable = true, + .msix_capable = true, + .align = SZ_64K, + .bar[BAR_0] = { .type = BAR_RESIZABLE, }, + .bar[BAR_1] = { .type = BAR_RESIZABLE, }, + .bar[BAR_2] = { .type = BAR_RESIZABLE, }, + .bar[BAR_3] = { .type = BAR_RESIZABLE, }, + .bar[BAR_4] = { .type = BAR_RESERVED, }, + .bar[BAR_5] = { .type = BAR_RESIZABLE, }, +}; + +static const struct pci_epc_features * +rockchip_pcie_get_features(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + + return rockchip->data->epc_features; +} + +static const struct dw_pcie_ep_ops rockchip_pcie_ep_ops = { + .init = rockchip_pcie_ep_init, + .raise_irq = rockchip_pcie_raise_irq, + .get_features = rockchip_pcie_get_features, +}; + +static int rockchip_pcie_clk_init(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->pci.dev; + int ret; + + ret = devm_clk_bulk_get_all(dev, &rockchip->clks); + if (ret < 0) + return dev_err_probe(dev, ret, "failed to get clocks\n"); + + rockchip->clk_cnt = ret; + + ret = clk_bulk_prepare_enable(rockchip->clk_cnt, rockchip->clks); + if (ret) + return dev_err_probe(dev, ret, "failed to enable clocks\n"); + + return 0; +} + +static int rockchip_pcie_resource_get(struct platform_device *pdev, + struct rockchip_pcie *rockchip) +{ + rockchip->apb_base = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(rockchip->apb_base)) + return dev_err_probe(&pdev->dev, PTR_ERR(rockchip->apb_base), + "failed to map apb registers\n"); + + rockchip->rst_gpio = devm_gpiod_get_optional(&pdev->dev, "reset", + GPIOD_OUT_LOW); + if (IS_ERR(rockchip->rst_gpio)) + return dev_err_probe(&pdev->dev, PTR_ERR(rockchip->rst_gpio), + "failed to get reset gpio\n"); + + rockchip->rst = devm_reset_control_array_get_exclusive(&pdev->dev); + if (IS_ERR(rockchip->rst)) + return dev_err_probe(&pdev->dev, PTR_ERR(rockchip->rst), + "failed to get reset lines\n"); + + rockchip->supports_clkreq = of_property_read_bool(pdev->dev.of_node, + "supports-clkreq"); + + return 0; +} + +static int rockchip_pcie_phy_init(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->pci.dev; + int ret; + + rockchip->phy = devm_phy_get(dev, "pcie-phy"); + if (IS_ERR(rockchip->phy)) + return dev_err_probe(dev, PTR_ERR(rockchip->phy), + "missing PHY\n"); + + ret = phy_init(rockchip->phy); + if (ret < 0) + return ret; + + ret = phy_power_on(rockchip->phy); + if (ret) + phy_exit(rockchip->phy); + + return ret; +} + +static void rockchip_pcie_phy_deinit(struct rockchip_pcie *rockchip) +{ + phy_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, +}; + +static irqreturn_t rockchip_pcie_rc_sys_irq_thread(int irq, void *arg) +{ + struct rockchip_pcie *rockchip = arg; + struct dw_pcie *pci = &rockchip->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = pci->dev; + u32 reg; + + reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_MISC); + rockchip_pcie_writel_apb(rockchip, reg, PCIE_CLIENT_INTR_STATUS_MISC); + + dev_dbg(dev, "PCIE_CLIENT_INTR_STATUS_MISC: %#x\n", reg); + dev_dbg(dev, "LTSSM_STATUS: %#x\n", rockchip_pcie_get_ltssm(rockchip)); + + if (reg & PCIE_RDLH_LINK_UP_CHGED) { + if (rockchip_pcie_link_up(pci)) { + msleep(PCIE_RESET_CONFIG_WAIT_MS); + dev_dbg(dev, "Received Link up event. Starting enumeration!\n"); + /* Rescan the bus to enumerate endpoint devices */ + pci_lock_rescan_remove(); + pci_rescan_bus(pp->bridge->bus); + pci_unlock_rescan_remove(); + } + } + + return IRQ_HANDLED; +} + +static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) +{ + struct rockchip_pcie *rockchip = arg; + struct dw_pcie *pci = &rockchip->pci; + 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_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) { + if (rockchip_pcie_link_up(pci)) { + dev_dbg(dev, "link up\n"); + dw_pcie_ep_linkup(&pci->ep); + } + } + + return IRQ_HANDLED; +} + +static int rockchip_pcie_configure_rc(struct platform_device *pdev, + struct rockchip_pcie *rockchip) +{ + struct device *dev = &pdev->dev; + struct dw_pcie_rp *pp; + int irq, ret; + u32 val; + + if (!IS_ENABLED(CONFIG_PCIE_ROCKCHIP_DW_HOST)) + return -ENODEV; + + irq = platform_get_irq_byname(pdev, "sys"); + if (irq < 0) + return irq; + + ret = devm_request_threaded_irq(dev, irq, NULL, + rockchip_pcie_rc_sys_irq_thread, + IRQF_ONESHOT, "pcie-sys-rc", rockchip); + if (ret) { + dev_err(dev, "failed to request PCIe sys IRQ\n"); + return ret; + } + + /* LTSSM enable control mode */ + val = 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_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 = FIELD_PREP_WM16(PCIE_RDLH_LINK_UP_CHGED, 0); + rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC); + + return ret; +} + +static int rockchip_pcie_configure_ep(struct platform_device *pdev, + struct rockchip_pcie *rockchip) +{ + struct device *dev = &pdev->dev; + int irq, ret; + u32 val; + + if (!IS_ENABLED(CONFIG_PCIE_ROCKCHIP_DW_EP)) + return -ENODEV; + + irq = platform_get_irq_byname(pdev, "sys"); + if (irq < 0) + return irq; + + ret = devm_request_threaded_irq(dev, irq, NULL, + rockchip_pcie_ep_sys_irq_thread, + IRQF_ONESHOT, "pcie-sys-ep", rockchip); + if (ret) { + dev_err(dev, "failed to request PCIe sys IRQ\n"); + return ret; + } + + /* + * 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_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; + + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + + ret = dw_pcie_ep_init(&rockchip->pci.ep); + if (ret) { + dev_err(dev, "failed to initialize endpoint\n"); + return ret; + } + + ret = dw_pcie_ep_init_registers(&rockchip->pci.ep); + if (ret) { + dev_err(dev, "failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(&rockchip->pci.ep); + return ret; + } + + pci_epc_init_notify(rockchip->pci.ep.epc); + + /* unmask DLL up/down indicator and hot reset/link-down reset */ + 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; +} + +static int rockchip_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rockchip_pcie *rockchip; + const struct rockchip_pcie_of_data *data; + int ret; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + rockchip = devm_kzalloc(dev, sizeof(*rockchip), GFP_KERNEL); + if (!rockchip) + return -ENOMEM; + + platform_set_drvdata(pdev, rockchip); + + rockchip->pci.dev = dev; + rockchip->pci.ops = &dw_pcie_ops; + 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; + + ret = reset_control_assert(rockchip->rst); + if (ret) + return ret; + + /* DON'T MOVE ME: must be enable before PHY init */ + 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) + return dev_err_probe(dev, ret, + "failed to initialize the phy\n"); + + ret = reset_control_deassert(rockchip->rst); + if (ret) + goto deinit_phy; + + ret = rockchip_pcie_clk_init(rockchip); + if (ret) + goto deinit_phy; + + switch (data->mode) { + case DW_PCIE_RC_TYPE: + ret = rockchip_pcie_configure_rc(pdev, rockchip); + if (ret) + goto deinit_clk; + break; + case DW_PCIE_EP_TYPE: + ret = rockchip_pcie_configure_ep(pdev, rockchip); + if (ret) + goto deinit_clk; + break; + default: + dev_err(dev, "INVALID device type %d\n", data->mode); + ret = -EINVAL; + goto deinit_clk; + } + + return 0; + +deinit_clk: + clk_bulk_disable_unprepare(rockchip->clk_cnt, rockchip->clks); +deinit_phy: + rockchip_pcie_phy_deinit(rockchip); + + return ret; +} + +static const struct rockchip_pcie_of_data rockchip_pcie_rc_of_data_rk3568 = { + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct rockchip_pcie_of_data rockchip_pcie_ep_of_data_rk3568 = { + .mode = DW_PCIE_EP_TYPE, + .epc_features = &rockchip_pcie_epc_features_rk3568, +}; + +static const struct rockchip_pcie_of_data rockchip_pcie_ep_of_data_rk3588 = { + .mode = DW_PCIE_EP_TYPE, + .epc_features = &rockchip_pcie_epc_features_rk3588, +}; + +static const struct of_device_id rockchip_pcie_of_match[] = { + { + .compatible = "rockchip,rk3568-pcie", + .data = &rockchip_pcie_rc_of_data_rk3568, + }, + { + .compatible = "rockchip,rk3568-pcie-ep", + .data = &rockchip_pcie_ep_of_data_rk3568, + }, + { + .compatible = "rockchip,rk3588-pcie-ep", + .data = &rockchip_pcie_ep_of_data_rk3588, + }, + {}, +}; + +static struct platform_driver rockchip_pcie_driver = { + .driver = { + .name = "rockchip-dw-pcie", + .of_match_table = rockchip_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = rockchip_pcie_probe, +}; +builtin_platform_driver(rockchip_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c new file mode 100644 index 000000000000..66367252032b --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-fu740.c @@ -0,0 +1,357 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * FU740 DesignWare PCIe Controller integration + * Copyright (C) 2019-2021 SiFive, Inc. + * Paul Walmsley + * Greentime Hu + * + * Based in part on the i.MX6 PCIe host controller shim which is: + * + * Copyright (C) 2013 Kosagi + * https://www.kosagi.com + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +#define to_fu740_pcie(x) dev_get_drvdata((x)->dev) + +struct fu740_pcie { + struct dw_pcie pci; + void __iomem *mgmt_base; + struct gpio_desc *reset; + struct gpio_desc *pwren; + struct clk *pcie_aux; + struct reset_control *rst; +}; + +#define SIFIVE_DEVICESRESETREG 0x28 + +#define PCIEX8MGMT_PERST_N 0x0 +#define PCIEX8MGMT_APP_LTSSM_ENABLE 0x10 +#define PCIEX8MGMT_APP_HOLD_PHY_RST 0x18 +#define PCIEX8MGMT_DEVICE_TYPE 0x708 +#define PCIEX8MGMT_PHY0_CR_PARA_ADDR 0x860 +#define PCIEX8MGMT_PHY0_CR_PARA_RD_EN 0x870 +#define PCIEX8MGMT_PHY0_CR_PARA_RD_DATA 0x878 +#define PCIEX8MGMT_PHY0_CR_PARA_SEL 0x880 +#define PCIEX8MGMT_PHY0_CR_PARA_WR_DATA 0x888 +#define PCIEX8MGMT_PHY0_CR_PARA_WR_EN 0x890 +#define PCIEX8MGMT_PHY0_CR_PARA_ACK 0x898 +#define PCIEX8MGMT_PHY1_CR_PARA_ADDR 0x8a0 +#define PCIEX8MGMT_PHY1_CR_PARA_RD_EN 0x8b0 +#define PCIEX8MGMT_PHY1_CR_PARA_RD_DATA 0x8b8 +#define PCIEX8MGMT_PHY1_CR_PARA_SEL 0x8c0 +#define PCIEX8MGMT_PHY1_CR_PARA_WR_DATA 0x8c8 +#define PCIEX8MGMT_PHY1_CR_PARA_WR_EN 0x8d0 +#define PCIEX8MGMT_PHY1_CR_PARA_ACK 0x8d8 + +#define PCIEX8MGMT_PHY_CDR_TRACK_EN BIT(0) +#define PCIEX8MGMT_PHY_LOS_THRSHLD BIT(5) +#define PCIEX8MGMT_PHY_TERM_EN BIT(9) +#define PCIEX8MGMT_PHY_TERM_ACDC BIT(10) +#define PCIEX8MGMT_PHY_EN BIT(11) +#define PCIEX8MGMT_PHY_INIT_VAL (PCIEX8MGMT_PHY_CDR_TRACK_EN|\ + PCIEX8MGMT_PHY_LOS_THRSHLD|\ + PCIEX8MGMT_PHY_TERM_EN|\ + PCIEX8MGMT_PHY_TERM_ACDC|\ + PCIEX8MGMT_PHY_EN) + +#define PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 0x1008 +#define PCIEX8MGMT_PHY_LANE_OFF 0x100 +#define PCIEX8MGMT_PHY_LANE0_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 0) +#define PCIEX8MGMT_PHY_LANE1_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 1) +#define PCIEX8MGMT_PHY_LANE2_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 2) +#define PCIEX8MGMT_PHY_LANE3_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 3) + +static void fu740_pcie_assert_reset(struct fu740_pcie *afp) +{ + /* Assert PERST_N GPIO */ + gpiod_set_value_cansleep(afp->reset, 0); + /* Assert controller PERST_N */ + writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_PERST_N); +} + +static void fu740_pcie_deassert_reset(struct fu740_pcie *afp) +{ + /* Deassert controller PERST_N */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PERST_N); + /* Deassert PERST_N GPIO */ + gpiod_set_value_cansleep(afp->reset, 1); +} + +static void fu740_pcie_power_on(struct fu740_pcie *afp) +{ + gpiod_set_value_cansleep(afp->pwren, 1); + /* + * Ensure that PERST has been asserted for at least 100 ms. + * Section 2.2 of PCI Express Card Electromechanical Specification + * Revision 3.0 + */ + msleep(100); +} + +static void fu740_pcie_drive_reset(struct fu740_pcie *afp) +{ + fu740_pcie_assert_reset(afp); + fu740_pcie_power_on(afp); + fu740_pcie_deassert_reset(afp); +} + +static void fu740_phyregwrite(const uint8_t phy, const uint16_t addr, + const uint16_t wrdata, struct fu740_pcie *afp) +{ + struct device *dev = afp->pci.dev; + void __iomem *phy_cr_para_addr; + void __iomem *phy_cr_para_wr_data; + void __iomem *phy_cr_para_wr_en; + void __iomem *phy_cr_para_ack; + int ret, val; + + /* Setup */ + if (phy) { + phy_cr_para_addr = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_ADDR; + phy_cr_para_wr_data = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_WR_DATA; + phy_cr_para_wr_en = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_WR_EN; + phy_cr_para_ack = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_ACK; + } else { + phy_cr_para_addr = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_ADDR; + phy_cr_para_wr_data = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_WR_DATA; + phy_cr_para_wr_en = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_WR_EN; + phy_cr_para_ack = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_ACK; + } + + writel_relaxed(addr, phy_cr_para_addr); + writel_relaxed(wrdata, phy_cr_para_wr_data); + writel_relaxed(1, phy_cr_para_wr_en); + + /* Wait for wait_idle */ + ret = readl_poll_timeout(phy_cr_para_ack, val, val, 10, 5000); + if (ret) + dev_warn(dev, "Wait for wait_idle state failed!\n"); + + /* Clear */ + writel_relaxed(0, phy_cr_para_wr_en); + + /* Wait for ~wait_idle */ + ret = readl_poll_timeout(phy_cr_para_ack, val, !val, 10, 5000); + if (ret) + dev_warn(dev, "Wait for !wait_idle state failed!\n"); +} + +static void fu740_pcie_init_phy(struct fu740_pcie *afp) +{ + /* Enable phy cr_para_sel interfaces */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_SEL); + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_SEL); + + /* + * Wait 10 cr_para cycles to guarantee that the registers are ready + * to be edited. + */ + ndelay(10); + + /* Set PHY AC termination mode */ + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE0_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE1_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE2_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE3_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE0_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE1_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE2_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE3_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); +} + +static int fu740_pcie_start_link(struct dw_pcie *pci) +{ + struct device *dev = pci->dev; + struct fu740_pcie *afp = dev_get_drvdata(dev); + u8 cap_exp = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + int ret; + u32 orig, tmp; + + /* + * Force 2.5GT/s when starting the link, due to some devices not + * probing at higher speeds. This happens with the PCIe switch + * on the Unmatched board when U-Boot has not initialised the PCIe. + * The fix in U-Boot is to force 2.5GT/s, which then gets cleared + * by the soft reset done by this driver. + */ + dev_dbg(dev, "cap_exp at %x\n", cap_exp); + dw_pcie_dbi_ro_wr_en(pci); + + tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP); + orig = tmp & PCI_EXP_LNKCAP_SLS; + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= PCI_EXP_LNKCAP_SLS_2_5GB; + dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp); + + /* Enable LTSSM */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_LTSSM_ENABLE); + + ret = dw_pcie_wait_for_link(pci); + if (ret) { + dev_err(dev, "error: link did not start\n"); + goto err; + } + + tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP); + if ((tmp & PCI_EXP_LNKCAP_SLS) != orig) { + dev_dbg(dev, "changing speed back to original\n"); + + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= orig; + dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp); + + tmp = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + tmp |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp); + + ret = dw_pcie_wait_for_link(pci); + if (ret) { + dev_err(dev, "error: link did not start at new speed\n"); + goto err; + } + } + + ret = 0; +err: + WARN_ON(ret); /* we assume that errors will be very rare */ + dw_pcie_dbi_ro_wr_dis(pci); + return ret; +} + +static int fu740_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct fu740_pcie *afp = to_fu740_pcie(pci); + struct device *dev = pci->dev; + int ret; + + /* Power on reset */ + fu740_pcie_drive_reset(afp); + + /* Enable pcieauxclk */ + ret = clk_prepare_enable(afp->pcie_aux); + if (ret) { + dev_err(dev, "unable to enable pcie_aux clock\n"); + return ret; + } + + /* + * Assert hold_phy_rst (hold the controller LTSSM in reset after + * power_up_rst_n for register programming with cr_para) + */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST); + + /* Deassert power_up_rst_n */ + ret = reset_control_deassert(afp->rst); + if (ret) { + dev_err(dev, "unable to deassert pcie_power_up_rst_n\n"); + return ret; + } + + fu740_pcie_init_phy(afp); + + /* Disable pcieauxclk */ + clk_disable_unprepare(afp->pcie_aux); + /* Clear hold_phy_rst */ + writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST); + /* Enable pcieauxclk */ + clk_prepare_enable(afp->pcie_aux); + /* Set RC mode */ + writel_relaxed(0x4, afp->mgmt_base + PCIEX8MGMT_DEVICE_TYPE); + + return 0; +} + +static const struct dw_pcie_host_ops fu740_pcie_host_ops = { + .init = fu740_pcie_host_init, +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = fu740_pcie_start_link, +}; + +static int fu740_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct fu740_pcie *afp; + + afp = devm_kzalloc(dev, sizeof(*afp), GFP_KERNEL); + if (!afp) + return -ENOMEM; + pci = &afp->pci; + pci->dev = dev; + pci->ops = &dw_pcie_ops; + pci->pp.ops = &fu740_pcie_host_ops; + pci->pp.num_vectors = MAX_MSI_IRQS; + + /* SiFive specific region: mgmt */ + afp->mgmt_base = devm_platform_ioremap_resource_byname(pdev, "mgmt"); + if (IS_ERR(afp->mgmt_base)) + return PTR_ERR(afp->mgmt_base); + + /* Fetch GPIOs */ + afp->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(afp->reset)) + return dev_err_probe(dev, PTR_ERR(afp->reset), "unable to get reset-gpios\n"); + + afp->pwren = devm_gpiod_get_optional(dev, "pwren", GPIOD_OUT_LOW); + if (IS_ERR(afp->pwren)) + return dev_err_probe(dev, PTR_ERR(afp->pwren), "unable to get pwren-gpios\n"); + + /* Fetch clocks */ + afp->pcie_aux = devm_clk_get(dev, "pcie_aux"); + if (IS_ERR(afp->pcie_aux)) + return dev_err_probe(dev, PTR_ERR(afp->pcie_aux), + "pcie_aux clock source missing or invalid\n"); + + /* Fetch reset */ + afp->rst = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(afp->rst)) + return dev_err_probe(dev, PTR_ERR(afp->rst), "unable to get reset\n"); + + platform_set_drvdata(pdev, afp); + + return dw_pcie_host_init(&pci->pp); +} + +static void fu740_pcie_shutdown(struct platform_device *pdev) +{ + struct fu740_pcie *afp = platform_get_drvdata(pdev); + + /* Bring down link, so bootloader gets clean state in case of reboot */ + fu740_pcie_assert_reset(afp); +} + +static const struct of_device_id fu740_pcie_of_match[] = { + { .compatible = "sifive,fu740-pcie", }, + {}, +}; + +static struct platform_driver fu740_pcie_driver = { + .driver = { + .name = "fu740-pcie", + .of_match_table = fu740_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = fu740_pcie_probe, + .shutdown = fu740_pcie_shutdown, +}; + +builtin_platform_driver(fu740_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-hisi.c b/drivers/pci/controller/dwc/pcie-hisi.c index 6d9e1b2b8f7b..3c17897e56fc 100644 --- a/drivers/pci/controller/dwc/pcie-hisi.c +++ b/drivers/pci/controller/dwc/pcie-hisi.c @@ -10,19 +10,19 @@ */ #include <linux/interrupt.h> #include <linux/init.h> -#include <linux/mfd/syscon.h> -#include <linux/of_address.h> -#include <linux/of_pci.h> #include <linux/platform_device.h> -#include <linux/of_device.h> #include <linux/pci.h> #include <linux/pci-acpi.h> #include <linux/pci-ecam.h> -#include <linux/regmap.h> #include "../../pci.h" +#include "../pci-host-common.h" #if defined(CONFIG_PCI_HISI) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) +struct hisi_pcie { + void __iomem *reg_base; +}; + static int hisi_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { @@ -63,10 +63,10 @@ static void __iomem *hisi_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, int where) { struct pci_config_window *cfg = bus->sysdata; - void __iomem *reg_base = cfg->priv; + struct hisi_pcie *pcie = cfg->priv; if (bus->number == cfg->busr.start) - return reg_base + where; + return pcie->reg_base + where; else return pci_ecam_map_bus(bus, devfn, where); } @@ -76,12 +76,16 @@ static void __iomem *hisi_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, static int hisi_pcie_init(struct pci_config_window *cfg) { struct device *dev = cfg->parent; + struct hisi_pcie *pcie; struct acpi_device *adev = to_acpi_device(dev); struct acpi_pci_root *root = acpi_driver_data(adev); struct resource *res; - void __iomem *reg_base; int ret; + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + /* * Retrieve RC base and size from a HISI0081 device with _UID * matching our segment. @@ -96,16 +100,15 @@ static int hisi_pcie_init(struct pci_config_window *cfg) return -ENOMEM; } - reg_base = devm_pci_remap_cfgspace(dev, res->start, resource_size(res)); - if (!reg_base) + pcie->reg_base = devm_pci_remap_cfgspace(dev, res->start, resource_size(res)); + if (!pcie->reg_base) return -ENOMEM; - cfg->priv = reg_base; + cfg->priv = pcie; return 0; } -struct pci_ecam_ops hisi_pcie_ops = { - .bus_shift = 20, +const struct pci_ecam_ops hisi_pcie_ops = { .init = hisi_pcie_init, .pci_ops = { .map_bus = hisi_pcie_map_bus, @@ -118,235 +121,16 @@ struct pci_ecam_ops hisi_pcie_ops = { #ifdef CONFIG_PCI_HISI -#include "pcie-designware.h" - -#define PCIE_SUBCTRL_SYS_STATE4_REG 0x6818 -#define PCIE_HIP06_CTRL_OFF 0x1000 -#define PCIE_SYS_STATE4 (PCIE_HIP06_CTRL_OFF + 0x31c) -#define PCIE_LTSSM_LINKUP_STATE 0x11 -#define PCIE_LTSSM_STATE_MASK 0x3F - -#define to_hisi_pcie(x) dev_get_drvdata((x)->dev) - -struct hisi_pcie; - -struct pcie_soc_ops { - int (*hisi_pcie_link_up)(struct hisi_pcie *hisi_pcie); -}; - -struct hisi_pcie { - struct dw_pcie *pci; - struct regmap *subctrl; - u32 port_id; - const struct pcie_soc_ops *soc_ops; -}; - -/* HipXX PCIe host only supports 32-bit config access */ -static int hisi_pcie_cfg_read(struct pcie_port *pp, int where, int size, - u32 *val) -{ - u32 reg; - u32 reg_val; - void *walker = ®_val; - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - - walker += (where & 0x3); - reg = where & ~0x3; - reg_val = dw_pcie_readl_dbi(pci, reg); - - if (size == 1) - *val = *(u8 __force *) walker; - else if (size == 2) - *val = *(u16 __force *) walker; - else if (size == 4) - *val = reg_val; - else - return PCIBIOS_BAD_REGISTER_NUMBER; - - return PCIBIOS_SUCCESSFUL; -} - -/* HipXX PCIe host only supports 32-bit config access */ -static int hisi_pcie_cfg_write(struct pcie_port *pp, int where, int size, - u32 val) -{ - u32 reg_val; - u32 reg; - void *walker = ®_val; - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - - walker += (where & 0x3); - reg = where & ~0x3; - if (size == 4) - dw_pcie_writel_dbi(pci, reg, val); - else if (size == 2) { - reg_val = dw_pcie_readl_dbi(pci, reg); - *(u16 __force *) walker = val; - dw_pcie_writel_dbi(pci, reg, reg_val); - } else if (size == 1) { - reg_val = dw_pcie_readl_dbi(pci, reg); - *(u8 __force *) walker = val; - dw_pcie_writel_dbi(pci, reg, reg_val); - } else - return PCIBIOS_BAD_REGISTER_NUMBER; - - return PCIBIOS_SUCCESSFUL; -} - -static int hisi_pcie_link_up_hip05(struct hisi_pcie *hisi_pcie) -{ - u32 val; - - regmap_read(hisi_pcie->subctrl, PCIE_SUBCTRL_SYS_STATE4_REG + - 0x100 * hisi_pcie->port_id, &val); - - return ((val & PCIE_LTSSM_STATE_MASK) == PCIE_LTSSM_LINKUP_STATE); -} - -static int hisi_pcie_link_up_hip06(struct hisi_pcie *hisi_pcie) -{ - struct dw_pcie *pci = hisi_pcie->pci; - u32 val; - - val = dw_pcie_readl_dbi(pci, PCIE_SYS_STATE4); - - return ((val & PCIE_LTSSM_STATE_MASK) == PCIE_LTSSM_LINKUP_STATE); -} - -static int hisi_pcie_link_up(struct dw_pcie *pci) -{ - struct hisi_pcie *hisi_pcie = to_hisi_pcie(pci); - - return hisi_pcie->soc_ops->hisi_pcie_link_up(hisi_pcie); -} - -static const struct dw_pcie_host_ops hisi_pcie_host_ops = { - .rd_own_conf = hisi_pcie_cfg_read, - .wr_own_conf = hisi_pcie_cfg_write, -}; - -static int hisi_add_pcie_port(struct hisi_pcie *hisi_pcie, - struct platform_device *pdev) -{ - struct dw_pcie *pci = hisi_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = &pdev->dev; - int ret; - u32 port_id; - - if (of_property_read_u32(dev->of_node, "port-id", &port_id)) { - dev_err(dev, "failed to read port-id\n"); - return -EINVAL; - } - if (port_id > 3) { - dev_err(dev, "Invalid port-id: %d\n", port_id); - return -EINVAL; - } - hisi_pcie->port_id = port_id; - - pp->ops = &hisi_pcie_host_ops; - - ret = dw_pcie_host_init(pp); - if (ret) { - dev_err(dev, "failed to initialize host\n"); - return ret; - } - - return 0; -} - -static const struct dw_pcie_ops dw_pcie_ops = { - .link_up = hisi_pcie_link_up, -}; - -static int hisi_pcie_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct dw_pcie *pci; - struct hisi_pcie *hisi_pcie; - struct resource *reg; - int ret; - - hisi_pcie = devm_kzalloc(dev, sizeof(*hisi_pcie), GFP_KERNEL); - if (!hisi_pcie) - return -ENOMEM; - - pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); - if (!pci) - return -ENOMEM; - - pci->dev = dev; - pci->ops = &dw_pcie_ops; - - hisi_pcie->pci = pci; - - hisi_pcie->soc_ops = of_device_get_match_data(dev); - - hisi_pcie->subctrl = - syscon_regmap_lookup_by_compatible("hisilicon,pcie-sas-subctrl"); - if (IS_ERR(hisi_pcie->subctrl)) { - dev_err(dev, "cannot get subctrl base\n"); - return PTR_ERR(hisi_pcie->subctrl); - } - - reg = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rc_dbi"); - pci->dbi_base = devm_pci_remap_cfg_resource(dev, reg); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); - platform_set_drvdata(pdev, hisi_pcie); - - ret = hisi_add_pcie_port(hisi_pcie, pdev); - if (ret) - return ret; - - return 0; -} - -static struct pcie_soc_ops hip05_ops = { - &hisi_pcie_link_up_hip05 -}; - -static struct pcie_soc_ops hip06_ops = { - &hisi_pcie_link_up_hip06 -}; - -static const struct of_device_id hisi_pcie_of_match[] = { - { - .compatible = "hisilicon,hip05-pcie", - .data = (void *) &hip05_ops, - }, - { - .compatible = "hisilicon,hip06-pcie", - .data = (void *) &hip06_ops, - }, - {}, -}; - -static struct platform_driver hisi_pcie_driver = { - .probe = hisi_pcie_probe, - .driver = { - .name = "hisi-pcie", - .of_match_table = hisi_pcie_of_match, - .suppress_bind_attrs = true, - }, -}; -builtin_platform_driver(hisi_pcie_driver); - -static int hisi_pcie_almost_ecam_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct pci_ecam_ops *ops; - - ops = (struct pci_ecam_ops *)of_device_get_match_data(dev); - return pci_host_common_probe(pdev, ops); -} - static int hisi_pcie_platform_init(struct pci_config_window *cfg) { struct device *dev = cfg->parent; + struct hisi_pcie *pcie; struct platform_device *pdev = to_platform_device(dev); struct resource *res; - void __iomem *reg_base; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; res = platform_get_resource(pdev, IORESOURCE_MEM, 1); if (!res) { @@ -354,16 +138,15 @@ static int hisi_pcie_platform_init(struct pci_config_window *cfg) return -EINVAL; } - reg_base = devm_pci_remap_cfgspace(dev, res->start, resource_size(res)); - if (!reg_base) + pcie->reg_base = devm_pci_remap_cfgspace(dev, res->start, resource_size(res)); + if (!pcie->reg_base) return -ENOMEM; - cfg->priv = reg_base; + cfg->priv = pcie; return 0; } -struct pci_ecam_ops hisi_pcie_platform_ops = { - .bus_shift = 20, +static const struct pci_ecam_ops hisi_pcie_platform_ops = { .init = hisi_pcie_platform_init, .pci_ops = { .map_bus = hisi_pcie_map_bus, @@ -375,17 +158,17 @@ struct pci_ecam_ops hisi_pcie_platform_ops = { static const struct of_device_id hisi_pcie_almost_ecam_of_match[] = { { .compatible = "hisilicon,hip06-pcie-ecam", - .data = (void *) &hisi_pcie_platform_ops, + .data = &hisi_pcie_platform_ops, }, { .compatible = "hisilicon,hip07-pcie-ecam", - .data = (void *) &hisi_pcie_platform_ops, + .data = &hisi_pcie_platform_ops, }, {}, }; static struct platform_driver hisi_pcie_almost_ecam_driver = { - .probe = hisi_pcie_almost_ecam_probe, + .probe = pci_host_common_probe, .driver = { .name = "hisi-pcie-almost-ecam", .of_match_table = hisi_pcie_almost_ecam_of_match, diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c index 954bc2b74bbc..a52071589377 100644 --- a/drivers/pci/controller/dwc/pcie-histb.c +++ b/drivers/pci/controller/dwc/pcie-histb.c @@ -10,11 +10,11 @@ #include <linux/clk.h> #include <linux/delay.h> +#include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> -#include <linux/of_gpio.h> #include <linux/pci.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> @@ -60,7 +60,7 @@ struct histb_pcie { struct reset_control *sys_reset; struct reset_control *bus_reset; void __iomem *ctrl; - int reset_gpio; + struct gpio_desc *reset_gpio; struct regulator *vpcie; }; @@ -74,7 +74,7 @@ static void histb_pcie_writel(struct histb_pcie *histb_pcie, u32 reg, u32 val) writel(val, histb_pcie->ctrl + reg); } -static void histb_pcie_dbi_w_mode(struct pcie_port *pp, bool enable) +static void histb_pcie_dbi_w_mode(struct dw_pcie_rp *pp, bool enable) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct histb_pcie *hipcie = to_histb_pcie(pci); @@ -88,7 +88,7 @@ static void histb_pcie_dbi_w_mode(struct pcie_port *pp, bool enable) histb_pcie_writel(hipcie, PCIE_SYS_CTRL0, val); } -static void histb_pcie_dbi_r_mode(struct pcie_port *pp, bool enable) +static void histb_pcie_dbi_r_mode(struct dw_pcie_rp *pp, bool enable) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct histb_pcie *hipcie = to_histb_pcie(pci); @@ -122,33 +122,36 @@ static void histb_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, histb_pcie_dbi_w_mode(&pci->pp, false); } -static int histb_pcie_rd_own_conf(struct pcie_port *pp, int where, - int size, u32 *val) +static int histb_pcie_rd_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - int ret; + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); - histb_pcie_dbi_r_mode(pp, true); - ret = dw_pcie_read(pci->dbi_base + where, size, val); - histb_pcie_dbi_r_mode(pp, false); + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; - return ret; + *val = dw_pcie_read_dbi(pci, where, size); + return PCIBIOS_SUCCESSFUL; } -static int histb_pcie_wr_own_conf(struct pcie_port *pp, int where, - int size, u32 val) +static int histb_pcie_wr_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - int ret; + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); - histb_pcie_dbi_w_mode(pp, true); - ret = dw_pcie_write(pci->dbi_base + where, size, val); - histb_pcie_dbi_w_mode(pp, false); + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; - return ret; + dw_pcie_write_dbi(pci, where, size, val); + return PCIBIOS_SUCCESSFUL; } -static int histb_pcie_link_up(struct dw_pcie *pci) +static struct pci_ops histb_pci_ops = { + .read = histb_pcie_rd_own_conf, + .write = histb_pcie_wr_own_conf, +}; + +static bool histb_pcie_link_up(struct dw_pcie *pci) { struct histb_pcie *hipcie = to_histb_pcie(pci); u32 regval; @@ -157,55 +160,42 @@ 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_establish_link(struct pcie_port *pp) +static int histb_pcie_start_link(struct dw_pcie *pci) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct histb_pcie *hipcie = to_histb_pcie(pci); u32 regval; - if (dw_pcie_link_up(pci)) { - dev_info(pci->dev, "Link already up\n"); - return 0; - } - - /* PCIe RC work mode */ - regval = histb_pcie_readl(hipcie, PCIE_SYS_CTRL0); - regval &= ~PCIE_DEVICE_TYPE_MASK; - regval |= PCIE_WM_RC; - histb_pcie_writel(hipcie, PCIE_SYS_CTRL0, regval); - - /* setup root complex */ - dw_pcie_setup_rc(pp); - /* assert LTSSM enable */ regval = histb_pcie_readl(hipcie, PCIE_SYS_CTRL7); regval |= PCIE_APP_LTSSM_ENABLE; histb_pcie_writel(hipcie, PCIE_SYS_CTRL7, regval); - return dw_pcie_wait_for_link(pci); + return 0; } -static int histb_pcie_host_init(struct pcie_port *pp) +static int histb_pcie_host_init(struct dw_pcie_rp *pp) { - histb_pcie_establish_link(pp); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct histb_pcie *hipcie = to_histb_pcie(pci); + u32 regval; - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(pp); + pp->bridge->ops = &histb_pci_ops; + + /* PCIe RC work mode */ + regval = histb_pcie_readl(hipcie, PCIE_SYS_CTRL0); + regval &= ~PCIE_DEVICE_TYPE_MASK; + regval |= PCIE_WM_RC; + histb_pcie_writel(hipcie, PCIE_SYS_CTRL0, regval); return 0; } static const struct dw_pcie_host_ops histb_pcie_host_ops = { - .rd_own_conf = histb_pcie_rd_own_conf, - .wr_own_conf = histb_pcie_wr_own_conf, - .host_init = histb_pcie_host_init, + .init = histb_pcie_host_init, }; static void histb_pcie_host_disable(struct histb_pcie *hipcie) @@ -219,14 +209,14 @@ static void histb_pcie_host_disable(struct histb_pcie *hipcie) clk_disable_unprepare(hipcie->sys_clk); clk_disable_unprepare(hipcie->bus_clk); - if (gpio_is_valid(hipcie->reset_gpio)) - gpio_set_value_cansleep(hipcie->reset_gpio, 0); + if (hipcie->reset_gpio) + gpiod_set_value_cansleep(hipcie->reset_gpio, 1); if (hipcie->vpcie) regulator_disable(hipcie->vpcie); } -static int histb_pcie_host_enable(struct pcie_port *pp) +static int histb_pcie_host_enable(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct histb_pcie *hipcie = to_histb_pcie(pci); @@ -242,8 +232,8 @@ static int histb_pcie_host_enable(struct pcie_port *pp) } } - if (gpio_is_valid(hipcie->reset_gpio)) - gpio_set_value_cansleep(hipcie->reset_gpio, 1); + if (hipcie->reset_gpio) + gpiod_set_value_cansleep(hipcie->reset_gpio, 0); ret = clk_prepare_enable(hipcie->bus_clk); if (ret) { @@ -297,18 +287,15 @@ static const struct dw_pcie_ops dw_pcie_ops = { .read_dbi = histb_pcie_read_dbi, .write_dbi = histb_pcie_write_dbi, .link_up = histb_pcie_link_up, + .start_link = histb_pcie_start_link, }; static int histb_pcie_probe(struct platform_device *pdev) { struct histb_pcie *hipcie; struct dw_pcie *pci; - struct pcie_port *pp; - struct resource *res; - struct device_node *np = pdev->dev.of_node; + struct dw_pcie_rp *pp; struct device *dev = &pdev->dev; - enum of_gpio_flags of_flags; - unsigned long flag = GPIOF_DIR_OUT; int ret; hipcie = devm_kzalloc(dev, sizeof(*hipcie), GFP_KERNEL); @@ -324,15 +311,13 @@ static int histb_pcie_probe(struct platform_device *pdev) pci->dev = dev; pci->ops = &dw_pcie_ops; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "control"); - hipcie->ctrl = devm_ioremap_resource(dev, res); + hipcie->ctrl = devm_platform_ioremap_resource_byname(pdev, "control"); if (IS_ERR(hipcie->ctrl)) { dev_err(dev, "cannot get control reg base\n"); return PTR_ERR(hipcie->ctrl); } - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rc-dbi"); - pci->dbi_base = devm_ioremap_resource(dev, res); + pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "rc-dbi"); if (IS_ERR(pci->dbi_base)) { dev_err(dev, "cannot get rc-dbi base\n"); return PTR_ERR(pci->dbi_base); @@ -340,22 +325,24 @@ static int histb_pcie_probe(struct platform_device *pdev) hipcie->vpcie = devm_regulator_get_optional(dev, "vpcie"); if (IS_ERR(hipcie->vpcie)) { - if (PTR_ERR(hipcie->vpcie) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(hipcie->vpcie) != -ENODEV) + return PTR_ERR(hipcie->vpcie); hipcie->vpcie = NULL; } - hipcie->reset_gpio = of_get_named_gpio_flags(np, - "reset-gpios", 0, &of_flags); - if (of_flags & OF_GPIO_ACTIVE_LOW) - flag |= GPIOF_ACTIVE_LOW; - if (gpio_is_valid(hipcie->reset_gpio)) { - ret = devm_gpio_request_one(dev, hipcie->reset_gpio, - flag, "PCIe device power control"); - if (ret) { - dev_err(dev, "unable to request gpio\n"); - return ret; - } + hipcie->reset_gpio = devm_gpiod_get_optional(dev, "reset", + GPIOD_OUT_HIGH); + ret = PTR_ERR_OR_ZERO(hipcie->reset_gpio); + if (ret) { + dev_err(dev, "unable to request reset gpio: %d\n", ret); + return ret; + } + + ret = gpiod_set_consumer_name(hipcie->reset_gpio, + "PCIe device power control"); + if (ret) { + dev_err(dev, "unable to set reset gpio name: %d\n", ret); + return ret; } hipcie->aux_clk = devm_clk_get(dev, "aux"); @@ -400,14 +387,6 @@ static int histb_pcie_probe(struct platform_device *pdev) return PTR_ERR(hipcie->bus_reset); } - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq_byname(pdev, "msi"); - if (pp->msi_irq < 0) { - dev_err(dev, "Failed to get MSI IRQ\n"); - return pp->msi_irq; - } - } - hipcie->phy = devm_phy_get(dev, "phy"); if (IS_ERR(hipcie->phy)) { dev_info(dev, "no pcie-phy found\n"); @@ -427,28 +406,30 @@ static int histb_pcie_probe(struct platform_device *pdev) ret = histb_pcie_host_enable(pp); if (ret) { dev_err(dev, "failed to enable host\n"); - return ret; + goto err_exit_phy; } ret = dw_pcie_host_init(pp); if (ret) { dev_err(dev, "failed to initialize host\n"); - return ret; + goto err_exit_phy; } return 0; + +err_exit_phy: + phy_exit(hipcie->phy); + + return ret; } -static int histb_pcie_remove(struct platform_device *pdev) +static void histb_pcie_remove(struct platform_device *pdev) { struct histb_pcie *hipcie = platform_get_drvdata(pdev); histb_pcie_host_disable(hipcie); - if (hipcie->phy) - phy_exit(hipcie->phy); - - return 0; + phy_exit(hipcie->phy); } static const struct of_device_id histb_pcie_of_match[] = { @@ -459,7 +440,7 @@ MODULE_DEVICE_TABLE(of, histb_pcie_of_match); static struct platform_driver histb_pcie_platform_driver = { .probe = histb_pcie_probe, - .remove = histb_pcie_remove, + .remove = histb_pcie_remove, .driver = { .name = "histb-pcie", .of_match_table = histb_pcie_of_match, @@ -468,4 +449,3 @@ static struct platform_driver histb_pcie_platform_driver = { module_platform_driver(histb_pcie_platform_driver); MODULE_DESCRIPTION("HiSilicon STB PCIe host controller driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c new file mode 100644 index 000000000000..c21906eced61 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-intel-gw.c @@ -0,0 +1,447 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Intel Gateway SoCs + * + * Copyright (c) 2019 Intel Corporation. + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/iopoll.h> +#include <linux/mod_devicetable.h> +#include <linux/pci_regs.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/property.h> +#include <linux/reset.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +#define PORT_AFR_N_FTS_GEN12_DFT (SZ_128 - 1) +#define PORT_AFR_N_FTS_GEN3 180 +#define PORT_AFR_N_FTS_GEN4 196 + +/* PCIe Application logic Registers */ +#define PCIE_APP_CCR 0x10 +#define PCIE_APP_CCR_LTSSM_ENABLE BIT(0) + +#define PCIE_APP_MSG_CR 0x30 +#define PCIE_APP_MSG_XMT_PM_TURNOFF BIT(0) + +#define PCIE_APP_PMC 0x44 +#define PCIE_APP_PMC_IN_L2 BIT(20) + +#define PCIE_APP_IRNEN 0xF4 +#define PCIE_APP_IRNCR 0xF8 +#define PCIE_APP_IRN_AER_REPORT BIT(0) +#define PCIE_APP_IRN_PME BIT(2) +#define PCIE_APP_IRN_RX_VDM_MSG BIT(4) +#define PCIE_APP_IRN_PM_TO_ACK BIT(9) +#define PCIE_APP_IRN_LINK_AUTO_BW_STAT BIT(11) +#define PCIE_APP_IRN_BW_MGT BIT(12) +#define PCIE_APP_IRN_INTA BIT(13) +#define PCIE_APP_IRN_INTB BIT(14) +#define PCIE_APP_IRN_INTC BIT(15) +#define PCIE_APP_IRN_INTD BIT(16) +#define PCIE_APP_IRN_MSG_LTR BIT(18) +#define PCIE_APP_IRN_SYS_ERR_RC BIT(29) +#define PCIE_APP_INTX_OFST 12 + +#define PCIE_APP_IRN_INT \ + (PCIE_APP_IRN_AER_REPORT | PCIE_APP_IRN_PME | \ + PCIE_APP_IRN_RX_VDM_MSG | PCIE_APP_IRN_SYS_ERR_RC | \ + PCIE_APP_IRN_PM_TO_ACK | PCIE_APP_IRN_MSG_LTR | \ + PCIE_APP_IRN_BW_MGT | PCIE_APP_IRN_LINK_AUTO_BW_STAT | \ + PCIE_APP_IRN_INTA | PCIE_APP_IRN_INTB | \ + PCIE_APP_IRN_INTC | PCIE_APP_IRN_INTD) + +#define RESET_INTERVAL_MS 100 + +struct intel_pcie { + struct dw_pcie pci; + void __iomem *app_base; + struct gpio_desc *reset_gpio; + u32 rst_intrvl; + struct clk *core_clk; + struct reset_control *core_rst; + struct phy *phy; +}; + +static void pcie_update_bits(void __iomem *base, u32 ofs, u32 mask, u32 val) +{ + u32 old; + + old = readl(base + ofs); + val = (old & ~mask) | (val & mask); + + if (val != old) + writel(val, base + ofs); +} + +static inline void pcie_app_wr(struct intel_pcie *pcie, u32 ofs, u32 val) +{ + writel(val, pcie->app_base + ofs); +} + +static void pcie_app_wr_mask(struct intel_pcie *pcie, u32 ofs, + u32 mask, u32 val) +{ + pcie_update_bits(pcie->app_base, ofs, mask, val); +} + +static inline u32 pcie_rc_cfg_rd(struct intel_pcie *pcie, u32 ofs) +{ + return dw_pcie_readl_dbi(&pcie->pci, ofs); +} + +static inline void pcie_rc_cfg_wr(struct intel_pcie *pcie, u32 ofs, u32 val) +{ + dw_pcie_writel_dbi(&pcie->pci, ofs, val); +} + +static void pcie_rc_cfg_wr_mask(struct intel_pcie *pcie, u32 ofs, + u32 mask, u32 val) +{ + pcie_update_bits(pcie->pci.dbi_base, ofs, mask, val); +} + +static void intel_pcie_ltssm_enable(struct intel_pcie *pcie) +{ + pcie_app_wr_mask(pcie, PCIE_APP_CCR, PCIE_APP_CCR_LTSSM_ENABLE, + PCIE_APP_CCR_LTSSM_ENABLE); +} + +static void intel_pcie_ltssm_disable(struct intel_pcie *pcie) +{ + pcie_app_wr_mask(pcie, PCIE_APP_CCR, PCIE_APP_CCR_LTSSM_ENABLE, 0); +} + +static void intel_pcie_link_setup(struct intel_pcie *pcie) +{ + u32 val; + u8 offset = dw_pcie_find_capability(&pcie->pci, PCI_CAP_ID_EXP); + + val = pcie_rc_cfg_rd(pcie, offset + PCI_EXP_LNKCTL); + + val &= ~(PCI_EXP_LNKCTL_LD | PCI_EXP_LNKCTL_ASPMC); + pcie_rc_cfg_wr(pcie, offset + PCI_EXP_LNKCTL, val); +} + +static void intel_pcie_init_n_fts(struct dw_pcie *pci) +{ + switch (pci->max_link_speed) { + case 3: + pci->n_fts[1] = PORT_AFR_N_FTS_GEN3; + break; + case 4: + pci->n_fts[1] = PORT_AFR_N_FTS_GEN4; + break; + default: + pci->n_fts[1] = PORT_AFR_N_FTS_GEN12_DFT; + break; + } + pci->n_fts[0] = PORT_AFR_N_FTS_GEN12_DFT; +} + +static int intel_pcie_ep_rst_init(struct intel_pcie *pcie) +{ + struct device *dev = pcie->pci.dev; + int ret; + + pcie->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(pcie->reset_gpio)) { + ret = PTR_ERR(pcie->reset_gpio); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to request PCIe GPIO: %d\n", ret); + return ret; + } + + /* Make initial reset last for 100us */ + usleep_range(100, 200); + + return 0; +} + +static void intel_pcie_core_rst_assert(struct intel_pcie *pcie) +{ + reset_control_assert(pcie->core_rst); +} + +static void intel_pcie_core_rst_deassert(struct intel_pcie *pcie) +{ + /* + * One micro-second delay to make sure the reset pulse + * wide enough so that core reset is clean. + */ + udelay(1); + reset_control_deassert(pcie->core_rst); + + /* + * Some SoC core reset also reset PHY, more delay needed + * to make sure the reset process is done. + */ + usleep_range(1000, 2000); +} + +static void intel_pcie_device_rst_assert(struct intel_pcie *pcie) +{ + gpiod_set_value_cansleep(pcie->reset_gpio, 1); +} + +static void intel_pcie_device_rst_deassert(struct intel_pcie *pcie) +{ + msleep(pcie->rst_intrvl); + gpiod_set_value_cansleep(pcie->reset_gpio, 0); +} + +static void intel_pcie_core_irq_disable(struct intel_pcie *pcie) +{ + pcie_app_wr(pcie, PCIE_APP_IRNEN, 0); + pcie_app_wr(pcie, PCIE_APP_IRNCR, PCIE_APP_IRN_INT); +} + +static int intel_pcie_get_resources(struct platform_device *pdev) +{ + struct intel_pcie *pcie = platform_get_drvdata(pdev); + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pci->dev; + int ret; + + pcie->core_clk = devm_clk_get(dev, NULL); + if (IS_ERR(pcie->core_clk)) { + ret = PTR_ERR(pcie->core_clk); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get clks: %d\n", ret); + return ret; + } + + pcie->core_rst = devm_reset_control_get(dev, NULL); + if (IS_ERR(pcie->core_rst)) { + ret = PTR_ERR(pcie->core_rst); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get resets: %d\n", ret); + return ret; + } + + ret = device_property_read_u32(dev, "reset-assert-ms", + &pcie->rst_intrvl); + if (ret) + pcie->rst_intrvl = RESET_INTERVAL_MS; + + pcie->app_base = devm_platform_ioremap_resource_byname(pdev, "app"); + if (IS_ERR(pcie->app_base)) + return PTR_ERR(pcie->app_base); + + pcie->phy = devm_phy_get(dev, "pcie"); + if (IS_ERR(pcie->phy)) { + ret = PTR_ERR(pcie->phy); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Couldn't get pcie-phy: %d\n", ret); + return ret; + } + + return 0; +} + +static int intel_pcie_wait_l2(struct intel_pcie *pcie) +{ + u32 value; + int ret; + struct dw_pcie *pci = &pcie->pci; + + if (pci->max_link_speed < 3) + return 0; + + /* Send PME_TURN_OFF message */ + pcie_app_wr_mask(pcie, PCIE_APP_MSG_CR, PCIE_APP_MSG_XMT_PM_TURNOFF, + PCIE_APP_MSG_XMT_PM_TURNOFF); + + /* Read PMC status and wait for falling into L2 link state */ + ret = readl_poll_timeout(pcie->app_base + PCIE_APP_PMC, value, + value & PCIE_APP_PMC_IN_L2, 20, + jiffies_to_usecs(5 * HZ)); + if (ret) + dev_err(pcie->pci.dev, "PCIe link enter L2 timeout!\n"); + + return ret; +} + +static void intel_pcie_turn_off(struct intel_pcie *pcie) +{ + if (dw_pcie_link_up(&pcie->pci)) + intel_pcie_wait_l2(pcie); + + /* Put endpoint device in reset state */ + intel_pcie_device_rst_assert(pcie); + pcie_rc_cfg_wr_mask(pcie, PCI_COMMAND, PCI_COMMAND_MEMORY, 0); +} + +static int intel_pcie_host_setup(struct intel_pcie *pcie) +{ + int ret; + struct dw_pcie *pci = &pcie->pci; + + intel_pcie_core_rst_assert(pcie); + intel_pcie_device_rst_assert(pcie); + + ret = phy_init(pcie->phy); + if (ret) + return ret; + + intel_pcie_core_rst_deassert(pcie); + + ret = clk_prepare_enable(pcie->core_clk); + if (ret) { + dev_err(pcie->pci.dev, "Core clock enable failed: %d\n", ret); + goto clk_err; + } + + pci->atu_base = pci->dbi_base + 0xC0000; + + intel_pcie_ltssm_disable(pcie); + intel_pcie_link_setup(pcie); + intel_pcie_init_n_fts(pci); + + ret = dw_pcie_setup_rc(&pci->pp); + if (ret) + goto app_init_err; + + dw_pcie_upconfig_setup(pci); + + intel_pcie_device_rst_deassert(pcie); + intel_pcie_ltssm_enable(pcie); + + ret = dw_pcie_wait_for_link(pci); + if (ret) + goto app_init_err; + + /* Enable integrated interrupts */ + pcie_app_wr_mask(pcie, PCIE_APP_IRNEN, PCIE_APP_IRN_INT, + PCIE_APP_IRN_INT); + + return 0; + +app_init_err: + clk_disable_unprepare(pcie->core_clk); +clk_err: + intel_pcie_core_rst_assert(pcie); + phy_exit(pcie->phy); + + return ret; +} + +static void __intel_pcie_remove(struct intel_pcie *pcie) +{ + intel_pcie_core_irq_disable(pcie); + intel_pcie_turn_off(pcie); + clk_disable_unprepare(pcie->core_clk); + intel_pcie_core_rst_assert(pcie); + phy_exit(pcie->phy); +} + +static void intel_pcie_remove(struct platform_device *pdev) +{ + struct intel_pcie *pcie = platform_get_drvdata(pdev); + struct dw_pcie_rp *pp = &pcie->pci.pp; + + dw_pcie_host_deinit(pp); + __intel_pcie_remove(pcie); +} + +static int intel_pcie_suspend_noirq(struct device *dev) +{ + struct intel_pcie *pcie = dev_get_drvdata(dev); + int ret; + + intel_pcie_core_irq_disable(pcie); + ret = intel_pcie_wait_l2(pcie); + if (ret) + return ret; + + phy_exit(pcie->phy); + clk_disable_unprepare(pcie->core_clk); + return ret; +} + +static int intel_pcie_resume_noirq(struct device *dev) +{ + struct intel_pcie *pcie = dev_get_drvdata(dev); + + return intel_pcie_host_setup(pcie); +} + +static int intel_pcie_rc_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct intel_pcie *pcie = dev_get_drvdata(pci->dev); + + return intel_pcie_host_setup(pcie); +} + +static const struct dw_pcie_ops intel_pcie_ops = { +}; + +static const struct dw_pcie_host_ops intel_pcie_dw_ops = { + .init = intel_pcie_rc_init, +}; + +static int intel_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct intel_pcie *pcie; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + platform_set_drvdata(pdev, pcie); + pci = &pcie->pci; + pci->dev = dev; + pci->use_parent_dt_ranges = true; + pp = &pci->pp; + + ret = intel_pcie_get_resources(pdev); + if (ret) + return ret; + + ret = intel_pcie_ep_rst_init(pcie); + if (ret) + return ret; + + pci->ops = &intel_pcie_ops; + pp->ops = &intel_pcie_dw_ops; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "Cannot initialize host\n"); + return ret; + } + + return 0; +} + +static const struct dev_pm_ops intel_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pcie_suspend_noirq, + intel_pcie_resume_noirq) +}; + +static const struct of_device_id of_intel_pcie_match[] = { + { .compatible = "intel,lgm-pcie" }, + {} +}; + +static struct platform_driver intel_pcie_driver = { + .probe = intel_pcie_probe, + .remove = intel_pcie_remove, + .driver = { + .name = "intel-gw-pcie", + .of_match_table = of_intel_pcie_match, + .pm = &intel_pcie_pm_ops, + }, +}; +builtin_platform_driver(intel_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c new file mode 100644 index 000000000000..60e74ac782af --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-keembay.c @@ -0,0 +1,483 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PCIe controller driver for Intel Keem Bay + * Copyright (C) 2020 Intel Corporation + */ + +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/gpio/consumer.h> +#include <linux/init.h> +#include <linux/iopoll.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/kernel.h> +#include <linux/mod_devicetable.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/property.h> + +#include "pcie-designware.h" + +/* PCIE_REGS_APB_SLV Registers */ +#define PCIE_REGS_PCIE_CFG 0x0004 +#define PCIE_DEVICE_TYPE BIT(8) +#define PCIE_RSTN BIT(0) +#define PCIE_REGS_PCIE_APP_CNTRL 0x0008 +#define APP_LTSSM_ENABLE BIT(0) +#define PCIE_REGS_INTERRUPT_ENABLE 0x0028 +#define MSI_CTRL_INT_EN BIT(8) +#define EDMA_INT_EN GENMASK(7, 0) +#define PCIE_REGS_INTERRUPT_STATUS 0x002c +#define MSI_CTRL_INT BIT(8) +#define PCIE_REGS_PCIE_SII_PM_STATE 0x00b0 +#define SMLH_LINK_UP BIT(19) +#define RDLH_LINK_UP BIT(8) +#define PCIE_REGS_PCIE_SII_LINK_UP (SMLH_LINK_UP | RDLH_LINK_UP) +#define PCIE_REGS_PCIE_PHY_CNTL 0x0164 +#define PHY0_SRAM_BYPASS BIT(8) +#define PCIE_REGS_PCIE_PHY_STAT 0x0168 +#define PHY0_MPLLA_STATE BIT(1) +#define PCIE_REGS_LJPLL_STA 0x016c +#define LJPLL_LOCK BIT(0) +#define PCIE_REGS_LJPLL_CNTRL_0 0x0170 +#define LJPLL_EN BIT(29) +#define LJPLL_FOUT_EN GENMASK(24, 21) +#define PCIE_REGS_LJPLL_CNTRL_2 0x0178 +#define LJPLL_REF_DIV GENMASK(17, 12) +#define LJPLL_FB_DIV GENMASK(11, 0) +#define PCIE_REGS_LJPLL_CNTRL_3 0x017c +#define LJPLL_POST_DIV3A GENMASK(24, 22) +#define LJPLL_POST_DIV2A GENMASK(18, 16) + +#define PERST_DELAY_US 1000 +#define AUX_CLK_RATE_HZ 24000000 + +struct keembay_pcie { + struct dw_pcie pci; + void __iomem *apb_base; + enum dw_pcie_device_mode mode; + + struct clk *clk_master; + struct clk *clk_aux; + struct gpio_desc *reset; +}; + +struct keembay_pcie_of_data { + enum dw_pcie_device_mode mode; +}; + +static void keembay_ep_reset_assert(struct keembay_pcie *pcie) +{ + gpiod_set_value_cansleep(pcie->reset, 1); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); +} + +static void keembay_ep_reset_deassert(struct keembay_pcie *pcie) +{ + /* + * Ensure that PERST# is asserted for a minimum of 100ms. + * + * For more details, refer to PCI Express Card Electromechanical + * Specification Revision 1.1, Table-2.4. + */ + msleep(100); + + gpiod_set_value_cansleep(pcie->reset, 0); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); +} + +static void keembay_pcie_ltssm_set(struct keembay_pcie *pcie, bool enable) +{ + u32 val; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_APP_CNTRL); + if (enable) + val |= APP_LTSSM_ENABLE; + else + val &= ~APP_LTSSM_ENABLE; + writel(val, pcie->apb_base + PCIE_REGS_PCIE_APP_CNTRL); +} + +static bool keembay_pcie_link_up(struct dw_pcie *pci) +{ + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + u32 val; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_SII_PM_STATE); + + return (val & PCIE_REGS_PCIE_SII_LINK_UP) == PCIE_REGS_PCIE_SII_LINK_UP; +} + +static int keembay_pcie_start_link(struct dw_pcie *pci) +{ + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + u32 val; + int ret; + + if (pcie->mode == DW_PCIE_EP_TYPE) + return 0; + + keembay_pcie_ltssm_set(pcie, false); + + ret = readl_poll_timeout(pcie->apb_base + PCIE_REGS_PCIE_PHY_STAT, + val, val & PHY0_MPLLA_STATE, 20, + 500 * USEC_PER_MSEC); + if (ret) { + dev_err(pci->dev, "MPLLA is not locked\n"); + return ret; + } + + keembay_pcie_ltssm_set(pcie, true); + + return 0; +} + +static void keembay_pcie_stop_link(struct dw_pcie *pci) +{ + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + + keembay_pcie_ltssm_set(pcie, false); +} + +static const struct dw_pcie_ops keembay_pcie_ops = { + .link_up = keembay_pcie_link_up, + .start_link = keembay_pcie_start_link, + .stop_link = keembay_pcie_stop_link, +}; + +static inline void keembay_pcie_disable_clock(void *data) +{ + struct clk *clk = data; + + clk_disable_unprepare(clk); +} + +static inline struct clk *keembay_pcie_probe_clock(struct device *dev, + const char *id, u64 rate) +{ + struct clk *clk; + int ret; + + clk = devm_clk_get(dev, id); + if (IS_ERR(clk)) + return clk; + + if (rate) { + ret = clk_set_rate(clk, rate); + if (ret) + return ERR_PTR(ret); + } + + ret = clk_prepare_enable(clk); + if (ret) + return ERR_PTR(ret); + + ret = devm_add_action_or_reset(dev, keembay_pcie_disable_clock, clk); + if (ret) + return ERR_PTR(ret); + + return clk; +} + +static int keembay_pcie_probe_clocks(struct keembay_pcie *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pci->dev; + + pcie->clk_master = keembay_pcie_probe_clock(dev, "master", 0); + if (IS_ERR(pcie->clk_master)) + return dev_err_probe(dev, PTR_ERR(pcie->clk_master), + "Failed to enable master clock"); + + pcie->clk_aux = keembay_pcie_probe_clock(dev, "aux", AUX_CLK_RATE_HZ); + if (IS_ERR(pcie->clk_aux)) + return dev_err_probe(dev, PTR_ERR(pcie->clk_aux), + "Failed to enable auxiliary clock"); + + return 0; +} + +/* + * Initialize the internal PCIe PLL in Host mode. + * See the following sections in Keem Bay data book, + * (1) 6.4.6.1 PCIe Subsystem Example Initialization, + * (2) 6.8 PCIe Low Jitter PLL for Ref Clk Generation. + */ +static int keembay_pcie_pll_init(struct keembay_pcie *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + u32 val; + int ret; + + val = FIELD_PREP(LJPLL_REF_DIV, 0) | FIELD_PREP(LJPLL_FB_DIV, 0x32); + writel(val, pcie->apb_base + PCIE_REGS_LJPLL_CNTRL_2); + + val = FIELD_PREP(LJPLL_POST_DIV3A, 0x2) | + FIELD_PREP(LJPLL_POST_DIV2A, 0x2); + writel(val, pcie->apb_base + PCIE_REGS_LJPLL_CNTRL_3); + + val = FIELD_PREP(LJPLL_EN, 0x1) | FIELD_PREP(LJPLL_FOUT_EN, 0xc); + writel(val, pcie->apb_base + PCIE_REGS_LJPLL_CNTRL_0); + + ret = readl_poll_timeout(pcie->apb_base + PCIE_REGS_LJPLL_STA, + val, val & LJPLL_LOCK, 20, + 500 * USEC_PER_MSEC); + if (ret) + dev_err(pci->dev, "Low jitter PLL is not locked\n"); + + return ret; +} + +static void keembay_pcie_msi_irq_handler(struct irq_desc *desc) +{ + struct keembay_pcie *pcie = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + u32 val, mask, status; + struct dw_pcie_rp *pp; + + /* + * Keem Bay PCIe Controller provides an additional IP logic on top of + * standard DWC IP to clear MSI IRQ by writing '1' to the respective + * bit of the status register. + * + * So, a chained irq handler is defined to handle this additional + * IP logic. + */ + + chained_irq_enter(chip, desc); + + pp = &pcie->pci.pp; + val = readl(pcie->apb_base + PCIE_REGS_INTERRUPT_STATUS); + mask = readl(pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); + + status = val & mask; + + if (status & MSI_CTRL_INT) { + dw_handle_msi_irq(pp); + writel(status, pcie->apb_base + PCIE_REGS_INTERRUPT_STATUS); + } + + chained_irq_exit(chip, desc); +} + +static int keembay_pcie_setup_msi_irq(struct keembay_pcie *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + int irq; + + irq = platform_get_irq_byname(pdev, "pcie"); + if (irq < 0) + return irq; + + irq_set_chained_handler_and_data(irq, keembay_pcie_msi_irq_handler, + pcie); + + return 0; +} + +static void keembay_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + + writel(EDMA_INT_EN, pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); +} + +static int keembay_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + unsigned int type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_IRQ_INTX: + /* INTx interrupts are not supported in Keem Bay */ + dev_err(pci->dev, "INTx IRQ is not supported\n"); + return -EINVAL; + case PCI_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + case PCI_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "Unknown IRQ type %d\n", type); + return -EINVAL; + } +} + +static const struct pci_epc_features keembay_pcie_epc_features = { + .msi_capable = true, + .msix_capable = true, + .bar[BAR_0] = { .only_64bit = true, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .only_64bit = true, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .only_64bit = true, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + .align = SZ_16K, +}; + +static const struct pci_epc_features * +keembay_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &keembay_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops keembay_pcie_ep_ops = { + .init = keembay_pcie_ep_init, + .raise_irq = keembay_pcie_ep_raise_irq, + .get_features = keembay_pcie_get_features, +}; + +static const struct dw_pcie_host_ops keembay_pcie_host_ops = { +}; + +static int keembay_pcie_add_pcie_port(struct keembay_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + u32 val; + int ret; + + pp->ops = &keembay_pcie_host_ops; + pp->msi_irq[0] = -ENODEV; + + ret = keembay_pcie_setup_msi_irq(pcie); + if (ret) + return ret; + + pcie->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(pcie->reset)) + return PTR_ERR(pcie->reset); + + ret = keembay_pcie_probe_clocks(pcie); + if (ret) + return ret; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_PHY_CNTL); + val |= PHY0_SRAM_BYPASS; + writel(val, pcie->apb_base + PCIE_REGS_PCIE_PHY_CNTL); + + writel(PCIE_DEVICE_TYPE, pcie->apb_base + PCIE_REGS_PCIE_CFG); + + ret = keembay_pcie_pll_init(pcie); + if (ret) + return ret; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_CFG); + writel(val | PCIE_RSTN, pcie->apb_base + PCIE_REGS_PCIE_CFG); + keembay_ep_reset_deassert(pcie); + + ret = dw_pcie_host_init(pp); + if (ret) { + keembay_ep_reset_assert(pcie); + dev_err(dev, "Failed to initialize host: %d\n", ret); + return ret; + } + + val = readl(pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); + if (IS_ENABLED(CONFIG_PCI_MSI)) + val |= MSI_CTRL_INT_EN; + writel(val, pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); + + return 0; +} + +static int keembay_pcie_probe(struct platform_device *pdev) +{ + const struct keembay_pcie_of_data *data; + struct device *dev = &pdev->dev; + struct keembay_pcie *pcie; + struct dw_pcie *pci; + enum dw_pcie_device_mode mode; + int ret; + + data = device_get_match_data(dev); + if (!data) + return -ENODEV; + + mode = (enum dw_pcie_device_mode)data->mode; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = &pcie->pci; + pci->dev = dev; + pci->ops = &keembay_pcie_ops; + + pcie->mode = mode; + + pcie->apb_base = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(pcie->apb_base)) + return PTR_ERR(pcie->apb_base); + + platform_set_drvdata(pdev, pcie); + + switch (pcie->mode) { + case DW_PCIE_RC_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_KEEMBAY_HOST)) + return -ENODEV; + + return keembay_pcie_add_pcie_port(pcie, pdev); + case DW_PCIE_EP_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_KEEMBAY_EP)) + return -ENODEV; + + pci->ep.ops = &keembay_pcie_ep_ops; + ret = dw_pcie_ep_init(&pci->ep); + if (ret) + return ret; + + ret = dw_pcie_ep_init_registers(&pci->ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(&pci->ep); + return ret; + } + + pci_epc_init_notify(pci->ep.epc); + + break; + default: + dev_err(dev, "Invalid device type %d\n", pcie->mode); + return -ENODEV; + } + + return 0; +} + +static const struct keembay_pcie_of_data keembay_pcie_rc_of_data = { + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct keembay_pcie_of_data keembay_pcie_ep_of_data = { + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct of_device_id keembay_pcie_of_match[] = { + { + .compatible = "intel,keembay-pcie", + .data = &keembay_pcie_rc_of_data, + }, + { + .compatible = "intel,keembay-pcie-ep", + .data = &keembay_pcie_ep_of_data, + }, + {} +}; + +static struct platform_driver keembay_pcie_driver = { + .driver = { + .name = "keembay-pcie", + .of_match_table = keembay_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = keembay_pcie_probe, +}; +builtin_platform_driver(keembay_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c index 9b599296205d..91559c8b1866 100644 --- a/drivers/pci/controller/dwc/pcie-kirin.c +++ b/drivers/pci/controller/dwc/pcie-kirin.c @@ -2,22 +2,22 @@ /* * PCIe host controller driver for Kirin Phone SoCs * - * Copyright (C) 2017 Hilisicon Electronics Co., Ltd. - * http://www.huawei.com + * Copyright (C) 2017 HiSilicon Electronics Co., Ltd. + * https://www.huawei.com * * Author: Xiaowei Song <songxiaowei@huawei.com> */ -#include <linux/compiler.h> #include <linux/clk.h> +#include <linux/compiler.h> #include <linux/delay.h> #include <linux/err.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/mfd/syscon.h> -#include <linux/of_address.h> -#include <linux/of_gpio.h> +#include <linux/of.h> #include <linux/of_pci.h> +#include <linux/phy/phy.h> #include <linux/pci.h> #include <linux/pci_regs.h> #include <linux/platform_device.h> @@ -28,26 +28,16 @@ #define to_kirin_pcie(x) dev_get_drvdata((x)->dev) -#define REF_CLK_FREQ 100000000 - /* PCIe ELBI registers */ #define SOC_PCIECTRL_CTRL0_ADDR 0x000 #define SOC_PCIECTRL_CTRL1_ADDR 0x004 -#define SOC_PCIEPHY_CTRL2_ADDR 0x008 -#define SOC_PCIEPHY_CTRL3_ADDR 0x00c #define PCIE_ELBI_SLV_DBI_ENABLE (0x1 << 21) /* info located in APB */ #define PCIE_APP_LTSSM_ENABLE 0x01c -#define PCIE_APB_PHY_CTRL0 0x0 -#define PCIE_APB_PHY_CTRL1 0x4 #define PCIE_APB_PHY_STATUS0 0x400 #define PCIE_LINKUP_ENABLE (0x8020) #define PCIE_LTSSM_ENABLE_BIT (0x1 << 11) -#define PIPE_CLK_STABLE (0x1 << 19) -#define PHY_REF_PAD_BIT (0x1 << 8) -#define PHY_PWR_DOWN_BIT (0x1 << 22) -#define PHY_RST_ACK_BIT (0x1 << 16) /* info located in sysctrl */ #define SCTRL_PCIE_CMOS_OFFSET 0x60 @@ -60,17 +50,70 @@ #define PCIE_DEBOUNCE_PARAM 0xF0F400 #define PCIE_OE_BYPASS (0x3 << 28) +/* + * Max number of connected PCI slots at an external PCI bridge + * + * This is used on HiKey 970, which has a PEX 8606 bridge with 4 connected + * lanes (lane 0 upstream, and the other three lanes, one connected to an + * in-board Ethernet adapter and the other two connected to M.2 and mini + * PCI slots. + * + * Each slot has a different clock source and uses a separate PERST# pin. + */ +#define MAX_PCI_SLOTS 3 + +enum pcie_kirin_phy_type { + PCIE_KIRIN_INTERNAL_PHY, + PCIE_KIRIN_EXTERNAL_PHY +}; + +struct kirin_pcie { + enum pcie_kirin_phy_type type; + + struct dw_pcie *pci; + struct regmap *apb; + struct phy *phy; + void *phy_priv; /* only for PCIE_KIRIN_INTERNAL_PHY */ + + /* DWC PERST# */ + struct gpio_desc *id_dwc_perst_gpio; + + /* Per-slot PERST# */ + int num_slots; + struct gpio_desc *id_reset_gpio[MAX_PCI_SLOTS]; + const char *reset_names[MAX_PCI_SLOTS]; + + /* Per-slot clkreq */ + int n_gpio_clkreq; + struct gpio_desc *id_clkreq_gpio[MAX_PCI_SLOTS]; + const char *clkreq_names[MAX_PCI_SLOTS]; +}; + +/* + * Kirin 960 PHY. Can't be split into a PHY driver without changing the + * DT schema. + */ + +#define REF_CLK_FREQ 100000000 + +/* PHY info located in APB */ +#define PCIE_APB_PHY_CTRL0 0x0 +#define PCIE_APB_PHY_CTRL1 0x4 +#define PCIE_APB_PHY_STATUS0 0x400 +#define PIPE_CLK_STABLE BIT(19) +#define PHY_REF_PAD_BIT BIT(8) +#define PHY_PWR_DOWN_BIT BIT(22) +#define PHY_RST_ACK_BIT BIT(16) + /* peri_crg ctrl */ #define CRGCTRL_PCIE_ASSERT_OFFSET 0x88 #define CRGCTRL_PCIE_ASSERT_BIT 0x8c000000 /* Time for delay */ -#define REF_2_PERST_MIN 20000 +#define REF_2_PERST_MIN 21000 #define REF_2_PERST_MAX 25000 #define PERST_2_ACCESS_MIN 10000 #define PERST_2_ACCESS_MAX 12000 -#define LINK_WAIT_MIN 900 -#define LINK_WAIT_MAX 1000 #define PIPE_CLK_WAIT_MIN 550 #define PIPE_CLK_WAIT_MAX 600 #define TIME_CMOS_MIN 100 @@ -78,233 +121,366 @@ #define TIME_PHY_PD_MIN 10 #define TIME_PHY_PD_MAX 11 -struct kirin_pcie { - struct dw_pcie *pci; - void __iomem *apb_base; - void __iomem *phy_base; +struct hi3660_pcie_phy { + struct device *dev; + void __iomem *base; struct regmap *crgctrl; struct regmap *sysctrl; struct clk *apb_sys_clk; struct clk *apb_phy_clk; struct clk *phy_ref_clk; - struct clk *pcie_aclk; - struct clk *pcie_aux_clk; - int gpio_id_reset; + struct clk *aclk; + struct clk *aux_clk; }; -/* Registers in PCIeCTRL */ -static inline void kirin_apb_ctrl_writel(struct kirin_pcie *kirin_pcie, - u32 val, u32 reg) -{ - writel(val, kirin_pcie->apb_base + reg); -} - -static inline u32 kirin_apb_ctrl_readl(struct kirin_pcie *kirin_pcie, u32 reg) -{ - return readl(kirin_pcie->apb_base + reg); -} - /* Registers in PCIePHY */ -static inline void kirin_apb_phy_writel(struct kirin_pcie *kirin_pcie, +static inline void kirin_apb_phy_writel(struct hi3660_pcie_phy *hi3660_pcie_phy, u32 val, u32 reg) { - writel(val, kirin_pcie->phy_base + reg); + writel(val, hi3660_pcie_phy->base + reg); } -static inline u32 kirin_apb_phy_readl(struct kirin_pcie *kirin_pcie, u32 reg) +static inline u32 kirin_apb_phy_readl(struct hi3660_pcie_phy *hi3660_pcie_phy, + u32 reg) { - return readl(kirin_pcie->phy_base + reg); + return readl(hi3660_pcie_phy->base + reg); } -static long kirin_pcie_get_clk(struct kirin_pcie *kirin_pcie, - struct platform_device *pdev) +static int hi3660_pcie_phy_get_clk(struct hi3660_pcie_phy *phy) { - struct device *dev = &pdev->dev; + struct device *dev = phy->dev; - kirin_pcie->phy_ref_clk = devm_clk_get(dev, "pcie_phy_ref"); - if (IS_ERR(kirin_pcie->phy_ref_clk)) - return PTR_ERR(kirin_pcie->phy_ref_clk); + phy->phy_ref_clk = devm_clk_get(dev, "pcie_phy_ref"); + if (IS_ERR(phy->phy_ref_clk)) + return PTR_ERR(phy->phy_ref_clk); - kirin_pcie->pcie_aux_clk = devm_clk_get(dev, "pcie_aux"); - if (IS_ERR(kirin_pcie->pcie_aux_clk)) - return PTR_ERR(kirin_pcie->pcie_aux_clk); + phy->aux_clk = devm_clk_get(dev, "pcie_aux"); + if (IS_ERR(phy->aux_clk)) + return PTR_ERR(phy->aux_clk); - kirin_pcie->apb_phy_clk = devm_clk_get(dev, "pcie_apb_phy"); - if (IS_ERR(kirin_pcie->apb_phy_clk)) - return PTR_ERR(kirin_pcie->apb_phy_clk); + phy->apb_phy_clk = devm_clk_get(dev, "pcie_apb_phy"); + if (IS_ERR(phy->apb_phy_clk)) + return PTR_ERR(phy->apb_phy_clk); - kirin_pcie->apb_sys_clk = devm_clk_get(dev, "pcie_apb_sys"); - if (IS_ERR(kirin_pcie->apb_sys_clk)) - return PTR_ERR(kirin_pcie->apb_sys_clk); + phy->apb_sys_clk = devm_clk_get(dev, "pcie_apb_sys"); + if (IS_ERR(phy->apb_sys_clk)) + return PTR_ERR(phy->apb_sys_clk); - kirin_pcie->pcie_aclk = devm_clk_get(dev, "pcie_aclk"); - if (IS_ERR(kirin_pcie->pcie_aclk)) - return PTR_ERR(kirin_pcie->pcie_aclk); + phy->aclk = devm_clk_get(dev, "pcie_aclk"); + if (IS_ERR(phy->aclk)) + return PTR_ERR(phy->aclk); return 0; } -static long kirin_pcie_get_resource(struct kirin_pcie *kirin_pcie, - struct platform_device *pdev) +static int hi3660_pcie_phy_get_resource(struct hi3660_pcie_phy *phy) { - struct device *dev = &pdev->dev; - struct resource *apb; - struct resource *phy; - struct resource *dbi; - - apb = platform_get_resource_byname(pdev, IORESOURCE_MEM, "apb"); - kirin_pcie->apb_base = devm_ioremap_resource(dev, apb); - if (IS_ERR(kirin_pcie->apb_base)) - return PTR_ERR(kirin_pcie->apb_base); - - phy = platform_get_resource_byname(pdev, IORESOURCE_MEM, "phy"); - kirin_pcie->phy_base = devm_ioremap_resource(dev, phy); - if (IS_ERR(kirin_pcie->phy_base)) - return PTR_ERR(kirin_pcie->phy_base); - - dbi = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); - kirin_pcie->pci->dbi_base = devm_ioremap_resource(dev, dbi); - if (IS_ERR(kirin_pcie->pci->dbi_base)) - return PTR_ERR(kirin_pcie->pci->dbi_base); - - kirin_pcie->crgctrl = - syscon_regmap_lookup_by_compatible("hisilicon,hi3660-crgctrl"); - if (IS_ERR(kirin_pcie->crgctrl)) - return PTR_ERR(kirin_pcie->crgctrl); - - kirin_pcie->sysctrl = - syscon_regmap_lookup_by_compatible("hisilicon,hi3660-sctrl"); - if (IS_ERR(kirin_pcie->sysctrl)) - return PTR_ERR(kirin_pcie->sysctrl); + struct device *dev = phy->dev; + struct platform_device *pdev; + + /* registers */ + pdev = container_of(dev, struct platform_device, dev); + + phy->base = devm_platform_ioremap_resource_byname(pdev, "phy"); + if (IS_ERR(phy->base)) + return PTR_ERR(phy->base); + + phy->crgctrl = syscon_regmap_lookup_by_compatible("hisilicon,hi3660-crgctrl"); + if (IS_ERR(phy->crgctrl)) + return PTR_ERR(phy->crgctrl); + + phy->sysctrl = syscon_regmap_lookup_by_compatible("hisilicon,hi3660-sctrl"); + if (IS_ERR(phy->sysctrl)) + return PTR_ERR(phy->sysctrl); return 0; } -static int kirin_pcie_phy_init(struct kirin_pcie *kirin_pcie) +static int hi3660_pcie_phy_start(struct hi3660_pcie_phy *phy) { - struct device *dev = kirin_pcie->pci->dev; + struct device *dev = phy->dev; u32 reg_val; - reg_val = kirin_apb_phy_readl(kirin_pcie, PCIE_APB_PHY_CTRL1); + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_CTRL1); reg_val &= ~PHY_REF_PAD_BIT; - kirin_apb_phy_writel(kirin_pcie, reg_val, PCIE_APB_PHY_CTRL1); + kirin_apb_phy_writel(phy, reg_val, PCIE_APB_PHY_CTRL1); - reg_val = kirin_apb_phy_readl(kirin_pcie, PCIE_APB_PHY_CTRL0); + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_CTRL0); reg_val &= ~PHY_PWR_DOWN_BIT; - kirin_apb_phy_writel(kirin_pcie, reg_val, PCIE_APB_PHY_CTRL0); + kirin_apb_phy_writel(phy, reg_val, PCIE_APB_PHY_CTRL0); usleep_range(TIME_PHY_PD_MIN, TIME_PHY_PD_MAX); - reg_val = kirin_apb_phy_readl(kirin_pcie, PCIE_APB_PHY_CTRL1); + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_CTRL1); reg_val &= ~PHY_RST_ACK_BIT; - kirin_apb_phy_writel(kirin_pcie, reg_val, PCIE_APB_PHY_CTRL1); + kirin_apb_phy_writel(phy, reg_val, PCIE_APB_PHY_CTRL1); usleep_range(PIPE_CLK_WAIT_MIN, PIPE_CLK_WAIT_MAX); - reg_val = kirin_apb_phy_readl(kirin_pcie, PCIE_APB_PHY_STATUS0); - if (reg_val & PIPE_CLK_STABLE) { - dev_err(dev, "PIPE clk is not stable\n"); - return -EINVAL; - } + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_STATUS0); + if (reg_val & PIPE_CLK_STABLE) + return dev_err_probe(dev, -ETIMEDOUT, + "PIPE clk is not stable\n"); return 0; } -static void kirin_pcie_oe_enable(struct kirin_pcie *kirin_pcie) +static void hi3660_pcie_phy_oe_enable(struct hi3660_pcie_phy *phy) { u32 val; - regmap_read(kirin_pcie->sysctrl, SCTRL_PCIE_OE_OFFSET, &val); + regmap_read(phy->sysctrl, SCTRL_PCIE_OE_OFFSET, &val); val |= PCIE_DEBOUNCE_PARAM; val &= ~PCIE_OE_BYPASS; - regmap_write(kirin_pcie->sysctrl, SCTRL_PCIE_OE_OFFSET, val); + regmap_write(phy->sysctrl, SCTRL_PCIE_OE_OFFSET, val); } -static int kirin_pcie_clk_ctrl(struct kirin_pcie *kirin_pcie, bool enable) +static int hi3660_pcie_phy_clk_ctrl(struct hi3660_pcie_phy *phy, bool enable) { int ret = 0; if (!enable) goto close_clk; - ret = clk_set_rate(kirin_pcie->phy_ref_clk, REF_CLK_FREQ); + ret = clk_set_rate(phy->phy_ref_clk, REF_CLK_FREQ); if (ret) return ret; - ret = clk_prepare_enable(kirin_pcie->phy_ref_clk); + ret = clk_prepare_enable(phy->phy_ref_clk); if (ret) return ret; - ret = clk_prepare_enable(kirin_pcie->apb_sys_clk); + ret = clk_prepare_enable(phy->apb_sys_clk); if (ret) goto apb_sys_fail; - ret = clk_prepare_enable(kirin_pcie->apb_phy_clk); + ret = clk_prepare_enable(phy->apb_phy_clk); if (ret) goto apb_phy_fail; - ret = clk_prepare_enable(kirin_pcie->pcie_aclk); + ret = clk_prepare_enable(phy->aclk); if (ret) goto aclk_fail; - ret = clk_prepare_enable(kirin_pcie->pcie_aux_clk); + ret = clk_prepare_enable(phy->aux_clk); if (ret) goto aux_clk_fail; return 0; close_clk: - clk_disable_unprepare(kirin_pcie->pcie_aux_clk); + clk_disable_unprepare(phy->aux_clk); aux_clk_fail: - clk_disable_unprepare(kirin_pcie->pcie_aclk); + clk_disable_unprepare(phy->aclk); aclk_fail: - clk_disable_unprepare(kirin_pcie->apb_phy_clk); + clk_disable_unprepare(phy->apb_phy_clk); apb_phy_fail: - clk_disable_unprepare(kirin_pcie->apb_sys_clk); + clk_disable_unprepare(phy->apb_sys_clk); apb_sys_fail: - clk_disable_unprepare(kirin_pcie->phy_ref_clk); + clk_disable_unprepare(phy->phy_ref_clk); return ret; } -static int kirin_pcie_power_on(struct kirin_pcie *kirin_pcie) +static int hi3660_pcie_phy_power_on(struct kirin_pcie *pcie) { + struct hi3660_pcie_phy *phy = pcie->phy_priv; int ret; /* Power supply for Host */ - regmap_write(kirin_pcie->sysctrl, + regmap_write(phy->sysctrl, SCTRL_PCIE_CMOS_OFFSET, SCTRL_PCIE_CMOS_BIT); usleep_range(TIME_CMOS_MIN, TIME_CMOS_MAX); - kirin_pcie_oe_enable(kirin_pcie); - ret = kirin_pcie_clk_ctrl(kirin_pcie, true); + hi3660_pcie_phy_oe_enable(phy); + + ret = hi3660_pcie_phy_clk_ctrl(phy, true); if (ret) return ret; /* ISO disable, PCIeCtrl, PHY assert and clk gate clear */ - regmap_write(kirin_pcie->sysctrl, + regmap_write(phy->sysctrl, SCTRL_PCIE_ISO_OFFSET, SCTRL_PCIE_ISO_BIT); - regmap_write(kirin_pcie->crgctrl, + regmap_write(phy->crgctrl, CRGCTRL_PCIE_ASSERT_OFFSET, CRGCTRL_PCIE_ASSERT_BIT); - regmap_write(kirin_pcie->sysctrl, + regmap_write(phy->sysctrl, SCTRL_PCIE_HPCLK_OFFSET, SCTRL_PCIE_HPCLK_BIT); - ret = kirin_pcie_phy_init(kirin_pcie); + ret = hi3660_pcie_phy_start(phy); if (ret) - goto close_clk; + goto disable_clks; - /* perst assert Endpoint */ - if (!gpio_request(kirin_pcie->gpio_id_reset, "pcie_perst")) { - usleep_range(REF_2_PERST_MIN, REF_2_PERST_MAX); - ret = gpio_direction_output(kirin_pcie->gpio_id_reset, 1); - if (ret) - goto close_clk; - usleep_range(PERST_2_ACCESS_MIN, PERST_2_ACCESS_MAX); + return 0; +disable_clks: + hi3660_pcie_phy_clk_ctrl(phy, false); + return ret; +} + +static int hi3660_pcie_phy_init(struct platform_device *pdev, + struct kirin_pcie *pcie) +{ + struct device *dev = &pdev->dev; + struct hi3660_pcie_phy *phy; + int ret; + + phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL); + if (!phy) + return -ENOMEM; + + pcie->phy_priv = phy; + phy->dev = dev; + + ret = hi3660_pcie_phy_get_clk(phy); + if (ret) + return ret; + + return hi3660_pcie_phy_get_resource(phy); +} + +static int hi3660_pcie_phy_power_off(struct kirin_pcie *pcie) +{ + struct hi3660_pcie_phy *phy = pcie->phy_priv; + + /* Drop power supply for Host */ + regmap_write(phy->sysctrl, SCTRL_PCIE_CMOS_OFFSET, 0x00); + + hi3660_pcie_phy_clk_ctrl(phy, false); + + return 0; +} + +/* + * The non-PHY part starts here + */ + +static const struct regmap_config pcie_kirin_regmap_conf = { + .name = "kirin_pcie_apb", + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, +}; + +static int kirin_pcie_get_gpio_enable(struct kirin_pcie *pcie, + struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + int ret, i; + + /* This is an optional property */ + ret = gpiod_count(dev, "hisilicon,clken"); + if (ret < 0) return 0; + + if (ret > MAX_PCI_SLOTS) + return dev_err_probe(dev, -EINVAL, + "Too many GPIO clock requests!\n"); + + pcie->n_gpio_clkreq = ret; + + for (i = 0; i < pcie->n_gpio_clkreq; i++) { + pcie->id_clkreq_gpio[i] = devm_gpiod_get_index(dev, + "hisilicon,clken", i, + GPIOD_OUT_LOW); + if (IS_ERR(pcie->id_clkreq_gpio[i])) + return dev_err_probe(dev, PTR_ERR(pcie->id_clkreq_gpio[i]), + "unable to get a valid clken gpio\n"); + + pcie->clkreq_names[i] = devm_kasprintf(dev, GFP_KERNEL, + "pcie_clkreq_%d", i); + if (!pcie->clkreq_names[i]) + return -ENOMEM; + + gpiod_set_consumer_name(pcie->id_clkreq_gpio[i], + pcie->clkreq_names[i]); } -close_clk: - kirin_pcie_clk_ctrl(kirin_pcie, false); - return ret; + return 0; +} + +static int kirin_pcie_parse_port(struct kirin_pcie *pcie, + struct platform_device *pdev, + struct device_node *node) +{ + struct device *dev = &pdev->dev; + int ret, slot, i; + + for_each_available_child_of_node_scoped(node, parent) { + for_each_available_child_of_node_scoped(parent, child) { + i = pcie->num_slots; + + pcie->id_reset_gpio[i] = devm_fwnode_gpiod_get_index(dev, + of_fwnode_handle(child), + "reset", 0, GPIOD_OUT_LOW, + NULL); + if (IS_ERR(pcie->id_reset_gpio[i])) { + if (PTR_ERR(pcie->id_reset_gpio[i]) == -ENOENT) + continue; + return dev_err_probe(dev, PTR_ERR(pcie->id_reset_gpio[i]), + "unable to get a valid reset gpio\n"); + } + + if (pcie->num_slots + 1 >= MAX_PCI_SLOTS) + return dev_err_probe(dev, -EINVAL, + "Too many PCI slots!\n"); + + pcie->num_slots++; + + ret = of_pci_get_devfn(child); + if (ret < 0) + return dev_err_probe(dev, ret, + "failed to parse devfn\n"); + + slot = PCI_SLOT(ret); + + pcie->reset_names[i] = devm_kasprintf(dev, GFP_KERNEL, + "pcie_perst_%d", + slot); + if (!pcie->reset_names[i]) + return -ENOMEM; + + gpiod_set_consumer_name(pcie->id_reset_gpio[i], + pcie->reset_names[i]); + } + } + + return 0; +} + +static long kirin_pcie_get_resource(struct kirin_pcie *kirin_pcie, + struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + void __iomem *apb_base; + int ret; + + apb_base = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(apb_base)) + return PTR_ERR(apb_base); + + kirin_pcie->apb = devm_regmap_init_mmio(dev, apb_base, + &pcie_kirin_regmap_conf); + if (IS_ERR(kirin_pcie->apb)) + return PTR_ERR(kirin_pcie->apb); + + /* pcie internal PERST# gpio */ + kirin_pcie->id_dwc_perst_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(kirin_pcie->id_dwc_perst_gpio)) + return dev_err_probe(dev, PTR_ERR(kirin_pcie->id_dwc_perst_gpio), + "unable to get a valid gpio pin\n"); + gpiod_set_consumer_name(kirin_pcie->id_dwc_perst_gpio, "pcie_perst_bridge"); + + ret = kirin_pcie_get_gpio_enable(kirin_pcie, pdev); + if (ret) + return ret; + + /* Parse OF children */ + for_each_available_child_of_node_scoped(node, child) { + ret = kirin_pcie_parse_port(kirin_pcie, pdev, child); + if (ret) + return ret; + } + + return 0; } static void kirin_pcie_sideband_dbi_w_mode(struct kirin_pcie *kirin_pcie, @@ -312,13 +488,13 @@ static void kirin_pcie_sideband_dbi_w_mode(struct kirin_pcie *kirin_pcie, { u32 val; - val = kirin_apb_ctrl_readl(kirin_pcie, SOC_PCIECTRL_CTRL0_ADDR); + regmap_read(kirin_pcie->apb, SOC_PCIECTRL_CTRL0_ADDR, &val); if (on) val = val | PCIE_ELBI_SLV_DBI_ENABLE; else val = val & ~PCIE_ELBI_SLV_DBI_ENABLE; - kirin_apb_ctrl_writel(kirin_pcie, val, SOC_PCIECTRL_CTRL0_ADDR); + regmap_write(kirin_pcie->apb, SOC_PCIECTRL_CTRL0_ADDR, val); } static void kirin_pcie_sideband_dbi_r_mode(struct kirin_pcie *kirin_pcie, @@ -326,43 +502,67 @@ static void kirin_pcie_sideband_dbi_r_mode(struct kirin_pcie *kirin_pcie, { u32 val; - val = kirin_apb_ctrl_readl(kirin_pcie, SOC_PCIECTRL_CTRL1_ADDR); + regmap_read(kirin_pcie->apb, SOC_PCIECTRL_CTRL1_ADDR, &val); if (on) val = val | PCIE_ELBI_SLV_DBI_ENABLE; else val = val & ~PCIE_ELBI_SLV_DBI_ENABLE; - kirin_apb_ctrl_writel(kirin_pcie, val, SOC_PCIECTRL_CTRL1_ADDR); + regmap_write(kirin_pcie->apb, SOC_PCIECTRL_CTRL1_ADDR, val); } -static int kirin_pcie_rd_own_conf(struct pcie_port *pp, +static int kirin_pcie_rd_own_conf(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); - int ret; + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); - kirin_pcie_sideband_dbi_r_mode(kirin_pcie, true); - ret = dw_pcie_read(pci->dbi_base + where, size, val); - kirin_pcie_sideband_dbi_r_mode(kirin_pcie, false); + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; - return ret; + *val = dw_pcie_read_dbi(pci, where, size); + return PCIBIOS_SUCCESSFUL; } -static int kirin_pcie_wr_own_conf(struct pcie_port *pp, +static int kirin_pcie_wr_own_conf(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 val) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + dw_pcie_write_dbi(pci, where, size, val); + return PCIBIOS_SUCCESSFUL; +} + +static int kirin_pcie_add_bus(struct pci_bus *bus) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); - int ret; + int i, ret; - kirin_pcie_sideband_dbi_w_mode(kirin_pcie, true); - ret = dw_pcie_write(pci->dbi_base + where, size, val); - kirin_pcie_sideband_dbi_w_mode(kirin_pcie, false); + if (!kirin_pcie->num_slots) + return 0; - return ret; + /* Send PERST# to each slot */ + for (i = 0; i < kirin_pcie->num_slots; i++) { + ret = gpiod_direction_output_raw(kirin_pcie->id_reset_gpio[i], 1); + if (ret) { + dev_err(pci->dev, "PERST# %s error: %d\n", + kirin_pcie->reset_names[i], ret); + } + } + usleep_range(PERST_2_ACCESS_MIN, PERST_2_ACCESS_MAX); + + return 0; } +static struct pci_ops kirin_pci_ops = { + .read = kirin_pcie_rd_own_conf, + .write = kirin_pcie_wr_own_conf, + .add_bus = kirin_pcie_add_bus, +}; + static u32 kirin_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg, size_t size) { @@ -386,112 +586,142 @@ 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 = kirin_apb_ctrl_readl(kirin_pcie, PCIE_APB_PHY_STATUS0); - - if ((val & PCIE_LINKUP_ENABLE) == PCIE_LINKUP_ENABLE) - return 1; + u32 val; - return 0; + regmap_read(kirin_pcie->apb, PCIE_APB_PHY_STATUS0, &val); + return (val & PCIE_LINKUP_ENABLE) == PCIE_LINKUP_ENABLE; } -static int kirin_pcie_establish_link(struct pcie_port *pp) +static int kirin_pcie_start_link(struct dw_pcie *pci) { - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); - struct device *dev = kirin_pcie->pci->dev; - int count = 0; - - if (kirin_pcie_link_up(pci)) - return 0; - - dw_pcie_setup_rc(pp); /* assert LTSSM enable */ - kirin_apb_ctrl_writel(kirin_pcie, PCIE_LTSSM_ENABLE_BIT, - PCIE_APP_LTSSM_ENABLE); - - /* check if the link is up or not */ - while (!kirin_pcie_link_up(pci)) { - usleep_range(LINK_WAIT_MIN, LINK_WAIT_MAX); - count++; - if (count == 1000) { - dev_err(dev, "Link Fail\n"); - return -EINVAL; - } - } + regmap_write(kirin_pcie->apb, PCIE_APP_LTSSM_ENABLE, + PCIE_LTSSM_ENABLE_BIT); return 0; } -static int kirin_pcie_host_init(struct pcie_port *pp) +static int kirin_pcie_host_init(struct dw_pcie_rp *pp) { - kirin_pcie_establish_link(pp); - - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(pp); + pp->bridge->ops = &kirin_pci_ops; return 0; } -static struct dw_pcie_ops kirin_dw_pcie_ops = { +static const struct dw_pcie_ops kirin_dw_pcie_ops = { .read_dbi = kirin_pcie_read_dbi, .write_dbi = kirin_pcie_write_dbi, .link_up = kirin_pcie_link_up, + .start_link = kirin_pcie_start_link, }; static const struct dw_pcie_host_ops kirin_pcie_host_ops = { - .rd_own_conf = kirin_pcie_rd_own_conf, - .wr_own_conf = kirin_pcie_wr_own_conf, - .host_init = kirin_pcie_host_init, + .init = kirin_pcie_host_init, }; -static int kirin_pcie_add_msi(struct dw_pcie *pci, - struct platform_device *pdev) +static int kirin_pcie_power_off(struct kirin_pcie *kirin_pcie) { - int irq; - - if (IS_ENABLED(CONFIG_PCI_MSI)) { - irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(&pdev->dev, - "failed to get MSI IRQ (%d)\n", irq); - return irq; - } + int i; - pci->pp.msi_irq = irq; - } + if (kirin_pcie->type == PCIE_KIRIN_INTERNAL_PHY) + return hi3660_pcie_phy_power_off(kirin_pcie); + + for (i = 0; i < kirin_pcie->n_gpio_clkreq; i++) + gpiod_direction_output_raw(kirin_pcie->id_clkreq_gpio[i], 1); + + phy_power_off(kirin_pcie->phy); + phy_exit(kirin_pcie->phy); return 0; } -static int kirin_add_pcie_port(struct dw_pcie *pci, - struct platform_device *pdev) +static int kirin_pcie_power_on(struct platform_device *pdev, + struct kirin_pcie *kirin_pcie) { + struct device *dev = &pdev->dev; int ret; - ret = kirin_pcie_add_msi(pci, pdev); + if (kirin_pcie->type == PCIE_KIRIN_INTERNAL_PHY) { + ret = hi3660_pcie_phy_init(pdev, kirin_pcie); + if (ret) + return ret; + + ret = hi3660_pcie_phy_power_on(kirin_pcie); + if (ret) + return ret; + } else { + kirin_pcie->phy = devm_of_phy_get(dev, dev->of_node, NULL); + if (IS_ERR(kirin_pcie->phy)) + return PTR_ERR(kirin_pcie->phy); + + ret = phy_init(kirin_pcie->phy); + if (ret) + goto err; + + ret = phy_power_on(kirin_pcie->phy); + if (ret) + goto err; + } + + /* perst assert Endpoint */ + usleep_range(REF_2_PERST_MIN, REF_2_PERST_MAX); + + ret = gpiod_direction_output_raw(kirin_pcie->id_dwc_perst_gpio, 1); if (ret) - return ret; + goto err; - pci->pp.ops = &kirin_pcie_host_ops; + usleep_range(PERST_2_ACCESS_MIN, PERST_2_ACCESS_MAX); - return dw_pcie_host_init(&pci->pp); + return 0; +err: + kirin_pcie_power_off(kirin_pcie); + + return ret; +} + +static void kirin_pcie_remove(struct platform_device *pdev) +{ + struct kirin_pcie *kirin_pcie = platform_get_drvdata(pdev); + + dw_pcie_host_deinit(&kirin_pcie->pci->pp); + + kirin_pcie_power_off(kirin_pcie); } +struct kirin_pcie_data { + enum pcie_kirin_phy_type phy_type; +}; + +static const struct kirin_pcie_data kirin_960_data = { + .phy_type = PCIE_KIRIN_INTERNAL_PHY, +}; + +static const struct kirin_pcie_data kirin_970_data = { + .phy_type = PCIE_KIRIN_EXTERNAL_PHY, +}; + +static const struct of_device_id kirin_pcie_match[] = { + { .compatible = "hisilicon,kirin960-pcie", .data = &kirin_960_data }, + { .compatible = "hisilicon,kirin970-pcie", .data = &kirin_970_data }, + {}, +}; + static int kirin_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; + const struct kirin_pcie_data *data; struct kirin_pcie *kirin_pcie; struct dw_pcie *pci; int ret; - if (!dev->of_node) { - dev_err(dev, "NULL node\n"); - return -EINVAL; - } + data = of_device_get_match_data(dev); + if (!data) + return dev_err_probe(dev, -EINVAL, "OF data missing\n"); kirin_pcie = devm_kzalloc(dev, sizeof(struct kirin_pcie), GFP_KERNEL); if (!kirin_pcie) @@ -503,41 +733,35 @@ static int kirin_pcie_probe(struct platform_device *pdev) pci->dev = dev; pci->ops = &kirin_dw_pcie_ops; + pci->pp.ops = &kirin_pcie_host_ops; kirin_pcie->pci = pci; - - ret = kirin_pcie_get_clk(kirin_pcie, pdev); - if (ret) - return ret; + kirin_pcie->type = data->phy_type; ret = kirin_pcie_get_resource(kirin_pcie, pdev); if (ret) return ret; - kirin_pcie->gpio_id_reset = of_get_named_gpio(dev->of_node, - "reset-gpios", 0); - if (kirin_pcie->gpio_id_reset < 0) - return -ENODEV; + platform_set_drvdata(pdev, kirin_pcie); - ret = kirin_pcie_power_on(kirin_pcie); + ret = kirin_pcie_power_on(pdev, kirin_pcie); if (ret) return ret; - platform_set_drvdata(pdev, kirin_pcie); - - return kirin_add_pcie_port(pci, pdev); + return dw_pcie_host_init(&pci->pp); } -static const struct of_device_id kirin_pcie_match[] = { - { .compatible = "hisilicon,kirin960-pcie" }, - {}, -}; - static struct platform_driver kirin_pcie_driver = { .probe = kirin_pcie_probe, + .remove = kirin_pcie_remove, .driver = { .name = "kirin-pcie", - .of_match_table = kirin_pcie_match, - .suppress_bind_attrs = true, + .of_match_table = kirin_pcie_match, + .suppress_bind_attrs = true, }, }; -builtin_platform_driver(kirin_pcie_driver); +module_platform_driver(kirin_pcie_driver); + +MODULE_DEVICE_TABLE(of, kirin_pcie_match); +MODULE_DESCRIPTION("PCIe host controller driver for Kirin Phone SoCs"); +MODULE_AUTHOR("Xiaowei Song <songxiaowei@huawei.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-nxp-s32g.c b/drivers/pci/controller/dwc/pcie-nxp-s32g.c new file mode 100644 index 000000000000..47745749f75c --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-nxp-s32g.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for NXP S32G SoCs + * + * Copyright 2019-2025 NXP + */ + +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/sizes.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +/* PCIe controller Sub-System */ + +/* PCIe controller 0 General Control 1 */ +#define PCIE_S32G_PE0_GEN_CTRL_1 0x50 +#define DEVICE_TYPE_MASK GENMASK(3, 0) +#define SRIS_MODE BIT(8) + +/* PCIe controller 0 General Control 3 */ +#define PCIE_S32G_PE0_GEN_CTRL_3 0x58 +#define LTSSM_EN BIT(0) + +/* PCIe Controller 0 Interrupt Status */ +#define PCIE_S32G_PE0_INT_STS 0xE8 +#define HP_INT_STS BIT(6) + +/* Boundary between peripheral space and physical memory space */ +#define S32G_MEMORY_BOUNDARY_ADDR 0x80000000 + +struct s32g_pcie_port { + struct list_head list; + struct phy *phy; +}; + +struct s32g_pcie { + struct dw_pcie pci; + void __iomem *ctrl_base; + struct list_head ports; +}; + +#define to_s32g_from_dw_pcie(x) \ + container_of(x, struct s32g_pcie, pci) + +static void s32g_pcie_writel_ctrl(struct s32g_pcie *s32g_pp, u32 reg, u32 val) +{ + writel(val, s32g_pp->ctrl_base + reg); +} + +static u32 s32g_pcie_readl_ctrl(struct s32g_pcie *s32g_pp, u32 reg) +{ + return readl(s32g_pp->ctrl_base + reg); +} + +static void s32g_pcie_enable_ltssm(struct s32g_pcie *s32g_pp) +{ + u32 reg; + + reg = s32g_pcie_readl_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3); + reg |= LTSSM_EN; + s32g_pcie_writel_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3, reg); +} + +static void s32g_pcie_disable_ltssm(struct s32g_pcie *s32g_pp) +{ + u32 reg; + + reg = s32g_pcie_readl_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3); + reg &= ~LTSSM_EN; + s32g_pcie_writel_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3, reg); +} + +static int s32g_pcie_start_link(struct dw_pcie *pci) +{ + struct s32g_pcie *s32g_pp = to_s32g_from_dw_pcie(pci); + + s32g_pcie_enable_ltssm(s32g_pp); + + return 0; +} + +static void s32g_pcie_stop_link(struct dw_pcie *pci) +{ + struct s32g_pcie *s32g_pp = to_s32g_from_dw_pcie(pci); + + s32g_pcie_disable_ltssm(s32g_pp); +} + +static struct dw_pcie_ops s32g_pcie_ops = { + .start_link = s32g_pcie_start_link, + .stop_link = s32g_pcie_stop_link, +}; + +/* Configure the AMBA AXI Coherency Extensions (ACE) interface */ +static void s32g_pcie_reset_mstr_ace(struct dw_pcie *pci) +{ + u32 ddr_base_low = lower_32_bits(S32G_MEMORY_BOUNDARY_ADDR); + u32 ddr_base_high = upper_32_bits(S32G_MEMORY_BOUNDARY_ADDR); + + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, COHERENCY_CONTROL_3_OFF, 0x0); + + /* + * Ncore is a cache-coherent interconnect module that enables the + * integration of heterogeneous coherent and non-coherent agents in + * the chip. Ncore transactions to peripheral should be non-coherent + * or it might drop them. + * + * One example where this is needed are PCIe MSIs, which use NoSnoop=0 + * and might end up routed to Ncore. PCIe coherent traffic (e.g. MSIs) + * that targets peripheral space will be dropped by Ncore because + * peripherals on S32G are not coherent as slaves. We add a hard + * boundary in the PCIe controller coherency control registers to + * separate physical memory space from peripheral space. + * + * Define the start of DDR as seen by Linux as this boundary between + * "memory" and "peripherals", with peripherals being below. + */ + dw_pcie_writel_dbi(pci, COHERENCY_CONTROL_1_OFF, + (ddr_base_low & CFG_MEMTYPE_BOUNDARY_LOW_ADDR_MASK)); + dw_pcie_writel_dbi(pci, COHERENCY_CONTROL_2_OFF, ddr_base_high); + dw_pcie_dbi_ro_wr_dis(pci); +} + +static int s32g_init_pcie_controller(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct s32g_pcie *s32g_pp = to_s32g_from_dw_pcie(pci); + u32 val; + + /* Set RP mode */ + val = s32g_pcie_readl_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_1); + val &= ~DEVICE_TYPE_MASK; + val |= FIELD_PREP(DEVICE_TYPE_MASK, PCI_EXP_TYPE_ROOT_PORT); + + /* Use default CRNS */ + val &= ~SRIS_MODE; + + s32g_pcie_writel_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_1, val); + + /* + * Make sure we use the coherency defaults (just in case the settings + * have been changed from their reset values) + */ + s32g_pcie_reset_mstr_ace(pci); + + dw_pcie_dbi_ro_wr_en(pci); + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_FORCE); + val |= PORT_FORCE_DO_DESKEW_FOR_SRIS; + dw_pcie_writel_dbi(pci, PCIE_PORT_FORCE, val); + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val |= GEN3_RELATED_OFF_EQ_PHASE_2_3; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static const struct dw_pcie_host_ops s32g_pcie_host_ops = { + .init = s32g_init_pcie_controller, +}; + +static int s32g_init_pcie_phy(struct s32g_pcie *s32g_pp) +{ + struct dw_pcie *pci = &s32g_pp->pci; + struct device *dev = pci->dev; + struct s32g_pcie_port *port, *tmp; + int ret; + + list_for_each_entry(port, &s32g_pp->ports, list) { + ret = phy_init(port->phy); + if (ret) { + dev_err(dev, "Failed to init serdes PHY\n"); + goto err_phy_revert; + } + + ret = phy_set_mode_ext(port->phy, PHY_MODE_PCIE, 0); + if (ret) { + dev_err(dev, "Failed to set mode on serdes PHY\n"); + goto err_phy_exit; + } + + ret = phy_power_on(port->phy); + if (ret) { + dev_err(dev, "Failed to power on serdes PHY\n"); + goto err_phy_exit; + } + } + + return 0; + +err_phy_exit: + phy_exit(port->phy); + +err_phy_revert: + list_for_each_entry_continue_reverse(port, &s32g_pp->ports, list) { + phy_power_off(port->phy); + phy_exit(port->phy); + } + + list_for_each_entry_safe(port, tmp, &s32g_pp->ports, list) + list_del(&port->list); + + return ret; +} + +static void s32g_deinit_pcie_phy(struct s32g_pcie *s32g_pp) +{ + struct s32g_pcie_port *port, *tmp; + + list_for_each_entry_safe(port, tmp, &s32g_pp->ports, list) { + phy_power_off(port->phy); + phy_exit(port->phy); + list_del(&port->list); + } +} + +static int s32g_pcie_init(struct device *dev, struct s32g_pcie *s32g_pp) +{ + s32g_pcie_disable_ltssm(s32g_pp); + + return s32g_init_pcie_phy(s32g_pp); +} + +static void s32g_pcie_deinit(struct s32g_pcie *s32g_pp) +{ + s32g_pcie_disable_ltssm(s32g_pp); + + s32g_deinit_pcie_phy(s32g_pp); +} + +static int s32g_pcie_parse_port(struct s32g_pcie *s32g_pp, struct device_node *node) +{ + struct device *dev = s32g_pp->pci.dev; + struct s32g_pcie_port *port; + int num_lanes; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->phy = devm_of_phy_get(dev, node, NULL); + if (IS_ERR(port->phy)) + return dev_err_probe(dev, PTR_ERR(port->phy), + "Failed to get serdes PHY\n"); + + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &s32g_pp->ports); + + /* + * The DWC core initialization code cannot yet parse the num-lanes + * attribute in the Root Port node. The S32G only supports one Root + * Port for now so its driver can parse the node and set the num_lanes + * field of struct dwc_pcie before calling dw_pcie_host_init(). + */ + if (!of_property_read_u32(node, "num-lanes", &num_lanes)) + s32g_pp->pci.num_lanes = num_lanes; + + return 0; +} + +static int s32g_pcie_parse_ports(struct device *dev, struct s32g_pcie *s32g_pp) +{ + struct s32g_pcie_port *port, *tmp; + int ret = -ENOENT; + + for_each_available_child_of_node_scoped(dev->of_node, of_port) { + if (!of_node_is_type(of_port, "pci")) + continue; + + ret = s32g_pcie_parse_port(s32g_pp, of_port); + if (ret) + goto err_port; + } + +err_port: + list_for_each_entry_safe(port, tmp, &s32g_pp->ports, list) + list_del(&port->list); + + return ret; +} + +static int s32g_pcie_get_resources(struct platform_device *pdev, + struct s32g_pcie *s32g_pp) +{ + struct dw_pcie *pci = &s32g_pp->pci; + struct device *dev = &pdev->dev; + int ret; + + pci->dev = dev; + pci->ops = &s32g_pcie_ops; + + s32g_pp->ctrl_base = devm_platform_ioremap_resource_byname(pdev, "ctrl"); + if (IS_ERR(s32g_pp->ctrl_base)) + return PTR_ERR(s32g_pp->ctrl_base); + + INIT_LIST_HEAD(&s32g_pp->ports); + + ret = s32g_pcie_parse_ports(dev, s32g_pp); + if (ret) + return dev_err_probe(dev, ret, + "Failed to parse Root Port: %d\n", ret); + + platform_set_drvdata(pdev, s32g_pp); + + return 0; +} + +static int s32g_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct s32g_pcie *s32g_pp; + struct dw_pcie_rp *pp; + int ret; + + s32g_pp = devm_kzalloc(dev, sizeof(*s32g_pp), GFP_KERNEL); + if (!s32g_pp) + return -ENOMEM; + + ret = s32g_pcie_get_resources(pdev, s32g_pp); + if (ret) + return ret; + + pm_runtime_no_callbacks(dev); + devm_pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) + goto err_pm_runtime_put; + + ret = s32g_pcie_init(dev, s32g_pp); + if (ret) + goto err_pm_runtime_put; + + pp = &s32g_pp->pci.pp; + pp->ops = &s32g_pcie_host_ops; + pp->use_atu_msg = true; + + ret = dw_pcie_host_init(pp); + if (ret) + goto err_pcie_deinit; + + return 0; + +err_pcie_deinit: + s32g_pcie_deinit(s32g_pp); +err_pm_runtime_put: + pm_runtime_put(dev); + + return ret; +} + +static int s32g_pcie_suspend_noirq(struct device *dev) +{ + struct s32g_pcie *s32g_pp = dev_get_drvdata(dev); + struct dw_pcie *pci = &s32g_pp->pci; + + return dw_pcie_suspend_noirq(pci); +} + +static int s32g_pcie_resume_noirq(struct device *dev) +{ + struct s32g_pcie *s32g_pp = dev_get_drvdata(dev); + struct dw_pcie *pci = &s32g_pp->pci; + + return dw_pcie_resume_noirq(pci); +} + +static const struct dev_pm_ops s32g_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(s32g_pcie_suspend_noirq, + s32g_pcie_resume_noirq) +}; + +static const struct of_device_id s32g_pcie_of_match[] = { + { .compatible = "nxp,s32g2-pcie" }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, s32g_pcie_of_match); + +static struct platform_driver s32g_pcie_driver = { + .driver = { + .name = "s32g-pcie", + .of_match_table = s32g_pcie_of_match, + .suppress_bind_attrs = true, + .pm = pm_sleep_ptr(&s32g_pcie_pm_ops), + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = s32g_pcie_probe, +}; + +builtin_platform_driver(s32g_pcie_driver); + +MODULE_AUTHOR("Ionut Vicovan <Ionut.Vicovan@nxp.com>"); +MODULE_DESCRIPTION("NXP S32G PCIe Host controller driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/dwc/pcie-qcom-common.c b/drivers/pci/controller/dwc/pcie-qcom-common.c new file mode 100644 index 000000000000..01c5387e53bf --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-qcom-common.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include <linux/pci.h> + +#include "pcie-designware.h" +#include "pcie-qcom-common.h" + +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 + * settings at various data transmission rates through registers namely + * GEN3_EQ_*. The RATE_SHADOW_SEL bit field of GEN3_RELATED_OFF + * determines the data rate for which these equalization settings are + * applied. + */ + + 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_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_equalization); + +void qcom_pcie_common_set_16gt_lane_margining(struct dw_pcie *pci) +{ + u32 reg; + + reg = dw_pcie_readl_dbi(pci, GEN4_LANE_MARGINING_1_OFF); + reg &= ~(MARGINING_MAX_VOLTAGE_OFFSET | + MARGINING_NUM_VOLTAGE_STEPS | + MARGINING_MAX_TIMING_OFFSET | + MARGINING_NUM_TIMING_STEPS); + reg |= FIELD_PREP(MARGINING_MAX_VOLTAGE_OFFSET, 0x24) | + FIELD_PREP(MARGINING_NUM_VOLTAGE_STEPS, 0x78) | + FIELD_PREP(MARGINING_MAX_TIMING_OFFSET, 0x32) | + FIELD_PREP(MARGINING_NUM_TIMING_STEPS, 0x10); + dw_pcie_writel_dbi(pci, GEN4_LANE_MARGINING_1_OFF, reg); + + reg = dw_pcie_readl_dbi(pci, GEN4_LANE_MARGINING_2_OFF); + reg |= MARGINING_IND_ERROR_SAMPLER | + MARGINING_SAMPLE_REPORTING_METHOD | + MARGINING_IND_LEFT_RIGHT_TIMING | + MARGINING_VOLTAGE_SUPPORTED; + reg &= ~(MARGINING_IND_UP_DOWN_VOLTAGE | + MARGINING_MAXLANES | + MARGINING_SAMPLE_RATE_TIMING | + MARGINING_SAMPLE_RATE_VOLTAGE); + reg |= FIELD_PREP(MARGINING_MAXLANES, pci->num_lanes) | + FIELD_PREP(MARGINING_SAMPLE_RATE_TIMING, 0x3f) | + FIELD_PREP(MARGINING_SAMPLE_RATE_VOLTAGE, 0x3f); + dw_pcie_writel_dbi(pci, GEN4_LANE_MARGINING_2_OFF, reg); +} +EXPORT_SYMBOL_GPL(qcom_pcie_common_set_16gt_lane_margining); diff --git a/drivers/pci/controller/dwc/pcie-qcom-common.h b/drivers/pci/controller/dwc/pcie-qcom-common.h new file mode 100644 index 000000000000..7f5ca2fd9a72 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-qcom-common.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _PCIE_QCOM_COMMON_H +#define _PCIE_QCOM_COMMON_H + +struct dw_pcie; + +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 new file mode 100644 index 000000000000..f1bc0ac81a92 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -0,0 +1,955 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Qualcomm PCIe Endpoint controller driver + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Author: Siddartha Mohanadoss <smohanad@codeaurora.org + * + * Copyright (c) 2021, Linaro Ltd. + * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org + */ + +#include <linux/clk.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/interconnect.h> +#include <linux/mfd/syscon.h> +#include <linux/phy/pcie.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/module.h> + +#include "../../pci.h" +#include "pcie-designware.h" +#include "pcie-qcom-common.h" + +/* PARF registers */ +#define PARF_SYS_CTRL 0x00 +#define PARF_DB_CTRL 0x10 +#define PARF_PM_CTRL 0x20 +#define PARF_MHI_CLOCK_RESET_CTRL 0x174 +#define PARF_MHI_BASE_ADDR_LOWER 0x178 +#define PARF_MHI_BASE_ADDR_UPPER 0x17c +#define PARF_DEBUG_INT_EN 0x190 +#define PARF_AXI_MSTR_RD_HALT_NO_WRITES 0x1a4 +#define PARF_AXI_MSTR_WR_ADDR_HALT 0x1a8 +#define PARF_Q2A_FLUSH 0x1ac +#define PARF_LTSSM 0x1b0 +#define PARF_CFG_BITS 0x210 +#define PARF_INT_ALL_STATUS 0x224 +#define PARF_INT_ALL_CLEAR 0x228 +#define PARF_INT_ALL_MASK 0x22c +#define PARF_SLV_ADDR_MSB_CTRL 0x2c0 +#define PARF_DBI_BASE_ADDR 0x350 +#define PARF_DBI_BASE_ADDR_HI 0x354 +#define PARF_SLV_ADDR_SPACE_SIZE 0x358 +#define PARF_SLV_ADDR_SPACE_SIZE_HI 0x35c +#define PARF_NO_SNOOP_OVERRIDE 0x3d4 +#define PARF_ATU_BASE_ADDR 0x634 +#define PARF_ATU_BASE_ADDR_HI 0x638 +#define PARF_SRIS_MODE 0x644 +#define PARF_DEBUG_CNT_PM_LINKST_IN_L2 0xc04 +#define PARF_DEBUG_CNT_PM_LINKST_IN_L1 0xc0c +#define PARF_DEBUG_CNT_PM_LINKST_IN_L0S 0xc10 +#define PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L1 0xc84 +#define PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L2 0xc88 +#define PARF_DEVICE_TYPE 0x1000 +#define PARF_BDF_TO_SID_CFG 0x2c00 +#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) +#define PARF_INT_ALL_BME BIT(2) +#define PARF_INT_ALL_PM_TURNOFF BIT(3) +#define PARF_INT_ALL_DEBUG BIT(4) +#define PARF_INT_ALL_LTR BIT(5) +#define PARF_INT_ALL_MHI_Q6 BIT(6) +#define PARF_INT_ALL_MHI_A7 BIT(7) +#define PARF_INT_ALL_DSTATE_CHANGE BIT(8) +#define PARF_INT_ALL_L1SUB_TIMEOUT BIT(9) +#define PARF_INT_ALL_MMIO_WRITE BIT(10) +#define PARF_INT_ALL_CFG_WRITE BIT(11) +#define PARF_INT_ALL_BRIDGE_FLUSH_N BIT(12) +#define PARF_INT_ALL_LINK_UP BIT(13) +#define PARF_INT_ALL_AER_LEGACY BIT(14) +#define PARF_INT_ALL_PLS_ERR BIT(15) +#define PARF_INT_ALL_PME_LEGACY BIT(16) +#define PARF_INT_ALL_PLS_PME BIT(17) +#define PARF_INT_ALL_EDMA BIT(22) + +/* PARF_BDF_TO_SID_CFG register fields */ +#define PARF_BDF_TO_SID_BYPASS BIT(0) + +/* PARF_DEBUG_INT_EN register fields */ +#define PARF_DEBUG_INT_PM_DSTATE_CHANGE BIT(1) +#define PARF_DEBUG_INT_CFG_BUS_MASTER_EN BIT(2) +#define PARF_DEBUG_INT_RADM_PM_TURNOFF BIT(3) + +/* PARF_NO_SNOOP_OVERRIDE register fields */ +#define WR_NO_SNOOP_OVERRIDE_EN BIT(1) +#define RD_NO_SNOOP_OVERRIDE_EN BIT(3) + +/* PARF_DEVICE_TYPE register fields */ +#define PARF_DEVICE_TYPE_EP 0x0 + +/* PARF_PM_CTRL register fields */ +#define PARF_PM_CTRL_REQ_EXIT_L1 BIT(1) +#define PARF_PM_CTRL_READY_ENTR_L23 BIT(2) +#define PARF_PM_CTRL_REQ_NOT_ENTR_L1 BIT(5) + +/* PARF_MHI_CLOCK_RESET_CTRL fields */ +#define PARF_MSTR_AXI_CLK_EN BIT(1) + +/* PARF_AXI_MSTR_RD_HALT_NO_WRITES register fields */ +#define PARF_AXI_MSTR_RD_HALT_NO_WRITE_EN BIT(0) + +/* PARF_AXI_MSTR_WR_ADDR_HALT register fields */ +#define PARF_AXI_MSTR_WR_ADDR_HALT_EN BIT(31) + +/* PARF_Q2A_FLUSH register fields */ +#define PARF_Q2A_FLUSH_EN BIT(16) + +/* PARF_SYS_CTRL register fields */ +#define PARF_SYS_CTRL_AUX_PWR_DET BIT(4) +#define PARF_SYS_CTRL_CORE_CLK_CGC_DIS BIT(6) +#define PARF_SYS_CTRL_MSTR_ACLK_CGC_DIS BIT(10) +#define PARF_SYS_CTRL_SLV_DBI_WAKE_DISABLE BIT(11) + +/* PARF_DB_CTRL register fields */ +#define PARF_DB_CTRL_INSR_DBNCR_BLOCK BIT(0) +#define PARF_DB_CTRL_RMVL_DBNCR_BLOCK BIT(1) +#define PARF_DB_CTRL_DBI_WKP_BLOCK BIT(4) +#define PARF_DB_CTRL_SLV_WKP_BLOCK BIT(5) +#define PARF_DB_CTRL_MST_WKP_BLOCK BIT(6) + +/* PARF_CFG_BITS register fields */ +#define PARF_CFG_BITS_REQ_EXIT_L1SS_MSI_LTR_EN BIT(1) + +/* 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 + +/* DBI registers */ +#define DBI_CON_STATUS 0x44 + +/* DBI register fields */ +#define DBI_CON_STATUS_POWER_STATE_MASK GENMASK(1, 0) + +#define XMLH_LINK_UP 0x400 +#define CORE_RESET_TIME_US_MIN 1000 +#define CORE_RESET_TIME_US_MAX 1005 +#define WAKE_DELAY_US 2000 /* 2 ms */ + +#define QCOM_PCIE_LINK_SPEED_TO_BW(speed) \ + Mbps_to_icc(PCIE_SPEED2MBS_ENC(pcie_link_speed[speed])) + +#define to_pcie_ep(x) dev_get_drvdata((x)->dev) + +enum qcom_pcie_ep_link_status { + QCOM_PCIE_EP_LINK_DISABLED, + QCOM_PCIE_EP_LINK_ENABLED, + QCOM_PCIE_EP_LINK_UP, + QCOM_PCIE_EP_LINK_DOWN, +}; + +/** + * struct qcom_pcie_ep_cfg - Per SoC config struct + * @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 + */ +struct qcom_pcie_ep_cfg { + bool hdma_support; + bool override_no_snoop; + bool disable_mhi_ram_parity_check; +}; + +/** + * struct qcom_pcie_ep - Qualcomm PCIe Endpoint Controller + * @pci: Designware PCIe controller struct + * @parf: Qualcomm PCIe specific PARF register base + * @mmio: MMIO register base + * @perst_map: PERST regmap + * @mmio_res: MMIO region resource + * @core_reset: PCIe Endpoint core reset + * @reset: PERST# GPIO + * @wake: WAKE# GPIO + * @phy: PHY controller block + * @debugfs: PCIe Endpoint Debugfs directory + * @icc_mem: Handle to an interconnect path between PCIe and MEM + * @clks: PCIe clocks + * @num_clks: PCIe clocks count + * @perst_en: Flag for PERST enable + * @perst_sep_en: Flag for PERST separation enable + * @cfg: PCIe EP config struct + * @link_status: PCIe Link status + * @global_irq: Qualcomm PCIe specific Global IRQ + * @perst_irq: PERST# IRQ + */ +struct qcom_pcie_ep { + struct dw_pcie pci; + + void __iomem *parf; + void __iomem *mmio; + struct regmap *perst_map; + struct resource *mmio_res; + + struct reset_control *core_reset; + struct gpio_desc *reset; + struct gpio_desc *wake; + struct phy *phy; + struct dentry *debugfs; + + struct icc_path *icc_mem; + + struct clk_bulk_data *clks; + int num_clks; + + u32 perst_en; + u32 perst_sep_en; + + const struct qcom_pcie_ep_cfg *cfg; + enum qcom_pcie_ep_link_status link_status; + int global_irq; + int perst_irq; +}; + +static int qcom_pcie_ep_core_reset(struct qcom_pcie_ep *pcie_ep) +{ + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + int ret; + + ret = reset_control_assert(pcie_ep->core_reset); + if (ret) { + dev_err(dev, "Cannot assert core reset\n"); + return ret; + } + + usleep_range(CORE_RESET_TIME_US_MIN, CORE_RESET_TIME_US_MAX); + + ret = reset_control_deassert(pcie_ep->core_reset); + if (ret) { + dev_err(dev, "Cannot de-assert core reset\n"); + return ret; + } + + usleep_range(CORE_RESET_TIME_US_MIN, CORE_RESET_TIME_US_MAX); + + return 0; +} + +/* + * Delatch PERST_EN and PERST_SEPARATION_ENABLE with TCSR to avoid + * device reset during host reboot and hibernation. The driver is + * expected to handle this situation. + */ +static void qcom_pcie_ep_configure_tcsr(struct qcom_pcie_ep *pcie_ep) +{ + if (pcie_ep->perst_map) { + regmap_write(pcie_ep->perst_map, pcie_ep->perst_en, 0); + regmap_write(pcie_ep->perst_map, pcie_ep->perst_sep_en, 0); + } +} + +static bool qcom_pcie_dw_link_up(struct dw_pcie *pci) +{ + u32 reg; + + reg = readl_relaxed(pci->elbi_base + ELBI_SYS_STTS); + + return reg & XMLH_LINK_UP; +} + +static int qcom_pcie_dw_start_link(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + + enable_irq(pcie_ep->perst_irq); + + return 0; +} + +static void qcom_pcie_dw_stop_link(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + + disable_irq(pcie_ep->perst_irq); +} + +static void qcom_pcie_dw_write_dbi2(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + int ret; + + 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, pci->elbi_base + ELBI_CS2_ENABLE); +} + +static void qcom_pcie_ep_icc_update(struct qcom_pcie_ep *pcie_ep) +{ + struct dw_pcie *pci = &pcie_ep->pci; + u32 offset, status; + int speed, width; + int ret; + + if (!pcie_ep->icc_mem) + return; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + status = readw(pci->dbi_base + offset + PCI_EXP_LNKSTA); + + speed = FIELD_GET(PCI_EXP_LNKSTA_CLS, status); + width = FIELD_GET(PCI_EXP_LNKSTA_NLW, status); + + ret = icc_set_bw(pcie_ep->icc_mem, 0, width * QCOM_PCIE_LINK_SPEED_TO_BW(speed)); + if (ret) + dev_err(pci->dev, "failed to set interconnect bandwidth: %d\n", + ret); +} + +static int qcom_pcie_enable_resources(struct qcom_pcie_ep *pcie_ep) +{ + struct dw_pcie *pci = &pcie_ep->pci; + int ret; + + ret = clk_bulk_prepare_enable(pcie_ep->num_clks, pcie_ep->clks); + if (ret) + return ret; + + ret = qcom_pcie_ep_core_reset(pcie_ep); + if (ret) + goto err_disable_clk; + + ret = phy_init(pcie_ep->phy); + if (ret) + goto err_disable_clk; + + ret = phy_set_mode_ext(pcie_ep->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_EP); + if (ret) + goto err_phy_exit; + + ret = phy_power_on(pcie_ep->phy); + if (ret) + goto err_phy_exit; + + /* + * Some Qualcomm platforms require interconnect bandwidth constraints + * to be set before enabling interconnect clocks. + * + * Set an initial peak bandwidth corresponding to single-lane Gen 1 + * for the pcie-mem path. + */ + ret = icc_set_bw(pcie_ep->icc_mem, 0, QCOM_PCIE_LINK_SPEED_TO_BW(1)); + if (ret) { + dev_err(pci->dev, "failed to set interconnect bandwidth: %d\n", + ret); + goto err_phy_off; + } + + return 0; + +err_phy_off: + phy_power_off(pcie_ep->phy); +err_phy_exit: + phy_exit(pcie_ep->phy); +err_disable_clk: + clk_bulk_disable_unprepare(pcie_ep->num_clks, pcie_ep->clks); + + return ret; +} + +static void qcom_pcie_disable_resources(struct qcom_pcie_ep *pcie_ep) +{ + icc_set_bw(pcie_ep->icc_mem, 0, 0); + phy_power_off(pcie_ep->phy); + phy_exit(pcie_ep->phy); + clk_bulk_disable_unprepare(pcie_ep->num_clks, pcie_ep->clks); +} + +static int qcom_pcie_perst_deassert(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + struct device *dev = pci->dev; + u32 val, offset; + int ret; + + ret = qcom_pcie_enable_resources(pcie_ep); + if (ret) { + dev_err(dev, "Failed to enable resources: %d\n", ret); + return ret; + } + + /* Perform cleanup that requires refclk */ + pci_epc_deinit_notify(pci->ep.epc); + dw_pcie_ep_cleanup(&pci->ep); + + /* Assert WAKE# to RC to indicate device is ready */ + gpiod_set_value_cansleep(pcie_ep->wake, 1); + usleep_range(WAKE_DELAY_US, WAKE_DELAY_US + 500); + gpiod_set_value_cansleep(pcie_ep->wake, 0); + + qcom_pcie_ep_configure_tcsr(pcie_ep); + + /* Disable BDF to SID mapping */ + val = readl_relaxed(pcie_ep->parf + PARF_BDF_TO_SID_CFG); + val |= PARF_BDF_TO_SID_BYPASS; + writel_relaxed(val, pcie_ep->parf + PARF_BDF_TO_SID_CFG); + + /* Enable debug IRQ */ + val = readl_relaxed(pcie_ep->parf + PARF_DEBUG_INT_EN); + val |= PARF_DEBUG_INT_RADM_PM_TURNOFF | + PARF_DEBUG_INT_CFG_BUS_MASTER_EN | + PARF_DEBUG_INT_PM_DSTATE_CHANGE; + writel_relaxed(val, pcie_ep->parf + PARF_DEBUG_INT_EN); + + /* Configure PCIe to endpoint mode */ + writel_relaxed(PARF_DEVICE_TYPE_EP, pcie_ep->parf + PARF_DEVICE_TYPE); + + /* Allow entering L1 state */ + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val &= ~PARF_PM_CTRL_REQ_NOT_ENTR_L1; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + + /* Read halts write */ + val = readl_relaxed(pcie_ep->parf + PARF_AXI_MSTR_RD_HALT_NO_WRITES); + val &= ~PARF_AXI_MSTR_RD_HALT_NO_WRITE_EN; + writel_relaxed(val, pcie_ep->parf + PARF_AXI_MSTR_RD_HALT_NO_WRITES); + + /* Write after write halt */ + val = readl_relaxed(pcie_ep->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + val |= PARF_AXI_MSTR_WR_ADDR_HALT_EN; + writel_relaxed(val, pcie_ep->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + + /* Q2A flush disable */ + val = readl_relaxed(pcie_ep->parf + PARF_Q2A_FLUSH); + val &= ~PARF_Q2A_FLUSH_EN; + writel_relaxed(val, pcie_ep->parf + PARF_Q2A_FLUSH); + + /* + * Disable Master AXI clock during idle. Do not allow DBI access + * to take the core out of L1. Disable core clock gating that + * gates PIPE clock from propagating to core clock. Report to the + * host that Vaux is present. + */ + val = readl_relaxed(pcie_ep->parf + PARF_SYS_CTRL); + val &= ~PARF_SYS_CTRL_MSTR_ACLK_CGC_DIS; + val |= PARF_SYS_CTRL_SLV_DBI_WAKE_DISABLE | + PARF_SYS_CTRL_CORE_CLK_CGC_DIS | + PARF_SYS_CTRL_AUX_PWR_DET; + writel_relaxed(val, pcie_ep->parf + PARF_SYS_CTRL); + + /* Disable the debouncers */ + val = readl_relaxed(pcie_ep->parf + PARF_DB_CTRL); + val |= PARF_DB_CTRL_INSR_DBNCR_BLOCK | PARF_DB_CTRL_RMVL_DBNCR_BLOCK | + PARF_DB_CTRL_DBI_WKP_BLOCK | PARF_DB_CTRL_SLV_WKP_BLOCK | + PARF_DB_CTRL_MST_WKP_BLOCK; + writel_relaxed(val, pcie_ep->parf + PARF_DB_CTRL); + + /* Request to exit from L1SS for MSI and LTR MSG */ + val = readl_relaxed(pcie_ep->parf + PARF_CFG_BITS); + val |= PARF_CFG_BITS_REQ_EXIT_L1SS_MSI_LTR_EN; + writel_relaxed(val, pcie_ep->parf + PARF_CFG_BITS); + + dw_pcie_dbi_ro_wr_en(pci); + + /* Set the L0s Exit Latency to 2us-4us = 0x6 */ + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_L0SEL; + val |= FIELD_PREP(PCI_EXP_LNKCAP_L0SEL, 0x6); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, val); + + /* Set the L1 Exit Latency to be 32us-64 us = 0x6 */ + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_L1EL; + val |= FIELD_PREP(PCI_EXP_LNKCAP_L1EL, 0x6); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + writel_relaxed(0, pcie_ep->parf + PARF_INT_ALL_MASK); + val = PARF_INT_ALL_LINK_DOWN | PARF_INT_ALL_BME | + PARF_INT_ALL_PM_TURNOFF | PARF_INT_ALL_DSTATE_CHANGE | + PARF_INT_ALL_LINK_UP | PARF_INT_ALL_EDMA; + writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_MASK); + + if (pcie_ep->cfg && pcie_ep->cfg->disable_mhi_ram_parity_check) { + val = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_5_MASK); + val &= ~PARF_INT_ALL_5_MHI_RAM_DATA_PARITY_ERR; + 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; + } + + 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 + * should be written to MHI BASE registers. + */ + writel_relaxed(pcie_ep->mmio_res->start, + pcie_ep->parf + PARF_MHI_BASE_ADDR_LOWER); + writel_relaxed(0, pcie_ep->parf + PARF_MHI_BASE_ADDR_UPPER); + + /* Gate Master AXI clock to MHI bus during L1SS */ + val = readl_relaxed(pcie_ep->parf + PARF_MHI_CLOCK_RESET_CTRL); + val &= ~PARF_MSTR_AXI_CLK_EN; + writel_relaxed(val, pcie_ep->parf + PARF_MHI_CLOCK_RESET_CTRL); + + pci_epc_init_notify(pcie_ep->pci.ep.epc); + + /* Enable LTSSM */ + val = readl_relaxed(pcie_ep->parf + PARF_LTSSM); + val |= BIT(8); + writel_relaxed(val, pcie_ep->parf + PARF_LTSSM); + + if (pcie_ep->cfg && pcie_ep->cfg->override_no_snoop) + writel_relaxed(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN, + pcie_ep->parf + PARF_NO_SNOOP_OVERRIDE); + + return 0; + +err_disable_resources: + qcom_pcie_disable_resources(pcie_ep); + + return ret; +} + +static void qcom_pcie_perst_assert(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + + qcom_pcie_disable_resources(pcie_ep); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_DISABLED; +} + +/* Common DWC controller ops */ +static const struct dw_pcie_ops pci_ops = { + .link_up = qcom_pcie_dw_link_up, + .start_link = qcom_pcie_dw_start_link, + .stop_link = qcom_pcie_dw_stop_link, + .write_dbi2 = qcom_pcie_dw_write_dbi2, +}; + +static int qcom_pcie_ep_get_io_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci = &pcie_ep->pci; + struct device_node *syscon; + struct resource *res; + int ret; + + pcie_ep->parf = devm_platform_ioremap_resource_byname(pdev, "parf"); + if (IS_ERR(pcie_ep->parf)) + return PTR_ERR(pcie_ep->parf); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + pci->dbi_base2 = pci->dbi_base; + + pcie_ep->mmio_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "mmio"); + if (!pcie_ep->mmio_res) { + dev_err(dev, "Failed to get mmio resource\n"); + return -EINVAL; + } + + pcie_ep->mmio = devm_pci_remap_cfg_resource(dev, pcie_ep->mmio_res); + if (IS_ERR(pcie_ep->mmio)) + return PTR_ERR(pcie_ep->mmio); + + syscon = of_parse_phandle(dev->of_node, "qcom,perst-regs", 0); + if (!syscon) { + dev_dbg(dev, "PERST separation not available\n"); + return 0; + } + + pcie_ep->perst_map = syscon_node_to_regmap(syscon); + of_node_put(syscon); + if (IS_ERR(pcie_ep->perst_map)) + return PTR_ERR(pcie_ep->perst_map); + + ret = of_property_read_u32_index(dev->of_node, "qcom,perst-regs", + 1, &pcie_ep->perst_en); + if (ret < 0) { + dev_err(dev, "No Perst Enable offset in syscon\n"); + return ret; + } + + ret = of_property_read_u32_index(dev->of_node, "qcom,perst-regs", + 2, &pcie_ep->perst_sep_en); + if (ret < 0) { + dev_err(dev, "No Perst Separation Enable offset in syscon\n"); + return ret; + } + + return 0; +} + +static int qcom_pcie_ep_get_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + struct device *dev = &pdev->dev; + int ret; + + ret = qcom_pcie_ep_get_io_resources(pdev, pcie_ep); + if (ret) { + dev_err(dev, "Failed to get io resources %d\n", ret); + return ret; + } + + pcie_ep->num_clks = devm_clk_bulk_get_all(dev, &pcie_ep->clks); + if (pcie_ep->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return pcie_ep->num_clks; + } + + pcie_ep->core_reset = devm_reset_control_get_exclusive(dev, "core"); + if (IS_ERR(pcie_ep->core_reset)) + return PTR_ERR(pcie_ep->core_reset); + + pcie_ep->reset = devm_gpiod_get(dev, "reset", GPIOD_IN); + if (IS_ERR(pcie_ep->reset)) + return PTR_ERR(pcie_ep->reset); + + pcie_ep->wake = devm_gpiod_get_optional(dev, "wake", GPIOD_OUT_LOW); + if (IS_ERR(pcie_ep->wake)) + return PTR_ERR(pcie_ep->wake); + + pcie_ep->phy = devm_phy_optional_get(dev, "pciephy"); + if (IS_ERR(pcie_ep->phy)) + ret = PTR_ERR(pcie_ep->phy); + + pcie_ep->icc_mem = devm_of_icc_get(dev, "pcie-mem"); + if (IS_ERR(pcie_ep->icc_mem)) + ret = PTR_ERR(pcie_ep->icc_mem); + + return ret; +} + +/* TODO: Notify clients about PCIe state change */ +static irqreturn_t qcom_pcie_ep_global_irq_thread(int irq, void *data) +{ + struct qcom_pcie_ep *pcie_ep = data; + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + u32 status = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_STATUS); + u32 dstate, val; + + writel_relaxed(status, pcie_ep->parf + PARF_INT_ALL_CLEAR); + + if (FIELD_GET(PARF_INT_ALL_LINK_DOWN, status)) { + dev_dbg(dev, "Received Linkdown event\n"); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_DOWN; + dw_pcie_ep_linkdown(&pci->ep); + } else if (FIELD_GET(PARF_INT_ALL_BME, status)) { + dev_dbg(dev, "Received Bus Master Enable event\n"); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_ENABLED; + qcom_pcie_ep_icc_update(pcie_ep); + pci_epc_bus_master_enable_notify(pci->ep.epc); + } else if (FIELD_GET(PARF_INT_ALL_PM_TURNOFF, status)) { + dev_dbg(dev, "Received PM Turn-off event! Entering L23\n"); + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val |= PARF_PM_CTRL_READY_ENTR_L23; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + } else if (FIELD_GET(PARF_INT_ALL_DSTATE_CHANGE, status)) { + dstate = dw_pcie_readl_dbi(pci, DBI_CON_STATUS) & + DBI_CON_STATUS_POWER_STATE_MASK; + dev_dbg(dev, "Received D%d state event\n", dstate); + if (dstate == 3) { + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val |= PARF_PM_CTRL_REQ_EXIT_L1; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + } + } else if (FIELD_GET(PARF_INT_ALL_LINK_UP, status)) { + dev_dbg(dev, "Received Linkup event. Enumeration complete!\n"); + dw_pcie_ep_linkup(&pci->ep); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_UP; + } else { + dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n", + status); + } + + return IRQ_HANDLED; +} + +static irqreturn_t qcom_pcie_ep_perst_irq_thread(int irq, void *data) +{ + struct qcom_pcie_ep *pcie_ep = data; + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + u32 perst; + + perst = gpiod_get_value(pcie_ep->reset); + if (perst) { + dev_dbg(dev, "PERST asserted by host. Shutting down the PCIe link!\n"); + qcom_pcie_perst_assert(pci); + } else { + dev_dbg(dev, "PERST de-asserted by host. Starting link training!\n"); + qcom_pcie_perst_deassert(pci); + } + + irq_set_irq_type(gpiod_to_irq(pcie_ep->reset), + (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW)); + + return IRQ_HANDLED; +} + +static int qcom_pcie_ep_enable_irq_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + struct device *dev = pcie_ep->pci.dev; + char *name; + int ret; + + name = devm_kasprintf(dev, GFP_KERNEL, "qcom_pcie_ep_global_irq%d", + pcie_ep->pci.ep.epc->domain_nr); + if (!name) + return -ENOMEM; + + pcie_ep->global_irq = platform_get_irq_byname(pdev, "global"); + if (pcie_ep->global_irq < 0) + return pcie_ep->global_irq; + + ret = devm_request_threaded_irq(&pdev->dev, pcie_ep->global_irq, NULL, + qcom_pcie_ep_global_irq_thread, + IRQF_ONESHOT, + name, pcie_ep); + if (ret) { + dev_err(&pdev->dev, "Failed to request Global IRQ\n"); + return ret; + } + + name = devm_kasprintf(dev, GFP_KERNEL, "qcom_pcie_ep_perst_irq%d", + pcie_ep->pci.ep.epc->domain_nr); + if (!name) + return -ENOMEM; + + pcie_ep->perst_irq = gpiod_to_irq(pcie_ep->reset); + irq_set_status_flags(pcie_ep->perst_irq, IRQ_NOAUTOEN); + ret = devm_request_threaded_irq(&pdev->dev, pcie_ep->perst_irq, NULL, + qcom_pcie_ep_perst_irq_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + name, pcie_ep); + if (ret) { + dev_err(&pdev->dev, "Failed to request PERST IRQ\n"); + disable_irq(pcie_ep->global_irq); + return ret; + } + + return 0; +} + +static int qcom_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + 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 int qcom_pcie_ep_link_transition_count(struct seq_file *s, void *data) +{ + struct qcom_pcie_ep *pcie_ep = (struct qcom_pcie_ep *) + dev_get_drvdata(s->private); + + seq_printf(s, "L0s transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_PM_LINKST_IN_L0S)); + + seq_printf(s, "L1 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_PM_LINKST_IN_L1)); + + seq_printf(s, "L1.1 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L1)); + + seq_printf(s, "L1.2 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L2)); + + seq_printf(s, "L2 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_PM_LINKST_IN_L2)); + + return 0; +} + +static void qcom_pcie_ep_init_debugfs(struct qcom_pcie_ep *pcie_ep) +{ + struct dw_pcie *pci = &pcie_ep->pci; + + debugfs_create_devm_seqfile(pci->dev, "link_transition_count", pcie_ep->debugfs, + qcom_pcie_ep_link_transition_count); +} + +static const struct pci_epc_features qcom_pcie_epc_features = { + .linkup_notifier = true, + .msi_capable = true, + .align = SZ_4K, + .bar[BAR_0] = { .only_64bit = true, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .only_64bit = true, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, +}; + +static const struct pci_epc_features * +qcom_pcie_epc_get_features(struct dw_pcie_ep *pci_ep) +{ + return &qcom_pcie_epc_features; +} + +static void qcom_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + for (bar = BAR_0; bar <= BAR_5; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static const struct dw_pcie_ep_ops pci_ep_ops = { + .init = qcom_pcie_ep_init, + .raise_irq = qcom_pcie_ep_raise_irq, + .get_features = qcom_pcie_epc_get_features, +}; + +static int qcom_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct qcom_pcie_ep *pcie_ep; + char *name; + int ret; + + pcie_ep = devm_kzalloc(dev, sizeof(*pcie_ep), GFP_KERNEL); + if (!pcie_ep) + return -ENOMEM; + + pcie_ep->pci.dev = dev; + pcie_ep->pci.ops = &pci_ops; + pcie_ep->pci.ep.ops = &pci_ep_ops; + + pcie_ep->cfg = of_device_get_match_data(dev); + if (pcie_ep->cfg && pcie_ep->cfg->hdma_support) { + pcie_ep->pci.edma.ll_wr_cnt = 8; + pcie_ep->pci.edma.ll_rd_cnt = 8; + pcie_ep->pci.edma.mf = EDMA_MF_HDMA_NATIVE; + } + + platform_set_drvdata(pdev, pcie_ep); + + ret = qcom_pcie_ep_get_resources(pdev, pcie_ep); + if (ret) + return ret; + + ret = dw_pcie_ep_init(&pcie_ep->pci.ep); + if (ret) { + dev_err(dev, "Failed to initialize endpoint: %d\n", ret); + return ret; + } + + ret = qcom_pcie_ep_enable_irq_resources(pdev, pcie_ep); + if (ret) + goto err_ep_deinit; + + name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node); + if (!name) { + ret = -ENOMEM; + goto err_disable_irqs; + } + + pcie_ep->debugfs = debugfs_create_dir(name, NULL); + qcom_pcie_ep_init_debugfs(pcie_ep); + + return 0; + +err_disable_irqs: + disable_irq(pcie_ep->global_irq); + disable_irq(pcie_ep->perst_irq); + +err_ep_deinit: + dw_pcie_ep_deinit(&pcie_ep->pci.ep); + + return ret; +} + +static void qcom_pcie_ep_remove(struct platform_device *pdev) +{ + struct qcom_pcie_ep *pcie_ep = platform_get_drvdata(pdev); + + disable_irq(pcie_ep->global_irq); + disable_irq(pcie_ep->perst_irq); + + debugfs_remove_recursive(pcie_ep->debugfs); + + if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED) + return; + + qcom_pcie_disable_resources(pcie_ep); +} + +static const struct qcom_pcie_ep_cfg cfg_1_34_0 = { + .hdma_support = true, + .override_no_snoop = true, + .disable_mhi_ram_parity_check = true, +}; + +static const struct of_device_id qcom_pcie_ep_match[] = { + { .compatible = "qcom,sa8775p-pcie-ep", .data = &cfg_1_34_0}, + { .compatible = "qcom,sdx55-pcie-ep", }, + { .compatible = "qcom,sm8450-pcie-ep", }, + { .compatible = "qcom,sar2130p-pcie-ep", }, + { } +}; +MODULE_DEVICE_TABLE(of, qcom_pcie_ep_match); + +static struct platform_driver qcom_pcie_ep_driver = { + .probe = qcom_pcie_ep_probe, + .remove = qcom_pcie_ep_remove, + .driver = { + .name = "qcom-pcie-ep", + .of_match_table = qcom_pcie_ep_match, + }, +}; +builtin_platform_driver(qcom_pcie_ep_driver); + +MODULE_AUTHOR("Siddartha Mohanadoss <smohanad@codeaurora.org>"); +MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>"); +MODULE_DESCRIPTION("Qualcomm PCIe Endpoint controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index d185ea5fe996..7b92e7a1c0d9 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -9,27 +9,84 @@ */ #include <linux/clk.h> +#include <linux/crc8.h> +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> +#include <linux/interconnect.h> #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iopoll.h> #include <linux/kernel.h> +#include <linux/limits.h> #include <linux/init.h> -#include <linux/of_device.h> -#include <linux/of_gpio.h> +#include <linux/of.h> +#include <linux/of_pci.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/pm_opp.h> #include <linux/pm_runtime.h> #include <linux/platform_device.h> +#include <linux/phy/pcie.h> #include <linux/phy/phy.h> #include <linux/regulator/consumer.h> #include <linux/reset.h> #include <linux/slab.h> #include <linux/types.h> +#include <linux/units.h> +#include "../../pci.h" +#include "../pci-host-common.h" #include "pcie-designware.h" - -#define PCIE20_PARF_SYS_CTRL 0x00 +#include "pcie-qcom-common.h" + +/* PARF registers */ +#define PARF_SYS_CTRL 0x00 +#define PARF_PM_CTRL 0x20 +#define PARF_PCS_DEEMPH 0x34 +#define PARF_PCS_SWING 0x38 +#define PARF_PHY_CTRL 0x40 +#define PARF_PHY_REFCLK 0x4c +#define PARF_CONFIG_BITS 0x50 +#define PARF_DBI_BASE_ADDR 0x168 +#define PARF_SLV_ADDR_SPACE_SIZE 0x16c +#define PARF_MHI_CLOCK_RESET_CTRL 0x174 +#define PARF_AXI_MSTR_WR_ADDR_HALT 0x178 +#define PARF_AXI_MSTR_WR_ADDR_HALT_V2 0x1a8 +#define PARF_Q2A_FLUSH 0x1ac +#define PARF_LTSSM 0x1b0 +#define PARF_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 +#define PARF_DBI_BASE_ADDR_V2_HI 0x354 +#define PARF_SLV_ADDR_SPACE_SIZE_V2 0x358 +#define PARF_SLV_ADDR_SPACE_SIZE_V2_HI 0x35c +#define PARF_NO_SNOOP_OVERRIDE 0x3d4 +#define PARF_ATU_BASE_ADDR 0x634 +#define PARF_ATU_BASE_ADDR_HI 0x638 +#define PARF_DEVICE_TYPE 0x1000 +#define PARF_BDF_TO_SID_TABLE_N 0x2000 +#define PARF_BDF_TO_SID_CFG 0x2c00 + +/* ELBI registers */ +#define ELBI_SYS_CTRL 0x04 + +/* DBI registers */ +#define AXI_MSTR_RESP_COMP_CTRL0 0x818 +#define AXI_MSTR_RESP_COMP_CTRL1 0x81c + +/* MHI registers */ +#define PARF_DEBUG_CNT_PM_LINKST_IN_L2 0xc04 +#define PARF_DEBUG_CNT_PM_LINKST_IN_L1 0xc0c +#define PARF_DEBUG_CNT_PM_LINKST_IN_L0S 0xc10 +#define PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L1 0xc84 +#define PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L2 0xc88 + +/* PARF_SYS_CTRL register fields */ +#define MAC_PHY_POWERDOWN_IN_P2_D_MUX_EN BIT(29) #define MST_WAKEUP_EN BIT(13) #define SLV_WAKEUP_EN BIT(12) #define MSTR_ACLK_CGC_DIS BIT(10) @@ -39,104 +96,139 @@ #define L23_CLK_RMV_DIS BIT(2) #define L1_CLK_RMV_DIS BIT(1) -#define PCIE20_COMMAND_STATUS 0x04 -#define CMD_BME_VAL 0x4 -#define PCIE20_DEVICE_CONTROL2_STATUS2 0x98 -#define PCIE_CAP_CPL_TIMEOUT_DISABLE 0x10 - -#define PCIE20_PARF_PHY_CTRL 0x40 -#define PCIE20_PARF_PHY_REFCLK 0x4C -#define PCIE20_PARF_DBI_BASE_ADDR 0x168 -#define PCIE20_PARF_SLV_ADDR_SPACE_SIZE 0x16C -#define PCIE20_PARF_MHI_CLOCK_RESET_CTRL 0x174 -#define PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT 0x178 -#define PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2 0x1A8 -#define PCIE20_PARF_LTSSM 0x1B0 -#define PCIE20_PARF_SID_OFFSET 0x234 -#define PCIE20_PARF_BDF_TRANSLATE_CFG 0x24C - -#define PCIE20_ELBI_SYS_CTRL 0x04 -#define PCIE20_ELBI_SYS_CTRL_LT_ENABLE BIT(0) - -#define PCIE20_AXI_MSTR_RESP_COMP_CTRL0 0x818 +/* PARF_PM_CTRL register fields */ +#define REQ_NOT_ENTR_L1 BIT(5) + +/* PARF_PCS_DEEMPH register fields */ +#define PCS_DEEMPH_TX_DEEMPH_GEN1(x) FIELD_PREP(GENMASK(21, 16), x) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(x) FIELD_PREP(GENMASK(13, 8), x) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(x) FIELD_PREP(GENMASK(5, 0), x) + +/* PARF_PCS_SWING register fields */ +#define PCS_SWING_TX_SWING_FULL(x) FIELD_PREP(GENMASK(14, 8), x) +#define PCS_SWING_TX_SWING_LOW(x) FIELD_PREP(GENMASK(6, 0), x) + +/* PARF_PHY_CTRL register fields */ +#define PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK GENMASK(20, 16) +#define PHY_CTRL_PHY_TX0_TERM_OFFSET(x) FIELD_PREP(PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK, x) +#define PHY_TEST_PWR_DOWN BIT(0) + +/* PARF_PHY_REFCLK register fields */ +#define PHY_REFCLK_SSP_EN BIT(16) +#define PHY_REFCLK_USE_PAD BIT(12) + +/* PARF_CONFIG_BITS register fields */ +#define PHY_RX0_EQ(x) FIELD_PREP(GENMASK(26, 24), x) + +/* PARF_SLV_ADDR_SPACE_SIZE register value */ +#define SLV_ADDR_SPACE_SZ 0x80000000 + +/* PARF_MHI_CLOCK_RESET_CTRL register fields */ +#define AHB_CLK_EN BIT(0) +#define MSTR_AXI_CLK_EN BIT(1) +#define BYPASS BIT(4) + +/* PARF_AXI_MSTR_WR_ADDR_HALT register fields */ +#define EN BIT(31) + +/* 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) + +/* PARF_DEVICE_TYPE register fields */ +#define DEVICE_TYPE_RC 0x4 + +/* PARF_BDF_TO_SID_CFG fields */ +#define BDF_TO_SID_BYPASS BIT(0) + +/* ELBI_SYS_CTRL register fields */ +#define ELBI_SYS_CTRL_LT_ENABLE BIT(0) + +/* AXI_MSTR_RESP_COMP_CTRL0 register fields */ #define CFG_REMOTE_RD_REQ_BRIDGE_SIZE_2K 0x4 #define CFG_REMOTE_RD_REQ_BRIDGE_SIZE_4K 0x5 -#define PCIE20_AXI_MSTR_RESP_COMP_CTRL1 0x81c -#define CFG_BRIDGE_SB_INIT BIT(0) - -#define PCIE20_CAP 0x70 -#define PCIE20_CAP_LINK_CAPABILITIES (PCIE20_CAP + 0xC) -#define PCIE20_CAP_ACTIVE_STATE_LINK_PM_SUPPORT (BIT(10) | BIT(11)) -#define PCIE20_CAP_LINK_1 (PCIE20_CAP + 0x14) -#define PCIE_CAP_LINK1_VAL 0x2FD7F -#define PCIE20_PARF_Q2A_FLUSH 0x1AC +/* AXI_MSTR_RESP_COMP_CTRL1 register fields */ +#define CFG_BRIDGE_SB_INIT BIT(0) -#define PCIE20_MISC_CONTROL_1_REG 0x8BC -#define DBI_RO_WR_EN 1 +/* PCI_EXP_SLTCAP register fields */ +#define PCIE_CAP_SLOT_POWER_LIMIT_VAL FIELD_PREP(PCI_EXP_SLTCAP_SPLV, 250) +#define PCIE_CAP_SLOT_POWER_LIMIT_SCALE FIELD_PREP(PCI_EXP_SLTCAP_SPLS, 1) +#define PCIE_CAP_SLOT_VAL (PCI_EXP_SLTCAP_ABP | \ + PCI_EXP_SLTCAP_PCP | \ + PCI_EXP_SLTCAP_MRLSP | \ + PCI_EXP_SLTCAP_AIP | \ + PCI_EXP_SLTCAP_PIP | \ + PCI_EXP_SLTCAP_HPS | \ + PCI_EXP_SLTCAP_EIP | \ + PCIE_CAP_SLOT_POWER_LIMIT_VAL | \ + PCIE_CAP_SLOT_POWER_LIMIT_SCALE) #define PERST_DELAY_US 1000 -#define PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE 0x358 -#define SLV_ADDR_SPACE_SZ 0x10000000 +#define QCOM_PCIE_CRC8_POLYNOMIAL (BIT(2) | BIT(1) | BIT(0)) -#define QCOM_PCIE_2_1_0_MAX_SUPPLY 3 -struct qcom_pcie_resources_2_1_0 { - struct clk *iface_clk; - struct clk *core_clk; - struct clk *phy_clk; - struct reset_control *pci_reset; - struct reset_control *axi_reset; - struct reset_control *ahb_reset; - struct reset_control *por_reset; - struct reset_control *phy_reset; - struct regulator_bulk_data supplies[QCOM_PCIE_2_1_0_MAX_SUPPLY]; -}; +#define QCOM_PCIE_LINK_SPEED_TO_BW(speed) \ + Mbps_to_icc(PCIE_SPEED2MBS_ENC(pcie_link_speed[speed])) struct qcom_pcie_resources_1_0_0 { - struct clk *iface; - struct clk *aux; - struct clk *master_bus; - struct clk *slave_bus; + struct clk_bulk_data *clks; + int num_clks; struct reset_control *core; struct regulator *vdda; }; -#define QCOM_PCIE_2_3_2_MAX_SUPPLY 2 +#define QCOM_PCIE_2_1_0_MAX_RESETS 6 +#define QCOM_PCIE_2_1_0_MAX_SUPPLY 3 +struct qcom_pcie_resources_2_1_0 { + struct clk_bulk_data *clks; + int num_clks; + struct reset_control_bulk_data resets[QCOM_PCIE_2_1_0_MAX_RESETS]; + int num_resets; + struct regulator_bulk_data supplies[QCOM_PCIE_2_1_0_MAX_SUPPLY]; +}; + +#define QCOM_PCIE_2_3_2_MAX_SUPPLY 2 struct qcom_pcie_resources_2_3_2 { - struct clk *aux_clk; - struct clk *master_clk; - struct clk *slave_clk; - struct clk *cfg_clk; - struct clk *pipe_clk; + struct clk_bulk_data *clks; + int num_clks; struct regulator_bulk_data supplies[QCOM_PCIE_2_3_2_MAX_SUPPLY]; }; +#define QCOM_PCIE_2_3_3_MAX_RESETS 7 +struct qcom_pcie_resources_2_3_3 { + struct clk_bulk_data *clks; + int num_clks; + struct reset_control_bulk_data rst[QCOM_PCIE_2_3_3_MAX_RESETS]; +}; + +#define QCOM_PCIE_2_4_0_MAX_RESETS 12 struct qcom_pcie_resources_2_4_0 { - struct clk *aux_clk; - struct clk *master_clk; - struct clk *slave_clk; - struct reset_control *axi_m_reset; - struct reset_control *axi_s_reset; - struct reset_control *pipe_reset; - struct reset_control *axi_m_vmid_reset; - struct reset_control *axi_s_xpu_reset; - struct reset_control *parf_reset; - struct reset_control *phy_reset; - struct reset_control *axi_m_sticky_reset; - struct reset_control *pipe_sticky_reset; - struct reset_control *pwr_reset; - struct reset_control *ahb_reset; - struct reset_control *phy_ahb_reset; + struct clk_bulk_data *clks; + int num_clks; + struct reset_control_bulk_data resets[QCOM_PCIE_2_4_0_MAX_RESETS]; + int num_resets; }; -struct qcom_pcie_resources_2_3_3 { - struct clk *iface; - struct clk *axi_m_clk; - struct clk *axi_s_clk; - struct clk *ahb_clk; - struct clk *aux_clk; - struct reset_control *rst[7]; +#define QCOM_PCIE_2_7_0_MAX_SUPPLIES 2 +struct qcom_pcie_resources_2_7_0 { + struct clk_bulk_data *clks; + int num_clks; + struct regulator_bulk_data supplies[QCOM_PCIE_2_7_0_MAX_SUPPLIES]; + struct reset_control *rst; +}; + +struct qcom_pcie_resources_2_9_0 { + struct clk_bulk_data *clks; + int num_clks; + struct reset_control *rst; }; union qcom_pcie_resources { @@ -145,6 +237,8 @@ union qcom_pcie_resources { struct qcom_pcie_resources_2_3_2 v2_3_2; struct qcom_pcie_resources_2_3_3 v2_3_3; struct qcom_pcie_resources_2_4_0 v2_4_0; + struct qcom_pcie_resources_2_7_0 v2_7_0; + struct qcom_pcie_resources_2_9_0 v2_9_0; }; struct qcom_pcie; @@ -153,57 +247,178 @@ struct qcom_pcie_ops { int (*get_resources)(struct qcom_pcie *pcie); int (*init)(struct qcom_pcie *pcie); int (*post_init)(struct qcom_pcie *pcie); + void (*host_post_init)(struct qcom_pcie *pcie); void (*deinit)(struct qcom_pcie *pcie); - void (*post_deinit)(struct qcom_pcie *pcie); void (*ltssm_enable)(struct qcom_pcie *pcie); + int (*config_sid)(struct qcom_pcie *pcie); +}; + + /** + * struct qcom_pcie_cfg - Per SoC config struct + * @ops: qcom PCIe ops structure + * @override_no_snoop: Override NO_SNOOP attribute in TLP to enable cache + * snooping + * @firmware_managed: Set if the Root Complex is firmware managed + */ +struct qcom_pcie_cfg { + const struct qcom_pcie_ops *ops; + bool override_no_snoop; + bool firmware_managed; + bool no_l0s; +}; + +struct qcom_pcie_port { + struct list_head list; + struct gpio_desc *reset; + struct phy *phy; }; struct qcom_pcie { struct dw_pcie *pci; void __iomem *parf; /* DT parf */ - void __iomem *elbi; /* DT elbi */ + void __iomem *mhi; union qcom_pcie_resources res; - struct phy *phy; - struct gpio_desc *reset; - const struct qcom_pcie_ops *ops; + struct icc_path *icc_mem; + struct icc_path *icc_cpu; + const struct qcom_pcie_cfg *cfg; + struct dentry *debugfs; + struct list_head ports; + bool suspended; + bool use_pm_opp; }; #define to_qcom_pcie(x) dev_get_drvdata((x)->dev) -static void qcom_ep_reset_assert(struct qcom_pcie *pcie) +static void qcom_perst_assert(struct qcom_pcie *pcie, bool assert) { - gpiod_set_value_cansleep(pcie->reset, 1); + struct qcom_pcie_port *port; + int val = assert ? 1 : 0; + + list_for_each_entry(port, &pcie->ports, list) + gpiod_set_value_cansleep(port->reset, val); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); } +static void qcom_ep_reset_assert(struct qcom_pcie *pcie) +{ + qcom_perst_assert(pcie, true); +} + static void qcom_ep_reset_deassert(struct qcom_pcie *pcie) { - gpiod_set_value_cansleep(pcie->reset, 0); - usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); + /* Ensure that PERST has been asserted for at least 100 ms */ + msleep(PCIE_T_PVPERL_MS); + qcom_perst_assert(pcie, false); } -static int qcom_pcie_establish_link(struct qcom_pcie *pcie) +static int qcom_pcie_start_link(struct dw_pcie *pci) { - struct dw_pcie *pci = pcie->pci; + struct qcom_pcie *pcie = to_qcom_pcie(pci); - if (dw_pcie_link_up(pci)) - return 0; + 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->ops->ltssm_enable) - pcie->ops->ltssm_enable(pcie); + if (pcie->cfg->ops->ltssm_enable) + pcie->cfg->ops->ltssm_enable(pcie); + + return 0; +} + +static void qcom_pcie_clear_aspm_l0s(struct dw_pcie *pci) +{ + struct qcom_pcie *pcie = to_qcom_pcie(pci); + u16 offset; + u32 val; + + if (!pcie->cfg->no_l0s) + return; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + dw_pcie_dbi_ro_wr_en(pci); + + val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_ASPM_L0S; + writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP); + + dw_pcie_dbi_ro_wr_dis(pci); +} + +static void qcom_pcie_clear_hpc(struct dw_pcie *pci) +{ + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; + + dw_pcie_dbi_ro_wr_en(pci); + + val = readl(pci->dbi_base + offset + PCI_EXP_SLTCAP); + val &= ~PCI_EXP_SLTCAP_HPC; + writel(val, pci->dbi_base + offset + PCI_EXP_SLTCAP); - return dw_pcie_wait_for_link(pci); + dw_pcie_dbi_ro_wr_dis(pci); +} + +static void qcom_pcie_configure_dbi_base(struct qcom_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + + if (pci->dbi_phys_addr) { + /* + * PARF_DBI_BASE_ADDR register is in CPU domain and require to + * be programmed with CPU physical address. + */ + writel(lower_32_bits(pci->dbi_phys_addr), pcie->parf + + PARF_DBI_BASE_ADDR); + writel(SLV_ADDR_SPACE_SZ, pcie->parf + + PARF_SLV_ADDR_SPACE_SIZE); + } +} + +static void qcom_pcie_configure_dbi_atu_base(struct qcom_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + + if (pci->dbi_phys_addr) { + /* + * PARF_DBI_BASE_ADDR_V2 and PARF_ATU_BASE_ADDR registers are + * in CPU domain and require to be programmed with CPU + * physical addresses. + */ + writel(lower_32_bits(pci->dbi_phys_addr), pcie->parf + + PARF_DBI_BASE_ADDR_V2); + writel(upper_32_bits(pci->dbi_phys_addr), pcie->parf + + PARF_DBI_BASE_ADDR_V2_HI); + + if (pci->atu_phys_addr) { + writel(lower_32_bits(pci->atu_phys_addr), pcie->parf + + PARF_ATU_BASE_ADDR); + writel(upper_32_bits(pci->atu_phys_addr), pcie->parf + + PARF_ATU_BASE_ADDR_HI); + } + + writel(0x0, pcie->parf + PARF_SLV_ADDR_SPACE_SIZE_V2); + writel(SLV_ADDR_SPACE_SZ, pcie->parf + + PARF_SLV_ADDR_SPACE_SIZE_V2_HI); + } } 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 + PCIE20_ELBI_SYS_CTRL); - val |= PCIE20_ELBI_SYS_CTRL_LT_ENABLE; - writel(val, pcie->elbi + PCIE20_ELBI_SYS_CTRL); + val = readl(pci->elbi_base + ELBI_SYS_CTRL); + val |= ELBI_SYS_CTRL_LT_ENABLE; + writel(val, pci->elbi_base + ELBI_SYS_CTRL); } static int qcom_pcie_get_resources_2_1_0(struct qcom_pcie *pcie) @@ -211,6 +426,7 @@ static int qcom_pcie_get_resources_2_1_0(struct qcom_pcie *pcie) struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; + bool is_apq = of_device_is_compatible(dev->of_node, "qcom,pcie-apq8064"); int ret; res->supplies[0].supply = "vdda"; @@ -221,50 +437,37 @@ static int qcom_pcie_get_resources_2_1_0(struct qcom_pcie *pcie) if (ret) return ret; - res->iface_clk = devm_clk_get(dev, "iface"); - if (IS_ERR(res->iface_clk)) - return PTR_ERR(res->iface_clk); - - res->core_clk = devm_clk_get(dev, "core"); - if (IS_ERR(res->core_clk)) - return PTR_ERR(res->core_clk); - - res->phy_clk = devm_clk_get(dev, "phy"); - if (IS_ERR(res->phy_clk)) - return PTR_ERR(res->phy_clk); - - res->pci_reset = devm_reset_control_get_exclusive(dev, "pci"); - if (IS_ERR(res->pci_reset)) - return PTR_ERR(res->pci_reset); - - res->axi_reset = devm_reset_control_get_exclusive(dev, "axi"); - if (IS_ERR(res->axi_reset)) - return PTR_ERR(res->axi_reset); - - res->ahb_reset = devm_reset_control_get_exclusive(dev, "ahb"); - if (IS_ERR(res->ahb_reset)) - return PTR_ERR(res->ahb_reset); + res->num_clks = devm_clk_bulk_get_all(dev, &res->clks); + if (res->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return res->num_clks; + } - res->por_reset = devm_reset_control_get_exclusive(dev, "por"); - if (IS_ERR(res->por_reset)) - return PTR_ERR(res->por_reset); + res->resets[0].id = "pci"; + res->resets[1].id = "axi"; + res->resets[2].id = "ahb"; + res->resets[3].id = "por"; + res->resets[4].id = "phy"; + res->resets[5].id = "ext"; + + /* ext is optional on APQ8016 */ + res->num_resets = is_apq ? 5 : 6; + ret = devm_reset_control_bulk_get_exclusive(dev, res->num_resets, res->resets); + if (ret < 0) + return ret; - res->phy_reset = devm_reset_control_get_exclusive(dev, "phy"); - return PTR_ERR_OR_ZERO(res->phy_reset); + return 0; } static void qcom_pcie_deinit_2_1_0(struct qcom_pcie *pcie) { struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; - reset_control_assert(res->pci_reset); - reset_control_assert(res->axi_reset); - reset_control_assert(res->ahb_reset); - reset_control_assert(res->por_reset); - reset_control_assert(res->pci_reset); - clk_disable_unprepare(res->iface_clk); - clk_disable_unprepare(res->core_clk); - clk_disable_unprepare(res->phy_clk); + clk_bulk_disable_unprepare(res->num_clks, res->clks); + reset_control_bulk_assert(res->num_resets, res->resets); + + writel(1, pcie->parf + PARF_PHY_CTRL); + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); } @@ -273,101 +476,89 @@ static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie) struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; - u32 val; int ret; - ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies); + /* reset the PCIe interface as uboot can leave it undefined state */ + ret = reset_control_bulk_assert(res->num_resets, res->resets); if (ret < 0) { - dev_err(dev, "cannot enable regulators\n"); + dev_err(dev, "cannot assert resets\n"); return ret; } - ret = reset_control_assert(res->ahb_reset); - if (ret) { - dev_err(dev, "cannot assert ahb reset\n"); - goto err_assert_ahb; - } - - ret = clk_prepare_enable(res->iface_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable iface clock\n"); - goto err_assert_ahb; + ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies); + if (ret < 0) { + dev_err(dev, "cannot enable regulators\n"); + return ret; } - ret = clk_prepare_enable(res->phy_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable phy clock\n"); - goto err_clk_phy; + ret = reset_control_bulk_deassert(res->num_resets, res->resets); + if (ret < 0) { + dev_err(dev, "cannot deassert resets\n"); + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); + return ret; } - ret = clk_prepare_enable(res->core_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable core clock\n"); - goto err_clk_core; - } + return 0; +} - ret = reset_control_deassert(res->ahb_reset); - if (ret) { - dev_err(dev, "cannot deassert ahb reset\n"); - goto err_deassert_ahb; - } +static int qcom_pcie_post_init_2_1_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + struct device_node *node = dev->of_node; + u32 val; + int ret; /* enable PCIe clocks and resets */ - val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL); - val &= ~BIT(0); - writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); - - /* enable external reference clock */ - val = readl(pcie->parf + PCIE20_PARF_PHY_REFCLK); - val |= BIT(16); - writel(val, pcie->parf + PCIE20_PARF_PHY_REFCLK); + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~PHY_TEST_PWR_DOWN; + writel(val, pcie->parf + PARF_PHY_CTRL); - ret = reset_control_deassert(res->phy_reset); - if (ret) { - dev_err(dev, "cannot deassert phy reset\n"); + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); + if (ret) return ret; - } - ret = reset_control_deassert(res->pci_reset); - if (ret) { - dev_err(dev, "cannot deassert pci reset\n"); - return ret; + if (of_device_is_compatible(node, "qcom,pcie-ipq8064") || + of_device_is_compatible(node, "qcom,pcie-ipq8064-v2")) { + writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(34), + pcie->parf + PARF_PCS_DEEMPH); + writel(PCS_SWING_TX_SWING_FULL(120) | + PCS_SWING_TX_SWING_LOW(120), + pcie->parf + PARF_PCS_SWING); + writel(PHY_RX0_EQ(4), pcie->parf + PARF_CONFIG_BITS); } - ret = reset_control_deassert(res->por_reset); - if (ret) { - dev_err(dev, "cannot deassert por reset\n"); - return ret; + if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) { + /* set TX termination offset */ + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK; + val |= PHY_CTRL_PHY_TX0_TERM_OFFSET(7); + writel(val, pcie->parf + PARF_PHY_CTRL); } - ret = reset_control_deassert(res->axi_reset); - if (ret) { - dev_err(dev, "cannot deassert axi reset\n"); - return ret; - } + /* enable external reference clock */ + val = readl(pcie->parf + PARF_PHY_REFCLK); + /* USE_PAD is required only for ipq806x */ + if (!of_device_is_compatible(node, "qcom,pcie-apq8064")) + val &= ~PHY_REFCLK_USE_PAD; + val |= PHY_REFCLK_SSP_EN; + writel(val, pcie->parf + PARF_PHY_REFCLK); /* wait for clock acquisition */ usleep_range(1000, 1500); - /* Set the Max TLP size to 2K, instead of using default of 4K */ writel(CFG_REMOTE_RD_REQ_BRIDGE_SIZE_2K, - pci->dbi_base + PCIE20_AXI_MSTR_RESP_COMP_CTRL0); + pci->dbi_base + AXI_MSTR_RESP_COMP_CTRL0); writel(CFG_BRIDGE_SB_INIT, - pci->dbi_base + PCIE20_AXI_MSTR_RESP_COMP_CTRL1); + pci->dbi_base + AXI_MSTR_RESP_COMP_CTRL1); - return 0; - -err_deassert_ahb: - clk_disable_unprepare(res->core_clk); -err_clk_core: - clk_disable_unprepare(res->phy_clk); -err_clk_phy: - clk_disable_unprepare(res->iface_clk); -err_assert_ahb: - regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); + qcom_pcie_clear_hpc(pcie->pci); - return ret; + return 0; } static int qcom_pcie_get_resources_1_0_0(struct qcom_pcie *pcie) @@ -380,21 +571,11 @@ static int qcom_pcie_get_resources_1_0_0(struct qcom_pcie *pcie) if (IS_ERR(res->vdda)) return PTR_ERR(res->vdda); - res->iface = devm_clk_get(dev, "iface"); - if (IS_ERR(res->iface)) - return PTR_ERR(res->iface); - - res->aux = devm_clk_get(dev, "aux"); - if (IS_ERR(res->aux)) - return PTR_ERR(res->aux); - - res->master_bus = devm_clk_get(dev, "master_bus"); - if (IS_ERR(res->master_bus)) - return PTR_ERR(res->master_bus); - - res->slave_bus = devm_clk_get(dev, "slave_bus"); - if (IS_ERR(res->slave_bus)) - return PTR_ERR(res->slave_bus); + res->num_clks = devm_clk_bulk_get_all(dev, &res->clks); + if (res->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return res->num_clks; + } res->core = devm_reset_control_get_exclusive(dev, "core"); return PTR_ERR_OR_ZERO(res->core); @@ -405,10 +586,7 @@ static void qcom_pcie_deinit_1_0_0(struct qcom_pcie *pcie) struct qcom_pcie_resources_1_0_0 *res = &pcie->res.v1_0_0; reset_control_assert(res->core); - clk_disable_unprepare(res->slave_bus); - clk_disable_unprepare(res->master_bus); - clk_disable_unprepare(res->iface); - clk_disable_unprepare(res->aux); + clk_bulk_disable_unprepare(res->num_clks, res->clks); regulator_disable(res->vdda); } @@ -425,59 +603,54 @@ static int qcom_pcie_init_1_0_0(struct qcom_pcie *pcie) return ret; } - ret = clk_prepare_enable(res->aux); + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); if (ret) { - dev_err(dev, "cannot prepare/enable aux clock\n"); - goto err_res; + dev_err(dev, "cannot prepare/enable clocks\n"); + goto err_assert_reset; } - ret = clk_prepare_enable(res->iface); + ret = regulator_enable(res->vdda); if (ret) { - dev_err(dev, "cannot prepare/enable iface clock\n"); - goto err_aux; + dev_err(dev, "cannot enable vdda regulator\n"); + goto err_disable_clks; } - ret = clk_prepare_enable(res->master_bus); - if (ret) { - dev_err(dev, "cannot prepare/enable master_bus clock\n"); - goto err_iface; - } + return 0; - ret = clk_prepare_enable(res->slave_bus); - if (ret) { - dev_err(dev, "cannot prepare/enable slave_bus clock\n"); - goto err_master; - } +err_disable_clks: + clk_bulk_disable_unprepare(res->num_clks, res->clks); +err_assert_reset: + reset_control_assert(res->core); - ret = regulator_enable(res->vdda); - if (ret) { - dev_err(dev, "cannot enable vdda regulator\n"); - goto err_slave; - } + return ret; +} - /* change DBI base address */ - writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR); +static int qcom_pcie_post_init_1_0_0(struct qcom_pcie *pcie) +{ + qcom_pcie_configure_dbi_base(pcie); if (IS_ENABLED(CONFIG_PCI_MSI)) { - u32 val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT); + u32 val = readl(pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT); - val |= BIT(31); - writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT); + val |= EN; + writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT); } + qcom_pcie_clear_hpc(pcie->pci); + return 0; -err_slave: - clk_disable_unprepare(res->slave_bus); -err_master: - clk_disable_unprepare(res->master_bus); -err_iface: - clk_disable_unprepare(res->iface); -err_aux: - clk_disable_unprepare(res->aux); -err_res: - reset_control_assert(res->core); +} - return ret; +static int qcom_pcie_assert_perst(struct dw_pcie *pci, bool assert) +{ + struct qcom_pcie *pcie = to_qcom_pcie(pci); + + if (assert) + qcom_ep_reset_assert(pcie); + else + qcom_ep_reset_deassert(pcie); + + return 0; } static void qcom_pcie_2_3_2_ltssm_enable(struct qcom_pcie *pcie) @@ -485,9 +658,9 @@ static void qcom_pcie_2_3_2_ltssm_enable(struct qcom_pcie *pcie) u32 val; /* enable link training */ - val = readl(pcie->parf + PCIE20_PARF_LTSSM); - val |= BIT(8); - writel(val, pcie->parf + PCIE20_PARF_LTSSM); + val = readl(pcie->parf + PARF_LTSSM); + val |= LTSSM_EN; + writel(val, pcie->parf + PARF_LTSSM); } static int qcom_pcie_get_resources_2_3_2(struct qcom_pcie *pcie) @@ -504,51 +677,28 @@ static int qcom_pcie_get_resources_2_3_2(struct qcom_pcie *pcie) if (ret) return ret; - res->aux_clk = devm_clk_get(dev, "aux"); - if (IS_ERR(res->aux_clk)) - return PTR_ERR(res->aux_clk); - - res->cfg_clk = devm_clk_get(dev, "cfg"); - if (IS_ERR(res->cfg_clk)) - return PTR_ERR(res->cfg_clk); - - res->master_clk = devm_clk_get(dev, "bus_master"); - if (IS_ERR(res->master_clk)) - return PTR_ERR(res->master_clk); - - res->slave_clk = devm_clk_get(dev, "bus_slave"); - if (IS_ERR(res->slave_clk)) - return PTR_ERR(res->slave_clk); + res->num_clks = devm_clk_bulk_get_all(dev, &res->clks); + if (res->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return res->num_clks; + } - res->pipe_clk = devm_clk_get(dev, "pipe"); - return PTR_ERR_OR_ZERO(res->pipe_clk); + return 0; } static void qcom_pcie_deinit_2_3_2(struct qcom_pcie *pcie) { struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2; - clk_disable_unprepare(res->slave_clk); - clk_disable_unprepare(res->master_clk); - clk_disable_unprepare(res->cfg_clk); - clk_disable_unprepare(res->aux_clk); - + clk_bulk_disable_unprepare(res->num_clks, res->clks); regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); } -static void qcom_pcie_post_deinit_2_3_2(struct qcom_pcie *pcie) -{ - struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2; - - clk_disable_unprepare(res->pipe_clk); -} - static int qcom_pcie_init_2_3_2(struct qcom_pcie *pcie) { struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; - u32 val; int ret; ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies); @@ -557,533 +707,594 @@ static int qcom_pcie_init_2_3_2(struct qcom_pcie *pcie) return ret; } - ret = clk_prepare_enable(res->aux_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable aux clock\n"); - goto err_aux_clk; - } - - ret = clk_prepare_enable(res->cfg_clk); + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); if (ret) { - dev_err(dev, "cannot prepare/enable cfg clock\n"); - goto err_cfg_clk; + dev_err(dev, "cannot prepare/enable clocks\n"); + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); + return ret; } - ret = clk_prepare_enable(res->master_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable master clock\n"); - goto err_master_clk; - } + return 0; +} - ret = clk_prepare_enable(res->slave_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable slave clock\n"); - goto err_slave_clk; - } +static int qcom_pcie_post_init_2_3_2(struct qcom_pcie *pcie) +{ + u32 val; /* enable PCIe clocks and resets */ - val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL); - val &= ~BIT(0); - writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~PHY_TEST_PWR_DOWN; + writel(val, pcie->parf + PARF_PHY_CTRL); - /* change DBI base address */ - writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR); + qcom_pcie_configure_dbi_base(pcie); /* MAC PHY_POWERDOWN MUX DISABLE */ - val = readl(pcie->parf + PCIE20_PARF_SYS_CTRL); - val &= ~BIT(29); - writel(val, pcie->parf + PCIE20_PARF_SYS_CTRL); - - val = readl(pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL); - val |= BIT(4); - writel(val, pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL); - - val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2); - val |= BIT(31); - writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2); + val = readl(pcie->parf + PARF_SYS_CTRL); + val &= ~MAC_PHY_POWERDOWN_IN_P2_D_MUX_EN; + writel(val, pcie->parf + PARF_SYS_CTRL); - return 0; + val = readl(pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + val |= BYPASS; + writel(val, pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); -err_slave_clk: - clk_disable_unprepare(res->master_clk); -err_master_clk: - clk_disable_unprepare(res->cfg_clk); -err_cfg_clk: - clk_disable_unprepare(res->aux_clk); + val = readl(pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); + val |= EN; + writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); -err_aux_clk: - regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); + qcom_pcie_clear_hpc(pcie->pci); - return ret; + return 0; } -static int qcom_pcie_post_init_2_3_2(struct qcom_pcie *pcie) +static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie) { - struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2; + struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; + bool is_ipq = of_device_is_compatible(dev->of_node, "qcom,pcie-ipq4019"); int ret; - ret = clk_prepare_enable(res->pipe_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable pipe clock\n"); - return ret; + res->num_clks = devm_clk_bulk_get_all(dev, &res->clks); + if (res->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return res->num_clks; } + res->resets[0].id = "axi_m"; + res->resets[1].id = "axi_s"; + res->resets[2].id = "axi_m_sticky"; + res->resets[3].id = "pipe_sticky"; + res->resets[4].id = "pwr"; + res->resets[5].id = "ahb"; + res->resets[6].id = "pipe"; + res->resets[7].id = "axi_m_vmid"; + res->resets[8].id = "axi_s_xpu"; + res->resets[9].id = "parf"; + res->resets[10].id = "phy"; + res->resets[11].id = "phy_ahb"; + + res->num_resets = is_ipq ? 12 : 6; + + ret = devm_reset_control_bulk_get_exclusive(dev, res->num_resets, res->resets); + if (ret < 0) + return ret; + return 0; } -static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie) +static void qcom_pcie_deinit_2_4_0(struct qcom_pcie *pcie) { struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; - struct dw_pcie *pci = pcie->pci; - struct device *dev = pci->dev; - - res->aux_clk = devm_clk_get(dev, "aux"); - if (IS_ERR(res->aux_clk)) - return PTR_ERR(res->aux_clk); - - res->master_clk = devm_clk_get(dev, "master_bus"); - if (IS_ERR(res->master_clk)) - return PTR_ERR(res->master_clk); - res->slave_clk = devm_clk_get(dev, "slave_bus"); - if (IS_ERR(res->slave_clk)) - return PTR_ERR(res->slave_clk); - - res->axi_m_reset = devm_reset_control_get_exclusive(dev, "axi_m"); - if (IS_ERR(res->axi_m_reset)) - return PTR_ERR(res->axi_m_reset); + reset_control_bulk_assert(res->num_resets, res->resets); + clk_bulk_disable_unprepare(res->num_clks, res->clks); +} - res->axi_s_reset = devm_reset_control_get_exclusive(dev, "axi_s"); - if (IS_ERR(res->axi_s_reset)) - return PTR_ERR(res->axi_s_reset); +static int qcom_pcie_init_2_4_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; - res->pipe_reset = devm_reset_control_get_exclusive(dev, "pipe"); - if (IS_ERR(res->pipe_reset)) - return PTR_ERR(res->pipe_reset); + ret = reset_control_bulk_assert(res->num_resets, res->resets); + if (ret < 0) { + dev_err(dev, "cannot assert resets\n"); + return ret; + } - res->axi_m_vmid_reset = devm_reset_control_get_exclusive(dev, - "axi_m_vmid"); - if (IS_ERR(res->axi_m_vmid_reset)) - return PTR_ERR(res->axi_m_vmid_reset); + usleep_range(10000, 12000); - res->axi_s_xpu_reset = devm_reset_control_get_exclusive(dev, - "axi_s_xpu"); - if (IS_ERR(res->axi_s_xpu_reset)) - return PTR_ERR(res->axi_s_xpu_reset); + ret = reset_control_bulk_deassert(res->num_resets, res->resets); + if (ret < 0) { + dev_err(dev, "cannot deassert resets\n"); + return ret; + } - res->parf_reset = devm_reset_control_get_exclusive(dev, "parf"); - if (IS_ERR(res->parf_reset)) - return PTR_ERR(res->parf_reset); + usleep_range(10000, 12000); - res->phy_reset = devm_reset_control_get_exclusive(dev, "phy"); - if (IS_ERR(res->phy_reset)) - return PTR_ERR(res->phy_reset); + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); + if (ret) { + reset_control_bulk_assert(res->num_resets, res->resets); + return ret; + } - res->axi_m_sticky_reset = devm_reset_control_get_exclusive(dev, - "axi_m_sticky"); - if (IS_ERR(res->axi_m_sticky_reset)) - return PTR_ERR(res->axi_m_sticky_reset); + return 0; +} - res->pipe_sticky_reset = devm_reset_control_get_exclusive(dev, - "pipe_sticky"); - if (IS_ERR(res->pipe_sticky_reset)) - return PTR_ERR(res->pipe_sticky_reset); +static int qcom_pcie_get_resources_2_3_3(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; - res->pwr_reset = devm_reset_control_get_exclusive(dev, "pwr"); - if (IS_ERR(res->pwr_reset)) - return PTR_ERR(res->pwr_reset); + res->num_clks = devm_clk_bulk_get_all(dev, &res->clks); + if (res->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return res->num_clks; + } - res->ahb_reset = devm_reset_control_get_exclusive(dev, "ahb"); - if (IS_ERR(res->ahb_reset)) - return PTR_ERR(res->ahb_reset); + res->rst[0].id = "axi_m"; + res->rst[1].id = "axi_s"; + res->rst[2].id = "pipe"; + res->rst[3].id = "axi_m_sticky"; + res->rst[4].id = "sticky"; + res->rst[5].id = "ahb"; + res->rst[6].id = "sleep"; - res->phy_ahb_reset = devm_reset_control_get_exclusive(dev, "phy_ahb"); - if (IS_ERR(res->phy_ahb_reset)) - return PTR_ERR(res->phy_ahb_reset); + ret = devm_reset_control_bulk_get_exclusive(dev, ARRAY_SIZE(res->rst), res->rst); + if (ret < 0) + return ret; return 0; } -static void qcom_pcie_deinit_2_4_0(struct qcom_pcie *pcie) +static void qcom_pcie_deinit_2_3_3(struct qcom_pcie *pcie) { - struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; + struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; - reset_control_assert(res->axi_m_reset); - reset_control_assert(res->axi_s_reset); - reset_control_assert(res->pipe_reset); - reset_control_assert(res->pipe_sticky_reset); - reset_control_assert(res->phy_reset); - reset_control_assert(res->phy_ahb_reset); - reset_control_assert(res->axi_m_sticky_reset); - reset_control_assert(res->pwr_reset); - reset_control_assert(res->ahb_reset); - clk_disable_unprepare(res->aux_clk); - clk_disable_unprepare(res->master_clk); - clk_disable_unprepare(res->slave_clk); + clk_bulk_disable_unprepare(res->num_clks, res->clks); } -static int qcom_pcie_init_2_4_0(struct qcom_pcie *pcie) +static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie) { - struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; + struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; struct dw_pcie *pci = pcie->pci; struct device *dev = pci->dev; - u32 val; int ret; - ret = reset_control_assert(res->axi_m_reset); - if (ret) { - dev_err(dev, "cannot assert axi master reset\n"); + ret = reset_control_bulk_assert(ARRAY_SIZE(res->rst), res->rst); + if (ret < 0) { + dev_err(dev, "cannot assert resets\n"); return ret; } - ret = reset_control_assert(res->axi_s_reset); - if (ret) { - dev_err(dev, "cannot assert axi slave reset\n"); + usleep_range(2000, 2500); + + ret = reset_control_bulk_deassert(ARRAY_SIZE(res->rst), res->rst); + if (ret < 0) { + dev_err(dev, "cannot deassert resets\n"); return ret; } - usleep_range(10000, 12000); + /* + * Don't have a way to see if the reset has completed. + * Wait for some time. + */ + usleep_range(2000, 2500); - ret = reset_control_assert(res->pipe_reset); + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); if (ret) { - dev_err(dev, "cannot assert pipe reset\n"); - return ret; + dev_err(dev, "cannot prepare/enable clocks\n"); + goto err_assert_resets; } - ret = reset_control_assert(res->pipe_sticky_reset); - if (ret) { - dev_err(dev, "cannot assert pipe sticky reset\n"); - return ret; - } + return 0; - ret = reset_control_assert(res->phy_reset); - if (ret) { - dev_err(dev, "cannot assert phy reset\n"); - return ret; - } +err_assert_resets: + /* + * Not checking for failure, will anyway return + * the original failure in 'ret'. + */ + reset_control_bulk_assert(ARRAY_SIZE(res->rst), res->rst); - ret = reset_control_assert(res->phy_ahb_reset); - if (ret) { - dev_err(dev, "cannot assert phy ahb reset\n"); - return ret; - } + return ret; +} - usleep_range(10000, 12000); +static int qcom_pcie_post_init_2_3_3(struct qcom_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; - ret = reset_control_assert(res->axi_m_sticky_reset); - if (ret) { - dev_err(dev, "cannot assert axi master sticky reset\n"); - return ret; - } + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~PHY_TEST_PWR_DOWN; + writel(val, pcie->parf + PARF_PHY_CTRL); - ret = reset_control_assert(res->pwr_reset); - if (ret) { - dev_err(dev, "cannot assert power reset\n"); - return ret; - } + qcom_pcie_configure_dbi_atu_base(pcie); - ret = reset_control_assert(res->ahb_reset); - if (ret) { - dev_err(dev, "cannot assert ahb reset\n"); - return ret; - } + writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS + | SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS | + AUX_PWR_DET | L23_CLK_RMV_DIS | L1_CLK_RMV_DIS, + pcie->parf + PARF_SYS_CTRL); + writel(0, pcie->parf + PARF_Q2A_FLUSH); - usleep_range(10000, 12000); + writel(PCI_COMMAND_MASTER, pci->dbi_base + PCI_COMMAND); - ret = reset_control_deassert(res->phy_ahb_reset); - if (ret) { - dev_err(dev, "cannot deassert phy ahb reset\n"); - return ret; - } + dw_pcie_dbi_ro_wr_en(pci); - ret = reset_control_deassert(res->phy_reset); - if (ret) { - dev_err(dev, "cannot deassert phy reset\n"); - goto err_rst_phy; - } + writel(PCIE_CAP_SLOT_VAL, pci->dbi_base + offset + PCI_EXP_SLTCAP); - ret = reset_control_deassert(res->pipe_reset); - if (ret) { - dev_err(dev, "cannot deassert pipe reset\n"); - goto err_rst_pipe; - } + val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_ASPMS; + writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP); - ret = reset_control_deassert(res->pipe_sticky_reset); - if (ret) { - dev_err(dev, "cannot deassert pipe sticky reset\n"); - goto err_rst_pipe_sticky; - } + writel(PCI_EXP_DEVCTL2_COMP_TMOUT_DIS, pci->dbi_base + offset + + PCI_EXP_DEVCTL2); - usleep_range(10000, 12000); + dw_pcie_dbi_ro_wr_dis(pci); - ret = reset_control_deassert(res->axi_m_reset); - if (ret) { - dev_err(dev, "cannot deassert axi master reset\n"); - goto err_rst_axi_m; - } + return 0; +} - ret = reset_control_deassert(res->axi_m_sticky_reset); - if (ret) { - dev_err(dev, "cannot deassert axi master sticky reset\n"); - goto err_rst_axi_m_sticky; - } +static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; - ret = reset_control_deassert(res->axi_s_reset); - if (ret) { - dev_err(dev, "cannot deassert axi slave reset\n"); - goto err_rst_axi_s; - } + res->rst = devm_reset_control_array_get_exclusive(dev); + if (IS_ERR(res->rst)) + return PTR_ERR(res->rst); - ret = reset_control_deassert(res->pwr_reset); - if (ret) { - dev_err(dev, "cannot deassert power reset\n"); - goto err_rst_pwr; - } + res->supplies[0].supply = "vdda"; + res->supplies[1].supply = "vddpe-3v3"; + ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(res->supplies), + res->supplies); + if (ret) + return ret; - ret = reset_control_deassert(res->ahb_reset); - if (ret) { - dev_err(dev, "cannot deassert ahb reset\n"); - goto err_rst_ahb; + res->num_clks = devm_clk_bulk_get_all(dev, &res->clks); + if (res->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return res->num_clks; } - usleep_range(10000, 12000); + return 0; +} - ret = clk_prepare_enable(res->aux_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable iface clock\n"); - goto err_clk_aux; +static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + u32 val; + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies); + if (ret < 0) { + dev_err(dev, "cannot enable regulators\n"); + return ret; } - ret = clk_prepare_enable(res->master_clk); + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); + if (ret < 0) + goto err_disable_regulators; + + ret = reset_control_assert(res->rst); if (ret) { - dev_err(dev, "cannot prepare/enable core clock\n"); - goto err_clk_axi_m; + dev_err(dev, "reset assert failed (%d)\n", ret); + goto err_disable_clocks; } - ret = clk_prepare_enable(res->slave_clk); + usleep_range(1000, 1500); + + ret = reset_control_deassert(res->rst); if (ret) { - dev_err(dev, "cannot prepare/enable phy clock\n"); - goto err_clk_axi_s; + dev_err(dev, "reset deassert failed (%d)\n", ret); + goto err_disable_clocks; } + /* Wait for reset to complete, required on SM8450 */ + usleep_range(1000, 1500); + + /* configure PCIe to RC mode */ + writel(DEVICE_TYPE_RC, pcie->parf + PARF_DEVICE_TYPE); + /* enable PCIe clocks and resets */ - val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL); - val &= ~BIT(0); - writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~PHY_TEST_PWR_DOWN; + writel(val, pcie->parf + PARF_PHY_CTRL); - /* change DBI base address */ - writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR); + qcom_pcie_configure_dbi_atu_base(pcie); /* MAC PHY_POWERDOWN MUX DISABLE */ - val = readl(pcie->parf + PCIE20_PARF_SYS_CTRL); - val &= ~BIT(29); - writel(val, pcie->parf + PCIE20_PARF_SYS_CTRL); + val = readl(pcie->parf + PARF_SYS_CTRL); + val &= ~MAC_PHY_POWERDOWN_IN_P2_D_MUX_EN; + writel(val, pcie->parf + PARF_SYS_CTRL); - val = readl(pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL); - val |= BIT(4); - writel(val, pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL); + val = readl(pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + val |= BYPASS; + writel(val, pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); - val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2); - val |= BIT(31); - writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2); + /* Enable L1 and L1SS */ + val = readl(pcie->parf + PARF_PM_CTRL); + 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); return 0; +err_disable_clocks: + clk_bulk_disable_unprepare(res->num_clks, res->clks); +err_disable_regulators: + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); -err_clk_axi_s: - clk_disable_unprepare(res->master_clk); -err_clk_axi_m: - clk_disable_unprepare(res->aux_clk); -err_clk_aux: - reset_control_assert(res->ahb_reset); -err_rst_ahb: - reset_control_assert(res->pwr_reset); -err_rst_pwr: - reset_control_assert(res->axi_s_reset); -err_rst_axi_s: - reset_control_assert(res->axi_m_sticky_reset); -err_rst_axi_m_sticky: - reset_control_assert(res->axi_m_reset); -err_rst_axi_m: - reset_control_assert(res->pipe_sticky_reset); -err_rst_pipe_sticky: - reset_control_assert(res->pipe_reset); -err_rst_pipe: - reset_control_assert(res->phy_reset); -err_rst_phy: - reset_control_assert(res->phy_ahb_reset); return ret; } -static int qcom_pcie_get_resources_2_3_3(struct qcom_pcie *pcie) +static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) { - struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; - struct dw_pcie *pci = pcie->pci; - struct device *dev = pci->dev; - int i; - const char *rst_names[] = { "axi_m", "axi_s", "pipe", - "axi_m_sticky", "sticky", - "ahb", "sleep", }; - - res->iface = devm_clk_get(dev, "iface"); - if (IS_ERR(res->iface)) - return PTR_ERR(res->iface); - - res->axi_m_clk = devm_clk_get(dev, "axi_m"); - if (IS_ERR(res->axi_m_clk)) - return PTR_ERR(res->axi_m_clk); - - res->axi_s_clk = devm_clk_get(dev, "axi_s"); - if (IS_ERR(res->axi_s_clk)) - return PTR_ERR(res->axi_s_clk); - - res->ahb_clk = devm_clk_get(dev, "ahb"); - if (IS_ERR(res->ahb_clk)) - return PTR_ERR(res->ahb_clk); - - res->aux_clk = devm_clk_get(dev, "aux"); - if (IS_ERR(res->aux_clk)) - return PTR_ERR(res->aux_clk); - - for (i = 0; i < ARRAY_SIZE(rst_names); i++) { - res->rst[i] = devm_reset_control_get(dev, rst_names[i]); - if (IS_ERR(res->rst[i])) - return PTR_ERR(res->rst[i]); - } + const struct qcom_pcie_cfg *pcie_cfg = pcie->cfg; + + if (pcie_cfg->override_no_snoop) + 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; } -static void qcom_pcie_deinit_2_3_3(struct qcom_pcie *pcie) +static int qcom_pcie_enable_aspm(struct pci_dev *pdev, void *userdata) { - struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; + /* + * Downstream devices need to be in D0 state before enabling PCI PM + * substates. + */ + pci_set_power_state_locked(pdev, PCI_D0); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); - clk_disable_unprepare(res->iface); - clk_disable_unprepare(res->axi_m_clk); - clk_disable_unprepare(res->axi_s_clk); - clk_disable_unprepare(res->ahb_clk); - clk_disable_unprepare(res->aux_clk); + return 0; } -static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie) +static void qcom_pcie_host_post_init_2_7_0(struct qcom_pcie *pcie) { - struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; - struct dw_pcie *pci = pcie->pci; - struct device *dev = pci->dev; - int i, ret; + struct dw_pcie_rp *pp = &pcie->pci->pp; + + pci_walk_bus(pp->bridge->bus, qcom_pcie_enable_aspm, NULL); +} + +static void qcom_pcie_deinit_2_7_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0; + + clk_bulk_disable_unprepare(res->num_clks, res->clks); + + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); +} + +static int qcom_pcie_config_sid_1_9_0(struct qcom_pcie *pcie) +{ + /* iommu map structure */ + struct { + u32 bdf; + u32 phandle; + u32 smmu_sid; + u32 smmu_sid_len; + } *map; + void __iomem *bdf_to_sid_base = pcie->parf + PARF_BDF_TO_SID_TABLE_N; + struct device *dev = pcie->pci->dev; + u8 qcom_pcie_crc8_table[CRC8_TABLE_SIZE]; + int i, nr_map, size = 0; + u32 smmu_sid_base; u32 val; - for (i = 0; i < ARRAY_SIZE(res->rst); i++) { - ret = reset_control_assert(res->rst[i]); - if (ret) { - dev_err(dev, "reset #%d assert failed (%d)\n", i, ret); - return ret; - } - } + of_get_property(dev->of_node, "iommu-map", &size); + if (!size) + return 0; - usleep_range(2000, 2500); + /* Enable BDF to SID translation by disabling bypass mode (default) */ + val = readl(pcie->parf + PARF_BDF_TO_SID_CFG); + val &= ~BDF_TO_SID_BYPASS; + writel(val, pcie->parf + PARF_BDF_TO_SID_CFG); - for (i = 0; i < ARRAY_SIZE(res->rst); i++) { - ret = reset_control_deassert(res->rst[i]); - if (ret) { - dev_err(dev, "reset #%d deassert failed (%d)\n", i, - ret); - return ret; + map = kzalloc(size, GFP_KERNEL); + if (!map) + return -ENOMEM; + + of_property_read_u32_array(dev->of_node, "iommu-map", (u32 *)map, + size / sizeof(u32)); + + nr_map = size / (sizeof(*map)); + + crc8_populate_msb(qcom_pcie_crc8_table, QCOM_PCIE_CRC8_POLYNOMIAL); + + /* Registers need to be zero out first */ + memset_io(bdf_to_sid_base, 0, CRC8_TABLE_SIZE * sizeof(u32)); + + /* Extract the SMMU SID base from the first entry of iommu-map */ + smmu_sid_base = map[0].smmu_sid; + + /* Look for an available entry to hold the mapping */ + for (i = 0; i < nr_map; i++) { + __be16 bdf_be = cpu_to_be16(map[i].bdf); + u32 val; + u8 hash; + + hash = crc8(qcom_pcie_crc8_table, (u8 *)&bdf_be, sizeof(bdf_be), 0); + + val = readl(bdf_to_sid_base + hash * sizeof(u32)); + + /* If the register is already populated, look for next available entry */ + while (val) { + u8 current_hash = hash++; + u8 next_mask = 0xff; + + /* If NEXT field is NULL then update it with next hash */ + if (!(val & next_mask)) { + val |= (u32)hash; + writel(val, bdf_to_sid_base + current_hash * sizeof(u32)); + } + + val = readl(bdf_to_sid_base + hash * sizeof(u32)); } + + /* BDF [31:16] | SID [15:8] | NEXT [7:0] */ + val = map[i].bdf << 16 | (map[i].smmu_sid - smmu_sid_base) << 8 | 0; + writel(val, bdf_to_sid_base + hash * sizeof(u32)); } - /* - * Don't have a way to see if the reset has completed. - * Wait for some time. - */ - usleep_range(2000, 2500); + kfree(map); - ret = clk_prepare_enable(res->iface); - if (ret) { - dev_err(dev, "cannot prepare/enable core clock\n"); - goto err_clk_iface; - } + return 0; +} - ret = clk_prepare_enable(res->axi_m_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable core clock\n"); - goto err_clk_axi_m; - } +static int qcom_pcie_get_resources_2_9_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; - ret = clk_prepare_enable(res->axi_s_clk); - if (ret) { - dev_err(dev, "cannot prepare/enable axi slave clock\n"); - goto err_clk_axi_s; + res->num_clks = devm_clk_bulk_get_all(dev, &res->clks); + if (res->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return res->num_clks; } - ret = clk_prepare_enable(res->ahb_clk); + res->rst = devm_reset_control_array_get_exclusive(dev); + if (IS_ERR(res->rst)) + return PTR_ERR(res->rst); + + return 0; +} + +static void qcom_pcie_deinit_2_9_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0; + + clk_bulk_disable_unprepare(res->num_clks, res->clks); +} + +static int qcom_pcie_init_2_9_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0; + struct device *dev = pcie->pci->dev; + int ret; + + ret = reset_control_assert(res->rst); if (ret) { - dev_err(dev, "cannot prepare/enable ahb clock\n"); - goto err_clk_ahb; + dev_err(dev, "reset assert failed (%d)\n", ret); + return ret; } - ret = clk_prepare_enable(res->aux_clk); + /* + * Delay periods before and after reset deassert are working values + * from downstream Codeaurora kernel + */ + usleep_range(2000, 2500); + + ret = reset_control_deassert(res->rst); if (ret) { - dev_err(dev, "cannot prepare/enable aux clock\n"); - goto err_clk_aux; + dev_err(dev, "reset deassert failed (%d)\n", ret); + return ret; } - writel(SLV_ADDR_SPACE_SZ, - pcie->parf + PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE); + usleep_range(2000, 2500); + + return clk_bulk_prepare_enable(res->num_clks, res->clks); +} - val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL); - val &= ~BIT(0); - writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL); +static int qcom_pcie_post_init_2_9_0(struct qcom_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; + int i; - writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR); + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~PHY_TEST_PWR_DOWN; + writel(val, pcie->parf + PARF_PHY_CTRL); - writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS - | SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS | + qcom_pcie_configure_dbi_atu_base(pcie); + + writel(DEVICE_TYPE_RC, pcie->parf + PARF_DEVICE_TYPE); + writel(BYPASS | MSTR_AXI_CLK_EN | AHB_CLK_EN, + pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + writel(GEN3_RELATED_OFF_RXEQ_RGRDLESS_RXTS | + GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL, + pci->dbi_base + GEN3_RELATED_OFF); + + writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS | + SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS | AUX_PWR_DET | L23_CLK_RMV_DIS | L1_CLK_RMV_DIS, - pcie->parf + PCIE20_PARF_SYS_CTRL); - writel(0, pcie->parf + PCIE20_PARF_Q2A_FLUSH); + pcie->parf + PARF_SYS_CTRL); + + writel(0, pcie->parf + PARF_Q2A_FLUSH); + + dw_pcie_dbi_ro_wr_en(pci); + + writel(PCIE_CAP_SLOT_VAL, pci->dbi_base + offset + PCI_EXP_SLTCAP); + + val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_ASPMS; + writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP); - writel(CMD_BME_VAL, pci->dbi_base + PCIE20_COMMAND_STATUS); - writel(DBI_RO_WR_EN, pci->dbi_base + PCIE20_MISC_CONTROL_1_REG); - writel(PCIE_CAP_LINK1_VAL, pci->dbi_base + PCIE20_CAP_LINK_1); + writel(PCI_EXP_DEVCTL2_COMP_TMOUT_DIS, pci->dbi_base + offset + + PCI_EXP_DEVCTL2); - val = readl(pci->dbi_base + PCIE20_CAP_LINK_CAPABILITIES); - val &= ~PCIE20_CAP_ACTIVE_STATE_LINK_PM_SUPPORT; - writel(val, pci->dbi_base + PCIE20_CAP_LINK_CAPABILITIES); + dw_pcie_dbi_ro_wr_dis(pci); - writel(PCIE_CAP_CPL_TIMEOUT_DISABLE, pci->dbi_base + - PCIE20_DEVICE_CONTROL2_STATUS2); + for (i = 0; i < 256; i++) + writel(0, pcie->parf + PARF_BDF_TO_SID_TABLE_N + (4 * i)); return 0; +} -err_clk_aux: - clk_disable_unprepare(res->ahb_clk); -err_clk_ahb: - clk_disable_unprepare(res->axi_s_clk); -err_clk_axi_s: - clk_disable_unprepare(res->axi_m_clk); -err_clk_axi_m: - clk_disable_unprepare(res->iface); -err_clk_iface: - /* - * Not checking for failure, will anyway return - * the original failure in 'ret'. - */ - for (i = 0; i < ARRAY_SIZE(res->rst); i++) - reset_control_assert(res->rst[i]); +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 ret; + 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_link_up(struct dw_pcie *pci) +static int qcom_pcie_phy_power_on(struct qcom_pcie *pcie) { - u16 val = readw(pci->dbi_base + PCIE20_CAP + PCI_EXP_LNKSTA); + 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 !!(val & PCI_EXP_LNKSTA_DLLLA); + return 0; } -static int qcom_pcie_host_init(struct pcie_port *pp) +static int qcom_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct qcom_pcie *pcie = to_qcom_pcie(pci); @@ -1091,69 +1302,70 @@ static int qcom_pcie_host_init(struct pcie_port *pp) qcom_ep_reset_assert(pcie); - ret = pcie->ops->init(pcie); + ret = pcie->cfg->ops->init(pcie); if (ret) return ret; - ret = phy_power_on(pcie->phy); + ret = qcom_pcie_phy_power_on(pcie); if (ret) goto err_deinit; - if (pcie->ops->post_init) { - ret = pcie->ops->post_init(pcie); + if (pcie->cfg->ops->post_init) { + ret = pcie->cfg->ops->post_init(pcie); if (ret) goto err_disable_phy; } - dw_pcie_setup_rc(pp); - - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(pp); - qcom_ep_reset_deassert(pcie); - ret = qcom_pcie_establish_link(pcie); - if (ret) - goto err; + if (pcie->cfg->ops->config_sid) { + ret = pcie->cfg->ops->config_sid(pcie); + if (ret) + goto err_assert_reset; + } return 0; -err: + +err_assert_reset: qcom_ep_reset_assert(pcie); - if (pcie->ops->post_deinit) - pcie->ops->post_deinit(pcie); err_disable_phy: - phy_power_off(pcie->phy); + qcom_pcie_phy_power_off(pcie); err_deinit: - pcie->ops->deinit(pcie); + pcie->cfg->ops->deinit(pcie); return ret; } -static int qcom_pcie_rd_own_conf(struct pcie_port *pp, int where, int size, - u32 *val) +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); - /* the device class is not reported correctly from the register */ - if (where == PCI_CLASS_REVISION && size == 4) { - *val = readl(pci->dbi_base + PCI_CLASS_REVISION); - *val &= 0xff; /* keep revision id */ - *val |= PCI_CLASS_BRIDGE_PCI << 16; - return PCIBIOS_SUCCESSFUL; - } + qcom_ep_reset_assert(pcie); + qcom_pcie_phy_power_off(pcie); + pcie->cfg->ops->deinit(pcie); +} + +static void qcom_pcie_host_post_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct qcom_pcie *pcie = to_qcom_pcie(pci); - return dw_pcie_read(pci->dbi_base + where, size, val); + if (pcie->cfg->ops->host_post_init) + pcie->cfg->ops->host_post_init(pcie); } static const struct dw_pcie_host_ops qcom_pcie_dw_ops = { - .host_init = qcom_pcie_host_init, - .rd_own_conf = qcom_pcie_rd_own_conf, + .init = qcom_pcie_host_init, + .deinit = qcom_pcie_host_deinit, + .post_init = qcom_pcie_host_post_init, }; /* Qcom IP rev.: 2.1.0 Synopsys IP rev.: 4.01a */ static const struct qcom_pcie_ops ops_2_1_0 = { .get_resources = qcom_pcie_get_resources_2_1_0, .init = qcom_pcie_init_2_1_0, + .post_init = qcom_pcie_post_init_2_1_0, .deinit = qcom_pcie_deinit_2_1_0, .ltssm_enable = qcom_pcie_2_1_0_ltssm_enable, }; @@ -1162,6 +1374,7 @@ static const struct qcom_pcie_ops ops_2_1_0 = { static const struct qcom_pcie_ops ops_1_0_0 = { .get_resources = qcom_pcie_get_resources_1_0_0, .init = qcom_pcie_init_1_0_0, + .post_init = qcom_pcie_post_init_1_0_0, .deinit = qcom_pcie_deinit_1_0_0, .ltssm_enable = qcom_pcie_2_1_0_ltssm_enable, }; @@ -1172,7 +1385,6 @@ static const struct qcom_pcie_ops ops_2_3_2 = { .init = qcom_pcie_init_2_3_2, .post_init = qcom_pcie_post_init_2_3_2, .deinit = qcom_pcie_deinit_2_3_2, - .post_deinit = qcom_pcie_post_deinit_2_3_2, .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, }; @@ -1180,6 +1392,7 @@ static const struct qcom_pcie_ops ops_2_3_2 = { static const struct qcom_pcie_ops ops_2_4_0 = { .get_resources = qcom_pcie_get_resources_2_4_0, .init = qcom_pcie_init_2_4_0, + .post_init = qcom_pcie_post_init_2_3_2, .deinit = qcom_pcie_deinit_2_4_0, .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, }; @@ -1188,110 +1401,605 @@ static const struct qcom_pcie_ops ops_2_4_0 = { static const struct qcom_pcie_ops ops_2_3_3 = { .get_resources = qcom_pcie_get_resources_2_3_3, .init = qcom_pcie_init_2_3_3, + .post_init = qcom_pcie_post_init_2_3_3, .deinit = qcom_pcie_deinit_2_3_3, .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, }; +/* Qcom IP rev.: 2.7.0 Synopsys IP rev.: 4.30a */ +static const struct qcom_pcie_ops ops_2_7_0 = { + .get_resources = qcom_pcie_get_resources_2_7_0, + .init = qcom_pcie_init_2_7_0, + .post_init = qcom_pcie_post_init_2_7_0, + .deinit = qcom_pcie_deinit_2_7_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +/* Qcom IP rev.: 1.9.0 */ +static const struct qcom_pcie_ops ops_1_9_0 = { + .get_resources = qcom_pcie_get_resources_2_7_0, + .init = qcom_pcie_init_2_7_0, + .post_init = qcom_pcie_post_init_2_7_0, + .host_post_init = qcom_pcie_host_post_init_2_7_0, + .deinit = qcom_pcie_deinit_2_7_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, + .config_sid = qcom_pcie_config_sid_1_9_0, +}; + +/* Qcom IP rev.: 1.21.0 Synopsys IP rev.: 5.60a */ +static const struct qcom_pcie_ops ops_1_21_0 = { + .get_resources = qcom_pcie_get_resources_2_7_0, + .init = qcom_pcie_init_2_7_0, + .post_init = qcom_pcie_post_init_2_7_0, + .host_post_init = qcom_pcie_host_post_init_2_7_0, + .deinit = qcom_pcie_deinit_2_7_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +/* Qcom IP rev.: 2.9.0 Synopsys IP rev.: 5.00a */ +static const struct qcom_pcie_ops ops_2_9_0 = { + .get_resources = qcom_pcie_get_resources_2_9_0, + .init = qcom_pcie_init_2_9_0, + .post_init = qcom_pcie_post_init_2_9_0, + .deinit = qcom_pcie_deinit_2_9_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +static const struct qcom_pcie_cfg cfg_1_0_0 = { + .ops = &ops_1_0_0, +}; + +static const struct qcom_pcie_cfg cfg_1_9_0 = { + .ops = &ops_1_9_0, +}; + +static const struct qcom_pcie_cfg cfg_1_34_0 = { + .ops = &ops_1_9_0, + .override_no_snoop = true, +}; + +static const struct qcom_pcie_cfg cfg_2_1_0 = { + .ops = &ops_2_1_0, +}; + +static const struct qcom_pcie_cfg cfg_2_3_2 = { + .ops = &ops_2_3_2, +}; + +static const struct qcom_pcie_cfg cfg_2_3_3 = { + .ops = &ops_2_3_3, +}; + +static const struct qcom_pcie_cfg cfg_2_4_0 = { + .ops = &ops_2_4_0, +}; + +static const struct qcom_pcie_cfg cfg_2_7_0 = { + .ops = &ops_2_7_0, +}; + +static const struct qcom_pcie_cfg cfg_2_9_0 = { + .ops = &ops_2_9_0, +}; + +static const struct qcom_pcie_cfg cfg_sc8280xp = { + .ops = &ops_1_21_0, + .no_l0s = true, +}; + +static const struct qcom_pcie_cfg cfg_fw_managed = { + .firmware_managed = true, +}; + static const struct dw_pcie_ops dw_pcie_ops = { .link_up = qcom_pcie_link_up, + .start_link = qcom_pcie_start_link, + .assert_perst = qcom_pcie_assert_perst, }; -static int qcom_pcie_probe(struct platform_device *pdev) +static int qcom_pcie_icc_init(struct qcom_pcie *pcie) { - struct device *dev = &pdev->dev; - struct resource *res; - struct pcie_port *pp; - struct dw_pcie *pci; - struct qcom_pcie *pcie; + struct dw_pcie *pci = pcie->pci; int ret; - pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); - if (!pcie) - return -ENOMEM; + pcie->icc_mem = devm_of_icc_get(pci->dev, "pcie-mem"); + if (IS_ERR(pcie->icc_mem)) + return PTR_ERR(pcie->icc_mem); + + pcie->icc_cpu = devm_of_icc_get(pci->dev, "cpu-pcie"); + if (IS_ERR(pcie->icc_cpu)) + return PTR_ERR(pcie->icc_cpu); + /* + * Some Qualcomm platforms require interconnect bandwidth constraints + * to be set before enabling interconnect clocks. + * + * Set an initial peak bandwidth corresponding to single-lane Gen 1 + * for the pcie-mem path. + */ + ret = icc_set_bw(pcie->icc_mem, 0, QCOM_PCIE_LINK_SPEED_TO_BW(1)); + if (ret) { + dev_err(pci->dev, "Failed to set bandwidth for PCIe-MEM interconnect path: %d\n", + ret); + return ret; + } + + /* + * Since the CPU-PCIe path is only used for activities like register + * access of the host controller and endpoint Config/BAR space access, + * HW team has recommended to use a minimal bandwidth of 1KBps just to + * keep the path active. + */ + ret = icc_set_bw(pcie->icc_cpu, 0, kBps_to_icc(1)); + if (ret) { + dev_err(pci->dev, "Failed to set bandwidth for CPU-PCIe interconnect path: %d\n", + ret); + icc_set_bw(pcie->icc_mem, 0, 0); + return ret; + } + + return 0; +} + +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; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + status = readw(pci->dbi_base + offset + PCI_EXP_LNKSTA); + + /* Only update constraints if link is up. */ + if (!(status & PCI_EXP_LNKSTA_DLLLA)) + return; + + speed = FIELD_GET(PCI_EXP_LNKSTA_CLS, status); + width = FIELD_GET(PCI_EXP_LNKSTA_NLW, status); + + if (pcie->icc_mem) { + ret = icc_set_bw(pcie->icc_mem, 0, + width * QCOM_PCIE_LINK_SPEED_TO_BW(speed)); + if (ret) { + dev_err(pci->dev, "Failed to set bandwidth for PCIe-MEM interconnect path: %d\n", + ret); + } + } else if (pcie->use_pm_opp) { + freq_mbps = pcie_dev_speed_mbps(pcie_link_speed[speed]); + if (freq_mbps < 0) + return; + + freq_kbps = freq_mbps * KILO; + 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) + dev_err(pci->dev, "Failed to set OPP for freq (%lu): %d\n", + freq_kbps * width, ret); + dev_pm_opp_put(opp); + } + } +} + +static int qcom_pcie_link_transition_count(struct seq_file *s, void *data) +{ + struct qcom_pcie *pcie = (struct qcom_pcie *)dev_get_drvdata(s->private); + + seq_printf(s, "L0s transition count: %u\n", + readl_relaxed(pcie->mhi + PARF_DEBUG_CNT_PM_LINKST_IN_L0S)); + + seq_printf(s, "L1 transition count: %u\n", + readl_relaxed(pcie->mhi + PARF_DEBUG_CNT_PM_LINKST_IN_L1)); + + seq_printf(s, "L1.1 transition count: %u\n", + readl_relaxed(pcie->mhi + PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L1)); + + seq_printf(s, "L1.2 transition count: %u\n", + readl_relaxed(pcie->mhi + PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L2)); + + seq_printf(s, "L2 transition count: %u\n", + readl_relaxed(pcie->mhi + PARF_DEBUG_CNT_PM_LINKST_IN_L2)); + + return 0; +} + +static void qcom_pcie_init_debugfs(struct qcom_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->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, "link_transition_count", pcie->debugfs, + qcom_pcie_link_transition_count); +} + +static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data) +{ + 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); + + writel_relaxed(status, pcie->parf + PARF_INT_ALL_CLEAR); + + if (FIELD_GET(PARF_INT_ALL_LINK_UP, status)) { + msleep(PCIE_RESET_CONFIG_WAIT_MS); + dev_dbg(dev, "Received Link up event. Starting enumeration!\n"); + /* Rescan the bus to enumerate endpoint devices */ + pci_lock_rescan_remove(); + pci_rescan_bus(pp->bridge->bus); + pci_unlock_rescan_remove(); + + qcom_pcie_icc_opp_update(pcie); + } else { + dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n", + status); + } + + return IRQ_HANDLED; +} + +static void qcom_pci_free_msi(void *ptr) +{ + struct dw_pcie_rp *pp = (struct dw_pcie_rp *)ptr; + + if (pp && pp->has_msi_ctrl) + dw_pcie_free_msi(pp); +} + +static int qcom_pcie_ecam_host_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + int ret; pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); if (!pci) return -ENOMEM; + pci->dev = dev; + pp = &pci->pp; + pci->dbi_base = cfg->win; + pp->num_vectors = MSI_DEF_NUM_VECTORS; + + ret = dw_pcie_msi_host_init(pp); + if (ret) + return ret; + + pp->has_msi_ctrl = true; + dw_pcie_msi_init(pp); + + return devm_add_action_or_reset(dev, qcom_pci_free_msi, pp); +} + +static const struct pci_ecam_ops pci_qcom_ecam_ops = { + .init = qcom_pcie_ecam_host_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static int qcom_pcie_parse_port(struct qcom_pcie *pcie, struct device_node *node) +{ + struct device *dev = pcie->pci->dev; + struct qcom_pcie_port *port; + struct gpio_desc *reset; + struct phy *phy; + int ret; + + reset = devm_fwnode_gpiod_get(dev, of_fwnode_handle(node), + "reset", GPIOD_OUT_HIGH, "PERST#"); + if (IS_ERR(reset)) + return PTR_ERR(reset); + + phy = devm_of_phy_get(dev, node, NULL); + if (IS_ERR(phy)) + return PTR_ERR(phy); + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + ret = phy_init(phy); + if (ret) + return ret; + + port->reset = reset; + port->phy = phy; + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + return 0; +} + +static int qcom_pcie_parse_ports(struct qcom_pcie *pcie) +{ + struct device *dev = pcie->pci->dev; + struct qcom_pcie_port *port, *tmp; + int ret = -ENOENT; + + for_each_available_child_of_node_scoped(dev->of_node, of_port) { + if (!of_node_is_type(of_port, "pci")) + continue; + ret = qcom_pcie_parse_port(pcie, of_port); + if (ret) + goto err_port_del; + } + + return ret; + +err_port_del: + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + phy_exit(port->phy); + list_del(&port->list); + } + + return ret; +} + +static int qcom_pcie_parse_legacy_binding(struct qcom_pcie *pcie) +{ + struct device *dev = pcie->pci->dev; + struct qcom_pcie_port *port; + struct gpio_desc *reset; + struct phy *phy; + int ret; + + phy = devm_phy_optional_get(dev, "pciephy"); + if (IS_ERR(phy)) + return PTR_ERR(phy); + + reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH); + if (IS_ERR(reset)) + return PTR_ERR(reset); + + ret = phy_init(phy); + if (ret) + return ret; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->reset = reset; + port->phy = phy; + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + return 0; +} + +static int qcom_pcie_probe(struct platform_device *pdev) +{ + const struct qcom_pcie_cfg *pcie_cfg; + unsigned long max_freq = ULONG_MAX; + struct qcom_pcie_port *port, *tmp; + struct device *dev = &pdev->dev; + struct dev_pm_opp *opp; + struct qcom_pcie *pcie; + struct dw_pcie_rp *pp; + struct resource *res; + struct dw_pcie *pci; + int ret, irq; + char *name; + + pcie_cfg = of_device_get_match_data(dev); + if (!pcie_cfg) { + dev_err(dev, "No platform data\n"); + return -ENODATA; + } + + 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) { - pm_runtime_disable(dev); - return ret; + 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; pcie->pci = pci; - pcie->ops = of_device_get_match_data(dev); - - pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_LOW); - if (IS_ERR(pcie->reset)) { - ret = PTR_ERR(pcie->reset); - goto err_pm_runtime_put; - } + pcie->cfg = pcie_cfg; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "parf"); - pcie->parf = devm_ioremap_resource(dev, res); + pcie->parf = devm_platform_ioremap_resource_byname(pdev, "parf"); if (IS_ERR(pcie->parf)) { ret = PTR_ERR(pcie->parf); goto err_pm_runtime_put; } - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); - pci->dbi_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(pci->dbi_base)) { - ret = PTR_ERR(pci->dbi_base); - goto err_pm_runtime_put; + /* MHI region is optional */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mhi"); + if (res) { + pcie->mhi = devm_ioremap_resource(dev, res); + if (IS_ERR(pcie->mhi)) { + ret = PTR_ERR(pcie->mhi); + goto err_pm_runtime_put; + } } - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); - pcie->elbi = devm_ioremap_resource(dev, res); - if (IS_ERR(pcie->elbi)) { - ret = PTR_ERR(pcie->elbi); + /* OPP table is optional */ + ret = devm_pm_opp_of_add_table(dev); + if (ret && ret != -ENODEV) { + dev_err_probe(dev, ret, "Failed to add OPP table\n"); goto err_pm_runtime_put; } - pcie->phy = devm_phy_optional_get(dev, "pciephy"); - if (IS_ERR(pcie->phy)) { - ret = PTR_ERR(pcie->phy); - goto err_pm_runtime_put; + /* + * Before the PCIe link is initialized, vote for highest OPP in the OPP + * table, so that we are voting for maximum voltage corner for the + * link to come up in maximum supported speed. At the end of the + * probe(), OPP will be updated using qcom_pcie_icc_opp_update(). + */ + if (!ret) { + opp = dev_pm_opp_find_freq_floor(dev, &max_freq); + if (IS_ERR(opp)) { + ret = PTR_ERR(opp); + dev_err_probe(pci->dev, ret, + "Unable to find max freq OPP\n"); + goto err_pm_runtime_put; + } else { + ret = dev_pm_opp_set_opp(dev, opp); + } + + dev_pm_opp_put(opp); + if (ret) { + dev_err_probe(pci->dev, ret, + "Failed to set OPP for freq %lu\n", + max_freq); + goto err_pm_runtime_put; + } + + pcie->use_pm_opp = true; + } else { + /* Skip ICC init if OPP is supported as it is handled by OPP */ + ret = qcom_pcie_icc_init(pcie); + if (ret) + goto err_pm_runtime_put; } - ret = pcie->ops->get_resources(pcie); + ret = pcie->cfg->ops->get_resources(pcie); if (ret) goto err_pm_runtime_put; pp->ops = &qcom_pcie_dw_ops; - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq_byname(pdev, "msi"); - if (pp->msi_irq < 0) { - ret = pp->msi_irq; + ret = qcom_pcie_parse_ports(pcie); + if (ret) { + if (ret != -ENOENT) { + dev_err_probe(pci->dev, ret, + "Failed to parse Root Port: %d\n", ret); goto err_pm_runtime_put; } - } - ret = phy_init(pcie->phy); - if (ret) { - pm_runtime_disable(&pdev->dev); - goto err_pm_runtime_put; + /* + * In the case of properties not populated in Root Port node, + * fallback to the legacy method of parsing the Host Bridge + * node. This is to maintain DT backwards compatibility. + */ + ret = qcom_pcie_parse_legacy_binding(pcie); + if (ret) + goto err_pm_runtime_put; } platform_set_drvdata(pdev, pcie); + irq = platform_get_irq_byname_optional(pdev, "global"); + if (irq > 0) + pp->use_linkup_irq = true; + ret = dw_pcie_host_init(pp); if (ret) { dev_err(dev, "cannot initialize host\n"); - pm_runtime_disable(&pdev->dev); - goto err_pm_runtime_put; + 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) + qcom_pcie_init_debugfs(pcie); + return 0; +err_host_deinit: + dw_pcie_host_deinit(pp); +err_phy_exit: + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + phy_exit(port->phy); + list_del(&port->list); + } err_pm_runtime_put: pm_runtime_put(dev); pm_runtime_disable(dev); @@ -1299,22 +2007,151 @@ err_pm_runtime_put: return ret; } +static int qcom_pcie_suspend_noirq(struct device *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. + */ + if (pcie->icc_mem) { + ret = icc_set_bw(pcie->icc_mem, 0, kBps_to_icc(1)); + if (ret) { + dev_err(dev, + "Failed to set bandwidth for PCIe-MEM interconnect path: %d\n", + ret); + return ret; + } + } + + /* + * Turn OFF the resources only for controllers without active PCIe + * devices. For controllers with active devices, the resources are kept + * ON and the link is expected to be in L0/L1 (sub)states. + * + * Turning OFF the resources for controllers with active PCIe devices + * will trigger access violation during the end of the suspend cycle, + * as kernel tries to access the PCIe devices config space for masking + * MSIs. + * + * Also, it is not desirable to put the link into L2/L3 state as that + * implies VDD supply will be removed and the devices may go into + * powerdown state. This will affect the lifetime of the storage devices + * like NVMe. + */ + if (!dw_pcie_link_up(pcie->pci)) { + qcom_pcie_host_deinit(&pcie->pci->pp); + pcie->suspended = true; + } + + /* + * Only disable CPU-PCIe interconnect path if the suspend is non-S2RAM. + * Because on some platforms, DBI access can happen very late during the + * S2RAM and a non-active CPU-PCIe interconnect path may lead to NoC + * error. + */ + if (pm_suspend_target_state != PM_SUSPEND_MEM) { + ret = icc_disable(pcie->icc_cpu); + if (ret) + dev_err(dev, "Failed to disable CPU-PCIe interconnect path: %d\n", ret); + + if (pcie->use_pm_opp) + dev_pm_opp_set_opp(pcie->pci->dev, NULL); + } + return ret; +} + +static int qcom_pcie_resume_noirq(struct device *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) { + dev_err(dev, "Failed to enable CPU-PCIe interconnect path: %d\n", ret); + return ret; + } + } + + if (pcie->suspended) { + ret = qcom_pcie_host_init(&pcie->pci->pp); + if (ret) + return ret; + + pcie->suspended = false; + } + + qcom_pcie_icc_opp_update(pcie); + + return 0; +} + static const struct of_device_id qcom_pcie_match[] = { - { .compatible = "qcom,pcie-apq8084", .data = &ops_1_0_0 }, - { .compatible = "qcom,pcie-ipq8064", .data = &ops_2_1_0 }, - { .compatible = "qcom,pcie-apq8064", .data = &ops_2_1_0 }, - { .compatible = "qcom,pcie-msm8996", .data = &ops_2_3_2 }, - { .compatible = "qcom,pcie-ipq8074", .data = &ops_2_3_3 }, - { .compatible = "qcom,pcie-ipq4019", .data = &ops_2_4_0 }, + { .compatible = "qcom,pcie-apq8064", .data = &cfg_2_1_0 }, + { .compatible = "qcom,pcie-apq8084", .data = &cfg_1_0_0 }, + { .compatible = "qcom,pcie-ipq4019", .data = &cfg_2_4_0 }, + { .compatible = "qcom,pcie-ipq5018", .data = &cfg_2_9_0 }, + { .compatible = "qcom,pcie-ipq6018", .data = &cfg_2_9_0 }, + { .compatible = "qcom,pcie-ipq8064", .data = &cfg_2_1_0 }, + { .compatible = "qcom,pcie-ipq8064-v2", .data = &cfg_2_1_0 }, + { .compatible = "qcom,pcie-ipq8074", .data = &cfg_2_3_3 }, + { .compatible = "qcom,pcie-ipq8074-gen3", .data = &cfg_2_9_0 }, + { .compatible = "qcom,pcie-ipq9574", .data = &cfg_2_9_0 }, + { .compatible = "qcom,pcie-msm8996", .data = &cfg_2_3_2 }, + { .compatible = "qcom,pcie-qcs404", .data = &cfg_2_4_0 }, + { .compatible = "qcom,pcie-sa8255p", .data = &cfg_fw_managed }, + { .compatible = "qcom,pcie-sa8540p", .data = &cfg_sc8280xp }, + { .compatible = "qcom,pcie-sa8775p", .data = &cfg_1_34_0}, + { .compatible = "qcom,pcie-sc7280", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sc8180x", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sc8280xp", .data = &cfg_sc8280xp }, + { .compatible = "qcom,pcie-sdm845", .data = &cfg_2_7_0 }, + { .compatible = "qcom,pcie-sdx55", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8150", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8250", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8350", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8450-pcie0", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8450-pcie1", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8550", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-x1e80100", .data = &cfg_sc8280xp }, { } }; +static void qcom_fixup_class(struct pci_dev *dev) +{ + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0101, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0104, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0106, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0107, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0302, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1000, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1001, qcom_fixup_class); + +static const struct dev_pm_ops qcom_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(qcom_pcie_suspend_noirq, qcom_pcie_resume_noirq) +}; + static struct platform_driver qcom_pcie_driver = { .probe = qcom_pcie_probe, .driver = { .name = "qcom-pcie", .suppress_bind_attrs = true, .of_match_table = qcom_pcie_match, + .pm = &qcom_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; builtin_platform_driver(qcom_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c new file mode 100644 index 000000000000..80778917d2dd --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c @@ -0,0 +1,804 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PCIe controller driver for Renesas R-Car Gen4 Series SoCs + * Copyright (C) 2022-2023 Renesas Electronics Corporation + * + * The r8a779g0 (R-Car V4H) controller requires a specific firmware to be + * provided, to initialize the PHY. Otherwise, the PCIe controller will not + * work. + */ + +#include <linux/delay.h> +#include <linux/firmware.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +/* Renesas-specific */ +/* PCIe Mode Setting Register 0 */ +#define PCIEMSR0 0x0000 +#define APP_SRIS_MODE BIT(6) +#define DEVICE_TYPE_EP 0 +#define DEVICE_TYPE_RC BIT(4) +#define BIFUR_MOD_SET_ON BIT(0) + +/* PCIe Interrupt Status 0 */ +#define PCIEINTSTS0 0x0084 + +/* PCIe Interrupt Status 0 Enable */ +#define PCIEINTSTS0EN 0x0310 +#define MSI_CTRL_INT BIT(26) +#define SMLH_LINK_UP BIT(7) +#define RDLH_LINK_UP BIT(6) + +/* PCIe DMA Interrupt Status Enable */ +#define PCIEDMAINTSTSEN 0x0314 +#define PCIEDMAINTSTSEN_INIT GENMASK(15, 0) + +/* Port Logic Registers 89 */ +#define PRTLGC89 0x0b70 + +/* Port Logic Registers 90 */ +#define PRTLGC90 0x0b74 + +/* PCIe Reset Control Register 1 */ +#define PCIERSTCTRL1 0x0014 +#define APP_HOLD_PHY_RST BIT(16) +#define APP_LTSSM_ENABLE BIT(0) + +/* PCIe Power Management Control */ +#define PCIEPWRMNGCTRL 0x0070 +#define APP_CLK_REQ_N BIT(11) +#define APP_CLK_PM_EN BIT(10) + +#define RCAR_NUM_SPEED_CHANGE_RETRIES 10 +#define RCAR_MAX_LINK_SPEED 4 + +#define RCAR_GEN4_PCIE_EP_FUNC_DBI_OFFSET 0x1000 +#define RCAR_GEN4_PCIE_EP_FUNC_DBI2_OFFSET 0x800 + +#define RCAR_GEN4_PCIE_FIRMWARE_NAME "rcar_gen4_pcie.bin" +#define RCAR_GEN4_PCIE_FIRMWARE_BASE_ADDR 0xc000 +MODULE_FIRMWARE(RCAR_GEN4_PCIE_FIRMWARE_NAME); + +struct rcar_gen4_pcie; +struct rcar_gen4_pcie_drvdata { + void (*additional_common_init)(struct rcar_gen4_pcie *rcar); + int (*ltssm_control)(struct rcar_gen4_pcie *rcar, bool enable); + enum dw_pcie_device_mode mode; +}; + +struct rcar_gen4_pcie { + struct dw_pcie dw; + void __iomem *base; + void __iomem *phy_base; + struct platform_device *pdev; + const struct rcar_gen4_pcie_drvdata *drvdata; +}; +#define to_rcar_gen4_pcie(_dw) container_of(_dw, struct rcar_gen4_pcie, dw) + +/* Common */ +static bool rcar_gen4_pcie_link_up(struct dw_pcie *dw) +{ + struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw); + u32 val, mask; + + val = readl(rcar->base + PCIEINTSTS0); + mask = RDLH_LINK_UP | SMLH_LINK_UP; + + return (val & mask) == mask; +} + +/* + * Manually initiate the speed change. Return 0 if change succeeded; otherwise + * -ETIMEDOUT. + */ +static int rcar_gen4_pcie_speed_change(struct dw_pcie *dw) +{ + u32 val; + int i; + + val = dw_pcie_readl_dbi(dw, PCIE_LINK_WIDTH_SPEED_CONTROL); + val &= ~PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(dw, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + + val = dw_pcie_readl_dbi(dw, PCIE_LINK_WIDTH_SPEED_CONTROL); + val |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(dw, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + + for (i = 0; i < RCAR_NUM_SPEED_CHANGE_RETRIES; i++) { + val = dw_pcie_readl_dbi(dw, PCIE_LINK_WIDTH_SPEED_CONTROL); + if (!(val & PORT_LOGIC_SPEED_CHANGE)) + return 0; + usleep_range(10000, 11000); + } + + return -ETIMEDOUT; +} + +/* + * Enable LTSSM of this controller and manually initiate the speed change. + * Always return 0. + */ +static int rcar_gen4_pcie_start_link(struct dw_pcie *dw) +{ + struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw); + int i, changes, ret; + + if (rcar->drvdata->ltssm_control) { + ret = rcar->drvdata->ltssm_control(rcar, true); + if (ret) + return ret; + } + + /* + * Require direct speed change with retrying here if the max_link_speed + * is PCIe Gen2 or higher. + */ + changes = min_not_zero(dw->max_link_speed, RCAR_MAX_LINK_SPEED) - 1; + + /* + * Since dw_pcie_setup_rc() sets it once, PCIe Gen2 will be trained. + * So, this needs remaining times for up to PCIe Gen4 if RC mode. + */ + if (changes && rcar->drvdata->mode == DW_PCIE_RC_TYPE) + changes--; + + for (i = 0; i < changes; i++) { + /* It may not be connected in EP mode yet. So, break the loop */ + if (rcar_gen4_pcie_speed_change(dw)) + break; + } + + return 0; +} + +static void rcar_gen4_pcie_stop_link(struct dw_pcie *dw) +{ + struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw); + + if (rcar->drvdata->ltssm_control) + rcar->drvdata->ltssm_control(rcar, false); +} + +static int rcar_gen4_pcie_common_init(struct rcar_gen4_pcie *rcar) +{ + struct dw_pcie *dw = &rcar->dw; + u32 val; + int ret; + + ret = clk_bulk_prepare_enable(DW_PCIE_NUM_CORE_CLKS, dw->core_clks); + if (ret) { + dev_err(dw->dev, "Enabling core clocks failed\n"); + return ret; + } + + 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) { + val |= DEVICE_TYPE_RC; + } else if (rcar->drvdata->mode == DW_PCIE_EP_TYPE) { + val |= DEVICE_TYPE_EP; + } else { + ret = -EINVAL; + goto err_unprepare; + } + + if (dw->num_lanes < 4) + val |= BIFUR_MOD_SET_ON; + + writel(val, rcar->base + PCIEMSR0); + + ret = reset_control_deassert(dw->core_rsts[DW_PCIE_PWR_RST].rstc); + 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); + + return 0; + +err_unprepare: + clk_bulk_disable_unprepare(DW_PCIE_NUM_CORE_CLKS, dw->core_clks); + + return ret; +} + +static void rcar_gen4_pcie_common_deinit(struct rcar_gen4_pcie *rcar) +{ + struct dw_pcie *dw = &rcar->dw; + + reset_control_assert(dw->core_rsts[DW_PCIE_PWR_RST].rstc); + clk_bulk_disable_unprepare(DW_PCIE_NUM_CORE_CLKS, dw->core_clks); +} + +static int rcar_gen4_pcie_prepare(struct rcar_gen4_pcie *rcar) +{ + struct device *dev = rcar->dw.dev; + int err; + + pm_runtime_enable(dev); + err = pm_runtime_resume_and_get(dev); + if (err < 0) { + dev_err(dev, "Runtime resume failed\n"); + pm_runtime_disable(dev); + } + + return err; +} + +static void rcar_gen4_pcie_unprepare(struct rcar_gen4_pcie *rcar) +{ + struct device *dev = rcar->dw.dev; + + pm_runtime_put(dev); + pm_runtime_disable(dev); +} + +static int rcar_gen4_pcie_get_resources(struct rcar_gen4_pcie *rcar) +{ + rcar->phy_base = devm_platform_ioremap_resource_byname(rcar->pdev, "phy"); + if (IS_ERR(rcar->phy_base)) + return PTR_ERR(rcar->phy_base); + + /* Renesas-specific registers */ + rcar->base = devm_platform_ioremap_resource_byname(rcar->pdev, "app"); + + return PTR_ERR_OR_ZERO(rcar->base); +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = rcar_gen4_pcie_start_link, + .stop_link = rcar_gen4_pcie_stop_link, + .link_up = rcar_gen4_pcie_link_up, +}; + +static struct rcar_gen4_pcie *rcar_gen4_pcie_alloc(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rcar_gen4_pcie *rcar; + + rcar = devm_kzalloc(dev, sizeof(*rcar), GFP_KERNEL); + if (!rcar) + return ERR_PTR(-ENOMEM); + + rcar->dw.ops = &dw_pcie_ops; + rcar->dw.dev = dev; + rcar->pdev = pdev; + rcar->dw.edma.mf = EDMA_MF_EDMA_UNROLL; + dw_pcie_cap_set(&rcar->dw, REQ_RES); + platform_set_drvdata(pdev, rcar); + + return rcar; +} + +/* Host mode */ +static int rcar_gen4_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *dw = to_dw_pcie_from_pp(pp); + struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw); + int ret; + u32 val; + + gpiod_set_value_cansleep(dw->pe_rst, 1); + + ret = rcar_gen4_pcie_common_init(rcar); + if (ret) + return ret; + + /* + * According to the section 3.5.7.2 "RC Mode" in DWC PCIe Dual Mode + * Rev.5.20a and 3.5.6.1 "RC mode" in DWC PCIe RC databook v5.20a, we + * should disable two BARs to avoid unnecessary memory assignment + * during device enumeration. + */ + dw_pcie_writel_dbi2(dw, PCI_BASE_ADDRESS_0, 0x0); + dw_pcie_writel_dbi2(dw, PCI_BASE_ADDRESS_1, 0x0); + + /* Enable MSI interrupt signal */ + val = readl(rcar->base + PCIEINTSTS0EN); + val |= MSI_CTRL_INT; + writel(val, rcar->base + PCIEINTSTS0EN); + + msleep(PCIE_T_PVPERL_MS); /* pe_rst requires 100msec delay */ + + gpiod_set_value_cansleep(dw->pe_rst, 0); + + return 0; +} + +static void rcar_gen4_pcie_host_deinit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *dw = to_dw_pcie_from_pp(pp); + struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw); + + gpiod_set_value_cansleep(dw->pe_rst, 1); + rcar_gen4_pcie_common_deinit(rcar); +} + +static const struct dw_pcie_host_ops rcar_gen4_pcie_host_ops = { + .init = rcar_gen4_pcie_host_init, + .deinit = rcar_gen4_pcie_host_deinit, +}; + +static int rcar_gen4_add_dw_pcie_rp(struct rcar_gen4_pcie *rcar) +{ + struct dw_pcie_rp *pp = &rcar->dw.pp; + + if (!IS_ENABLED(CONFIG_PCIE_RCAR_GEN4_HOST)) + return -ENODEV; + + pp->num_vectors = MAX_MSI_IRQS; + pp->ops = &rcar_gen4_pcie_host_ops; + + return dw_pcie_host_init(pp); +} + +static void rcar_gen4_remove_dw_pcie_rp(struct rcar_gen4_pcie *rcar) +{ + dw_pcie_host_deinit(&rcar->dw.pp); +} + +/* Endpoint mode */ +static void rcar_gen4_pcie_ep_pre_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *dw = to_dw_pcie_from_ep(ep); + struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw); + int ret; + + ret = rcar_gen4_pcie_common_init(rcar); + if (ret) + return; + + writel(PCIEDMAINTSTSEN_INIT, rcar->base + PCIEDMAINTSTSEN); +} + +static void rcar_gen4_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 void rcar_gen4_pcie_ep_deinit(struct rcar_gen4_pcie *rcar) +{ + writel(0, rcar->base + PCIEDMAINTSTSEN); + rcar_gen4_pcie_common_deinit(rcar); +} + +static int rcar_gen4_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + unsigned int type, u16 interrupt_num) +{ + struct dw_pcie *dw = 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(dw->dev, "Unknown IRQ type\n"); + return -EINVAL; + } + + return 0; +} + +static const struct pci_epc_features rcar_gen4_pcie_epc_features = { + .msi_capable = true, + .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, +}; + +static const struct pci_epc_features* +rcar_gen4_pcie_ep_get_features(struct dw_pcie_ep *ep) +{ + return &rcar_gen4_pcie_epc_features; +} + +static unsigned int rcar_gen4_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep, + u8 func_no) +{ + return func_no * RCAR_GEN4_PCIE_EP_FUNC_DBI_OFFSET; +} + +static unsigned int rcar_gen4_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep, + u8 func_no) +{ + return func_no * RCAR_GEN4_PCIE_EP_FUNC_DBI2_OFFSET; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .pre_init = rcar_gen4_pcie_ep_pre_init, + .init = rcar_gen4_pcie_ep_init, + .raise_irq = rcar_gen4_pcie_ep_raise_irq, + .get_features = rcar_gen4_pcie_ep_get_features, + .get_dbi_offset = rcar_gen4_pcie_ep_get_dbi_offset, + .get_dbi2_offset = rcar_gen4_pcie_ep_get_dbi2_offset, +}; + +static int rcar_gen4_add_dw_pcie_ep(struct rcar_gen4_pcie *rcar) +{ + struct dw_pcie_ep *ep = &rcar->dw.ep; + struct device *dev = rcar->dw.dev; + int ret; + + if (!IS_ENABLED(CONFIG_PCIE_RCAR_GEN4_EP)) + return -ENODEV; + + ep->ops = &pcie_ep_ops; + + ret = dw_pcie_ep_init(ep); + if (ret) { + rcar_gen4_pcie_ep_deinit(rcar); + return ret; + } + + ret = dw_pcie_ep_init_registers(ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(ep); + rcar_gen4_pcie_ep_deinit(rcar); + } + + pci_epc_init_notify(ep->epc); + + return ret; +} + +static void rcar_gen4_remove_dw_pcie_ep(struct rcar_gen4_pcie *rcar) +{ + dw_pcie_ep_deinit(&rcar->dw.ep); + rcar_gen4_pcie_ep_deinit(rcar); +} + +/* Common */ +static int rcar_gen4_add_dw_pcie(struct rcar_gen4_pcie *rcar) +{ + rcar->drvdata = of_device_get_match_data(&rcar->pdev->dev); + if (!rcar->drvdata) + return -EINVAL; + + switch (rcar->drvdata->mode) { + case DW_PCIE_RC_TYPE: + return rcar_gen4_add_dw_pcie_rp(rcar); + case DW_PCIE_EP_TYPE: + return rcar_gen4_add_dw_pcie_ep(rcar); + default: + return -EINVAL; + } +} + +static int rcar_gen4_pcie_probe(struct platform_device *pdev) +{ + struct rcar_gen4_pcie *rcar; + int err; + + rcar = rcar_gen4_pcie_alloc(pdev); + if (IS_ERR(rcar)) + return PTR_ERR(rcar); + + err = rcar_gen4_pcie_get_resources(rcar); + if (err) + return err; + + err = rcar_gen4_pcie_prepare(rcar); + if (err) + return err; + + err = rcar_gen4_add_dw_pcie(rcar); + if (err) + goto err_unprepare; + + return 0; + +err_unprepare: + rcar_gen4_pcie_unprepare(rcar); + + return err; +} + +static void rcar_gen4_remove_dw_pcie(struct rcar_gen4_pcie *rcar) +{ + switch (rcar->drvdata->mode) { + case DW_PCIE_RC_TYPE: + rcar_gen4_remove_dw_pcie_rp(rcar); + break; + case DW_PCIE_EP_TYPE: + rcar_gen4_remove_dw_pcie_ep(rcar); + break; + default: + break; + } +} + +static void rcar_gen4_pcie_remove(struct platform_device *pdev) +{ + struct rcar_gen4_pcie *rcar = platform_get_drvdata(pdev); + + rcar_gen4_remove_dw_pcie(rcar); + rcar_gen4_pcie_unprepare(rcar); +} + +static int r8a779f0_pcie_ltssm_control(struct rcar_gen4_pcie *rcar, bool enable) +{ + u32 val; + + val = readl(rcar->base + PCIERSTCTRL1); + if (enable) { + val |= APP_LTSSM_ENABLE; + val &= ~APP_HOLD_PHY_RST; + } else { + /* + * Since the datasheet of R-Car doesn't mention how to assert + * the APP_HOLD_PHY_RST, don't assert it again. Otherwise, + * hang-up issue happened in the dw_edma_core_off() when + * the controller didn't detect a PCI device. + */ + val &= ~APP_LTSSM_ENABLE; + } + writel(val, rcar->base + PCIERSTCTRL1); + + return 0; +} + +static void rcar_gen4_pcie_additional_common_init(struct rcar_gen4_pcie *rcar) +{ + struct dw_pcie *dw = &rcar->dw; + u32 val; + + val = dw_pcie_readl_dbi(dw, PCIE_PORT_LANE_SKEW); + val &= ~PORT_LANE_SKEW_INSERT_MASK; + if (dw->num_lanes < 4) + val |= BIT(6); + dw_pcie_writel_dbi(dw, PCIE_PORT_LANE_SKEW, val); + + val = readl(rcar->base + PCIEPWRMNGCTRL); + val |= APP_CLK_REQ_N | APP_CLK_PM_EN; + writel(val, rcar->base + PCIEPWRMNGCTRL); +} + +static void rcar_gen4_pcie_phy_reg_update_bits(struct rcar_gen4_pcie *rcar, + u32 offset, u32 mask, u32 val) +{ + u32 tmp; + + tmp = readl(rcar->phy_base + offset); + tmp &= ~mask; + tmp |= val; + writel(tmp, rcar->phy_base + offset); +} + +/* + * SoC datasheet suggests checking port logic register bits during firmware + * write. If read returns non-zero value, then this function returns -EAGAIN + * indicating that the write needs to be done again. If read returns zero, + * then return 0 to indicate success. + */ +static int rcar_gen4_pcie_reg_test_bit(struct rcar_gen4_pcie *rcar, + u32 offset, u32 mask) +{ + struct dw_pcie *dw = &rcar->dw; + + if (dw_pcie_readl_dbi(dw, offset) & mask) + return -EAGAIN; + + return 0; +} + +static int rcar_gen4_pcie_download_phy_firmware(struct rcar_gen4_pcie *rcar) +{ + /* The check_addr values are magical numbers in the datasheet */ + static const u32 check_addr[] = { + 0x00101018, + 0x00101118, + 0x00101021, + 0x00101121, + }; + struct dw_pcie *dw = &rcar->dw; + const struct firmware *fw; + unsigned int i, timeout; + u32 data; + int ret; + + ret = request_firmware(&fw, RCAR_GEN4_PCIE_FIRMWARE_NAME, dw->dev); + if (ret) { + dev_err(dw->dev, "Failed to load firmware (%s): %d\n", + RCAR_GEN4_PCIE_FIRMWARE_NAME, ret); + return ret; + } + + for (i = 0; i < (fw->size / 2); i++) { + data = fw->data[(i * 2) + 1] << 8 | fw->data[i * 2]; + timeout = 100; + do { + dw_pcie_writel_dbi(dw, PRTLGC89, RCAR_GEN4_PCIE_FIRMWARE_BASE_ADDR + i); + dw_pcie_writel_dbi(dw, PRTLGC90, data); + if (!rcar_gen4_pcie_reg_test_bit(rcar, PRTLGC89, BIT(30))) + break; + if (!(--timeout)) { + ret = -ETIMEDOUT; + goto exit; + } + usleep_range(100, 200); + } while (1); + } + + rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x0f8, BIT(17), BIT(17)); + + for (i = 0; i < ARRAY_SIZE(check_addr); i++) { + timeout = 100; + do { + dw_pcie_writel_dbi(dw, PRTLGC89, check_addr[i]); + ret = rcar_gen4_pcie_reg_test_bit(rcar, PRTLGC89, BIT(30)); + ret |= rcar_gen4_pcie_reg_test_bit(rcar, PRTLGC90, BIT(0)); + if (!ret) + break; + if (!(--timeout)) { + ret = -ETIMEDOUT; + goto exit; + } + usleep_range(100, 200); + } while (1); + } + +exit: + release_firmware(fw); + + return ret; +} + +static int rcar_gen4_pcie_ltssm_control(struct rcar_gen4_pcie *rcar, bool enable) +{ + struct dw_pcie *dw = &rcar->dw; + u32 val; + int ret; + + if (!enable) { + val = readl(rcar->base + PCIERSTCTRL1); + val &= ~APP_LTSSM_ENABLE; + writel(val, rcar->base + PCIERSTCTRL1); + + return 0; + } + + val = dw_pcie_readl_dbi(dw, PCIE_PORT_FORCE); + val |= PORT_FORCE_DO_DESKEW_FOR_SRIS; + dw_pcie_writel_dbi(dw, PCIE_PORT_FORCE, val); + + val = readl(rcar->base + PCIEMSR0); + val |= APP_SRIS_MODE; + writel(val, rcar->base + PCIEMSR0); + + /* + * The R-Car Gen4 datasheet doesn't describe the PHY registers' name. + * But, the initialization procedure describes these offsets. So, + * this driver has magical offset numbers. + */ + rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x700, BIT(28), 0); + rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x700, BIT(20), 0); + rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x700, BIT(12), 0); + rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x700, BIT(4), 0); + + 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(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); + rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x0f8, BIT(19), BIT(19)); + + val = readl(rcar->base + PCIERSTCTRL1); + val &= ~APP_HOLD_PHY_RST; + writel(val, rcar->base + PCIERSTCTRL1); + + ret = readl_poll_timeout(rcar->phy_base + 0x0f8, val, val & BIT(18), 100, 10000); + if (ret < 0) + return ret; + + ret = rcar_gen4_pcie_download_phy_firmware(rcar); + if (ret) + return ret; + + val = readl(rcar->base + PCIERSTCTRL1); + val |= APP_LTSSM_ENABLE; + writel(val, rcar->base + PCIERSTCTRL1); + + return 0; +} + +static struct rcar_gen4_pcie_drvdata drvdata_r8a779f0_pcie = { + .ltssm_control = r8a779f0_pcie_ltssm_control, + .mode = DW_PCIE_RC_TYPE, +}; + +static struct rcar_gen4_pcie_drvdata drvdata_r8a779f0_pcie_ep = { + .ltssm_control = r8a779f0_pcie_ltssm_control, + .mode = DW_PCIE_EP_TYPE, +}; + +static struct rcar_gen4_pcie_drvdata drvdata_rcar_gen4_pcie = { + .additional_common_init = rcar_gen4_pcie_additional_common_init, + .ltssm_control = rcar_gen4_pcie_ltssm_control, + .mode = DW_PCIE_RC_TYPE, +}; + +static struct rcar_gen4_pcie_drvdata drvdata_rcar_gen4_pcie_ep = { + .additional_common_init = rcar_gen4_pcie_additional_common_init, + .ltssm_control = rcar_gen4_pcie_ltssm_control, + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct of_device_id rcar_gen4_pcie_of_match[] = { + { + .compatible = "renesas,r8a779f0-pcie", + .data = &drvdata_r8a779f0_pcie, + }, + { + .compatible = "renesas,r8a779f0-pcie-ep", + .data = &drvdata_r8a779f0_pcie_ep, + }, + { + .compatible = "renesas,rcar-gen4-pcie", + .data = &drvdata_rcar_gen4_pcie, + }, + { + .compatible = "renesas,rcar-gen4-pcie-ep", + .data = &drvdata_rcar_gen4_pcie_ep, + }, + {}, +}; +MODULE_DEVICE_TABLE(of, rcar_gen4_pcie_of_match); + +static struct platform_driver rcar_gen4_pcie_driver = { + .driver = { + .name = "pcie-rcar-gen4", + .of_match_table = rcar_gen4_pcie_of_match, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = rcar_gen4_pcie_probe, + .remove = rcar_gen4_pcie_remove, +}; +module_platform_driver(rcar_gen4_pcie_driver); + +MODULE_DESCRIPTION("Renesas R-Car Gen4 PCIe controller driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/dwc/pcie-sophgo.c b/drivers/pci/controller/dwc/pcie-sophgo.c new file mode 100644 index 000000000000..ad4baaa34ffa --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-sophgo.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sophgo DesignWare based PCIe host controller driver + */ + +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/property.h> +#include <linux/platform_device.h> + +#include "pcie-designware.h" + +#define to_sophgo_pcie(x) dev_get_drvdata((x)->dev) + +#define PCIE_INT_SIGNAL 0xc48 +#define PCIE_INT_EN 0xca0 + +#define PCIE_INT_SIGNAL_INTX GENMASK(8, 5) + +#define PCIE_INT_EN_INTX GENMASK(4, 1) +#define PCIE_INT_EN_INT_MSI BIT(5) + +struct sophgo_pcie { + struct dw_pcie pci; + void __iomem *app_base; + struct clk_bulk_data *clks; + unsigned int clk_cnt; + struct irq_domain *irq_domain; +}; + +static int sophgo_pcie_readl_app(struct sophgo_pcie *sophgo, u32 reg) +{ + return readl_relaxed(sophgo->app_base + reg); +} + +static void sophgo_pcie_writel_app(struct sophgo_pcie *sophgo, u32 val, u32 reg) +{ + writel_relaxed(val, sophgo->app_base + reg); +} + +static void sophgo_pcie_intx_handler(struct irq_desc *desc) +{ + struct dw_pcie_rp *pp = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long hwirq, reg; + + chained_irq_enter(chip, desc); + + reg = sophgo_pcie_readl_app(sophgo, PCIE_INT_SIGNAL); + reg = FIELD_GET(PCIE_INT_SIGNAL_INTX, reg); + + for_each_set_bit(hwirq, ®, PCI_NUM_INTX) + generic_handle_domain_irq(sophgo->irq_domain, hwirq); + + chained_irq_exit(chip, desc); +} + +static void sophgo_intx_irq_mask(struct irq_data *d) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = sophgo_pcie_readl_app(sophgo, PCIE_INT_EN); + val &= ~FIELD_PREP(PCIE_INT_EN_INTX, BIT(d->hwirq)); + sophgo_pcie_writel_app(sophgo, val, PCIE_INT_EN); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +}; + +static void sophgo_intx_irq_unmask(struct irq_data *d) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = sophgo_pcie_readl_app(sophgo, PCIE_INT_EN); + val |= FIELD_PREP(PCIE_INT_EN_INTX, BIT(d->hwirq)); + sophgo_pcie_writel_app(sophgo, val, PCIE_INT_EN); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +}; + +static struct irq_chip sophgo_intx_irq_chip = { + .name = "INTx", + .irq_mask = sophgo_intx_irq_mask, + .irq_unmask = sophgo_intx_irq_unmask, +}; + +static int sophgo_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &sophgo_intx_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = sophgo_pcie_intx_map, +}; + +static int sophgo_pcie_init_irq_domain(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + struct device *dev = sophgo->pci.dev; + struct fwnode_handle *intc; + int irq; + + intc = device_get_named_child_node(dev, "interrupt-controller"); + if (!intc) { + dev_err(dev, "missing child interrupt-controller node\n"); + return -ENODEV; + } + + irq = fwnode_irq_get(intc, 0); + if (irq < 0) { + dev_err(dev, "failed to get INTx irq number\n"); + fwnode_handle_put(intc); + return irq; + } + + sophgo->irq_domain = irq_domain_create_linear(intc, PCI_NUM_INTX, + &intx_domain_ops, pp); + fwnode_handle_put(intc); + if (!sophgo->irq_domain) { + dev_err(dev, "failed to get a INTx irq domain\n"); + return -EINVAL; + } + + return irq; +} + +static void sophgo_pcie_msi_enable(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = sophgo_pcie_readl_app(sophgo, PCIE_INT_EN); + val |= PCIE_INT_EN_INT_MSI; + sophgo_pcie_writel_app(sophgo, val, PCIE_INT_EN); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static int sophgo_pcie_host_init(struct dw_pcie_rp *pp) +{ + int irq; + + irq = sophgo_pcie_init_irq_domain(pp); + if (irq < 0) + return irq; + + irq_set_chained_handler_and_data(irq, sophgo_pcie_intx_handler, pp); + + sophgo_pcie_msi_enable(pp); + + return 0; +} + +static const struct dw_pcie_host_ops sophgo_pcie_host_ops = { + .init = sophgo_pcie_host_init, +}; + +static int sophgo_pcie_clk_init(struct sophgo_pcie *sophgo) +{ + struct device *dev = sophgo->pci.dev; + int ret; + + ret = devm_clk_bulk_get_all_enabled(dev, &sophgo->clks); + if (ret < 0) + return dev_err_probe(dev, ret, "failed to get clocks\n"); + + sophgo->clk_cnt = ret; + + return 0; +} + +static int sophgo_pcie_resource_get(struct platform_device *pdev, + struct sophgo_pcie *sophgo) +{ + sophgo->app_base = devm_platform_ioremap_resource_byname(pdev, "app"); + if (IS_ERR(sophgo->app_base)) + return dev_err_probe(&pdev->dev, PTR_ERR(sophgo->app_base), + "failed to map app registers\n"); + + return 0; +} + +static int sophgo_pcie_configure_rc(struct sophgo_pcie *sophgo) +{ + struct dw_pcie_rp *pp; + + pp = &sophgo->pci.pp; + pp->ops = &sophgo_pcie_host_ops; + + return dw_pcie_host_init(pp); +} + +static int sophgo_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct sophgo_pcie *sophgo; + int ret; + + sophgo = devm_kzalloc(dev, sizeof(*sophgo), GFP_KERNEL); + if (!sophgo) + return -ENOMEM; + + platform_set_drvdata(pdev, sophgo); + + sophgo->pci.dev = dev; + + ret = sophgo_pcie_resource_get(pdev, sophgo); + if (ret) + return ret; + + ret = sophgo_pcie_clk_init(sophgo); + if (ret) + return ret; + + return sophgo_pcie_configure_rc(sophgo); +} + +static const struct of_device_id sophgo_pcie_of_match[] = { + { .compatible = "sophgo,sg2044-pcie" }, + { } +}; +MODULE_DEVICE_TABLE(of, sophgo_pcie_of_match); + +static struct platform_driver sophgo_pcie_driver = { + .driver = { + .name = "sophgo-pcie", + .of_match_table = sophgo_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = sophgo_pcie_probe, +}; +builtin_platform_driver(sophgo_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-spacemit-k1.c b/drivers/pci/controller/dwc/pcie-spacemit-k1.c new file mode 100644 index 000000000000..be20a520255b --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-spacemit-k1.c @@ -0,0 +1,357 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SpacemiT K1 PCIe host driver + * + * Copyright (C) 2025 by RISCstar Solutions Corporation. All rights reserved. + * Copyright (c) 2023, spacemit Corporation. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/gfp.h> +#include <linux/mfd/syscon.h> +#include <linux/mod_devicetable.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +#define PCI_VENDOR_ID_SPACEMIT 0x201f +#define PCI_DEVICE_ID_SPACEMIT_K1 0x0001 + +/* Offsets and field definitions for link management registers */ +#define K1_PHY_AHB_IRQ_EN 0x0000 +#define PCIE_INTERRUPT_EN BIT(0) + +#define K1_PHY_AHB_LINK_STS 0x0004 +#define SMLH_LINK_UP BIT(1) +#define RDLH_LINK_UP BIT(12) + +#define INTR_ENABLE 0x0014 +#define MSI_CTRL_INT BIT(11) + +/* Some controls require APMU regmap access */ +#define SYSCON_APMU "spacemit,apmu" + +/* Offsets and field definitions for APMU registers */ +#define PCIE_CLK_RESET_CONTROL 0x0000 +#define LTSSM_EN BIT(6) +#define PCIE_AUX_PWR_DET BIT(9) +#define PCIE_RC_PERST BIT(12) /* 1: assert PERST# */ +#define APP_HOLD_PHY_RST BIT(30) +#define DEVICE_TYPE_RC BIT(31) /* 0: endpoint; 1: RC */ + +#define PCIE_CONTROL_LOGIC 0x0004 +#define PCIE_SOFT_RESET BIT(0) + +struct k1_pcie { + struct dw_pcie pci; + struct phy *phy; + void __iomem *link; + struct regmap *pmu; /* Errors ignored; MMIO-backed regmap */ + u32 pmu_off; +}; + +#define to_k1_pcie(dw_pcie) \ + platform_get_drvdata(to_platform_device((dw_pcie)->dev)) + +static void k1_pcie_toggle_soft_reset(struct k1_pcie *k1) +{ + u32 offset; + u32 val; + + /* + * Write, then read back to guarantee it has reached the device + * before we start the delay. + */ + offset = k1->pmu_off + PCIE_CONTROL_LOGIC; + regmap_set_bits(k1->pmu, offset, PCIE_SOFT_RESET); + regmap_read(k1->pmu, offset, &val); + + mdelay(2); + + regmap_clear_bits(k1->pmu, offset, PCIE_SOFT_RESET); +} + +/* Enable app clocks, deassert resets */ +static int k1_pcie_enable_resources(struct k1_pcie *k1) +{ + struct dw_pcie *pci = &k1->pci; + int ret; + + ret = clk_bulk_prepare_enable(ARRAY_SIZE(pci->app_clks), pci->app_clks); + if (ret) + return ret; + + ret = reset_control_bulk_deassert(ARRAY_SIZE(pci->app_rsts), + pci->app_rsts); + if (ret) + goto err_disable_clks; + + return 0; + +err_disable_clks: + clk_bulk_disable_unprepare(ARRAY_SIZE(pci->app_clks), pci->app_clks); + + return ret; +} + +/* Assert resets, disable app clocks */ +static void k1_pcie_disable_resources(struct k1_pcie *k1) +{ + struct dw_pcie *pci = &k1->pci; + + reset_control_bulk_assert(ARRAY_SIZE(pci->app_rsts), pci->app_rsts); + clk_bulk_disable_unprepare(ARRAY_SIZE(pci->app_clks), pci->app_clks); +} + +/* FIXME: Disable ASPM L1 to avoid errors reported on some NVMe drives */ +static void k1_pcie_disable_aspm_l1(struct k1_pcie *k1) +{ + struct dw_pcie *pci = &k1->pci; + u8 offset; + u32 val; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + offset += PCI_EXP_LNKCAP; + + dw_pcie_dbi_ro_wr_en(pci); + val = dw_pcie_readl_dbi(pci, offset); + val &= ~PCI_EXP_LNKCAP_ASPM_L1; + dw_pcie_writel_dbi(pci, offset, val); + dw_pcie_dbi_ro_wr_dis(pci); +} + +static int k1_pcie_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 reset_ctrl; + u32 val; + int ret; + + k1_pcie_toggle_soft_reset(k1); + + ret = k1_pcie_enable_resources(k1); + if (ret) + return ret; + + /* Set the PCI vendor and device ID */ + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, PCI_VENDOR_ID_SPACEMIT); + dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, PCI_DEVICE_ID_SPACEMIT_K1); + dw_pcie_dbi_ro_wr_dis(pci); + + /* + * Start by asserting fundamental reset (drive PERST# low). The + * PCI CEM spec says that PERST# should be deasserted at least + * 100ms after the power becomes stable, so we'll insert that + * delay first. Write, then read it back to guarantee the write + * reaches the device before we start the delay. + */ + reset_ctrl = k1->pmu_off + PCIE_CLK_RESET_CONTROL; + regmap_set_bits(k1->pmu, reset_ctrl, PCIE_RC_PERST); + regmap_read(k1->pmu, reset_ctrl, &val); + mdelay(PCIE_T_PVPERL_MS); + + /* + * Put the controller in root complex mode, and indicate that + * Vaux (3.3v) is present. + */ + regmap_set_bits(k1->pmu, reset_ctrl, DEVICE_TYPE_RC | PCIE_AUX_PWR_DET); + + ret = phy_init(k1->phy); + if (ret) { + k1_pcie_disable_resources(k1); + + return ret; + } + + /* Deassert fundamental reset (drive PERST# high) */ + regmap_clear_bits(k1->pmu, reset_ctrl, PCIE_RC_PERST); + + /* Finally, as a workaround, disable ASPM L1 */ + k1_pcie_disable_aspm_l1(k1); + + return 0; +} + +static void k1_pcie_deinit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct k1_pcie *k1 = to_k1_pcie(pci); + + /* Assert fundamental reset (drive PERST# low) */ + regmap_set_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + PCIE_RC_PERST); + + phy_exit(k1->phy); + + k1_pcie_disable_resources(k1); +} + +static const struct dw_pcie_host_ops k1_pcie_host_ops = { + .init = k1_pcie_init, + .deinit = k1_pcie_deinit, +}; + +static bool k1_pcie_link_up(struct dw_pcie *pci) +{ + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 val; + + val = readl_relaxed(k1->link + K1_PHY_AHB_LINK_STS); + + return (val & RDLH_LINK_UP) && (val & SMLH_LINK_UP); +} + +static int k1_pcie_start_link(struct dw_pcie *pci) +{ + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 val; + + /* Stop holding the PHY in reset, and enable link training */ + regmap_update_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + APP_HOLD_PHY_RST | LTSSM_EN, LTSSM_EN); + + /* Enable the MSI interrupt */ + writel_relaxed(MSI_CTRL_INT, k1->link + INTR_ENABLE); + + /* Top-level interrupt enable */ + val = readl_relaxed(k1->link + K1_PHY_AHB_IRQ_EN); + val |= PCIE_INTERRUPT_EN; + writel_relaxed(val, k1->link + K1_PHY_AHB_IRQ_EN); + + return 0; +} + +static void k1_pcie_stop_link(struct dw_pcie *pci) +{ + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 val; + + /* Disable interrupts */ + val = readl_relaxed(k1->link + K1_PHY_AHB_IRQ_EN); + val &= ~PCIE_INTERRUPT_EN; + writel_relaxed(val, k1->link + K1_PHY_AHB_IRQ_EN); + + writel_relaxed(0, k1->link + INTR_ENABLE); + + /* Disable the link and hold the PHY in reset */ + regmap_update_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + APP_HOLD_PHY_RST | LTSSM_EN, APP_HOLD_PHY_RST); +} + +static const struct dw_pcie_ops k1_pcie_ops = { + .link_up = k1_pcie_link_up, + .start_link = k1_pcie_start_link, + .stop_link = k1_pcie_stop_link, +}; + +static int k1_pcie_parse_port(struct k1_pcie *k1) +{ + struct device *dev = k1->pci.dev; + struct device_node *root_port; + struct phy *phy; + + /* We assume only one root port */ + root_port = of_get_next_available_child(dev_of_node(dev), NULL); + if (!root_port) + return -EINVAL; + + phy = devm_of_phy_get(dev, root_port, NULL); + + of_node_put(root_port); + + if (IS_ERR(phy)) + return PTR_ERR(phy); + + k1->phy = phy; + + return 0; +} + +static int k1_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct k1_pcie *k1; + int ret; + + k1 = devm_kzalloc(dev, sizeof(*k1), GFP_KERNEL); + if (!k1) + return -ENOMEM; + + k1->pmu = syscon_regmap_lookup_by_phandle_args(dev_of_node(dev), + SYSCON_APMU, 1, + &k1->pmu_off); + if (IS_ERR(k1->pmu)) + return dev_err_probe(dev, PTR_ERR(k1->pmu), + "failed to lookup PMU registers\n"); + + k1->link = devm_platform_ioremap_resource_byname(pdev, "link"); + if (IS_ERR(k1->link)) + return dev_err_probe(dev, PTR_ERR(k1->link), + "failed to map \"link\" registers\n"); + + k1->pci.dev = dev; + k1->pci.ops = &k1_pcie_ops; + k1->pci.pp.num_vectors = MAX_MSI_IRQS; + dw_pcie_cap_set(&k1->pci, REQ_RES); + + k1->pci.pp.ops = &k1_pcie_host_ops; + + /* Hold the PHY in reset until we start the link */ + regmap_set_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + APP_HOLD_PHY_RST); + + ret = devm_regulator_get_enable(dev, "vpcie3v3"); + if (ret) + return dev_err_probe(dev, ret, + "failed to get \"vpcie3v3\" supply\n"); + + pm_runtime_set_active(dev); + pm_runtime_no_callbacks(dev); + devm_pm_runtime_enable(dev); + + platform_set_drvdata(pdev, k1); + + ret = k1_pcie_parse_port(k1); + if (ret) + return dev_err_probe(dev, ret, "failed to parse root port\n"); + + ret = dw_pcie_host_init(&k1->pci.pp); + if (ret) + return dev_err_probe(dev, ret, "failed to initialize host\n"); + + return 0; +} + +static void k1_pcie_remove(struct platform_device *pdev) +{ + struct k1_pcie *k1 = platform_get_drvdata(pdev); + + dw_pcie_host_deinit(&k1->pci.pp); +} + +static const struct of_device_id k1_pcie_of_match_table[] = { + { .compatible = "spacemit,k1-pcie", }, + { } +}; + +static struct platform_driver k1_pcie_driver = { + .probe = k1_pcie_probe, + .remove = k1_pcie_remove, + .driver = { + .name = "spacemit-k1-pcie", + .of_match_table = k1_pcie_of_match_table, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; +module_platform_driver(k1_pcie_driver); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SpacemiT K1 PCIe host driver"); diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c index 7d0cdfd8138b..01794a9d3ad2 100644 --- a/drivers/pci/controller/dwc/pcie-spear13xx.c +++ b/drivers/pci/controller/dwc/pcie-spear13xx.c @@ -26,7 +26,6 @@ struct spear13xx_pcie { void __iomem *app_base; struct phy *phy; struct clk *clk; - bool is_gen1; }; struct pcie_app_reg { @@ -65,60 +64,12 @@ struct pcie_app_reg { /* CR6 */ #define MSI_CTRL_INT (1 << 26) -#define EXP_CAP_ID_OFFSET 0x70 - #define to_spear13xx_pcie(x) dev_get_drvdata((x)->dev) -static int spear13xx_pcie_establish_link(struct spear13xx_pcie *spear13xx_pcie) +static int spear13xx_pcie_start_link(struct dw_pcie *pci) { - struct dw_pcie *pci = spear13xx_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct pcie_app_reg *app_reg = spear13xx_pcie->app_base; - u32 val; - u32 exp_cap_off = EXP_CAP_ID_OFFSET; - - if (dw_pcie_link_up(pci)) { - dev_err(pci->dev, "link already up\n"); - return 0; - } - - dw_pcie_setup_rc(pp); - - /* - * this controller support only 128 bytes read size, however its - * default value in capability register is 512 bytes. So force - * it to 128 here. - */ - dw_pcie_read(pci->dbi_base + exp_cap_off + PCI_EXP_DEVCTL, 2, &val); - val &= ~PCI_EXP_DEVCTL_READRQ; - dw_pcie_write(pci->dbi_base + exp_cap_off + PCI_EXP_DEVCTL, 2, val); - - dw_pcie_write(pci->dbi_base + PCI_VENDOR_ID, 2, 0x104A); - dw_pcie_write(pci->dbi_base + PCI_DEVICE_ID, 2, 0xCD80); - - /* - * if is_gen1 is set then handle it, so that some buggy card - * also works - */ - if (spear13xx_pcie->is_gen1) { - dw_pcie_read(pci->dbi_base + exp_cap_off + PCI_EXP_LNKCAP, - 4, &val); - if ((val & PCI_EXP_LNKCAP_SLS) != PCI_EXP_LNKCAP_SLS_2_5GB) { - val &= ~((u32)PCI_EXP_LNKCAP_SLS); - val |= PCI_EXP_LNKCAP_SLS_2_5GB; - dw_pcie_write(pci->dbi_base + exp_cap_off + - PCI_EXP_LNKCAP, 4, val); - } - - dw_pcie_read(pci->dbi_base + exp_cap_off + PCI_EXP_LNKCTL2, - 2, &val); - if ((val & PCI_EXP_LNKCAP_SLS) != PCI_EXP_LNKCAP_SLS_2_5GB) { - val &= ~((u32)PCI_EXP_LNKCAP_SLS); - val |= PCI_EXP_LNKCAP_SLS_2_5GB; - dw_pcie_write(pci->dbi_base + exp_cap_off + - PCI_EXP_LNKCTL2, 2, val); - } - } + struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci); + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; /* enable ltssm */ writel(DEVICE_TYPE_RC | (1 << MISCTRL_EN_ID) @@ -126,15 +77,15 @@ static int spear13xx_pcie_establish_link(struct spear13xx_pcie *spear13xx_pcie) | ((u32)1 << REG_TRANSLATION_ENABLE), &app_reg->app_ctrl_0); - return dw_pcie_wait_for_link(pci); + return 0; } static irqreturn_t spear13xx_pcie_irq_handler(int irq, void *arg) { struct spear13xx_pcie *spear13xx_pcie = arg; - struct pcie_app_reg *app_reg = spear13xx_pcie->app_base; + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; struct dw_pcie *pci = spear13xx_pcie->pci; - struct pcie_port *pp = &pci->pp; + struct dw_pcie_rp *pp = &pci->pp; unsigned int status; status = readl(&app_reg->int_sts); @@ -151,57 +102,64 @@ static irqreturn_t spear13xx_pcie_irq_handler(int irq, void *arg) static void spear13xx_pcie_enable_interrupts(struct spear13xx_pcie *spear13xx_pcie) { - struct dw_pcie *pci = spear13xx_pcie->pci; - struct pcie_port *pp = &pci->pp; - struct pcie_app_reg *app_reg = spear13xx_pcie->app_base; + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; /* Enable MSI interrupt */ - if (IS_ENABLED(CONFIG_PCI_MSI)) { - dw_pcie_msi_init(pp); + if (IS_ENABLED(CONFIG_PCI_MSI)) writel(readl(&app_reg->int_mask) | MSI_CTRL_INT, &app_reg->int_mask); - } } -static int spear13xx_pcie_link_up(struct dw_pcie *pci) +static bool spear13xx_pcie_link_up(struct dw_pcie *pci) { struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci); - struct pcie_app_reg *app_reg = spear13xx_pcie->app_base; - - if (readl(&app_reg->app_status_1) & XMLH_LINK_UP) - return 1; + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; - return 0; + return readl(&app_reg->app_status_1) & XMLH_LINK_UP; } -static int spear13xx_pcie_host_init(struct pcie_port *pp) +static int spear13xx_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci); + u32 exp_cap_off = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; + + spear13xx_pcie->app_base = pci->dbi_base + 0x2000; + + /* + * this controller support only 128 bytes read size, however its + * default value in capability register is 512 bytes. So force + * it to 128 here. + */ + val = dw_pcie_readw_dbi(pci, exp_cap_off + PCI_EXP_DEVCTL); + val &= ~PCI_EXP_DEVCTL_READRQ; + dw_pcie_writew_dbi(pci, exp_cap_off + PCI_EXP_DEVCTL, val); + + dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, 0x104A); + dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, 0xCD80); - spear13xx_pcie_establish_link(spear13xx_pcie); spear13xx_pcie_enable_interrupts(spear13xx_pcie); return 0; } static const struct dw_pcie_host_ops spear13xx_pcie_host_ops = { - .host_init = spear13xx_pcie_host_init, + .init = spear13xx_pcie_host_init, }; static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie, struct platform_device *pdev) { struct dw_pcie *pci = spear13xx_pcie->pci; - struct pcie_port *pp = &pci->pp; + struct dw_pcie_rp *pp = &pci->pp; struct device *dev = &pdev->dev; int ret; pp->irq = platform_get_irq(pdev, 0); - if (pp->irq < 0) { - dev_err(dev, "failed to get irq\n"); + if (pp->irq < 0) return pp->irq; - } + ret = devm_request_irq(dev, pp->irq, spear13xx_pcie_irq_handler, IRQF_SHARED | IRQF_NO_THREAD, "spear1340-pcie", spear13xx_pcie); @@ -211,6 +169,7 @@ static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie, } pp->ops = &spear13xx_pcie_host_ops; + pp->msi_irq[0] = -ENODEV; ret = dw_pcie_host_init(pp); if (ret) { @@ -223,6 +182,7 @@ static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie, static const struct dw_pcie_ops dw_pcie_ops = { .link_up = spear13xx_pcie_link_up, + .start_link = spear13xx_pcie_start_link, }; static int spear13xx_pcie_probe(struct platform_device *pdev) @@ -231,7 +191,6 @@ static int spear13xx_pcie_probe(struct platform_device *pdev) struct dw_pcie *pci; struct spear13xx_pcie *spear13xx_pcie; struct device_node *np = dev->of_node; - struct resource *dbi_base; int ret; spear13xx_pcie = devm_kzalloc(dev, sizeof(*spear13xx_pcie), GFP_KERNEL); @@ -270,17 +229,8 @@ static int spear13xx_pcie_probe(struct platform_device *pdev) return ret; } - dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); - pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base); - if (IS_ERR(pci->dbi_base)) { - dev_err(dev, "couldn't remap dbi base %p\n", dbi_base); - ret = PTR_ERR(pci->dbi_base); - goto fail_clk; - } - spear13xx_pcie->app_base = pci->dbi_base + 0x2000; - if (of_property_read_bool(np, "st,pcie-is-gen1")) - spear13xx_pcie->is_gen1 = true; + pci->max_link_speed = 1; platform_set_drvdata(pdev, spear13xx_pcie); @@ -305,7 +255,7 @@ static struct platform_driver spear13xx_pcie_driver = { .probe = spear13xx_pcie_probe, .driver = { .name = "spear-pcie", - .of_match_table = of_match_ptr(spear13xx_pcie_of_match), + .of_match_table = spear13xx_pcie_of_match, .suppress_bind_attrs = true, }, }; diff --git a/drivers/pci/controller/dwc/pcie-stm32-ep.c b/drivers/pci/controller/dwc/pcie-stm32-ep.c new file mode 100644 index 000000000000..2cecf32d2b0f --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-stm32-ep.c @@ -0,0 +1,343 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * STMicroelectronics STM32MP25 PCIe endpoint driver. + * + * Copyright (C) 2025 STMicroelectronics + * Author: Christian Bruel <christian.bruel@foss.st.com> + */ + +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/mfd/syscon.h> +#include <linux/of_platform.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include "pcie-designware.h" +#include "pcie-stm32.h" + +struct stm32_pcie { + struct dw_pcie pci; + struct regmap *regmap; + struct reset_control *rst; + struct phy *phy; + struct clk *clk; + struct gpio_desc *perst_gpio; + unsigned int perst_irq; +}; + +static void stm32_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static int stm32_pcie_start_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + enable_irq(stm32_pcie->perst_irq); + + return 0; +} + +static void stm32_pcie_stop_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + disable_irq(stm32_pcie->perst_irq); +} + +static int stm32_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + unsigned int type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_IRQ_INTX: + return dw_pcie_ep_raise_intx_irq(ep, func_no); + case PCI_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + return -EINVAL; + } +} + +static const struct pci_epc_features stm32_pcie_epc_features = { + .msi_capable = true, + .align = SZ_64K, +}; + +static const struct pci_epc_features* +stm32_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &stm32_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops stm32_pcie_ep_ops = { + .init = stm32_pcie_ep_init, + .raise_irq = stm32_pcie_raise_irq, + .get_features = stm32_pcie_get_features, +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = stm32_pcie_start_link, + .stop_link = stm32_pcie_stop_link, +}; + +static int stm32_pcie_enable_resources(struct stm32_pcie *stm32_pcie) +{ + int ret; + + ret = phy_init(stm32_pcie->phy); + if (ret) + return ret; + + ret = clk_prepare_enable(stm32_pcie->clk); + if (ret) + phy_exit(stm32_pcie->phy); + + return ret; +} + +static void stm32_pcie_disable_resources(struct stm32_pcie *stm32_pcie) +{ + clk_disable_unprepare(stm32_pcie->clk); + + phy_exit(stm32_pcie->phy); +} + +static void stm32_pcie_perst_assert(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + struct dw_pcie_ep *ep = &stm32_pcie->pci.ep; + struct device *dev = pci->dev; + + dev_dbg(dev, "PERST asserted by host\n"); + + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, 0); + + pci_epc_deinit_notify(ep->epc); + + stm32_pcie_disable_resources(stm32_pcie); + + pm_runtime_put_sync(dev); +} + +static void stm32_pcie_perst_deassert(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + struct device *dev = pci->dev; + struct dw_pcie_ep *ep = &pci->ep; + int ret; + + dev_dbg(dev, "PERST de-asserted by host\n"); + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + dev_err(dev, "Failed to resume runtime PM: %d\n", ret); + return; + } + + ret = stm32_pcie_enable_resources(stm32_pcie); + if (ret) { + dev_err(dev, "Failed to enable resources: %d\n", ret); + goto err_pm_put_sync; + } + + /* + * Reprogram the configuration space registers here because the DBI + * registers were reset by the PHY RCC during phy_init(). + */ + ret = dw_pcie_ep_init_registers(ep); + if (ret) { + dev_err(dev, "Failed to complete initialization: %d\n", ret); + goto err_disable_resources; + } + + pci_epc_init_notify(ep->epc); + + /* Enable link training */ + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, + STM32MP25_PCIECR_LTSSM_EN); + + return; + +err_disable_resources: + stm32_pcie_disable_resources(stm32_pcie); + +err_pm_put_sync: + pm_runtime_put_sync(dev); +} + +static irqreturn_t stm32_pcie_ep_perst_irq_thread(int irq, void *data) +{ + struct stm32_pcie *stm32_pcie = data; + struct dw_pcie *pci = &stm32_pcie->pci; + u32 perst; + + perst = gpiod_get_value(stm32_pcie->perst_gpio); + if (perst) + stm32_pcie_perst_assert(pci); + else + stm32_pcie_perst_deassert(pci); + + irq_set_irq_type(gpiod_to_irq(stm32_pcie->perst_gpio), + (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW)); + + return IRQ_HANDLED; +} + +static int stm32_add_pcie_ep(struct stm32_pcie *stm32_pcie, + struct platform_device *pdev) +{ + struct dw_pcie_ep *ep = &stm32_pcie->pci.ep; + struct device *dev = &pdev->dev; + int ret; + + ret = regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_TYPE_MASK, + STM32MP25_PCIECR_EP); + if (ret) + return ret; + + reset_control_assert(stm32_pcie->rst); + reset_control_deassert(stm32_pcie->rst); + + ep->ops = &stm32_pcie_ep_ops; + + ep->page_size = stm32_pcie_epc_features.align; + + ret = dw_pcie_ep_init(ep); + if (ret) { + dev_err(dev, "Failed to initialize ep: %d\n", ret); + return ret; + } + + ret = stm32_pcie_enable_resources(stm32_pcie); + if (ret) { + dev_err(dev, "Failed to enable resources: %d\n", ret); + dw_pcie_ep_deinit(ep); + return ret; + } + + return 0; +} + +static int stm32_pcie_probe(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie; + struct device *dev = &pdev->dev; + int ret; + + stm32_pcie = devm_kzalloc(dev, sizeof(*stm32_pcie), GFP_KERNEL); + if (!stm32_pcie) + return -ENOMEM; + + stm32_pcie->pci.dev = dev; + stm32_pcie->pci.ops = &dw_pcie_ops; + + stm32_pcie->regmap = syscon_regmap_lookup_by_compatible("st,stm32mp25-syscfg"); + if (IS_ERR(stm32_pcie->regmap)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->regmap), + "No syscfg specified\n"); + + stm32_pcie->phy = devm_phy_get(dev, NULL); + if (IS_ERR(stm32_pcie->phy)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->phy), + "failed to get pcie-phy\n"); + + stm32_pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(stm32_pcie->clk)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->clk), + "Failed to get PCIe clock source\n"); + + stm32_pcie->rst = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(stm32_pcie->rst)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->rst), + "Failed to get PCIe reset\n"); + + stm32_pcie->perst_gpio = devm_gpiod_get(dev, "reset", GPIOD_IN); + if (IS_ERR(stm32_pcie->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->perst_gpio), + "Failed to get reset GPIO\n"); + + ret = phy_set_mode(stm32_pcie->phy, PHY_MODE_PCIE); + if (ret) + return ret; + + platform_set_drvdata(pdev, stm32_pcie); + + pm_runtime_get_noresume(dev); + + ret = devm_pm_runtime_enable(dev); + if (ret < 0) { + pm_runtime_put_noidle(&pdev->dev); + return dev_err_probe(dev, ret, "Failed to enable runtime PM\n"); + } + + stm32_pcie->perst_irq = gpiod_to_irq(stm32_pcie->perst_gpio); + + /* Will be enabled in start_link when device is initialized. */ + irq_set_status_flags(stm32_pcie->perst_irq, IRQ_NOAUTOEN); + + ret = devm_request_threaded_irq(dev, stm32_pcie->perst_irq, NULL, + stm32_pcie_ep_perst_irq_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "perst_irq", stm32_pcie); + if (ret) { + pm_runtime_put_noidle(&pdev->dev); + return dev_err_probe(dev, ret, "Failed to request PERST IRQ\n"); + } + + ret = stm32_add_pcie_ep(stm32_pcie, pdev); + if (ret) + pm_runtime_put_noidle(&pdev->dev); + + return ret; +} + +static void stm32_pcie_remove(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie = platform_get_drvdata(pdev); + struct dw_pcie *pci = &stm32_pcie->pci; + struct dw_pcie_ep *ep = &pci->ep; + + dw_pcie_stop_link(pci); + + pci_epc_deinit_notify(ep->epc); + dw_pcie_ep_deinit(ep); + + stm32_pcie_disable_resources(stm32_pcie); + + pm_runtime_put_sync(&pdev->dev); +} + +static const struct of_device_id stm32_pcie_ep_of_match[] = { + { .compatible = "st,stm32mp25-pcie-ep" }, + {}, +}; + +static struct platform_driver stm32_pcie_ep_driver = { + .probe = stm32_pcie_probe, + .remove = stm32_pcie_remove, + .driver = { + .name = "stm32-ep-pcie", + .of_match_table = stm32_pcie_ep_of_match, + }, +}; + +module_platform_driver(stm32_pcie_ep_driver); + +MODULE_AUTHOR("Christian Bruel <christian.bruel@foss.st.com>"); +MODULE_DESCRIPTION("STM32MP25 PCIe Endpoint Controller driver"); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(of, stm32_pcie_ep_of_match); diff --git a/drivers/pci/controller/dwc/pcie-stm32.c b/drivers/pci/controller/dwc/pcie-stm32.c new file mode 100644 index 000000000000..a9e77478443b --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-stm32.c @@ -0,0 +1,370 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * STMicroelectronics STM32MP25 PCIe root complex driver. + * + * Copyright (C) 2025 STMicroelectronics + * Author: Christian Bruel <christian.bruel@foss.st.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/gpio/consumer.h> +#include <linux/irq.h> +#include <linux/mfd/syscon.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/phy/phy.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> +#include <linux/pm_wakeirq.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/stddef.h> + +#include "../../pci.h" + +#include "pcie-designware.h" +#include "pcie-stm32.h" + +struct stm32_pcie { + struct dw_pcie pci; + struct regmap *regmap; + struct reset_control *rst; + struct phy *phy; + struct clk *clk; + struct gpio_desc *perst_gpio; + struct gpio_desc *wake_gpio; +}; + +static void stm32_pcie_deassert_perst(struct stm32_pcie *stm32_pcie) +{ + if (stm32_pcie->perst_gpio) { + msleep(PCIE_T_PVPERL_MS); + gpiod_set_value(stm32_pcie->perst_gpio, 0); + } + + msleep(PCIE_RESET_CONFIG_WAIT_MS); +} + +static void stm32_pcie_assert_perst(struct stm32_pcie *stm32_pcie) +{ + gpiod_set_value(stm32_pcie->perst_gpio, 1); +} + +static int stm32_pcie_start_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + return regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, + STM32MP25_PCIECR_LTSSM_EN); +} + +static void stm32_pcie_stop_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, 0); +} + +static int stm32_pcie_suspend_noirq(struct device *dev) +{ + struct stm32_pcie *stm32_pcie = dev_get_drvdata(dev); + int ret; + + ret = dw_pcie_suspend_noirq(&stm32_pcie->pci); + if (ret) + return ret; + + stm32_pcie_assert_perst(stm32_pcie); + + clk_disable_unprepare(stm32_pcie->clk); + + if (!device_wakeup_path(dev)) + phy_exit(stm32_pcie->phy); + + return pinctrl_pm_select_sleep_state(dev); +} + +static int stm32_pcie_resume_noirq(struct device *dev) +{ + struct stm32_pcie *stm32_pcie = dev_get_drvdata(dev); + int ret; + + /* + * The core clock is gated with CLKREQ# from the COMBOPHY REFCLK, + * thus if no device is present, must deassert it with a GPIO from + * pinctrl pinmux before accessing the DBI registers. + */ + ret = pinctrl_pm_select_init_state(dev); + if (ret) { + dev_err(dev, "Failed to activate pinctrl pm state: %d\n", ret); + return ret; + } + + if (!device_wakeup_path(dev)) { + ret = phy_init(stm32_pcie->phy); + if (ret) { + pinctrl_pm_select_default_state(dev); + return ret; + } + } + + ret = clk_prepare_enable(stm32_pcie->clk); + if (ret) + goto err_phy_exit; + + stm32_pcie_deassert_perst(stm32_pcie); + + ret = dw_pcie_resume_noirq(&stm32_pcie->pci); + if (ret) + goto err_disable_clk; + + pinctrl_pm_select_default_state(dev); + + return 0; + +err_disable_clk: + stm32_pcie_assert_perst(stm32_pcie); + clk_disable_unprepare(stm32_pcie->clk); + +err_phy_exit: + phy_exit(stm32_pcie->phy); + pinctrl_pm_select_default_state(dev); + + return ret; +} + +static const struct dev_pm_ops stm32_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_pcie_suspend_noirq, + stm32_pcie_resume_noirq) +}; + +static const struct dw_pcie_host_ops stm32_pcie_host_ops = { +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = stm32_pcie_start_link, + .stop_link = stm32_pcie_stop_link +}; + +static int stm32_add_pcie_port(struct stm32_pcie *stm32_pcie) +{ + struct device *dev = stm32_pcie->pci.dev; + unsigned int wake_irq; + int ret; + + ret = phy_set_mode(stm32_pcie->phy, PHY_MODE_PCIE); + if (ret) + return ret; + + ret = phy_init(stm32_pcie->phy); + if (ret) + return ret; + + ret = regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_TYPE_MASK, + STM32MP25_PCIECR_RC); + if (ret) + goto err_phy_exit; + + stm32_pcie_deassert_perst(stm32_pcie); + + if (stm32_pcie->wake_gpio) { + wake_irq = gpiod_to_irq(stm32_pcie->wake_gpio); + ret = dev_pm_set_dedicated_wake_irq(dev, wake_irq); + if (ret) { + dev_err(dev, "Failed to enable wakeup irq %d\n", ret); + goto err_assert_perst; + } + irq_set_irq_type(wake_irq, IRQ_TYPE_EDGE_FALLING); + } + + return 0; + +err_assert_perst: + stm32_pcie_assert_perst(stm32_pcie); + +err_phy_exit: + phy_exit(stm32_pcie->phy); + + return ret; +} + +static void stm32_remove_pcie_port(struct stm32_pcie *stm32_pcie) +{ + dev_pm_clear_wake_irq(stm32_pcie->pci.dev); + + stm32_pcie_assert_perst(stm32_pcie); + + phy_exit(stm32_pcie->phy); +} + +static int stm32_pcie_parse_port(struct stm32_pcie *stm32_pcie) +{ + struct device *dev = stm32_pcie->pci.dev; + struct device_node *root_port; + + root_port = of_get_next_available_child(dev->of_node, NULL); + + stm32_pcie->phy = devm_of_phy_get(dev, root_port, NULL); + if (IS_ERR(stm32_pcie->phy)) { + of_node_put(root_port); + return dev_err_probe(dev, PTR_ERR(stm32_pcie->phy), + "Failed to get pcie-phy\n"); + } + + stm32_pcie->perst_gpio = devm_fwnode_gpiod_get(dev, of_fwnode_handle(root_port), + "reset", GPIOD_OUT_HIGH, NULL); + if (IS_ERR(stm32_pcie->perst_gpio)) { + if (PTR_ERR(stm32_pcie->perst_gpio) != -ENOENT) { + of_node_put(root_port); + return dev_err_probe(dev, PTR_ERR(stm32_pcie->perst_gpio), + "Failed to get reset GPIO\n"); + } + stm32_pcie->perst_gpio = NULL; + } + + stm32_pcie->wake_gpio = devm_fwnode_gpiod_get(dev, of_fwnode_handle(root_port), + "wake", GPIOD_IN, NULL); + + if (IS_ERR(stm32_pcie->wake_gpio)) { + if (PTR_ERR(stm32_pcie->wake_gpio) != -ENOENT) { + of_node_put(root_port); + return dev_err_probe(dev, PTR_ERR(stm32_pcie->wake_gpio), + "Failed to get wake GPIO\n"); + } + stm32_pcie->wake_gpio = NULL; + } + + of_node_put(root_port); + + return 0; +} + +static int stm32_pcie_probe(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie; + struct device *dev = &pdev->dev; + int ret; + + stm32_pcie = devm_kzalloc(dev, sizeof(*stm32_pcie), GFP_KERNEL); + if (!stm32_pcie) + return -ENOMEM; + + stm32_pcie->pci.dev = dev; + stm32_pcie->pci.ops = &dw_pcie_ops; + stm32_pcie->pci.pp.ops = &stm32_pcie_host_ops; + + stm32_pcie->regmap = syscon_regmap_lookup_by_compatible("st,stm32mp25-syscfg"); + if (IS_ERR(stm32_pcie->regmap)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->regmap), + "No syscfg specified\n"); + + stm32_pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(stm32_pcie->clk)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->clk), + "Failed to get PCIe clock source\n"); + + stm32_pcie->rst = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(stm32_pcie->rst)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->rst), + "Failed to get PCIe reset\n"); + + ret = stm32_pcie_parse_port(stm32_pcie); + if (ret) + return ret; + + platform_set_drvdata(pdev, stm32_pcie); + + ret = stm32_add_pcie_port(stm32_pcie); + if (ret) + return ret; + + reset_control_assert(stm32_pcie->rst); + reset_control_deassert(stm32_pcie->rst); + + ret = clk_prepare_enable(stm32_pcie->clk); + if (ret) { + dev_err(dev, "Core clock enable failed %d\n", ret); + goto err_remove_port; + } + + ret = pm_runtime_set_active(dev); + if (ret < 0) { + dev_err_probe(dev, ret, "Failed to activate runtime PM\n"); + goto err_disable_clk; + } + + pm_runtime_no_callbacks(dev); + + ret = devm_pm_runtime_enable(dev); + if (ret < 0) { + dev_err_probe(dev, ret, "Failed to enable runtime PM\n"); + goto err_disable_clk; + } + + ret = dw_pcie_host_init(&stm32_pcie->pci.pp); + if (ret) + goto err_disable_clk; + + if (stm32_pcie->wake_gpio) + device_init_wakeup(dev, true); + + return 0; + +err_disable_clk: + clk_disable_unprepare(stm32_pcie->clk); + +err_remove_port: + stm32_remove_pcie_port(stm32_pcie); + + return ret; +} + +static void stm32_pcie_remove(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie = platform_get_drvdata(pdev); + struct dw_pcie_rp *pp = &stm32_pcie->pci.pp; + + if (stm32_pcie->wake_gpio) + device_init_wakeup(&pdev->dev, false); + + dw_pcie_host_deinit(pp); + + clk_disable_unprepare(stm32_pcie->clk); + + stm32_remove_pcie_port(stm32_pcie); + + pm_runtime_put_noidle(&pdev->dev); +} + +static const struct of_device_id stm32_pcie_of_match[] = { + { .compatible = "st,stm32mp25-pcie-rc" }, + {}, +}; + +static struct platform_driver stm32_pcie_driver = { + .probe = stm32_pcie_probe, + .remove = stm32_pcie_remove, + .driver = { + .name = "stm32-pcie", + .of_match_table = stm32_pcie_of_match, + .pm = &stm32_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +module_platform_driver(stm32_pcie_driver); + +MODULE_AUTHOR("Christian Bruel <christian.bruel@foss.st.com>"); +MODULE_DESCRIPTION("STM32MP25 PCIe Controller driver"); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(of, stm32_pcie_of_match); diff --git a/drivers/pci/controller/dwc/pcie-stm32.h b/drivers/pci/controller/dwc/pcie-stm32.h new file mode 100644 index 000000000000..419cf1ff669d --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-stm32.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * ST PCIe driver definitions for STM32-MP25 SoC + * + * Copyright (C) 2025 STMicroelectronics - All Rights Reserved + * Author: Christian Bruel <christian.bruel@foss.st.com> + */ + +#include <linux/bits.h> +#include <linux/device.h> + +#define to_stm32_pcie(x) dev_get_drvdata((x)->dev) + +#define STM32MP25_PCIECR_TYPE_MASK GENMASK(11, 8) +#define STM32MP25_PCIECR_EP 0 +#define STM32MP25_PCIECR_LTSSM_EN BIT(2) +#define STM32MP25_PCIECR_RC BIT(10) + +#define SYSCFG_PCIECR 0x6000 diff --git a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c new file mode 100644 index 000000000000..55f61914a986 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * ACPI quirks for Tegra194 PCIe host controller + * + * Copyright (C) 2021 NVIDIA Corporation. + * + * Author: Vidya Sagar <vidyas@nvidia.com> + */ + +#include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> + +#include "pcie-designware.h" + +struct tegra194_pcie_ecam { + void __iomem *config_base; + void __iomem *iatu_base; + void __iomem *dbi_base; +}; + +static int tegra194_acpi_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct tegra194_pcie_ecam *pcie_ecam; + + pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL); + if (!pcie_ecam) + return -ENOMEM; + + pcie_ecam->config_base = cfg->win; + pcie_ecam->iatu_base = cfg->win + SZ_256K; + pcie_ecam->dbi_base = cfg->win + SZ_512K; + cfg->priv = pcie_ecam; + + return 0; +} + +static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index, + u32 val, u32 reg) +{ + u32 offset = PCIE_ATU_UNROLL_BASE(PCIE_ATU_REGION_DIR_OB, index) + + PCIE_ATU_VIEWPORT_BASE; + + writel(val, pcie_ecam->iatu_base + offset + reg); +} + +static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam, + int index, int type, u64 cpu_addr, + u64 pci_addr, u64 size) +{ + atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr), + PCIE_ATU_LOWER_BASE); + atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr), + PCIE_ATU_UPPER_BASE); + atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr), + PCIE_ATU_LOWER_TARGET); + atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1), + PCIE_ATU_LIMIT); + atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr), + PCIE_ATU_UPPER_TARGET); + atu_reg_write(pcie_ecam, index, type, PCIE_ATU_REGION_CTRL1); + atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_REGION_CTRL2); +} + +static void __iomem *tegra194_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct tegra194_pcie_ecam *pcie_ecam = cfg->priv; + u32 busdev; + int type; + + if (bus->number < cfg->busr.start || bus->number > cfg->busr.end) + return NULL; + + if (bus->number == cfg->busr.start) { + if (PCI_SLOT(devfn) == 0) + return pcie_ecam->dbi_base + where; + else + return NULL; + } + + busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) | + PCIE_ATU_FUNC(PCI_FUNC(devfn)); + + if (bus->parent->number == cfg->busr.start) { + if (PCI_SLOT(devfn) == 0) + type = PCIE_ATU_TYPE_CFG0; + else + return NULL; + } else { + type = PCIE_ATU_TYPE_CFG1; + } + + program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev, + SZ_256K); + + return pcie_ecam->config_base + where; +} + +const struct pci_ecam_ops tegra194_pcie_ops = { + .init = tegra194_acpi_init, + .pci_ops = { + .map_bus = tegra194_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c new file mode 100644 index 000000000000..0ddeef70726d --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -0,0 +1,2503 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for the following SoCs + * Tegra194 + * Tegra234 + * + * Copyright (C) 2019-2022 NVIDIA Corporation. + * + * Author: Vidya Sagar <vidyas@nvidia.com> + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/interconnect.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/random.h> +#include <linux/reset.h> +#include <linux/resource.h> +#include <linux/types.h> +#include "pcie-designware.h" +#include <soc/tegra/bpmp.h> +#include <soc/tegra/bpmp-abi.h> +#include "../../pci.h" + +#define TEGRA194_DWC_IP_VER 0x490A +#define TEGRA234_DWC_IP_VER 0x562A + +#define APPL_PINMUX 0x0 +#define APPL_PINMUX_PEX_RST BIT(0) +#define APPL_PINMUX_CLKREQ_OVERRIDE_EN BIT(2) +#define APPL_PINMUX_CLKREQ_OVERRIDE BIT(3) +#define APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN BIT(4) +#define APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE BIT(5) + +#define APPL_CTRL 0x4 +#define APPL_CTRL_SYS_PRE_DET_STATE BIT(6) +#define APPL_CTRL_LTSSM_EN BIT(7) +#define APPL_CTRL_HW_HOT_RST_EN BIT(20) +#define APPL_CTRL_HW_HOT_RST_MODE_MASK GENMASK(1, 0) +#define APPL_CTRL_HW_HOT_RST_MODE_SHIFT 22 +#define APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST 0x1 +#define APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST_LTSSM_EN 0x2 + +#define APPL_INTR_EN_L0_0 0x8 +#define APPL_INTR_EN_L0_0_LINK_STATE_INT_EN BIT(0) +#define APPL_INTR_EN_L0_0_MSI_RCV_INT_EN BIT(4) +#define APPL_INTR_EN_L0_0_INT_INT_EN BIT(8) +#define APPL_INTR_EN_L0_0_PCI_CMD_EN_INT_EN BIT(15) +#define APPL_INTR_EN_L0_0_CDM_REG_CHK_INT_EN BIT(19) +#define APPL_INTR_EN_L0_0_SYS_INTR_EN BIT(30) +#define APPL_INTR_EN_L0_0_SYS_MSI_INTR_EN BIT(31) + +#define APPL_INTR_STATUS_L0 0xC +#define APPL_INTR_STATUS_L0_LINK_STATE_INT BIT(0) +#define APPL_INTR_STATUS_L0_INT_INT BIT(8) +#define APPL_INTR_STATUS_L0_PCI_CMD_EN_INT BIT(15) +#define APPL_INTR_STATUS_L0_PEX_RST_INT BIT(16) +#define APPL_INTR_STATUS_L0_CDM_REG_CHK_INT BIT(18) + +#define APPL_INTR_EN_L1_0_0 0x1C +#define APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN BIT(1) +#define APPL_INTR_EN_L1_0_0_RDLH_LINK_UP_INT_EN BIT(3) +#define APPL_INTR_EN_L1_0_0_HOT_RESET_DONE_INT_EN BIT(30) + +#define APPL_INTR_STATUS_L1_0_0 0x20 +#define APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED BIT(1) +#define APPL_INTR_STATUS_L1_0_0_RDLH_LINK_UP_CHGED BIT(3) +#define APPL_INTR_STATUS_L1_0_0_HOT_RESET_DONE BIT(30) + +#define APPL_INTR_STATUS_L1_1 0x2C +#define APPL_INTR_STATUS_L1_2 0x30 +#define APPL_INTR_STATUS_L1_3 0x34 +#define APPL_INTR_STATUS_L1_6 0x3C +#define APPL_INTR_STATUS_L1_7 0x40 +#define APPL_INTR_STATUS_L1_15_CFG_BME_CHGED BIT(1) + +#define APPL_INTR_EN_L1_8_0 0x44 +#define APPL_INTR_EN_L1_8_BW_MGT_INT_EN BIT(2) +#define APPL_INTR_EN_L1_8_AUTO_BW_INT_EN BIT(3) +#define APPL_INTR_EN_L1_8_INTX_EN BIT(11) +#define APPL_INTR_EN_L1_8_AER_INT_EN BIT(15) + +#define APPL_INTR_STATUS_L1_8_0 0x4C +#define APPL_INTR_STATUS_L1_8_0_EDMA_INT_MASK GENMASK(11, 6) +#define APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS BIT(2) +#define APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS BIT(3) + +#define APPL_INTR_STATUS_L1_9 0x54 +#define APPL_INTR_STATUS_L1_10 0x58 +#define APPL_INTR_STATUS_L1_11 0x64 +#define APPL_INTR_STATUS_L1_13 0x74 +#define APPL_INTR_STATUS_L1_14 0x78 +#define APPL_INTR_STATUS_L1_15 0x7C +#define APPL_INTR_STATUS_L1_17 0x88 + +#define APPL_INTR_EN_L1_18 0x90 +#define APPL_INTR_EN_L1_18_CDM_REG_CHK_CMPLT BIT(2) +#define APPL_INTR_EN_L1_18_CDM_REG_CHK_CMP_ERR BIT(1) +#define APPL_INTR_EN_L1_18_CDM_REG_CHK_LOGIC_ERR BIT(0) + +#define APPL_INTR_STATUS_L1_18 0x94 +#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT BIT(2) +#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR BIT(1) +#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR BIT(0) + +#define APPL_MSI_CTRL_1 0xAC + +#define APPL_MSI_CTRL_2 0xB0 + +#define APPL_LEGACY_INTX 0xB8 + +#define APPL_LTR_MSG_1 0xC4 +#define LTR_MSG_REQ BIT(15) +#define LTR_NOSNOOP_MSG_REQ BIT(31) + +#define APPL_LTR_MSG_2 0xC8 +#define APPL_LTR_MSG_2_LTR_MSG_REQ_STATE BIT(3) + +#define APPL_LINK_STATUS 0xCC +#define APPL_LINK_STATUS_RDLH_LINK_UP BIT(0) + +#define APPL_DEBUG 0xD0 +#define APPL_DEBUG_PM_LINKST_IN_L2_LAT BIT(21) +#define APPL_DEBUG_PM_LINKST_IN_L0 0x11 +#define APPL_DEBUG_LTSSM_STATE_MASK GENMASK(8, 3) +#define APPL_DEBUG_LTSSM_STATE_SHIFT 3 +#define LTSSM_STATE_PRE_DETECT 5 + +#define APPL_RADM_STATUS 0xE4 +#define APPL_PM_XMT_TURNOFF_STATE BIT(0) + +#define APPL_DM_TYPE 0x100 +#define APPL_DM_TYPE_MASK GENMASK(3, 0) +#define APPL_DM_TYPE_RP 0x4 +#define APPL_DM_TYPE_EP 0x0 + +#define APPL_CFG_BASE_ADDR 0x104 +#define APPL_CFG_BASE_ADDR_MASK GENMASK(31, 12) + +#define APPL_CFG_IATU_DMA_BASE_ADDR 0x108 +#define APPL_CFG_IATU_DMA_BASE_ADDR_MASK GENMASK(31, 18) + +#define APPL_CFG_MISC 0x110 +#define APPL_CFG_MISC_SLV_EP_MODE BIT(14) +#define APPL_CFG_MISC_ARCACHE_MASK GENMASK(13, 10) +#define APPL_CFG_MISC_ARCACHE_SHIFT 10 +#define APPL_CFG_MISC_ARCACHE_VAL 3 + +#define APPL_CFG_SLCG_OVERRIDE 0x114 +#define APPL_CFG_SLCG_OVERRIDE_SLCG_EN_MASTER BIT(0) + +#define APPL_CAR_RESET_OVRD 0x12C +#define APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N BIT(0) + +#define IO_BASE_IO_DECODE BIT(0) +#define IO_BASE_IO_DECODE_BIT8 BIT(8) + +#define CFG_PREF_MEM_LIMIT_BASE_MEM_DECODE BIT(0) +#define CFG_PREF_MEM_LIMIT_BASE_MEM_LIMIT_DECODE BIT(16) + +#define CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF 0x718 +#define CFG_TIMER_CTRL_ACK_NAK_SHIFT (19) + +#define N_FTS_VAL 52 +#define FTS_VAL 52 + +#define PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT 0x8D0 +#define AMBA_ERROR_RESPONSE_RRS_SHIFT 3 +#define AMBA_ERROR_RESPONSE_RRS_MASK GENMASK(1, 0) +#define AMBA_ERROR_RESPONSE_RRS_OKAY 0 +#define AMBA_ERROR_RESPONSE_RRS_OKAY_FFFFFFFF 1 +#define AMBA_ERROR_RESPONSE_RRS_OKAY_FFFF0001 2 + +#define MSIX_ADDR_MATCH_LOW_OFF 0x940 +#define MSIX_ADDR_MATCH_LOW_OFF_EN BIT(0) +#define MSIX_ADDR_MATCH_LOW_OFF_MASK GENMASK(31, 2) + +#define MSIX_ADDR_MATCH_HIGH_OFF 0x944 +#define MSIX_ADDR_MATCH_HIGH_OFF_MASK GENMASK(31, 0) + +#define PORT_LOGIC_MSIX_DOORBELL 0x948 + +#define CAP_SPCIE_CAP_OFF 0x154 +#define CAP_SPCIE_CAP_OFF_DSP_TX_PRESET0_MASK GENMASK(3, 0) +#define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK GENMASK(11, 8) +#define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT 8 + +#define PME_ACK_TIMEOUT 10000 + +#define LTSSM_TIMEOUT 50000 /* 50ms */ + +#define GEN3_GEN4_EQ_PRESET_INIT 5 + +#define GEN1_CORE_CLK_FREQ 62500000 +#define GEN2_CORE_CLK_FREQ 125000000 +#define GEN3_CORE_CLK_FREQ 250000000 +#define GEN4_CORE_CLK_FREQ 500000000 + +#define LTR_MSG_TIMEOUT (100 * 1000) + +#define PERST_DEBOUNCE_TIME (5 * 1000) + +#define EP_STATE_DISABLED 0 +#define EP_STATE_ENABLED 1 + +static const unsigned int pcie_gen_freq[] = { + GEN1_CORE_CLK_FREQ, /* PCI_EXP_LNKSTA_CLS == 0; undefined */ + GEN1_CORE_CLK_FREQ, + GEN2_CORE_CLK_FREQ, + GEN3_CORE_CLK_FREQ, + GEN4_CORE_CLK_FREQ +}; + +struct tegra_pcie_dw_of_data { + u32 version; + enum dw_pcie_device_mode mode; + bool has_msix_doorbell_access_fix; + bool has_sbr_reset_fix; + bool has_l1ss_exit_fix; + bool has_ltr_req_fix; + u32 cdm_chk_int_en_bit; + u32 gen4_preset_vec; + u8 n_fts[2]; +}; + +struct tegra_pcie_dw { + struct device *dev; + struct resource *appl_res; + struct resource *dbi_res; + struct resource *atu_dma_res; + void __iomem *appl_base; + struct clk *core_clk; + struct reset_control *core_apb_rst; + struct reset_control *core_rst; + struct dw_pcie pci; + struct tegra_bpmp *bpmp; + + struct tegra_pcie_dw_of_data *of_data; + + bool supports_clkreq; + bool enable_cdm_check; + bool enable_srns; + bool link_state; + bool update_fc_fixup; + bool enable_ext_refclk; + u8 init_link_width; + u32 msi_ctrl_int; + u32 num_lanes; + u32 cid; + u32 ras_des_cap; + u32 pcie_cap_base; + u32 aspm_cmrt; + u32 aspm_pwr_on_t; + u32 aspm_l0s_enter_lat; + + struct regulator *pex_ctl_supply; + struct regulator *slot_ctl_3v3; + struct regulator *slot_ctl_12v; + + unsigned int phy_count; + struct phy **phys; + + struct dentry *debugfs; + + /* Endpoint mode specific */ + struct gpio_desc *pex_rst_gpiod; + struct gpio_desc *pex_refclk_sel_gpiod; + unsigned int pex_rst_irq; + int ep_state; + long link_status; + struct icc_path *icc_path; +}; + +static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci) +{ + return container_of(pci, struct tegra_pcie_dw, pci); +} + +static inline void appl_writel(struct tegra_pcie_dw *pcie, const u32 value, + const u32 reg) +{ + writel_relaxed(value, pcie->appl_base + reg); +} + +static inline u32 appl_readl(struct tegra_pcie_dw *pcie, const u32 reg) +{ + return readl_relaxed(pcie->appl_base + reg); +} + +static void tegra_pcie_icc_set(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + u32 val, speed, width; + + val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA); + + speed = FIELD_GET(PCI_EXP_LNKSTA_CLS, val); + width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val); + + val = width * PCIE_SPEED2MBS_ENC(pcie_link_speed[speed]); + + if (icc_set_bw(pcie->icc_path, Mbps_to_icc(val), 0)) + dev_err(pcie->dev, "can't set bw[%u]\n", val); + + if (speed >= ARRAY_SIZE(pcie_gen_freq)) + speed = 0; + + clk_set_rate(pcie->core_clk, pcie_gen_freq[speed]); +} + +static void apply_bad_link_workaround(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 current_link_width; + u16 val; + + /* + * NOTE:- Since this scenario is uncommon and link as such is not + * stable anyway, not waiting to confirm if link is really + * transitioning to Gen-2 speed + */ + val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA); + if (val & PCI_EXP_LNKSTA_LBMS) { + current_link_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val); + if (pcie->init_link_width > current_link_width) { + dev_warn(pci->dev, "PCIe link is bad, width reduced\n"); + val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL2); + val &= ~PCI_EXP_LNKCTL2_TLS; + val |= PCI_EXP_LNKCTL2_TLS_2_5GT; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL2, val); + + val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL); + val |= PCI_EXP_LNKCTL_RL; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL, val); + } + } +} + +static irqreturn_t tegra_pcie_rp_irq_handler(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + u32 val, status_l0, status_l1; + u16 val_w; + + status_l0 = appl_readl(pcie, APPL_INTR_STATUS_L0); + if (status_l0 & APPL_INTR_STATUS_L0_LINK_STATE_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_0_0); + if (!pcie->of_data->has_sbr_reset_fix && + status_l1 & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) { + /* SBR & Surprise Link Down WAR */ + val = appl_readl(pcie, APPL_CAR_RESET_OVRD); + val &= ~APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N; + appl_writel(pcie, val, APPL_CAR_RESET_OVRD); + udelay(1); + val = appl_readl(pcie, APPL_CAR_RESET_OVRD); + val |= APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N; + appl_writel(pcie, val, APPL_CAR_RESET_OVRD); + + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + } + } + + if (status_l0 & APPL_INTR_STATUS_L0_INT_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0); + if (status_l1 & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) { + appl_writel(pcie, + APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS, + APPL_INTR_STATUS_L1_8_0); + apply_bad_link_workaround(pp); + } + if (status_l1 & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) { + val_w = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + val_w |= PCI_EXP_LNKSTA_LBMS; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA, val_w); + + appl_writel(pcie, + APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS, + APPL_INTR_STATUS_L1_8_0); + + val_w = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + dev_dbg(pci->dev, "Link Speed : Gen-%u\n", val_w & + PCI_EXP_LNKSTA_CLS); + } + } + + if (status_l0 & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_18); + val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS); + if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) { + dev_info(pci->dev, "CDM check complete\n"); + val |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE; + } + if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) { + dev_err(pci->dev, "CDM comparison mismatch\n"); + val |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR; + } + if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) { + dev_err(pci->dev, "CDM Logic error\n"); + val |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR; + } + dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val); + val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR); + dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", val); + } + + return IRQ_HANDLED; +} + +static void pex_ep_event_hot_rst_done(struct tegra_pcie_dw *pcie) +{ + u32 val; + + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_1); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_2); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_3); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_6); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_7); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_8_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_9); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_10); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_11); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_13); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_14); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17); + appl_writel(pcie, 0xFFFFFFFF, APPL_MSI_CTRL_2); + + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); +} + +static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + struct dw_pcie_ep *ep = &pcie->pci.ep; + struct dw_pcie *pci = &pcie->pci; + u32 val; + + if (test_and_clear_bit(0, &pcie->link_status)) + dw_pcie_ep_linkup(ep); + + tegra_pcie_icc_set(pcie); + + if (pcie->of_data->has_ltr_req_fix) + return IRQ_HANDLED; + + /* If EP doesn't advertise L1SS, just return */ + if (!pci->l1ss_support) + return IRQ_HANDLED; + + /* Check if BME is set to '1' */ + val = dw_pcie_readl_dbi(pci, PCI_COMMAND); + if (val & PCI_COMMAND_MASTER) { + ktime_t timeout; + + /* 110us for both snoop and no-snoop */ + val = FIELD_PREP(PCI_LTR_VALUE_MASK, 110) | + FIELD_PREP(PCI_LTR_SCALE_MASK, 2) | + LTR_MSG_REQ | + FIELD_PREP(PCI_LTR_NOSNOOP_VALUE, 110) | + FIELD_PREP(PCI_LTR_NOSNOOP_SCALE, 2) | + LTR_NOSNOOP_MSG_REQ; + appl_writel(pcie, val, APPL_LTR_MSG_1); + + /* Send LTR upstream */ + val = appl_readl(pcie, APPL_LTR_MSG_2); + val |= APPL_LTR_MSG_2_LTR_MSG_REQ_STATE; + appl_writel(pcie, val, APPL_LTR_MSG_2); + + timeout = ktime_add_us(ktime_get(), LTR_MSG_TIMEOUT); + for (;;) { + val = appl_readl(pcie, APPL_LTR_MSG_2); + if (!(val & APPL_LTR_MSG_2_LTR_MSG_REQ_STATE)) + break; + if (ktime_after(ktime_get(), timeout)) + break; + usleep_range(1000, 1100); + } + if (val & APPL_LTR_MSG_2_LTR_MSG_REQ_STATE) + dev_err(pcie->dev, "Failed to send LTR message\n"); + } + + return IRQ_HANDLED; +} + +static irqreturn_t tegra_pcie_ep_hard_irq(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + int spurious = 1; + u32 status_l0, status_l1, link_status; + + status_l0 = appl_readl(pcie, APPL_INTR_STATUS_L0); + if (status_l0 & APPL_INTR_STATUS_L0_LINK_STATE_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_0_0); + + if (status_l1 & APPL_INTR_STATUS_L1_0_0_HOT_RESET_DONE) + pex_ep_event_hot_rst_done(pcie); + + if (status_l1 & APPL_INTR_STATUS_L1_0_0_RDLH_LINK_UP_CHGED) { + link_status = appl_readl(pcie, APPL_LINK_STATUS); + if (link_status & APPL_LINK_STATUS_RDLH_LINK_UP) { + dev_dbg(pcie->dev, "Link is up with Host\n"); + set_bit(0, &pcie->link_status); + return IRQ_WAKE_THREAD; + } + } + + spurious = 0; + } + + if (status_l0 & APPL_INTR_STATUS_L0_PCI_CMD_EN_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_15); + + if (status_l1 & APPL_INTR_STATUS_L1_15_CFG_BME_CHGED) + return IRQ_WAKE_THREAD; + + spurious = 0; + } + + if (spurious) { + dev_warn(pcie->dev, "Random interrupt (STATUS = 0x%08X)\n", + status_l0); + appl_writel(pcie, status_l0, APPL_INTR_STATUS_L0); + } + + return IRQ_HANDLED; +} + +static int tegra_pcie_dw_rd_own_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 *val) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + /* + * This is an endpoint mode specific register happen to appear even + * when controller is operating in root port mode and system hangs + * when it is accessed with link being in ASPM-L1 state. + * So skip accessing it altogether + */ + if (!pcie->of_data->has_msix_doorbell_access_fix && + !PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL) { + *val = 0x00000000; + return PCIBIOS_SUCCESSFUL; + } + + return pci_generic_config_read(bus, devfn, where, size, val); +} + +static int tegra_pcie_dw_wr_own_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 val) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + /* + * This is an endpoint mode specific register happen to appear even + * when controller is operating in root port mode and system hangs + * when it is accessed with link being in ASPM-L1 state. + * So skip accessing it altogether + */ + if (!pcie->of_data->has_msix_doorbell_access_fix && + !PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL) + return PCIBIOS_SUCCESSFUL; + + return pci_generic_config_write(bus, devfn, where, size, val); +} + +static struct pci_ops tegra_pci_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = tegra_pcie_dw_rd_own_conf, + .write = tegra_pcie_dw_wr_own_conf, +}; + +#if defined(CONFIG_PCIEASPM) +static inline u32 event_counter_prog(struct tegra_pcie_dw *pcie, u32 event) +{ + u32 val; + + val = dw_pcie_readl_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL); + val &= ~(EVENT_COUNTER_EVENT_SEL_MASK << EVENT_COUNTER_EVENT_SEL_SHIFT); + val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT; + val |= event << EVENT_COUNTER_EVENT_SEL_SHIFT; + val |= EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT; + dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val); + val = dw_pcie_readl_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_DATA); + + return val; +} + +static int aspm_state_cnt(struct seq_file *s, void *data) +{ + struct tegra_pcie_dw *pcie = (struct tegra_pcie_dw *) + dev_get_drvdata(s->private); + u32 val; + + seq_printf(s, "Tx L0s entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_Tx_L0S)); + + seq_printf(s, "Rx L0s entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_Rx_L0S)); + + seq_printf(s, "Link L1 entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1)); + + seq_printf(s, "Link L1.1 entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1_1)); + + seq_printf(s, "Link L1.2 entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1_2)); + + /* Clear all counters */ + dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, + EVENT_COUNTER_ALL_CLEAR); + + /* Re-enable counting */ + val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT; + val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT; + dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val); + + return 0; +} + +static void init_host_aspm(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + u32 l1ss, val; + + 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); + + /* Enable ASPM counters */ + val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT; + val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT; + dw_pcie_writel_dbi(pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val); + + /* Program T_cmrt and T_pwr_on values */ + val = dw_pcie_readl_dbi(pci, 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, 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); + val &= ~PORT_AFR_L0S_ENTRANCE_LAT_MASK; + val |= (pcie->aspm_l0s_enter_lat << PORT_AFR_L0S_ENTRANCE_LAT_SHIFT); + val |= PORT_AFR_ENTER_ASPM; + dw_pcie_writel_dbi(pci, PCIE_PORT_AFR, val); +} + +static void init_debugfs(struct tegra_pcie_dw *pcie) +{ + 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 init_host_aspm(struct tegra_pcie_dw *pcie) { return; } +static inline void init_debugfs(struct tegra_pcie_dw *pcie) { return; } +#endif + +static void tegra_pcie_enable_system_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + u16 val_w; + + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_LINK_STATE_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + if (!pcie->of_data->has_sbr_reset_fix) { + val = appl_readl(pcie, APPL_INTR_EN_L1_0_0); + val |= APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L1_0_0); + } + + if (pcie->enable_cdm_check) { + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= pcie->of_data->cdm_chk_int_en_bit; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + val = appl_readl(pcie, APPL_INTR_EN_L1_18); + val |= APPL_INTR_EN_L1_18_CDM_REG_CHK_CMP_ERR; + val |= APPL_INTR_EN_L1_18_CDM_REG_CHK_LOGIC_ERR; + appl_writel(pcie, val, APPL_INTR_EN_L1_18); + } + + val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + pcie->init_link_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val_w); + + val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL); + val_w |= PCI_EXP_LNKCTL_LBMIE; + dw_pcie_writew_dbi(&pcie->pci, pcie->pcie_cap_base + PCI_EXP_LNKCTL, + val_w); +} + +static void tegra_pcie_enable_intx_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + + /* Enable INTX interrupt generation */ + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_SYS_INTR_EN; + val |= APPL_INTR_EN_L0_0_INT_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + val = appl_readl(pcie, APPL_INTR_EN_L1_8_0); + val |= APPL_INTR_EN_L1_8_INTX_EN; + val |= APPL_INTR_EN_L1_8_AUTO_BW_INT_EN; + val |= APPL_INTR_EN_L1_8_BW_MGT_INT_EN; + if (IS_ENABLED(CONFIG_PCIEAER)) + val |= APPL_INTR_EN_L1_8_AER_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L1_8_0); +} + +static void tegra_pcie_enable_msi_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + + /* Enable MSI interrupt generation */ + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_SYS_MSI_INTR_EN; + val |= APPL_INTR_EN_L0_0_MSI_RCV_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); +} + +static void tegra_pcie_enable_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + /* Clear interrupt statuses before enabling interrupts */ + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_1); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_2); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_3); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_6); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_7); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_8_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_9); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_10); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_11); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_13); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_14); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17); + + tegra_pcie_enable_system_interrupts(pp); + tegra_pcie_enable_intx_interrupts(pp); + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_pcie_enable_msi_interrupts(pp); +} + +static void config_gen3_gen4_eq_presets(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + u32 val, offset, i; + + /* Program init preset */ + for (i = 0; i < pcie->num_lanes; i++) { + val = dw_pcie_readw_dbi(pci, CAP_SPCIE_CAP_OFF + (i * 2)); + val &= ~CAP_SPCIE_CAP_OFF_DSP_TX_PRESET0_MASK; + val |= GEN3_GEN4_EQ_PRESET_INIT; + val &= ~CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK; + val |= (GEN3_GEN4_EQ_PRESET_INIT << + CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT); + dw_pcie_writew_dbi(pci, CAP_SPCIE_CAP_OFF + (i * 2), val); + + offset = dw_pcie_find_ext_capability(pci, + PCI_EXT_CAP_ID_PL_16GT) + + PCI_PL_16GT_LE_CTRL; + val = dw_pcie_readb_dbi(pci, offset + i); + val &= ~PCI_PL_16GT_LE_CTRL_DSP_TX_PRESET_MASK; + val |= GEN3_GEN4_EQ_PRESET_INIT; + val &= ~PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK; + val |= (GEN3_GEN4_EQ_PRESET_INIT << + PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT); + dw_pcie_writeb_dbi(pci, offset + i, val); + } + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF); + val &= ~GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC; + val |= FIELD_PREP(GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC, 0x3ff); + val &= ~GEN3_EQ_CONTROL_OFF_FB_MODE; + dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; + val |= (0x1 << GEN3_RELATED_OFF_RATE_SHADOW_SEL_SHIFT); + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF); + val &= ~GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC; + val |= FIELD_PREP(GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC, + pcie->of_data->gen4_preset_vec); + val &= ~GEN3_EQ_CONTROL_OFF_FB_MODE; + dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); +} + +static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + u16 val_16; + + pp->bridge->ops = &tegra_pci_ops; + + if (!pcie->pcie_cap_base) + pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci, + PCI_CAP_ID_EXP); + + val = dw_pcie_readl_dbi(pci, PCI_IO_BASE); + val &= ~(IO_BASE_IO_DECODE | IO_BASE_IO_DECODE_BIT8); + dw_pcie_writel_dbi(pci, PCI_IO_BASE, val); + + val = dw_pcie_readl_dbi(pci, PCI_PREF_MEMORY_BASE); + val |= CFG_PREF_MEM_LIMIT_BASE_MEM_DECODE; + val |= CFG_PREF_MEM_LIMIT_BASE_MEM_LIMIT_DECODE; + dw_pcie_writel_dbi(pci, PCI_PREF_MEMORY_BASE, val); + + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); + + /* Enable as 0xFFFF0001 response for RRS */ + val = dw_pcie_readl_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT); + val &= ~(AMBA_ERROR_RESPONSE_RRS_MASK << AMBA_ERROR_RESPONSE_RRS_SHIFT); + val |= (AMBA_ERROR_RESPONSE_RRS_OKAY_FFFF0001 << + AMBA_ERROR_RESPONSE_RRS_SHIFT); + dw_pcie_writel_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT, val); + + /* Clear Slot Clock Configuration bit if SRNS configuration */ + if (pcie->enable_srns) { + val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + val_16 &= ~PCI_EXP_LNKSTA_SLC; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA, + val_16); + } + + config_gen3_gen4_eq_presets(pcie); + + init_host_aspm(pcie); + + if (!pcie->of_data->has_l1ss_exit_fix) { + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + } + + if (pcie->update_fc_fixup) { + val = dw_pcie_readl_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF); + val |= 0x1 << CFG_TIMER_CTRL_ACK_NAK_SHIFT; + dw_pcie_writel_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF, val); + } + + clk_set_rate(pcie->core_clk, GEN4_CORE_CLK_FREQ); + + return 0; +} + +static int tegra_pcie_dw_start_link(struct dw_pcie *pci) +{ + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + struct dw_pcie_rp *pp = &pci->pp; + u32 val, offset, tmp; + bool retry = true; + + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { + enable_irq(pcie->pex_rst_irq); + return 0; + } + +retry_link: + /* Assert RST */ + val = appl_readl(pcie, APPL_PINMUX); + val &= ~APPL_PINMUX_PEX_RST; + appl_writel(pcie, val, APPL_PINMUX); + + usleep_range(100, 200); + + /* Enable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + /* De-assert RST */ + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_PEX_RST; + appl_writel(pcie, val, APPL_PINMUX); + + msleep(100); + + if (dw_pcie_wait_for_link(pci)) { + if (!retry) + return 0; + /* + * There are some endpoints which can't get the link up if + * root port has Data Link Feature (DLF) enabled. + * Refer Spec rev 4.0 ver 1.0 sec 3.4.2 & 7.7.4 for more info + * on Scaled Flow Control and DLF. + * So, need to confirm that is indeed the case here and attempt + * link up once again with DLF disabled. + */ + val = appl_readl(pcie, APPL_DEBUG); + val &= APPL_DEBUG_LTSSM_STATE_MASK; + val >>= APPL_DEBUG_LTSSM_STATE_SHIFT; + tmp = appl_readl(pcie, APPL_LINK_STATUS); + tmp &= APPL_LINK_STATUS_RDLH_LINK_UP; + if (!(val == 0x11 && !tmp)) { + /* Link is down for all good reasons */ + return 0; + } + + dev_info(pci->dev, "Link is down in DLL"); + dev_info(pci->dev, "Trying again with DLFE disabled\n"); + /* Disable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val &= ~APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + reset_control_assert(pcie->core_rst); + reset_control_deassert(pcie->core_rst); + + offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_DLF); + val = dw_pcie_readl_dbi(pci, offset + PCI_DLF_CAP); + val &= ~PCI_DLF_EXCHANGE_ENABLE; + dw_pcie_writel_dbi(pci, offset + PCI_DLF_CAP, val); + + tegra_pcie_dw_host_init(pp); + dw_pcie_setup_rc(pp); + + retry = false; + goto retry_link; + } + + tegra_pcie_icc_set(pcie); + + tegra_pcie_enable_interrupts(pp); + + return 0; +} + +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; +} + +static void tegra_pcie_dw_stop_link(struct dw_pcie *pci) +{ + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + disable_irq(pcie->pex_rst_irq); +} + +static const struct dw_pcie_ops tegra_dw_pcie_ops = { + .link_up = tegra_pcie_dw_link_up, + .start_link = tegra_pcie_dw_start_link, + .stop_link = tegra_pcie_dw_stop_link, +}; + +static const struct dw_pcie_host_ops tegra_pcie_dw_host_ops = { + .init = tegra_pcie_dw_host_init, +}; + +static void tegra_pcie_disable_phy(struct tegra_pcie_dw *pcie) +{ + unsigned int phy_count = pcie->phy_count; + + while (phy_count--) { + phy_power_off(pcie->phys[phy_count]); + phy_exit(pcie->phys[phy_count]); + } +} + +static int tegra_pcie_enable_phy(struct tegra_pcie_dw *pcie) +{ + unsigned int i; + int ret; + + for (i = 0; i < pcie->phy_count; i++) { + ret = phy_init(pcie->phys[i]); + if (ret < 0) + goto phy_power_off; + + ret = phy_power_on(pcie->phys[i]); + if (ret < 0) + goto phy_exit; + } + + return 0; + +phy_power_off: + while (i--) { + phy_power_off(pcie->phys[i]); +phy_exit: + phy_exit(pcie->phys[i]); + } + + return ret; +} + +static int tegra_pcie_dw_parse_dt(struct tegra_pcie_dw *pcie) +{ + struct platform_device *pdev = to_platform_device(pcie->dev); + struct device_node *np = pcie->dev->of_node; + int ret; + + pcie->dbi_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + if (!pcie->dbi_res) { + dev_err(pcie->dev, "Failed to find \"dbi\" region\n"); + return -ENODEV; + } + + ret = of_property_read_u32(np, "nvidia,aspm-cmrt-us", &pcie->aspm_cmrt); + if (ret < 0) { + dev_info(pcie->dev, "Failed to read ASPM T_cmrt: %d\n", ret); + return ret; + } + + ret = of_property_read_u32(np, "nvidia,aspm-pwr-on-t-us", + &pcie->aspm_pwr_on_t); + if (ret < 0) + dev_info(pcie->dev, "Failed to read ASPM Power On time: %d\n", + ret); + + ret = of_property_read_u32(np, "nvidia,aspm-l0s-entrance-latency-us", + &pcie->aspm_l0s_enter_lat); + if (ret < 0) + dev_info(pcie->dev, + "Failed to read ASPM L0s Entrance latency: %d\n", ret); + + ret = of_property_read_u32(np, "num-lanes", &pcie->num_lanes); + if (ret < 0) { + dev_err(pcie->dev, "Failed to read num-lanes: %d\n", ret); + return ret; + } + + ret = of_property_read_u32_index(np, "nvidia,bpmp", 1, &pcie->cid); + if (ret) { + dev_err(pcie->dev, "Failed to read Controller-ID: %d\n", ret); + return ret; + } + + ret = of_property_count_strings(np, "phy-names"); + if (ret < 0) { + dev_err(pcie->dev, "Failed to find PHY entries: %d\n", + ret); + return ret; + } + pcie->phy_count = ret; + + if (of_property_read_bool(np, "nvidia,update-fc-fixup")) + pcie->update_fc_fixup = true; + + /* RP using an external REFCLK is supported only in Tegra234 */ + if (pcie->of_data->version == TEGRA194_DWC_IP_VER) { + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) + pcie->enable_ext_refclk = true; + } else { + pcie->enable_ext_refclk = + of_property_read_bool(pcie->dev->of_node, + "nvidia,enable-ext-refclk"); + } + + pcie->supports_clkreq = + of_property_read_bool(pcie->dev->of_node, "supports-clkreq"); + + pcie->enable_cdm_check = + of_property_read_bool(np, "snps,enable-cdm-check"); + + if (pcie->of_data->version == TEGRA234_DWC_IP_VER) + pcie->enable_srns = + of_property_read_bool(np, "nvidia,enable-srns"); + + if (pcie->of_data->mode == DW_PCIE_RC_TYPE) + return 0; + + /* Endpoint mode specific DT entries */ + pcie->pex_rst_gpiod = devm_gpiod_get(pcie->dev, "reset", GPIOD_IN); + if (IS_ERR(pcie->pex_rst_gpiod)) { + int err = PTR_ERR(pcie->pex_rst_gpiod); + const char *level = KERN_ERR; + + if (err == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, pcie->dev, + dev_fmt("Failed to get PERST GPIO: %d\n"), + err); + return err; + } + + pcie->pex_refclk_sel_gpiod = devm_gpiod_get(pcie->dev, + "nvidia,refclk-select", + GPIOD_OUT_HIGH); + if (IS_ERR(pcie->pex_refclk_sel_gpiod)) { + int err = PTR_ERR(pcie->pex_refclk_sel_gpiod); + const char *level = KERN_ERR; + + if (err == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, pcie->dev, + dev_fmt("Failed to get REFCLK select GPIOs: %d\n"), + err); + pcie->pex_refclk_sel_gpiod = NULL; + } + + return 0; +} + +static int tegra_pcie_bpmp_set_ctrl_state(struct tegra_pcie_dw *pcie, + bool enable) +{ + struct mrq_uphy_response resp; + struct tegra_bpmp_message msg; + struct mrq_uphy_request req; + int err; + + /* + * Controller-5 doesn't need to have its state set by BPMP-FW in + * Tegra194 + */ + if (pcie->of_data->version == TEGRA194_DWC_IP_VER && pcie->cid == 5) + return 0; + + memset(&req, 0, sizeof(req)); + memset(&resp, 0, sizeof(resp)); + + req.cmd = CMD_UPHY_PCIE_CONTROLLER_STATE; + req.controller_state.pcie_controller = pcie->cid; + req.controller_state.enable = enable; + + memset(&msg, 0, sizeof(msg)); + msg.mrq = MRQ_UPHY; + msg.tx.data = &req; + msg.tx.size = sizeof(req); + msg.rx.data = &resp; + msg.rx.size = sizeof(resp); + + 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, + bool enable) +{ + 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)); + + if (enable) { + req.cmd = CMD_UPHY_PCIE_EP_CONTROLLER_PLL_INIT; + req.ep_ctrlr_pll_init.ep_controller = pcie->cid; + } else { + req.cmd = CMD_UPHY_PCIE_EP_CONTROLLER_PLL_OFF; + req.ep_ctrlr_pll_off.ep_controller = pcie->cid; + } + + memset(&msg, 0, sizeof(msg)); + msg.mrq = MRQ_UPHY; + msg.tx.data = &req; + msg.tx.size = sizeof(req); + msg.rx.data = &resp; + msg.rx.size = sizeof(resp); + + 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_port_bus = NULL; + struct pci_dev *pdev; + + /* + * link doesn't go into L2 state with some of the endpoints with Tegra + * if they are not in D0 state. So, need to make sure that immediate + * downstream devices are in D0 state before sending PME_TurnOff to put + * link into L2 state. + * This is as per PCI Express Base r4.0 v1.0 September 27-2017, + * 5.2 Link State Power Management (Page #428). + */ + + list_for_each_entry(child, &pp->bridge->bus->children, node) { + if (child->parent == pp->bridge->bus) { + root_port_bus = child; + break; + } + } + + if (!root_port_bus) { + dev_err(pcie->dev, "Failed to find downstream bus of Root Port\n"); + return; + } + + /* 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, + "Failed to transition %s to D0 state\n", + dev_name(&pdev->dev)); + } + } +} + +static int tegra_pcie_get_slot_regulators(struct tegra_pcie_dw *pcie) +{ + pcie->slot_ctl_3v3 = devm_regulator_get_optional(pcie->dev, "vpcie3v3"); + if (IS_ERR(pcie->slot_ctl_3v3)) { + if (PTR_ERR(pcie->slot_ctl_3v3) != -ENODEV) + return PTR_ERR(pcie->slot_ctl_3v3); + + pcie->slot_ctl_3v3 = NULL; + } + + pcie->slot_ctl_12v = devm_regulator_get_optional(pcie->dev, "vpcie12v"); + if (IS_ERR(pcie->slot_ctl_12v)) { + if (PTR_ERR(pcie->slot_ctl_12v) != -ENODEV) + return PTR_ERR(pcie->slot_ctl_12v); + + pcie->slot_ctl_12v = NULL; + } + + return 0; +} + +static int tegra_pcie_enable_slot_regulators(struct tegra_pcie_dw *pcie) +{ + int ret; + + if (pcie->slot_ctl_3v3) { + ret = regulator_enable(pcie->slot_ctl_3v3); + if (ret < 0) { + dev_err(pcie->dev, + "Failed to enable 3.3V slot supply: %d\n", ret); + return ret; + } + } + + if (pcie->slot_ctl_12v) { + ret = regulator_enable(pcie->slot_ctl_12v); + if (ret < 0) { + dev_err(pcie->dev, + "Failed to enable 12V slot supply: %d\n", ret); + goto fail_12v_enable; + } + } + + /* + * According to PCI Express Card Electromechanical Specification + * Revision 1.1, Table-2.4, T_PVPERL (Power stable to PERST# inactive) + * should be a minimum of 100ms. + */ + if (pcie->slot_ctl_3v3 || pcie->slot_ctl_12v) + msleep(100); + + return 0; + +fail_12v_enable: + if (pcie->slot_ctl_3v3) + regulator_disable(pcie->slot_ctl_3v3); + return ret; +} + +static void tegra_pcie_disable_slot_regulators(struct tegra_pcie_dw *pcie) +{ + if (pcie->slot_ctl_12v) + regulator_disable(pcie->slot_ctl_12v); + if (pcie->slot_ctl_3v3) + regulator_disable(pcie->slot_ctl_3v3); +} + +static int tegra_pcie_config_controller(struct tegra_pcie_dw *pcie, + bool en_hw_hot_rst) +{ + int ret; + u32 val; + + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, true); + if (ret) { + dev_err(pcie->dev, + "Failed to enable controller %u: %d\n", pcie->cid, ret); + return ret; + } + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, true); + if (ret) { + dev_err(pcie->dev, "Failed to init UPHY: %d\n", ret); + goto fail_pll_init; + } + } + + ret = tegra_pcie_enable_slot_regulators(pcie); + if (ret < 0) + goto fail_slot_reg_en; + + ret = regulator_enable(pcie->pex_ctl_supply); + if (ret < 0) { + dev_err(pcie->dev, "Failed to enable regulator: %d\n", ret); + goto fail_reg_en; + } + + ret = clk_prepare_enable(pcie->core_clk); + if (ret) { + dev_err(pcie->dev, "Failed to enable core clock: %d\n", ret); + goto fail_core_clk; + } + + ret = reset_control_deassert(pcie->core_apb_rst); + if (ret) { + dev_err(pcie->dev, "Failed to deassert core APB reset: %d\n", + ret); + goto fail_core_apb_rst; + } + + if (en_hw_hot_rst || pcie->of_data->has_sbr_reset_fix) { + /* Enable HW_HOT_RST mode */ + val = appl_readl(pcie, APPL_CTRL); + val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= (APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST_LTSSM_EN << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + } + + ret = tegra_pcie_enable_phy(pcie); + if (ret) { + dev_err(pcie->dev, "Failed to enable PHY: %d\n", ret); + goto fail_phy; + } + + /* Update CFG base address */ + appl_writel(pcie, pcie->dbi_res->start & APPL_CFG_BASE_ADDR_MASK, + APPL_CFG_BASE_ADDR); + + /* Configure this core for RP mode operation */ + appl_writel(pcie, APPL_DM_TYPE_RP, APPL_DM_TYPE); + + appl_writel(pcie, 0x0, APPL_CFG_SLCG_OVERRIDE); + + val = appl_readl(pcie, APPL_CTRL); + appl_writel(pcie, val | APPL_CTRL_SYS_PRE_DET_STATE, APPL_CTRL); + + val = appl_readl(pcie, APPL_CFG_MISC); + val |= (APPL_CFG_MISC_ARCACHE_VAL << APPL_CFG_MISC_ARCACHE_SHIFT); + appl_writel(pcie, val, APPL_CFG_MISC); + + if (pcie->enable_srns || pcie->enable_ext_refclk) { + /* + * When Tegra PCIe RP is using external clock, it cannot supply + * same clock to its downstream hierarchy. Hence, gate PCIe RP + * REFCLK out pads when RP & EP are using separate clocks or RP + * is using an external REFCLK. + */ + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN; + val &= ~APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE; + appl_writel(pcie, val, APPL_PINMUX); + } + + if (!pcie->supports_clkreq) { + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_CLKREQ_OVERRIDE_EN; + val &= ~APPL_PINMUX_CLKREQ_OVERRIDE; + appl_writel(pcie, val, APPL_PINMUX); + } + + /* Update iATU_DMA base address */ + appl_writel(pcie, + pcie->atu_dma_res->start & APPL_CFG_IATU_DMA_BASE_ADDR_MASK, + APPL_CFG_IATU_DMA_BASE_ADDR); + + reset_control_deassert(pcie->core_rst); + + return ret; + +fail_phy: + reset_control_assert(pcie->core_apb_rst); +fail_core_apb_rst: + clk_disable_unprepare(pcie->core_clk); +fail_core_clk: + regulator_disable(pcie->pex_ctl_supply); +fail_reg_en: + tegra_pcie_disable_slot_regulators(pcie); +fail_slot_reg_en: + if (pcie->enable_ext_refclk) + tegra_pcie_bpmp_set_pll_state(pcie, false); +fail_pll_init: + tegra_pcie_bpmp_set_ctrl_state(pcie, false); + + return ret; +} + +static void tegra_pcie_unconfig_controller(struct tegra_pcie_dw *pcie) +{ + int ret; + + ret = reset_control_assert(pcie->core_rst); + if (ret) + dev_err(pcie->dev, "Failed to assert \"core\" reset: %d\n", ret); + + tegra_pcie_disable_phy(pcie); + + ret = reset_control_assert(pcie->core_apb_rst); + if (ret) + dev_err(pcie->dev, "Failed to assert APB reset: %d\n", ret); + + clk_disable_unprepare(pcie->core_clk); + + ret = regulator_disable(pcie->pex_ctl_supply); + if (ret) + dev_err(pcie->dev, "Failed to disable regulator: %d\n", ret); + + tegra_pcie_disable_slot_regulators(pcie); + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, false); + if (ret) + dev_err(pcie->dev, "Failed to deinit UPHY: %d\n", ret); + } + + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, false); + if (ret) + dev_err(pcie->dev, "Failed to disable controller %d: %d\n", + pcie->cid, ret); +} + +static int tegra_pcie_init_controller(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + int ret; + + ret = tegra_pcie_config_controller(pcie, false); + if (ret < 0) + return ret; + + pp->ops = &tegra_pcie_dw_host_ops; + + ret = dw_pcie_host_init(pp); + if (ret < 0) { + dev_err(pcie->dev, "Failed to add PCIe port: %d\n", ret); + goto fail_host_init; + } + + return 0; + +fail_host_init: + tegra_pcie_unconfig_controller(pcie); + return ret; +} + +static int tegra_pcie_try_link_l2(struct tegra_pcie_dw *pcie) +{ + u32 val; + + if (!tegra_pcie_dw_link_up(&pcie->pci)) + return 0; + + val = appl_readl(pcie, APPL_RADM_STATUS); + val |= APPL_PM_XMT_TURNOFF_STATE; + appl_writel(pcie, val, APPL_RADM_STATUS); + + return readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG, val, + val & APPL_DEBUG_PM_LINKST_IN_L2_LAT, + 1, PME_ACK_TIMEOUT); +} + +static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie) +{ + u32 data; + int err; + + if (!tegra_pcie_dw_link_up(&pcie->pci)) { + dev_dbg(pcie->dev, "PCIe link is not up...!\n"); + return; + } + + /* + * PCIe controller exits from L2 only if reset is applied, so + * controller doesn't handle interrupts. But in cases where + * L2 entry fails, PERST# is asserted which can trigger surprise + * link down AER. However this function call happens in + * suspend_noirq(), so AER interrupt will not be processed. + * Disable all interrupts to avoid such a scenario. + */ + appl_writel(pcie, 0x0, APPL_INTR_EN_L0_0); + + if (tegra_pcie_try_link_l2(pcie)) { + dev_info(pcie->dev, "Link didn't transition to L2 state\n"); + /* + * TX lane clock freq will reset to Gen1 only if link is in L2 + * or detect state. + * So apply pex_rst to end point to force RP to go into detect + * state + */ + data = appl_readl(pcie, APPL_PINMUX); + data &= ~APPL_PINMUX_PEX_RST; + appl_writel(pcie, data, APPL_PINMUX); + + /* + * Some cards do not go to detect state even after de-asserting + * PERST#. So, de-assert LTSSM to bring link to detect state. + */ + data = readl(pcie->appl_base + APPL_CTRL); + data &= ~APPL_CTRL_LTSSM_EN; + writel(data, pcie->appl_base + APPL_CTRL); + + err = readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG, + data, + ((data & + APPL_DEBUG_LTSSM_STATE_MASK) >> + APPL_DEBUG_LTSSM_STATE_SHIFT) == + LTSSM_STATE_PRE_DETECT, + 1, LTSSM_TIMEOUT); + if (err) + dev_info(pcie->dev, "Link didn't go to detect state\n"); + } + /* + * DBI registers may not be accessible after this as PLL-E would be + * down depending on how CLKREQ is pulled by end point + */ + data = appl_readl(pcie, APPL_PINMUX); + data |= (APPL_PINMUX_CLKREQ_OVERRIDE_EN | APPL_PINMUX_CLKREQ_OVERRIDE); + /* Cut REFCLK to slot */ + data |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN; + data &= ~APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE; + appl_writel(pcie, data, APPL_PINMUX); +} + +static void tegra_pcie_deinit_controller(struct tegra_pcie_dw *pcie) +{ + tegra_pcie_downstream_dev_to_D0(pcie); + dw_pcie_host_deinit(&pcie->pci.pp); + tegra_pcie_dw_pme_turnoff(pcie); + tegra_pcie_unconfig_controller(pcie); +} + +static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie) +{ + struct device *dev = pcie->dev; + int ret; + + pm_runtime_enable(dev); + + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "Failed to get runtime sync for PCIe dev: %d\n", + ret); + goto fail_pm_get_sync; + } + + ret = pinctrl_pm_select_default_state(dev); + if (ret < 0) { + dev_err(dev, "Failed to configure sideband pins: %d\n", ret); + goto fail_pm_get_sync; + } + + ret = tegra_pcie_init_controller(pcie); + if (ret < 0) { + dev_err(dev, "Failed to initialize controller: %d\n", ret); + goto fail_pm_get_sync; + } + + pcie->link_state = tegra_pcie_dw_link_up(&pcie->pci); + if (!pcie->link_state) { + ret = -ENOMEDIUM; + goto fail_host_init; + } + + init_debugfs(pcie); + + return ret; + +fail_host_init: + tegra_pcie_deinit_controller(pcie); +fail_pm_get_sync: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + return ret; +} + +static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie) +{ + u32 val; + int ret; + + if (pcie->ep_state == EP_STATE_DISABLED) + return; + + /* Disable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val &= ~APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + ret = readl_poll_timeout(pcie->appl_base + APPL_DEBUG, val, + ((val & APPL_DEBUG_LTSSM_STATE_MASK) >> + APPL_DEBUG_LTSSM_STATE_SHIFT) == + LTSSM_STATE_PRE_DETECT, + 1, LTSSM_TIMEOUT); + if (ret) + dev_err(pcie->dev, "Failed to go Detect state: %d\n", ret); + + reset_control_assert(pcie->core_rst); + + tegra_pcie_disable_phy(pcie); + + reset_control_assert(pcie->core_apb_rst); + + clk_disable_unprepare(pcie->core_clk); + + pm_runtime_put_sync(pcie->dev); + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, false); + if (ret) + dev_err(pcie->dev, "Failed to turn off UPHY: %d\n", + ret); + } + + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, false); + if (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"); +} + +static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_ep *ep = &pci->ep; + struct device *dev = pcie->dev; + u32 val; + int ret; + u16 val_16; + + if (pcie->ep_state == EP_STATE_ENABLED) + return; + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + dev_err(dev, "Failed to get runtime sync for PCIe dev: %d\n", + ret); + return; + } + + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, true); + if (ret) { + dev_err(pcie->dev, "Failed to enable controller %u: %d\n", + pcie->cid, ret); + goto fail_set_ctrl_state; + } + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, true); + if (ret) { + dev_err(dev, "Failed to init UPHY for PCIe EP: %d\n", + ret); + goto fail_pll_init; + } + } + + ret = clk_prepare_enable(pcie->core_clk); + if (ret) { + dev_err(dev, "Failed to enable core clock: %d\n", ret); + goto fail_core_clk_enable; + } + + ret = reset_control_deassert(pcie->core_apb_rst); + if (ret) { + dev_err(dev, "Failed to deassert core APB reset: %d\n", ret); + goto fail_core_apb_rst; + } + + ret = tegra_pcie_enable_phy(pcie); + if (ret) { + dev_err(dev, "Failed to enable PHY: %d\n", ret); + goto fail_phy; + } + + /* Perform cleanup that requires refclk */ + pci_epc_deinit_notify(pcie->pci.ep.epc); + dw_pcie_ep_cleanup(&pcie->pci.ep); + + /* Clear any stale interrupt statuses */ + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_1); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_2); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_3); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_6); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_7); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_8_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_9); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_10); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_11); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_13); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_14); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17); + + /* configure this core for EP mode operation */ + val = appl_readl(pcie, APPL_DM_TYPE); + val &= ~APPL_DM_TYPE_MASK; + val |= APPL_DM_TYPE_EP; + appl_writel(pcie, val, APPL_DM_TYPE); + + appl_writel(pcie, 0x0, APPL_CFG_SLCG_OVERRIDE); + + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_SYS_PRE_DET_STATE; + val |= APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + + val = appl_readl(pcie, APPL_CFG_MISC); + val |= APPL_CFG_MISC_SLV_EP_MODE; + val |= (APPL_CFG_MISC_ARCACHE_VAL << APPL_CFG_MISC_ARCACHE_SHIFT); + appl_writel(pcie, val, APPL_CFG_MISC); + + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN; + val |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE; + appl_writel(pcie, val, APPL_PINMUX); + + appl_writel(pcie, pcie->dbi_res->start & APPL_CFG_BASE_ADDR_MASK, + APPL_CFG_BASE_ADDR); + + appl_writel(pcie, pcie->atu_dma_res->start & + APPL_CFG_IATU_DMA_BASE_ADDR_MASK, + APPL_CFG_IATU_DMA_BASE_ADDR); + + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_SYS_INTR_EN; + val |= APPL_INTR_EN_L0_0_LINK_STATE_INT_EN; + val |= APPL_INTR_EN_L0_0_PCI_CMD_EN_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + val = appl_readl(pcie, APPL_INTR_EN_L1_0_0); + val |= APPL_INTR_EN_L1_0_0_HOT_RESET_DONE_INT_EN; + val |= APPL_INTR_EN_L1_0_0_RDLH_LINK_UP_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L1_0_0); + + reset_control_deassert(pcie->core_rst); + + if (pcie->update_fc_fixup) { + val = dw_pcie_readl_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF); + val |= 0x1 << CFG_TIMER_CTRL_ACK_NAK_SHIFT; + dw_pcie_writel_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF, val); + } + + config_gen3_gen4_eq_presets(pcie); + + init_host_aspm(pcie); + + if (!pcie->of_data->has_l1ss_exit_fix) { + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + } + + pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci, + PCI_CAP_ID_EXP); + + /* Clear Slot Clock Configuration bit if SRNS configuration */ + if (pcie->enable_srns) { + val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + val_16 &= ~PCI_EXP_LNKSTA_SLC; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA, + val_16); + } + + clk_set_rate(pcie->core_clk, GEN4_CORE_CLK_FREQ); + + val = (ep->msi_mem_phys & MSIX_ADDR_MATCH_LOW_OFF_MASK); + val |= MSIX_ADDR_MATCH_LOW_OFF_EN; + dw_pcie_writel_dbi(pci, MSIX_ADDR_MATCH_LOW_OFF, val); + val = (upper_32_bits(ep->msi_mem_phys) & MSIX_ADDR_MATCH_HIGH_OFF_MASK); + dw_pcie_writel_dbi(pci, MSIX_ADDR_MATCH_HIGH_OFF, val); + + ret = dw_pcie_ep_init_registers(ep); + if (ret) { + dev_err(dev, "Failed to complete initialization: %d\n", ret); + goto fail_init_complete; + } + + pci_epc_init_notify(ep->epc); + + /* Program the private control to allow sending LTR upstream */ + if (pcie->of_data->has_ltr_req_fix) { + val = appl_readl(pcie, APPL_LTR_MSG_2); + val |= APPL_LTR_MSG_2_LTR_MSG_REQ_STATE; + appl_writel(pcie, val, APPL_LTR_MSG_2); + } + + /* Enable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + pcie->ep_state = EP_STATE_ENABLED; + dev_dbg(dev, "Initialization of endpoint is completed\n"); + + return; + +fail_init_complete: + reset_control_assert(pcie->core_rst); + tegra_pcie_disable_phy(pcie); +fail_phy: + reset_control_assert(pcie->core_apb_rst); +fail_core_apb_rst: + clk_disable_unprepare(pcie->core_clk); +fail_core_clk_enable: + tegra_pcie_bpmp_set_pll_state(pcie, false); +fail_pll_init: + tegra_pcie_bpmp_set_ctrl_state(pcie, false); +fail_set_ctrl_state: + pm_runtime_put_sync(dev); +} + +static irqreturn_t tegra_pcie_ep_pex_rst_irq(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + + if (gpiod_get_value(pcie->pex_rst_gpiod)) + pex_ep_event_pex_rst_assert(pcie); + else + pex_ep_event_pex_rst_deassert(pcie); + + return IRQ_HANDLED; +} + +static 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 */ + if (irq > 1) + return -EINVAL; + + appl_writel(pcie, 1, APPL_LEGACY_INTX); + usleep_range(1000, 2000); + appl_writel(pcie, 0, APPL_LEGACY_INTX); + return 0; +} + +static int tegra_pcie_ep_raise_msi_irq(struct tegra_pcie_dw *pcie, u16 irq) +{ + if (unlikely(irq > 32)) + return -EINVAL; + + appl_writel(pcie, BIT(irq - 1), APPL_MSI_CTRL_1); + + return 0; +} + +static int tegra_pcie_ep_raise_msix_irq(struct tegra_pcie_dw *pcie, u16 irq) +{ + struct dw_pcie_ep *ep = &pcie->pci.ep; + + writel(irq, ep->msi_mem); + + return 0; +} + +static int tegra_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + unsigned int type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + switch (type) { + case PCI_IRQ_INTX: + return tegra_pcie_ep_raise_intx_irq(pcie, interrupt_num); + + case PCI_IRQ_MSI: + return tegra_pcie_ep_raise_msi_irq(pcie, interrupt_num); + + case PCI_IRQ_MSIX: + return tegra_pcie_ep_raise_msix_irq(pcie, interrupt_num); + + default: + dev_err(pci->dev, "Unknown IRQ type\n"); + return -EPERM; + } + + return 0; +} + +static const struct pci_epc_features tegra_pcie_epc_features = { + .linkup_notifier = true, + .msi_capable = true, + .bar[BAR_0] = { .type = BAR_FIXED, .fixed_size = SZ_1M, + .only_64bit = true, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .type = BAR_RESERVED, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .type = BAR_RESERVED, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + .align = SZ_64K, +}; + +static const struct pci_epc_features* +tegra_pcie_ep_get_features(struct dw_pcie_ep *ep) +{ + return &tegra_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .init = tegra_pcie_ep_init, + .raise_irq = tegra_pcie_ep_raise_irq, + .get_features = tegra_pcie_ep_get_features, +}; + +static int tegra_pcie_config_ep(struct tegra_pcie_dw *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pcie->dev; + struct dw_pcie_ep *ep; + char *name; + int ret; + + ep = &pci->ep; + ep->ops = &pcie_ep_ops; + + ep->page_size = SZ_64K; + + ret = gpiod_set_debounce(pcie->pex_rst_gpiod, PERST_DEBOUNCE_TIME); + if (ret < 0) { + dev_err(dev, "Failed to set PERST GPIO debounce time: %d\n", + ret); + return ret; + } + + ret = gpiod_to_irq(pcie->pex_rst_gpiod); + if (ret < 0) { + dev_err(dev, "Failed to get IRQ for PERST GPIO: %d\n", ret); + return ret; + } + pcie->pex_rst_irq = (unsigned int)ret; + + name = devm_kasprintf(dev, GFP_KERNEL, "tegra_pcie_%u_pex_rst_irq", + pcie->cid); + if (!name) { + dev_err(dev, "Failed to create PERST IRQ string\n"); + return -ENOMEM; + } + + irq_set_status_flags(pcie->pex_rst_irq, IRQ_NOAUTOEN); + + pcie->ep_state = EP_STATE_DISABLED; + + ret = devm_request_threaded_irq(dev, pcie->pex_rst_irq, NULL, + tegra_pcie_ep_pex_rst_irq, + IRQF_TRIGGER_RISING | + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + name, (void *)pcie); + if (ret < 0) { + dev_err(dev, "Failed to request IRQ for PERST: %d\n", ret); + return ret; + } + + pm_runtime_enable(dev); + + ret = dw_pcie_ep_init(ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC Endpoint subsystem: %d\n", + ret); + pm_runtime_disable(dev); + return ret; + } + + return 0; +} + +static int tegra_pcie_dw_probe(struct platform_device *pdev) +{ + const struct tegra_pcie_dw_of_data *data; + struct device *dev = &pdev->dev; + struct resource *atu_dma_res; + struct tegra_pcie_dw *pcie; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + struct phy **phys; + char *name; + int ret; + u32 i; + + data = of_device_get_match_data(dev); + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = &pcie->pci; + pci->dev = &pdev->dev; + pci->ops = &tegra_dw_pcie_ops; + pcie->dev = &pdev->dev; + pcie->of_data = (struct tegra_pcie_dw_of_data *)data; + pci->n_fts[0] = pcie->of_data->n_fts[0]; + pci->n_fts[1] = pcie->of_data->n_fts[1]; + pp = &pci->pp; + pp->num_vectors = MAX_MSI_IRQS; + + ret = tegra_pcie_dw_parse_dt(pcie); + if (ret < 0) { + const char *level = KERN_ERR; + + if (ret == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, dev, + dev_fmt("Failed to parse device tree: %d\n"), + ret); + return ret; + } + + ret = tegra_pcie_get_slot_regulators(pcie); + if (ret < 0) { + const char *level = KERN_ERR; + + if (ret == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, dev, + dev_fmt("Failed to get slot regulators: %d\n"), + ret); + return ret; + } + + if (pcie->pex_refclk_sel_gpiod) + gpiod_set_value(pcie->pex_refclk_sel_gpiod, 1); + + pcie->pex_ctl_supply = devm_regulator_get(dev, "vddio-pex-ctl"); + if (IS_ERR(pcie->pex_ctl_supply)) { + ret = PTR_ERR(pcie->pex_ctl_supply); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get regulator: %ld\n", + PTR_ERR(pcie->pex_ctl_supply)); + return ret; + } + + pcie->core_clk = devm_clk_get(dev, "core"); + if (IS_ERR(pcie->core_clk)) { + dev_err(dev, "Failed to get core clock: %ld\n", + PTR_ERR(pcie->core_clk)); + return PTR_ERR(pcie->core_clk); + } + + pcie->appl_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "appl"); + if (!pcie->appl_res) { + dev_err(dev, "Failed to find \"appl\" region\n"); + return -ENODEV; + } + + pcie->appl_base = devm_ioremap_resource(dev, pcie->appl_res); + if (IS_ERR(pcie->appl_base)) + return PTR_ERR(pcie->appl_base); + + pcie->core_apb_rst = devm_reset_control_get(dev, "apb"); + if (IS_ERR(pcie->core_apb_rst)) { + dev_err(dev, "Failed to get APB reset: %ld\n", + PTR_ERR(pcie->core_apb_rst)); + return PTR_ERR(pcie->core_apb_rst); + } + + phys = devm_kcalloc(dev, pcie->phy_count, sizeof(*phys), GFP_KERNEL); + if (!phys) + return -ENOMEM; + + for (i = 0; i < pcie->phy_count; i++) { + name = kasprintf(GFP_KERNEL, "p2u-%u", i); + if (!name) { + dev_err(dev, "Failed to create P2U string\n"); + return -ENOMEM; + } + phys[i] = devm_phy_get(dev, name); + kfree(name); + if (IS_ERR(phys[i])) { + ret = PTR_ERR(phys[i]); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get PHY: %d\n", ret); + return ret; + } + } + + pcie->phys = phys; + + atu_dma_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "atu_dma"); + if (!atu_dma_res) { + dev_err(dev, "Failed to find \"atu_dma\" region\n"); + return -ENODEV; + } + pcie->atu_dma_res = atu_dma_res; + + pci->atu_size = resource_size(atu_dma_res); + pci->atu_base = devm_ioremap_resource(dev, atu_dma_res); + if (IS_ERR(pci->atu_base)) + return PTR_ERR(pci->atu_base); + + pcie->core_rst = devm_reset_control_get(dev, "core"); + if (IS_ERR(pcie->core_rst)) { + dev_err(dev, "Failed to get core reset: %ld\n", + PTR_ERR(pcie->core_rst)); + return PTR_ERR(pcie->core_rst); + } + + pp->irq = platform_get_irq_byname(pdev, "intr"); + if (pp->irq < 0) + return pp->irq; + + pcie->bpmp = tegra_bpmp_get(dev); + if (IS_ERR(pcie->bpmp)) + return PTR_ERR(pcie->bpmp); + + platform_set_drvdata(pdev, pcie); + + pcie->icc_path = devm_of_icc_get(&pdev->dev, "write"); + ret = PTR_ERR_OR_ZERO(pcie->icc_path); + if (ret) { + tegra_bpmp_put(pcie->bpmp); + dev_err_probe(&pdev->dev, ret, "failed to get write interconnect\n"); + return ret; + } + + switch (pcie->of_data->mode) { + case DW_PCIE_RC_TYPE: + ret = devm_request_irq(dev, pp->irq, tegra_pcie_rp_irq_handler, + IRQF_SHARED, "tegra-pcie-intr", pcie); + if (ret) { + dev_err(dev, "Failed to request IRQ %d: %d\n", pp->irq, + ret); + goto fail; + } + + ret = tegra_pcie_config_rp(pcie); + if (ret && ret != -ENOMEDIUM) + goto fail; + else + return 0; + break; + + case DW_PCIE_EP_TYPE: + ret = devm_request_threaded_irq(dev, pp->irq, + tegra_pcie_ep_hard_irq, + tegra_pcie_ep_irq_thread, + IRQF_SHARED | IRQF_ONESHOT, + "tegra-pcie-ep-intr", pcie); + if (ret) { + dev_err(dev, "Failed to request IRQ %d: %d\n", pp->irq, + ret); + goto fail; + } + + ret = tegra_pcie_config_ep(pcie, pdev); + if (ret < 0) + goto fail; + else + return 0; + break; + + default: + dev_err(dev, "Invalid PCIe device type %d\n", + pcie->of_data->mode); + ret = -EINVAL; + } + +fail: + tegra_bpmp_put(pcie->bpmp); + return ret; +} + +static void tegra_pcie_dw_remove(struct platform_device *pdev) +{ + struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev); + + if (pcie->of_data->mode == DW_PCIE_RC_TYPE) { + if (!pcie->link_state) + return; + + debugfs_remove_recursive(pcie->debugfs); + tegra_pcie_deinit_controller(pcie); + pm_runtime_put_sync(pcie->dev); + } else { + disable_irq(pcie->pex_rst_irq); + pex_ep_event_pex_rst_assert(pcie); + } + + pm_runtime_disable(pcie->dev); + tegra_bpmp_put(pcie->bpmp); + if (pcie->pex_refclk_sel_gpiod) + gpiod_set_value(pcie->pex_refclk_sel_gpiod, 0); +} + +static int tegra_pcie_dw_suspend_late(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + u32 val; + + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { + dev_err(dev, "Failed to Suspend as Tegra PCIe is in EP mode\n"); + return -EPERM; + } + + if (!pcie->link_state) + return 0; + + /* Enable HW_HOT_RST mode */ + if (!pcie->of_data->has_sbr_reset_fix) { + val = appl_readl(pcie, APPL_CTRL); + val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + } + + return 0; +} + +static int tegra_pcie_dw_suspend_noirq(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + + if (!pcie->link_state) + return 0; + + tegra_pcie_downstream_dev_to_D0(pcie); + tegra_pcie_dw_pme_turnoff(pcie); + tegra_pcie_unconfig_controller(pcie); + + return 0; +} + +static int tegra_pcie_dw_resume_noirq(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + int ret; + + if (!pcie->link_state) + return 0; + + ret = tegra_pcie_config_controller(pcie, true); + if (ret < 0) + return ret; + + ret = tegra_pcie_dw_host_init(&pcie->pci.pp); + if (ret < 0) { + dev_err(dev, "Failed to init host: %d\n", ret); + goto fail_host_init; + } + + dw_pcie_setup_rc(&pcie->pci.pp); + + ret = tegra_pcie_dw_start_link(&pcie->pci); + if (ret < 0) + goto fail_host_init; + + return 0; + +fail_host_init: + tegra_pcie_unconfig_controller(pcie); + return ret; +} + +static int tegra_pcie_dw_resume_early(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + u32 val; + + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { + dev_err(dev, "Suspend is not supported in EP mode"); + return -ENOTSUPP; + } + + if (!pcie->link_state) + return 0; + + /* Disable HW_HOT_RST mode */ + if (!pcie->of_data->has_sbr_reset_fix) { + val = appl_readl(pcie, APPL_CTRL); + val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT; + val &= ~APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + } + + return 0; +} + +static void tegra_pcie_dw_shutdown(struct platform_device *pdev) +{ + struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev); + + if (pcie->of_data->mode == DW_PCIE_RC_TYPE) { + if (!pcie->link_state) + return; + + debugfs_remove_recursive(pcie->debugfs); + tegra_pcie_downstream_dev_to_D0(pcie); + + disable_irq(pcie->pci.pp.irq); + if (IS_ENABLED(CONFIG_PCI_MSI)) + disable_irq(pcie->pci.pp.msi_irq[0]); + + tegra_pcie_dw_pme_turnoff(pcie); + tegra_pcie_unconfig_controller(pcie); + pm_runtime_put_sync(pcie->dev); + } else { + disable_irq(pcie->pex_rst_irq); + pex_ep_event_pex_rst_assert(pcie); + } +} + +static const struct tegra_pcie_dw_of_data tegra194_pcie_dw_rc_of_data = { + .version = TEGRA194_DWC_IP_VER, + .mode = DW_PCIE_RC_TYPE, + .cdm_chk_int_en_bit = BIT(19), + /* Gen4 - 5, 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x360, + .n_fts = { 52, 52 }, +}; + +static const struct tegra_pcie_dw_of_data tegra194_pcie_dw_ep_of_data = { + .version = TEGRA194_DWC_IP_VER, + .mode = DW_PCIE_EP_TYPE, + .cdm_chk_int_en_bit = BIT(19), + /* Gen4 - 5, 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x360, + .n_fts = { 52, 52 }, +}; + +static const struct tegra_pcie_dw_of_data tegra234_pcie_dw_rc_of_data = { + .version = TEGRA234_DWC_IP_VER, + .mode = DW_PCIE_RC_TYPE, + .has_msix_doorbell_access_fix = true, + .has_sbr_reset_fix = true, + .has_l1ss_exit_fix = true, + .cdm_chk_int_en_bit = BIT(18), + /* Gen4 - 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x340, + .n_fts = { 52, 80 }, +}; + +static const struct tegra_pcie_dw_of_data tegra234_pcie_dw_ep_of_data = { + .version = TEGRA234_DWC_IP_VER, + .mode = DW_PCIE_EP_TYPE, + .has_l1ss_exit_fix = true, + .has_ltr_req_fix = true, + .cdm_chk_int_en_bit = BIT(18), + /* Gen4 - 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x340, + .n_fts = { 52, 80 }, +}; + +static const struct of_device_id tegra_pcie_dw_of_match[] = { + { + .compatible = "nvidia,tegra194-pcie", + .data = &tegra194_pcie_dw_rc_of_data, + }, + { + .compatible = "nvidia,tegra194-pcie-ep", + .data = &tegra194_pcie_dw_ep_of_data, + }, + { + .compatible = "nvidia,tegra234-pcie", + .data = &tegra234_pcie_dw_rc_of_data, + }, + { + .compatible = "nvidia,tegra234-pcie-ep", + .data = &tegra234_pcie_dw_ep_of_data, + }, + {} +}; + +static const struct dev_pm_ops tegra_pcie_dw_pm_ops = { + .suspend_late = tegra_pcie_dw_suspend_late, + .suspend_noirq = tegra_pcie_dw_suspend_noirq, + .resume_noirq = tegra_pcie_dw_resume_noirq, + .resume_early = tegra_pcie_dw_resume_early, +}; + +static struct platform_driver tegra_pcie_dw_driver = { + .probe = tegra_pcie_dw_probe, + .remove = tegra_pcie_dw_remove, + .shutdown = tegra_pcie_dw_shutdown, + .driver = { + .name = "tegra194-pcie", + .pm = &tegra_pcie_dw_pm_ops, + .of_match_table = tegra_pcie_dw_of_match, + }, +}; +module_platform_driver(tegra_pcie_dw_driver); + +MODULE_DEVICE_TABLE(of, tegra_pcie_dw_of_match); + +MODULE_AUTHOR("Vidya Sagar <vidyas@nvidia.com>"); +MODULE_DESCRIPTION("NVIDIA PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c new file mode 100644 index 000000000000..d6e73811216e --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c @@ -0,0 +1,474 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe endpoint controller driver for UniPhier SoCs + * Copyright 2018 Socionext Inc. + * Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com> + */ + +#include <linux/bitops.h> +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/iopoll.h> +#include <linux/of.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +/* Link Glue registers */ +#define PCL_RSTCTRL0 0x0010 +#define PCL_RSTCTRL_AXI_REG BIT(3) +#define PCL_RSTCTRL_AXI_SLAVE BIT(2) +#define PCL_RSTCTRL_AXI_MASTER BIT(1) +#define PCL_RSTCTRL_PIPE3 BIT(0) + +#define PCL_RSTCTRL1 0x0020 +#define PCL_RSTCTRL_PERST BIT(0) + +#define PCL_RSTCTRL2 0x0024 +#define PCL_RSTCTRL_PHY_RESET BIT(0) + +#define PCL_PINCTRL0 0x002c +#define PCL_PERST_PLDN_REGEN BIT(12) +#define PCL_PERST_NOE_REGEN BIT(11) +#define PCL_PERST_OUT_REGEN BIT(8) +#define PCL_PERST_PLDN_REGVAL BIT(4) +#define PCL_PERST_NOE_REGVAL BIT(3) +#define PCL_PERST_OUT_REGVAL BIT(0) + +#define PCL_PIPEMON 0x0044 +#define PCL_PCLK_ALIVE BIT(15) + +#define PCL_MODE 0x8000 +#define PCL_MODE_REGEN BIT(8) +#define PCL_MODE_REGVAL BIT(0) + +#define PCL_APP_CLK_CTRL 0x8004 +#define PCL_APP_CLK_REQ BIT(0) + +#define PCL_APP_READY_CTRL 0x8008 +#define PCL_APP_LTSSM_ENABLE BIT(0) + +#define PCL_APP_MSI0 0x8040 +#define PCL_APP_VEN_MSI_TC_MASK GENMASK(10, 8) +#define PCL_APP_VEN_MSI_VECTOR_MASK GENMASK(4, 0) + +#define PCL_APP_MSI1 0x8044 +#define PCL_APP_MSI_REQ BIT(0) + +#define PCL_APP_INTX 0x8074 +#define PCL_APP_INTX_SYS_INT BIT(0) + +#define PCL_APP_PM0 0x8078 +#define PCL_SYS_AUX_PWR_DET BIT(8) + +/* assertion time of INTx in usec */ +#define PCL_INTX_WIDTH_USEC 30 + +struct uniphier_pcie_ep_priv { + void __iomem *base; + struct dw_pcie pci; + struct clk *clk, *clk_gio; + struct reset_control *rst, *rst_gio; + struct phy *phy; + const struct uniphier_pcie_ep_soc_data *data; +}; + +struct uniphier_pcie_ep_soc_data { + bool has_gio; + void (*init)(struct uniphier_pcie_ep_priv *priv); + int (*wait)(struct uniphier_pcie_ep_priv *priv); + const struct pci_epc_features features; +}; + +#define to_uniphier_pcie(x) dev_get_drvdata((x)->dev) + +static void uniphier_pcie_ltssm_enable(struct uniphier_pcie_ep_priv *priv, + bool enable) +{ + u32 val; + + val = readl(priv->base + PCL_APP_READY_CTRL); + if (enable) + val |= PCL_APP_LTSSM_ENABLE; + else + val &= ~PCL_APP_LTSSM_ENABLE; + writel(val, priv->base + PCL_APP_READY_CTRL); +} + +static void uniphier_pcie_phy_reset(struct uniphier_pcie_ep_priv *priv, + bool assert) +{ + u32 val; + + val = readl(priv->base + PCL_RSTCTRL2); + if (assert) + val |= PCL_RSTCTRL_PHY_RESET; + else + val &= ~PCL_RSTCTRL_PHY_RESET; + writel(val, priv->base + PCL_RSTCTRL2); +} + +static void uniphier_pcie_pro5_init_ep(struct uniphier_pcie_ep_priv *priv) +{ + u32 val; + + /* set EP mode */ + val = readl(priv->base + PCL_MODE); + val |= PCL_MODE_REGEN | PCL_MODE_REGVAL; + writel(val, priv->base + PCL_MODE); + + /* clock request */ + val = readl(priv->base + PCL_APP_CLK_CTRL); + val &= ~PCL_APP_CLK_REQ; + writel(val, priv->base + PCL_APP_CLK_CTRL); + + /* deassert PIPE3 and AXI reset */ + val = readl(priv->base + PCL_RSTCTRL0); + val |= PCL_RSTCTRL_AXI_REG | PCL_RSTCTRL_AXI_SLAVE + | PCL_RSTCTRL_AXI_MASTER | PCL_RSTCTRL_PIPE3; + writel(val, priv->base + PCL_RSTCTRL0); + + uniphier_pcie_ltssm_enable(priv, false); + + msleep(100); +} + +static void uniphier_pcie_nx1_init_ep(struct uniphier_pcie_ep_priv *priv) +{ + u32 val; + + /* set EP mode */ + val = readl(priv->base + PCL_MODE); + val |= PCL_MODE_REGEN | PCL_MODE_REGVAL; + writel(val, priv->base + PCL_MODE); + + /* use auxiliary power detection */ + val = readl(priv->base + PCL_APP_PM0); + val |= PCL_SYS_AUX_PWR_DET; + writel(val, priv->base + PCL_APP_PM0); + + /* assert PERST# */ + val = readl(priv->base + PCL_PINCTRL0); + val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL + | PCL_PERST_PLDN_REGVAL); + val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN + | PCL_PERST_PLDN_REGEN; + writel(val, priv->base + PCL_PINCTRL0); + + uniphier_pcie_ltssm_enable(priv, false); + + usleep_range(100000, 200000); + + /* deassert PERST# */ + val = readl(priv->base + PCL_PINCTRL0); + val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN; + writel(val, priv->base + PCL_PINCTRL0); +} + +static int uniphier_pcie_nx1_wait_ep(struct uniphier_pcie_ep_priv *priv) +{ + u32 status; + int ret; + + /* wait PIPE clock */ + ret = readl_poll_timeout(priv->base + PCL_PIPEMON, status, + status & PCL_PCLK_ALIVE, 100000, 1000000); + if (ret) { + dev_err(priv->pci.dev, + "Failed to initialize controller in EP mode\n"); + return ret; + } + + return 0; +} + +static int uniphier_pcie_start_link(struct dw_pcie *pci) +{ + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + + uniphier_pcie_ltssm_enable(priv, true); + + return 0; +} + +static void uniphier_pcie_stop_link(struct dw_pcie *pci) +{ + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + + uniphier_pcie_ltssm_enable(priv, false); +} + +static void uniphier_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + for (bar = BAR_0; bar <= BAR_5; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static int uniphier_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + u32 val; + + /* + * This makes pulse signal to send INTx to the RC, so this should + * be cleared as soon as possible. This sequence is covered with + * mutex in pci_epc_raise_irq(). + */ + /* assert INTx */ + val = readl(priv->base + PCL_APP_INTX); + val |= PCL_APP_INTX_SYS_INT; + writel(val, priv->base + PCL_APP_INTX); + + udelay(PCL_INTX_WIDTH_USEC); + + /* deassert INTx */ + val &= ~PCL_APP_INTX_SYS_INT; + writel(val, priv->base + PCL_APP_INTX); + + return 0; +} + +static int uniphier_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, + u8 func_no, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + u32 val; + + val = FIELD_PREP(PCL_APP_VEN_MSI_TC_MASK, func_no) + | FIELD_PREP(PCL_APP_VEN_MSI_VECTOR_MASK, interrupt_num - 1); + writel(val, priv->base + PCL_APP_MSI0); + + val = readl(priv->base + PCL_APP_MSI1); + val |= PCL_APP_MSI_REQ; + writel(val, priv->base + PCL_APP_MSI1); + + return 0; +} + +static int uniphier_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + unsigned int type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_IRQ_INTX: + return uniphier_pcie_ep_raise_intx_irq(ep); + case PCI_IRQ_MSI: + return uniphier_pcie_ep_raise_msi_irq(ep, func_no, + interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type (%d)\n", type); + } + + return 0; +} + +static const struct pci_epc_features* +uniphier_pcie_get_features(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + + return &priv->data->features; +} + +static const struct dw_pcie_ep_ops uniphier_pcie_ep_ops = { + .init = uniphier_pcie_ep_init, + .raise_irq = uniphier_pcie_ep_raise_irq, + .get_features = uniphier_pcie_get_features, +}; + +static int uniphier_pcie_ep_enable(struct uniphier_pcie_ep_priv *priv) +{ + int ret; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + + ret = clk_prepare_enable(priv->clk_gio); + if (ret) + goto out_clk_disable; + + ret = reset_control_deassert(priv->rst); + if (ret) + goto out_clk_gio_disable; + + ret = reset_control_deassert(priv->rst_gio); + if (ret) + goto out_rst_assert; + + if (priv->data->init) + priv->data->init(priv); + + uniphier_pcie_phy_reset(priv, true); + + ret = phy_init(priv->phy); + if (ret) + goto out_rst_gio_assert; + + uniphier_pcie_phy_reset(priv, false); + + if (priv->data->wait) { + ret = priv->data->wait(priv); + if (ret) + goto out_phy_exit; + } + + return 0; + +out_phy_exit: + phy_exit(priv->phy); +out_rst_gio_assert: + reset_control_assert(priv->rst_gio); +out_rst_assert: + reset_control_assert(priv->rst); +out_clk_gio_disable: + clk_disable_unprepare(priv->clk_gio); +out_clk_disable: + clk_disable_unprepare(priv->clk); + + return ret; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = uniphier_pcie_start_link, + .stop_link = uniphier_pcie_stop_link, +}; + +static int uniphier_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct uniphier_pcie_ep_priv *priv; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->data = of_device_get_match_data(dev); + if (WARN_ON(!priv->data)) + return -EINVAL; + + priv->pci.dev = dev; + priv->pci.ops = &dw_pcie_ops; + + priv->base = devm_platform_ioremap_resource_byname(pdev, "link"); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + if (priv->data->has_gio) { + priv->clk_gio = devm_clk_get(dev, "gio"); + if (IS_ERR(priv->clk_gio)) + return PTR_ERR(priv->clk_gio); + + priv->rst_gio = devm_reset_control_get_shared(dev, "gio"); + if (IS_ERR(priv->rst_gio)) + return PTR_ERR(priv->rst_gio); + } + + priv->clk = devm_clk_get(dev, "link"); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + + priv->rst = devm_reset_control_get_shared(dev, "link"); + if (IS_ERR(priv->rst)) + return PTR_ERR(priv->rst); + + priv->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(priv->phy)) { + ret = PTR_ERR(priv->phy); + dev_err(dev, "Failed to get phy (%d)\n", ret); + return ret; + } + + platform_set_drvdata(pdev, priv); + + ret = uniphier_pcie_ep_enable(priv); + if (ret) + return ret; + + priv->pci.ep.ops = &uniphier_pcie_ep_ops; + ret = dw_pcie_ep_init(&priv->pci.ep); + if (ret) + return ret; + + ret = dw_pcie_ep_init_registers(&priv->pci.ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC endpoint registers\n"); + dw_pcie_ep_deinit(&priv->pci.ep); + return ret; + } + + pci_epc_init_notify(priv->pci.ep.epc); + + return 0; +} + +static const struct uniphier_pcie_ep_soc_data uniphier_pro5_data = { + .has_gio = true, + .init = uniphier_pcie_pro5_init_ep, + .wait = NULL, + .features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, + .align = 1 << 16, + .bar[BAR_0] = { .only_64bit = true, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .only_64bit = true, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .type = BAR_RESERVED, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + }, +}; + +static const struct uniphier_pcie_ep_soc_data uniphier_nx1_data = { + .has_gio = false, + .init = uniphier_pcie_nx1_init_ep, + .wait = uniphier_pcie_nx1_wait_ep, + .features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, + .align = 1 << 12, + .bar[BAR_0] = { .only_64bit = true, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .only_64bit = true, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .only_64bit = true, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + }, +}; + +static const struct of_device_id uniphier_pcie_ep_match[] = { + { + .compatible = "socionext,uniphier-pro5-pcie-ep", + .data = &uniphier_pro5_data, + }, + { + .compatible = "socionext,uniphier-nx1-pcie-ep", + .data = &uniphier_nx1_data, + }, + { /* sentinel */ }, +}; + +static struct platform_driver uniphier_pcie_ep_driver = { + .probe = uniphier_pcie_ep_probe, + .driver = { + .name = "uniphier-pcie-ep", + .of_match_table = uniphier_pcie_ep_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(uniphier_pcie_ep_driver); diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c index d5dc40289cce..297e7a3d9b36 100644 --- a/drivers/pci/controller/dwc/pcie-uniphier.c +++ b/drivers/pci/controller/dwc/pcie-uniphier.c @@ -9,11 +9,11 @@ #include <linux/bitfield.h> #include <linux/clk.h> #include <linux/delay.h> +#include <linux/init.h> #include <linux/interrupt.h> #include <linux/iopoll.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> -#include <linux/module.h> #include <linux/of_irq.h> #include <linux/pci.h> #include <linux/phy/phy.h> @@ -33,6 +33,10 @@ #define PCL_PIPEMON 0x0044 #define PCL_PCLK_ALIVE BIT(15) +#define PCL_MODE 0x8000 +#define PCL_MODE_REGEN BIT(8) +#define PCL_MODE_REGVAL BIT(0) + #define PCL_APP_READY_CTRL 0x8008 #define PCL_APP_LTSSM_ENABLE BIT(0) @@ -57,67 +61,73 @@ #define PCL_RDLH_LINK_UP BIT(1) #define PCL_XMLH_LINK_UP BIT(0) -struct uniphier_pcie_priv { - void __iomem *base; +struct uniphier_pcie { struct dw_pcie pci; + void __iomem *base; struct clk *clk; struct reset_control *rst; struct phy *phy; - struct irq_domain *legacy_irq_domain; + struct irq_domain *intx_irq_domain; }; #define to_uniphier_pcie(x) dev_get_drvdata((x)->dev) -static void uniphier_pcie_ltssm_enable(struct uniphier_pcie_priv *priv, +static void uniphier_pcie_ltssm_enable(struct uniphier_pcie *pcie, bool enable) { u32 val; - val = readl(priv->base + PCL_APP_READY_CTRL); + val = readl(pcie->base + PCL_APP_READY_CTRL); if (enable) val |= PCL_APP_LTSSM_ENABLE; else val &= ~PCL_APP_LTSSM_ENABLE; - writel(val, priv->base + PCL_APP_READY_CTRL); + writel(val, pcie->base + PCL_APP_READY_CTRL); } -static void uniphier_pcie_init_rc(struct uniphier_pcie_priv *priv) +static void uniphier_pcie_init_rc(struct uniphier_pcie *pcie) { u32 val; + /* set RC MODE */ + val = readl(pcie->base + PCL_MODE); + val |= PCL_MODE_REGEN; + val &= ~PCL_MODE_REGVAL; + writel(val, pcie->base + PCL_MODE); + /* use auxiliary power detection */ - val = readl(priv->base + PCL_APP_PM0); + val = readl(pcie->base + PCL_APP_PM0); val |= PCL_SYS_AUX_PWR_DET; - writel(val, priv->base + PCL_APP_PM0); + writel(val, pcie->base + PCL_APP_PM0); /* assert PERST# */ - val = readl(priv->base + PCL_PINCTRL0); + val = readl(pcie->base + PCL_PINCTRL0); val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL | PCL_PERST_PLDN_REGVAL); val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN | PCL_PERST_PLDN_REGEN; - writel(val, priv->base + PCL_PINCTRL0); + writel(val, pcie->base + PCL_PINCTRL0); - uniphier_pcie_ltssm_enable(priv, false); + uniphier_pcie_ltssm_enable(pcie, false); usleep_range(100000, 200000); /* deassert PERST# */ - val = readl(priv->base + PCL_PINCTRL0); + val = readl(pcie->base + PCL_PINCTRL0); val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN; - writel(val, priv->base + PCL_PINCTRL0); + writel(val, pcie->base + PCL_PINCTRL0); } -static int uniphier_pcie_wait_rc(struct uniphier_pcie_priv *priv) +static int uniphier_pcie_wait_rc(struct uniphier_pcie *pcie) { u32 status; int ret; /* wait PIPE clock */ - ret = readl_poll_timeout(priv->base + PCL_PIPEMON, status, + ret = readl_poll_timeout(pcie->base + PCL_PIPEMON, status, status & PCL_PCLK_ALIVE, 100000, 1000000); if (ret) { - dev_err(priv->pci.dev, + dev_err(pcie->pci.dev, "Failed to initialize controller in RC mode\n"); return ret; } @@ -125,90 +135,76 @@ static int uniphier_pcie_wait_rc(struct uniphier_pcie_priv *priv) 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_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); u32 val, mask; - val = readl(priv->base + PCL_STATUS_LINK); + val = readl(pcie->base + PCL_STATUS_LINK); mask = PCL_RDLH_LINK_UP | PCL_XMLH_LINK_UP; return (val & mask) == mask; } -static int uniphier_pcie_establish_link(struct dw_pcie *pci) +static int uniphier_pcie_start_link(struct dw_pcie *pci) { - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); - if (dw_pcie_link_up(pci)) - return 0; + uniphier_pcie_ltssm_enable(pcie, true); - uniphier_pcie_ltssm_enable(priv, true); - - return dw_pcie_wait_for_link(pci); + return 0; } static void uniphier_pcie_stop_link(struct dw_pcie *pci) { - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); - uniphier_pcie_ltssm_enable(priv, false); + uniphier_pcie_ltssm_enable(pcie, false); } -static void uniphier_pcie_irq_enable(struct uniphier_pcie_priv *priv) +static void uniphier_pcie_irq_enable(struct uniphier_pcie *pcie) { - writel(PCL_RCV_INT_ALL_ENABLE, priv->base + PCL_RCV_INT); - writel(PCL_RCV_INTX_ALL_ENABLE, priv->base + PCL_RCV_INTX); + writel(PCL_RCV_INT_ALL_ENABLE, pcie->base + PCL_RCV_INT); + writel(PCL_RCV_INTX_ALL_ENABLE, pcie->base + PCL_RCV_INTX); } -static void uniphier_pcie_irq_disable(struct uniphier_pcie_priv *priv) -{ - writel(0, priv->base + PCL_RCV_INT); - writel(0, priv->base + PCL_RCV_INTX); -} - -static void uniphier_pcie_irq_ack(struct irq_data *d) -{ - struct pcie_port *pp = irq_data_get_irq_chip_data(d); - struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); - u32 val; - - val = readl(priv->base + PCL_RCV_INTX); - val &= ~PCL_RCV_INTX_ALL_STATUS; - val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_STATUS_SHIFT); - writel(val, priv->base + PCL_RCV_INTX); -} static void uniphier_pcie_irq_mask(struct irq_data *d) { - struct pcie_port *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + unsigned long flags; u32 val; - val = readl(priv->base + PCL_RCV_INTX); - val &= ~PCL_RCV_INTX_ALL_MASK; + raw_spin_lock_irqsave(&pp->lock, flags); + + val = readl(pcie->base + PCL_RCV_INTX); val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); - writel(val, priv->base + PCL_RCV_INTX); + writel(val, pcie->base + PCL_RCV_INTX); + + raw_spin_unlock_irqrestore(&pp->lock, flags); } static void uniphier_pcie_irq_unmask(struct irq_data *d) { - struct pcie_port *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + unsigned long flags; u32 val; - val = readl(priv->base + PCL_RCV_INTX); - val &= ~PCL_RCV_INTX_ALL_MASK; + raw_spin_lock_irqsave(&pp->lock, flags); + + val = readl(pcie->base + PCL_RCV_INTX); val &= ~BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); - writel(val, priv->base + PCL_RCV_INTX); + writel(val, pcie->base + PCL_RCV_INTX); + + raw_spin_unlock_irqrestore(&pp->lock, flags); } static struct irq_chip uniphier_pcie_irq_chip = { .name = "PCI", - .irq_ack = uniphier_pcie_irq_ack, .irq_mask = uniphier_pcie_irq_mask, .irq_unmask = uniphier_pcie_irq_unmask, }; @@ -229,15 +225,15 @@ static const struct irq_domain_ops uniphier_intx_domain_ops = { static void uniphier_pcie_irq_handler(struct irq_desc *desc) { - struct pcie_port *pp = irq_desc_get_handler_data(desc); + struct dw_pcie_rp *pp = irq_desc_get_handler_data(desc); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long reg; - u32 val, bit, virq; + u32 val, bit; /* INT for debug */ - val = readl(priv->base + PCL_RCV_INT); + val = readl(pcie->base + PCL_RCV_INT); if (val & PCL_CFG_BW_MGT_STATUS) dev_dbg(pci->dev, "Link Bandwidth Management Event\n"); @@ -248,28 +244,27 @@ static void uniphier_pcie_irq_handler(struct irq_desc *desc) if (val & PCL_CFG_PME_MSI_STATUS) dev_dbg(pci->dev, "PME Interrupt\n"); - writel(val, priv->base + PCL_RCV_INT); + writel(val, pcie->base + PCL_RCV_INT); /* INTx */ chained_irq_enter(chip, desc); - val = readl(priv->base + PCL_RCV_INTX); + val = readl(pcie->base + PCL_RCV_INTX); reg = FIELD_GET(PCL_RCV_INTX_ALL_STATUS, val); - for_each_set_bit(bit, ®, PCI_NUM_INTX) { - virq = irq_linear_revmap(priv->legacy_irq_domain, bit); - generic_handle_irq(virq); - } + for_each_set_bit(bit, ®, PCI_NUM_INTX) + generic_handle_domain_irq(pcie->intx_irq_domain, bit); chained_irq_exit(chip, desc); } -static int uniphier_pcie_config_legacy_irq(struct pcie_port *pp) +static int uniphier_pcie_config_intx_irq(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); struct device_node *np = pci->dev->of_node; struct device_node *np_intc; + int ret = 0; np_intc = of_get_child_by_name(np, "legacy-interrupt-controller"); if (!np_intc) { @@ -280,118 +275,81 @@ static int uniphier_pcie_config_legacy_irq(struct pcie_port *pp) pp->irq = irq_of_parse_and_map(np_intc, 0); if (!pp->irq) { dev_err(pci->dev, "Failed to get an IRQ entry in legacy-interrupt-controller\n"); - return -EINVAL; + ret = -EINVAL; + goto out_put_node; } - priv->legacy_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 (!priv->legacy_irq_domain) { + if (!pcie->intx_irq_domain) { dev_err(pci->dev, "Failed to get INTx domain\n"); - return -ENODEV; + ret = -ENODEV; + goto out_put_node; } irq_set_chained_handler_and_data(pp->irq, uniphier_pcie_irq_handler, pp); - return 0; +out_put_node: + of_node_put(np_intc); + return ret; } -static int uniphier_pcie_host_init(struct pcie_port *pp) +static int uniphier_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); int ret; - ret = uniphier_pcie_config_legacy_irq(pp); - if (ret) - return ret; - - uniphier_pcie_irq_enable(priv); - - dw_pcie_setup_rc(pp); - ret = uniphier_pcie_establish_link(pci); + ret = uniphier_pcie_config_intx_irq(pp); if (ret) return ret; - if (IS_ENABLED(CONFIG_PCI_MSI)) - dw_pcie_msi_init(pp); + uniphier_pcie_irq_enable(pcie); return 0; } static const struct dw_pcie_host_ops uniphier_pcie_host_ops = { - .host_init = uniphier_pcie_host_init, + .init = uniphier_pcie_host_init, }; -static int uniphier_add_pcie_port(struct uniphier_pcie_priv *priv, - struct platform_device *pdev) +static int uniphier_pcie_host_enable(struct uniphier_pcie *pcie) { - struct dw_pcie *pci = &priv->pci; - struct pcie_port *pp = &pci->pp; - struct device *dev = &pdev->dev; int ret; - pp->ops = &uniphier_pcie_host_ops; - - if (IS_ENABLED(CONFIG_PCI_MSI)) { - pp->msi_irq = platform_get_irq_byname(pdev, "msi"); - if (pp->msi_irq < 0) - return pp->msi_irq; - } - - ret = dw_pcie_host_init(pp); - if (ret) { - dev_err(dev, "Failed to initialize host (%d)\n", ret); - return ret; - } - - return 0; -} - -static int uniphier_pcie_host_enable(struct uniphier_pcie_priv *priv) -{ - int ret; - - ret = clk_prepare_enable(priv->clk); + ret = clk_prepare_enable(pcie->clk); if (ret) return ret; - ret = reset_control_deassert(priv->rst); + ret = reset_control_deassert(pcie->rst); if (ret) goto out_clk_disable; - uniphier_pcie_init_rc(priv); + uniphier_pcie_init_rc(pcie); - ret = phy_init(priv->phy); + ret = phy_init(pcie->phy); if (ret) goto out_rst_assert; - ret = uniphier_pcie_wait_rc(priv); + ret = uniphier_pcie_wait_rc(pcie); if (ret) goto out_phy_exit; return 0; out_phy_exit: - phy_exit(priv->phy); + phy_exit(pcie->phy); out_rst_assert: - reset_control_assert(priv->rst); + reset_control_assert(pcie->rst); out_clk_disable: - clk_disable_unprepare(priv->clk); + clk_disable_unprepare(pcie->clk); return ret; } -static void uniphier_pcie_host_disable(struct uniphier_pcie_priv *priv) -{ - uniphier_pcie_irq_disable(priv); - phy_exit(priv->phy); - reset_control_assert(priv->rst); - clk_disable_unprepare(priv->clk); -} - static const struct dw_pcie_ops dw_pcie_ops = { - .start_link = uniphier_pcie_establish_link, + .start_link = uniphier_pcie_start_link, .stop_link = uniphier_pcie_stop_link, .link_up = uniphier_pcie_link_up, }; @@ -399,73 +357,53 @@ static const struct dw_pcie_ops dw_pcie_ops = { static int uniphier_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct uniphier_pcie_priv *priv; - struct resource *res; + struct uniphier_pcie *pcie; int ret; - priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); - if (!priv) + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) return -ENOMEM; - priv->pci.dev = dev; - priv->pci.ops = &dw_pcie_ops; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); - priv->pci.dbi_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(priv->pci.dbi_base)) - return PTR_ERR(priv->pci.dbi_base); + pcie->pci.dev = dev; + pcie->pci.ops = &dw_pcie_ops; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "link"); - priv->base = devm_ioremap_resource(dev, res); - if (IS_ERR(priv->base)) - return PTR_ERR(priv->base); + pcie->base = devm_platform_ioremap_resource_byname(pdev, "link"); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); - priv->clk = devm_clk_get(dev, NULL); - if (IS_ERR(priv->clk)) - return PTR_ERR(priv->clk); + pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(pcie->clk)) + return PTR_ERR(pcie->clk); - priv->rst = devm_reset_control_get_shared(dev, NULL); - if (IS_ERR(priv->rst)) - return PTR_ERR(priv->rst); + pcie->rst = devm_reset_control_get_shared(dev, NULL); + if (IS_ERR(pcie->rst)) + return PTR_ERR(pcie->rst); - priv->phy = devm_phy_optional_get(dev, "pcie-phy"); - if (IS_ERR(priv->phy)) - return PTR_ERR(priv->phy); + pcie->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(pcie->phy)) + return PTR_ERR(pcie->phy); - platform_set_drvdata(pdev, priv); + platform_set_drvdata(pdev, pcie); - ret = uniphier_pcie_host_enable(priv); + ret = uniphier_pcie_host_enable(pcie); if (ret) return ret; - return uniphier_add_pcie_port(priv, pdev); -} - -static int uniphier_pcie_remove(struct platform_device *pdev) -{ - struct uniphier_pcie_priv *priv = platform_get_drvdata(pdev); + pcie->pci.pp.ops = &uniphier_pcie_host_ops; - uniphier_pcie_host_disable(priv); - - return 0; + return dw_pcie_host_init(&pcie->pci.pp); } static const struct of_device_id uniphier_pcie_match[] = { { .compatible = "socionext,uniphier-pcie", }, { /* sentinel */ }, }; -MODULE_DEVICE_TABLE(of, uniphier_pcie_match); static struct platform_driver uniphier_pcie_driver = { .probe = uniphier_pcie_probe, - .remove = uniphier_pcie_remove, .driver = { .name = "uniphier-pcie", .of_match_table = uniphier_pcie_match, }, }; builtin_platform_driver(uniphier_pcie_driver); - -MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>"); -MODULE_DESCRIPTION("UniPhier PCIe host controller driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c new file mode 100644 index 000000000000..cdeac6177143 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-visconti.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DWC PCIe RC driver for Toshiba Visconti ARM SoC + * + * Copyright (C) 2021 Toshiba Electronic Device & Storage Corporation + * Copyright (C) 2021 TOSHIBA CORPORATION + * + * Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/types.h> + +#include "pcie-designware.h" +#include "../../pci.h" + +struct visconti_pcie { + struct dw_pcie pci; + void __iomem *ulreg_base; + void __iomem *smu_base; + void __iomem *mpu_base; + struct clk *refclk; + struct clk *coreclk; + struct clk *auxclk; +}; + +#define PCIE_UL_REG_S_PCIE_MODE 0x00F4 +#define PCIE_UL_REG_S_PCIE_MODE_EP 0x00 +#define PCIE_UL_REG_S_PCIE_MODE_RC 0x04 + +#define PCIE_UL_REG_S_PERSTN_CTRL 0x00F8 +#define PCIE_UL_IOM_PCIE_PERSTN_I_EN BIT(3) +#define PCIE_UL_DIRECT_PERSTN_EN BIT(2) +#define PCIE_UL_PERSTN_OUT BIT(1) +#define PCIE_UL_DIRECT_PERSTN BIT(0) +#define PCIE_UL_REG_S_PERSTN_CTRL_INIT (PCIE_UL_IOM_PCIE_PERSTN_I_EN | \ + PCIE_UL_DIRECT_PERSTN_EN | \ + PCIE_UL_DIRECT_PERSTN) + +#define PCIE_UL_REG_S_PHY_INIT_02 0x0104 +#define PCIE_UL_PHY0_SRAM_EXT_LD_DONE BIT(0) + +#define PCIE_UL_REG_S_PHY_INIT_03 0x0108 +#define PCIE_UL_PHY0_SRAM_INIT_DONE BIT(0) + +#define PCIE_UL_REG_S_INT_EVENT_MASK1 0x0138 +#define PCIE_UL_CFG_PME_INT BIT(0) +#define PCIE_UL_CFG_LINK_EQ_REQ_INT BIT(1) +#define PCIE_UL_EDMA_INT0 BIT(2) +#define PCIE_UL_EDMA_INT1 BIT(3) +#define PCIE_UL_EDMA_INT2 BIT(4) +#define PCIE_UL_EDMA_INT3 BIT(5) +#define PCIE_UL_S_INT_EVENT_MASK1_ALL (PCIE_UL_CFG_PME_INT | \ + PCIE_UL_CFG_LINK_EQ_REQ_INT | \ + PCIE_UL_EDMA_INT0 | \ + PCIE_UL_EDMA_INT1 | \ + PCIE_UL_EDMA_INT2 | \ + PCIE_UL_EDMA_INT3) + +#define PCIE_UL_REG_S_SB_MON 0x0198 +#define PCIE_UL_REG_S_SIG_MON 0x019C +#define PCIE_UL_CORE_RST_N_MON BIT(0) + +#define PCIE_UL_REG_V_SII_DBG_00 0x0844 +#define PCIE_UL_REG_V_SII_GEN_CTRL_01 0x0860 +#define PCIE_UL_APP_LTSSM_ENABLE BIT(0) + +#define PCIE_UL_REG_V_PHY_ST_00 0x0864 +#define PCIE_UL_SMLH_LINK_UP BIT(0) + +#define PCIE_UL_REG_V_PHY_ST_02 0x0868 +#define PCIE_UL_S_DETECT_ACT 0x01 +#define PCIE_UL_S_L0 0x11 + +#define PISMU_CKON_PCIE 0x0038 +#define PISMU_CKON_PCIE_AUX_CLK BIT(1) +#define PISMU_CKON_PCIE_MSTR_ACLK BIT(0) + +#define PISMU_RSOFF_PCIE 0x0538 +#define PISMU_RSOFF_PCIE_ULREG_RST_N BIT(1) +#define PISMU_RSOFF_PCIE_PWR_UP_RST_N BIT(0) + +#define PCIE_MPU_REG_MP_EN 0x0 +#define MPU_MP_EN_DISABLE BIT(0) + +/* Access registers in PCIe ulreg */ +static void visconti_ulreg_writel(struct visconti_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->ulreg_base + reg); +} + +static u32 visconti_ulreg_readl(struct visconti_pcie *pcie, u32 reg) +{ + return readl_relaxed(pcie->ulreg_base + reg); +} + +/* Access registers in PCIe smu */ +static void visconti_smu_writel(struct visconti_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->smu_base + reg); +} + +/* Access registers in PCIe mpu */ +static void visconti_mpu_writel(struct visconti_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->mpu_base + reg); +} + +static u32 visconti_mpu_readl(struct visconti_pcie *pcie, u32 reg) +{ + return readl_relaxed(pcie->mpu_base + reg); +} + +static 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; +} + +static int visconti_pcie_start_link(struct dw_pcie *pci) +{ + struct visconti_pcie *pcie = dev_get_drvdata(pci->dev); + void __iomem *addr = pcie->ulreg_base; + u32 val; + int ret; + + visconti_ulreg_writel(pcie, PCIE_UL_APP_LTSSM_ENABLE, + PCIE_UL_REG_V_SII_GEN_CTRL_01); + + ret = readl_relaxed_poll_timeout(addr + PCIE_UL_REG_V_PHY_ST_02, + val, (val & PCIE_UL_S_L0), + 90000, 100000); + if (ret) + return ret; + + visconti_ulreg_writel(pcie, PCIE_UL_S_INT_EVENT_MASK1_ALL, + PCIE_UL_REG_S_INT_EVENT_MASK1); + + if (dw_pcie_link_up(pci)) { + val = visconti_mpu_readl(pcie, PCIE_MPU_REG_MP_EN); + visconti_mpu_writel(pcie, val & ~MPU_MP_EN_DISABLE, + PCIE_MPU_REG_MP_EN); + } + + return 0; +} + +static void visconti_pcie_stop_link(struct dw_pcie *pci) +{ + struct visconti_pcie *pcie = dev_get_drvdata(pci->dev); + u32 val; + + val = visconti_ulreg_readl(pcie, PCIE_UL_REG_V_SII_GEN_CTRL_01); + val &= ~PCIE_UL_APP_LTSSM_ENABLE; + visconti_ulreg_writel(pcie, val, PCIE_UL_REG_V_SII_GEN_CTRL_01); + + val = visconti_mpu_readl(pcie, PCIE_MPU_REG_MP_EN); + visconti_mpu_writel(pcie, val | MPU_MP_EN_DISABLE, PCIE_MPU_REG_MP_EN); +} + +/* + * In this SoC specification, the CPU bus outputs the offset value from + * 0x40000000 to the PCIe bus, so 0x40000000 is subtracted from the CPU + * bus address. This 0x40000000 is also based on io_base from DT. + */ +static u64 visconti_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 cpu_addr) +{ + struct dw_pcie_rp *pp = &pci->pp; + + return cpu_addr & ~pp->io_base; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .cpu_addr_fixup = visconti_pcie_cpu_addr_fixup, + .link_up = visconti_pcie_link_up, + .start_link = visconti_pcie_start_link, + .stop_link = visconti_pcie_stop_link, +}; + +static int visconti_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct visconti_pcie *pcie = dev_get_drvdata(pci->dev); + void __iomem *addr; + int err; + u32 val; + + visconti_smu_writel(pcie, + PISMU_CKON_PCIE_AUX_CLK | PISMU_CKON_PCIE_MSTR_ACLK, + PISMU_CKON_PCIE); + ndelay(250); + + visconti_smu_writel(pcie, PISMU_RSOFF_PCIE_ULREG_RST_N, + PISMU_RSOFF_PCIE); + visconti_ulreg_writel(pcie, PCIE_UL_REG_S_PCIE_MODE_RC, + PCIE_UL_REG_S_PCIE_MODE); + + val = PCIE_UL_REG_S_PERSTN_CTRL_INIT; + visconti_ulreg_writel(pcie, val, PCIE_UL_REG_S_PERSTN_CTRL); + udelay(100); + + val |= PCIE_UL_PERSTN_OUT; + visconti_ulreg_writel(pcie, val, PCIE_UL_REG_S_PERSTN_CTRL); + udelay(100); + + visconti_smu_writel(pcie, PISMU_RSOFF_PCIE_PWR_UP_RST_N, + PISMU_RSOFF_PCIE); + + addr = pcie->ulreg_base + PCIE_UL_REG_S_PHY_INIT_03; + err = readl_relaxed_poll_timeout(addr, val, + (val & PCIE_UL_PHY0_SRAM_INIT_DONE), + 100, 1000); + if (err) + return err; + + visconti_ulreg_writel(pcie, PCIE_UL_PHY0_SRAM_EXT_LD_DONE, + PCIE_UL_REG_S_PHY_INIT_02); + + addr = pcie->ulreg_base + PCIE_UL_REG_S_SIG_MON; + return readl_relaxed_poll_timeout(addr, val, + (val & PCIE_UL_CORE_RST_N_MON), 100, + 1000); +} + +static const struct dw_pcie_host_ops visconti_pcie_host_ops = { + .init = visconti_pcie_host_init, +}; + +static int visconti_get_resources(struct platform_device *pdev, + struct visconti_pcie *pcie) +{ + struct device *dev = &pdev->dev; + + pcie->ulreg_base = devm_platform_ioremap_resource_byname(pdev, "ulreg"); + if (IS_ERR(pcie->ulreg_base)) + return PTR_ERR(pcie->ulreg_base); + + pcie->smu_base = devm_platform_ioremap_resource_byname(pdev, "smu"); + if (IS_ERR(pcie->smu_base)) + return PTR_ERR(pcie->smu_base); + + pcie->mpu_base = devm_platform_ioremap_resource_byname(pdev, "mpu"); + if (IS_ERR(pcie->mpu_base)) + return PTR_ERR(pcie->mpu_base); + + pcie->refclk = devm_clk_get(dev, "ref"); + if (IS_ERR(pcie->refclk)) + return dev_err_probe(dev, PTR_ERR(pcie->refclk), + "Failed to get ref clock\n"); + + pcie->coreclk = devm_clk_get(dev, "core"); + if (IS_ERR(pcie->coreclk)) + return dev_err_probe(dev, PTR_ERR(pcie->coreclk), + "Failed to get core clock\n"); + + pcie->auxclk = devm_clk_get(dev, "aux"); + if (IS_ERR(pcie->auxclk)) + return dev_err_probe(dev, PTR_ERR(pcie->auxclk), + "Failed to get aux clock\n"); + + return 0; +} + +static int visconti_add_pcie_port(struct visconti_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + + pp->irq = platform_get_irq_byname(pdev, "intr"); + if (pp->irq < 0) + return pp->irq; + + pp->ops = &visconti_pcie_host_ops; + + return dw_pcie_host_init(pp); +} + +static int visconti_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct visconti_pcie *pcie; + struct dw_pcie *pci; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = &pcie->pci; + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + ret = visconti_get_resources(pdev, pcie); + if (ret) + return ret; + + platform_set_drvdata(pdev, pcie); + + return visconti_add_pcie_port(pcie, pdev); +} + +static const struct of_device_id visconti_pcie_match[] = { + { .compatible = "toshiba,visconti-pcie" }, + {}, +}; + +static struct platform_driver visconti_pcie_driver = { + .probe = visconti_pcie_probe, + .driver = { + .name = "visconti-pcie", + .of_match_table = visconti_pcie_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(visconti_pcie_driver); diff --git a/drivers/pci/controller/mobiveil/Kconfig b/drivers/pci/controller/mobiveil/Kconfig new file mode 100644 index 000000000000..c50c4625937f --- /dev/null +++ b/drivers/pci/controller/mobiveil/Kconfig @@ -0,0 +1,35 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Mobiveil-based PCIe controllers" + depends on PCI + +config PCIE_MOBIVEIL + bool + +config PCIE_MOBIVEIL_HOST + bool + depends on PCI_MSI + select IRQ_MSI_LIB + select PCIE_MOBIVEIL + +config PCIE_LAYERSCAPE_GEN4 + bool "Freescale Layerscape Gen4 PCIe controller" + depends on ARCH_LAYERSCAPE || COMPILE_TEST + depends on PCI_MSI + select PCIE_MOBIVEIL_HOST + help + Say Y here if you want PCIe Gen4 controller support on + Layerscape SoCs. + +config PCIE_MOBIVEIL_PLAT + bool "Mobiveil AXI PCIe controller" + depends on ARCH_ZYNQMP || COMPILE_TEST + depends on OF + depends on PCI_MSI + select PCIE_MOBIVEIL_HOST + help + Say Y here if you want to enable support for the Mobiveil AXI PCIe + Soft IP. It has up to 8 outbound and inbound windows + for address translation and it is a PCIe Gen4 IP. + +endmenu diff --git a/drivers/pci/controller/mobiveil/Makefile b/drivers/pci/controller/mobiveil/Makefile new file mode 100644 index 000000000000..99d879de32d6 --- /dev/null +++ b/drivers/pci/controller/mobiveil/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_PCIE_MOBIVEIL) += pcie-mobiveil.o +obj-$(CONFIG_PCIE_MOBIVEIL_HOST) += pcie-mobiveil-host.o +obj-$(CONFIG_PCIE_MOBIVEIL_PLAT) += pcie-mobiveil-plat.o +obj-$(CONFIG_PCIE_LAYERSCAPE_GEN4) += pcie-layerscape-gen4.o diff --git a/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c new file mode 100644 index 000000000000..4919b27eaf44 --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe Gen4 host controller driver for NXP Layerscape SoCs + * + * Copyright 2019-2020 NXP + * + * Author: Zhiqiang Hou <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/kernel.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> + +#include "pcie-mobiveil.h" + +/* LUT and PF control registers */ +#define PCIE_LUT_OFF 0x80000 +#define PCIE_PF_OFF 0xc0000 +#define PCIE_PF_INT_STAT 0x18 +#define PF_INT_STAT_PABRST BIT(31) + +#define PCIE_PF_DBG 0x7fc +#define PF_DBG_LTSSM_MASK 0x3f +#define PF_DBG_LTSSM_L0 0x2d /* L0 state */ +#define PF_DBG_WE BIT(31) +#define PF_DBG_PABR BIT(27) + +#define to_ls_g4_pcie(x) platform_get_drvdata((x)->pdev) + +struct ls_g4_pcie { + struct mobiveil_pcie pci; + struct delayed_work dwork; + int irq; +}; + +static inline u32 ls_g4_pcie_pf_readl(struct ls_g4_pcie *pcie, u32 off) +{ + return ioread32(pcie->pci.csr_axi_slave_base + PCIE_PF_OFF + off); +} + +static inline void ls_g4_pcie_pf_writel(struct ls_g4_pcie *pcie, + u32 off, u32 val) +{ + iowrite32(val, pcie->pci.csr_axi_slave_base + PCIE_PF_OFF + off); +} + +static 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); + return (state & PF_DBG_LTSSM_MASK) == PF_DBG_LTSSM_L0; +} + +static void ls_g4_pcie_disable_interrupt(struct ls_g4_pcie *pcie) +{ + struct mobiveil_pcie *mv_pci = &pcie->pci; + + mobiveil_csr_writel(mv_pci, 0, PAB_INTP_AMBA_MISC_ENB); +} + +static void ls_g4_pcie_enable_interrupt(struct ls_g4_pcie *pcie) +{ + struct mobiveil_pcie *mv_pci = &pcie->pci; + u32 val; + + /* Clear the interrupt status */ + mobiveil_csr_writel(mv_pci, 0xffffffff, PAB_INTP_AMBA_MISC_STAT); + + val = PAB_INTP_INTX_MASK | PAB_INTP_MSI | PAB_INTP_RESET | + PAB_INTP_PCIE_UE | PAB_INTP_IE_PMREDI | PAB_INTP_IE_EC; + mobiveil_csr_writel(mv_pci, val, PAB_INTP_AMBA_MISC_ENB); +} + +static int ls_g4_pcie_reinit_hw(struct ls_g4_pcie *pcie) +{ + struct mobiveil_pcie *mv_pci = &pcie->pci; + struct device *dev = &mv_pci->pdev->dev; + u32 val, act_stat; + int to = 100; + + /* Poll for pab_csb_reset to set and PAB activity to clear */ + do { + usleep_range(10, 15); + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_INT_STAT); + act_stat = mobiveil_csr_readl(mv_pci, PAB_ACTIVITY_STAT); + } while (((val & PF_INT_STAT_PABRST) == 0 || act_stat) && to--); + if (to < 0) { + dev_err(dev, "Poll PABRST&PABACT timeout\n"); + return -EIO; + } + + /* clear PEX_RESET bit in PEX_PF0_DBG register */ + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG); + val |= PF_DBG_WE; + ls_g4_pcie_pf_writel(pcie, PCIE_PF_DBG, val); + + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG); + val |= PF_DBG_PABR; + ls_g4_pcie_pf_writel(pcie, PCIE_PF_DBG, val); + + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG); + val &= ~PF_DBG_WE; + ls_g4_pcie_pf_writel(pcie, PCIE_PF_DBG, val); + + mobiveil_host_init(mv_pci, true); + + to = 100; + while (!ls_g4_pcie_link_up(mv_pci) && to--) + usleep_range(200, 250); + if (to < 0) { + dev_err(dev, "PCIe link training timeout\n"); + return -EIO; + } + + return 0; +} + +static irqreturn_t ls_g4_pcie_isr(int irq, void *dev_id) +{ + struct ls_g4_pcie *pcie = (struct ls_g4_pcie *)dev_id; + struct mobiveil_pcie *mv_pci = &pcie->pci; + u32 val; + + val = mobiveil_csr_readl(mv_pci, PAB_INTP_AMBA_MISC_STAT); + if (!val) + return IRQ_NONE; + + if (val & PAB_INTP_RESET) { + ls_g4_pcie_disable_interrupt(pcie); + schedule_delayed_work(&pcie->dwork, msecs_to_jiffies(1)); + } + + mobiveil_csr_writel(mv_pci, val, PAB_INTP_AMBA_MISC_STAT); + + return IRQ_HANDLED; +} + +static int ls_g4_pcie_interrupt_init(struct mobiveil_pcie *mv_pci) +{ + struct ls_g4_pcie *pcie = to_ls_g4_pcie(mv_pci); + struct platform_device *pdev = mv_pci->pdev; + struct device *dev = &pdev->dev; + int ret; + + pcie->irq = platform_get_irq_byname(pdev, "intr"); + if (pcie->irq < 0) + return pcie->irq; + + ret = devm_request_irq(dev, pcie->irq, ls_g4_pcie_isr, + IRQF_SHARED, pdev->name, pcie); + if (ret) { + dev_err(dev, "Can't register PCIe IRQ, errno = %d\n", ret); + return ret; + } + + return 0; +} + +static void ls_g4_pcie_reset(struct work_struct *work) +{ + struct delayed_work *dwork = 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; + + ctrl = mobiveil_csr_readw(mv_pci, PCI_BRIDGE_CONTROL); + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + mobiveil_csr_writew(mv_pci, ctrl, PCI_BRIDGE_CONTROL); + + if (!ls_g4_pcie_reinit_hw(pcie)) + return; + + ls_g4_pcie_enable_interrupt(pcie); +} + +static const struct mobiveil_rp_ops ls_g4_pcie_rp_ops = { + .interrupt_init = ls_g4_pcie_interrupt_init, +}; + +static const struct mobiveil_pab_ops ls_g4_pcie_pab_ops = { + .link_up = ls_g4_pcie_link_up, +}; + +static int __init ls_g4_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct mobiveil_pcie *mv_pci; + struct ls_g4_pcie *pcie; + struct device_node *np = dev->of_node; + int ret; + + if (!of_parse_phandle(np, "msi-parent", 0)) { + dev_err(dev, "Failed to find msi-parent\n"); + return -EINVAL; + } + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + mv_pci = &pcie->pci; + + mv_pci->pdev = pdev; + mv_pci->ops = &ls_g4_pcie_pab_ops; + mv_pci->rp.ops = &ls_g4_pcie_rp_ops; + mv_pci->rp.bridge = bridge; + + platform_set_drvdata(pdev, pcie); + + INIT_DELAYED_WORK(&pcie->dwork, ls_g4_pcie_reset); + + ret = mobiveil_pcie_host_probe(mv_pci); + if (ret) { + dev_err(dev, "Fail to probe\n"); + return ret; + } + + ls_g4_pcie_enable_interrupt(pcie); + + return 0; +} + +static const struct of_device_id ls_g4_pcie_of_match[] = { + { .compatible = "fsl,lx2160a-pcie", }, + { }, +}; + +static struct platform_driver ls_g4_pcie_driver = { + .driver = { + .name = "layerscape-pcie-gen4", + .of_match_table = ls_g4_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; + +builtin_platform_driver_probe(ls_g4_pcie_driver, ls_g4_pcie_probe); diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c new file mode 100644 index 000000000000..dbc72c73fd0a --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c @@ -0,0 +1,582 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019-2020 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "pcie-mobiveil.h" + +static bool mobiveil_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) +{ + /* Only one device down on each root port */ + if (pci_is_root_bus(bus) && (devfn > 0)) + return false; + + /* + * Do not read more than one device on the bus directly + * attached to RC + */ + if ((bus->primary == to_pci_host_bridge(bus->bridge)->busnr) && (PCI_SLOT(devfn) > 0)) + return false; + + return true; +} + +/* + * mobiveil_pcie_map_bus - routine to get the configuration base of either + * root port or endpoint + */ +static void __iomem *mobiveil_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct mobiveil_pcie *pcie = bus->sysdata; + struct mobiveil_root_port *rp = &pcie->rp; + u32 value; + + if (!mobiveil_pcie_valid_device(bus, devfn)) + return NULL; + + /* RC config access */ + if (pci_is_root_bus(bus)) + return pcie->csr_axi_slave_base + where; + + /* + * EP config access (in Config/APIO space) + * Program PEX Address base (31..16 bits) with appropriate value + * (BDF) in PAB_AXI_AMAP_PEX_WIN_L0 Register. + * Relies on pci_lock serialization + */ + value = bus->number << PAB_BUS_SHIFT | + PCI_SLOT(devfn) << PAB_DEVICE_SHIFT | + PCI_FUNC(devfn) << PAB_FUNCTION_SHIFT; + + mobiveil_csr_writel(pcie, value, PAB_AXI_AMAP_PEX_WIN_L(WIN_NUM_0)); + + return rp->config_axi_slave_base + where; +} + +static struct pci_ops mobiveil_pcie_ops = { + .map_bus = mobiveil_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static void mobiveil_pcie_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct mobiveil_pcie *pcie = irq_desc_get_handler_data(desc); + struct device *dev = &pcie->pdev->dev; + struct mobiveil_root_port *rp = &pcie->rp; + struct mobiveil_msi *msi = &rp->msi; + u32 msi_data, msi_addr_lo, msi_addr_hi; + u32 intr_status, msi_status; + unsigned long shifted_status; + u32 bit, val, mask; + + /* + * The core provides a single interrupt for both INTx/MSI messages. + * So we'll read both INTx and MSI status + */ + + chained_irq_enter(chip, desc); + + /* read INTx status */ + val = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT); + mask = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); + intr_status = val & mask; + + /* Handle INTx */ + if (intr_status & PAB_INTP_INTX_MASK) { + shifted_status = mobiveil_csr_readl(pcie, + PAB_INTP_AMBA_MISC_STAT); + shifted_status &= PAB_INTP_INTX_MASK; + shifted_status >>= PAB_INTX_START; + do { + for_each_set_bit(bit, &shifted_status, PCI_NUM_INTX) { + int ret; + ret = generic_handle_domain_irq(rp->intx_domain, + bit + 1); + if (ret) + dev_err_ratelimited(dev, "unexpected IRQ, INT%d\n", + bit); + + /* clear interrupt handled */ + mobiveil_csr_writel(pcie, + 1 << (PAB_INTX_START + bit), + PAB_INTP_AMBA_MISC_STAT); + } + + shifted_status = mobiveil_csr_readl(pcie, + PAB_INTP_AMBA_MISC_STAT); + shifted_status &= PAB_INTP_INTX_MASK; + shifted_status >>= PAB_INTX_START; + } while (shifted_status != 0); + } + + /* read extra MSI status register */ + msi_status = readl_relaxed(pcie->apb_csr_base + MSI_STATUS_OFFSET); + + /* handle MSI interrupts */ + while (msi_status & 1) { + msi_data = readl_relaxed(pcie->apb_csr_base + MSI_DATA_OFFSET); + + /* + * MSI_STATUS_OFFSET register gets updated to zero + * once we pop not only the MSI data but also address + * from MSI hardware FIFO. So keeping these following + * two dummy reads. + */ + msi_addr_lo = readl_relaxed(pcie->apb_csr_base + + MSI_ADDR_L_OFFSET); + msi_addr_hi = readl_relaxed(pcie->apb_csr_base + + MSI_ADDR_H_OFFSET); + dev_dbg(dev, "MSI registers, data: %08x, addr: %08x:%08x\n", + msi_data, msi_addr_hi, msi_addr_lo); + + generic_handle_domain_irq(msi->dev_domain, msi_data); + + msi_status = readl_relaxed(pcie->apb_csr_base + + MSI_STATUS_OFFSET); + } + + /* Clear the interrupt status */ + mobiveil_csr_writel(pcie, intr_status, PAB_INTP_AMBA_MISC_STAT); + chained_irq_exit(chip, desc); +} + +static int mobiveil_pcie_parse_dt(struct mobiveil_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct platform_device *pdev = pcie->pdev; + struct device_node *node = dev->of_node; + struct mobiveil_root_port *rp = &pcie->rp; + struct resource *res; + + /* map config resource */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "config_axi_slave"); + rp->config_axi_slave_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(rp->config_axi_slave_base)) + return PTR_ERR(rp->config_axi_slave_base); + rp->ob_io_res = res; + + /* map csr resource */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "csr_axi_slave"); + pcie->csr_axi_slave_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pcie->csr_axi_slave_base)) + return PTR_ERR(pcie->csr_axi_slave_base); + pcie->pcie_reg_base = res->start; + + /* read the number of windows requested */ + if (of_property_read_u32(node, "apio-wins", &pcie->apio_wins)) + pcie->apio_wins = MAX_PIO_WINDOWS; + + if (of_property_read_u32(node, "ppio-wins", &pcie->ppio_wins)) + pcie->ppio_wins = MAX_PIO_WINDOWS; + + return 0; +} + +static void mobiveil_pcie_enable_msi(struct mobiveil_pcie *pcie) +{ + phys_addr_t msg_addr = pcie->pcie_reg_base; + struct mobiveil_msi *msi = &pcie->rp.msi; + + msi->num_of_vectors = PCI_NUM_MSI; + msi->msi_pages_phys = (phys_addr_t)msg_addr; + + writel_relaxed(lower_32_bits(msg_addr), + pcie->apb_csr_base + MSI_BASE_LO_OFFSET); + writel_relaxed(upper_32_bits(msg_addr), + pcie->apb_csr_base + MSI_BASE_HI_OFFSET); + writel_relaxed(4096, pcie->apb_csr_base + MSI_SIZE_OFFSET); + writel_relaxed(1, pcie->apb_csr_base + MSI_ENABLE_OFFSET); +} + +int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit) +{ + struct mobiveil_root_port *rp = &pcie->rp; + struct pci_host_bridge *bridge = rp->bridge; + u32 value, pab_ctrl, type; + struct resource_entry *win; + + pcie->ib_wins_configured = 0; + pcie->ob_wins_configured = 0; + + if (!reinit) { + /* setup bus numbers */ + value = mobiveil_csr_readl(pcie, PCI_PRIMARY_BUS); + value &= 0xff000000; + value |= 0x00ff0100; + mobiveil_csr_writel(pcie, value, PCI_PRIMARY_BUS); + } + + /* + * program Bus Master Enable Bit in Command Register in PAB Config + * Space + */ + value = mobiveil_csr_readl(pcie, PCI_COMMAND); + value |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; + mobiveil_csr_writel(pcie, value, PCI_COMMAND); + + /* + * program PIO Enable Bit to 1 (and PEX PIO Enable to 1) in PAB_CTRL + * register + */ + pab_ctrl = mobiveil_csr_readl(pcie, PAB_CTRL); + pab_ctrl |= (1 << AMBA_PIO_ENABLE_SHIFT) | (1 << PEX_PIO_ENABLE_SHIFT); + mobiveil_csr_writel(pcie, pab_ctrl, PAB_CTRL); + + /* + * program PIO Enable Bit to 1 and Config Window Enable Bit to 1 in + * PAB_AXI_PIO_CTRL Register + */ + value = mobiveil_csr_readl(pcie, PAB_AXI_PIO_CTRL); + value |= APIO_EN_MASK; + mobiveil_csr_writel(pcie, value, PAB_AXI_PIO_CTRL); + + /* Enable PCIe PIO master */ + value = mobiveil_csr_readl(pcie, PAB_PEX_PIO_CTRL); + value |= 1 << PIO_ENABLE_SHIFT; + mobiveil_csr_writel(pcie, value, PAB_PEX_PIO_CTRL); + + /* + * we'll program one outbound window for config reads and + * another default inbound window for all the upstream traffic + * rest of the outbound windows will be configured according to + * the "ranges" field defined in device tree + */ + + /* config outbound translation window */ + program_ob_windows(pcie, WIN_NUM_0, rp->ob_io_res->start, 0, + CFG_WINDOW_TYPE, resource_size(rp->ob_io_res)); + + /* memory inbound translation window */ + program_ib_windows(pcie, WIN_NUM_0, 0, 0, MEM_WINDOW_TYPE, IB_WIN_SIZE); + + /* Get the I/O and memory ranges from DT */ + resource_list_for_each_entry(win, &bridge->windows) { + if (resource_type(win->res) == IORESOURCE_MEM) + type = MEM_WINDOW_TYPE; + else if (resource_type(win->res) == IORESOURCE_IO) + type = IO_WINDOW_TYPE; + else + continue; + + /* configure outbound translation window */ + program_ob_windows(pcie, pcie->ob_wins_configured, + win->res->start, + win->res->start - win->offset, + type, resource_size(win->res)); + } + + /* fixup for PCIe class register */ + value = mobiveil_csr_readl(pcie, PAB_INTP_AXI_PIO_CLASS); + value &= 0xff; + value |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + mobiveil_csr_writel(pcie, value, PAB_INTP_AXI_PIO_CLASS); + + return 0; +} + +static void mobiveil_mask_intx_irq(struct irq_data *data) +{ + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data); + struct mobiveil_root_port *rp; + unsigned long flags; + u32 mask, shifted_val; + + rp = &pcie->rp; + mask = 1 << ((data->hwirq + PAB_INTX_START) - 1); + raw_spin_lock_irqsave(&rp->intx_mask_lock, flags); + shifted_val = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); + shifted_val &= ~mask; + mobiveil_csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB); + raw_spin_unlock_irqrestore(&rp->intx_mask_lock, flags); +} + +static void mobiveil_unmask_intx_irq(struct irq_data *data) +{ + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data); + struct mobiveil_root_port *rp; + unsigned long flags; + u32 shifted_val, mask; + + rp = &pcie->rp; + mask = 1 << ((data->hwirq + PAB_INTX_START) - 1); + raw_spin_lock_irqsave(&rp->intx_mask_lock, flags); + shifted_val = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); + shifted_val |= mask; + mobiveil_csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB); + raw_spin_unlock_irqrestore(&rp->intx_mask_lock, flags); +} + +static struct irq_chip intx_irq_chip = { + .name = "mobiveil_pcie:intx", + .irq_enable = mobiveil_unmask_intx_irq, + .irq_disable = mobiveil_mask_intx_irq, + .irq_mask = mobiveil_mask_intx_irq, + .irq_unmask = mobiveil_unmask_intx_irq, +}; + +/* routine to setup the INTx related data */ +static int mobiveil_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &intx_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +/* INTx domain operations structure */ +static const struct irq_domain_ops intx_domain_ops = { + .map = mobiveil_pcie_intx_map, +}; + +#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 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) +{ + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data); + phys_addr_t addr = pcie->pcie_reg_base + (data->hwirq * sizeof(int)); + + msg->address_lo = lower_32_bits(addr); + msg->address_hi = upper_32_bits(addr); + msg->data = data->hwirq; + + dev_dbg(&pcie->pdev->dev, "msi#%d address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); +} + +static struct irq_chip mobiveil_msi_bottom_irq_chip = { + .name = "Mobiveil MSI", + .irq_compose_msi_msg = mobiveil_compose_msi_msg, +}; + +static int mobiveil_irq_msi_domain_alloc(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct mobiveil_pcie *pcie = domain->host_data; + struct mobiveil_msi *msi = &pcie->rp.msi; + unsigned long bit; + + WARN_ON(nr_irqs != 1); + mutex_lock(&msi->lock); + + bit = find_first_zero_bit(msi->msi_irq_in_use, msi->num_of_vectors); + if (bit >= msi->num_of_vectors) { + mutex_unlock(&msi->lock); + return -ENOSPC; + } + + set_bit(bit, msi->msi_irq_in_use); + + mutex_unlock(&msi->lock); + + irq_domain_set_info(domain, virq, bit, &mobiveil_msi_bottom_irq_chip, + domain->host_data, handle_level_irq, NULL, NULL); + return 0; +} + +static void mobiveil_irq_msi_domain_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(d); + struct mobiveil_msi *msi = &pcie->rp.msi; + + mutex_lock(&msi->lock); + + if (!test_bit(d->hwirq, msi->msi_irq_in_use)) + dev_err(&pcie->pdev->dev, "trying to free unused MSI#%lu\n", + d->hwirq); + else + __clear_bit(d->hwirq, msi->msi_irq_in_use); + + mutex_unlock(&msi->lock); +} +static const struct irq_domain_ops msi_domain_ops = { + .alloc = mobiveil_irq_msi_domain_alloc, + .free = mobiveil_irq_msi_domain_free, +}; + +static int mobiveil_allocate_msi_domains(struct mobiveil_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct mobiveil_msi *msi = &pcie->rp.msi; + + mutex_init(&msi->lock); + + 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"); + return -ENOMEM; + } + + return 0; +} + +static int mobiveil_pcie_init_irq_domain(struct mobiveil_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct mobiveil_root_port *rp = &pcie->rp; + + /* setup INTx */ + 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; + } + + raw_spin_lock_init(&rp->intx_mask_lock); + + /* setup MSI */ + return mobiveil_allocate_msi_domains(pcie); +} + +static int mobiveil_pcie_integrated_interrupt_init(struct mobiveil_pcie *pcie) +{ + struct platform_device *pdev = pcie->pdev; + struct device *dev = &pdev->dev; + struct mobiveil_root_port *rp = &pcie->rp; + struct resource *res; + int ret; + + /* map MSI config resource */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "apb_csr"); + pcie->apb_csr_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pcie->apb_csr_base)) + return PTR_ERR(pcie->apb_csr_base); + + /* setup MSI hardware registers */ + mobiveil_pcie_enable_msi(pcie); + + rp->irq = platform_get_irq(pdev, 0); + if (rp->irq < 0) + return rp->irq; + + /* initialize the IRQ domains */ + ret = mobiveil_pcie_init_irq_domain(pcie); + if (ret) { + dev_err(dev, "Failed creating IRQ Domain\n"); + return ret; + } + + irq_set_chained_handler_and_data(rp->irq, mobiveil_pcie_isr, pcie); + + /* Enable interrupts */ + mobiveil_csr_writel(pcie, (PAB_INTP_INTX_MASK | PAB_INTP_MSI_MASK), + PAB_INTP_AMBA_MISC_ENB); + + + return 0; +} + +static int mobiveil_pcie_interrupt_init(struct mobiveil_pcie *pcie) +{ + struct mobiveil_root_port *rp = &pcie->rp; + + if (rp->ops->interrupt_init) + return rp->ops->interrupt_init(pcie); + + return mobiveil_pcie_integrated_interrupt_init(pcie); +} + +static bool mobiveil_pcie_is_bridge(struct mobiveil_pcie *pcie) +{ + u32 header_type; + + header_type = mobiveil_csr_readb(pcie, PCI_HEADER_TYPE); + header_type &= PCI_HEADER_TYPE_MASK; + + return header_type == PCI_HEADER_TYPE_BRIDGE; +} + +int mobiveil_pcie_host_probe(struct mobiveil_pcie *pcie) +{ + struct mobiveil_root_port *rp = &pcie->rp; + struct pci_host_bridge *bridge = rp->bridge; + struct device *dev = &pcie->pdev->dev; + int ret; + + ret = mobiveil_pcie_parse_dt(pcie); + if (ret) { + dev_err(dev, "Parsing DT failed, ret: %x\n", ret); + return ret; + } + + if (!mobiveil_pcie_is_bridge(pcie)) + return -ENODEV; + + /* + * configure all inbound and outbound windows and prepare the RC for + * config access + */ + ret = mobiveil_host_init(pcie, false); + if (ret) { + dev_err(dev, "Failed to initialize host\n"); + return ret; + } + + ret = mobiveil_pcie_interrupt_init(pcie); + if (ret) { + dev_err(dev, "Interrupt init failed\n"); + return ret; + } + + /* Initialize bridge */ + bridge->sysdata = pcie; + bridge->ops = &mobiveil_pcie_ops; + + ret = mobiveil_bringup_link(pcie); + if (ret) { + dev_info(dev, "link bring-up failed\n"); + return ret; + } + + return pci_host_probe(bridge); +} diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-plat.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-plat.c new file mode 100644 index 000000000000..c5bb87ff6d9a --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-plat.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "pcie-mobiveil.h" + +static int mobiveil_pcie_probe(struct platform_device *pdev) +{ + struct mobiveil_pcie *pcie; + struct pci_host_bridge *bridge; + struct device *dev = &pdev->dev; + + /* allocate the PCIe port */ + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->rp.bridge = bridge; + + pcie->pdev = pdev; + + return mobiveil_pcie_host_probe(pcie); +} + +static const struct of_device_id mobiveil_pcie_of_match[] = { + {.compatible = "mbvl,gpex40-pcie",}, + {}, +}; + +MODULE_DEVICE_TABLE(of, mobiveil_pcie_of_match); + +static struct platform_driver mobiveil_pcie_driver = { + .probe = mobiveil_pcie_probe, + .driver = { + .name = "mobiveil-pcie", + .of_match_table = mobiveil_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; + +builtin_platform_driver(mobiveil_pcie_driver); + +MODULE_DESCRIPTION("Mobiveil PCIe host controller driver"); +MODULE_AUTHOR("Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>"); diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil.c b/drivers/pci/controller/mobiveil/pcie-mobiveil.c new file mode 100644 index 000000000000..62ecbaeb0a60 --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include "pcie-mobiveil.h" + +/* + * mobiveil_pcie_sel_page - routine to access paged register + * + * Registers whose address greater than PAGED_ADDR_BNDRY (0xc00) are paged, + * for this scheme to work extracted higher 6 bits of the offset will be + * written to pg_sel field of PAB_CTRL register and rest of the lower 10 + * bits enabled with PAGED_ADDR_BNDRY are used as offset of the register. + */ +static void mobiveil_pcie_sel_page(struct mobiveil_pcie *pcie, u8 pg_idx) +{ + u32 val; + + val = readl(pcie->csr_axi_slave_base + PAB_CTRL); + val &= ~(PAGE_SEL_MASK << PAGE_SEL_SHIFT); + val |= (pg_idx & PAGE_SEL_MASK) << PAGE_SEL_SHIFT; + + writel(val, pcie->csr_axi_slave_base + PAB_CTRL); +} + +static void __iomem *mobiveil_pcie_comp_addr(struct mobiveil_pcie *pcie, + u32 off) +{ + if (off < PAGED_ADDR_BNDRY) { + /* For directly accessed registers, clear the pg_sel field */ + mobiveil_pcie_sel_page(pcie, 0); + return pcie->csr_axi_slave_base + off; + } + + mobiveil_pcie_sel_page(pcie, OFFSET_TO_PAGE_IDX(off)); + return pcie->csr_axi_slave_base + OFFSET_TO_PAGE_ADDR(off); +} + +static int mobiveil_pcie_read(void __iomem *addr, int size, u32 *val) +{ + if ((uintptr_t)addr & (size - 1)) { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + switch (size) { + case 4: + *val = readl(addr); + break; + case 2: + *val = readw(addr); + break; + case 1: + *val = readb(addr); + break; + default: + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int mobiveil_pcie_write(void __iomem *addr, int size, u32 val) +{ + if ((uintptr_t)addr & (size - 1)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + switch (size) { + case 4: + writel(val, addr); + break; + case 2: + writew(val, addr); + break; + case 1: + writeb(val, addr); + break; + default: + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + return PCIBIOS_SUCCESSFUL; +} + +u32 mobiveil_csr_read(struct mobiveil_pcie *pcie, u32 off, size_t size) +{ + void __iomem *addr; + u32 val; + int ret; + + addr = mobiveil_pcie_comp_addr(pcie, off); + + ret = mobiveil_pcie_read(addr, size, &val); + if (ret) + dev_err(&pcie->pdev->dev, "read CSR address failed\n"); + + return val; +} + +void mobiveil_csr_write(struct mobiveil_pcie *pcie, u32 val, u32 off, + size_t size) +{ + void __iomem *addr; + int ret; + + addr = mobiveil_pcie_comp_addr(pcie, off); + + ret = mobiveil_pcie_write(addr, size, val); + if (ret) + dev_err(&pcie->pdev->dev, "write CSR address failed\n"); +} + +bool mobiveil_pcie_link_up(struct mobiveil_pcie *pcie) +{ + if (pcie->ops->link_up) + return pcie->ops->link_up(pcie); + + return (mobiveil_csr_readl(pcie, LTSSM_STATUS) & + LTSSM_STATUS_L0_MASK) == LTSSM_STATUS_L0; +} + +void program_ib_windows(struct mobiveil_pcie *pcie, int win_num, + u64 cpu_addr, u64 pci_addr, u32 type, u64 size) +{ + u32 value; + u64 size64 = ~(size - 1); + + if (win_num >= pcie->ppio_wins) { + dev_err(&pcie->pdev->dev, + "ERROR: max inbound windows reached !\n"); + return; + } + + value = mobiveil_csr_readl(pcie, PAB_PEX_AMAP_CTRL(win_num)); + value &= ~(AMAP_CTRL_TYPE_MASK << AMAP_CTRL_TYPE_SHIFT | WIN_SIZE_MASK); + value |= type << AMAP_CTRL_TYPE_SHIFT | 1 << AMAP_CTRL_EN_SHIFT | + (lower_32_bits(size64) & WIN_SIZE_MASK); + mobiveil_csr_writel(pcie, value, PAB_PEX_AMAP_CTRL(win_num)); + + mobiveil_csr_writel(pcie, upper_32_bits(size64), + PAB_EXT_PEX_AMAP_SIZEN(win_num)); + + mobiveil_csr_writel(pcie, lower_32_bits(cpu_addr), + PAB_PEX_AMAP_AXI_WIN(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(cpu_addr), + PAB_EXT_PEX_AMAP_AXI_WIN(win_num)); + + mobiveil_csr_writel(pcie, lower_32_bits(pci_addr), + PAB_PEX_AMAP_PEX_WIN_L(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(pci_addr), + PAB_PEX_AMAP_PEX_WIN_H(win_num)); + + pcie->ib_wins_configured++; +} + +/* + * routine to program the outbound windows + */ +void program_ob_windows(struct mobiveil_pcie *pcie, int win_num, + u64 cpu_addr, u64 pci_addr, u32 type, u64 size) +{ + u32 value; + u64 size64 = ~(size - 1); + + if (win_num >= pcie->apio_wins) { + dev_err(&pcie->pdev->dev, + "ERROR: max outbound windows reached !\n"); + return; + } + + /* + * program Enable Bit to 1, Type Bit to (00) base 2, AXI Window Size Bit + * to 4 KB in PAB_AXI_AMAP_CTRL register + */ + value = mobiveil_csr_readl(pcie, PAB_AXI_AMAP_CTRL(win_num)); + value &= ~(WIN_TYPE_MASK << WIN_TYPE_SHIFT | WIN_SIZE_MASK); + value |= 1 << WIN_ENABLE_SHIFT | type << WIN_TYPE_SHIFT | + (lower_32_bits(size64) & WIN_SIZE_MASK); + mobiveil_csr_writel(pcie, value, PAB_AXI_AMAP_CTRL(win_num)); + + mobiveil_csr_writel(pcie, upper_32_bits(size64), + PAB_EXT_AXI_AMAP_SIZE(win_num)); + + /* + * program AXI window base with appropriate value in + * PAB_AXI_AMAP_AXI_WIN0 register + */ + mobiveil_csr_writel(pcie, + lower_32_bits(cpu_addr) & (~AXI_WINDOW_ALIGN_MASK), + PAB_AXI_AMAP_AXI_WIN(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(cpu_addr), + PAB_EXT_AXI_AMAP_AXI_WIN(win_num)); + + mobiveil_csr_writel(pcie, lower_32_bits(pci_addr), + PAB_AXI_AMAP_PEX_WIN_L(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(pci_addr), + PAB_AXI_AMAP_PEX_WIN_H(win_num)); + + pcie->ob_wins_configured++; +} + +int mobiveil_bringup_link(struct mobiveil_pcie *pcie) +{ + int retries; + + /* check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (mobiveil_pcie_link_up(pcie)) + return 0; + + usleep_range(LINK_WAIT_MIN, LINK_WAIT_MAX); + } + + dev_err(&pcie->pdev->dev, "link never came up\n"); + + return -ETIMEDOUT; +} diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil.h b/drivers/pci/controller/mobiveil/pcie-mobiveil.h new file mode 100644 index 000000000000..7246de6a7176 --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil.h @@ -0,0 +1,224 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#ifndef _PCIE_MOBIVEIL_H +#define _PCIE_MOBIVEIL_H + +#include <linux/pci.h> +#include <linux/irq.h> +#include <linux/msi.h> +#include "../../pci.h" + +/* register offsets and bit positions */ + +/* + * translation tables are grouped into windows, each window registers are + * grouped into blocks of 4 or 16 registers each + */ +#define PAB_REG_BLOCK_SIZE 16 +#define PAB_EXT_REG_BLOCK_SIZE 4 + +#define PAB_REG_ADDR(offset, win) \ + (offset + (win * PAB_REG_BLOCK_SIZE)) +#define PAB_EXT_REG_ADDR(offset, win) \ + (offset + (win * PAB_EXT_REG_BLOCK_SIZE)) + +#define LTSSM_STATUS 0x0404 +#define LTSSM_STATUS_L0_MASK 0x3f +#define LTSSM_STATUS_L0 0x2d + +#define PAB_CTRL 0x0808 +#define AMBA_PIO_ENABLE_SHIFT 0 +#define PEX_PIO_ENABLE_SHIFT 1 +#define PAGE_SEL_SHIFT 13 +#define PAGE_SEL_MASK 0x3f +#define PAGE_LO_MASK 0x3ff +#define PAGE_SEL_OFFSET_SHIFT 10 + +#define PAB_ACTIVITY_STAT 0x81c + +#define PAB_AXI_PIO_CTRL 0x0840 +#define APIO_EN_MASK 0xf + +#define PAB_PEX_PIO_CTRL 0x08c0 +#define PIO_ENABLE_SHIFT 0 + +#define PAB_INTP_AMBA_MISC_ENB 0x0b0c +#define PAB_INTP_AMBA_MISC_STAT 0x0b1c +#define PAB_INTP_RESET BIT(1) +#define PAB_INTP_MSI BIT(3) +#define PAB_INTP_INTA BIT(5) +#define PAB_INTP_INTB BIT(6) +#define PAB_INTP_INTC BIT(7) +#define PAB_INTP_INTD BIT(8) +#define PAB_INTP_PCIE_UE BIT(9) +#define PAB_INTP_IE_PMREDI BIT(29) +#define PAB_INTP_IE_EC BIT(30) +#define PAB_INTP_MSI_MASK PAB_INTP_MSI +#define PAB_INTP_INTX_MASK (PAB_INTP_INTA | PAB_INTP_INTB |\ + PAB_INTP_INTC | PAB_INTP_INTD) + +#define PAB_AXI_AMAP_CTRL(win) PAB_REG_ADDR(0x0ba0, win) +#define WIN_ENABLE_SHIFT 0 +#define WIN_TYPE_SHIFT 1 +#define WIN_TYPE_MASK 0x3 +#define WIN_SIZE_MASK 0xfffffc00 + +#define PAB_EXT_AXI_AMAP_SIZE(win) PAB_EXT_REG_ADDR(0xbaf0, win) + +#define PAB_EXT_AXI_AMAP_AXI_WIN(win) PAB_EXT_REG_ADDR(0x80a0, win) +#define PAB_AXI_AMAP_AXI_WIN(win) PAB_REG_ADDR(0x0ba4, win) +#define AXI_WINDOW_ALIGN_MASK 3 + +#define PAB_AXI_AMAP_PEX_WIN_L(win) PAB_REG_ADDR(0x0ba8, win) +#define PAB_BUS_SHIFT 24 +#define PAB_DEVICE_SHIFT 19 +#define PAB_FUNCTION_SHIFT 16 + +#define PAB_AXI_AMAP_PEX_WIN_H(win) PAB_REG_ADDR(0x0bac, win) +#define PAB_INTP_AXI_PIO_CLASS 0x474 + +#define PAB_PEX_AMAP_CTRL(win) PAB_REG_ADDR(0x4ba0, win) +#define AMAP_CTRL_EN_SHIFT 0 +#define AMAP_CTRL_TYPE_SHIFT 1 +#define AMAP_CTRL_TYPE_MASK 3 + +#define PAB_EXT_PEX_AMAP_SIZEN(win) PAB_EXT_REG_ADDR(0xbef0, win) +#define PAB_EXT_PEX_AMAP_AXI_WIN(win) PAB_EXT_REG_ADDR(0xb4a0, win) +#define PAB_PEX_AMAP_AXI_WIN(win) PAB_REG_ADDR(0x4ba4, win) +#define PAB_PEX_AMAP_PEX_WIN_L(win) PAB_REG_ADDR(0x4ba8, win) +#define PAB_PEX_AMAP_PEX_WIN_H(win) PAB_REG_ADDR(0x4bac, win) + +/* starting offset of INTX bits in status register */ +#define PAB_INTX_START 5 + +/* supported number of MSI interrupts */ +#define PCI_NUM_MSI 16 + +/* MSI registers */ +#define MSI_BASE_LO_OFFSET 0x04 +#define MSI_BASE_HI_OFFSET 0x08 +#define MSI_SIZE_OFFSET 0x0c +#define MSI_ENABLE_OFFSET 0x14 +#define MSI_STATUS_OFFSET 0x18 +#define MSI_DATA_OFFSET 0x20 +#define MSI_ADDR_L_OFFSET 0x24 +#define MSI_ADDR_H_OFFSET 0x28 + +/* outbound and inbound window definitions */ +#define WIN_NUM_0 0 +#define WIN_NUM_1 1 +#define CFG_WINDOW_TYPE 0 +#define IO_WINDOW_TYPE 1 +#define MEM_WINDOW_TYPE 2 +#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024) +#define MAX_PIO_WINDOWS 8 + +/* Parameters for the waiting for link up routine */ +#define LINK_WAIT_MAX_RETRIES 10 +#define LINK_WAIT_MIN 90000 +#define LINK_WAIT_MAX 100000 + +#define PAGED_ADDR_BNDRY 0xc00 +#define OFFSET_TO_PAGE_ADDR(off) \ + ((off & PAGE_LO_MASK) | PAGED_ADDR_BNDRY) +#define OFFSET_TO_PAGE_IDX(off) \ + ((off >> PAGE_SEL_OFFSET_SHIFT) & PAGE_SEL_MASK) + +struct mobiveil_msi { /* MSI information */ + struct mutex lock; /* protect bitmap variable */ + struct irq_domain *dev_domain; + phys_addr_t msi_pages_phys; + int num_of_vectors; + DECLARE_BITMAP(msi_irq_in_use, PCI_NUM_MSI); +}; + +struct mobiveil_pcie; + +struct mobiveil_rp_ops { + int (*interrupt_init)(struct mobiveil_pcie *pcie); +}; + +struct mobiveil_root_port { + void __iomem *config_axi_slave_base; /* endpoint config base */ + struct resource *ob_io_res; + const struct mobiveil_rp_ops *ops; + int irq; + raw_spinlock_t intx_mask_lock; + struct irq_domain *intx_domain; + struct mobiveil_msi msi; + struct pci_host_bridge *bridge; +}; + +struct mobiveil_pab_ops { + bool (*link_up)(struct mobiveil_pcie *pcie); +}; + +struct mobiveil_pcie { + struct platform_device *pdev; + void __iomem *csr_axi_slave_base; /* root port config base */ + void __iomem *apb_csr_base; /* MSI register base */ + phys_addr_t pcie_reg_base; /* Physical PCIe Controller Base */ + int apio_wins; + int ppio_wins; + int ob_wins_configured; /* configured outbound windows */ + int ib_wins_configured; /* configured inbound windows */ + const struct mobiveil_pab_ops *ops; + struct mobiveil_root_port rp; +}; + +int mobiveil_pcie_host_probe(struct mobiveil_pcie *pcie); +int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit); +bool mobiveil_pcie_link_up(struct mobiveil_pcie *pcie); +int mobiveil_bringup_link(struct mobiveil_pcie *pcie); +void program_ob_windows(struct mobiveil_pcie *pcie, int win_num, u64 cpu_addr, + u64 pci_addr, u32 type, u64 size); +void program_ib_windows(struct mobiveil_pcie *pcie, int win_num, u64 cpu_addr, + u64 pci_addr, u32 type, u64 size); +u32 mobiveil_csr_read(struct mobiveil_pcie *pcie, u32 off, size_t size); +void mobiveil_csr_write(struct mobiveil_pcie *pcie, u32 val, u32 off, + size_t size); + +static inline u32 mobiveil_csr_readl(struct mobiveil_pcie *pcie, u32 off) +{ + return mobiveil_csr_read(pcie, off, 0x4); +} + +static inline u16 mobiveil_csr_readw(struct mobiveil_pcie *pcie, u32 off) +{ + return mobiveil_csr_read(pcie, off, 0x2); +} + +static inline u8 mobiveil_csr_readb(struct mobiveil_pcie *pcie, u32 off) +{ + return mobiveil_csr_read(pcie, off, 0x1); +} + + +static inline void mobiveil_csr_writel(struct mobiveil_pcie *pcie, u32 val, + u32 off) +{ + mobiveil_csr_write(pcie, val, off, 0x4); +} + +static inline void mobiveil_csr_writew(struct mobiveil_pcie *pcie, u16 val, + u32 off) +{ + mobiveil_csr_write(pcie, val, off, 0x2); +} + +static inline void mobiveil_csr_writeb(struct mobiveil_pcie *pcie, u8 val, + u32 off) +{ + mobiveil_csr_write(pcie, val, off, 0x1); +} + +#endif /* _PCIE_MOBIVEIL_H */ diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index 750081c1cb48..e34bea1ff0ac 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -8,14 +8,21 @@ * Author: Hezi Shahmoon <hezi.shahmoon@marvell.com> */ +#include <linux/bitfield.h> #include <linux/delay.h> +#include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> +#include <linux/module.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> #include <linux/init.h> +#include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/msi.h> #include <linux/of_address.h> #include <linux/of_pci.h> @@ -25,30 +32,15 @@ /* PCIe core registers */ #define PCIE_CORE_DEV_ID_REG 0x0 #define PCIE_CORE_CMD_STATUS_REG 0x4 -#define PCIE_CORE_CMD_IO_ACCESS_EN BIT(0) -#define PCIE_CORE_CMD_MEM_ACCESS_EN BIT(1) -#define PCIE_CORE_CMD_MEM_IO_REQ_EN BIT(2) #define PCIE_CORE_DEV_REV_REG 0x8 +#define PCIE_CORE_SSDEV_ID_REG 0x2c #define PCIE_CORE_PCIEXP_CAP 0xc0 -#define PCIE_CORE_DEV_CTRL_STATS_REG 0xc8 -#define PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE (0 << 4) -#define PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT 5 -#define PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE (0 << 11) -#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT 12 -#define PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ 0x2 -#define PCIE_CORE_LINK_CTRL_STAT_REG 0xd0 -#define PCIE_CORE_LINK_L0S_ENTRY BIT(0) -#define PCIE_CORE_LINK_TRAINING BIT(5) -#define PCIE_CORE_LINK_WIDTH_SHIFT 20 +#define PCIE_CORE_PCIERR_CAP 0x100 #define PCIE_CORE_ERR_CAPCTL_REG 0x118 #define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX BIT(5) #define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN BIT(6) #define PCIE_CORE_ERR_CAPCTL_ECRC_CHCK BIT(7) #define PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV BIT(8) -#define PCIE_CORE_INT_A_ASSERT_ENABLE 1 -#define PCIE_CORE_INT_B_ASSERT_ENABLE 2 -#define PCIE_CORE_INT_C_ASSERT_ENABLE 3 -#define PCIE_CORE_INT_D_ASSERT_ENABLE 4 /* PIO registers base address and register offsets */ #define PIO_BASE_ADDR 0x4000 #define PIO_CTRL (PIO_BASE_ADDR + 0x0) @@ -59,9 +51,10 @@ #define PIO_COMPLETION_STATUS_MASK GENMASK(9, 7) #define PIO_COMPLETION_STATUS_OK 0 #define PIO_COMPLETION_STATUS_UR 1 -#define PIO_COMPLETION_STATUS_CRS 2 +#define PIO_COMPLETION_STATUS_RRS 2 #define PIO_COMPLETION_STATUS_CA 4 -#define PIO_NON_POSTED_REQ BIT(0) +#define PIO_NON_POSTED_REQ BIT(10) +#define PIO_ERR_STATUS BIT(11) #define PIO_ADDR_LS (PIO_BASE_ADDR + 0x8) #define PIO_ADDR_MS (PIO_BASE_ADDR + 0xc) #define PIO_WR_DATA (PIO_BASE_ADDR + 0x10) @@ -100,34 +93,126 @@ #define PCIE_CORE_CTRL2_STRICT_ORDER_ENABLE BIT(5) #define PCIE_CORE_CTRL2_OB_WIN_ENABLE BIT(6) #define PCIE_CORE_CTRL2_MSI_ENABLE BIT(10) +#define PCIE_CORE_REF_CLK_REG (CONTROL_BASE_ADDR + 0x14) +#define PCIE_CORE_REF_CLK_TX_ENABLE BIT(1) +#define PCIE_CORE_REF_CLK_RX_ENABLE BIT(2) #define PCIE_MSG_LOG_REG (CONTROL_BASE_ADDR + 0x30) #define PCIE_ISR0_REG (CONTROL_BASE_ADDR + 0x40) #define PCIE_MSG_PM_PME_MASK BIT(7) #define PCIE_ISR0_MASK_REG (CONTROL_BASE_ADDR + 0x44) #define PCIE_ISR0_MSI_INT_PENDING BIT(24) +#define PCIE_ISR0_CORR_ERR BIT(11) +#define PCIE_ISR0_NFAT_ERR BIT(12) +#define PCIE_ISR0_FAT_ERR BIT(13) +#define PCIE_ISR0_ERR_MASK GENMASK(13, 11) #define PCIE_ISR0_INTX_ASSERT(val) BIT(16 + (val)) #define PCIE_ISR0_INTX_DEASSERT(val) BIT(20 + (val)) -#define PCIE_ISR0_ALL_MASK GENMASK(26, 0) +#define PCIE_ISR0_ALL_MASK GENMASK(31, 0) #define PCIE_ISR1_REG (CONTROL_BASE_ADDR + 0x48) #define PCIE_ISR1_MASK_REG (CONTROL_BASE_ADDR + 0x4C) #define PCIE_ISR1_POWER_STATE_CHANGE BIT(4) #define PCIE_ISR1_FLUSH BIT(5) #define PCIE_ISR1_INTX_ASSERT(val) BIT(8 + (val)) -#define PCIE_ISR1_ALL_MASK GENMASK(11, 4) +#define PCIE_ISR1_ALL_MASK GENMASK(31, 0) #define PCIE_MSI_ADDR_LOW_REG (CONTROL_BASE_ADDR + 0x50) #define PCIE_MSI_ADDR_HIGH_REG (CONTROL_BASE_ADDR + 0x54) #define PCIE_MSI_STATUS_REG (CONTROL_BASE_ADDR + 0x58) #define PCIE_MSI_MASK_REG (CONTROL_BASE_ADDR + 0x5C) +#define PCIE_MSI_ALL_MASK GENMASK(31, 0) #define PCIE_MSI_PAYLOAD_REG (CONTROL_BASE_ADDR + 0x9C) +#define PCIE_MSI_DATA_MASK GENMASK(15, 0) + +/* PCIe window configuration */ +#define OB_WIN_BASE_ADDR 0x4c00 +#define OB_WIN_BLOCK_SIZE 0x20 +#define OB_WIN_COUNT 8 +#define OB_WIN_REG_ADDR(win, offset) (OB_WIN_BASE_ADDR + \ + OB_WIN_BLOCK_SIZE * (win) + \ + (offset)) +#define OB_WIN_MATCH_LS(win) OB_WIN_REG_ADDR(win, 0x00) +#define OB_WIN_ENABLE BIT(0) +#define OB_WIN_MATCH_MS(win) OB_WIN_REG_ADDR(win, 0x04) +#define OB_WIN_REMAP_LS(win) OB_WIN_REG_ADDR(win, 0x08) +#define OB_WIN_REMAP_MS(win) OB_WIN_REG_ADDR(win, 0x0c) +#define OB_WIN_MASK_LS(win) OB_WIN_REG_ADDR(win, 0x10) +#define OB_WIN_MASK_MS(win) OB_WIN_REG_ADDR(win, 0x14) +#define OB_WIN_ACTIONS(win) OB_WIN_REG_ADDR(win, 0x18) +#define OB_WIN_DEFAULT_ACTIONS (OB_WIN_ACTIONS(OB_WIN_COUNT-1) + 0x4) +#define OB_WIN_FUNC_NUM_MASK GENMASK(31, 24) +#define OB_WIN_FUNC_NUM_SHIFT 24 +#define OB_WIN_FUNC_NUM_ENABLE BIT(23) +#define OB_WIN_BUS_NUM_BITS_MASK GENMASK(22, 20) +#define OB_WIN_BUS_NUM_BITS_SHIFT 20 +#define OB_WIN_MSG_CODE_ENABLE BIT(22) +#define OB_WIN_MSG_CODE_MASK GENMASK(21, 14) +#define OB_WIN_MSG_CODE_SHIFT 14 +#define OB_WIN_MSG_PAYLOAD_LEN BIT(12) +#define OB_WIN_ATTR_ENABLE BIT(11) +#define OB_WIN_ATTR_TC_MASK GENMASK(10, 8) +#define OB_WIN_ATTR_TC_SHIFT 8 +#define OB_WIN_ATTR_RELAXED BIT(7) +#define OB_WIN_ATTR_NOSNOOP BIT(6) +#define OB_WIN_ATTR_POISON BIT(5) +#define OB_WIN_ATTR_IDO BIT(4) +#define OB_WIN_TYPE_MASK GENMASK(3, 0) +#define OB_WIN_TYPE_SHIFT 0 +#define OB_WIN_TYPE_MEM 0x0 +#define OB_WIN_TYPE_IO 0x4 +#define OB_WIN_TYPE_CONFIG_TYPE0 0x8 +#define OB_WIN_TYPE_CONFIG_TYPE1 0x9 +#define OB_WIN_TYPE_MSG 0xc /* LMI registers base address and register offsets */ #define LMI_BASE_ADDR 0x6000 #define CFG_REG (LMI_BASE_ADDR + 0x0) #define LTSSM_SHIFT 24 #define LTSSM_MASK 0x3f -#define LTSSM_L0 0x10 #define RC_BAR_CONFIG 0x300 +/* LTSSM values in CFG_REG */ +enum { + LTSSM_DETECT_QUIET = 0x0, + LTSSM_DETECT_ACTIVE = 0x1, + LTSSM_POLLING_ACTIVE = 0x2, + LTSSM_POLLING_COMPLIANCE = 0x3, + LTSSM_POLLING_CONFIGURATION = 0x4, + LTSSM_CONFIG_LINKWIDTH_START = 0x5, + LTSSM_CONFIG_LINKWIDTH_ACCEPT = 0x6, + LTSSM_CONFIG_LANENUM_ACCEPT = 0x7, + LTSSM_CONFIG_LANENUM_WAIT = 0x8, + LTSSM_CONFIG_COMPLETE = 0x9, + LTSSM_CONFIG_IDLE = 0xa, + LTSSM_RECOVERY_RCVR_LOCK = 0xb, + LTSSM_RECOVERY_SPEED = 0xc, + LTSSM_RECOVERY_RCVR_CFG = 0xd, + LTSSM_RECOVERY_IDLE = 0xe, + LTSSM_L0 = 0x10, + LTSSM_RX_L0S_ENTRY = 0x11, + LTSSM_RX_L0S_IDLE = 0x12, + LTSSM_RX_L0S_FTS = 0x13, + LTSSM_TX_L0S_ENTRY = 0x14, + LTSSM_TX_L0S_IDLE = 0x15, + LTSSM_TX_L0S_FTS = 0x16, + LTSSM_L1_ENTRY = 0x17, + LTSSM_L1_IDLE = 0x18, + LTSSM_L2_IDLE = 0x19, + LTSSM_L2_TRANSMIT_WAKE = 0x1a, + LTSSM_DISABLED = 0x20, + LTSSM_LOOPBACK_ENTRY_MASTER = 0x21, + LTSSM_LOOPBACK_ACTIVE_MASTER = 0x22, + LTSSM_LOOPBACK_EXIT_MASTER = 0x23, + LTSSM_LOOPBACK_ENTRY_SLAVE = 0x24, + LTSSM_LOOPBACK_ACTIVE_SLAVE = 0x25, + LTSSM_LOOPBACK_EXIT_SLAVE = 0x26, + LTSSM_HOT_RESET = 0x27, + LTSSM_RECOVERY_EQUALIZATION_PHASE0 = 0x28, + LTSSM_RECOVERY_EQUALIZATION_PHASE1 = 0x29, + LTSSM_RECOVERY_EQUALIZATION_PHASE2 = 0x2a, + LTSSM_RECOVERY_EQUALIZATION_PHASE3 = 0x2b, +}; + +#define VENDOR_ID_REG (LMI_BASE_ADDR + 0x44) + /* PCIe core controller registers */ #define CTRL_CORE_BASE_ADDR 0x18000 #define CTRL_CONFIG_REG (CTRL_CORE_BASE_ADDR + 0x0) @@ -158,7 +243,7 @@ #define PCIE_IRQ_MSI_INT2_DET BIT(21) #define PCIE_IRQ_RC_DBELL_DET BIT(22) #define PCIE_IRQ_EP_STATUS BIT(23) -#define PCIE_IRQ_ALL_MASK 0xfff0fb +#define PCIE_IRQ_ALL_MASK GENMASK(31, 0) #define PCIE_IRQ_ENABLE_INTS_MASK PCIE_IRQ_CORE_INT /* Transaction types */ @@ -167,38 +252,41 @@ #define PCIE_CONFIG_WR_TYPE0 0xa #define PCIE_CONFIG_WR_TYPE1 0xb -#define PCIE_CONF_BUS(bus) (((bus) & 0xff) << 20) -#define PCIE_CONF_DEV(dev) (((dev) & 0x1f) << 15) -#define PCIE_CONF_FUNC(fun) (((fun) & 0x7) << 12) -#define PCIE_CONF_REG(reg) ((reg) & 0xffc) -#define PCIE_CONF_ADDR(bus, devfn, where) \ - (PCIE_CONF_BUS(bus) | PCIE_CONF_DEV(PCI_SLOT(devfn)) | \ - PCIE_CONF_FUNC(PCI_FUNC(devfn)) | PCIE_CONF_REG(where)) - -#define PIO_TIMEOUT_MS 1 +#define PIO_RETRY_CNT 750000 /* 1.5 s */ +#define PIO_RETRY_DELAY 2 /* 2 us*/ #define LINK_WAIT_MAX_RETRIES 10 #define LINK_WAIT_USLEEP_MIN 90000 #define LINK_WAIT_USLEEP_MAX 100000 +#define RETRAIN_WAIT_MAX_RETRIES 10 +#define RETRAIN_WAIT_USLEEP_US 2000 #define MSI_IRQ_NUM 32 +#define CFG_RD_RRS_VAL 0xffff0001 + struct advk_pcie { struct platform_device *pdev; void __iomem *base; - struct list_head resources; + struct { + phys_addr_t match; + phys_addr_t remap; + phys_addr_t mask; + u32 actions; + } wins[OB_WIN_COUNT]; + u8 wins_count; + struct irq_domain *rp_irq_domain; struct irq_domain *irq_domain; struct irq_chip irq_chip; - struct irq_domain *msi_domain; + raw_spinlock_t irq_lock; struct irq_domain *msi_inner_domain; - struct irq_chip msi_bottom_irq_chip; - struct irq_chip msi_irq_chip; - struct msi_domain_info msi_domain_info; + raw_spinlock_t msi_irq_lock; DECLARE_BITMAP(msi_used, MSI_IRQ_NUM); struct mutex msi_used_lock; - u16 msi_msg; - int root_bus_nr; + int link_gen; struct pci_bridge_emul bridge; + struct gpio_desc *reset_gpio; + struct phy *phy; }; static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg) @@ -211,37 +299,198 @@ static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg) return readl(pcie->base + reg); } -static int advk_pcie_link_up(struct advk_pcie *pcie) +static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie) { - u32 val, ltssm_state; + u32 val; + u8 ltssm_state; val = advk_readl(pcie, CFG_REG); ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK; - return ltssm_state >= LTSSM_L0; + return ltssm_state; +} + +static inline bool advk_pcie_link_up(struct advk_pcie *pcie) +{ + /* check if LTSSM is in normal operation - some L* state */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED; +} + +static inline bool advk_pcie_link_active(struct advk_pcie *pcie) +{ + /* + * According to PCIe Base specification 3.0, Table 4-14: Link + * Status Mapped to the LTSSM, and 4.2.6.3.6 Configuration.Idle + * is Link Up mapped to LTSSM Configuration.Idle, Recovery, L0, + * L0s, L1 and L2 states. And according to 3.2.1. Data Link + * Control and Management State Machine Rules is DL Up status + * reported in DL Active state. + */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ltssm_state >= LTSSM_CONFIG_IDLE && ltssm_state < LTSSM_DISABLED; +} + +static inline bool advk_pcie_link_training(struct advk_pcie *pcie) +{ + /* + * According to PCIe Base specification 3.0, Table 4-14: Link + * Status Mapped to the LTSSM is Link Training mapped to LTSSM + * Configuration and Recovery states. + */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START && + ltssm_state < LTSSM_L0) || + (ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 && + ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3)); } static int advk_pcie_wait_for_link(struct advk_pcie *pcie) { - struct device *dev = &pcie->pdev->dev; int retries; /* check if the link is up or not */ for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { - if (advk_pcie_link_up(pcie)) { - dev_info(dev, "link up\n"); + if (advk_pcie_link_up(pcie)) return 0; - } usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); } - dev_err(dev, "link never came up\n"); return -ETIMEDOUT; } +static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie) +{ + size_t retries; + + for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) { + if (advk_pcie_link_training(pcie)) + break; + udelay(RETRAIN_WAIT_USLEEP_US); + } +} + +static void advk_pcie_issue_perst(struct advk_pcie *pcie) +{ + if (!pcie->reset_gpio) + return; + + /* 10ms delay is needed for some cards */ + dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n"); + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + usleep_range(10000, 11000); + gpiod_set_value_cansleep(pcie->reset_gpio, 0); +} + +static void advk_pcie_train_link(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + u32 reg; + int ret; + + /* + * Setup PCIe rev / gen compliance based on device tree property + * 'max-link-speed' which also forces maximal link speed. + */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg &= ~PCIE_GEN_SEL_MSK; + if (pcie->link_gen == 3) + reg |= SPEED_GEN_3; + else if (pcie->link_gen == 2) + reg |= SPEED_GEN_2; + else + reg |= SPEED_GEN_1; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Set maximal link speed value also into PCIe Link Control 2 register. + * Armada 3700 Functional Specification says that default value is based + * on SPEED_GEN but tests showed that default value is always 8.0 GT/s. + */ + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + reg &= ~PCI_EXP_LNKCTL2_TLS; + if (pcie->link_gen == 3) + reg |= PCI_EXP_LNKCTL2_TLS_8_0GT; + else if (pcie->link_gen == 2) + reg |= PCI_EXP_LNKCTL2_TLS_5_0GT; + else + reg |= PCI_EXP_LNKCTL2_TLS_2_5GT; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + + /* Enable link training after selecting PCIe generation */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg |= LINK_TRAINING_EN; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Reset PCIe card via PERST# signal. Some cards are not detected + * during link training when they are in some non-initial state. + */ + advk_pcie_issue_perst(pcie); + + /* + * PERST# signal could have been asserted by pinctrl subsystem before + * probe() callback has been called or issued explicitly by reset gpio + * function advk_pcie_issue_perst(), making the endpoint going into + * fundamental reset. As required by PCI Express spec (PCI Express + * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1 + * Conventional Reset) a delay for at least 100ms after such a reset + * before sending a Configuration Request to the device is needed. + * So wait until PCIe link is up. Function advk_pcie_wait_for_link() + * waits for link at least 900ms. + */ + ret = advk_pcie_wait_for_link(pcie); + if (ret < 0) + dev_err(dev, "link never came up\n"); + else + dev_info(dev, "link up\n"); +} + +/* + * Set PCIe address window register which could be used for memory + * mapping. + */ +static void advk_pcie_set_ob_win(struct advk_pcie *pcie, u8 win_num, + phys_addr_t match, phys_addr_t remap, + phys_addr_t mask, u32 actions) +{ + advk_writel(pcie, OB_WIN_ENABLE | + lower_32_bits(match), OB_WIN_MATCH_LS(win_num)); + advk_writel(pcie, upper_32_bits(match), OB_WIN_MATCH_MS(win_num)); + advk_writel(pcie, lower_32_bits(remap), OB_WIN_REMAP_LS(win_num)); + advk_writel(pcie, upper_32_bits(remap), OB_WIN_REMAP_MS(win_num)); + advk_writel(pcie, lower_32_bits(mask), OB_WIN_MASK_LS(win_num)); + advk_writel(pcie, upper_32_bits(mask), OB_WIN_MASK_MS(win_num)); + advk_writel(pcie, actions, OB_WIN_ACTIONS(win_num)); +} + +static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num) +{ + advk_writel(pcie, 0, OB_WIN_MATCH_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_MATCH_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_REMAP_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_REMAP_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_MASK_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_MASK_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_ACTIONS(win_num)); +} + static void advk_pcie_setup_hw(struct advk_pcie *pcie) { + phys_addr_t msi_addr; u32 reg; + int i; + + /* + * Configure PCIe Reference clock. Direction is from the PCIe + * controller to the endpoint card, so enable transmitting of + * Reference clock differential signal off-chip and disable + * receiving off-chip differential signal. + */ + reg = advk_readl(pcie, PCIE_CORE_REF_CLK_REG); + reg |= PCIE_CORE_REF_CLK_TX_ENABLE; + reg &= ~PCIE_CORE_REF_CLK_RX_ENABLE; + advk_writel(pcie, reg, PCIE_CORE_REF_CLK_REG); /* Set to Direct mode */ reg = advk_readl(pcie, CTRL_CONFIG_REG); @@ -254,6 +503,41 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) reg |= (IS_RC_MSK << IS_RC_SHIFT); advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + /* + * Replace incorrect PCI vendor id value 0x1b4b by correct value 0x11ab. + * VENDOR_ID_REG contains vendor id in low 16 bits and subsystem vendor + * id in high 16 bits. Updating this register changes readback value of + * read-only vendor id bits in PCIE_CORE_DEV_ID_REG register. Workaround + * for erratum 4.1: "The value of device and vendor ID is incorrect". + */ + reg = (PCI_VENDOR_ID_MARVELL << 16) | PCI_VENDOR_ID_MARVELL; + advk_writel(pcie, reg, VENDOR_ID_REG); + + /* + * Change Class Code of PCI Bridge device to PCI Bridge (0x600400), + * because the default value is Mass storage controller (0x010400). + * + * Note that this Aardvark PCI Bridge does not have compliant Type 1 + * Configuration Space and it even cannot be accessed via Aardvark's + * PCI config space access method. Something like config space is + * available in internal Aardvark registers starting at offset 0x0 + * and is reported as Type 0. In range 0x10 - 0x34 it has totally + * different registers. + * + * Therefore driver uses emulation of PCI Bridge which emulates + * access to configuration space via internal Aardvark registers or + * emulated configuration buffer. + */ + reg = advk_readl(pcie, PCIE_CORE_DEV_REV_REG); + reg &= ~0xffffff00; + reg |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + advk_writel(pcie, reg, PCIE_CORE_DEV_REV_REG); + + /* Disable Root Bridge I/O space, memory space and bus mastering */ + reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); + reg &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG); + /* Set Advanced Error Capabilities and Control PF0 register */ reg = PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX | PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN | @@ -261,35 +545,31 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV; advk_writel(pcie, reg, PCIE_CORE_ERR_CAPCTL_REG); - /* Set PCIe Device Control and Status 1 PF0 register */ - reg = PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE | - (7 << PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT) | - PCIE_CORE_DEV_CTRL_STATS_SNOOP_DISABLE | - (PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SZ << - PCIE_CORE_DEV_CTRL_STATS_MAX_RD_REQ_SIZE_SHIFT); - advk_writel(pcie, reg, PCIE_CORE_DEV_CTRL_STATS_REG); + /* Set PCIe Device Control register */ + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); + reg &= ~PCI_EXP_DEVCTL_RELAX_EN; + reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN; + reg &= ~PCI_EXP_DEVCTL_PAYLOAD; + reg &= ~PCI_EXP_DEVCTL_READRQ; + reg |= PCI_EXP_DEVCTL_PAYLOAD_512B; + reg |= PCI_EXP_DEVCTL_READRQ_512B; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); /* Program PCIe Control 2 to disable strict ordering */ reg = PCIE_CORE_CTRL2_RESERVED | PCIE_CORE_CTRL2_TD_ENABLE; advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); - /* Set GEN2 */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg &= ~PCIE_GEN_SEL_MSK; - reg |= SPEED_GEN_2; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* Set lane X1 */ reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); reg &= ~LANE_CNT_MSK; reg |= LANE_COUNT_1; advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); - /* Enable link training */ - reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); - reg |= LINK_TRAINING_EN; - advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + /* Set MSI address */ + msi_addr = virt_to_phys(pcie); + advk_writel(pcie, lower_32_bits(msi_addr), PCIE_MSI_ADDR_LOW_REG); + advk_writel(pcie, upper_32_bits(msi_addr), PCIE_MSI_ADDR_HIGH_REG); /* Enable MSI */ reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG); @@ -297,109 +577,279 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie) advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); /* Clear all interrupts */ + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_STATUS_REG); advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_REG); advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG); advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG); - /* Disable All ISR0/1 Sources */ - reg = PCIE_ISR0_ALL_MASK; + /* Disable All ISR0/1 and MSI Sources */ + advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_MASK_REG); + advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG); + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG); + + /* Unmask summary MSI interrupt */ + reg = advk_readl(pcie, PCIE_ISR0_MASK_REG); reg &= ~PCIE_ISR0_MSI_INT_PENDING; advk_writel(pcie, reg, PCIE_ISR0_MASK_REG); - advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG); - - /* Unmask all MSI's */ - advk_writel(pcie, 0, PCIE_MSI_MASK_REG); + /* Unmask PME interrupt for processing of PME requester */ + reg = advk_readl(pcie, PCIE_ISR0_MASK_REG); + reg &= ~PCIE_MSG_PM_PME_MASK; + advk_writel(pcie, reg, PCIE_ISR0_MASK_REG); /* Enable summary interrupt for GIC SPI source */ reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK); advk_writel(pcie, reg, HOST_CTRL_INT_MASK_REG); + /* + * Enable AXI address window location generation: + * When it is enabled, the default outbound window + * configurations (Default User Field: 0xD0074CFC) + * are used to transparent address translation for + * the outbound transactions. Thus, PCIe address + * windows are not required for transparent memory + * access when default outbound window configuration + * is set for memory access. + */ reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG); reg |= PCIE_CORE_CTRL2_OB_WIN_ENABLE; advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); - /* Bypass the address window mapping for PIO */ + /* + * Set memory access in Default User Field so it + * is not required to configure PCIe address for + * transparent memory access. + */ + advk_writel(pcie, OB_WIN_TYPE_MEM, OB_WIN_DEFAULT_ACTIONS); + + /* + * Bypass the address window mapping for PIO: + * Since PIO access already contains all required + * info over AXI interface by PIO registers, the + * address window is not required. + */ reg = advk_readl(pcie, PIO_CTRL); reg |= PIO_CTRL_ADDR_WIN_DISABLE; advk_writel(pcie, reg, PIO_CTRL); - /* Start link training */ - reg = advk_readl(pcie, PCIE_CORE_LINK_CTRL_STAT_REG); - reg |= PCIE_CORE_LINK_TRAINING; - advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); - - advk_pcie_wait_for_link(pcie); - - reg = PCIE_CORE_LINK_L0S_ENTRY | - (1 << PCIE_CORE_LINK_WIDTH_SHIFT); - advk_writel(pcie, reg, PCIE_CORE_LINK_CTRL_STAT_REG); - - reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); - reg |= PCIE_CORE_CMD_MEM_ACCESS_EN | - PCIE_CORE_CMD_IO_ACCESS_EN | - PCIE_CORE_CMD_MEM_IO_REQ_EN; - advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG); + /* + * Configure PCIe address windows for non-memory or + * non-transparent access as by default PCIe uses + * transparent memory access. + */ + for (i = 0; i < pcie->wins_count; i++) + advk_pcie_set_ob_win(pcie, i, + pcie->wins[i].match, pcie->wins[i].remap, + pcie->wins[i].mask, pcie->wins[i].actions); + + /* Disable remaining PCIe outbound windows */ + for (i = pcie->wins_count; i < OB_WIN_COUNT; i++) + advk_pcie_disable_ob_win(pcie, i); + + advk_pcie_train_link(pcie); } -static void advk_pcie_check_pio_status(struct advk_pcie *pcie) +static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_rrs, u32 *val) { struct device *dev = &pcie->pdev->dev; u32 reg; unsigned int status; char *strcomp_status, *str_posted; + int ret; reg = advk_readl(pcie, PIO_STAT); status = (reg & PIO_COMPLETION_STATUS_MASK) >> PIO_COMPLETION_STATUS_SHIFT; - if (!status) - return; - + /* + * According to HW spec, the PIO status check sequence as below: + * 1) even if COMPLETION_STATUS(bit9:7) indicates successful, + * it still needs to check Error Status(bit11), only when this bit + * indicates no error happen, the operation is successful. + * 2) value Unsupported Request(1) of COMPLETION_STATUS(bit9:7) only + * means a PIO write error, and for PIO read it is successful with + * a read value of 0xFFFFFFFF. + * 3) value Config Request Retry Status(RRS) of COMPLETION_STATUS(bit9:7) + * only means a PIO write error, and for PIO read it is successful + * with a read value of 0xFFFF0001. + * 4) value Completer Abort (CA) of COMPLETION_STATUS(bit9:7) means + * error for both PIO read and PIO write operation. + * 5) other errors are indicated as 'unknown'. + */ switch (status) { + case PIO_COMPLETION_STATUS_OK: + if (reg & PIO_ERR_STATUS) { + strcomp_status = "COMP_ERR"; + ret = -EFAULT; + break; + } + /* Get the read result */ + if (val) + *val = advk_readl(pcie, PIO_RD_DATA); + /* No error */ + strcomp_status = NULL; + ret = 0; + break; case PIO_COMPLETION_STATUS_UR: strcomp_status = "UR"; + ret = -EOPNOTSUPP; break; - case PIO_COMPLETION_STATUS_CRS: - strcomp_status = "CRS"; + case PIO_COMPLETION_STATUS_RRS: + if (allow_rrs && val) { + /* PCIe r6.0, sec 2.3.2, says: + * If Configuration RRS Software Visibility is enabled: + * For a Configuration Read Request that includes both + * bytes of the Vendor ID field of a device Function's + * Configuration Space Header, the Root Complex must + * complete the Request to the host by returning a + * read-data value of 0001h for the Vendor ID field and + * all '1's for any additional bytes included in the + * request. + * + * So RRS in this case is not an error status. + */ + *val = CFG_RD_RRS_VAL; + strcomp_status = NULL; + ret = 0; + break; + } + /* PCIe r6.0, sec 2.3.2, says: + * If RRS Software Visibility is not enabled, the Root Complex + * must re-issue the Configuration Request as a new Request. + * If RRS Software Visibility is enabled: For a Configuration + * Write Request or for any other Configuration Read Request, + * the Root Complex must re-issue the Configuration Request as + * a new Request. + * A Root Complex implementation may choose to limit the number + * of Configuration Request/RRS Completion Status loops before + * determining that something is wrong with the target of the + * Request and taking appropriate action, e.g., complete the + * Request to the host as a failed transaction. + * + * So return -EAGAIN and caller (pci-aardvark.c driver) will + * re-issue request again up to the PIO_RETRY_CNT retries. + */ + strcomp_status = "RRS"; + ret = -EAGAIN; break; case PIO_COMPLETION_STATUS_CA: strcomp_status = "CA"; + ret = -ECANCELED; break; default: strcomp_status = "Unknown"; + ret = -EINVAL; break; } + if (!strcomp_status) + return ret; + if (reg & PIO_NON_POSTED_REQ) str_posted = "Non-posted"; else str_posted = "Posted"; - dev_err(dev, "%s PIO Response Status: %s, %#x @ %#x\n", + dev_dbg(dev, "%s PIO Response Status: %s, %#x @ %#x\n", str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS)); + + return ret; } static int advk_pcie_wait_pio(struct advk_pcie *pcie) { struct device *dev = &pcie->pdev->dev; - unsigned long timeout; - - timeout = jiffies + msecs_to_jiffies(PIO_TIMEOUT_MS); + int i; - while (time_before(jiffies, timeout)) { + for (i = 1; i <= PIO_RETRY_CNT; i++) { u32 start, isr; start = advk_readl(pcie, PIO_START); isr = advk_readl(pcie, PIO_ISR); if (!start && isr) - return 0; + return i; + udelay(PIO_RETRY_DELAY); } - dev_err(dev, "config read/write timed out\n"); + dev_err(dev, "PIO read/write transfer time out\n"); return -ETIMEDOUT; } +static pci_bridge_emul_read_status_t +advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + case PCI_COMMAND: + *value = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); + return PCI_BRIDGE_EMUL_HANDLED; + + case PCI_INTERRUPT_LINE: { + /* + * From the whole 32bit register we support reading from HW only + * two bits: PCI_BRIDGE_CTL_BUS_RESET and PCI_BRIDGE_CTL_SERR. + * Other bits are retrieved only from emulated config buffer. + */ + __le32 *cfgspace = (__le32 *)&bridge->conf; + u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]); + if (advk_readl(pcie, PCIE_ISR0_MASK_REG) & PCIE_ISR0_ERR_MASK) + val &= ~(PCI_BRIDGE_CTL_SERR << 16); + else + val |= PCI_BRIDGE_CTL_SERR << 16; + if (advk_readl(pcie, PCIE_CORE_CTRL1_REG) & HOT_RESET_GEN) + val |= PCI_BRIDGE_CTL_BUS_RESET << 16; + else + val &= ~(PCI_BRIDGE_CTL_BUS_RESET << 16); + *value = val; + return PCI_BRIDGE_EMUL_HANDLED; + } + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } +} + +static void +advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + case PCI_COMMAND: + advk_writel(pcie, new, PCIE_CORE_CMD_STATUS_REG); + break; + + case PCI_INTERRUPT_LINE: + /* + * According to Figure 6-3: Pseudo Logic Diagram for Error + * Message Controls in PCIe base specification, SERR# Enable bit + * in Bridge Control register enable receiving of ERR_* messages + */ + if (mask & (PCI_BRIDGE_CTL_SERR << 16)) { + u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG); + if (new & (PCI_BRIDGE_CTL_SERR << 16)) + val &= ~PCIE_ISR0_ERR_MASK; + else + val |= PCIE_ISR0_ERR_MASK; + advk_writel(pcie, val, PCIE_ISR0_MASK_REG); + } + if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) { + u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG); + if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16)) + val |= HOT_RESET_GEN; + else + val &= ~HOT_RESET_GEN; + advk_writel(pcie, val, PCIE_CORE_CTRL1_REG); + } + break; + + default: + break; + } +} static pci_bridge_emul_read_status_t advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, @@ -409,30 +859,46 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, switch (reg) { - case PCI_EXP_SLTCTL: - *value = PCI_EXP_SLTSTA_PDS << 16; - return PCI_BRIDGE_EMUL_HANDLED; - - case PCI_EXP_RTCTL: { - u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG); - *value = (val & PCIE_MSG_PM_PME_MASK) ? PCI_EXP_RTCTL_PMEIE : 0; + /* + * PCI_EXP_SLTCAP, PCI_EXP_SLTCTL, PCI_EXP_RTCTL and PCI_EXP_RTSTA are + * also supported, but do not need to be handled here, because their + * values are stored in emulated config space buffer, and we read them + * from there when needed. + */ + + case PCI_EXP_LNKCAP: { + u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); + /* + * PCI_EXP_LNKCAP_DLLLARC bit is hardwired in aardvark HW to 0. + * But support for PCI_EXP_LNKSTA_DLLLA is emulated via ltssm + * state so explicitly enable PCI_EXP_LNKCAP_DLLLARC flag. + */ + val |= PCI_EXP_LNKCAP_DLLLARC; + *value = val; return PCI_BRIDGE_EMUL_HANDLED; } - case PCI_EXP_RTSTA: { - u32 isr0 = advk_readl(pcie, PCIE_ISR0_REG); - u32 msglog = advk_readl(pcie, PCIE_MSG_LOG_REG); - *value = (isr0 & PCIE_MSG_PM_PME_MASK) << 16 | (msglog >> 16); + case PCI_EXP_LNKCTL: { + /* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */ + u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) & + ~(PCI_EXP_LNKSTA_LT << 16); + if (advk_pcie_link_training(pcie)) + val |= (PCI_EXP_LNKSTA_LT << 16); + if (advk_pcie_link_active(pcie)) + val |= (PCI_EXP_LNKSTA_DLLLA << 16); + *value = val; return PCI_BRIDGE_EMUL_HANDLED; } - case PCI_CAP_LIST_ID: case PCI_EXP_DEVCAP: case PCI_EXP_DEVCTL: - case PCI_EXP_LNKCAP: - case PCI_EXP_LNKCTL: + case PCI_EXP_DEVCAP2: + case PCI_EXP_DEVCTL2: + case PCI_EXP_LNKCAP2: + case PCI_EXP_LNKCTL2: *value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); return PCI_BRIDGE_EMUL_HANDLED; + default: return PCI_BRIDGE_EMUL_NOT_HANDLED; } @@ -446,19 +912,106 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, struct advk_pcie *pcie = bridge->data; switch (reg) { - case PCI_EXP_DEVCTL: case PCI_EXP_LNKCTL: advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); + if (new & PCI_EXP_LNKCTL_RL) + advk_pcie_wait_for_retrain(pcie); + break; + + case PCI_EXP_RTCTL: { + u16 rootctl = le16_to_cpu(bridge->pcie_conf.rootctl); + /* Only emulation of PMEIE and RRS_SVE bits is provided */ + rootctl &= PCI_EXP_RTCTL_PMEIE | PCI_EXP_RTCTL_RRS_SVE; + bridge->pcie_conf.rootctl = cpu_to_le16(rootctl); + break; + } + + /* + * PCI_EXP_RTSTA is also supported, but does not need to be handled + * here, because its value is stored in emulated config space buffer, + * and we write it there when needed. + */ + + case PCI_EXP_DEVCTL: + case PCI_EXP_DEVCTL2: + case PCI_EXP_LNKCTL2: + advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); break; - case PCI_EXP_RTCTL: - new = (new & PCI_EXP_RTCTL_PMEIE) << 3; - advk_writel(pcie, new, PCIE_ISR0_MASK_REG); + default: break; + } +} + +static pci_bridge_emul_read_status_t +advk_pci_bridge_emul_ext_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct advk_pcie *pcie = bridge->data; - case PCI_EXP_RTSTA: - new = (new & PCI_EXP_RTSTA_PME) >> 9; - advk_writel(pcie, new, PCIE_ISR0_REG); + switch (reg) { + case 0: + *value = advk_readl(pcie, PCIE_CORE_PCIERR_CAP + reg); + + /* + * PCI_EXT_CAP_NEXT bits are set to offset 0x150, but Armada + * 3700 Functional Specification does not document registers + * at those addresses. + * + * Thus we clear PCI_EXT_CAP_NEXT bits to make Advanced Error + * Reporting Capability header the last Extended Capability. + * If we obtain documentation for those registers in the + * future, this can be changed. + */ + *value &= 0x000fffff; + return PCI_BRIDGE_EMUL_HANDLED; + + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_STATUS: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG + 0: + case PCI_ERR_HEADER_LOG + 4: + case PCI_ERR_HEADER_LOG + 8: + case PCI_ERR_HEADER_LOG + 12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_STATUS: + case PCI_ERR_ROOT_ERR_SRC: + *value = advk_readl(pcie, PCIE_CORE_PCIERR_CAP + reg); + return PCI_BRIDGE_EMUL_HANDLED; + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } +} + +static void +advk_pci_bridge_emul_ext_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + /* These are W1C registers, so clear other bits */ + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_COR_STATUS: + case PCI_ERR_ROOT_STATUS: + new &= mask; + fallthrough; + + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG + 0: + case PCI_ERR_HEADER_LOG + 4: + case PCI_ERR_HEADER_LOG + 8: + case PCI_ERR_HEADER_LOG + 12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_ERR_SRC: + advk_writel(pcie, new, PCIE_CORE_PCIERR_CAP + reg); break; default: @@ -466,106 +1019,207 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, } } -struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = { +static const struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = { + .read_base = advk_pci_bridge_emul_base_conf_read, + .write_base = advk_pci_bridge_emul_base_conf_write, .read_pcie = advk_pci_bridge_emul_pcie_conf_read, .write_pcie = advk_pci_bridge_emul_pcie_conf_write, + .read_ext = advk_pci_bridge_emul_ext_conf_read, + .write_ext = advk_pci_bridge_emul_ext_conf_write, }; /* * Initialize the configuration space of the PCI-to-PCI bridge * associated with the given PCIe interface. */ -static void advk_sw_pci_bridge_init(struct advk_pcie *pcie) +static int advk_sw_pci_bridge_init(struct advk_pcie *pcie) { struct pci_bridge_emul *bridge = &pcie->bridge; - bridge->conf.vendor = advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff; - bridge->conf.device = advk_readl(pcie, PCIE_CORE_DEV_ID_REG) >> 16; + bridge->conf.vendor = + cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff); + bridge->conf.device = + cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) >> 16); bridge->conf.class_revision = - advk_readl(pcie, PCIE_CORE_DEV_REV_REG) & 0xff; + cpu_to_le32(advk_readl(pcie, PCIE_CORE_DEV_REV_REG) & 0xff); /* Support 32 bits I/O addressing */ bridge->conf.iobase = PCI_IO_RANGE_TYPE_32; bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32; /* Support 64 bits memory pref */ - bridge->conf.pref_mem_base = PCI_PREF_RANGE_TYPE_64; - bridge->conf.pref_mem_limit = PCI_PREF_RANGE_TYPE_64; + bridge->conf.pref_mem_base = cpu_to_le16(PCI_PREF_RANGE_TYPE_64); + bridge->conf.pref_mem_limit = cpu_to_le16(PCI_PREF_RANGE_TYPE_64); /* Support interrupt A for MSI feature */ - bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE; - + bridge->conf.intpin = PCI_INTERRUPT_INTA; + + /* + * Aardvark HW provides PCIe Capability structure in version 2 and + * indicate slot support, which is emulated. + */ + bridge->pcie_conf.cap = cpu_to_le16(2 | PCI_EXP_FLAGS_SLOT); + + /* + * Set Presence Detect State bit permanently since there is no support + * for unplugging the card nor detecting whether it is plugged. (If a + * platform exists in the future that supports it, via a GPIO for + * example, it should be implemented via this bit.) + * + * Set physical slot number to 1 since there is only one port and zero + * value is reserved for ports within the same silicon as Root Port + * which is not our case. + */ + bridge->pcie_conf.slotcap = cpu_to_le32(FIELD_PREP(PCI_EXP_SLTCAP_PSN, + 1)); + bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS); + + /* Indicates supports for Completion Retry Status */ + bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_RRS_SV); + + bridge->subsystem_vendor_id = advk_readl(pcie, PCIE_CORE_SSDEV_ID_REG) & 0xffff; + bridge->subsystem_id = advk_readl(pcie, PCIE_CORE_SSDEV_ID_REG) >> 16; bridge->has_pcie = true; + bridge->pcie_start = PCIE_CORE_PCIEXP_CAP; bridge->data = pcie; bridge->ops = &advk_pci_bridge_emul_ops; - pci_bridge_emul_init(bridge); - + return pci_bridge_emul_init(bridge, 0); } static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, int devfn) { - if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) + if (pci_is_root_bus(bus) && PCI_SLOT(devfn) != 0) + return false; + + /* + * If the link goes down after we check for link-up, we have a problem: + * if a PIO request is executed while link-down, the whole controller + * gets stuck in a non-functional state, and even after link comes up + * again, PIO requests won't work anymore, and a reset of the whole PCIe + * controller is needed. Therefore we need to prevent sending PIO + * requests while the link is down. + */ + if (!pci_is_root_bus(bus) && !advk_pcie_link_up(pcie)) return false; return true; } +static bool advk_pcie_pio_is_running(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + + /* + * Trying to start a new PIO transfer when previous has not completed + * cause External Abort on CPU which results in kernel panic: + * + * SError Interrupt on CPU0, code 0xbf000002 -- SError + * Kernel panic - not syncing: Asynchronous SError Interrupt + * + * Functions advk_pcie_rd_conf() and advk_pcie_wr_conf() are protected + * by raw_spin_lock_irqsave() at pci_lock_config() level to prevent + * concurrent calls at the same time. But because PIO transfer may take + * about 1.5s when link is down or card is disconnected, it means that + * advk_pcie_wait_pio() does not always have to wait for completion. + * + * Some versions of ARM Trusted Firmware handles this External Abort at + * EL3 level and mask it to prevent kernel panic. Relevant TF-A commit: + * https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/commit/?id=3c7dcdac5c50 + */ + if (advk_readl(pcie, PIO_START)) { + dev_err(dev, "Previous PIO read/write transfer is still running\n"); + return true; + } + + return false; +} + static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { struct advk_pcie *pcie = bus->sysdata; + int retry_count; + bool allow_rrs; u32 reg; int ret; - if (!advk_pcie_valid_device(pcie, bus, devfn)) { - *val = 0xffffffff; + if (!advk_pcie_valid_device(pcie, bus, devfn)) return PCIBIOS_DEVICE_NOT_FOUND; - } - if (bus->number == pcie->root_bus_nr) + if (pci_is_root_bus(bus)) return pci_bridge_emul_conf_read(&pcie->bridge, where, size, val); - /* Start PIO */ - advk_writel(pcie, 0, PIO_START); - advk_writel(pcie, 1, PIO_ISR); + /* + * Configuration Request Retry Status (RRS) is possible to return + * only when reading both bytes from PCI_VENDOR_ID at once and + * RRS_SVE flag on Root Port is enabled. + */ + allow_rrs = (where == PCI_VENDOR_ID) && (size >= 2) && + (le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & + PCI_EXP_RTCTL_RRS_SVE); + + if (advk_pcie_pio_is_running(pcie)) + goto try_rrs; /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); reg &= ~PIO_CTRL_TYPE_MASK; - if (bus->primary == pcie->root_bus_nr) + if (pci_is_root_bus(bus->parent)) reg |= PCIE_CONFIG_RD_TYPE0; else reg |= PCIE_CONFIG_RD_TYPE1; advk_writel(pcie, reg, PIO_CTRL); /* Program the address registers */ - reg = PCIE_CONF_ADDR(bus->number, devfn, where); + reg = ALIGN_DOWN(PCIE_ECAM_OFFSET(bus->number, devfn, where), 4); advk_writel(pcie, reg, PIO_ADDR_LS); advk_writel(pcie, 0, PIO_ADDR_MS); /* Program the data strobe */ advk_writel(pcie, 0xf, PIO_WR_DATA_STRB); - /* Start the transfer */ - advk_writel(pcie, 1, PIO_START); + retry_count = 0; + do { + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); + advk_writel(pcie, 1, PIO_START); - ret = advk_pcie_wait_pio(pcie); - if (ret < 0) - return PCIBIOS_SET_FAILED; + ret = advk_pcie_wait_pio(pcie); + if (ret < 0) + goto try_rrs; - advk_pcie_check_pio_status(pcie); + retry_count += ret; + + /* Check PIO status and get the read result */ + ret = advk_pcie_check_pio_status(pcie, allow_rrs, val); + } while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT); + + if (ret < 0) + goto fail; - /* Get the read result */ - *val = advk_readl(pcie, PIO_RD_DATA); if (size == 1) *val = (*val >> (8 * (where & 3))) & 0xff; else if (size == 2) *val = (*val >> (8 * (where & 3))) & 0xffff; return PCIBIOS_SUCCESSFUL; + +try_rrs: + /* + * If it is possible, return Configuration Request Retry Status so + * that caller tries to issue the request again instead of failing. + */ + if (allow_rrs) { + *val = CFG_RD_RRS_VAL; + return PCIBIOS_SUCCESSFUL; + } + +fail: + *val = 0xffffffff; + return PCIBIOS_SET_FAILED; } static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, @@ -574,34 +1228,34 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, struct advk_pcie *pcie = bus->sysdata; u32 reg; u32 data_strobe = 0x0; + int retry_count; int offset; int ret; if (!advk_pcie_valid_device(pcie, bus, devfn)) return PCIBIOS_DEVICE_NOT_FOUND; - if (bus->number == pcie->root_bus_nr) + if (pci_is_root_bus(bus)) return pci_bridge_emul_conf_write(&pcie->bridge, where, size, val); if (where % size) return PCIBIOS_SET_FAILED; - /* Start PIO */ - advk_writel(pcie, 0, PIO_START); - advk_writel(pcie, 1, PIO_ISR); + if (advk_pcie_pio_is_running(pcie)) + return PCIBIOS_SET_FAILED; /* Program the control register */ reg = advk_readl(pcie, PIO_CTRL); reg &= ~PIO_CTRL_TYPE_MASK; - if (bus->primary == pcie->root_bus_nr) + if (pci_is_root_bus(bus->parent)) reg |= PCIE_CONFIG_WR_TYPE0; else reg |= PCIE_CONFIG_WR_TYPE1; advk_writel(pcie, reg, PIO_CTRL); /* Program the address registers */ - reg = PCIE_CONF_ADDR(bus->number, devfn, where); + reg = ALIGN_DOWN(PCIE_ECAM_OFFSET(bus->number, devfn, where), 4); advk_writel(pcie, reg, PIO_ADDR_LS); advk_writel(pcie, 0, PIO_ADDR_MS); @@ -616,16 +1270,22 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, /* Program the data strobe */ advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB); - /* Start the transfer */ - advk_writel(pcie, 1, PIO_START); + retry_count = 0; + do { + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); + advk_writel(pcie, 1, PIO_START); - ret = advk_pcie_wait_pio(pcie); - if (ret < 0) - return PCIBIOS_SET_FAILED; + ret = advk_pcie_wait_pio(pcie); + if (ret < 0) + return PCIBIOS_SET_FAILED; - advk_pcie_check_pio_status(pcie); + retry_count += ret; - return PCIBIOS_SUCCESSFUL; + ret = advk_pcie_check_pio_status(pcie, false, NULL); + } while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT); + + return ret < 0 ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL; } static struct pci_ops advk_pcie_ops = { @@ -637,19 +1297,48 @@ static void advk_msi_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct advk_pcie *pcie = irq_data_get_irq_chip_data(data); - phys_addr_t msi_msg = virt_to_phys(&pcie->msi_msg); + phys_addr_t msi_addr = virt_to_phys(pcie); + + msg->address_lo = lower_32_bits(msi_addr); + msg->address_hi = upper_32_bits(msi_addr); + msg->data = data->hwirq; +} + +static void advk_msi_irq_mask(struct irq_data *d) +{ + struct advk_pcie *pcie = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 mask; - msg->address_lo = lower_32_bits(msi_msg); - msg->address_hi = upper_32_bits(msi_msg); - msg->data = data->irq; + raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags); + mask = advk_readl(pcie, PCIE_MSI_MASK_REG); + mask |= BIT(hwirq); + advk_writel(pcie, mask, PCIE_MSI_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags); } -static int advk_msi_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) +static void advk_msi_irq_unmask(struct irq_data *d) { - return -EINVAL; + struct advk_pcie *pcie = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 mask; + + raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags); + mask = advk_readl(pcie, PCIE_MSI_MASK_REG); + mask &= ~BIT(hwirq); + advk_writel(pcie, mask, PCIE_MSI_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags); } +static struct irq_chip advk_msi_bottom_irq_chip = { + .name = "MSI", + .irq_compose_msi_msg = advk_msi_irq_compose_msi_msg, + .irq_mask = advk_msi_irq_mask, + .irq_unmask = advk_msi_irq_unmask, +}; + static int advk_msi_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *args) @@ -658,23 +1347,19 @@ static int advk_msi_irq_domain_alloc(struct irq_domain *domain, int hwirq, i; mutex_lock(&pcie->msi_used_lock); - hwirq = bitmap_find_next_zero_area(pcie->msi_used, MSI_IRQ_NUM, - 0, nr_irqs, 0); - if (hwirq >= MSI_IRQ_NUM) { - mutex_unlock(&pcie->msi_used_lock); - return -ENOSPC; - } - - bitmap_set(pcie->msi_used, hwirq, nr_irqs); + hwirq = bitmap_find_free_region(pcie->msi_used, MSI_IRQ_NUM, + order_base_2(nr_irqs)); mutex_unlock(&pcie->msi_used_lock); + if (hwirq < 0) + return -ENOSPC; for (i = 0; i < nr_irqs; i++) irq_domain_set_info(domain, virq + i, hwirq + i, - &pcie->msi_bottom_irq_chip, + &advk_msi_bottom_irq_chip, domain->host_data, handle_simple_irq, NULL, NULL); - return hwirq; + return 0; } static void advk_msi_irq_domain_free(struct irq_domain *domain, @@ -684,7 +1369,7 @@ static void advk_msi_irq_domain_free(struct irq_domain *domain, struct advk_pcie *pcie = domain->host_data; mutex_lock(&pcie->msi_used_lock); - bitmap_clear(pcie->msi_used, d->hwirq, nr_irqs); + bitmap_release_region(pcie->msi_used, d->hwirq, order_base_2(nr_irqs)); mutex_unlock(&pcie->msi_used_lock); } @@ -697,22 +1382,28 @@ static void advk_pcie_irq_mask(struct irq_data *d) { struct advk_pcie *pcie = d->domain->host_data; irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; u32 mask; + raw_spin_lock_irqsave(&pcie->irq_lock, flags); mask = advk_readl(pcie, PCIE_ISR1_MASK_REG); mask |= PCIE_ISR1_INTX_ASSERT(hwirq); advk_writel(pcie, mask, PCIE_ISR1_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); } static void advk_pcie_irq_unmask(struct irq_data *d) { struct advk_pcie *pcie = d->domain->host_data; irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; u32 mask; + raw_spin_lock_irqsave(&pcie->irq_lock, flags); mask = advk_readl(pcie, PCIE_ISR1_MASK_REG); mask &= ~PCIE_ISR1_INTX_ASSERT(hwirq); advk_writel(pcie, mask, PCIE_ISR1_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); } static int advk_pcie_irq_map(struct irq_domain *h, @@ -720,7 +1411,6 @@ static int advk_pcie_irq_map(struct irq_domain *h, { struct advk_pcie *pcie = h->host_data; - advk_pcie_irq_mask(irq_get_irq_data(virq)); irq_set_status_flags(virq, IRQ_LEVEL); irq_set_chip_and_handler(virq, &pcie->irq_chip, handle_level_irq); @@ -734,57 +1424,45 @@ static const struct irq_domain_ops advk_pcie_irq_domain_ops = { .xlate = irq_domain_xlate_onecell, }; +#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) { struct device *dev = &pcie->pdev->dev; - struct device_node *node = dev->of_node; - struct irq_chip *bottom_ic, *msi_ic; - struct msi_domain_info *msi_di; - phys_addr_t msi_msg_phys; + raw_spin_lock_init(&pcie->msi_irq_lock); mutex_init(&pcie->msi_used_lock); - bottom_ic = &pcie->msi_bottom_irq_chip; - - bottom_ic->name = "MSI"; - bottom_ic->irq_compose_msi_msg = advk_msi_irq_compose_msi_msg; - bottom_ic->irq_set_affinity = advk_msi_set_affinity; - - msi_ic = &pcie->msi_irq_chip; - msi_ic->name = "advk-MSI"; - - msi_di = &pcie->msi_domain_info; - msi_di->flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_MULTI_PCI_MSI; - msi_di->chip = msi_ic; + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &advk_msi_domain_ops, + .host_data = pcie, + .size = MSI_IRQ_NUM, + }; - msi_msg_phys = virt_to_phys(&pcie->msi_msg); - - advk_writel(pcie, lower_32_bits(msi_msg_phys), - PCIE_MSI_ADDR_LOW_REG); - advk_writel(pcie, upper_32_bits(msi_msg_phys), - PCIE_MSI_ADDR_HIGH_REG); - - pcie->msi_inner_domain = - irq_domain_add_linear(NULL, MSI_IRQ_NUM, - &advk_msi_domain_ops, pcie); + pcie->msi_inner_domain = msi_create_parent_irq_domain(&info, &advk_msi_parent_ops); if (!pcie->msi_inner_domain) return -ENOMEM; - pcie->msi_domain = - pci_msi_create_irq_domain(of_node_to_fwnode(node), - msi_di, pcie->msi_inner_domain); - if (!pcie->msi_domain) { - irq_domain_remove(pcie->msi_inner_domain); - return -ENOMEM; - } - return 0; } static void advk_pcie_remove_msi_irq_domain(struct advk_pcie *pcie) { - irq_domain_remove(pcie->msi_domain); irq_domain_remove(pcie->msi_inner_domain); } @@ -794,6 +1472,9 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie) struct device_node *node = dev->of_node; struct device_node *pcie_intc_node; struct irq_chip *irq_chip; + int ret = 0; + + raw_spin_lock_init(&pcie->irq_lock); pcie_intc_node = of_get_next_child(node, NULL); if (!pcie_intc_node) { @@ -806,24 +1487,24 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie) irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-irq", dev_name(dev)); if (!irq_chip->name) { - of_node_put(pcie_intc_node); - return -ENOMEM; + ret = -ENOMEM; + goto out_put_node; } irq_chip->irq_mask = advk_pcie_irq_mask; - irq_chip->irq_mask_ack = 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"); - of_node_put(pcie_intc_node); - return -ENOMEM; + ret = -ENOMEM; + goto out_put_node; } - return 0; +out_put_node: + of_node_put(pcie_intc_node); + return ret; } static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie) @@ -831,22 +1512,83 @@ static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie) irq_domain_remove(pcie->irq_domain); } +static struct irq_chip advk_rp_irq_chip = { + .name = "advk-RP", +}; + +static int advk_pcie_rp_irq_map(struct irq_domain *h, + unsigned int virq, irq_hw_number_t hwirq) +{ + struct advk_pcie *pcie = h->host_data; + + irq_set_chip_and_handler(virq, &advk_rp_irq_chip, handle_simple_irq); + irq_set_chip_data(virq, pcie); + + return 0; +} + +static const struct irq_domain_ops advk_pcie_rp_irq_domain_ops = { + .map = advk_pcie_rp_irq_map, + .xlate = irq_domain_xlate_onecell, +}; + +static int advk_pcie_init_rp_irq_domain(struct advk_pcie *pcie) +{ + pcie->rp_irq_domain = irq_domain_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; + } + + return 0; +} + +static void advk_pcie_remove_rp_irq_domain(struct advk_pcie *pcie) +{ + irq_domain_remove(pcie->rp_irq_domain); +} + +static void advk_pcie_handle_pme(struct advk_pcie *pcie) +{ + u32 requester = advk_readl(pcie, PCIE_MSG_LOG_REG) >> 16; + + advk_writel(pcie, PCIE_MSG_PM_PME_MASK, PCIE_ISR0_REG); + + /* + * PCIE_MSG_LOG_REG contains the last inbound message, so store + * the requester ID only when PME was not asserted yet. + * Also do not trigger PME interrupt when PME is still asserted. + */ + if (!(le32_to_cpu(pcie->bridge.pcie_conf.rootsta) & PCI_EXP_RTSTA_PME)) { + pcie->bridge.pcie_conf.rootsta = cpu_to_le32(requester | PCI_EXP_RTSTA_PME); + + /* + * Trigger PME interrupt only if PMEIE bit in Root Control is set. + * Aardvark HW returns zero for PCI_EXP_FLAGS_IRQ, so use PCIe interrupt 0. + */ + if (!(le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & PCI_EXP_RTCTL_PMEIE)) + return; + + if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unhandled PME IRQ\n"); + } +} + static void advk_pcie_handle_msi(struct advk_pcie *pcie) { u32 msi_val, msi_mask, msi_status, msi_idx; - u16 msi_data; msi_mask = advk_readl(pcie, PCIE_MSI_MASK_REG); msi_val = advk_readl(pcie, PCIE_MSI_STATUS_REG); - msi_status = msi_val & ~msi_mask; + msi_status = msi_val & ((~msi_mask) & PCIE_MSI_ALL_MASK); for (msi_idx = 0; msi_idx < MSI_IRQ_NUM; msi_idx++) { if (!(BIT(msi_idx) & msi_status)) continue; advk_writel(pcie, BIT(msi_idx), PCIE_MSI_STATUS_REG); - msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & 0xFF; - generic_handle_irq(msi_data); + if (generic_handle_domain_irq(pcie->msi_inner_domain, msi_idx) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unexpected MSI 0x%02x\n", msi_idx); } advk_writel(pcie, PCIE_ISR0_MSI_INT_PENDING, @@ -857,7 +1599,7 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie) { u32 isr0_val, isr0_mask, isr0_status; u32 isr1_val, isr1_mask, isr1_status; - int i, virq; + int i; isr0_val = advk_readl(pcie, PCIE_ISR0_REG); isr0_mask = advk_readl(pcie, PCIE_ISR0_MASK_REG); @@ -867,10 +1609,20 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie) isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG); isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK); - if (!isr0_status && !isr1_status) { - advk_writel(pcie, isr0_val, PCIE_ISR0_REG); - advk_writel(pcie, isr1_val, PCIE_ISR1_REG); - return; + /* Process PME interrupt as the first one to do not miss PME requester id */ + if (isr0_status & PCIE_MSG_PM_PME_MASK) + advk_pcie_handle_pme(pcie); + + /* Process ERR interrupt */ + if (isr0_status & PCIE_ISR0_ERR_MASK) { + advk_writel(pcie, PCIE_ISR0_ERR_MASK, PCIE_ISR0_REG); + + /* + * Aardvark HW returns zero for PCI_ERR_ROOT_AER_IRQ, so use + * PCIe interrupt 0 + */ + if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unhandled ERR IRQ\n"); } /* Process MSI interrupts */ @@ -885,8 +1637,9 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie) advk_writel(pcie, PCIE_ISR1_INTX_ASSERT(i), PCIE_ISR1_REG); - virq = irq_find_mapping(pcie->irq_domain, i); - generic_handle_irq(virq); + if (generic_handle_domain_irq(pcie->irq_domain, i) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unexpected INT%c IRQ\n", + (char)i + 'A'); } } @@ -907,64 +1660,83 @@ static irqreturn_t advk_pcie_irq_handler(int irq, void *arg) return IRQ_HANDLED; } -static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie) +static int advk_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { - int err, res_valid = 0; - struct device *dev = &pcie->pdev->dev; - struct resource_entry *win, *tmp; - resource_size_t iobase; - - INIT_LIST_HEAD(&pcie->resources); - - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, - &pcie->resources, &iobase); - if (err) - return err; - - err = devm_request_pci_bus_resources(dev, &pcie->resources); - if (err) - goto out_release_res; - - resource_list_for_each_entry_safe(win, tmp, &pcie->resources) { - struct resource *res = win->res; - - switch (resource_type(res)) { - case IORESOURCE_IO: - err = devm_pci_remap_iospace(dev, res, iobase); - if (err) { - dev_warn(dev, "error %d: failed to map resource %pR\n", - err, res); - resource_list_destroy_entry(win); - } - break; - case IORESOURCE_MEM: - res_valid |= !(res->flags & IORESOURCE_PREFETCH); - break; - case IORESOURCE_BUS: - pcie->root_bus_nr = res->start; - break; - } + struct advk_pcie *pcie = dev->bus->sysdata; + + /* + * Emulated root bridge has its own emulated irq chip and irq domain. + * Argument pin is the INTx pin (1=INTA, 2=INTB, 3=INTC, 4=INTD) and + * hwirq for irq_create_mapping() is indexed from zero. + */ + if (pci_is_root_bus(dev->bus)) + return irq_create_mapping(pcie->rp_irq_domain, pin - 1); + else + return of_irq_parse_and_map_pci(dev, slot, pin); +} + +static void advk_pcie_disable_phy(struct advk_pcie *pcie) +{ + phy_power_off(pcie->phy); + phy_exit(pcie->phy); +} + +static int advk_pcie_enable_phy(struct advk_pcie *pcie) +{ + int ret; + + if (!pcie->phy) + return 0; + + ret = phy_init(pcie->phy); + if (ret) + return ret; + + ret = phy_set_mode(pcie->phy, PHY_MODE_PCIE); + if (ret) { + phy_exit(pcie->phy); + return ret; } - if (!res_valid) { - dev_err(dev, "non-prefetchable memory resource required\n"); - err = -EINVAL; - goto out_release_res; + ret = phy_power_on(pcie->phy); + if (ret) { + phy_exit(pcie->phy); + return ret; } return 0; +} + +static int advk_pcie_setup_phy(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct device_node *node = dev->of_node; + int ret = 0; -out_release_res: - pci_free_resource_list(&pcie->resources); - return err; + pcie->phy = devm_of_phy_get(dev, node, NULL); + if (IS_ERR(pcie->phy) && (PTR_ERR(pcie->phy) == -EPROBE_DEFER)) + return PTR_ERR(pcie->phy); + + /* Old bindings miss the PHY handle */ + if (IS_ERR(pcie->phy)) { + dev_warn(dev, "PHY unavailable (%ld)\n", PTR_ERR(pcie->phy)); + pcie->phy = NULL; + return 0; + } + + ret = advk_pcie_enable_phy(pcie); + if (ret) + dev_err(dev, "Failed to initialize PHY (%d)\n", ret); + + return ret; } static int advk_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct advk_pcie *pcie; - struct resource *res; struct pci_host_bridge *bridge; + struct resource_entry *entry; int ret, irq; bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie)); @@ -973,13 +1745,88 @@ static int advk_pcie_probe(struct platform_device *pdev) pcie = pci_host_bridge_priv(bridge); pcie->pdev = pdev; + platform_set_drvdata(pdev, pcie); + + resource_list_for_each_entry(entry, &bridge->windows) { + resource_size_t start = entry->res->start; + resource_size_t size = resource_size(entry->res); + unsigned long type = resource_type(entry->res); + u64 win_size; + + /* + * Aardvark hardware allows to configure also PCIe window + * for config type 0 and type 1 mapping, but driver uses + * only PIO for issuing configuration transfers which does + * not use PCIe window configuration. + */ + if (type != IORESOURCE_MEM && type != IORESOURCE_IO) + continue; + + /* + * Skip transparent memory resources. Default outbound access + * configuration is set to transparent memory access so it + * does not need window configuration. + */ + if (type == IORESOURCE_MEM && entry->offset == 0) + continue; + + /* + * The n-th PCIe window is configured by tuple (match, remap, mask) + * and an access to address A uses this window if A matches the + * match with given mask. + * So every PCIe window size must be a power of two and every start + * address must be aligned to window size. Minimal size is 64 KiB + * because lower 16 bits of mask must be zero. Remapped address + * may have set only bits from the mask. + */ + while (pcie->wins_count < OB_WIN_COUNT && size > 0) { + /* Calculate the largest aligned window size */ + win_size = (1ULL << (fls64(size)-1)) | + (start ? (1ULL << __ffs64(start)) : 0); + win_size = 1ULL << __ffs64(win_size); + if (win_size < 0x10000) + break; + + dev_dbg(dev, + "Configuring PCIe window %d: [0x%llx-0x%llx] as %lu\n", + pcie->wins_count, (unsigned long long)start, + (unsigned long long)start + win_size, type); + + if (type == IORESOURCE_IO) { + pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_IO; + pcie->wins[pcie->wins_count].match = pci_pio_to_address(start); + } else { + pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_MEM; + pcie->wins[pcie->wins_count].match = start; + } + pcie->wins[pcie->wins_count].remap = start - entry->offset; + pcie->wins[pcie->wins_count].mask = ~(win_size - 1); + + if (pcie->wins[pcie->wins_count].remap & (win_size - 1)) + break; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pcie->base = devm_ioremap_resource(dev, res); + start += win_size; + size -= win_size; + pcie->wins_count++; + } + + if (size > 0) { + dev_err(&pcie->pdev->dev, + "Invalid PCIe region [0x%llx-0x%llx]\n", + (unsigned long long)entry->res->start, + (unsigned long long)entry->res->end + 1); + return -EINVAL; + } + } + + pcie->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pcie->base)) return PTR_ERR(pcie->base); irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + ret = devm_request_irq(dev, irq, advk_pcie_irq_handler, IRQF_SHARED | IRQF_NO_THREAD, "advk-pcie", pcie); @@ -988,15 +1835,37 @@ static int advk_pcie_probe(struct platform_device *pdev) return ret; } - ret = advk_pcie_parse_request_of_pci_ranges(pcie); + pcie->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + ret = PTR_ERR_OR_ZERO(pcie->reset_gpio); + if (ret) { + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get reset-gpio: %i\n", ret); + return ret; + } + + ret = gpiod_set_consumer_name(pcie->reset_gpio, "pcie1-reset"); if (ret) { - dev_err(dev, "Failed to parse resources\n"); + dev_err(dev, "Failed to set reset gpio name: %d\n", ret); return ret; } + ret = of_pci_get_max_link_speed(dev->of_node); + if (ret <= 0 || ret > 3) + pcie->link_gen = 3; + else + pcie->link_gen = ret; + + ret = advk_pcie_setup_phy(pcie); + if (ret) + return ret; + advk_pcie_setup_hw(pcie); - advk_sw_pci_bridge_init(pcie); + ret = advk_sw_pci_bridge_init(pcie); + if (ret) { + dev_err(dev, "Failed to register emulated root PCI bridge\n"); + return ret; + } ret = advk_pcie_init_irq_domain(pcie); if (ret) { @@ -1011,16 +1880,21 @@ static int advk_pcie_probe(struct platform_device *pdev) return ret; } - list_splice_init(&pcie->resources, &bridge->windows); - bridge->dev.parent = dev; + ret = advk_pcie_init_rp_irq_domain(pcie); + if (ret) { + dev_err(dev, "Failed to initialize irq\n"); + advk_pcie_remove_msi_irq_domain(pcie); + advk_pcie_remove_irq_domain(pcie); + return ret; + } + bridge->sysdata = pcie; - bridge->busnr = 0; bridge->ops = &advk_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; + bridge->map_irq = advk_pcie_map_irq; ret = pci_host_probe(bridge); if (ret < 0) { + advk_pcie_remove_rp_irq_domain(pcie); advk_pcie_remove_msi_irq_domain(pcie); advk_pcie_remove_irq_domain(pcie); return ret; @@ -1029,18 +1903,85 @@ static int advk_pcie_probe(struct platform_device *pdev) return 0; } +static void advk_pcie_remove(struct platform_device *pdev) +{ + struct advk_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + u32 val; + int i; + + /* Remove PCI bus with all devices */ + pci_lock_rescan_remove(); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + pci_unlock_rescan_remove(); + + /* Disable Root Bridge I/O space, memory space and bus mastering */ + val = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); + val &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + advk_writel(pcie, val, PCIE_CORE_CMD_STATUS_REG); + + /* Disable MSI */ + val = advk_readl(pcie, PCIE_CORE_CTRL2_REG); + val &= ~PCIE_CORE_CTRL2_MSI_ENABLE; + advk_writel(pcie, val, PCIE_CORE_CTRL2_REG); + + /* Clear MSI address */ + advk_writel(pcie, 0, PCIE_MSI_ADDR_LOW_REG); + advk_writel(pcie, 0, PCIE_MSI_ADDR_HIGH_REG); + + /* Mask all interrupts */ + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG); + advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_MASK_REG); + advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG); + advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_MASK_REG); + + /* Clear all interrupts */ + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_STATUS_REG); + advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_REG); + advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG); + advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG); + + /* Remove IRQ domains */ + advk_pcie_remove_rp_irq_domain(pcie); + advk_pcie_remove_msi_irq_domain(pcie); + advk_pcie_remove_irq_domain(pcie); + + /* Free config space for emulated root bridge */ + pci_bridge_emul_cleanup(&pcie->bridge); + + /* Assert PERST# signal which prepares PCIe card for power down */ + if (pcie->reset_gpio) + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + + /* Disable link training */ + val = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + val &= ~LINK_TRAINING_EN; + advk_writel(pcie, val, PCIE_CORE_CTRL0_REG); + + /* Disable outbound address windows mapping */ + for (i = 0; i < OB_WIN_COUNT; i++) + advk_pcie_disable_ob_win(pcie, i); + + /* Disable phy */ + advk_pcie_disable_phy(pcie); +} + static const struct of_device_id advk_pcie_of_match_table[] = { { .compatible = "marvell,armada-3700-pcie", }, {}, }; +MODULE_DEVICE_TABLE(of, advk_pcie_of_match_table); static struct platform_driver advk_pcie_driver = { .driver = { .name = "advk-pcie", .of_match_table = advk_pcie_of_match_table, - /* Driver unloading/unbinding currently not supported */ - .suppress_bind_attrs = true, }, .probe = advk_pcie_probe, + .remove = advk_pcie_remove, }; -builtin_platform_driver(advk_pcie_driver); +module_platform_driver(advk_pcie_driver); + +MODULE_DESCRIPTION("Aardvark PCIe controller"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index bf5ece5d9291..28e43831c0f1 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -15,8 +15,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> -#include <linux/of_address.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/of_irq.h> #include <linux/of_pci.h> #include <linux/pci.h> @@ -34,12 +33,12 @@ * Special configuration registers directly in the first few words * in I/O space. */ -#define PCI_IOSIZE 0x00 -#define PCI_PROT 0x04 /* AHB protection */ -#define PCI_CTRL 0x08 /* PCI control signal */ -#define PCI_SOFTRST 0x10 /* Soft reset counter and response error enable */ -#define PCI_CONFIG 0x28 /* PCI configuration command register */ -#define PCI_DATA 0x2C +#define FTPCI_IOSIZE 0x00 +#define FTPCI_PROT 0x04 /* AHB protection */ +#define FTPCI_CTRL 0x08 /* PCI control signal */ +#define FTPCI_SOFTRST 0x10 /* Soft reset counter and response error enable */ +#define FTPCI_CONFIG 0x28 /* PCI configuration command register */ +#define FTPCI_DATA 0x2C #define FARADAY_PCI_STATUS_CMD 0x04 /* Status and command */ #define FARADAY_PCI_PMC 0x40 /* Power management control */ @@ -103,13 +102,6 @@ #define FARADAY_PCI_DMA_MEM2_BASE 0x00000000 #define FARADAY_PCI_DMA_MEM3_BASE 0x00000000 -/* Defines for PCI configuration command register */ -#define PCI_CONF_ENABLE BIT(31) -#define PCI_CONF_WHERE(r) ((r) & 0xFC) -#define PCI_CONF_BUS(b) (((b) & 0xFF) << 16) -#define PCI_CONF_DEVICE(d) (((d) & 0x1F) << 11) -#define PCI_CONF_FUNCTION(f) (((f) & 0x07) << 8) - /** * struct faraday_pci_variant - encodes IP block differences * @cascaded_irq: this host has cascaded IRQs from an interrupt controller @@ -190,14 +182,11 @@ static int faraday_raw_pci_read_config(struct faraday_pci *p, int bus_number, unsigned int fn, int config, int size, u32 *value) { - writel(PCI_CONF_BUS(bus_number) | - PCI_CONF_DEVICE(PCI_SLOT(fn)) | - PCI_CONF_FUNCTION(PCI_FUNC(fn)) | - PCI_CONF_WHERE(config) | - PCI_CONF_ENABLE, - p->base + PCI_CONFIG); + writel(PCI_CONF1_ADDRESS(bus_number, PCI_SLOT(fn), + PCI_FUNC(fn), config), + p->base + FTPCI_CONFIG); - *value = readl(p->base + PCI_DATA); + *value = readl(p->base + FTPCI_DATA); if (size == 1) *value = (*value >> (8 * (config & 3))) & 0xFF; @@ -225,22 +214,19 @@ static int faraday_raw_pci_write_config(struct faraday_pci *p, int bus_number, { int ret = PCIBIOS_SUCCESSFUL; - writel(PCI_CONF_BUS(bus_number) | - PCI_CONF_DEVICE(PCI_SLOT(fn)) | - PCI_CONF_FUNCTION(PCI_FUNC(fn)) | - PCI_CONF_WHERE(config) | - PCI_CONF_ENABLE, - p->base + PCI_CONFIG); + writel(PCI_CONF1_ADDRESS(bus_number, PCI_SLOT(fn), + PCI_FUNC(fn), config), + p->base + FTPCI_CONFIG); switch (size) { case 4: - writel(value, p->base + PCI_DATA); + writel(value, p->base + FTPCI_DATA); break; case 2: - writew(value, p->base + PCI_DATA + (config & 3)); + writew(value, p->base + FTPCI_DATA + (config & 3)); break; case 1: - writeb(value, p->base + PCI_DATA + (config & 3)); + writeb(value, p->base + FTPCI_DATA + (config & 3)); break; default: ret = PCIBIOS_BAD_REGISTER_NUMBER; @@ -314,7 +300,7 @@ static void faraday_pci_irq_handler(struct irq_desc *desc) for (i = 0; i < 4; i++) { if ((irq_stat & BIT(i)) == 0) continue; - generic_handle_irq(irq_find_mapping(p->irqdomain, i)); + generic_handle_domain_irq(p->irqdomain, i); } chained_irq_exit(irqchip, desc); @@ -359,8 +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"); @@ -375,12 +361,11 @@ static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p) return 0; } -static int faraday_pci_parse_map_dma_ranges(struct faraday_pci *p, - struct device_node *np) +static int faraday_pci_parse_map_dma_ranges(struct faraday_pci *p) { - struct of_pci_range range; - struct of_pci_range_parser parser; struct device *dev = p->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(p); + struct resource_entry *entry; u32 confreg[3] = { FARADAY_PCI_MEM1_BASE_SIZE, FARADAY_PCI_MEM2_BASE_SIZE, @@ -389,19 +374,13 @@ static int faraday_pci_parse_map_dma_ranges(struct faraday_pci *p, int i = 0; u32 val; - if (of_pci_dma_range_parser_init(&parser, np)) { - dev_err(dev, "missing dma-ranges property\n"); - return -EINVAL; - } - - /* - * Get the dma-ranges from the device tree - */ - for_each_of_pci_range(&parser, &range) { - u64 end = range.pci_addr + range.size - 1; + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + u64 pci_addr = entry->res->start - entry->offset; + u64 end = entry->res->end - entry->offset; int ret; - ret = faraday_res_to_memcfg(range.pci_addr, range.size, &val); + ret = faraday_res_to_memcfg(pci_addr, + resource_size(entry->res), &val); if (ret) { dev_err(dev, "DMA range %d: illegal MEM resource size\n", i); @@ -409,7 +388,7 @@ static int faraday_pci_parse_map_dma_ranges(struct faraday_pci *p, } dev_info(dev, "DMA MEM%d BASE: 0x%016llx -> 0x%016llx config %08x\n", - i + 1, range.pci_addr, end, val); + i + 1, pci_addr, end, val); if (i <= 2) { faraday_raw_pci_write_config(p, 0, 0, confreg[i], 4, val); @@ -429,11 +408,8 @@ static int faraday_pci_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; const struct faraday_pci_variant *variant = of_device_get_match_data(dev); - struct resource *regs; - resource_size_t io_base; struct resource_entry *win; struct faraday_pci *p; - struct resource *mem; struct resource *io; struct pci_host_bridge *host; struct clk *clk; @@ -441,92 +417,47 @@ static int faraday_pci_probe(struct platform_device *pdev) unsigned char cur_bus_speed = PCI_SPEED_33MHz; int ret; u32 val; - LIST_HEAD(res); host = devm_pci_alloc_host_bridge(dev, sizeof(*p)); if (!host) return -ENOMEM; - host->dev.parent = dev; host->ops = &faraday_pci_ops; - host->busnr = 0; - host->msi = NULL; - host->map_irq = of_irq_parse_and_map_pci; - host->swizzle_irq = pci_common_swizzle; p = pci_host_bridge_priv(host); host->sysdata = p; p->dev = dev; /* Retrieve and enable optional clocks */ - clk = devm_clk_get(dev, "PCLK"); + clk = devm_clk_get_enabled(dev, "PCLK"); if (IS_ERR(clk)) return PTR_ERR(clk); - ret = clk_prepare_enable(clk); - if (ret) { - dev_err(dev, "could not prepare PCLK\n"); - return ret; - } - p->bus_clk = devm_clk_get(dev, "PCICLK"); + p->bus_clk = devm_clk_get_enabled(dev, "PCICLK"); if (IS_ERR(p->bus_clk)) return PTR_ERR(p->bus_clk); - ret = clk_prepare_enable(p->bus_clk); - if (ret) { - dev_err(dev, "could not prepare PCICLK\n"); - return ret; - } - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - p->base = devm_ioremap_resource(dev, regs); + p->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(p->base)) return PTR_ERR(p->base); - ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, - &res, &io_base); - if (ret) - return ret; - - ret = devm_request_pci_bus_resources(dev, &res); - if (ret) - return ret; - - /* Get the I/O and memory ranges from DT */ - resource_list_for_each_entry(win, &res) { - switch (resource_type(win->res)) { - case IORESOURCE_IO: - io = win->res; - io->name = "Gemini PCI I/O"; - if (!faraday_res_to_memcfg(io->start - win->offset, - resource_size(io), &val)) { - /* setup I/O space size */ - writel(val, p->base + PCI_IOSIZE); - } else { - dev_err(dev, "illegal IO mem size\n"); - return -EINVAL; - } - ret = devm_pci_remap_iospace(dev, io, io_base); - if (ret) { - dev_warn(dev, "error %d: failed to map resource %pR\n", - ret, io); - continue; - } - break; - case IORESOURCE_MEM: - mem = win->res; - mem->name = "Gemini PCI MEM"; - break; - case IORESOURCE_BUS: - break; - default: - break; + win = resource_list_first_type(&host->windows, IORESOURCE_IO); + if (win) { + io = win->res; + if (!faraday_res_to_memcfg(io->start - win->offset, + resource_size(io), &val)) { + /* setup I/O space size */ + writel(val, p->base + FTPCI_IOSIZE); + } else { + dev_err(dev, "illegal IO mem size\n"); + return -EINVAL; } } /* Setup hostbridge */ - val = readl(p->base + PCI_CTRL); + val = readl(p->base + FTPCI_CTRL); val |= PCI_COMMAND_IO; val |= PCI_COMMAND_MEMORY; val |= PCI_COMMAND_MASTER; - writel(val, p->base + PCI_CTRL); + writel(val, p->base + FTPCI_CTRL); /* Mask and clear all interrupts */ faraday_raw_pci_write_config(p, 0, 0, FARADAY_PCI_CTRL2 + 2, 2, 0xF000); if (variant->cascaded_irq) { @@ -565,11 +496,10 @@ static int faraday_pci_probe(struct platform_device *pdev) cur_bus_speed = PCI_SPEED_66MHz; } - ret = faraday_pci_parse_map_dma_ranges(p, dev->of_node); + ret = faraday_pci_parse_map_dma_ranges(p); if (ret) return ret; - list_splice_init(&res, &host->windows); ret = pci_scan_root_bus_bridge(host); if (ret) { dev_err(dev, "failed to scan host: %d\n", ret); @@ -581,7 +511,6 @@ static int faraday_pci_probe(struct platform_device *pdev) pci_bus_assign_resources(p->bus); pci_bus_add_devices(p->bus); - pci_free_resource_list(&res); return 0; } @@ -613,7 +542,7 @@ static const struct of_device_id faraday_pci_of_match[] = { static struct platform_driver faraday_pci_driver = { .driver = { .name = "ftpci100", - .of_match_table = of_match_ptr(faraday_pci_of_match), + .of_match_table = faraday_pci_of_match, .suppress_bind_attrs = true, }, .probe = faraday_pci_probe, diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c index c742881b5061..c473e7c03bac 100644 --- a/drivers/pci/controller/pci-host-common.c +++ b/drivers/pci/controller/pci-host-common.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Generic PCI host driver common code + * Common library for PCI host controller drivers * * Copyright (C) 2014 ARM Limited * @@ -8,103 +8,103 @@ */ #include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> #include <linux/of_address.h> #include <linux/of_pci.h> #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 list_head *resources, struct pci_ecam_ops *ops) +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; struct resource cfgres; - struct resource *bus_range = NULL; + struct resource_entry *bus; struct pci_config_window *cfg; - /* Parse our PCI ranges and request their resources */ - err = pci_parse_request_of_pci_ranges(dev, resources, &bus_range); - if (err) - return ERR_PTR(err); - err = of_address_to_resource(dev->of_node, 0, &cfgres); if (err) { dev_err(dev, "missing \"reg\" property\n"); - goto err_out; + return ERR_PTR(err); } - cfg = pci_ecam_create(dev, &cfgres, bus_range, ops); - if (IS_ERR(cfg)) { - err = PTR_ERR(cfg); - goto err_out; - } + bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!bus) + return ERR_PTR(-ENODEV); - err = devm_add_action(dev, gen_pci_unmap_cfg, cfg); - if (err) { - gen_pci_unmap_cfg(cfg); - goto err_out; - } - return cfg; + cfg = pci_ecam_create(dev, &cfgres, bus->res, ops); + if (IS_ERR(cfg)) + return cfg; + + err = devm_add_action_or_reset(dev, gen_pci_unmap_cfg, cfg); + if (err) + return ERR_PTR(err); -err_out: - pci_free_resource_list(resources); - return ERR_PTR(err); + return cfg; } +EXPORT_SYMBOL_GPL(pci_host_common_ecam_create); -int pci_host_common_probe(struct platform_device *pdev, - struct pci_ecam_ops *ops) +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; - struct list_head resources; - int ret; - - bridge = devm_pci_alloc_host_bridge(dev, 0); - if (!bridge) - return -ENOMEM; of_pci_check_probe_only(); + platform_set_drvdata(pdev, bridge); + /* Parse and map our Configuration Space windows */ - cfg = gen_pci_init(dev, &resources, ops); + cfg = pci_host_common_ecam_create(dev, bridge, ops); if (IS_ERR(cfg)) return PTR_ERR(cfg); - /* Do not reassign resources if probe only */ - if (!pci_has_flag(PCI_PROBE_ONLY)) - pci_add_flags(PCI_REASSIGN_ALL_BUS); - - list_splice_init(&resources, &bridge->windows); - bridge->dev.parent = dev; bridge->sysdata = cfg; - bridge->busnr = cfg->busr.start; - bridge->ops = &ops->pci_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - - ret = pci_host_probe(bridge); - if (ret < 0) { - pci_free_resource_list(&resources); - return ret; - } + bridge->ops = (struct pci_ops *)&ops->pci_ops; + bridge->enable_device = ops->enable_device; + bridge->disable_device = ops->disable_device; + bridge->msi_domain = true; + + return pci_host_probe(bridge); +} +EXPORT_SYMBOL_GPL(pci_host_common_init); + +int pci_host_common_probe(struct platform_device *pdev) +{ + const struct pci_ecam_ops *ops; + struct pci_host_bridge *bridge; + + ops = of_device_get_match_data(&pdev->dev); + if (!ops) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(&pdev->dev, 0); + if (!bridge) + return -ENOMEM; - platform_set_drvdata(pdev, bridge->bus); - return 0; + return pci_host_common_init(pdev, bridge, ops); } +EXPORT_SYMBOL_GPL(pci_host_common_probe); -int pci_host_common_remove(struct platform_device *pdev) +void pci_host_common_remove(struct platform_device *pdev) { - struct pci_bus *bus = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = platform_get_drvdata(pdev); pci_lock_rescan_remove(); - pci_stop_root_bus(bus); - pci_remove_root_bus(bus); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); pci_unlock_rescan_remove(); - - return 0; } +EXPORT_SYMBOL_GPL(pci_host_common_remove); + +MODULE_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 dea3ec7592a2..c1bc0d34348f 100644 --- a/drivers/pci/controller/pci-host-generic.c +++ b/drivers/pci/controller/pci-host-generic.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Simple, generic PCI host controller driver targetting firmware-initialised + * Simple, generic PCI host controller driver targeting firmware-initialised * systems and virtual machines (e.g. the PCI emulation provided by kvmtool). * * Copyright (C) 2014 ARM Limited @@ -10,12 +10,13 @@ #include <linux/kernel.h> #include <linux/init.h> -#include <linux/of_address.h> -#include <linux/of_pci.h> +#include <linux/module.h> #include <linux/pci-ecam.h> #include <linux/platform_device.h> -static struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = { +#include "pci-host-common.h" + +static const struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = { .bus_shift = 16, .pci_ops = { .map_bus = pci_ecam_map_bus, @@ -49,8 +50,7 @@ static void __iomem *pci_dw_ecam_map_bus(struct pci_bus *bus, return pci_ecam_map_bus(bus, devfn, where); } -static struct pci_ecam_ops pci_dw_ecam_bus_ops = { - .bus_shift = 20, +static const struct pci_ecam_ops pci_dw_ecam_bus_ops = { .pci_ops = { .map_bus = pci_dw_ecam_map_bus, .read = pci_generic_config_read, @@ -76,25 +76,17 @@ static const struct of_device_id gen_pci_of_match[] = { { }, }; - -static int gen_pci_probe(struct platform_device *pdev) -{ - const struct of_device_id *of_id; - struct pci_ecam_ops *ops; - - of_id = of_match_node(gen_pci_of_match, pdev->dev.of_node); - ops = (struct pci_ecam_ops *)of_id->data; - - return pci_host_common_probe(pdev, ops); -} +MODULE_DEVICE_TABLE(of, gen_pci_of_match); static struct platform_driver gen_pci_driver = { .driver = { .name = "pci-host-generic", .of_match_table = gen_pci_of_match, - .suppress_bind_attrs = true, }, - .probe = gen_pci_probe, + .probe = pci_host_common_probe, .remove = pci_host_common_remove, }; -builtin_platform_driver(gen_pci_driver); +module_platform_driver(gen_pci_driver); + +MODULE_DESCRIPTION("Generic PCI host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c new file mode 100644 index 000000000000..28b3e93d31c0 --- /dev/null +++ b/drivers/pci/controller/pci-hyperv-intf.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) Microsoft Corporation. + * + * Author: + * Haiyang Zhang <haiyangz@microsoft.com> + * + * This small module is a helper driver allows other drivers to + * have a common interface with the Hyper-V PCI frontend driver. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/hyperv.h> +#include <linux/export.h> + +struct hyperv_pci_block_ops hvpci_block_ops; +EXPORT_SYMBOL_GPL(hvpci_block_ops); + +int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned) +{ + if (!hvpci_block_ops.read_block) + return -EOPNOTSUPP; + + return hvpci_block_ops.read_block(dev, buf, buf_len, block_id, + bytes_returned); +} +EXPORT_SYMBOL_GPL(hyperv_read_cfg_blk); + +int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id) +{ + if (!hvpci_block_ops.write_block) + return -EOPNOTSUPP; + + return hvpci_block_ops.write_block(dev, buf, len, block_id); +} +EXPORT_SYMBOL_GPL(hyperv_write_cfg_blk); + +int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)) +{ + if (!hvpci_block_ops.reg_blk_invalidate) + return -EOPNOTSUPP; + + return hvpci_block_ops.reg_blk_invalidate(dev, context, + block_invalidate); +} +EXPORT_SYMBOL_GPL(hyperv_reg_block_invalidate); + +static void __exit exit_hv_pci_intf(void) +{ +} + +static int __init init_hv_pci_intf(void) +{ + return 0; +} + +module_init(init_hv_pci_intf); +module_exit(exit_hv_pci_intf); + +MODULE_DESCRIPTION("Hyper-V PCI Interface"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 9ba4d12c179c..1e237d3538f9 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -40,15 +40,18 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> #include <linux/delay.h> #include <linux/semaphore.h> -#include <linux/irqdomain.h> -#include <asm/irqdomain.h> -#include <asm/apic.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> /* @@ -63,6 +66,8 @@ enum pci_protocol_version_t { PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1), /* Win10 */ PCI_PROTOCOL_VERSION_1_2 = PCI_MAKE_VERSION(1, 2), /* RS1 */ + PCI_PROTOCOL_VERSION_1_3 = PCI_MAKE_VERSION(1, 3), /* Vibranium */ + PCI_PROTOCOL_VERSION_1_4 = PCI_MAKE_VERSION(1, 4), /* WS2022 */ }; #define CPU_AFFINITY_ALL -1ULL @@ -72,15 +77,12 @@ enum pci_protocol_version_t { * first. */ static enum pci_protocol_version_t pci_protocol_versions[] = { + PCI_PROTOCOL_VERSION_1_4, + PCI_PROTOCOL_VERSION_1_3, PCI_PROTOCOL_VERSION_1_2, PCI_PROTOCOL_VERSION_1_1, }; -/* - * Protocol version negotiated by hv_pci_protocol_negotiation(). - */ -static enum pci_protocol_version_t pci_protocol_version; - #define PCI_CONFIG_MMIO_LENGTH 0x2000 #define CFG_PAGE_OFFSET 0x1000 #define CFG_PAGE_SIZE (PCI_CONFIG_MMIO_LENGTH - CFG_PAGE_OFFSET) @@ -93,6 +95,13 @@ static enum pci_protocol_version_t pci_protocol_version; #define SLOT_NAME_SIZE 11 /* + * Size of requestor for VMbus; the value is based on the observation + * that having more than one request outstanding is 'rare', and so 64 + * should be generous in ensuring that we don't ever run out. + */ +#define HV_PCI_RQSTOR_SIZE 64 + +/* * Message Types */ @@ -124,6 +133,9 @@ enum pci_message_type { PCI_RESOURCES_ASSIGNED2 = PCI_MESSAGE_BASE + 0x16, PCI_CREATE_INTERRUPT_MESSAGE2 = PCI_MESSAGE_BASE + 0x17, PCI_DELETE_INTERRUPT_MESSAGE2 = PCI_MESSAGE_BASE + 0x18, /* unused */ + PCI_BUS_RELATIONS2 = PCI_MESSAGE_BASE + 0x19, + PCI_RESOURCES_ASSIGNED3 = PCI_MESSAGE_BASE + 0x1A, + PCI_CREATE_INTERRUPT_MESSAGE3 = PCI_MESSAGE_BASE + 0x1B, PCI_MESSAGE_MAXIMUM }; @@ -169,6 +181,26 @@ struct pci_function_description { u32 ser; /* serial number */ } __packed; +enum pci_device_description_flags { + HV_PCI_DEVICE_FLAG_NONE = 0x0, + HV_PCI_DEVICE_FLAG_NUMA_AFFINITY = 0x1, +}; + +struct pci_function_description2 { + u16 v_id; /* vendor ID */ + u16 d_id; /* device ID */ + u8 rev; + u8 prog_intf; + u8 subclass; + u8 base_class; + u32 subsystem_id; + union win_slot_encoding win_slot; + u32 ser; /* serial number */ + u32 flags; + u16 virtual_numa_node; + u16 reserved; +} __packed; + /** * struct hv_msi_desc * @vector: IDT entry @@ -217,6 +249,21 @@ struct hv_msi_desc2 { u16 processor_array[32]; } __packed; +/* + * struct hv_msi_desc3 - 1.3 version of hv_msi_desc + * Everything is the same as in 'hv_msi_desc2' except that the size of the + * 'vector' field is larger to support bigger vector values. For ex: LPI + * vectors on ARM. + */ +struct hv_msi_desc3 { + u32 vector; + u8 delivery_mode; + u8 reserved; + u16 vector_count; + u16 processor_count; + u16 processor_array[32]; +} __packed; + /** * struct tran_int_desc * @reserved: unused, padding @@ -264,8 +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[0]; }; /* @@ -301,13 +346,19 @@ struct pci_bus_d0_entry { struct pci_bus_relations { struct pci_incoming_message incoming; u32 device_count; - struct pci_function_description func[0]; + struct pci_function_description func[]; +} __packed; + +struct pci_bus_relations2 { + struct pci_incoming_message incoming; + u32 device_count; + struct pci_function_description2 func[]; } __packed; struct pci_q_res_req_response { struct vmpacket_descriptor hdr; s32 status; /* negative values are failures */ - u32 probed_bar[6]; + u32 probed_bar[PCI_STD_NUM_BARS]; } __packed; struct pci_set_power { @@ -359,69 +410,64 @@ struct pci_create_interrupt2 { struct hv_msi_desc2 int_desc; } __packed; -struct pci_delete_interrupt { +struct pci_create_interrupt3 { struct pci_message message_type; union win_slot_encoding wslot; - struct tran_int_desc int_desc; + struct hv_msi_desc3 int_desc; } __packed; -struct pci_dev_incoming { - struct pci_incoming_message incoming; +struct pci_delete_interrupt { + struct pci_message message_type; union win_slot_encoding wslot; + struct tran_int_desc int_desc; } __packed; -struct pci_eject_response { +/* + * Note: the VM must pass a valid block id, wslot and bytes_requested. + */ +struct pci_read_block { struct pci_message message_type; + u32 block_id; union win_slot_encoding wslot; - u32 status; + u32 bytes_requested; } __packed; -static int pci_ring_size = (4 * PAGE_SIZE); +struct pci_read_block_response { + struct vmpacket_descriptor hdr; + u32 status; + u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX]; +} __packed; /* - * Definitions or interrupt steering hypercall. + * Note: the VM must pass a valid block id, wslot and byte_count. */ -#define HV_PARTITION_ID_SELF ((u64)-1) -#define HVCALL_RETARGET_INTERRUPT 0x7e - -struct hv_interrupt_entry { - u32 source; /* 1 for MSI(-X) */ - u32 reserved1; - u32 address; - u32 data; -}; - -#define HV_VP_SET_BANK_COUNT_MAX 5 /* current implementation limit */ - -struct hv_vp_set { - u64 format; /* 0 (HvGenericSetSparse4k) */ - u64 valid_banks; - u64 masks[HV_VP_SET_BANK_COUNT_MAX]; -}; +struct pci_write_block { + struct pci_message message_type; + u32 block_id; + union win_slot_encoding wslot; + u32 byte_count; + u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX]; +} __packed; -/* - * flags for hv_device_interrupt_target.flags - */ -#define HV_DEVICE_INTERRUPT_TARGET_MULTICAST 1 -#define HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET 2 +struct pci_dev_inval_block { + struct pci_incoming_message incoming; + union win_slot_encoding wslot; + u64 block_mask; +} __packed; -struct hv_device_interrupt_target { - u32 vector; - u32 flags; - union { - u64 vp_mask; - struct hv_vp_set vp_set; - }; -}; +struct pci_dev_incoming { + struct pci_incoming_message incoming; + union win_slot_encoding wslot; +} __packed; -struct retarget_msi_interrupt { - u64 partition_id; /* use "self" */ - u64 device_id; - struct hv_interrupt_entry int_entry; - u64 reserved2; - struct hv_device_interrupt_target int_target; +struct pci_eject_response { + struct pci_message message_type; + union win_slot_encoding wslot; + u32 status; } __packed; +static int pci_ring_size = VMBUS_RING_SIZE(SZ_16K); + /* * Driver specific state. */ @@ -430,14 +476,24 @@ enum hv_pcibus_state { hv_pcibus_init = 0, hv_pcibus_probed, hv_pcibus_installed, - hv_pcibus_removed, + hv_pcibus_removing, hv_pcibus_maximum }; struct hv_pcibus_device { +#ifdef CONFIG_X86 struct pci_sysdata sysdata; +#elif defined(CONFIG_ARM64) + struct pci_config_window sysdata; +#endif + struct pci_host_bridge *bridge; + struct fwnode_handle *fwnode; + /* Protocol version negotiated with the host */ + enum pci_protocol_version_t protocol_version; + + struct mutex state_lock; enum hv_pcibus_state state; - refcount_t remove_lock; + struct hv_device *hdev; resource_size_t low_mmio_space; resource_size_t high_mmio_space; @@ -445,27 +501,21 @@ struct hv_pcibus_device { struct resource *low_mmio_res; struct resource *high_mmio_res; struct completion *survey_event; - struct completion remove_event; struct pci_bus *pci_bus; spinlock_t config_lock; /* Avoid two threads writing index page */ spinlock_t device_list_lock; /* Protect lists below */ void __iomem *cfg_addr; - struct list_head resources_for_children; - struct list_head children; struct list_head dr_list; - struct msi_domain_info msi_info; - struct msi_controller msi_chip; struct irq_domain *irq_domain; - /* hypercall arg, must not cross page boundary */ - struct retarget_msi_interrupt retarget_msi_interrupt_params; - - spinlock_t retarget_msi_interrupt_lock; - struct workqueue_struct *wq; + + /* Highest slot of child device with resources allocated */ + int wslot_res_allocated; + bool use_calls; /* Use hypercalls to access mmio cfg space */ }; /* @@ -478,36 +528,44 @@ struct hv_dr_work { struct hv_pcibus_device *bus; }; +struct hv_pcidev_description { + u16 v_id; /* vendor ID */ + u16 d_id; /* device ID */ + u8 rev; + u8 prog_intf; + u8 subclass; + u8 base_class; + u32 subsystem_id; + union win_slot_encoding win_slot; + u32 ser; /* serial number */ + u32 flags; + u16 virtual_numa_node; +}; + struct hv_dr_state { struct list_head list_entry; u32 device_count; - struct pci_function_description func[0]; -}; - -enum hv_pcichild_state { - hv_pcichild_init = 0, - hv_pcichild_requirements, - hv_pcichild_resourced, - hv_pcichild_ejecting, - hv_pcichild_maximum + struct hv_pcidev_description func[] __counted_by(device_count); }; struct hv_pci_dev { /* List protected by pci_rescan_remove_lock */ struct list_head list_entry; refcount_t refs; - enum hv_pcichild_state state; struct pci_slot *pci_slot; - struct pci_function_description desc; + struct hv_pcidev_description desc; bool reported_missing; struct hv_pcibus_device *hbus; struct work_struct wrk; + void (*block_invalidate)(void *context, u64 block_mask); + void *invalidate_context; + /* * What would be observed if one wrote 0xFFFFFFFF to a BAR and then * read it back, for each of the BAR offsets within config space. */ - u32 probed_bar[6]; + u32 probed_bar[PCI_STD_NUM_BARS]; }; struct hv_pci_compl { @@ -517,6 +575,437 @@ struct hv_pci_compl { static void hv_pci_onchannelcallback(void *context); +#ifdef CONFIG_X86 +#define DELIVERY_MODE APIC_DELIVERY_MODE_FIXED +#define HV_MSI_CHIP_FLAGS MSI_CHIP_FLAG_SET_ACK + +static int hv_pci_irqchip_init(void) +{ + return 0; +} + +static struct irq_domain *hv_pci_get_root_domain(void) +{ + return x86_vector_domain; +} + +static unsigned int hv_msi_get_int_vector(struct irq_data *data) +{ + struct irq_cfg *cfg = irqd_cfg(data); + + return cfg->vector; +} + +#define hv_msi_prepare pci_msi_prepare + +/** + * hv_irq_retarget_interrupt() - "Unmask" the IRQ by setting its current + * affinity. + * @data: Describes the IRQ + * + * Build new a destination for the MSI and make a hypercall to + * update the Interrupt Redirection Table. "Device Logical ID" + * is built out of this PCI bus's instance GUID and the function + * number of the device. + */ +static void hv_irq_retarget_interrupt(struct irq_data *data) +{ + struct msi_desc *msi_desc = irq_data_get_msi_desc(data); + struct hv_retarget_device_interrupt *params; + struct tran_int_desc *int_desc; + struct hv_pcibus_device *hbus; + const struct cpumask *dest; + cpumask_var_t tmp; + struct pci_bus *pbus; + struct pci_dev *pdev; + unsigned long flags; + u32 var_size = 0; + int cpu, nr_bank; + u64 res; + + dest = irq_data_get_effective_affinity_mask(data); + pdev = msi_desc_to_pci_dev(msi_desc); + pbus = pdev->bus; + hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); + int_desc = data->chip_data; + if (!int_desc) { + dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n", + __func__, data->irq); + return; + } + + local_irq_save(flags); + + params = *this_cpu_ptr(hyperv_pcpu_input_arg); + memset(params, 0, sizeof(*params)); + params->partition_id = HV_PARTITION_ID_SELF; + params->int_entry.source = HV_INTERRUPT_SOURCE_MSI; + params->int_entry.msi_entry.address.as_uint32 = int_desc->address & 0xffffffff; + params->int_entry.msi_entry.data.as_uint32 = int_desc->data; + params->device_id = (hbus->hdev->dev_instance.b[5] << 24) | + (hbus->hdev->dev_instance.b[4] << 16) | + (hbus->hdev->dev_instance.b[7] << 8) | + (hbus->hdev->dev_instance.b[6] & 0xf8) | + PCI_FUNC(pdev->devfn); + params->int_target.vector = hv_msi_get_int_vector(data); + + if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) { + /* + * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the + * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides + * with >64 VP support. + * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED + * is not sufficient for this hypercall. + */ + params->int_target.flags |= + HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET; + + if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) { + res = 1; + goto out; + } + + cpumask_and(tmp, dest, cpu_online_mask); + nr_bank = cpumask_to_vpset(¶ms->int_target.vp_set, tmp); + free_cpumask_var(tmp); + + if (nr_bank <= 0) { + res = 1; + goto out; + } + + /* + * var-sized hypercall, var-size starts after vp_mask (thus + * vp_set.format does not count, but vp_set.valid_bank_mask + * does). + */ + var_size = 1 + nr_bank; + } else { + for_each_cpu_and(cpu, dest, cpu_online_mask) { + params->int_target.vp_mask |= + (1ULL << hv_cpu_number_to_vp_number(cpu)); + } + } + + res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17), + params, NULL); + +out: + local_irq_restore(flags); + + /* + * During hibernation, when a CPU is offlined, the kernel tries + * to move the interrupt to the remaining CPUs that haven't + * been offlined yet. In this case, the below hv_do_hypercall() + * always fails since the vmbus channel has been closed: + * refer to cpu_disable_common() -> fixup_irqs() -> + * irq_migrate_all_off_this_cpu() -> migrate_one_irq(). + * + * Suppress the error message for hibernation because the failure + * during hibernation does not matter (at this time all the devices + * have been frozen). Note: the correct affinity info is still updated + * into the irqdata data structure in migrate_one_irq() -> + * irq_do_set_affinity(), so later when the VM resumes, + * hv_pci_restore_msi_state() is able to correctly restore the + * interrupt with the correct affinity. + */ + if (!hv_result_success(res) && hbus->state != hv_pcibus_removing) + dev_err(&hbus->hdev->device, + "%s() failed: %#llx", __func__, res); +} + +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 + * of room at the start to allow for SPIs to be specified through ACPI and + * starting with a power of two to satisfy power of 2 multi-MSI requirement. + */ +#define HV_PCI_MSI_SPI_START 64 +#define HV_PCI_MSI_SPI_NR (1020 - HV_PCI_MSI_SPI_START) +#define DELIVERY_MODE 0 +#define HV_MSI_CHIP_FLAGS MSI_CHIP_FLAG_SET_EOI +#define hv_msi_prepare NULL + +struct hv_pci_chip_data { + DECLARE_BITMAP(spi_map, HV_PCI_MSI_SPI_NR); + struct mutex map_lock; +}; + +/* Hyper-V vPCI MSI GIC IRQ domain */ +static struct irq_domain *hv_msi_gic_irq_domain; + +/* Hyper-V PCI MSI IRQ chip */ +static struct irq_chip hv_arm64_msi_irq_chip = { + .name = "MSI", + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent +}; + +static unsigned int hv_msi_get_int_vector(struct irq_data *irqd) +{ + return irqd->parent_data->hwirq; +} + +/* + * @nr_bm_irqs: Indicates the number of IRQs that were allocated from + * the bitmap. + * @nr_dom_irqs: Indicates the number of IRQs that were allocated from + * the parent domain. + */ +static void hv_pci_vec_irq_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_bm_irqs, + unsigned int nr_dom_irqs) +{ + struct hv_pci_chip_data *chip_data = domain->host_data; + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + int first = d->hwirq - HV_PCI_MSI_SPI_START; + int i; + + mutex_lock(&chip_data->map_lock); + bitmap_release_region(chip_data->spi_map, + first, + get_count_order(nr_bm_irqs)); + mutex_unlock(&chip_data->map_lock); + for (i = 0; i < nr_dom_irqs; i++) { + if (i) + d = irq_domain_get_irq_data(domain, virq + i); + irq_domain_reset_irq_data(d); + } + + irq_domain_free_irqs_parent(domain, virq, nr_dom_irqs); +} + +static void hv_pci_vec_irq_domain_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs) +{ + hv_pci_vec_irq_free(domain, virq, nr_irqs, nr_irqs); +} + +static int hv_pci_vec_alloc_device_irq(struct irq_domain *domain, + unsigned int nr_irqs, + irq_hw_number_t *hwirq) +{ + struct hv_pci_chip_data *chip_data = domain->host_data; + int index; + + /* Find and allocate region from the SPI bitmap */ + mutex_lock(&chip_data->map_lock); + index = bitmap_find_free_region(chip_data->spi_map, + HV_PCI_MSI_SPI_NR, + get_count_order(nr_irqs)); + mutex_unlock(&chip_data->map_lock); + if (index < 0) + return -ENOSPC; + + *hwirq = index + HV_PCI_MSI_SPI_START; + + return 0; +} + +static int hv_pci_vec_irq_gic_domain_alloc(struct irq_domain *domain, + unsigned int virq, + irq_hw_number_t hwirq) +{ + struct irq_fwspec fwspec; + struct irq_data *d; + int ret; + + fwspec.fwnode = domain->parent->fwnode; + 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) + return ret; + + /* + * Since the interrupt specifier is not coming from ACPI or DT, the + * trigger type will need to be set explicitly. Otherwise, it will be + * set to whatever is in the GIC configuration. + */ + d = irq_domain_get_irq_data(domain->parent, virq); + + return d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING); +} + +static int hv_pci_vec_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + irq_hw_number_t hwirq; + unsigned int i; + int ret; + + ret = hv_pci_vec_alloc_device_irq(domain, nr_irqs, &hwirq); + if (ret) + return ret; + + for (i = 0; i < nr_irqs; i++) { + ret = hv_pci_vec_irq_gic_domain_alloc(domain, virq + i, + hwirq + i); + if (ret) { + hv_pci_vec_irq_free(domain, virq, nr_irqs, i); + return ret; + } + + irq_domain_set_hwirq_and_chip(domain, virq + i, + hwirq + i, + &hv_arm64_msi_irq_chip, + domain->host_data); + pr_debug("pID:%d vID:%u\n", (int)(hwirq + i), virq + i); + } + + return 0; +} + +/* + * Pick the first cpu as the irq affinity that can be temporarily used for + * composing MSI from the hypervisor. GIC will eventually set the right + * affinity for the irq and the 'unmask' will retarget the interrupt to that + * cpu. + */ +static int hv_pci_vec_irq_domain_activate(struct irq_domain *domain, + struct irq_data *irqd, bool reserve) +{ + int cpu = cpumask_first(cpu_present_mask); + + irq_data_update_effective_affinity(irqd, cpumask_of(cpu)); + + return 0; +} + +static const struct irq_domain_ops hv_pci_domain_ops = { + .alloc = hv_pci_vec_irq_domain_alloc, + .free = hv_pci_vec_irq_domain_free, + .activate = hv_pci_vec_irq_domain_activate, +}; + +#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); + if (!chip_data) + return ret; + + mutex_init(&chip_data->map_lock); + fn = irq_domain_alloc_named_fwnode("hv_vpci_arm64"); + if (!fn) + goto free_chip; + + /* + * IRQ domain once enabled, should not be removed since there is no + * way to ensure that all the corresponding devices are also gone and + * no interrupts will be generated. + */ +#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"); + goto free_chip; + } + + return 0; + +free_chip: + kfree(chip_data); + if (fn) + irq_domain_free_fwnode(fn); + + return ret; +} + +static struct irq_domain *hv_pci_get_root_domain(void) +{ + return hv_msi_gic_irq_domain; +} + +/* + * SPIs are used for interrupts of PCI devices and SPIs is managed via GICD + * registers which Hyper-V already supports, so no hypercall needed. + */ +static void hv_arch_irq_unmask(struct irq_data *data) { } +#endif /* CONFIG_ARM64 */ + /** * hv_pci_generic_compl() - Invoked for a completion packet * @context: Set up by the sender of the packet. @@ -532,11 +1021,7 @@ static void hv_pci_generic_compl(void *context, struct pci_response *resp, { struct hv_pci_compl *comp_pkt = context; - if (resp_packet_size >= offsetofend(struct pci_response, status)) - comp_pkt->completion_status = resp->status; - else - comp_pkt->completion_status = -1; - + comp_pkt->completion_status = resp->status; complete(&comp_pkt->host_event); } @@ -554,9 +1039,6 @@ static void put_pcichild(struct hv_pci_dev *hpdev) kfree(hpdev); } -static void get_hvpcibus(struct hv_pcibus_device *hv_pcibus); -static void put_hvpcibus(struct hv_pcibus_device *hv_pcibus); - /* * There is no good way to get notified from vmbus_onoffer_rescind(), * so let's use polling here, since this is not a hot path. @@ -612,6 +1094,70 @@ static int wslot_to_devfn(u32 wslot) return PCI_DEVFN(slot_no.bits.dev, slot_no.bits.func); } +static void hv_pci_read_mmio(struct device *dev, phys_addr_t gpa, int size, u32 *val) +{ + struct hv_mmio_read_input *in; + struct hv_mmio_read_output *out; + u64 ret; + + /* + * Must be called with interrupts disabled so it is safe + * to use the per-cpu input argument page. Use it for + * both input and output. + */ + in = *this_cpu_ptr(hyperv_pcpu_input_arg); + out = *this_cpu_ptr(hyperv_pcpu_input_arg) + sizeof(*in); + in->gpa = gpa; + in->size = size; + + ret = hv_do_hypercall(HVCALL_MMIO_READ, in, out); + if (hv_result_success(ret)) { + switch (size) { + case 1: + *val = *(u8 *)(out->data); + break; + case 2: + *val = *(u16 *)(out->data); + break; + default: + *val = *(u32 *)(out->data); + break; + } + } else + dev_err(dev, "MMIO read hypercall error %llx addr %llx size %d\n", + ret, gpa, size); +} + +static void hv_pci_write_mmio(struct device *dev, phys_addr_t gpa, int size, u32 val) +{ + struct hv_mmio_write_input *in; + u64 ret; + + /* + * Must be called with interrupts disabled so it is safe + * to use the per-cpu input argument memory. + */ + in = *this_cpu_ptr(hyperv_pcpu_input_arg); + in->gpa = gpa; + in->size = size; + switch (size) { + case 1: + *(u8 *)(in->data) = val; + break; + case 2: + *(u16 *)(in->data) = val; + break; + default: + *(u32 *)(in->data) = val; + break; + } + + ret = hv_do_hypercall(HVCALL_MMIO_WRITE, in, NULL); + if (!hv_result_success(ret)) + dev_err(dev, "MMIO write hypercall error %llx addr %llx size %d\n", + ret, gpa, size); +} + /* * PCI Configuration Space for these root PCI buses is implemented as a pair * of pages in memory-mapped I/O space. Writing to the first page chooses @@ -630,8 +1176,10 @@ static int wslot_to_devfn(u32 wslot) static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, int size, u32 *val) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + int offset = where + CFG_PAGE_OFFSET; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; /* * If the attempt is to read the IDs or the ROM BAR, simulate that. @@ -650,8 +1198,8 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, PCI_CAPABILITY_LIST) { /* ROM BARs are unimplemented */ *val = 0; - } else if (where >= PCI_INTERRUPT_LINE && where + size <= - PCI_INTERRUPT_PIN) { + } else if ((where >= PCI_INTERRUPT_LINE && where + size <= PCI_INTERRUPT_PIN) || + (where >= PCI_INTERRUPT_PIN && where + size <= PCI_MIN_GNT)) { /* * Interrupt Line and Interrupt PIN are hard-wired to zero * because this front-end only supports message-signaled @@ -659,56 +1207,79 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, */ *val = 0; } else if (where + size <= CFG_PAGE_SIZE) { - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); - /* Choose the function to be read. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start reading. */ - mb(); - /* Read from that function's config space. */ - switch (size) { - case 1: - *val = readb(addr); - break; - case 2: - *val = readw(addr); - break; - default: - *val = readl(addr); - break; + + spin_lock_irqsave(&hbus->config_lock, flags); + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + offset; + + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_read_mmio(dev, addr, size, val); + } else { + void __iomem *addr = hbus->cfg_addr + offset; + + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before reading. */ + mb(); + /* Read from that function's config space. */ + switch (size) { + case 1: + *val = readb(addr); + break; + case 2: + *val = readw(addr); + break; + default: + *val = readl(addr); + break; + } + /* + * Make sure the read was done before we release the + * spinlock allowing consecutive reads/writes. + */ + mb(); } - /* - * Make sure the read was done before we release the spinlock - * allowing consecutive reads/writes. - */ - mb(); - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + spin_unlock_irqrestore(&hbus->config_lock, flags); } else { - dev_err(&hpdev->hbus->hdev->device, - "Attempt to read beyond a function's config space.\n"); + dev_err(dev, "Attempt to read beyond a function's config space.\n"); } } static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + u32 val; u16 ret; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + - PCI_VENDOR_ID; - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); + spin_lock_irqsave(&hbus->config_lock, flags); - /* Choose the function to be read. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start reading. */ - mb(); - /* Read from that function's config space. */ - ret = readw(addr); - /* - * mb() is not required here, because the spin_unlock_irqrestore() - * is a barrier. - */ + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + + CFG_PAGE_OFFSET + PCI_VENDOR_ID; - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_read_mmio(dev, addr, 2, &val); + ret = val; /* Truncates to 16 bits */ + } else { + void __iomem *addr = hbus->cfg_addr + CFG_PAGE_OFFSET + + PCI_VENDOR_ID; + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before we start reading. */ + mb(); + /* Read from that function's config space. */ + ret = readw(addr); + /* + * mb() is not required here, because the + * spin_unlock_irqrestore() is a barrier. + */ + } + + spin_unlock_irqrestore(&hbus->config_lock, flags); return ret; } @@ -723,39 +1294,51 @@ static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where, int size, u32 val) { + struct hv_pcibus_device *hbus = hpdev->hbus; + struct device *dev = &hbus->hdev->device; + int offset = where + CFG_PAGE_OFFSET; unsigned long flags; - void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <= PCI_CAPABILITY_LIST) { /* SSIDs and ROM BARs are read-only */ } else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) { - spin_lock_irqsave(&hpdev->hbus->config_lock, flags); - /* Choose the function to be written. (See comment above) */ - writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); - /* Make sure the function was chosen before we start writing. */ - wmb(); - /* Write to that function's config space. */ - switch (size) { - case 1: - writeb(val, addr); - break; - case 2: - writew(val, addr); - break; - default: - writel(val, addr); - break; + spin_lock_irqsave(&hbus->config_lock, flags); + + if (hbus->use_calls) { + phys_addr_t addr = hbus->mem_config->start + offset; + + hv_pci_write_mmio(dev, hbus->mem_config->start, 4, + hpdev->desc.win_slot.slot); + hv_pci_write_mmio(dev, addr, size, val); + } else { + void __iomem *addr = hbus->cfg_addr + offset; + + /* Choose the function to write. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hbus->cfg_addr); + /* Make sure the function was chosen before writing. */ + wmb(); + /* Write to that function's config space. */ + switch (size) { + case 1: + writeb(val, addr); + break; + case 2: + writew(val, addr); + break; + default: + writel(val, addr); + break; + } + /* + * Make sure the write was done before we release the + * spinlock allowing consecutive reads/writes. + */ + mb(); } - /* - * Make sure the write was done before we release the spinlock - * allowing consecutive reads/writes. - */ - mb(); - spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + spin_unlock_irqrestore(&hbus->config_lock, flags); } else { - dev_err(&hpdev->hbus->hdev->device, - "Attempt to write beyond a function's config space.\n"); + dev_err(dev, "Attempt to write beyond a function's config space.\n"); } } @@ -821,6 +1404,254 @@ static struct pci_ops hv_pcifront_ops = { .write = hv_pcifront_write_config, }; +/* + * Paravirtual backchannel + * + * Hyper-V SR-IOV provides a backchannel mechanism in software for + * communication between a VF driver and a PF driver. These + * "configuration blocks" are similar in concept to PCI configuration space, + * but instead of doing reads and writes in 32-bit chunks through a very slow + * path, packets of up to 128 bytes can be sent or received asynchronously. + * + * Nearly every SR-IOV device contains just such a communications channel in + * hardware, so using this one in software is usually optional. Using the + * software channel, however, allows driver implementers to leverage software + * tools that fuzz the communications channel looking for vulnerabilities. + * + * The usage model for these packets puts the responsibility for reading or + * writing on the VF driver. The VF driver sends a read or a write packet, + * indicating which "block" is being referred to by number. + * + * If the PF driver wishes to initiate communication, it can "invalidate" one or + * more of the first 64 blocks. This invalidation is delivered via a callback + * supplied to the VF driver by this driver. + * + * No protocol is implied, except that supplied by the PF and VF drivers. + */ + +struct hv_read_config_compl { + struct hv_pci_compl comp_pkt; + void *buf; + unsigned int len; + unsigned int bytes_returned; +}; + +/** + * hv_pci_read_config_compl() - Invoked when a response packet + * for a read config block operation arrives. + * @context: Identifies the read config operation + * @resp: The response packet itself + * @resp_packet_size: Size in bytes of the response packet + */ +static void hv_pci_read_config_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct hv_read_config_compl *comp = context; + struct pci_read_block_response *read_resp = + (struct pci_read_block_response *)resp; + unsigned int data_len, hdr_len; + + hdr_len = offsetof(struct pci_read_block_response, bytes); + if (resp_packet_size < hdr_len) { + comp->comp_pkt.completion_status = -1; + goto out; + } + + data_len = resp_packet_size - hdr_len; + if (data_len > 0 && read_resp->status == 0) { + comp->bytes_returned = min(comp->len, data_len); + memcpy(comp->buf, read_resp->bytes, comp->bytes_returned); + } else { + comp->bytes_returned = 0; + } + + comp->comp_pkt.completion_status = read_resp->status; +out: + complete(&comp->comp_pkt.host_event); +} + +/** + * hv_read_config_block() - Sends a read config block request to + * the back-end driver running in the Hyper-V parent partition. + * @pdev: The PCI driver's representation for this device. + * @buf: Buffer into which the config block will be copied. + * @len: Size in bytes of buf. + * @block_id: Identifies the config block which has been requested. + * @bytes_returned: Size which came back from the back-end driver. + * + * Return: 0 on success, -errno on failure + */ +static int hv_read_config_block(struct pci_dev *pdev, void *buf, + unsigned int len, unsigned int block_id, + unsigned int *bytes_returned) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct { + struct pci_packet pkt; + char buf[sizeof(struct pci_read_block)]; + } pkt; + struct hv_read_config_compl comp_pkt; + struct pci_read_block *read_blk; + int ret; + + if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX) + return -EINVAL; + + init_completion(&comp_pkt.comp_pkt.host_event); + comp_pkt.buf = buf; + comp_pkt.len = len; + + memset(&pkt, 0, sizeof(pkt)); + pkt.pkt.completion_func = hv_pci_read_config_compl; + pkt.pkt.compl_ctxt = &comp_pkt; + read_blk = (struct pci_read_block *)pkt.buf; + read_blk->message_type.type = PCI_READ_BLOCK; + read_blk->wslot.slot = devfn_to_wslot(pdev->devfn); + read_blk->block_id = block_id; + read_blk->bytes_requested = len; + + ret = vmbus_sendpacket(hbus->hdev->channel, read_blk, + sizeof(*read_blk), (unsigned long)&pkt.pkt, + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + return ret; + + ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event); + if (ret) + return ret; + + if (comp_pkt.comp_pkt.completion_status != 0 || + comp_pkt.bytes_returned == 0) { + dev_err(&hbus->hdev->device, + "Read Config Block failed: 0x%x, bytes_returned=%d\n", + comp_pkt.comp_pkt.completion_status, + comp_pkt.bytes_returned); + return -EIO; + } + + *bytes_returned = comp_pkt.bytes_returned; + return 0; +} + +/** + * hv_pci_write_config_compl() - Invoked when a response packet for a write + * config block operation arrives. + * @context: Identifies the write config operation + * @resp: The response packet itself + * @resp_packet_size: Size in bytes of the response packet + */ +static void hv_pci_write_config_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct hv_pci_compl *comp_pkt = context; + + comp_pkt->completion_status = resp->status; + complete(&comp_pkt->host_event); +} + +/** + * hv_write_config_block() - Sends a write config block request to the + * back-end driver running in the Hyper-V parent partition. + * @pdev: The PCI driver's representation for this device. + * @buf: Buffer from which the config block will be copied. + * @len: Size in bytes of buf. + * @block_id: Identifies the config block which is being written. + * + * Return: 0 on success, -errno on failure + */ +static int hv_write_config_block(struct pci_dev *pdev, void *buf, + unsigned int len, unsigned int block_id) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct { + struct pci_packet pkt; + char buf[sizeof(struct pci_write_block)]; + u32 reserved; + } pkt; + struct hv_pci_compl comp_pkt; + struct pci_write_block *write_blk; + u32 pkt_size; + int ret; + + if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX) + return -EINVAL; + + init_completion(&comp_pkt.host_event); + + memset(&pkt, 0, sizeof(pkt)); + pkt.pkt.completion_func = hv_pci_write_config_compl; + pkt.pkt.compl_ctxt = &comp_pkt; + write_blk = (struct pci_write_block *)pkt.buf; + write_blk->message_type.type = PCI_WRITE_BLOCK; + write_blk->wslot.slot = devfn_to_wslot(pdev->devfn); + write_blk->block_id = block_id; + write_blk->byte_count = len; + memcpy(write_blk->bytes, buf, len); + pkt_size = offsetof(struct pci_write_block, bytes) + len; + /* + * This quirk is required on some hosts shipped around 2018, because + * these hosts don't check the pkt_size correctly (new hosts have been + * fixed since early 2019). The quirk is also safe on very old hosts + * and new hosts, because, on them, what really matters is the length + * specified in write_blk->byte_count. + */ + pkt_size += sizeof(pkt.reserved); + + ret = vmbus_sendpacket(hbus->hdev->channel, write_blk, pkt_size, + (unsigned long)&pkt.pkt, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + return ret; + + ret = wait_for_response(hbus->hdev, &comp_pkt.host_event); + if (ret) + return ret; + + if (comp_pkt.completion_status != 0) { + dev_err(&hbus->hdev->device, + "Write Config Block failed: 0x%x\n", + comp_pkt.completion_status); + return -EIO; + } + + return 0; +} + +/** + * hv_register_block_invalidate() - Invoked when a config block invalidation + * arrives from the back-end driver. + * @pdev: The PCI driver's representation for this device. + * @context: Identifies the device. + * @block_invalidate: Identifies all of the blocks being invalidated. + * + * Return: 0 on success, -errno on failure + */ +static int hv_register_block_invalidate(struct pci_dev *pdev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct hv_pci_dev *hpdev; + + hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn)); + if (!hpdev) + return -ENODEV; + + hpdev->block_invalidate = block_invalidate; + hpdev->invalidate_context = context; + + put_pcichild(hpdev); + return 0; + +} + /* Interrupt management hooks */ static void hv_int_desc_free(struct hv_pci_dev *hpdev, struct tran_int_desc *int_desc) @@ -831,21 +1662,24 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev, u8 buffer[sizeof(struct pci_delete_interrupt)]; } ctxt; + if (!int_desc->vector_count) { + kfree(int_desc); + return; + } memset(&ctxt, 0, sizeof(ctxt)); - int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message; + int_pkt = (struct pci_delete_interrupt *)ctxt.buffer; int_pkt->message_type.type = PCI_DELETE_INTERRUPT_MESSAGE; int_pkt->wslot.slot = hpdev->desc.win_slot.slot; int_pkt->int_desc = *int_desc; vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt, sizeof(*int_pkt), - (unsigned long)&ctxt.pkt, VM_PKT_DATA_INBAND, 0); + 0, VM_PKT_DATA_INBAND, 0); kfree(int_desc); } /** * hv_msi_free() - Free the MSI. * @domain: The interrupt domain pointer - * @info: Extra MSI-related context * @irq: Identifies the IRQ. * * The Hyper-V parent partition and hypervisor are tracking the @@ -853,8 +1687,7 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev, * table up to date. This callback sends a message that frees * the IRT entry and related tracking nonsense. */ -static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info, - unsigned int irq) +static void hv_msi_free(struct irq_domain *domain, unsigned int irq) { struct hv_pcibus_device *hbus; struct hv_pci_dev *hpdev; @@ -864,7 +1697,7 @@ static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info, struct msi_desc *msi = irq_data_get_msi_desc(irq_data); pdev = msi_desc_to_pci_dev(msi); - hbus = info->data; + hbus = domain->host_data; int_desc = irq_data_get_irq_chip_data(irq_data); if (!int_desc) return; @@ -880,123 +1713,18 @@ static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info, put_pcichild(hpdev); } -static int hv_set_affinity(struct irq_data *data, const struct cpumask *dest, - bool force) -{ - struct irq_data *parent = data->parent_data; - - return parent->chip->irq_set_affinity(parent, dest, force); -} - 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); } -/** - * hv_irq_unmask() - "Unmask" the IRQ by setting its current - * affinity. - * @data: Describes the IRQ - * - * Build new a destination for the MSI and make a hypercall to - * update the Interrupt Redirection Table. "Device Logical ID" - * is built out of this PCI bus's instance GUID and the function - * number of the device. - */ static void hv_irq_unmask(struct irq_data *data) { - struct msi_desc *msi_desc = irq_data_get_msi_desc(data); - struct irq_cfg *cfg = irqd_cfg(data); - struct retarget_msi_interrupt *params; - struct hv_pcibus_device *hbus; - struct cpumask *dest; - struct pci_bus *pbus; - struct pci_dev *pdev; - unsigned long flags; - u32 var_size = 0; - int cpu_vmbus; - int cpu; - u64 res; - - dest = irq_data_get_effective_affinity_mask(data); - pdev = msi_desc_to_pci_dev(msi_desc); - pbus = pdev->bus; - hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); - - spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags); - - params = &hbus->retarget_msi_interrupt_params; - memset(params, 0, sizeof(*params)); - params->partition_id = HV_PARTITION_ID_SELF; - params->int_entry.source = 1; /* MSI(-X) */ - params->int_entry.address = msi_desc->msg.address_lo; - params->int_entry.data = msi_desc->msg.data; - params->device_id = (hbus->hdev->dev_instance.b[5] << 24) | - (hbus->hdev->dev_instance.b[4] << 16) | - (hbus->hdev->dev_instance.b[7] << 8) | - (hbus->hdev->dev_instance.b[6] & 0xf8) | - PCI_FUNC(pdev->devfn); - params->int_target.vector = cfg->vector; - - /* - * Honoring apic->irq_delivery_mode set to dest_Fixed by - * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a - * spurious interrupt storm. Not doing so does not seem to have a - * negative effect (yet?). - */ - - if (pci_protocol_version >= PCI_PROTOCOL_VERSION_1_2) { - /* - * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the - * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides - * with >64 VP support. - * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED - * is not sufficient for this hypercall. - */ - params->int_target.flags |= - HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET; - params->int_target.vp_set.valid_banks = - (1ull << HV_VP_SET_BANK_COUNT_MAX) - 1; - - /* - * var-sized hypercall, var-size starts after vp_mask (thus - * vp_set.format does not count, but vp_set.valid_banks does). - */ - var_size = 1 + HV_VP_SET_BANK_COUNT_MAX; - - for_each_cpu_and(cpu, dest, cpu_online_mask) { - cpu_vmbus = hv_cpu_number_to_vp_number(cpu); - - if (cpu_vmbus >= HV_VP_SET_BANK_COUNT_MAX * 64) { - dev_err(&hbus->hdev->device, - "too high CPU %d", cpu_vmbus); - res = 1; - goto exit_unlock; - } + hv_arch_irq_unmask(data); - params->int_target.vp_set.masks[cpu_vmbus / 64] |= - (1ULL << (cpu_vmbus & 63)); - } - } else { - for_each_cpu_and(cpu, dest, cpu_online_mask) { - params->int_target.vp_mask |= - (1ULL << hv_cpu_number_to_vp_number(cpu)); - } - } - - res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17), - params, NULL); - -exit_unlock: - spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags); - - if (res) { - dev_err(&hbus->hdev->device, - "%s() failed: %#llx", __func__, res); - return; - } - - pci_msi_unmask_irq(data); + if (data->parent_data->chip->irq_unmask) + irq_chip_unmask_parent(data); } struct compose_comp_ctxt { @@ -1011,20 +1739,25 @@ static void hv_pci_compose_compl(void *context, struct pci_response *resp, struct pci_create_int_response *int_resp = (struct pci_create_int_response *)resp; + if (resp_packet_size < sizeof(*int_resp)) { + comp_pkt->comp_pkt.completion_status = -1; + goto out; + } comp_pkt->comp_pkt.completion_status = resp->status; comp_pkt->int_desc = int_resp->int_desc; +out: complete(&comp_pkt->comp_pkt.host_event); } static u32 hv_compose_msi_req_v1( - struct pci_create_interrupt *int_pkt, struct cpumask *affinity, - u32 slot, u8 vector) + struct pci_create_interrupt *int_pkt, + u32 slot, u8 vector, u16 vector_count) { int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; - int_pkt->int_desc.vector_count = 1; - int_pkt->int_desc.delivery_mode = dest_Fixed; + int_pkt->int_desc.vector_count = vector_count; + int_pkt->int_desc.delivery_mode = DELIVERY_MODE; /* * Create MSI w/ dummy vCPU set, overwritten by subsequent retarget in @@ -1035,23 +1768,93 @@ static u32 hv_compose_msi_req_v1( return sizeof(*int_pkt); } -static u32 hv_compose_msi_req_v2( - struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity, - u32 slot, u8 vector) +/* + * The vCPU selected by hv_compose_multi_msi_req_get_cpu() and + * hv_compose_msi_req_get_cpu() is a "dummy" vCPU because the final vCPU to be + * interrupted is specified later in hv_irq_unmask() and communicated to Hyper-V + * via the HVCALL_RETARGET_INTERRUPT hypercall. But the choice of dummy vCPU is + * not irrelevant because Hyper-V chooses the physical CPU to handle the + * interrupts based on the vCPU specified in message sent to the vPCI VSP in + * hv_compose_msi_msg(). Hyper-V's choice of pCPU is not visible to the guest, + * but assigning too many vPCI device interrupts to the same pCPU can cause a + * performance bottleneck. So we spread out the dummy vCPUs to influence Hyper-V + * to spread out the pCPUs that it selects. + * + * For the single-MSI and MSI-X cases, it's OK for hv_compose_msi_req_get_cpu() + * to always return the same dummy vCPU, because a second call to + * hv_compose_msi_msg() contains the "real" vCPU, causing Hyper-V to choose a + * new pCPU for the interrupt. But for the multi-MSI case, the second call to + * hv_compose_msi_msg() exits without sending a message to the vPCI VSP, so the + * original dummy vCPU is used. This dummy vCPU must be round-robin'ed so that + * the pCPUs are spread out. All interrupts for a multi-MSI device end up using + * the same pCPU, even though the vCPUs will be spread out by later calls + * to hv_irq_unmask(), but that is the best we can do now. + * + * With Hyper-V in Nov 2022, the HVCALL_RETARGET_INTERRUPT hypercall does *not* + * cause Hyper-V to reselect the pCPU based on the specified vCPU. Such an + * enhancement is planned for a future version. With that enhancement, the + * dummy vCPU selection won't matter, and interrupts for the same multi-MSI + * device will be spread across multiple pCPUs. + */ + +/* + * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten + * by subsequent retarget in hv_irq_unmask(). + */ +static int hv_compose_msi_req_get_cpu(const struct cpumask *affinity) { + return cpumask_first_and(affinity, cpu_online_mask); +} + +/* + * Make sure the dummy vCPU values for multi-MSI don't all point to vCPU0. + */ +static int hv_compose_multi_msi_req_get_cpu(void) +{ + static DEFINE_SPINLOCK(multi_msi_cpu_lock); + + /* -1 means starting with CPU 0 */ + static int cpu_next = -1; + + unsigned long flags; int cpu; + spin_lock_irqsave(&multi_msi_cpu_lock, flags); + + cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask); + cpu = cpu_next; + + spin_unlock_irqrestore(&multi_msi_cpu_lock, flags); + + return cpu; +} + +static u32 hv_compose_msi_req_v2( + struct pci_create_interrupt2 *int_pkt, int cpu, + u32 slot, u8 vector, u16 vector_count) +{ int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2; int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; - int_pkt->int_desc.vector_count = 1; - int_pkt->int_desc.delivery_mode = dest_Fixed; + int_pkt->int_desc.vector_count = vector_count; + int_pkt->int_desc.delivery_mode = DELIVERY_MODE; + int_pkt->int_desc.processor_array[0] = + hv_cpu_number_to_vp_number(cpu); + int_pkt->int_desc.processor_count = 1; - /* - * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten - * by subsequent retarget in hv_irq_unmask(). - */ - cpu = cpumask_first_and(affinity, cpu_online_mask); + return sizeof(*int_pkt); +} + +static u32 hv_compose_msi_req_v3( + struct pci_create_interrupt3 *int_pkt, int cpu, + u32 slot, u32 vector, u16 vector_count) +{ + int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE3; + int_pkt->wslot.slot = slot; + int_pkt->int_desc.vector = vector; + int_pkt->int_desc.reserved = 0; + int_pkt->int_desc.vector_count = vector_count; + int_pkt->int_desc.delivery_mode = DELIVERY_MODE; int_pkt->int_desc.processor_array[0] = hv_cpu_number_to_vp_number(cpu); int_pkt->int_desc.processor_count = 1; @@ -1072,36 +1875,59 @@ static u32 hv_compose_msi_req_v2( */ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { - struct irq_cfg *cfg = irqd_cfg(data); struct hv_pcibus_device *hbus; + struct vmbus_channel *channel; struct hv_pci_dev *hpdev; struct pci_bus *pbus; struct pci_dev *pdev; - struct cpumask *dest; - unsigned long flags; + const struct cpumask *dest; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; + struct msi_desc *msi_desc; + /* + * vector_count should be u16: see hv_msi_desc, hv_msi_desc2 + * and hv_msi_desc3. vector must be u32: see hv_msi_desc3. + */ + u16 vector_count; + u32 vector; struct { struct pci_packet pci_pkt; union { struct pci_create_interrupt v1; struct pci_create_interrupt2 v2; + struct pci_create_interrupt3 v3; } int_pkts; } __packed ctxt; - + bool multi_msi; + u64 trans_id; u32 size; int ret; + int cpu; + + msi_desc = irq_data_get_msi_desc(data); + multi_msi = !msi_desc->pci.msi_attrib.is_msix && + msi_desc->nvec_used > 1; + + /* Reuse the previous allocation */ + if (data->chip_data && multi_msi) { + int_desc = data->chip_data; + msg->address_hi = int_desc->address >> 32; + msg->address_lo = int_desc->address & 0xffffffff; + msg->data = int_desc->data; + return; + } - pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data)); + pdev = msi_desc_to_pci_dev(msi_desc); dest = irq_data_get_effective_affinity_mask(data); pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); + channel = hbus->hdev->channel; hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn)); if (!hpdev) goto return_null_message; /* Free any previous message that might have already been composed. */ - if (data->chip_data) { + if (data->chip_data && !multi_msi) { int_desc = data->chip_data; data->chip_data = NULL; hv_int_desc_free(hpdev, int_desc); @@ -1111,24 +1937,71 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) if (!int_desc) goto drop_reference; + if (multi_msi) { + /* + * If this is not the first MSI of Multi MSI, we already have + * a mapping. Can exit early. + */ + if (msi_desc->irq != data->irq) { + data->chip_data = int_desc; + int_desc->address = msi_desc->msg.address_lo | + (u64)msi_desc->msg.address_hi << 32; + int_desc->data = msi_desc->msg.data + + (data->irq - msi_desc->irq); + msg->address_hi = msi_desc->msg.address_hi; + msg->address_lo = msi_desc->msg.address_lo; + msg->data = int_desc->data; + put_pcichild(hpdev); + return; + } + /* + * The vector we select here is a dummy value. The correct + * value gets sent to the hypervisor in unmask(). This needs + * to be aligned with the count, and also not zero. Multi-msi + * is powers of 2 up to 32, so 32 will always work here. + */ + vector = 32; + vector_count = msi_desc->nvec_used; + cpu = hv_compose_multi_msi_req_get_cpu(); + } else { + vector = hv_msi_get_int_vector(data); + vector_count = 1; + cpu = hv_compose_msi_req_get_cpu(dest); + } + + /* + * hv_compose_msi_req_v1 and v2 are for x86 only, meaning 'vector' + * can't exceed u8. Cast 'vector' down to u8 for v1/v2 explicitly + * for better readability. + */ memset(&ctxt, 0, sizeof(ctxt)); init_completion(&comp.comp_pkt.host_event); ctxt.pci_pkt.completion_func = hv_pci_compose_compl; ctxt.pci_pkt.compl_ctxt = ∁ - switch (pci_protocol_version) { + switch (hbus->protocol_version) { case PCI_PROTOCOL_VERSION_1_1: size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1, - dest, hpdev->desc.win_slot.slot, - cfg->vector); + (u8)vector, + vector_count); break; case PCI_PROTOCOL_VERSION_1_2: + case PCI_PROTOCOL_VERSION_1_3: size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2, - dest, + cpu, + hpdev->desc.win_slot.slot, + (u8)vector, + vector_count); + break; + + case PCI_PROTOCOL_VERSION_1_4: + size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3, + cpu, hpdev->desc.win_slot.slot, - cfg->vector); + vector, + vector_count); break; default: @@ -1141,10 +2014,10 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) goto free_int_desc; } - ret = vmbus_sendpacket(hpdev->hbus->hdev->channel, &ctxt.int_pkts, - size, (unsigned long)&ctxt.pci_pkt, - VM_PKT_DATA_INBAND, - VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + ret = vmbus_sendpacket_getid(hpdev->hbus->hdev->channel, &ctxt.int_pkts, + size, (unsigned long)&ctxt.pci_pkt, + &trans_id, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); if (ret) { dev_err(&hbus->hdev->device, "Sending request for interrupt failed: 0x%x", @@ -1153,42 +2026,45 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) } /* + * Prevents hv_pci_onchannelcallback() from running concurrently + * in the tasklet. + */ + tasklet_disable_in_atomic(&channel->callback_event); + + /* * Since this function is called with IRQ locks held, can't * do normal wait for completion; instead poll. */ while (!try_wait_for_completion(&comp.comp_pkt.host_event)) { + unsigned long flags; + /* 0xFFFF means an invalid PCI VENDOR ID. */ if (hv_pcifront_get_vendor_id(hpdev) == 0xFFFF) { dev_err_once(&hbus->hdev->device, "the device has gone\n"); - goto free_int_desc; + goto enable_tasklet; } /* - * When the higher level interrupt code calls us with - * interrupt disabled, we must poll the channel by calling - * the channel callback directly when channel->target_cpu is - * the current CPU. When the higher level interrupt code - * calls us with interrupt enabled, let's add the - * local_irq_save()/restore() to avoid race: - * hv_pci_onchannelcallback() can also run in tasklet. + * Make sure that the ring buffer data structure doesn't get + * freed while we dereference the ring buffer pointer. Test + * for the channel's onchannel_callback being NULL within a + * sched_lock critical section. See also the inline comments + * in vmbus_reset_channel_cb(). */ - local_irq_save(flags); - - if (hbus->hdev->channel->target_cpu == smp_processor_id()) - hv_pci_onchannelcallback(hbus); - - local_irq_restore(flags); - - if (hpdev->state == hv_pcichild_ejecting) { - dev_err_once(&hbus->hdev->device, - "the device is being ejected\n"); - goto free_int_desc; + spin_lock_irqsave(&channel->sched_lock, flags); + if (unlikely(channel->onchannel_callback == NULL)) { + spin_unlock_irqrestore(&channel->sched_lock, flags); + goto enable_tasklet; } + hv_pci_onchannelcallback(hbus); + spin_unlock_irqrestore(&channel->sched_lock, flags); udelay(100); } + tasklet_enable(&channel->callback_event); + if (comp.comp_pkt.completion_status < 0) { dev_err(&hbus->hdev->device, "Request for interrupt failed: 0x%x", @@ -1212,6 +2088,17 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) put_pcichild(hpdev); return; +enable_tasklet: + tasklet_enable(&channel->callback_event); + /* + * The completion packet on the stack becomes invalid after 'return'; + * remove the ID from the VMbus requestor if the identifier is still + * mapped to/associated with the packet. (The identifier could have + * been 're-used', i.e., already removed and (re-)mapped.) + * + * Cf. hv_pci_onchannelcallback(). + */ + vmbus_request_addr_match(channel, trans_id, (unsigned long)&ctxt.pci_pkt); free_int_desc: kfree(int_desc); drop_reference: @@ -1222,27 +2109,85 @@ return_null_message: msg->data = 0; } +static bool hv_pcie_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, struct msi_domain_info *info) +{ + struct irq_chip *chip = info->chip; + + if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) + return false; + + info->ops->msi_prepare = hv_msi_prepare; + + chip->irq_set_affinity = irq_chip_set_affinity_parent; + + if (IS_ENABLED(CONFIG_X86)) + chip->flags |= IRQCHIP_MOVE_DEFERRED; + + return true; +} + +#define HV_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) +#define HV_PCIE_MSI_FLAGS_SUPPORTED (MSI_FLAG_MULTI_PCI_MSI | \ + MSI_FLAG_PCI_MSIX | \ + MSI_FLAG_PCI_MSIX_ALLOC_DYN | \ + MSI_GENERIC_FLAGS_MASK) + +static const struct msi_parent_ops hv_pcie_msi_parent_ops = { + .required_flags = HV_PCIE_MSI_FLAGS_REQUIRED, + .supported_flags = HV_PCIE_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = HV_MSI_CHIP_FLAGS, + .prefix = "HV-", + .init_dev_msi_info = hv_pcie_init_dev_msi_info, +}; + /* HW Interrupt Chip Descriptor */ static struct irq_chip hv_msi_irq_chip = { .name = "Hyper-V PCIe MSI", .irq_compose_msi_msg = hv_compose_msi_msg, - .irq_set_affinity = hv_set_affinity, + .irq_set_affinity = irq_chip_set_affinity_parent, .irq_ack = irq_chip_ack_parent, + .irq_eoi = irq_chip_eoi_parent, .irq_mask = hv_irq_mask, .irq_unmask = hv_irq_unmask, }; -static irq_hw_number_t hv_msi_domain_ops_get_hwirq(struct msi_domain_info *info, - msi_alloc_info_t *arg) +static int hv_pcie_domain_alloc(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs, + void *arg) { - return arg->msi_hwirq; + /* + * 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 struct msi_domain_ops hv_msi_ops = { - .get_hwirq = hv_msi_domain_ops_get_hwirq, - .msi_prepare = pci_msi_prepare, - .set_desc = pci_msi_set_desc, - .msi_free = hv_msi_free, +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, }; /** @@ -1260,23 +2205,22 @@ 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 = handle_edge_irq; - hbus->msi_info.handler_name = "edge"; - hbus->msi_info.data = hbus; - hbus->irq_domain = pci_msi_create_irq_domain(hbus->sysdata.fwnode, - &hbus->msi_info, - x86_vector_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"); return -ENODEV; } + dev_set_msi_domain(&hbus->bridge->dev, hbus->irq_domain); + return 0; } @@ -1332,7 +2276,7 @@ static void survey_child_resources(struct hv_pcibus_device *hbus) * so it's sufficient to just add them up without tracking alignment. */ list_for_each_entry(hpdev, &hbus->children, list_entry) { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { if (hpdev->probed_bar[i] & PCI_BASE_ADDRESS_SPACE_IO) dev_err(&hbus->hdev->device, "There's an I/O BAR in this list!\n"); @@ -1403,10 +2347,27 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) spin_lock_irqsave(&hbus->device_list_lock, flags); + /* + * Clear the memory enable bit, in case it's already set. This occurs + * in the suspend path of hibernation, where the device is suspended, + * resumed and suspended again: see hibernation_snapshot() and + * hibernation_platform_enter(). + * + * If the memory enable bit is already set, Hyper-V silently ignores + * the below BAR updates, and the related PCI device driver can not + * work, because reading from the device register(s) always returns + * 0xFFFFFFFF (PCI_ERROR_RESPONSE). + */ + list_for_each_entry(hpdev, &hbus->children, list_entry) { + _hv_pcifront_read_config(hpdev, PCI_COMMAND, 2, &command); + command &= ~PCI_COMMAND_MEMORY; + _hv_pcifront_write_config(hpdev, PCI_COMMAND, 2, command); + } + /* Pick addresses for the BARs. */ do { list_for_each_entry(hpdev, &hbus->children, list_entry) { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { bar_val = hpdev->probed_bar[i]; if (bar_val == 0) continue; @@ -1444,12 +2405,17 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) } } if (high_size <= 1 && low_size <= 1) { - /* Set the memory enable bit. */ - _hv_pcifront_read_config(hpdev, PCI_COMMAND, 2, - &command); - command |= PCI_COMMAND_MEMORY; - _hv_pcifront_write_config(hpdev, PCI_COMMAND, 2, - command); + /* + * No need to set the PCI_COMMAND_MEMORY bit as + * the core PCI driver doesn't require the bit + * to be pre-set. Actually here we intentionally + * keep the bit off so that the PCI BAR probing + * in the core PCI driver doesn't cause Hyper-V + * to unnecessarily unmap/map the virtual BARs + * from/to the physical BARs multiple times. + * This reduces the VM boot time significantly + * if the BAR sizes are huge. + */ break; } } @@ -1482,7 +2448,7 @@ static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot)); snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser); - hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr, + hpdev->pci_slot = pci_create_slot(hbus->bridge->bus, slot_nr, name, NULL); if (IS_ERR(hpdev->pci_slot)) { pr_warn("pci_create slot %s failed\n", name); @@ -1491,6 +2457,51 @@ static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) } } +/* + * Remove entries in sysfs pci slot directory. + */ +static void hv_pci_remove_slots(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (!hpdev->pci_slot) + continue; + pci_destroy_slot(hpdev->pci_slot); + hpdev->pci_slot = NULL; + } +} + +/* + * Set NUMA node for the devices on the bus + */ +static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus) +{ + struct pci_dev *dev; + struct pci_bus *bus = hbus->bridge->bus; + struct hv_pci_dev *hv_dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + hv_dev = get_pcichild_wslot(hbus, devfn_to_wslot(dev->devfn)); + if (!hv_dev) + continue; + + if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY && + hv_dev->desc.virtual_numa_node < num_possible_nodes()) + /* + * The kernel may boot with some NUMA nodes offline + * (e.g. in a KDUMP kernel) or with NUMA disabled via + * "numa=off". In those cases, adjust the host provided + * NUMA node to a valid NUMA node used by the kernel. + */ + set_dev_node(&dev->dev, + numa_map_to_online_node( + hv_dev->desc.virtual_numa_node)); + + put_pcichild(hv_dev); + } +} + /** * create_root_hv_pci_bus() - Expose a new root PCI bus * @hbus: Root PCI bus, as understood by this driver @@ -1499,23 +2510,22 @@ static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) */ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus) { - /* Register the device */ - hbus->pci_bus = pci_create_root_bus(&hbus->hdev->device, - 0, /* bus number is always zero */ - &hv_pcifront_ops, - &hbus->sysdata, - &hbus->resources_for_children); - if (!hbus->pci_bus) - return -ENODEV; + int error; + struct pci_host_bridge *bridge = hbus->bridge; - hbus->pci_bus->msi = &hbus->msi_chip; - hbus->pci_bus->msi->dev = &hbus->hdev->device; + bridge->dev.parent = &hbus->hdev->device; + bridge->sysdata = &hbus->sysdata; + bridge->ops = &hv_pcifront_ops; + + error = pci_scan_root_bus_bridge(bridge); + if (error) + return error; pci_lock_rescan_remove(); - pci_scan_child_bus(hbus->pci_bus); - pci_bus_assign_resources(hbus->pci_bus); + hv_pci_assign_numa_node(hbus); + pci_bus_assign_resources(bridge->bus); hv_pci_assign_slots(hbus); - pci_bus_add_devices(hbus->pci_bus); + pci_bus_add_devices(bridge->bus); pci_unlock_rescan_remove(); hbus->state = hv_pcibus_installed; return 0; @@ -1541,14 +2551,16 @@ static void q_resource_requirements(void *context, struct pci_response *resp, struct q_res_req_compl *completion = context; struct pci_q_res_req_response *q_res_req = (struct pci_q_res_req_response *)resp; + s32 status; int i; - if (resp->status < 0) { + status = (resp_packet_size < sizeof(*q_res_req)) ? -1 : resp->status; + if (status < 0) { dev_err(&completion->hpdev->hbus->hdev->device, "query resource requirements failed: %x\n", - resp->status); + status); } else { - for (i = 0; i < 6; i++) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { completion->hpdev->probed_bar[i] = q_res_req->probed_bar[i]; } @@ -1569,7 +2581,7 @@ static void q_resource_requirements(void *context, struct pci_response *resp, * Return: Pointer to the new tracking struct */ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus, - struct pci_function_description *desc) + struct hv_pcidev_description *desc) { struct hv_pci_dev *hpdev; struct pci_child_message *res_req; @@ -1592,7 +2604,7 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus, comp_pkt.hpdev = hpdev; pkt.init_packet.compl_ctxt = &comp_pkt; pkt.init_packet.completion_func = q_resource_requirements; - res_req = (struct pci_child_message *)&pkt.init_packet.message; + res_req = (struct pci_child_message *)pkt.buffer; res_req->message_type.type = PCI_QUERY_RESOURCE_REQUIREMENTS; res_req->wslot.slot = desc->win_slot.slot; @@ -1680,7 +2692,7 @@ static void pci_devices_present_work(struct work_struct *work) { u32 child_no; bool found; - struct pci_function_description *new_desc; + struct hv_pcidev_description *new_desc; struct hv_pci_dev *hpdev; struct hv_pcibus_device *hbus; struct list_head removed; @@ -1709,10 +2721,10 @@ static void pci_devices_present_work(struct work_struct *work) } spin_unlock_irqrestore(&hbus->device_list_lock, flags); - if (!dr) { - put_hvpcibus(hbus); + if (!dr) return; - } + + mutex_lock(&hbus->state_lock); /* First, mark all existing children as reported missing. */ spin_lock_irqsave(&hbus->device_list_lock, flags); @@ -1766,6 +2778,10 @@ static void pci_devices_present_work(struct work_struct *work) hpdev = list_first_entry(&removed, struct hv_pci_dev, list_entry); list_del(&hpdev->list_entry); + + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + put_pcichild(hpdev); } @@ -1776,7 +2792,8 @@ static void pci_devices_present_work(struct work_struct *work) * because there may have been changes. */ pci_lock_rescan_remove(); - pci_scan_child_bus(hbus->pci_bus); + pci_scan_child_bus(hbus->bridge->bus); + hv_pci_assign_numa_node(hbus); hv_pci_assign_slots(hbus); pci_unlock_rescan_remove(); break; @@ -1790,46 +2807,37 @@ static void pci_devices_present_work(struct work_struct *work) break; } - put_hvpcibus(hbus); + mutex_unlock(&hbus->state_lock); + kfree(dr); } /** - * hv_pci_devices_present() - Handles list of new children + * hv_pci_start_relations_work() - Queue work to start device discovery * @hbus: Root PCI bus, as understood by this driver - * @relations: Packet from host listing children + * @dr: The list of children returned from host * - * This function is invoked whenever a new list of devices for - * this bus appears. + * Return: 0 on success, -errno on failure */ -static void hv_pci_devices_present(struct hv_pcibus_device *hbus, - struct pci_bus_relations *relations) +static int hv_pci_start_relations_work(struct hv_pcibus_device *hbus, + struct hv_dr_state *dr) { - struct hv_dr_state *dr; struct hv_dr_work *dr_wrk; unsigned long flags; bool pending_dr; + if (hbus->state == hv_pcibus_removing) { + dev_info(&hbus->hdev->device, + "PCI VMBus BUS_RELATIONS: ignored\n"); + return -ENOENT; + } + dr_wrk = kzalloc(sizeof(*dr_wrk), GFP_NOWAIT); if (!dr_wrk) - return; - - dr = kzalloc(offsetof(struct hv_dr_state, func) + - (sizeof(struct pci_function_description) * - (relations->device_count)), GFP_NOWAIT); - if (!dr) { - kfree(dr_wrk); - return; - } + return -ENOMEM; INIT_WORK(&dr_wrk->wrk, pci_devices_present_work); dr_wrk->bus = hbus; - dr->device_count = relations->device_count; - if (dr->device_count != 0) { - memcpy(dr->func, relations->func, - sizeof(struct pci_function_description) * - dr->device_count); - } spin_lock_irqsave(&hbus->device_list_lock, flags); /* @@ -1841,12 +2849,87 @@ static void hv_pci_devices_present(struct hv_pcibus_device *hbus, list_add_tail(&dr->list_entry, &hbus->dr_list); spin_unlock_irqrestore(&hbus->device_list_lock, flags); - if (pending_dr) { + if (pending_dr) kfree(dr_wrk); - } else { - get_hvpcibus(hbus); + else queue_work(hbus->wq, &dr_wrk->wrk); + + return 0; +} + +/** + * hv_pci_devices_present() - Handle list of new children + * @hbus: Root PCI bus, as understood by this driver + * @relations: Packet from host listing children + * + * Process a new list of devices on the bus. The list of devices is + * discovered by VSP and sent to us via VSP message PCI_BUS_RELATIONS, + * whenever a new list of devices for this bus appears. + */ +static void hv_pci_devices_present(struct hv_pcibus_device *hbus, + struct pci_bus_relations *relations) +{ + struct hv_dr_state *dr; + int i; + + dr = kzalloc(struct_size(dr, func, relations->device_count), + GFP_NOWAIT); + if (!dr) + return; + + dr->device_count = relations->device_count; + for (i = 0; i < dr->device_count; i++) { + dr->func[i].v_id = relations->func[i].v_id; + dr->func[i].d_id = relations->func[i].d_id; + dr->func[i].rev = relations->func[i].rev; + dr->func[i].prog_intf = relations->func[i].prog_intf; + dr->func[i].subclass = relations->func[i].subclass; + dr->func[i].base_class = relations->func[i].base_class; + dr->func[i].subsystem_id = relations->func[i].subsystem_id; + dr->func[i].win_slot = relations->func[i].win_slot; + dr->func[i].ser = relations->func[i].ser; } + + if (hv_pci_start_relations_work(hbus, dr)) + kfree(dr); +} + +/** + * hv_pci_devices_present2() - Handle list of new children + * @hbus: Root PCI bus, as understood by this driver + * @relations: Packet from host listing children + * + * This function is the v2 version of hv_pci_devices_present() + */ +static void hv_pci_devices_present2(struct hv_pcibus_device *hbus, + struct pci_bus_relations2 *relations) +{ + struct hv_dr_state *dr; + int i; + + dr = kzalloc(struct_size(dr, func, relations->device_count), + GFP_NOWAIT); + if (!dr) + return; + + dr->device_count = relations->device_count; + for (i = 0; i < dr->device_count; i++) { + dr->func[i].v_id = relations->func[i].v_id; + dr->func[i].d_id = relations->func[i].d_id; + dr->func[i].rev = relations->func[i].rev; + dr->func[i].prog_intf = relations->func[i].prog_intf; + dr->func[i].subclass = relations->func[i].subclass; + dr->func[i].base_class = relations->func[i].base_class; + dr->func[i].subsystem_id = relations->func[i].subsystem_id; + dr->func[i].win_slot = relations->func[i].win_slot; + dr->func[i].ser = relations->func[i].ser; + dr->func[i].flags = relations->func[i].flags; + dr->func[i].virtual_numa_node = + relations->func[i].virtual_numa_node; + } + + if (hv_pci_start_relations_work(hbus, dr)) + kfree(dr); } /** @@ -1861,6 +2944,7 @@ static void hv_pci_devices_present(struct hv_pcibus_device *hbus, static void hv_eject_device_work(struct work_struct *work) { struct pci_eject_response *ejct_pkt; + struct hv_pcibus_device *hbus; struct hv_pci_dev *hpdev; struct pci_dev *pdev; unsigned long flags; @@ -1871,18 +2955,18 @@ static void hv_eject_device_work(struct work_struct *work) } ctxt; hpdev = container_of(work, struct hv_pci_dev, wrk); + hbus = hpdev->hbus; - WARN_ON(hpdev->state != hv_pcichild_ejecting); + mutex_lock(&hbus->state_lock); /* * Ejection can come before or after the PCI bus has been set up, so * attempt to find it and tear down the bus state, if it exists. This - * must be done without constructs like pci_domain_nr(hbus->pci_bus) - * because hbus->pci_bus may not exist yet. + * must be done without constructs like pci_domain_nr(hbus->bridge->bus) + * because hbus->bridge->bus may not exist yet. */ wslot = wslot_to_devfn(hpdev->desc.win_slot.slot); - pdev = pci_get_domain_bus_and_slot(hpdev->hbus->sysdata.domain, 0, - wslot); + pdev = pci_get_domain_bus_and_slot(hbus->bridge->domain_nr, 0, wslot); if (pdev) { pci_lock_rescan_remove(); pci_stop_and_remove_bus_device(pdev); @@ -1890,24 +2974,29 @@ static void hv_eject_device_work(struct work_struct *work) pci_unlock_rescan_remove(); } - spin_lock_irqsave(&hpdev->hbus->device_list_lock, flags); + spin_lock_irqsave(&hbus->device_list_lock, flags); list_del(&hpdev->list_entry); - spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); if (hpdev->pci_slot) pci_destroy_slot(hpdev->pci_slot); memset(&ctxt, 0, sizeof(ctxt)); - ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; + ejct_pkt = (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(hpdev->hbus->hdev->channel, ejct_pkt, - sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt, + vmbus_sendpacket(hbus->hdev->channel, ejct_pkt, + sizeof(*ejct_pkt), 0, VM_PKT_DATA_INBAND, 0); + /* For the get_pcichild() in hv_pci_eject_device() */ put_pcichild(hpdev); + /* For the two refs got in new_pcichild_device() */ put_pcichild(hpdev); - put_hvpcibus(hpdev->hbus); + put_pcichild(hpdev); + /* hpdev has been freed. Do not use it any more. */ + + mutex_unlock(&hbus->state_lock); } /** @@ -1920,11 +3009,17 @@ static void hv_eject_device_work(struct work_struct *work) */ static void hv_pci_eject_device(struct hv_pci_dev *hpdev) { - hpdev->state = hv_pcichild_ejecting; + struct hv_pcibus_device *hbus = hpdev->hbus; + struct hv_device *hdev = hbus->hdev; + + if (hbus->state == hv_pcibus_removing) { + dev_info(&hdev->device, "PCI VMBus EJECT: ignored\n"); + return; + } + get_pcichild(hpdev); INIT_WORK(&hpdev->wrk, hv_eject_device_work); - get_hvpcibus(hpdev->hbus); - queue_work(hpdev->hbus->wq, &hpdev->wrk); + queue_work(hbus->wq, &hpdev->wrk); } /** @@ -1939,8 +3034,9 @@ static void hv_pci_onchannelcallback(void *context) const int packet_size = 0x100; int ret; struct hv_pcibus_device *hbus = context; + struct vmbus_channel *chan = hbus->hdev->channel; u32 bytes_recvd; - u64 req_id; + u64 req_id, req_addr; struct vmpacket_descriptor *desc; unsigned char *buffer; int bufferlen = packet_size; @@ -1948,16 +3044,19 @@ static void hv_pci_onchannelcallback(void *context) struct pci_response *response; struct pci_incoming_message *new_message; struct pci_bus_relations *bus_rel; + struct pci_bus_relations2 *bus_rel2; + struct pci_dev_inval_block *inval; struct pci_dev_incoming *dev_message; struct hv_pci_dev *hpdev; + unsigned long flags; buffer = kmalloc(bufferlen, GFP_ATOMIC); if (!buffer) return; while (1) { - ret = vmbus_recvpacket_raw(hbus->hdev->channel, buffer, - bufferlen, &bytes_recvd, &req_id); + ret = vmbus_recvpacket_raw(chan, buffer, bufferlen, + &bytes_recvd, &req_id); if (ret == -ENOBUFS) { kfree(buffer); @@ -1984,15 +3083,29 @@ static void hv_pci_onchannelcallback(void *context) switch (desc->type) { case VM_PKT_COMP: + lock_requestor(chan, flags); + req_addr = __vmbus_request_addr_match(chan, req_id, + VMBUS_RQST_ADDR_ANY); + if (req_addr == VMBUS_RQST_ERROR) { + unlock_requestor(chan, flags); + dev_err(&hbus->hdev->device, + "Invalid transaction ID %llx\n", + req_id); + break; + } + comp_packet = (struct pci_packet *)req_addr; + response = (struct pci_response *)buffer; /* - * The host is trusted, and thus it's safe to interpret - * this transaction ID as a pointer. + * Call ->completion_func() within the critical section to make + * sure that the packet pointer is still valid during the call: + * here 'valid' means that there's a task still waiting for the + * completion, and that the packet data is still on the waiting + * task's stack. Cf. hv_compose_msi_msg(). */ - comp_packet = (struct pci_packet *)req_id; - response = (struct pci_response *)buffer; comp_packet->completion_func(comp_packet->compl_ctxt, response, bytes_recvd); + unlock_requestor(chan, flags); break; case VM_PKT_DATA_INBAND: @@ -2002,10 +3115,10 @@ static void hv_pci_onchannelcallback(void *context) case PCI_BUS_RELATIONS: bus_rel = (struct pci_bus_relations *)buffer; - if (bytes_recvd < - offsetof(struct pci_bus_relations, func) + - (sizeof(struct pci_function_description) * - (bus_rel->device_count))) { + if (bytes_recvd < sizeof(*bus_rel) || + bytes_recvd < + struct_size(bus_rel, func, + bus_rel->device_count)) { dev_err(&hbus->hdev->device, "bus relations too small\n"); break; @@ -2014,9 +3127,29 @@ static void hv_pci_onchannelcallback(void *context) hv_pci_devices_present(hbus, bus_rel); break; + case PCI_BUS_RELATIONS2: + + bus_rel2 = (struct pci_bus_relations2 *)buffer; + if (bytes_recvd < sizeof(*bus_rel2) || + bytes_recvd < + struct_size(bus_rel2, func, + bus_rel2->device_count)) { + dev_err(&hbus->hdev->device, + "bus relations v2 too small\n"); + break; + } + + hv_pci_devices_present2(hbus, bus_rel2); + break; + case PCI_EJECT: dev_message = (struct pci_dev_incoming *)buffer; + if (bytes_recvd < sizeof(*dev_message)) { + dev_err(&hbus->hdev->device, + "eject message too small\n"); + break; + } hpdev = get_pcichild_wslot(hbus, dev_message->wslot.slot); if (hpdev) { @@ -2025,6 +3158,26 @@ static void hv_pci_onchannelcallback(void *context) } break; + case PCI_INVALIDATE_BLOCK: + + inval = (struct pci_dev_inval_block *)buffer; + if (bytes_recvd < sizeof(*inval)) { + dev_err(&hbus->hdev->device, + "invalidate message too small\n"); + break; + } + hpdev = get_pcichild_wslot(hbus, + inval->wslot.slot); + if (hpdev) { + if (hpdev->block_invalidate) { + hpdev->block_invalidate( + hpdev->invalidate_context, + inval->block_mask); + } + put_pcichild(hpdev); + } + break; + default: dev_warn(&hbus->hdev->device, "Unimplemented protocol message %x\n", @@ -2046,7 +3199,10 @@ static void hv_pci_onchannelcallback(void *context) /** * hv_pci_protocol_negotiation() - Set up protocol - * @hdev: VMBus's tracking struct for this root PCI bus + * @hdev: VMBus's tracking struct for this root PCI bus. + * @version: Array of supported channel protocol versions in + * the order of probing - highest go first. + * @num_version: Number of elements in the version array. * * This driver is intended to support running on Windows 10 * (server) and later versions. It will not run on earlier @@ -2060,8 +3216,11 @@ static void hv_pci_onchannelcallback(void *context) * failing if the host doesn't support the necessary protocol * level. */ -static int hv_pci_protocol_negotiation(struct hv_device *hdev) +static int hv_pci_protocol_negotiation(struct hv_device *hdev, + enum pci_protocol_version_t version[], + int num_version) { + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); struct pci_version_request *version_req; struct hv_pci_compl comp_pkt; struct pci_packet *pkt; @@ -2081,11 +3240,11 @@ 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 < ARRAY_SIZE(pci_protocol_versions); i++) { - version_req->protocol_version = pci_protocol_versions[i]; + for (i = 0; i < num_version; i++) { + version_req->protocol_version = version[i]; ret = vmbus_sendpacket(hdev->channel, version_req, sizeof(struct pci_version_request), (unsigned long)pkt, VM_PKT_DATA_INBAND, @@ -2101,10 +3260,10 @@ static int hv_pci_protocol_negotiation(struct hv_device *hdev) } if (comp_pkt.completion_status >= 0) { - pci_protocol_version = pci_protocol_versions[i]; + hbus->protocol_version = version[i]; dev_info(&hdev->device, "PCI VMBus probing: Using version %#x\n", - pci_protocol_version); + hbus->protocol_version); goto exit; } @@ -2199,8 +3358,7 @@ static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus) /* Modify this resource to become a bridge window. */ hbus->low_mmio_res->flags |= IORESOURCE_WINDOW; hbus->low_mmio_res->flags &= ~IORESOURCE_BUSY; - pci_add_resource(&hbus->resources_for_children, - hbus->low_mmio_res); + pci_add_resource(&hbus->bridge->windows, hbus->low_mmio_res); } if (hbus->high_mmio_space) { @@ -2219,8 +3377,7 @@ static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus) /* Modify this resource to become a bridge window. */ hbus->high_mmio_res->flags |= IORESOURCE_WINDOW; hbus->high_mmio_res->flags &= ~IORESOURCE_BUSY; - pci_add_resource(&hbus->resources_for_children, - hbus->high_mmio_res); + pci_add_resource(&hbus->bridge->windows, hbus->high_mmio_res); } return 0; @@ -2274,6 +3431,8 @@ static void hv_free_config_window(struct hv_pcibus_device *hbus) vmbus_free_mmio(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH); } +static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs); + /** * hv_pci_enter_d0() - Bring the "bus" into the D0 power state * @hdev: VMBus's tracking struct for this root PCI bus @@ -2286,8 +3445,10 @@ static int hv_pci_enter_d0(struct hv_device *hdev) struct pci_bus_d0_entry *d0_entry; struct hv_pci_compl comp_pkt; struct pci_packet *pkt; + bool retry = true; int ret; +enter_d0_retry: /* * Tell the host that the bus is ready to use, and moved into the * powered-on state. This includes telling the host which region @@ -2301,7 +3462,7 @@ static int hv_pci_enter_d0(struct hv_device *hdev) 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; @@ -2314,6 +3475,38 @@ static int hv_pci_enter_d0(struct hv_device *hdev) if (ret) goto exit; + /* + * In certain case (Kdump) the pci device of interest was + * not cleanly shut down and resource is still held on host + * side, the host could return invalid device status. + * We need to explicitly request host to release the resource + * and try to enter D0 again. + */ + if (comp_pkt.completion_status < 0 && retry) { + retry = false; + + dev_err(&hdev->device, "Retrying D0 Entry\n"); + + /* + * Hv_pci_bus_exit() calls hv_send_resource_released() + * to free up resources of its child devices. + * In the kdump kernel we need to set the + * wslot_res_allocated to 255 so it scans all child + * devices to release resources allocated in the + * normal kernel before panic happened. + */ + hbus->wslot_res_allocated = 255; + + ret = hv_pci_bus_exit(hdev, true); + + if (ret == 0) { + kfree(pkt); + goto enter_d0_retry; + } + dev_err(&hdev->device, + "Retrying D0 failed with ret %d\n", ret); + } + if (comp_pkt.completion_status < 0) { dev_err(&hdev->device, "PCI Pass-through VSP failed D0 Entry with status %x\n", @@ -2356,6 +3549,24 @@ static int hv_pci_query_relations(struct hv_device *hdev) if (!ret) ret = wait_for_response(hdev, &comp); + /* + * In the case of fast device addition/removal, it's possible that + * vmbus_sendpacket() or wait_for_response() returns -ENODEV but we + * already got a PCI_BUS_RELATIONS* message from the host and the + * channel callback already scheduled a work to hbus->wq, which can be + * running pci_devices_present_work() -> survey_child_resources() -> + * complete(&hbus->survey_event), even after hv_pci_query_relations() + * exits and the stack variable 'comp' is no longer valid; as a result, + * a hang or a page fault may happen when the complete() calls + * raw_spin_lock_irqsave(). Flush hbus->wq before we exit from + * hv_pci_query_relations() to avoid the issues. Note: if 'ret' is + * -ENODEV, there can't be any more work item scheduled to hbus->wq + * after the flush_workqueue(): see vmbus_onoffer_rescind() -> + * vmbus_reset_channel_cb(), vmbus_rescind_cleanup() -> + * channel->rescind = true. + */ + flush_workqueue(hbus->wq); + return ret; } @@ -2385,10 +3596,10 @@ static int hv_send_resources_allocated(struct hv_device *hdev) struct hv_pci_dev *hpdev; struct pci_packet *pkt; size_t size_res; - u32 wslot; + int wslot; int ret; - size_res = (pci_protocol_version < PCI_PROTOCOL_VERSION_1_2) + size_res = (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2) ? sizeof(*res_assigned) : sizeof(*res_assigned2); pkt = kmalloc(sizeof(*pkt) + size_res, GFP_KERNEL); @@ -2407,22 +3618,22 @@ static int hv_send_resources_allocated(struct hv_device *hdev) pkt->completion_func = hv_pci_generic_compl; pkt->compl_ctxt = &comp_pkt; - if (pci_protocol_version < PCI_PROTOCOL_VERSION_1_2) { + 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); @@ -2438,6 +3649,8 @@ static int hv_send_resources_allocated(struct hv_device *hdev) comp_pkt.completion_status); break; } + + hbus->wslot_res_allocated = wslot; } kfree(pkt); @@ -2456,10 +3669,10 @@ static int hv_send_resources_released(struct hv_device *hdev) struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); struct pci_child_message pkt; struct hv_pci_dev *hpdev; - u32 wslot; + int wslot; int ret; - for (wslot = 0; wslot < 256; wslot++) { + for (wslot = hbus->wslot_res_allocated; wslot >= 0; wslot--) { hpdev = get_pcichild_wslot(hbus, wslot); if (!hpdev) continue; @@ -2474,20 +3687,13 @@ static int hv_send_resources_released(struct hv_device *hdev) VM_PKT_DATA_INBAND, 0); if (ret) return ret; - } - return 0; -} + hbus->wslot_res_allocated = wslot - 1; + } -static void get_hvpcibus(struct hv_pcibus_device *hbus) -{ - refcount_inc(&hbus->remove_lock); -} + hbus->wslot_res_allocated = -1; -static void put_hvpcibus(struct hv_pcibus_device *hbus) -{ - if (refcount_dec_and_test(&hbus->remove_lock)) - complete(&hbus->remove_event); + return 0; } /** @@ -2500,51 +3706,88 @@ static void put_hvpcibus(struct hv_pcibus_device *hbus) static int hv_pci_probe(struct hv_device *hdev, const struct hv_vmbus_device_id *dev_id) { + struct pci_host_bridge *bridge; struct hv_pcibus_device *hbus; - int ret; + int ret, dom; + u16 dom_req; + char *name; - /* - * hv_pcibus_device contains the hypercall arguments for retargeting in - * hv_irq_unmask(). Those must not cross a page boundary. - */ - BUILD_BUG_ON(sizeof(*hbus) > PAGE_SIZE); + bridge = devm_pci_alloc_host_bridge(&hdev->device, 0); + if (!bridge) + return -ENOMEM; - hbus = (struct hv_pcibus_device *)get_zeroed_page(GFP_KERNEL); + hbus = kzalloc(sizeof(*hbus), GFP_KERNEL); if (!hbus) return -ENOMEM; + + hbus->bridge = bridge; + mutex_init(&hbus->state_lock); hbus->state = hv_pcibus_init; + hbus->wslot_res_allocated = -1; + + /* + * The PCI bus "domain" is what is called "segment" in ACPI and other + * specs. Pull it from the instance ID, to get something usually + * unique. In rare cases of collision, we will find out another number + * not in use. + * + * Note that, since this code only runs in a Hyper-V VM, Hyper-V + * together with this guest driver can guarantee that (1) The only + * domain used by Gen1 VMs for something that looks like a physical + * PCI bus (which is actually emulated by the hypervisor) is domain 0. + * (2) There will be no overlap between domains (after fixing possible + * collisions) in the same VM. + * + * 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 = 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; + goto free_bus; + } + if (dom != dom_req) + dev_info(&hdev->device, + "PCI dom# 0x%x has collision, using 0x%x", + dom_req, dom); + + hbus->bridge->domain_nr = dom; +#ifdef CONFIG_X86 + hbus->sysdata.domain = dom; + hbus->use_calls = !!(ms_hyperv.hints & HV_X64_USE_MMIO_HYPERCALLS); +#elif defined(CONFIG_ARM64) /* - * The PCI bus "domain" is what is called "segment" in ACPI and - * other specs. Pull it from the instance ID, to get something - * unique. Bytes 8 and 9 are what is used in Windows guests, so - * do the same thing for consistency. Note that, since this code - * only runs in a Hyper-V VM, Hyper-V can (and does) guarantee - * that (1) the only domain in use for something that looks like - * a physical PCI bus (which is actually emulated by the - * hypervisor) is domain 0 and (2) there will be no overlap - * between domains derived from these instance IDs in the same - * VM. + * Set the PCI bus parent to be the corresponding VMbus + * device. Then the VMbus device will be assigned as the + * ACPI companion in pcibios_root_bridge_prepare() and + * pci_dma_configure() will propagate device coherence + * information to devices created on the bus. */ - hbus->sysdata.domain = hdev->dev_instance.b[9] | - hdev->dev_instance.b[8] << 8; + hbus->sysdata.parent = hdev->device.parent; + hbus->use_calls = false; +#endif hbus->hdev = hdev; - refcount_set(&hbus->remove_lock, 1); INIT_LIST_HEAD(&hbus->children); INIT_LIST_HEAD(&hbus->dr_list); - INIT_LIST_HEAD(&hbus->resources_for_children); spin_lock_init(&hbus->config_lock); spin_lock_init(&hbus->device_list_lock); - spin_lock_init(&hbus->retarget_msi_interrupt_lock); - init_completion(&hbus->remove_event); hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0, - hbus->sysdata.domain); + hbus->bridge->domain_nr); if (!hbus->wq) { ret = -ENOMEM; - goto free_bus; + goto free_dom; } + hdev->channel->next_request_id_callback = vmbus_next_request_id; + hdev->channel->request_addr_callback = vmbus_request_addr; + hdev->channel->rqstor_size = HV_PCI_RQSTOR_SIZE; + ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0, hv_pci_onchannelcallback, hbus); if (ret) @@ -2552,7 +3795,8 @@ static int hv_pci_probe(struct hv_device *hdev, hv_set_drvdata(hdev, hbus); - ret = hv_pci_protocol_negotiation(hdev); + ret = hv_pci_protocol_negotiation(hdev, pci_protocol_versions, + ARRAY_SIZE(pci_protocol_versions)); if (ret) goto close; @@ -2569,8 +3813,15 @@ static int hv_pci_probe(struct hv_device *hdev, goto free_config; } - hbus->sysdata.fwnode = irq_domain_alloc_fwnode(hbus); - if (!hbus->sysdata.fwnode) { + name = kasprintf(GFP_KERNEL, "%pUL", &hdev->dev_instance); + if (!name) { + ret = -ENOMEM; + goto unmap; + } + + hbus->fwnode = irq_domain_alloc_named_fwnode(name); + kfree(name); + if (!hbus->fwnode) { ret = -ENOMEM; goto unmap; } @@ -2583,13 +3834,15 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_irq_domain; + mutex_lock(&hbus->state_lock); + ret = hv_pci_enter_d0(hdev); if (ret) - goto free_irq_domain; + goto release_state_lock; ret = hv_pci_allocate_bridge_windows(hbus); if (ret) - goto free_irq_domain; + goto exit_d0; ret = hv_send_resources_allocated(hdev); if (ret) @@ -2603,14 +3856,19 @@ static int hv_pci_probe(struct hv_device *hdev, if (ret) goto free_windows; + mutex_unlock(&hbus->state_lock); return 0; free_windows: hv_pci_free_bridge_windows(hbus); +exit_d0: + (void) hv_pci_bus_exit(hdev, true); +release_state_lock: + mutex_unlock(&hbus->state_lock); free_irq_domain: irq_domain_remove(hbus->irq_domain); free_fwnode: - irq_domain_free_fwnode(hbus->sysdata.fwnode); + irq_domain_free_fwnode(hbus->fwnode); unmap: iounmap(hbus->cfg_addr); free_config: @@ -2619,88 +3877,262 @@ close: vmbus_close(hdev->channel); destroy_wq: destroy_workqueue(hbus->wq); +free_dom: + pci_bus_release_emul_domain_nr(hbus->bridge->domain_nr); free_bus: - free_page((unsigned long)hbus); + kfree(hbus); return ret; } -static void hv_pci_bus_exit(struct hv_device *hdev) +static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs) { struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + struct vmbus_channel *chan = hdev->channel; struct { struct pci_packet teardown_packet; u8 buffer[sizeof(struct pci_message)]; } pkt; - struct pci_bus_relations relations; + struct pci_message *msg; struct hv_pci_compl comp_pkt; + struct hv_pci_dev *hpdev, *tmp; + unsigned long flags; + u64 trans_id; int ret; /* * After the host sends the RESCIND_CHANNEL message, it doesn't * access the per-channel ringbuffer any longer. */ - if (hdev->channel->rescind) - return; + if (chan->rescind) + return 0; + + if (!keep_devs) { + struct list_head removed; + + /* Move all present children to the list on stack */ + INIT_LIST_HEAD(&removed); + spin_lock_irqsave(&hbus->device_list_lock, flags); + list_for_each_entry_safe(hpdev, tmp, &hbus->children, list_entry) + list_move_tail(&hpdev->list_entry, &removed); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); - /* Delete any children which might still exist. */ - memset(&relations, 0, sizeof(relations)); - hv_pci_devices_present(hbus, &relations); + /* Remove all children in the list */ + list_for_each_entry_safe(hpdev, tmp, &removed, list_entry) { + list_del(&hpdev->list_entry); + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + /* For the two refs got in new_pcichild_device() */ + put_pcichild(hpdev); + put_pcichild(hpdev); + } + } ret = hv_send_resources_released(hdev); - if (ret) + if (ret) { dev_err(&hdev->device, "Couldn't send resources released packet(s)\n"); + return ret; + } memset(&pkt.teardown_packet, 0, sizeof(pkt.teardown_packet)); init_completion(&comp_pkt.host_event); pkt.teardown_packet.completion_func = hv_pci_generic_compl; pkt.teardown_packet.compl_ctxt = &comp_pkt; - pkt.teardown_packet.message[0].type = PCI_BUS_D0EXIT; + msg = (struct pci_message *)pkt.buffer; + msg->type = PCI_BUS_D0EXIT; - ret = vmbus_sendpacket(hdev->channel, &pkt.teardown_packet.message, - sizeof(struct pci_message), - (unsigned long)&pkt.teardown_packet, - VM_PKT_DATA_INBAND, - VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); - if (!ret) - wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ); + 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); + if (ret) + return ret; + + if (wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ) == 0) { + /* + * The completion packet on the stack becomes invalid after + * 'return'; remove the ID from the VMbus requestor if the + * identifier is still mapped to/associated with the packet. + * + * Cf. hv_pci_onchannelcallback(). + */ + vmbus_request_addr_match(chan, trans_id, + (unsigned long)&pkt.teardown_packet); + return -ETIMEDOUT; + } + + return 0; } /** * hv_pci_remove() - Remove routine for this VMBus channel * @hdev: VMBus's tracking struct for this root PCI bus - * - * Return: 0 on success, -errno on failure */ -static int hv_pci_remove(struct hv_device *hdev) +static void hv_pci_remove(struct hv_device *hdev) { struct hv_pcibus_device *hbus; hbus = hv_get_drvdata(hdev); if (hbus->state == hv_pcibus_installed) { + tasklet_disable(&hdev->channel->callback_event); + hbus->state = hv_pcibus_removing; + tasklet_enable(&hdev->channel->callback_event); + destroy_workqueue(hbus->wq); + hbus->wq = NULL; + /* + * At this point, no work is running or can be scheduled + * on hbus-wq. We can't race with hv_pci_devices_present() + * or hv_pci_eject_device(), it's safe to proceed. + */ + /* Remove the bus from PCI's point of view. */ pci_lock_rescan_remove(); - pci_stop_root_bus(hbus->pci_bus); - pci_remove_root_bus(hbus->pci_bus); + pci_stop_root_bus(hbus->bridge->bus); + hv_pci_remove_slots(hbus); + pci_remove_root_bus(hbus->bridge->bus); pci_unlock_rescan_remove(); - hbus->state = hv_pcibus_removed; } - hv_pci_bus_exit(hdev); + hv_pci_bus_exit(hdev, false); vmbus_close(hdev->channel); iounmap(hbus->cfg_addr); hv_free_config_window(hbus); - pci_free_resource_list(&hbus->resources_for_children); hv_pci_free_bridge_windows(hbus); irq_domain_remove(hbus->irq_domain); - irq_domain_free_fwnode(hbus->sysdata.fwnode); - put_hvpcibus(hbus); - wait_for_completion(&hbus->remove_event); - destroy_workqueue(hbus->wq); - free_page((unsigned long)hbus); + irq_domain_free_fwnode(hbus->fwnode); + + kfree(hbus); +} + +static int hv_pci_suspend(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + enum hv_pcibus_state old_state; + int ret; + + /* + * hv_pci_suspend() must make sure there are no pending work items + * before calling vmbus_close(), since it runs in a process context + * as a callback in dpm_suspend(). When it starts to run, the channel + * callback hv_pci_onchannelcallback(), which runs in a tasklet + * context, can be still running concurrently and scheduling new work + * items onto hbus->wq in hv_pci_devices_present() and + * hv_pci_eject_device(), and the work item handlers can access the + * vmbus channel, which can be being closed by hv_pci_suspend(), e.g. + * the work item handler pci_devices_present_work() -> + * new_pcichild_device() writes to the vmbus channel. + * + * To eliminate the race, hv_pci_suspend() disables the channel + * callback tasklet, sets hbus->state to hv_pcibus_removing, and + * re-enables the tasklet. This way, when hv_pci_suspend() proceeds, + * it knows that no new work item can be scheduled, and then it flushes + * hbus->wq and safely closes the vmbus channel. + */ + tasklet_disable(&hdev->channel->callback_event); + + /* Change the hbus state to prevent new work items. */ + old_state = hbus->state; + if (hbus->state == hv_pcibus_installed) + hbus->state = hv_pcibus_removing; + + tasklet_enable(&hdev->channel->callback_event); + + if (old_state != hv_pcibus_installed) + return -EINVAL; + + flush_workqueue(hbus->wq); + + ret = hv_pci_bus_exit(hdev, true); + if (ret) + return ret; + + vmbus_close(hdev->channel); + + return 0; +} + +static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg) +{ + struct irq_data *irq_data; + struct msi_desc *entry; + + if (!pdev->msi_enabled && !pdev->msix_enabled) + return 0; + + 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)) + return -EINVAL; + hv_compose_msi_msg(irq_data, &entry->msg); + } + return 0; +} + +/* + * Upon resume, pci_restore_msi_state() -> ... -> __pci_write_msi_msg() + * directly writes the MSI/MSI-X registers via MMIO, but since Hyper-V + * doesn't trap and emulate the MMIO accesses, here hv_compose_msi_msg() + * must be used to ask Hyper-V to re-create the IOMMU Interrupt Remapping + * Table entries. + */ +static void hv_pci_restore_msi_state(struct hv_pcibus_device *hbus) +{ + pci_walk_bus(hbus->bridge->bus, hv_pci_restore_msi_msg, NULL); +} + +static int hv_pci_resume(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + enum pci_protocol_version_t version[1]; + int ret; + + hbus->state = hv_pcibus_init; + + hdev->channel->next_request_id_callback = vmbus_next_request_id; + hdev->channel->request_addr_callback = vmbus_request_addr; + hdev->channel->rqstor_size = HV_PCI_RQSTOR_SIZE; + + ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0, + hv_pci_onchannelcallback, hbus); + if (ret) + return ret; + + /* Only use the version that was in use before hibernation. */ + version[0] = hbus->protocol_version; + ret = hv_pci_protocol_negotiation(hdev, version, 1); + if (ret) + goto out; + + ret = hv_pci_query_relations(hdev); + if (ret) + goto out; + + mutex_lock(&hbus->state_lock); + + ret = hv_pci_enter_d0(hdev); + if (ret) + goto release_state_lock; + + ret = hv_send_resources_allocated(hdev); + if (ret) + goto release_state_lock; + + prepopulate_bars(hbus); + + hv_pci_restore_msi_state(hbus); + + hbus->state = hv_pcibus_installed; + mutex_unlock(&hbus->state_lock); return 0; + +release_state_lock: + mutex_unlock(&hbus->state_lock); +out: + vmbus_close(hdev->channel); + return ret; } static const struct hv_vmbus_device_id hv_pci_id_table[] = { @@ -2717,15 +4149,38 @@ static struct hv_driver hv_pci_drv = { .id_table = hv_pci_id_table, .probe = hv_pci_probe, .remove = hv_pci_remove, + .suspend = hv_pci_suspend, + .resume = hv_pci_resume, }; static void __exit exit_hv_pci_drv(void) { vmbus_driver_unregister(&hv_pci_drv); + + hvpci_block_ops.read_block = NULL; + hvpci_block_ops.write_block = NULL; + hvpci_block_ops.reg_blk_invalidate = NULL; } static int __init init_hv_pci_drv(void) { + int ret; + + if (!hv_is_hyperv_initialized()) + return -ENODEV; + + if (hv_root_partition() && !hv_nested) + return -ENODEV; + + ret = hv_pci_irqchip_init(); + if (ret) + return ret; + + /* Initialize PCI block r/w interface */ + hvpci_block_ops.read_block = hv_read_config_block; + hvpci_block_ops.write_block = hv_write_config_block; + hvpci_block_ops.reg_blk_invalidate = hv_register_block_invalidate; + return vmbus_driver_register(&hv_pci_drv); } diff --git a/drivers/pci/controller/pci-ixp4xx.c b/drivers/pci/controller/pci-ixp4xx.c new file mode 100644 index 000000000000..9fd401838bad --- /dev/null +++ b/drivers/pci/controller/pci-ixp4xx.c @@ -0,0 +1,678 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for Intel IXP4xx PCI host controller + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * + * Based on the IXP4xx arch/arm/mach-ixp4xx/common-pci.c driver + * Copyright (C) 2002 Intel Corporation + * Copyright (C) 2003 Greg Ungerer <gerg@linux-m68k.org> + * Copyright (C) 2003-2004 MontaVista Software, Inc. + * Copyright (C) 2005 Deepak Saxena <dsaxena@plexity.net> + * Copyright (C) 2005 Alessandro Zummo <a.zummo@towertech.it> + * + * TODO: + * - Test IO-space access + * - DMA support + */ + +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/bits.h> +#include "../pci.h" + +/* Register offsets */ +#define IXP4XX_PCI_NP_AD 0x00 +#define IXP4XX_PCI_NP_CBE 0x04 +#define IXP4XX_PCI_NP_WDATA 0x08 +#define IXP4XX_PCI_NP_RDATA 0x0c +#define IXP4XX_PCI_CRP_AD_CBE 0x10 +#define IXP4XX_PCI_CRP_WDATA 0x14 +#define IXP4XX_PCI_CRP_RDATA 0x18 +#define IXP4XX_PCI_CSR 0x1c +#define IXP4XX_PCI_ISR 0x20 +#define IXP4XX_PCI_INTEN 0x24 +#define IXP4XX_PCI_DMACTRL 0x28 +#define IXP4XX_PCI_AHBMEMBASE 0x2c +#define IXP4XX_PCI_AHBIOBASE 0x30 +#define IXP4XX_PCI_PCIMEMBASE 0x34 +#define IXP4XX_PCI_AHBDOORBELL 0x38 +#define IXP4XX_PCI_PCIDOORBELL 0x3c +#define IXP4XX_PCI_ATPDMA0_AHBADDR 0x40 +#define IXP4XX_PCI_ATPDMA0_PCIADDR 0x44 +#define IXP4XX_PCI_ATPDMA0_LENADDR 0x48 +#define IXP4XX_PCI_ATPDMA1_AHBADDR 0x4c +#define IXP4XX_PCI_ATPDMA1_PCIADDR 0x50 +#define IXP4XX_PCI_ATPDMA1_LENADDR 0x54 + +/* CSR bit definitions */ +#define IXP4XX_PCI_CSR_HOST BIT(0) +#define IXP4XX_PCI_CSR_ARBEN BIT(1) +#define IXP4XX_PCI_CSR_ADS BIT(2) +#define IXP4XX_PCI_CSR_PDS BIT(3) +#define IXP4XX_PCI_CSR_ABE BIT(4) +#define IXP4XX_PCI_CSR_DBT BIT(5) +#define IXP4XX_PCI_CSR_ASE BIT(8) +#define IXP4XX_PCI_CSR_IC BIT(15) +#define IXP4XX_PCI_CSR_PRST BIT(16) + +/* ISR (Interrupt status) Register bit definitions */ +#define IXP4XX_PCI_ISR_PSE BIT(0) +#define IXP4XX_PCI_ISR_PFE BIT(1) +#define IXP4XX_PCI_ISR_PPE BIT(2) +#define IXP4XX_PCI_ISR_AHBE BIT(3) +#define IXP4XX_PCI_ISR_APDC BIT(4) +#define IXP4XX_PCI_ISR_PADC BIT(5) +#define IXP4XX_PCI_ISR_ADB BIT(6) +#define IXP4XX_PCI_ISR_PDB BIT(7) + +/* INTEN (Interrupt Enable) Register bit definitions */ +#define IXP4XX_PCI_INTEN_PSE BIT(0) +#define IXP4XX_PCI_INTEN_PFE BIT(1) +#define IXP4XX_PCI_INTEN_PPE BIT(2) +#define IXP4XX_PCI_INTEN_AHBE BIT(3) +#define IXP4XX_PCI_INTEN_APDC BIT(4) +#define IXP4XX_PCI_INTEN_PADC BIT(5) +#define IXP4XX_PCI_INTEN_ADB BIT(6) +#define IXP4XX_PCI_INTEN_PDB BIT(7) + +/* Shift value for byte enable on NP cmd/byte enable register */ +#define IXP4XX_PCI_NP_CBE_BESL 4 + +/* PCI commands supported by NP access unit */ +#define NP_CMD_IOREAD 0x2 +#define NP_CMD_IOWRITE 0x3 +#define NP_CMD_CONFIGREAD 0xa +#define NP_CMD_CONFIGWRITE 0xb +#define NP_CMD_MEMREAD 0x6 +#define NP_CMD_MEMWRITE 0x7 + +/* Constants for CRP access into local config space */ +#define CRP_AD_CBE_BESL 20 +#define CRP_AD_CBE_WRITE 0x00010000 + +/* Special PCI configuration space registers for this controller */ +#define IXP4XX_PCI_RTOTTO 0x40 + +struct ixp4xx_pci { + struct device *dev; + void __iomem *base; + bool errata_hammer; + bool host_mode; +}; + +/* + * The IXP4xx has a peculiar address bus that will change the + * byte order on SoC peripherals depending on whether the device + * operates in big-endian or little-endian mode. That means that + * readl() and writel() that always use little-endian access + * will not work for SoC peripherals such as the PCI controller + * when used in big-endian mode. The accesses to the individual + * PCI devices on the other hand, are always little-endian and + * can use readl() and writel(). + * + * For local AHB bus access we need to use __raw_[readl|writel]() + * to make sure that we access the SoC devices in the CPU native + * endianness. + */ +static inline u32 ixp4xx_readl(struct ixp4xx_pci *p, u32 reg) +{ + return __raw_readl(p->base + reg); +} + +static inline void ixp4xx_writel(struct ixp4xx_pci *p, u32 reg, u32 val) +{ + __raw_writel(val, p->base + reg); +} + +static int ixp4xx_pci_check_master_abort(struct ixp4xx_pci *p) +{ + u32 isr = ixp4xx_readl(p, IXP4XX_PCI_ISR); + + if (isr & IXP4XX_PCI_ISR_PFE) { + /* Make sure the master abort bit is reset */ + ixp4xx_writel(p, IXP4XX_PCI_ISR, IXP4XX_PCI_ISR_PFE); + dev_dbg(p->dev, "master abort detected\n"); + return -EINVAL; + } + + return 0; +} + +static int ixp4xx_pci_read_indirect(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 *data) +{ + ixp4xx_writel(p, IXP4XX_PCI_NP_AD, addr); + + if (p->errata_hammer) { + int i; + + /* + * PCI workaround - only works if NP PCI space reads have + * no side effects. Hammer the register and read twice 8 + * times. last one will be good. + */ + for (i = 0; i < 8; i++) { + ixp4xx_writel(p, IXP4XX_PCI_NP_CBE, cmd); + *data = ixp4xx_readl(p, IXP4XX_PCI_NP_RDATA); + *data = ixp4xx_readl(p, IXP4XX_PCI_NP_RDATA); + } + } else { + ixp4xx_writel(p, IXP4XX_PCI_NP_CBE, cmd); + *data = ixp4xx_readl(p, IXP4XX_PCI_NP_RDATA); + } + + return ixp4xx_pci_check_master_abort(p); +} + +static int ixp4xx_pci_write_indirect(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 data) +{ + ixp4xx_writel(p, IXP4XX_PCI_NP_AD, addr); + + /* Set up the write */ + ixp4xx_writel(p, IXP4XX_PCI_NP_CBE, cmd); + + /* Execute the write by writing to NP_WDATA */ + ixp4xx_writel(p, IXP4XX_PCI_NP_WDATA, data); + + return ixp4xx_pci_check_master_abort(p); +} + +static u32 ixp4xx_config_addr(u8 bus_num, u16 devfn, int where) +{ + /* Root bus is always 0 in this hardware */ + if (bus_num == 0) { + /* type 0 */ + return (PCI_CONF1_ADDRESS(0, 0, PCI_FUNC(devfn), where) & + ~PCI_CONF1_ENABLE) | BIT(32-PCI_SLOT(devfn)); + } else { + /* type 1 */ + return (PCI_CONF1_ADDRESS(bus_num, PCI_SLOT(devfn), + PCI_FUNC(devfn), where) & + ~PCI_CONF1_ENABLE) | 1; + } +} + +/* + * CRP functions are "Controller Configuration Port" accesses + * initiated from within this driver itself to read/write PCI + * control information in the config space. + */ +static u32 ixp4xx_crp_byte_lane_enable_bits(u32 n, int size) +{ + if (size == 1) + return (0xf & ~BIT(n)) << CRP_AD_CBE_BESL; + if (size == 2) + return (0xf & ~(BIT(n) | BIT(n+1))) << CRP_AD_CBE_BESL; + if (size == 4) + return 0; + return 0xffffffff; +} + +#ifdef CONFIG_ARM +static int ixp4xx_crp_read_config(struct ixp4xx_pci *p, int where, int size, + u32 *value) +{ + u32 n, cmd, val; + + n = where % 4; + cmd = where & ~3; + + dev_dbg(p->dev, "%s from %d size %d cmd %08x\n", + __func__, where, size, cmd); + + ixp4xx_writel(p, IXP4XX_PCI_CRP_AD_CBE, cmd); + val = ixp4xx_readl(p, IXP4XX_PCI_CRP_RDATA); + + val >>= (8*n); + switch (size) { + case 1: + val &= U8_MAX; + dev_dbg(p->dev, "%s read byte %02x\n", __func__, val); + break; + case 2: + val &= U16_MAX; + dev_dbg(p->dev, "%s read word %04x\n", __func__, val); + break; + case 4: + val &= U32_MAX; + dev_dbg(p->dev, "%s read long %08x\n", __func__, val); + break; + default: + /* Should not happen */ + dev_err(p->dev, "%s illegal size\n", __func__); + return PCIBIOS_DEVICE_NOT_FOUND; + } + *value = val; + + return PCIBIOS_SUCCESSFUL; +} +#endif + +static int ixp4xx_crp_write_config(struct ixp4xx_pci *p, int where, int size, + u32 value) +{ + u32 n, cmd, val; + + n = where % 4; + cmd = ixp4xx_crp_byte_lane_enable_bits(n, size); + if (cmd == 0xffffffff) + return PCIBIOS_BAD_REGISTER_NUMBER; + cmd |= where & ~3; + cmd |= CRP_AD_CBE_WRITE; + + val = value << (8*n); + + dev_dbg(p->dev, "%s to %d size %d cmd %08x val %08x\n", + __func__, where, size, cmd, val); + + ixp4xx_writel(p, IXP4XX_PCI_CRP_AD_CBE, cmd); + ixp4xx_writel(p, IXP4XX_PCI_CRP_WDATA, val); + + return PCIBIOS_SUCCESSFUL; +} + +/* + * Then follows the functions that read and write from the common PCI + * configuration space. + */ +static u32 ixp4xx_byte_lane_enable_bits(u32 n, int size) +{ + if (size == 1) + return (0xf & ~BIT(n)) << 4; + if (size == 2) + return (0xf & ~(BIT(n) | BIT(n+1))) << 4; + if (size == 4) + return 0; + return 0xffffffff; +} + +static int ixp4xx_pci_read_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *value) +{ + struct ixp4xx_pci *p = bus->sysdata; + u32 n, addr, val, cmd; + u8 bus_num = bus->number; + int ret; + + *value = 0xffffffff; + n = where % 4; + cmd = ixp4xx_byte_lane_enable_bits(n, size); + if (cmd == 0xffffffff) + return PCIBIOS_BAD_REGISTER_NUMBER; + + addr = ixp4xx_config_addr(bus_num, devfn, where); + cmd |= NP_CMD_CONFIGREAD; + dev_dbg(p->dev, "read_config from %d size %d dev %d:%d:%d address: %08x cmd: %08x\n", + where, size, bus_num, PCI_SLOT(devfn), PCI_FUNC(devfn), addr, cmd); + + ret = ixp4xx_pci_read_indirect(p, addr, cmd, &val); + if (ret) + return PCIBIOS_DEVICE_NOT_FOUND; + + val >>= (8*n); + switch (size) { + case 1: + val &= U8_MAX; + dev_dbg(p->dev, "%s read byte %02x\n", __func__, val); + break; + case 2: + val &= U16_MAX; + dev_dbg(p->dev, "%s read word %04x\n", __func__, val); + break; + case 4: + val &= U32_MAX; + dev_dbg(p->dev, "%s read long %08x\n", __func__, val); + break; + default: + /* Should not happen */ + dev_err(p->dev, "%s illegal size\n", __func__); + return PCIBIOS_DEVICE_NOT_FOUND; + } + *value = val; + + return PCIBIOS_SUCCESSFUL; +} + +static int ixp4xx_pci_write_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 value) +{ + struct ixp4xx_pci *p = bus->sysdata; + u32 n, addr, val, cmd; + u8 bus_num = bus->number; + int ret; + + n = where % 4; + cmd = ixp4xx_byte_lane_enable_bits(n, size); + if (cmd == 0xffffffff) + return PCIBIOS_BAD_REGISTER_NUMBER; + + addr = ixp4xx_config_addr(bus_num, devfn, where); + cmd |= NP_CMD_CONFIGWRITE; + val = value << (8*n); + + dev_dbg(p->dev, "write_config_byte %#x to %d size %d dev %d:%d:%d addr: %08x cmd %08x\n", + value, where, size, bus_num, PCI_SLOT(devfn), PCI_FUNC(devfn), addr, cmd); + + ret = ixp4xx_pci_write_indirect(p, addr, cmd, val); + if (ret) + return PCIBIOS_DEVICE_NOT_FOUND; + + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops ixp4xx_pci_ops = { + .read = ixp4xx_pci_read_config, + .write = ixp4xx_pci_write_config, +}; + +static u32 ixp4xx_pci_addr_to_64mconf(phys_addr_t addr) +{ + u8 base; + + base = ((addr & 0xff000000) >> 24); + return (base << 24) | ((base + 1) << 16) + | ((base + 2) << 8) | (base + 3); +} + +static int ixp4xx_pci_parse_map_ranges(struct ixp4xx_pci *p) +{ + struct device *dev = p->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(p); + struct resource_entry *win; + struct resource *res; + phys_addr_t addr; + + win = resource_list_first_type(&bridge->windows, IORESOURCE_MEM); + if (win) { + u32 pcimembase; + + res = win->res; + addr = res->start - win->offset; + + if (res->flags & IORESOURCE_PREFETCH) + res->name = "IXP4xx PCI PRE-MEM"; + else + res->name = "IXP4xx PCI NON-PRE-MEM"; + + dev_dbg(dev, "%s window %pR, bus addr %pa\n", + res->name, res, &addr); + if (resource_size(res) != SZ_64M) { + dev_err(dev, "memory range is not 64MB\n"); + return -EINVAL; + } + + pcimembase = ixp4xx_pci_addr_to_64mconf(addr); + /* Commit configuration */ + ixp4xx_writel(p, IXP4XX_PCI_PCIMEMBASE, pcimembase); + } else { + dev_err(dev, "no AHB memory mapping defined\n"); + } + + win = resource_list_first_type(&bridge->windows, IORESOURCE_IO); + if (win) { + res = win->res; + + addr = pci_pio_to_address(res->start); + if (addr & 0xff) { + dev_err(dev, "IO mem at uneven address: %pa\n", &addr); + return -EINVAL; + } + + res->name = "IXP4xx PCI IO MEM"; + /* + * Setup I/O space location for PCI->AHB access, the + * upper 24 bits of the address goes into the lower + * 24 bits of this register. + */ + ixp4xx_writel(p, IXP4XX_PCI_AHBIOBASE, (addr >> 8)); + } else { + dev_info(dev, "no IO space AHB memory mapping defined\n"); + } + + return 0; +} + +static int ixp4xx_pci_parse_map_dma_ranges(struct ixp4xx_pci *p) +{ + struct device *dev = p->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(p); + struct resource_entry *win; + struct resource *res; + phys_addr_t addr; + u32 ahbmembase; + + win = resource_list_first_type(&bridge->dma_ranges, IORESOURCE_MEM); + if (win) { + res = win->res; + addr = res->start - win->offset; + + if (resource_size(res) != SZ_64M) { + dev_err(dev, "DMA memory range is not 64MB\n"); + return -EINVAL; + } + + dev_dbg(dev, "DMA MEM BASE: %pa\n", &addr); + /* + * 4 PCI-to-AHB windows of 16 MB each, write the 8 high bits + * into each byte of the PCI_AHBMEMBASE register. + */ + ahbmembase = ixp4xx_pci_addr_to_64mconf(addr); + /* Commit AHB membase */ + ixp4xx_writel(p, IXP4XX_PCI_AHBMEMBASE, ahbmembase); + } else { + dev_err(dev, "no DMA memory range defined\n"); + } + + return 0; +} + +#ifdef CONFIG_ARM +/* Only used to get context for abort handling */ +static struct ixp4xx_pci *ixp4xx_pci_abort_singleton; + +static int ixp4xx_pci_abort_handler(unsigned long addr, unsigned int fsr, + struct pt_regs *regs) +{ + struct ixp4xx_pci *p = ixp4xx_pci_abort_singleton; + u32 isr, status; + int ret; + + isr = ixp4xx_readl(p, IXP4XX_PCI_ISR); + ret = ixp4xx_crp_read_config(p, PCI_STATUS, 2, &status); + if (ret) { + dev_err(p->dev, "unable to read abort status\n"); + return -EINVAL; + } + + dev_err(p->dev, + "PCI: abort_handler addr = %#lx, isr = %#x, status = %#x\n", + addr, isr, status); + + /* Make sure the Master Abort bit is reset */ + ixp4xx_writel(p, IXP4XX_PCI_ISR, IXP4XX_PCI_ISR_PFE); + status |= PCI_STATUS_REC_MASTER_ABORT; + ret = ixp4xx_crp_write_config(p, PCI_STATUS, 2, status); + if (ret) + dev_err(p->dev, "unable to clear abort status bit\n"); + + /* + * If it was an imprecise abort, then we need to correct the + * return address to be _after_ the instruction. + */ + if (fsr & (1 << 10)) { + dev_err(p->dev, "imprecise abort\n"); + regs->ARM_pc += 4; + } + + return 0; +} +#endif + +static int __init ixp4xx_pci_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct ixp4xx_pci *p; + struct pci_host_bridge *host; + int ret; + u32 val; + phys_addr_t addr; + u32 basereg[4] = { + PCI_BASE_ADDRESS_0, + PCI_BASE_ADDRESS_1, + PCI_BASE_ADDRESS_2, + PCI_BASE_ADDRESS_3, + }; + int i; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*p)); + if (!host) + return -ENOMEM; + + host->ops = &ixp4xx_pci_ops; + p = pci_host_bridge_priv(host); + host->sysdata = p; + p->dev = dev; + dev_set_drvdata(dev, p); + + /* + * Set up quirk for erratic behaviour in the 42x variant + * when accessing config space. + */ + if (of_device_is_compatible(np, "intel,ixp42x-pci")) { + p->errata_hammer = true; + dev_info(dev, "activate hammering errata\n"); + } + + p->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(p->base)) + return PTR_ERR(p->base); + + val = ixp4xx_readl(p, IXP4XX_PCI_CSR); + p->host_mode = !!(val & IXP4XX_PCI_CSR_HOST); + dev_info(dev, "controller is in %s mode\n", + p->host_mode ? "host" : "option"); + +#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) + return ret; + + ret = ixp4xx_pci_parse_map_dma_ranges(p); + if (ret) + return ret; + + /* This is only configured in host mode */ + if (p->host_mode) { + addr = __pa(PAGE_OFFSET); + /* This is a noop (0x00) but explains what is going on */ + addr |= PCI_BASE_ADDRESS_SPACE_MEMORY; + + for (i = 0; i < 4; i++) { + /* Write this directly into the config space */ + ret = ixp4xx_crp_write_config(p, basereg[i], 4, addr); + if (ret) + dev_err(dev, "failed to set up PCI_BASE_ADDRESS_%d\n", i); + else + dev_info(dev, "set PCI_BASE_ADDR_%d to %pa\n", i, &addr); + addr += SZ_16M; + } + + /* + * Enable CSR window at 64 MiB to allow PCI masters to continue + * prefetching past the 64 MiB boundary, if all AHB to PCI + * windows are consecutive. + */ + ret = ixp4xx_crp_write_config(p, PCI_BASE_ADDRESS_4, 4, addr); + if (ret) + dev_err(dev, "failed to set up PCI_BASE_ADDRESS_4\n"); + else + dev_info(dev, "set PCI_BASE_ADDR_4 to %pa\n", &addr); + + /* + * Put the IO memory window at the very end of physical memory + * at 0xfffffc00. This is when the system is trying to access IO + * memory over AHB. + */ + addr = 0xfffffc00; + addr |= PCI_BASE_ADDRESS_SPACE_IO; + ret = ixp4xx_crp_write_config(p, PCI_BASE_ADDRESS_5, 4, addr); + if (ret) + dev_err(dev, "failed to set up PCI_BASE_ADDRESS_5\n"); + else + dev_info(dev, "set PCI_BASE_ADDR_5 to %pa\n", &addr); + + /* + * Retry timeout to 0x80 + * Transfer ready timeout to 0xff + */ + ret = ixp4xx_crp_write_config(p, IXP4XX_PCI_RTOTTO, 4, + 0x000080ff); + if (ret) + dev_err(dev, "failed to set up TRDY limit\n"); + else + dev_info(dev, "set TRDY limit to 0x80ff\n"); + } + + /* Clear interrupts */ + val = IXP4XX_PCI_ISR_PSE | IXP4XX_PCI_ISR_PFE | IXP4XX_PCI_ISR_PPE | IXP4XX_PCI_ISR_AHBE; + ixp4xx_writel(p, IXP4XX_PCI_ISR, val); + + /* + * Set Initialize Complete in PCI Control Register: allow IXP4XX to + * generate PCI configuration cycles. Specify that the AHB bus is + * operating in big-endian mode. Set up byte lane swapping between + * little-endian PCI and the big-endian AHB bus. + */ + val = IXP4XX_PCI_CSR_IC | IXP4XX_PCI_CSR_ABE; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + val |= (IXP4XX_PCI_CSR_PDS | IXP4XX_PCI_CSR_ADS); + ixp4xx_writel(p, IXP4XX_PCI_CSR, val); + + ret = ixp4xx_crp_write_config(p, PCI_COMMAND, 2, PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY); + if (ret) + dev_err(dev, "unable to initialize master and command memory\n"); + else + dev_info(dev, "initialized as master\n"); + + pci_host_probe(host); + + return 0; +} + +static const struct of_device_id ixp4xx_pci_of_match[] = { + { + .compatible = "intel,ixp42x-pci", + }, + { + .compatible = "intel,ixp43x-pci", + }, + {}, +}; + +/* + * This driver needs to be a builtin module with suppressed bind + * attributes since the probe() is initializing a hard exception + * handler and this can only be done from __init-tagged code + * sections. This module cannot be removed and inserted at all. + */ +static struct platform_driver ixp4xx_pci_driver = { + .driver = { + .name = "ixp4xx-pci", + .suppress_bind_attrs = true, + .of_match_table = ixp4xx_pci_of_match, + }, +}; +builtin_platform_driver_probe(ixp4xx_pci_driver, ixp4xx_pci_probe); diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c new file mode 100644 index 000000000000..bc630ab8a283 --- /dev/null +++ b/drivers/pci/controller/pci-loongson.c @@ -0,0 +1,410 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Loongson PCI Host Controller Driver + * + * Copyright (C) 2020 Jiaxun Yang <jiaxun.yang@flygoat.com> + */ + +#include <linux/of.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> + +#include "../pci.h" + +/* Device IDs */ +#define DEV_LS2K_PCIE_PORT0 0x1a05 +#define DEV_LS7A_PCIE_PORT0 0x7a09 +#define DEV_LS7A_PCIE_PORT1 0x7a19 +#define DEV_LS7A_PCIE_PORT2 0x7a29 +#define DEV_LS7A_PCIE_PORT3 0x7a39 +#define DEV_LS7A_PCIE_PORT4 0x7a49 +#define DEV_LS7A_PCIE_PORT5 0x7a59 +#define DEV_LS7A_PCIE_PORT6 0x7a69 + +#define DEV_LS2K_APB 0x7a02 +#define DEV_LS7A_GMAC 0x7a03 +#define DEV_LS7A_DC1 0x7a06 +#define DEV_LS7A_LPC 0x7a0c +#define DEV_LS7A_AHCI 0x7a08 +#define DEV_LS7A_CONF 0x7a10 +#define DEV_LS7A_GNET 0x7a13 +#define DEV_LS7A_EHCI 0x7a14 +#define DEV_LS7A_DC2 0x7a36 +#define DEV_LS7A_HDMI 0x7a37 + +#define FLAG_CFG0 BIT(0) +#define FLAG_CFG1 BIT(1) +#define FLAG_DEV_FIX BIT(2) +#define FLAG_DEV_HIDDEN BIT(3) + +struct loongson_pci_data { + u32 flags; + struct pci_ops *ops; +}; + +struct loongson_pci { + void __iomem *cfg0_base; + void __iomem *cfg1_base; + struct platform_device *pdev; + const struct loongson_pci_data *data; +}; + +/* Fixup wrong class code in PCIe bridges */ +static void bridge_class_quirk(struct pci_dev *dev) +{ + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT0, bridge_class_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT1, bridge_class_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT2, bridge_class_quirk); + +static void system_bus_quirk(struct pci_dev *pdev) +{ + /* + * The address space consumed by these devices is outside the + * resources of the host bridge. + */ + pdev->mmio_always_on = 1; + pdev->non_compliant_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS2K_APB, system_bus_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_CONF, system_bus_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_LPC, system_bus_quirk); + +/* + * Some Loongson PCIe ports have hardware limitations on their Maximum Read + * Request Size. They can't handle anything larger than this. Sane + * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for + * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly, + * so we have to enforce maximum safe MRRS, which is 256 bytes. + */ +#ifdef CONFIG_MIPS +static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev) +{ + struct pci_bus *bus = pdev->bus; + struct pci_dev *bridge; + static const struct pci_device_id bridge_devids[] = { + { PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) }, + { 0, }, + }; + + /* look for the matching bridge */ + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + bus = bus->parent; + + if (pci_match_id(bridge_devids, bridge)) { + if (pcie_get_readrq(pdev) > 256) { + pci_info(pdev, "limiting MRRS to 256\n"); + pcie_set_readrq(pdev, 256); + } + break; + } + } +} +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk); +#endif + +static void loongson_mrrs_quirk(struct pci_dev *pdev) +{ + struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); + + bridge->no_inc_mrrs = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS2K_PCIE_PORT0, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT0, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT1, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT2, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT3, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT4, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT5, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT6, loongson_mrrs_quirk); + +static void loongson_pci_pin_quirk(struct pci_dev *pdev) +{ + pdev->pin = 1 + (PCI_FUNC(pdev->devfn) & 3); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_DC1, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_DC2, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_GMAC, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_AHCI, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_EHCI, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_GNET, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_HDMI, loongson_pci_pin_quirk); + +static void loongson_pci_msi_quirk(struct pci_dev *dev) +{ + u16 val, class = dev->class >> 8; + + if (class != PCI_CLASS_BRIDGE_HOST) + return; + + pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &val); + val |= PCI_MSI_FLAGS_ENABLE; + pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, val); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_PCIE_PORT5, loongson_pci_msi_quirk); + +static struct loongson_pci *pci_bus_to_loongson_pci(struct pci_bus *bus) +{ + struct pci_config_window *cfg; + + if (acpi_disabled) + return (struct loongson_pci *)(bus->sysdata); + + cfg = bus->sysdata; + return (struct loongson_pci *)(cfg->priv); +} + +static void __iomem *cfg0_map(struct loongson_pci *priv, struct pci_bus *bus, + unsigned int devfn, int where) +{ + unsigned long addroff = 0x0; + unsigned char busnum = bus->number; + + if (!pci_is_root_bus(bus)) { + addroff |= BIT(24); /* Type 1 Access */ + addroff |= (busnum << 16); + } + addroff |= (devfn << 8) | where; + return priv->cfg0_base + addroff; +} + +static void __iomem *cfg1_map(struct loongson_pci *priv, struct pci_bus *bus, + unsigned int devfn, int where) +{ + unsigned long addroff = 0x0; + unsigned char busnum = bus->number; + + if (!pci_is_root_bus(bus)) { + addroff |= BIT(28); /* Type 1 Access */ + addroff |= (busnum << 16); + } + addroff |= (devfn << 8) | (where & 0xff) | ((where & 0xf00) << 16); + return priv->cfg1_base + addroff; +} + +static bool pdev_may_exist(struct pci_bus *bus, unsigned int device, + unsigned int function) +{ + return !(pci_is_root_bus(bus) && + (device >= 9 && device <= 20) && (function > 0)); +} + +static void __iomem *pci_loongson_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + unsigned int device = PCI_SLOT(devfn); + unsigned int function = PCI_FUNC(devfn); + struct loongson_pci *priv = pci_bus_to_loongson_pci(bus); + + /* + * Do not read more than one device on the bus other than + * the host bus. + */ + if ((priv->data->flags & FLAG_DEV_FIX) && bus->self) { + if (!pci_is_root_bus(bus) && (device > 0)) + return NULL; + } + + /* Don't access non-existent devices */ + if (priv->data->flags & FLAG_DEV_HIDDEN) { + if (!pdev_may_exist(bus, device, function)) + return NULL; + } + + /* CFG0 can only access standard space */ + if (where < PCI_CFG_SPACE_SIZE && priv->cfg0_base) + return cfg0_map(priv, bus, devfn, where); + + /* CFG1 can access extended space */ + if (where < PCI_CFG_SPACE_EXP_SIZE && priv->cfg1_base) + return cfg1_map(priv, bus, devfn, where); + + return NULL; +} + +#ifdef CONFIG_OF + +static int loongson_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + int irq; + u8 val; + + irq = of_irq_parse_and_map_pci(dev, slot, pin); + if (irq > 0) + return irq; + + /* Care i8259 legacy systems */ + pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &val); + /* i8259 only have 15 IRQs */ + if (val > 15) + return 0; + + return val; +} + +/* LS2K/LS7A accept 8/16/32-bit PCI config operations */ +static struct pci_ops loongson_pci_ops = { + .map_bus = pci_loongson_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +/* RS780/SR5690 only accept 32-bit PCI config operations */ +static struct pci_ops loongson_pci_ops32 = { + .map_bus = pci_loongson_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, +}; + +static const struct loongson_pci_data ls2k_pci_data = { + .flags = FLAG_CFG1 | FLAG_DEV_FIX | FLAG_DEV_HIDDEN, + .ops = &loongson_pci_ops, +}; + +static const struct loongson_pci_data ls7a_pci_data = { + .flags = FLAG_CFG1 | FLAG_DEV_FIX | FLAG_DEV_HIDDEN, + .ops = &loongson_pci_ops, +}; + +static const struct loongson_pci_data rs780e_pci_data = { + .flags = FLAG_CFG0, + .ops = &loongson_pci_ops32, +}; + +static const struct of_device_id loongson_pci_of_match[] = { + { .compatible = "loongson,ls2k-pci", + .data = &ls2k_pci_data, }, + { .compatible = "loongson,ls7a-pci", + .data = &ls7a_pci_data, }, + { .compatible = "loongson,rs780e-pci", + .data = &rs780e_pci_data, }, + {} +}; + +static int loongson_pci_probe(struct platform_device *pdev) +{ + struct loongson_pci *priv; + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + struct pci_host_bridge *bridge; + struct resource *regs; + + if (!node) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*priv)); + if (!bridge) + return -ENODEV; + + priv = pci_host_bridge_priv(bridge); + priv->pdev = pdev; + priv->data = of_device_get_match_data(dev); + + if (priv->data->flags & FLAG_CFG0) { + regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!regs) + dev_err(dev, "missing mem resources for cfg0\n"); + else { + priv->cfg0_base = devm_pci_remap_cfg_resource(dev, regs); + if (IS_ERR(priv->cfg0_base)) + return PTR_ERR(priv->cfg0_base); + } + } + + if (priv->data->flags & FLAG_CFG1) { + regs = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!regs) + dev_info(dev, "missing mem resource for cfg1\n"); + else { + priv->cfg1_base = devm_pci_remap_cfg_resource(dev, regs); + if (IS_ERR(priv->cfg1_base)) + priv->cfg1_base = NULL; + } + } + + bridge->sysdata = priv; + bridge->ops = priv->data->ops; + bridge->map_irq = loongson_map_irq; + + return pci_host_probe(bridge); +} + +static struct platform_driver loongson_pci_driver = { + .driver = { + .name = "loongson-pci", + .of_match_table = loongson_pci_of_match, + }, + .probe = loongson_pci_probe, +}; +builtin_platform_driver(loongson_pci_driver); + +#endif + +#ifdef CONFIG_ACPI + +static int loongson_pci_ecam_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct loongson_pci *priv; + struct loongson_pci_data *data; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + cfg->priv = priv; + data->flags = FLAG_CFG1 | FLAG_DEV_HIDDEN; + priv->data = data; + priv->cfg1_base = cfg->win - (cfg->busr.start << 16); + + return 0; +} + +const struct pci_ecam_ops loongson_pci_ecam_ops = { + .bus_shift = 16, + .init = loongson_pci_ecam_init, + .pci_ops = { + .map_bus = pci_loongson_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +#endif diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index fa0fc46edb0c..a72aa57591c0 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -6,18 +6,20 @@ */ #include <linux/kernel.h> +#include <linux/module.h> #include <linux/pci.h> +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/delay.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/init.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> #include <linux/mbus.h> -#include <linux/msi.h> #include <linux/slab.h> #include <linux/platform_device.h> #include <linux/of_address.h> #include <linux/of_irq.h> -#include <linux/of_gpio.h> #include <linux/of_pci.h> #include <linux/of_platform.h> @@ -32,8 +34,9 @@ #define PCIE_DEV_REV_OFF 0x0008 #define PCIE_BAR_LO_OFF(n) (0x0010 + ((n) << 3)) #define PCIE_BAR_HI_OFF(n) (0x0014 + ((n) << 3)) +#define PCIE_SSDEV_ID_OFF 0x002c #define PCIE_CAP_PCIEXP 0x0060 -#define PCIE_HEADER_LOG_4_OFF 0x0128 +#define PCIE_CAP_PCIERR_OFF 0x0100 #define PCIE_BAR_CTRL_OFF(n) (0x1804 + (((n) - 1) * 4)) #define PCIE_WIN04_CTRL_OFF(n) (0x1820 + ((n) << 4)) #define PCIE_WIN04_BASE_OFF(n) (0x1824 + ((n) << 4)) @@ -52,14 +55,25 @@ PCIE_CONF_FUNC(PCI_FUNC(devfn)) | PCIE_CONF_REG(where) | \ PCIE_CONF_ADDR_EN) #define PCIE_CONF_DATA_OFF 0x18fc -#define PCIE_MASK_OFF 0x1910 -#define PCIE_MASK_ENABLE_INTS 0x0f000000 +#define PCIE_INT_CAUSE_OFF 0x1900 +#define PCIE_INT_UNMASK_OFF 0x1910 +#define PCIE_INT_INTX(i) BIT(24+i) +#define PCIE_INT_PM_PME BIT(28) +#define PCIE_INT_ALL_MASK GENMASK(31, 0) #define PCIE_CTRL_OFF 0x1a00 #define PCIE_CTRL_X1_MODE 0x0001 +#define PCIE_CTRL_RC_MODE BIT(1) +#define PCIE_CTRL_MASTER_HOT_RESET BIT(24) #define PCIE_STAT_OFF 0x1a04 #define PCIE_STAT_BUS 0xff00 #define PCIE_STAT_DEV 0x1f0000 #define PCIE_STAT_LINK_DOWN BIT(0) +#define PCIE_SSPL_OFF 0x1a0c +#define PCIE_SSPL_VALUE_SHIFT 0 +#define PCIE_SSPL_VALUE_MASK GENMASK(7, 0) +#define PCIE_SSPL_SCALE_SHIFT 8 +#define PCIE_SSPL_SCALE_MASK GENMASK(9, 8) +#define PCIE_SSPL_ENABLE BIT(16) #define PCIE_RC_RTSTA 0x1a14 #define PCIE_DEBUG_CTRL 0x1a60 #define PCIE_DEBUG_SOFT_RESET BIT(20) @@ -70,12 +84,9 @@ struct mvebu_pcie_port; struct mvebu_pcie { struct platform_device *pdev; struct mvebu_pcie_port *ports; - struct msi_controller *msi; - struct list_head resources; struct resource io; struct resource realio; struct resource mem; - struct resource busn; int nports; }; @@ -91,6 +102,7 @@ struct mvebu_pcie_port { void __iomem *base; u32 port; u32 lane; + bool is_x4; int devfn; unsigned int mem_target; unsigned int mem_attr; @@ -105,6 +117,12 @@ struct mvebu_pcie_port { struct mvebu_pcie_window memwin; struct mvebu_pcie_window iowin; u32 saved_pcie_stat; + struct resource regs; + u8 slot_power_limit_value; + u8 slot_power_limit_scale; + struct irq_domain *intx_irq_domain; + raw_spinlock_t irq_lock; + int intx_irq; }; static inline void mvebu_writel(struct mvebu_pcie_port *port, u32 val, u32 reg) @@ -127,6 +145,11 @@ static bool mvebu_pcie_link_up(struct mvebu_pcie_port *port) return !(mvebu_readl(port, PCIE_STAT_OFF) & PCIE_STAT_LINK_DOWN); } +static u8 mvebu_pcie_get_local_bus_nr(struct mvebu_pcie_port *port) +{ + return (mvebu_readl(port, PCIE_STAT_OFF) & PCIE_STAT_BUS) >> 8; +} + static void mvebu_pcie_set_local_bus_nr(struct mvebu_pcie_port *port, int nr) { u32 stat; @@ -147,20 +170,13 @@ static void mvebu_pcie_set_local_dev_nr(struct mvebu_pcie_port *port, int nr) mvebu_writel(port, stat, PCIE_STAT_OFF); } -/* - * Setup PCIE BARs and Address Decode Wins: - * BAR[0,2] -> disabled, BAR[1] -> covers all DRAM banks - * WIN[0-3] -> DRAM bank[0-3] - */ -static void mvebu_pcie_setup_wins(struct mvebu_pcie_port *port) +static void mvebu_pcie_disable_wins(struct mvebu_pcie_port *port) { - const struct mbus_dram_target_info *dram; - u32 size; int i; - dram = mv_mbus_dram_info(); + mvebu_writel(port, 0, PCIE_BAR_LO_OFF(0)); + mvebu_writel(port, 0, PCIE_BAR_HI_OFF(0)); - /* First, disable and clear BARs and windows. */ for (i = 1; i < 3; i++) { mvebu_writel(port, 0, PCIE_BAR_CTRL_OFF(i)); mvebu_writel(port, 0, PCIE_BAR_LO_OFF(i)); @@ -176,6 +192,25 @@ static void mvebu_pcie_setup_wins(struct mvebu_pcie_port *port) mvebu_writel(port, 0, PCIE_WIN5_CTRL_OFF); mvebu_writel(port, 0, PCIE_WIN5_BASE_OFF); mvebu_writel(port, 0, PCIE_WIN5_REMAP_OFF); +} + +/* + * Setup PCIE BARs and Address Decode Wins: + * BAR[0] -> internal registers (needed for MSI) + * BAR[1] -> covers all DRAM banks + * BAR[2] -> Disabled + * WIN[0-3] -> DRAM bank[0-3] + */ +static void mvebu_pcie_setup_wins(struct mvebu_pcie_port *port) +{ + const struct mbus_dram_target_info *dram; + u32 size; + int i; + + dram = mv_mbus_dram_info(); + + /* First, disable and clear BARs and windows. */ + mvebu_pcie_disable_wins(port); /* Setup windows for DDR banks. Count total DDR size on the fly. */ size = 0; @@ -203,33 +238,128 @@ static void mvebu_pcie_setup_wins(struct mvebu_pcie_port *port) mvebu_writel(port, 0, PCIE_BAR_HI_OFF(1)); mvebu_writel(port, ((size - 1) & 0xffff0000) | 1, PCIE_BAR_CTRL_OFF(1)); + + /* + * Point BAR[0] to the device's internal registers. + */ + mvebu_writel(port, round_down(port->regs.start, SZ_1M), PCIE_BAR_LO_OFF(0)); + mvebu_writel(port, 0, PCIE_BAR_HI_OFF(0)); } static void mvebu_pcie_setup_hw(struct mvebu_pcie_port *port) { - u32 cmd, mask; + u32 ctrl, lnkcap, cmd, dev_rev, unmask, sspl; - /* Point PCIe unit MBUS decode windows to DRAM space. */ - mvebu_pcie_setup_wins(port); + /* Setup PCIe controller to Root Complex mode. */ + ctrl = mvebu_readl(port, PCIE_CTRL_OFF); + ctrl |= PCIE_CTRL_RC_MODE; + mvebu_writel(port, ctrl, PCIE_CTRL_OFF); + + /* + * Set Maximum Link Width to X1 or X4 in Root Port's PCIe Link + * Capability register. This register is defined by PCIe specification + * as read-only but this mvebu controller has it as read-write and must + * be set to number of SerDes PCIe lanes (1 or 4). If this register is + * not set correctly then link with endpoint card is not established. + */ + lnkcap = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP); + lnkcap &= ~PCI_EXP_LNKCAP_MLW; + lnkcap |= FIELD_PREP(PCI_EXP_LNKCAP_MLW, port->is_x4 ? 4 : 1); + mvebu_writel(port, lnkcap, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP); - /* Master + slave enable. */ + /* Disable Root Bridge I/O space, memory space and bus mastering. */ cmd = mvebu_readl(port, PCIE_CMD_OFF); - cmd |= PCI_COMMAND_IO; - cmd |= PCI_COMMAND_MEMORY; - cmd |= PCI_COMMAND_MASTER; + cmd &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); mvebu_writel(port, cmd, PCIE_CMD_OFF); - /* Enable interrupt lines A-D. */ - mask = mvebu_readl(port, PCIE_MASK_OFF); - mask |= PCIE_MASK_ENABLE_INTS; - mvebu_writel(port, mask, PCIE_MASK_OFF); + /* + * Change Class Code of PCI Bridge device to PCI Bridge (0x6004) + * because default value is Memory controller (0x5080). + * + * Note that this mvebu PCI Bridge does not have compliant Type 1 + * Configuration Space. Header Type is reported as Type 0 and it + * has format of Type 0 config space. + * + * Moreover Type 0 BAR registers (ranges 0x10 - 0x28 and 0x30 - 0x34) + * have the same format in Marvell's specification as in PCIe + * specification, but their meaning is totally different and they do + * different things: they are aliased into internal mvebu registers + * (e.g. PCIE_BAR_LO_OFF) and these should not be changed or + * reconfigured by pci device drivers. + * + * Therefore driver uses emulation of PCI Bridge which emulates + * access to configuration space via internal mvebu registers or + * emulated configuration buffer. Driver access these PCI Bridge + * directly for simplification, but these registers can be accessed + * also via standard mvebu way for accessing PCI config space. + */ + dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF); + dev_rev &= ~0xffffff00; + dev_rev |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + mvebu_writel(port, dev_rev, PCIE_DEV_REV_OFF); + + /* Point PCIe unit MBUS decode windows to DRAM space. */ + mvebu_pcie_setup_wins(port); + + /* + * Program Root Port to automatically send Set_Slot_Power_Limit + * PCIe Message when changing status from Dl_Down to Dl_Up and valid + * slot power limit was specified. + */ + sspl = mvebu_readl(port, PCIE_SSPL_OFF); + sspl &= ~(PCIE_SSPL_VALUE_MASK | PCIE_SSPL_SCALE_MASK | PCIE_SSPL_ENABLE); + if (port->slot_power_limit_value) { + sspl |= port->slot_power_limit_value << PCIE_SSPL_VALUE_SHIFT; + sspl |= port->slot_power_limit_scale << PCIE_SSPL_SCALE_SHIFT; + sspl |= PCIE_SSPL_ENABLE; + } + mvebu_writel(port, sspl, PCIE_SSPL_OFF); + + /* Mask all interrupt sources. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF); + + /* Clear all interrupt causes. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF); + + /* Check if "intx" interrupt was specified in DT. */ + if (port->intx_irq > 0) + return; + + /* + * Fallback code when "intx" interrupt was not specified in DT: + * Unmask all legacy INTx interrupts as driver does not provide a way + * for masking and unmasking of individual legacy INTx interrupts. + * Legacy INTx are reported via one shared GIC source and therefore + * kernel cannot distinguish which individual legacy INTx was triggered. + * These interrupts are shared, so it should not cause any issue. Just + * performance penalty as every PCIe interrupt handler needs to be + * called when some interrupt is triggered. + */ + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + unmask |= PCIE_INT_INTX(0) | PCIE_INT_INTX(1) | + PCIE_INT_INTX(2) | PCIE_INT_INTX(3); + mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF); } -static int mvebu_pcie_hw_rd_conf(struct mvebu_pcie_port *port, - struct pci_bus *bus, - u32 devfn, int where, int size, u32 *val) +static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie, + struct pci_bus *bus, + int devfn); + +static int mvebu_pcie_child_rd_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 *val) { - void __iomem *conf_data = port->base + PCIE_CONF_DATA_OFF; + struct mvebu_pcie *pcie = bus->sysdata; + struct mvebu_pcie_port *port; + void __iomem *conf_data; + + port = mvebu_pcie_find_port(pcie, bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (!mvebu_pcie_link_up(port)) + return PCIBIOS_DEVICE_NOT_FOUND; + + conf_data = port->base + PCIE_CONF_DATA_OFF; mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where), PCIE_CONF_ADDR_OFF); @@ -244,16 +374,28 @@ static int mvebu_pcie_hw_rd_conf(struct mvebu_pcie_port *port, case 4: *val = readl_relaxed(conf_data); break; + default: + return PCIBIOS_BAD_REGISTER_NUMBER; } return PCIBIOS_SUCCESSFUL; } -static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port, - struct pci_bus *bus, - u32 devfn, int where, int size, u32 val) +static int mvebu_pcie_child_wr_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 val) { - void __iomem *conf_data = port->base + PCIE_CONF_DATA_OFF; + struct mvebu_pcie *pcie = bus->sysdata; + struct mvebu_pcie_port *port; + void __iomem *conf_data; + + port = mvebu_pcie_find_port(pcie, bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (!mvebu_pcie_link_up(port)) + return PCIBIOS_DEVICE_NOT_FOUND; + + conf_data = port->base + PCIE_CONF_DATA_OFF; mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where), PCIE_CONF_ADDR_OFF); @@ -275,6 +417,11 @@ static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port, return PCIBIOS_SUCCESSFUL; } +static struct pci_ops mvebu_pcie_child_ops = { + .read = mvebu_pcie_child_rd_conf, + .write = mvebu_pcie_child_wr_conf, +}; + /* * Remove windows, starting from the largest ones to the smallest * ones. @@ -297,7 +444,7 @@ static void mvebu_pcie_del_windows(struct mvebu_pcie_port *port, * areas each having a power of two size. We start from the largest * one (i.e highest order bit set in the size). */ -static void mvebu_pcie_add_windows(struct mvebu_pcie_port *port, +static int mvebu_pcie_add_windows(struct mvebu_pcie_port *port, unsigned int target, unsigned int attribute, phys_addr_t base, size_t size, phys_addr_t remap) @@ -318,7 +465,7 @@ static void mvebu_pcie_add_windows(struct mvebu_pcie_port *port, &base, &end, ret); mvebu_pcie_del_windows(port, base - size_mapped, size_mapped); - return; + return ret; } size -= sz; @@ -327,16 +474,20 @@ static void mvebu_pcie_add_windows(struct mvebu_pcie_port *port, if (remap != MVEBU_MBUS_NO_REMAP) remap += sz; } + + return 0; } -static void mvebu_pcie_set_window(struct mvebu_pcie_port *port, +static int mvebu_pcie_set_window(struct mvebu_pcie_port *port, unsigned int target, unsigned int attribute, const struct mvebu_pcie_window *desired, struct mvebu_pcie_window *cur) { + int ret; + if (desired->base == cur->base && desired->remap == cur->remap && desired->size == cur->size) - return; + return 0; if (cur->size != 0) { mvebu_pcie_del_windows(port, cur->base, cur->size); @@ -351,32 +502,30 @@ static void mvebu_pcie_set_window(struct mvebu_pcie_port *port, } if (desired->size == 0) - return; + return 0; + + ret = mvebu_pcie_add_windows(port, target, attribute, desired->base, + desired->size, desired->remap); + if (ret) { + cur->size = 0; + cur->base = 0; + return ret; + } - mvebu_pcie_add_windows(port, target, attribute, desired->base, - desired->size, desired->remap); *cur = *desired; + return 0; } -static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port) +static int mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port) { struct mvebu_pcie_window desired = {}; struct pci_bridge_emul_conf *conf = &port->bridge.conf; /* Are the new iobase/iolimit values invalid? */ if (conf->iolimit < conf->iobase || - conf->iolimitupper < conf->iobaseupper || - !(conf->command & PCI_COMMAND_IO)) { - mvebu_pcie_set_window(port, port->io_target, port->io_attr, - &desired, &port->iowin); - return; - } - - if (!mvebu_has_ioport(port)) { - dev_WARN(&port->pcie->pdev->dev, - "Attempt to set IO when IO is disabled\n"); - return; - } + le16_to_cpu(conf->iolimitupper) < le16_to_cpu(conf->iobaseupper)) + return mvebu_pcie_set_window(port, port->io_target, port->io_attr, + &desired, &port->iowin); /* * We read the PCI-to-PCI bridge emulated registers, and @@ -386,29 +535,26 @@ static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port) * is the CPU address. */ desired.remap = ((conf->iobase & 0xF0) << 8) | - (conf->iobaseupper << 16); + (le16_to_cpu(conf->iobaseupper) << 16); desired.base = port->pcie->io.start + desired.remap; desired.size = ((0xFFF | ((conf->iolimit & 0xF0) << 8) | - (conf->iolimitupper << 16)) - + (le16_to_cpu(conf->iolimitupper) << 16)) - desired.remap) + 1; - mvebu_pcie_set_window(port, port->io_target, port->io_attr, &desired, - &port->iowin); + return mvebu_pcie_set_window(port, port->io_target, port->io_attr, &desired, + &port->iowin); } -static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port) +static int mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port) { struct mvebu_pcie_window desired = {.remap = MVEBU_MBUS_NO_REMAP}; struct pci_bridge_emul_conf *conf = &port->bridge.conf; /* Are the new membase/memlimit values invalid? */ - if (conf->memlimit < conf->membase || - !(conf->command & PCI_COMMAND_MEMORY)) { - mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, - &desired, &port->memwin); - return; - } + if (le16_to_cpu(conf->memlimit) < le16_to_cpu(conf->membase)) + return mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, + &desired, &port->memwin); /* * We read the PCI-to-PCI bridge emulated registers, and @@ -416,12 +562,60 @@ static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port) * window to setup, according to the PCI-to-PCI bridge * specifications. */ - desired.base = ((conf->membase & 0xFFF0) << 16); - desired.size = (((conf->memlimit & 0xFFF0) << 16) | 0xFFFFF) - + desired.base = ((le16_to_cpu(conf->membase) & 0xFFF0) << 16); + desired.size = (((le16_to_cpu(conf->memlimit) & 0xFFF0) << 16) | 0xFFFFF) - desired.base + 1; - mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, &desired, - &port->memwin); + return mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, &desired, + &port->memwin); +} + +static pci_bridge_emul_read_status_t +mvebu_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + case PCI_COMMAND: + *value = mvebu_readl(port, PCIE_CMD_OFF); + break; + + case PCI_PRIMARY_BUS: { + /* + * From the whole 32bit register we support reading from HW only + * secondary bus number which is mvebu local bus number. + * Other bits are retrieved only from emulated config buffer. + */ + __le32 *cfgspace = (__le32 *)&bridge->conf; + u32 val = le32_to_cpu(cfgspace[PCI_PRIMARY_BUS / 4]); + val &= ~0xff00; + val |= mvebu_pcie_get_local_bus_nr(port) << 8; + *value = val; + break; + } + + case PCI_INTERRUPT_LINE: { + /* + * From the whole 32bit register we support reading from HW only + * one bit: PCI_BRIDGE_CTL_BUS_RESET. + * Other bits are retrieved only from emulated config buffer. + */ + __le32 *cfgspace = (__le32 *)&bridge->conf; + u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]); + if (mvebu_readl(port, PCIE_CTRL_OFF) & PCIE_CTRL_MASTER_HOT_RESET) + val |= PCI_BRIDGE_CTL_BUS_RESET << 16; + else + val &= ~(PCI_BRIDGE_CTL_BUS_RESET << 16); + *value = val; + break; + } + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } + + return PCI_BRIDGE_EMUL_HANDLED; } static pci_bridge_emul_read_status_t @@ -436,32 +630,93 @@ mvebu_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, break; case PCI_EXP_DEVCTL: - *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL) & - ~(PCI_EXP_DEVCTL_URRE | PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_CERE); + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL); break; case PCI_EXP_LNKCAP: /* - * PCIe requires the clock power management capability to be - * hard-wired to zero for downstream ports + * PCIe requires that the Clock Power Management capability bit + * is hard-wired to zero for downstream ports but HW returns 1. + * Additionally enable Data Link Layer Link Active Reporting + * Capable bit as DL_Active indication is provided too. */ - *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP) & - ~PCI_EXP_LNKCAP_CLKPM; + *value = (mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP) & + ~PCI_EXP_LNKCAP_CLKPM) | PCI_EXP_LNKCAP_DLLLARC; break; case PCI_EXP_LNKCTL: - *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL); + /* DL_Active indication is provided via PCIE_STAT_OFF */ + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL) | + (mvebu_pcie_link_up(port) ? + (PCI_EXP_LNKSTA_DLLLA << 16) : 0); break; - case PCI_EXP_SLTCTL: - *value = PCI_EXP_SLTSTA_PDS << 16; + case PCI_EXP_SLTCTL: { + u16 slotctl = le16_to_cpu(bridge->pcie_conf.slotctl); + u16 slotsta = le16_to_cpu(bridge->pcie_conf.slotsta); + u32 val = 0; + /* + * When slot power limit was not specified in DT then + * ASPL_DISABLE bit is stored only in emulated config space. + * Otherwise reflect status of PCIE_SSPL_ENABLE bit in HW. + */ + if (!port->slot_power_limit_value) + val |= slotctl & PCI_EXP_SLTCTL_ASPL_DISABLE; + else if (!(mvebu_readl(port, PCIE_SSPL_OFF) & PCIE_SSPL_ENABLE)) + val |= PCI_EXP_SLTCTL_ASPL_DISABLE; + /* This callback is 32-bit and in high bits is slot status. */ + val |= slotsta << 16; + *value = val; break; + } case PCI_EXP_RTSTA: *value = mvebu_readl(port, PCIE_RC_RTSTA); break; + case PCI_EXP_DEVCAP2: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCAP2); + break; + + case PCI_EXP_DEVCTL2: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL2); + break; + + case PCI_EXP_LNKCTL2: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL2); + break; + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } + + return PCI_BRIDGE_EMUL_HANDLED; +} + +static pci_bridge_emul_read_status_t +mvebu_pci_bridge_emul_ext_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + case 0: + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_STATUS: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG+0: + case PCI_ERR_HEADER_LOG+4: + case PCI_ERR_HEADER_LOG+8: + case PCI_ERR_HEADER_LOG+12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_STATUS: + case PCI_ERR_ROOT_ERR_SRC: + *value = mvebu_readl(port, PCIE_CAP_PCIERR_OFF + reg); + break; + default: return PCI_BRIDGE_EMUL_NOT_HANDLED; } @@ -478,39 +733,56 @@ mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge, switch (reg) { case PCI_COMMAND: - { - if (!mvebu_has_ioport(port)) - conf->command &= ~PCI_COMMAND_IO; - - if ((old ^ new) & PCI_COMMAND_IO) - mvebu_pcie_handle_iobase_change(port); - if ((old ^ new) & PCI_COMMAND_MEMORY) - mvebu_pcie_handle_membase_change(port); - + mvebu_writel(port, new, PCIE_CMD_OFF); break; - } case PCI_IO_BASE: - /* - * We keep bit 1 set, it is a read-only bit that - * indicates we support 32 bits addressing for the - * I/O - */ - conf->iobase |= PCI_IO_RANGE_TYPE_32; - conf->iolimit |= PCI_IO_RANGE_TYPE_32; - mvebu_pcie_handle_iobase_change(port); + if ((mask & 0xffff) && mvebu_has_ioport(port) && + mvebu_pcie_handle_iobase_change(port)) { + /* On error disable IO range */ + conf->iobase &= ~0xf0; + conf->iolimit &= ~0xf0; + conf->iobase |= 0xf0; + conf->iobaseupper = cpu_to_le16(0x0000); + conf->iolimitupper = cpu_to_le16(0x0000); + } break; case PCI_MEMORY_BASE: - mvebu_pcie_handle_membase_change(port); + if (mvebu_pcie_handle_membase_change(port)) { + /* On error disable mem range */ + conf->membase = cpu_to_le16(le16_to_cpu(conf->membase) & ~0xfff0); + conf->memlimit = cpu_to_le16(le16_to_cpu(conf->memlimit) & ~0xfff0); + conf->membase = cpu_to_le16(le16_to_cpu(conf->membase) | 0xfff0); + } break; case PCI_IO_BASE_UPPER16: - mvebu_pcie_handle_iobase_change(port); + if (mvebu_has_ioport(port) && + mvebu_pcie_handle_iobase_change(port)) { + /* On error disable IO range */ + conf->iobase &= ~0xf0; + conf->iolimit &= ~0xf0; + conf->iobase |= 0xf0; + conf->iobaseupper = cpu_to_le16(0x0000); + conf->iolimitupper = cpu_to_le16(0x0000); + } break; case PCI_PRIMARY_BUS: - mvebu_pcie_set_local_bus_nr(port, conf->secondary_bus); + if (mask & 0xff00) + mvebu_pcie_set_local_bus_nr(port, conf->secondary_bus); + break; + + case PCI_INTERRUPT_LINE: + if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) { + u32 ctrl = mvebu_readl(port, PCIE_CTRL_OFF); + if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16)) + ctrl |= PCIE_CTRL_MASTER_HOT_RESET; + else + ctrl &= ~PCIE_CTRL_MASTER_HOT_RESET; + mvebu_writel(port, ctrl, PCIE_CTRL_OFF); + } break; default: @@ -526,64 +798,159 @@ mvebu_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, switch (reg) { case PCI_EXP_DEVCTL: - /* - * Armada370 data says these bits must always - * be zero when in root complex mode. - */ - new &= ~(PCI_EXP_DEVCTL_URRE | PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_CERE); - mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL); break; case PCI_EXP_LNKCTL: /* - * If we don't support CLKREQ, we must ensure that the - * CLKREQ enable bit always reads zero. Since we haven't - * had this capability, and it's dependent on board wiring, - * disable it for the time being. + * PCIe requires that the Enable Clock Power Management bit + * is hard-wired to zero for downstream ports but HW allows + * to change it. */ new &= ~PCI_EXP_LNKCTL_CLKREQ_EN; mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL); break; + case PCI_EXP_SLTCTL: + /* + * Allow to change PCIE_SSPL_ENABLE bit only when slot power + * limit was specified in DT and configured into HW. + */ + if ((mask & PCI_EXP_SLTCTL_ASPL_DISABLE) && + port->slot_power_limit_value) { + u32 sspl = mvebu_readl(port, PCIE_SSPL_OFF); + if (new & PCI_EXP_SLTCTL_ASPL_DISABLE) + sspl &= ~PCIE_SSPL_ENABLE; + else + sspl |= PCIE_SSPL_ENABLE; + mvebu_writel(port, sspl, PCIE_SSPL_OFF); + } + break; + case PCI_EXP_RTSTA: - mvebu_writel(port, new, PCIE_RC_RTSTA); + /* + * PME Status bit in Root Status Register (PCIE_RC_RTSTA) + * is read-only and can be cleared only by writing 0b to the + * Interrupt Cause RW0C register (PCIE_INT_CAUSE_OFF). So + * clear PME via Interrupt Cause. + */ + if (new & PCI_EXP_RTSTA_PME) + mvebu_writel(port, ~PCIE_INT_PM_PME, PCIE_INT_CAUSE_OFF); + break; + + case PCI_EXP_DEVCTL2: + mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL2); + break; + + case PCI_EXP_LNKCTL2: + mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL2); + break; + + default: break; } } -struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = { +static void +mvebu_pci_bridge_emul_ext_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + /* These are W1C registers, so clear other bits */ + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_COR_STATUS: + case PCI_ERR_ROOT_STATUS: + new &= mask; + fallthrough; + + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG+0: + case PCI_ERR_HEADER_LOG+4: + case PCI_ERR_HEADER_LOG+8: + case PCI_ERR_HEADER_LOG+12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_ERR_SRC: + mvebu_writel(port, new, PCIE_CAP_PCIERR_OFF + reg); + break; + + default: + break; + } +} + +static const struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = { + .read_base = mvebu_pci_bridge_emul_base_conf_read, .write_base = mvebu_pci_bridge_emul_base_conf_write, .read_pcie = mvebu_pci_bridge_emul_pcie_conf_read, .write_pcie = mvebu_pci_bridge_emul_pcie_conf_write, + .read_ext = mvebu_pci_bridge_emul_ext_conf_read, + .write_ext = mvebu_pci_bridge_emul_ext_conf_write, }; /* * Initialize the configuration space of the PCI-to-PCI bridge * associated with the given PCIe interface. */ -static void mvebu_pci_bridge_emul_init(struct mvebu_pcie_port *port) +static int mvebu_pci_bridge_emul_init(struct mvebu_pcie_port *port) { + unsigned int bridge_flags = PCI_BRIDGE_EMUL_NO_PREFMEM_FORWARD; struct pci_bridge_emul *bridge = &port->bridge; + u32 dev_id = mvebu_readl(port, PCIE_DEV_ID_OFF); + u32 dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF); + u32 ssdev_id = mvebu_readl(port, PCIE_SSDEV_ID_OFF); + u32 pcie_cap = mvebu_readl(port, PCIE_CAP_PCIEXP); + u8 pcie_cap_ver = ((pcie_cap >> 16) & PCI_EXP_FLAGS_VERS); - bridge->conf.vendor = PCI_VENDOR_ID_MARVELL; - bridge->conf.device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16; - bridge->conf.class_revision = - mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff; + bridge->conf.vendor = cpu_to_le16(dev_id & 0xffff); + bridge->conf.device = cpu_to_le16(dev_id >> 16); + bridge->conf.class_revision = cpu_to_le32(dev_rev & 0xff); if (mvebu_has_ioport(port)) { /* We support 32 bits I/O addressing */ bridge->conf.iobase = PCI_IO_RANGE_TYPE_32; bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32; + } else { + bridge_flags |= PCI_BRIDGE_EMUL_NO_IO_FORWARD; } + /* + * Older mvebu hardware provides PCIe Capability structure only in + * version 1. New hardware provides it in version 2. + * Enable slot support which is emulated. + */ + bridge->pcie_conf.cap = cpu_to_le16(pcie_cap_ver | PCI_EXP_FLAGS_SLOT); + + /* + * Set Presence Detect State bit permanently as there is no support for + * unplugging PCIe card from the slot. Assume that PCIe card is always + * connected in slot. + * + * Set physical slot number to port+1 as mvebu ports are indexed from + * zero and zero value is reserved for ports within the same silicon + * as Root Port which is not mvebu case. + * + * Also set correct slot power limit. + */ + bridge->pcie_conf.slotcap = cpu_to_le32( + FIELD_PREP(PCI_EXP_SLTCAP_SPLV, port->slot_power_limit_value) | + FIELD_PREP(PCI_EXP_SLTCAP_SPLS, port->slot_power_limit_scale) | + FIELD_PREP(PCI_EXP_SLTCAP_PSN, port->port+1)); + bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS); + + bridge->subsystem_vendor_id = ssdev_id & 0xffff; + bridge->subsystem_id = ssdev_id >> 16; bridge->has_pcie = true; + bridge->pcie_start = PCIE_CAP_PCIEXP; bridge->data = port; bridge->ops = &mvebu_pci_bridge_emul_ops; - pci_bridge_emul_init(bridge); + return pci_bridge_emul_init(bridge, bridge_flags); } static inline struct mvebu_pcie *sys_to_pcie(struct pci_sys_data *sys) @@ -600,6 +967,9 @@ static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie, for (i = 0; i < pcie->nports; i++) { struct mvebu_pcie_port *port = &pcie->ports[i]; + if (!port->base) + continue; + if (bus->number == 0 && port->devfn == devfn) return port; if (bus->number != 0 && @@ -617,25 +987,12 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn, { struct mvebu_pcie *pcie = bus->sysdata; struct mvebu_pcie_port *port; - int ret; port = mvebu_pcie_find_port(pcie, bus, devfn); if (!port) return PCIBIOS_DEVICE_NOT_FOUND; - /* Access the emulated PCI-to-PCI bridge */ - if (bus->number == 0) - return pci_bridge_emul_conf_write(&port->bridge, where, - size, val); - - if (!mvebu_pcie_link_up(port)) - return PCIBIOS_DEVICE_NOT_FOUND; - - /* Access the real PCIe interface */ - ret = mvebu_pcie_hw_wr_conf(port, bus, devfn, - where, size, val); - - return ret; + return pci_bridge_emul_conf_write(&port->bridge, where, size, val); } /* PCI configuration space read function */ @@ -644,29 +1001,12 @@ static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, { struct mvebu_pcie *pcie = bus->sysdata; struct mvebu_pcie_port *port; - int ret; port = mvebu_pcie_find_port(pcie, bus, devfn); - if (!port) { - *val = 0xffffffff; - return PCIBIOS_DEVICE_NOT_FOUND; - } - - /* Access the emulated PCI-to-PCI bridge */ - if (bus->number == 0) - return pci_bridge_emul_conf_read(&port->bridge, where, - size, val); - - if (!mvebu_pcie_link_up(port)) { - *val = 0xffffffff; + if (!port) return PCIBIOS_DEVICE_NOT_FOUND; - } - - /* Access the real PCIe interface */ - ret = mvebu_pcie_hw_rd_conf(port, bus, devfn, - where, size, val); - return ret; + return pci_bridge_emul_conf_read(&port->bridge, where, size, val); } static struct pci_ops mvebu_pcie_ops = { @@ -674,6 +1014,117 @@ static struct pci_ops mvebu_pcie_ops = { .write = mvebu_pcie_wr_conf, }; +static void mvebu_pcie_intx_irq_mask(struct irq_data *d) +{ + struct mvebu_pcie_port *port = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 unmask; + + raw_spin_lock_irqsave(&port->irq_lock, flags); + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + unmask &= ~PCIE_INT_INTX(hwirq); + mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF); + raw_spin_unlock_irqrestore(&port->irq_lock, flags); +} + +static void mvebu_pcie_intx_irq_unmask(struct irq_data *d) +{ + struct mvebu_pcie_port *port = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 unmask; + + raw_spin_lock_irqsave(&port->irq_lock, flags); + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + unmask |= PCIE_INT_INTX(hwirq); + mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF); + raw_spin_unlock_irqrestore(&port->irq_lock, flags); +} + +static struct irq_chip intx_irq_chip = { + .name = "mvebu-INTx", + .irq_mask = mvebu_pcie_intx_irq_mask, + .irq_unmask = mvebu_pcie_intx_irq_unmask, +}; + +static int mvebu_pcie_intx_irq_map(struct irq_domain *h, + unsigned int virq, irq_hw_number_t hwirq) +{ + struct mvebu_pcie_port *port = h->host_data; + + irq_set_status_flags(virq, IRQ_LEVEL); + irq_set_chip_and_handler(virq, &intx_irq_chip, handle_level_irq); + irq_set_chip_data(virq, port); + + return 0; +} + +static const struct irq_domain_ops mvebu_pcie_intx_irq_domain_ops = { + .map = mvebu_pcie_intx_irq_map, + .xlate = irq_domain_xlate_onecell, +}; + +static int mvebu_pcie_init_irq_domain(struct mvebu_pcie_port *port) +{ + struct device *dev = &port->pcie->pdev->dev; + struct device_node *pcie_intc_node; + + raw_spin_lock_init(&port->irq_lock); + + pcie_intc_node = of_get_next_child(port->dn, NULL); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found for %s\n", port->name); + return -ENODEV; + } + + port->intx_irq_domain = irq_domain_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); + return -ENOMEM; + } + + return 0; +} + +static void mvebu_pcie_irq_handler(struct irq_desc *desc) +{ + struct mvebu_pcie_port *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct device *dev = &port->pcie->pdev->dev; + u32 cause, unmask, status; + int i; + + chained_irq_enter(chip, desc); + + cause = mvebu_readl(port, PCIE_INT_CAUSE_OFF); + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + status = cause & unmask; + + /* Process legacy INTx interrupts */ + for (i = 0; i < PCI_NUM_INTX; i++) { + if (!(status & PCIE_INT_INTX(i))) + continue; + + if (generic_handle_domain_irq(port->intx_irq_domain, i) == -EINVAL) + dev_err_ratelimited(dev, "unexpected INT%c IRQ\n", (char)i+'A'); + } + + chained_irq_exit(chip, desc); +} + +static int mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + /* Interrupt support on mvebu emulated bridges is not implemented yet */ + if (dev->bus->number == 0) + return 0; /* Proper return code 0 == NO_IRQ */ + + return of_irq_parse_and_map_pci(dev, slot, pin); +} + static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev, const struct resource *res, resource_size_t start, @@ -708,58 +1159,36 @@ static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev, struct device_node *np, struct mvebu_pcie_port *port) { - struct resource regs; int ret = 0; - ret = of_address_to_resource(np, 0, ®s); + ret = of_address_to_resource(np, 0, &port->regs); if (ret) - return ERR_PTR(ret); + return (void __iomem *)ERR_PTR(ret); - return devm_ioremap_resource(&pdev->dev, ®s); + 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_each_of_range(&parser, &range) { + u32 slot = upper_32_bits(range.bus_addr); - for (i = 0; i < nranges; i++, range += rangesz) { - u32 flags = of_read_number(range, 1); - u32 slot = of_read_number(range + 1, 1); - u64 cpuaddr = of_read_number(range + na, pna); - unsigned long rtype; - - if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_IO) - rtype = IORESOURCE_IO; - else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32) - rtype = IORESOURCE_MEM; - else - continue; - - if (slot == PCI_SLOT(devfn) && type == rtype) { - *tgt = DT_CPUADDR_TO_TARGET(cpuaddr); - *attr = DT_CPUADDR_TO_ATTR(cpuaddr); + 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; } } @@ -767,7 +1196,6 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, return -ENOENT; } -#ifdef CONFIG_PM_SLEEP static int mvebu_pcie_suspend(struct device *dev) { struct mvebu_pcie *pcie; @@ -776,6 +1204,8 @@ static int mvebu_pcie_suspend(struct device *dev) pcie = dev_get_drvdata(dev); for (i = 0; i < pcie->nports; i++) { struct mvebu_pcie_port *port = pcie->ports + i; + if (!port->base) + continue; port->saved_pcie_stat = mvebu_readl(port, PCIE_STAT_OFF); } @@ -790,13 +1220,14 @@ static int mvebu_pcie_resume(struct device *dev) pcie = dev_get_drvdata(dev); for (i = 0; i < pcie->nports; i++) { struct mvebu_pcie_port *port = pcie->ports + i; + if (!port->base) + continue; mvebu_writel(port, port->saved_pcie_stat, PCIE_STAT_OFF); mvebu_pcie_setup_hw(port); } return 0; } -#endif static void mvebu_pcie_port_clk_put(void *data) { @@ -809,8 +1240,9 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie, struct mvebu_pcie_port *port, struct device_node *child) { struct device *dev = &pcie->pdev->dev; - enum of_gpio_flags flags; - int reset_gpio, ret; + u32 slot_power_limit; + int ret; + u32 num_lanes; port->pcie = pcie; @@ -823,6 +1255,9 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie, if (of_property_read_u32(child, "marvell,pcie-lane", &port->lane)) port->lane = 0; + if (!of_property_read_u32(child, "num-lanes", &num_lanes) && num_lanes == 4) + port->is_x4 = true; + port->name = devm_kasprintf(dev, GFP_KERNEL, "pcie%d.%d", port->port, port->lane); if (!port->name) { @@ -833,6 +1268,11 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie, port->devfn = of_pci_get_devfn(child); if (port->devfn < 0) goto skip; + if (PCI_FUNC(port->devfn) != 0) { + dev_err(dev, "%s: invalid function number, must be zero\n", + port->name); + goto skip; + } ret = mvebu_get_tgt_attr(dev->of_node, port->devfn, IORESOURCE_MEM, &port->mem_target, &port->mem_attr); @@ -850,53 +1290,59 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie, port->io_attr = -1; } - reset_gpio = of_get_named_gpio_flags(child, "reset-gpios", 0, &flags); - if (reset_gpio == -EPROBE_DEFER) { - ret = reset_gpio; + /* + * Old DT bindings do not contain "intx" interrupt + * so do not fail probing driver when interrupt does not exist. + */ + port->intx_irq = of_irq_get_byname(child, "intx"); + if (port->intx_irq == -EPROBE_DEFER) { + ret = port->intx_irq; goto err; } + if (port->intx_irq <= 0) { + dev_warn(dev, "%s: legacy INTx interrupts cannot be masked individually, " + "%pOF does not contain intx interrupt\n", + port->name, child); + } - if (gpio_is_valid(reset_gpio)) { - unsigned long gpio_flags; + port->reset_name = devm_kasprintf(dev, GFP_KERNEL, "%s-reset", + port->name); + if (!port->reset_name) { + ret = -ENOMEM; + goto err; + } - port->reset_name = devm_kasprintf(dev, GFP_KERNEL, "%s-reset", - port->name); - if (!port->reset_name) { - ret = -ENOMEM; + port->reset_gpio = devm_fwnode_gpiod_get(dev, of_fwnode_handle(child), + "reset", GPIOD_OUT_HIGH, + port->name); + ret = PTR_ERR_OR_ZERO(port->reset_gpio); + if (ret) { + if (ret != -ENOENT) goto err; - } - - if (flags & OF_GPIO_ACTIVE_LOW) { - dev_info(dev, "%pOF: reset gpio is active low\n", - child); - gpio_flags = GPIOF_ACTIVE_LOW | - GPIOF_OUT_INIT_LOW; - } else { - gpio_flags = GPIOF_OUT_INIT_HIGH; - } - - ret = devm_gpio_request_one(dev, reset_gpio, gpio_flags, - port->reset_name); - if (ret) { - if (ret == -EPROBE_DEFER) - goto err; - goto skip; - } - - port->reset_gpio = gpio_to_desc(reset_gpio); + /* reset gpio is optional */ + port->reset_gpio = NULL; + devm_kfree(dev, port->reset_name); + port->reset_name = NULL; } + slot_power_limit = of_pci_get_slot_power_limit(child, + &port->slot_power_limit_value, + &port->slot_power_limit_scale); + if (slot_power_limit) + dev_info(dev, "%s: Slot power limit %u.%uW\n", + port->name, + slot_power_limit / 1000, + (slot_power_limit / 100) % 10); + port->clk = of_clk_get_by_name(child, NULL); if (IS_ERR(port->clk)) { dev_err(dev, "%s: cannot get clock\n", port->name); goto skip; } - ret = devm_add_action(dev, mvebu_pcie_port_clk_put, port); - if (ret < 0) { - clk_put(port->clk); + ret = devm_add_action_or_reset(dev, mvebu_pcie_port_clk_put, port); + if (ret < 0) goto err; - } return 1; @@ -953,26 +1399,16 @@ static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port) } /* - * We can't use devm_of_pci_get_host_bridge_resources() because we - * need to parse our special DT properties encoding the MEM and IO - * apertures. + * devm_of_pci_get_host_bridge_resources() only sets up translatable resources, + * so we need extra resource setup parsing our special DT properties encoding + * the MEM and IO apertures. */ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) { struct device *dev = &pcie->pdev->dev; - struct device_node *np = dev->of_node; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); int ret; - INIT_LIST_HEAD(&pcie->resources); - - /* Get the bus range */ - ret = of_pci_parse_bus_range(np, &pcie->busn); - if (ret) { - dev_err(dev, "failed to parse bus-range property: %d\n", ret); - return ret; - } - pci_add_resource(&pcie->resources, &pcie->busn); - /* Get the PCIe memory aperture */ mvebu_mbus_get_pcie_mem_aperture(&pcie->mem); if (resource_size(&pcie->mem) == 0) { @@ -981,7 +1417,10 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) } pcie->mem.name = "PCI MEM"; - pci_add_resource(&pcie->resources, &pcie->mem); + pci_add_resource(&bridge->windows, &pcie->mem); + ret = devm_request_resource(dev, &iomem_resource, &pcie->mem); + if (ret) + return ret; /* Get the PCIe IO aperture */ mvebu_mbus_get_pcie_io_aperture(&pcie->io); @@ -994,57 +1433,16 @@ static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) resource_size(&pcie->io) - 1); pcie->realio.name = "PCI I/O"; - pci_add_resource(&pcie->resources, &pcie->realio); - } - - return devm_request_pci_bus_resources(dev, &pcie->resources); -} - -/* - * This is a copy of pci_host_probe(), except that it does the I/O - * remap as the last step, once we are sure we won't fail. - * - * It should be removed once the I/O remap error handling issue has - * been sorted out. - */ -static int mvebu_pci_host_probe(struct pci_host_bridge *bridge) -{ - struct mvebu_pcie *pcie; - struct pci_bus *bus, *child; - int ret; - - ret = pci_scan_root_bus_bridge(bridge); - if (ret < 0) { - dev_err(bridge->dev.parent, "Scanning root bridge failed"); - return ret; - } - - pcie = pci_host_bridge_priv(bridge); - if (resource_size(&pcie->io) != 0) { - unsigned int i; - - for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K) - pci_ioremap_io(i, pcie->io.start + i); - } - - bus = bridge->bus; - - /* - * We insert PCI resources into the iomem_resource and - * ioport_resource trees in either pci_bus_claim_resources() - * or pci_bus_assign_resources(). - */ - if (pci_has_flag(PCI_PROBE_ONLY)) { - pci_bus_claim_resources(bus); - } else { - pci_bus_size_bridges(bus); - pci_bus_assign_resources(bus); + ret = devm_pci_remap_iospace(dev, &pcie->realio, pcie->io.start); + if (ret) + return ret; - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); + pci_add_resource(&bridge->windows, &pcie->realio); + ret = devm_request_resource(dev, &ioport_resource, &pcie->realio); + if (ret) + return ret; } - pci_bus_add_devices(bus); return 0; } @@ -1094,6 +1492,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev) for (i = 0; i < pcie->nports; i++) { struct mvebu_pcie_port *port = &pcie->ports[i]; + int irq = port->intx_irq; child = port->dn; if (!child) @@ -1111,24 +1510,179 @@ static int mvebu_pcie_probe(struct platform_device *pdev) continue; } + ret = mvebu_pci_bridge_emul_init(port); + if (ret < 0) { + dev_err(dev, "%s: cannot init emulated bridge\n", + port->name); + devm_iounmap(dev, port->base); + port->base = NULL; + mvebu_pcie_powerdown(port); + continue; + } + + if (irq > 0) { + ret = mvebu_pcie_init_irq_domain(port); + if (ret) { + dev_err(dev, "%s: cannot init irq domain\n", + port->name); + pci_bridge_emul_cleanup(&port->bridge); + devm_iounmap(dev, port->base); + port->base = NULL; + mvebu_pcie_powerdown(port); + continue; + } + irq_set_chained_handler_and_data(irq, + mvebu_pcie_irq_handler, + port); + } + + /* + * PCIe topology exported by mvebu hw is quite complicated. In + * reality has something like N fully independent host bridges + * where each host bridge has one PCIe Root Port (which acts as + * PCI Bridge device). Each host bridge has its own independent + * internal registers, independent access to PCI config space, + * independent interrupt lines, independent window and memory + * access configuration. But additionally there is some kind of + * peer-to-peer support between PCIe devices behind different + * host bridges limited just to forwarding of memory and I/O + * transactions (forwarding of error messages and config cycles + * is not supported). So we could say there are N independent + * PCIe Root Complexes. + * + * For this kind of setup DT should have been structured into + * N independent PCIe controllers / host bridges. But instead + * structure in past was defined to put PCIe Root Ports of all + * host bridges into one bus zero, like in classic multi-port + * Root Complex setup with just one host bridge. + * + * This means that pci-mvebu.c driver provides "virtual" bus 0 + * on which registers all PCIe Root Ports (PCI Bridge devices) + * specified in DT by their BDF addresses and virtually routes + * PCI config access of each PCI bridge device to specific PCIe + * host bridge. + * + * Normally PCI Bridge should choose between Type 0 and Type 1 + * config requests based on primary and secondary bus numbers + * configured on the bridge itself. But because mvebu PCI Bridge + * does not have registers for primary and secondary bus numbers + * in its config space, it determinates type of config requests + * via its own custom way. + * + * There are two options how mvebu determinate type of config + * request. + * + * 1. If Secondary Bus Number Enable bit is not set or is not + * available (applies for pre-XP PCIe controllers) then Type 0 + * is used if target bus number equals Local Bus Number (bits + * [15:8] in register 0x1a04) and target device number differs + * from Local Device Number (bits [20:16] in register 0x1a04). + * Type 1 is used if target bus number differs from Local Bus + * Number. And when target bus number equals Local Bus Number + * and target device equals Local Device Number then request is + * routed to Local PCI Bridge (PCIe Root Port). + * + * 2. If Secondary Bus Number Enable bit is set (bit 7 in + * register 0x1a2c) then mvebu hw determinate type of config + * request like compliant PCI Bridge based on primary bus number + * which is configured via Local Bus Number (bits [15:8] in + * register 0x1a04) and secondary bus number which is configured + * via Secondary Bus Number (bits [7:0] in register 0x1a2c). + * Local PCI Bridge (PCIe Root Port) is available on primary bus + * as device with Local Device Number (bits [20:16] in register + * 0x1a04). + * + * Secondary Bus Number Enable bit is disabled by default and + * option 2. is not available on pre-XP PCIe controllers. Hence + * this driver always use option 1. + * + * Basically it means that primary and secondary buses shares + * one virtual number configured via Local Bus Number bits and + * Local Device Number bits determinates if accessing primary + * or secondary bus. Set Local Device Number to 1 and redirect + * all writes of PCI Bridge Secondary Bus Number register to + * Local Bus Number (bits [15:8] in register 0x1a04). + * + * So when accessing devices on buses behind secondary bus + * number it would work correctly. And also when accessing + * device 0 at secondary bus number via config space would be + * correctly routed to secondary bus. Due to issues described + * in mvebu_pcie_setup_hw(), PCI Bridges at primary bus (zero) + * are not accessed directly via PCI config space but rarher + * indirectly via kernel emulated PCI bridge driver. + */ mvebu_pcie_setup_hw(port); mvebu_pcie_set_local_dev_nr(port, 1); - mvebu_pci_bridge_emul_init(port); + mvebu_pcie_set_local_bus_nr(port, 0); } - pcie->nports = i; - - list_splice_init(&pcie->resources, &bridge->windows); - bridge->dev.parent = dev; bridge->sysdata = pcie; - bridge->busnr = 0; bridge->ops = &mvebu_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; + bridge->child_ops = &mvebu_pcie_child_ops; bridge->align_resource = mvebu_pcie_align_resource; - bridge->msi = pcie->msi; + bridge->map_irq = mvebu_pcie_map_irq; - return mvebu_pci_host_probe(bridge); + return pci_host_probe(bridge); +} + +static void mvebu_pcie_remove(struct platform_device *pdev) +{ + struct mvebu_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + u32 cmd, sspl; + int i; + + /* Remove PCI bus with all devices. */ + pci_lock_rescan_remove(); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + pci_unlock_rescan_remove(); + + for (i = 0; i < pcie->nports; i++) { + struct mvebu_pcie_port *port = &pcie->ports[i]; + int irq = port->intx_irq; + + if (!port->base) + continue; + + /* Disable Root Bridge I/O space, memory space and bus mastering. */ + cmd = mvebu_readl(port, PCIE_CMD_OFF); + cmd &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + mvebu_writel(port, cmd, PCIE_CMD_OFF); + + /* Mask all interrupt sources. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF); + + /* Clear all interrupt causes. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF); + + if (irq > 0) + irq_set_chained_handler_and_data(irq, NULL, NULL); + + /* Remove IRQ domains. */ + if (port->intx_irq_domain) + irq_domain_remove(port->intx_irq_domain); + + /* Free config space for emulated root bridge. */ + pci_bridge_emul_cleanup(&port->bridge); + + /* Disable sending Set_Slot_Power_Limit PCIe Message. */ + sspl = mvebu_readl(port, PCIE_SSPL_OFF); + sspl &= ~(PCIE_SSPL_VALUE_MASK | PCIE_SSPL_SCALE_MASK | PCIE_SSPL_ENABLE); + mvebu_writel(port, sspl, PCIE_SSPL_OFF); + + /* Disable and clear BARs and windows. */ + mvebu_pcie_disable_wins(port); + + /* Delete PCIe IO and MEM windows. */ + if (port->iowin.size) + mvebu_pcie_del_windows(port, port->iowin.base, port->iowin.size); + if (port->memwin.size) + mvebu_pcie_del_windows(port, port->memwin.base, port->memwin.size); + + /* Power down card and disable clocks. Must be the last step. */ + mvebu_pcie_powerdown(port); + } } static const struct of_device_id mvebu_pcie_of_match_table[] = { @@ -1138,19 +1692,24 @@ static const struct of_device_id mvebu_pcie_of_match_table[] = { { .compatible = "marvell,kirkwood-pcie", }, {}, }; +MODULE_DEVICE_TABLE(of, mvebu_pcie_of_match_table); static const struct dev_pm_ops mvebu_pcie_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mvebu_pcie_suspend, mvebu_pcie_resume) + NOIRQ_SYSTEM_SLEEP_PM_OPS(mvebu_pcie_suspend, mvebu_pcie_resume) }; static struct platform_driver mvebu_pcie_driver = { .driver = { .name = "mvebu-pcie", .of_match_table = mvebu_pcie_of_match_table, - /* driver unloading/unbinding currently not supported */ - .suppress_bind_attrs = true, .pm = &mvebu_pcie_pm_ops, }, .probe = mvebu_pcie_probe, + .remove = mvebu_pcie_remove, }; -builtin_platform_driver(mvebu_pcie_driver); +module_platform_driver(mvebu_pcie_driver); + +MODULE_AUTHOR("Thomas Petazzoni <thomas.petazzoni@bootlin.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); +MODULE_DESCRIPTION("Marvell EBU PCIe controller"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-rcar-gen2.c b/drivers/pci/controller/pci-rcar-gen2.c index 326171cb1a97..d29866485361 100644 --- a/drivers/pci/controller/pci-rcar-gen2.c +++ b/drivers/pci/controller/pci-rcar-gen2.c @@ -93,27 +93,22 @@ #define RCAR_PCI_UNIT_REV_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x48) -struct rcar_pci_priv { +struct rcar_pci { struct device *dev; void __iomem *reg; struct resource mem_res; struct resource *cfg_res; - unsigned busnr; int irq; - unsigned long window_size; - unsigned long window_addr; - unsigned long window_pci; }; /* PCI configuration space operations */ static void __iomem *rcar_pci_cfg_base(struct pci_bus *bus, unsigned int devfn, int where) { - struct pci_sys_data *sys = bus->sysdata; - struct rcar_pci_priv *priv = sys->private_data; + struct rcar_pci *priv = bus->sysdata; int slot, val; - if (sys->busnr != bus->number || PCI_FUNC(devfn)) + if (!pci_is_root_bus(bus) || PCI_FUNC(devfn)) return NULL; /* Only one EHCI/OHCI device built-in */ @@ -132,26 +127,12 @@ static void __iomem *rcar_pci_cfg_base(struct pci_bus *bus, unsigned int devfn, return priv->reg + (slot >> 1) * 0x100 + where; } -/* PCI interrupt mapping */ -static int rcar_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) -{ - struct pci_sys_data *sys = dev->bus->sysdata; - struct rcar_pci_priv *priv = sys->private_data; - int irq; - - irq = of_irq_parse_and_map_pci(dev, slot, pin); - if (!irq) - irq = priv->irq; - - return irq; -} - #ifdef CONFIG_PCI_DEBUG /* if debug enabled, then attach an error handler irq to the bridge */ static irqreturn_t rcar_pci_err_irq(int irq, void *pw) { - struct rcar_pci_priv *priv = pw; + struct rcar_pci *priv = pw; struct device *dev = priv->dev; u32 status = ioread32(priv->reg + RCAR_PCI_INT_STATUS_REG); @@ -167,7 +148,7 @@ static irqreturn_t rcar_pci_err_irq(int irq, void *pw) return IRQ_NONE; } -static void rcar_pci_setup_errirq(struct rcar_pci_priv *priv) +static void rcar_pci_setup_errirq(struct rcar_pci *priv) { struct device *dev = priv->dev; int ret; @@ -185,23 +166,37 @@ static void rcar_pci_setup_errirq(struct rcar_pci_priv *priv) iowrite32(val, priv->reg + RCAR_PCI_INT_ENABLE_REG); } #else -static inline void rcar_pci_setup_errirq(struct rcar_pci_priv *priv) { } +static inline void rcar_pci_setup_errirq(struct rcar_pci *priv) { } #endif /* PCI host controller setup */ -static int rcar_pci_setup(int nr, struct pci_sys_data *sys) +static void rcar_pci_setup(struct rcar_pci *priv) { - struct rcar_pci_priv *priv = sys->private_data; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(priv); struct device *dev = priv->dev; void __iomem *reg = priv->reg; + struct resource_entry *entry; + unsigned long window_size; + unsigned long window_addr; + unsigned long window_pci; u32 val; - int ret; + + entry = resource_list_first_type(&bridge->dma_ranges, IORESOURCE_MEM); + if (!entry) { + window_addr = 0x40000000; + window_pci = 0x40000000; + window_size = SZ_1G; + } else { + window_addr = entry->res->start; + window_pci = entry->res->start - entry->offset; + window_size = resource_size(entry->res); + } pm_runtime_enable(dev); pm_runtime_get_sync(dev); val = ioread32(reg + RCAR_PCI_UNIT_REV_REG); - dev_info(dev, "PCI: bus%u revision %x\n", sys->busnr, val); + dev_info(dev, "PCI: revision %x\n", val); /* Disable Direct Power Down State and assert reset */ val = ioread32(reg + RCAR_USBCTR_REG) & ~RCAR_USBCTR_DIRPD; @@ -214,7 +209,7 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys) RCAR_USBCTR_USBH_RST | RCAR_USBCTR_PLL_RST); /* Setup PCIAHB window1 size */ - switch (priv->window_size) { + switch (window_size) { case SZ_2G: val |= RCAR_USBCTR_PCIAHB_WIN1_2G; break; @@ -226,9 +221,9 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys) break; default: pr_warn("unknown window size %ld - defaulting to 256M\n", - priv->window_size); - priv->window_size = SZ_256M; - /* fall-through */ + window_size); + window_size = SZ_256M; + fallthrough; case SZ_256M: val |= RCAR_USBCTR_PCIAHB_WIN1_256M; break; @@ -245,7 +240,7 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys) iowrite32(val, reg + RCAR_PCI_ARBITER_CTR_REG); /* PCI-AHB mapping */ - iowrite32(priv->window_addr | RCAR_PCIAHB_PREFETCH16, + iowrite32(window_addr | RCAR_PCIAHB_PREFETCH16, reg + RCAR_PCIAHB_WIN1_CTR_REG); /* AHB-PCI mapping: OHCI/EHCI registers */ @@ -256,7 +251,7 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys) iowrite32(RCAR_AHBPCI_WIN1_HOST | RCAR_AHBPCI_WIN_CTR_CFG, reg + RCAR_AHBPCI_WIN1_CTR_REG); /* Set PCI-AHB Window1 address */ - iowrite32(priv->window_pci | PCI_BASE_ADDRESS_MEM_PREFETCH, + iowrite32(window_pci | PCI_BASE_ADDRESS_MEM_PREFETCH, reg + PCI_BASE_ADDRESS_1); /* Set AHB-PCI bridge PCI communication area address */ val = priv->cfg_res->start + RCAR_AHBPCI_PCICOM_OFFSET; @@ -271,18 +266,7 @@ static int rcar_pci_setup(int nr, struct pci_sys_data *sys) iowrite32(RCAR_PCI_INT_A | RCAR_PCI_INT_B | RCAR_PCI_INT_PME, reg + RCAR_PCI_INT_ENABLE_REG); - if (priv->irq > 0) - rcar_pci_setup_errirq(priv); - - /* Add PCI resources */ - pci_add_resource(&sys->resources, &priv->mem_res); - ret = devm_request_pci_bus_resources(dev, &sys->resources); - if (ret < 0) - return ret; - - /* Setup bus number based on platform device id / of bus-range */ - sys->busnr = priv->busnr; - return 1; + rcar_pci_setup_errirq(priv); } static struct pci_ops rcar_pci_ops = { @@ -291,58 +275,22 @@ static struct pci_ops rcar_pci_ops = { .write = pci_generic_config_write, }; -static int rcar_pci_parse_map_dma_ranges(struct rcar_pci_priv *pci, - struct device_node *np) -{ - struct device *dev = pci->dev; - struct of_pci_range range; - struct of_pci_range_parser parser; - int index = 0; - - /* Failure to parse is ok as we fall back to defaults */ - if (of_pci_dma_range_parser_init(&parser, np)) - return 0; - - /* Get the dma-ranges from DT */ - for_each_of_pci_range(&parser, &range) { - /* Hardware only allows one inbound 32-bit range */ - if (index) - return -EINVAL; - - pci->window_addr = (unsigned long)range.cpu_addr; - pci->window_pci = (unsigned long)range.pci_addr; - pci->window_size = (unsigned long)range.size; - - /* Catch HW limitations */ - if (!(range.flags & IORESOURCE_PREFETCH)) { - dev_err(dev, "window must be prefetchable\n"); - return -EINVAL; - } - if (pci->window_addr) { - u32 lowaddr = 1 << (ffs(pci->window_addr) - 1); - - if (lowaddr < pci->window_size) { - dev_err(dev, "invalid window size/addr\n"); - return -EINVAL; - } - } - index++; - } - - return 0; -} - static int rcar_pci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct resource *cfg_res, *mem_res; - struct rcar_pci_priv *priv; + struct rcar_pci *priv; + struct pci_host_bridge *bridge; void __iomem *reg; - struct hw_pci hw; - void *hw_private[1]; - cfg_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - reg = devm_ioremap_resource(dev, cfg_res); + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*priv)); + if (!bridge) + return -ENOMEM; + + priv = pci_host_bridge_priv(bridge); + bridge->sysdata = priv; + + reg = devm_platform_get_and_ioremap_resource(pdev, 0, &cfg_res); if (IS_ERR(reg)) return PTR_ERR(reg); @@ -353,10 +301,6 @@ static int rcar_pci_probe(struct platform_device *pdev) if (mem_res->start & 0xFFFF) return -EINVAL; - priv = devm_kzalloc(dev, sizeof(struct rcar_pci_priv), GFP_KERNEL); - if (!priv) - return -ENOMEM; - priv->mem_res = *mem_res; priv->cfg_res = cfg_res; @@ -369,44 +313,13 @@ static int rcar_pci_probe(struct platform_device *pdev) return priv->irq; } - /* default window addr and size if not specified in DT */ - priv->window_addr = 0x40000000; - priv->window_pci = 0x40000000; - priv->window_size = SZ_1G; - - if (dev->of_node) { - struct resource busnr; - int ret; - - ret = of_pci_parse_bus_range(dev->of_node, &busnr); - if (ret < 0) { - dev_err(dev, "failed to parse bus-range\n"); - return ret; - } - - priv->busnr = busnr.start; - if (busnr.end != busnr.start) - dev_warn(dev, "only one bus number supported\n"); - - ret = rcar_pci_parse_map_dma_ranges(priv, dev->of_node); - if (ret < 0) { - dev_err(dev, "failed to parse dma-range\n"); - return ret; - } - } else { - priv->busnr = pdev->id; - } + bridge->ops = &rcar_pci_ops; + + pci_add_flags(PCI_REASSIGN_ALL_BUS); + + rcar_pci_setup(priv); - hw_private[0] = priv; - memset(&hw, 0, sizeof(hw)); - hw.nr_controllers = ARRAY_SIZE(hw_private); - hw.io_optional = 1; - hw.private_data = hw_private; - hw.map_irq = rcar_pci_map_irq; - hw.ops = &rcar_pci_ops; - hw.setup = rcar_pci_setup; - pci_common_init_dev(dev, &hw); - return 0; + return pci_host_probe(bridge); } static const struct of_device_id rcar_pci_of_match[] = { @@ -414,6 +327,7 @@ static const struct of_device_id rcar_pci_of_match[] = { { .compatible = "renesas,pci-r8a7791", }, { .compatible = "renesas,pci-r8a7794", }, { .compatible = "renesas,pci-rcar-gen2", }, + { .compatible = "renesas,pci-rzn1", }, { }, }; diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c index f4f53d092e00..942ddfca3bf6 100644 --- a/drivers/pci/controller/pci-tegra.c +++ b/drivers/pci/controller/pci-tegra.c @@ -14,12 +14,16 @@ */ #include <linux/clk.h> +#include <linux/cleanup.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/export.h> +#include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/iopoll.h> #include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/init.h> @@ -30,6 +34,7 @@ #include <linux/of_platform.h> #include <linux/pci.h> #include <linux/phy/phy.h> +#include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> #include <linux/reset.h> #include <linux/sizes.h> @@ -76,26 +81,12 @@ #define AFI_MSI_FPCI_BAR_ST 0x64 #define AFI_MSI_AXI_BAR_ST 0x68 -#define AFI_MSI_VEC0 0x6c -#define AFI_MSI_VEC1 0x70 -#define AFI_MSI_VEC2 0x74 -#define AFI_MSI_VEC3 0x78 -#define AFI_MSI_VEC4 0x7c -#define AFI_MSI_VEC5 0x80 -#define AFI_MSI_VEC6 0x84 -#define AFI_MSI_VEC7 0x88 - -#define AFI_MSI_EN_VEC0 0x8c -#define AFI_MSI_EN_VEC1 0x90 -#define AFI_MSI_EN_VEC2 0x94 -#define AFI_MSI_EN_VEC3 0x98 -#define AFI_MSI_EN_VEC4 0x9c -#define AFI_MSI_EN_VEC5 0xa0 -#define AFI_MSI_EN_VEC6 0xa4 -#define AFI_MSI_EN_VEC7 0xa8 +#define AFI_MSI_VEC(x) (0x6c + ((x) * 4)) +#define AFI_MSI_EN_VEC(x) (0x8c + ((x) * 4)) #define AFI_CONFIGURATION 0xac -#define AFI_CONFIGURATION_EN_FPCI (1 << 0) +#define AFI_CONFIGURATION_EN_FPCI (1 << 0) +#define AFI_CONFIGURATION_CLKEN_OVERRIDE (1 << 31) #define AFI_FPCI_ERROR_MASKS 0xb0 @@ -159,13 +150,14 @@ #define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211 (0x1 << 20) #define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411 (0x2 << 20) #define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111 (0x2 << 20) +#define AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(x) (1 << ((x) + 29)) +#define AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL (0x7 << 29) #define AFI_FUSE 0x104 #define AFI_FUSE_PCIE_T0_GEN2_DIS (1 << 2) #define AFI_PEX0_CTRL 0x110 #define AFI_PEX1_CTRL 0x118 -#define AFI_PEX2_CTRL 0x128 #define AFI_PEX_CTRL_RST (1 << 0) #define AFI_PEX_CTRL_CLKREQ_EN (1 << 1) #define AFI_PEX_CTRL_REFCLK_EN (1 << 3) @@ -177,20 +169,67 @@ #define AFI_PEXBIAS_CTRL_0 0x168 +#define RP_ECTL_2_R1 0x00000e84 +#define RP_ECTL_2_R1_RX_CTLE_1C_MASK 0xffff + +#define RP_ECTL_4_R1 0x00000e8c +#define RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK (0xffff << 16) +#define RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT 16 + +#define RP_ECTL_5_R1 0x00000e90 +#define RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK 0xffffffff + +#define RP_ECTL_6_R1 0x00000e94 +#define RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK 0xffffffff + +#define RP_ECTL_2_R2 0x00000ea4 +#define RP_ECTL_2_R2_RX_CTLE_1C_MASK 0xffff + +#define RP_ECTL_4_R2 0x00000eac +#define RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK (0xffff << 16) +#define RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT 16 + +#define RP_ECTL_5_R2 0x00000eb0 +#define RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK 0xffffffff + +#define RP_ECTL_6_R2 0x00000eb4 +#define RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK 0xffffffff + #define RP_VEND_XP 0x00000f00 -#define RP_VEND_XP_DL_UP (1 << 30) +#define RP_VEND_XP_DL_UP (1 << 30) +#define RP_VEND_XP_OPPORTUNISTIC_ACK (1 << 27) +#define RP_VEND_XP_OPPORTUNISTIC_UPDATEFC (1 << 28) +#define RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK (0xff << 18) + +#define RP_VEND_CTL0 0x00000f44 +#define RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK (0xf << 12) +#define RP_VEND_CTL0_DSK_RST_PULSE_WIDTH (0x9 << 12) + +#define RP_VEND_CTL1 0x00000f48 +#define RP_VEND_CTL1_ERPT (1 << 13) + +#define RP_VEND_XP_BIST 0x00000f4c +#define RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE (1 << 28) #define RP_VEND_CTL2 0x00000fa8 #define RP_VEND_CTL2_PCA_ENABLE (1 << 7) #define RP_PRIV_MISC 0x00000fe0 -#define RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0) -#define RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0) +#define RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0) +#define RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0) +#define RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK (0x7f << 16) +#define RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD (0xf << 16) +#define RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE (1 << 23) +#define RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK (0x7f << 24) +#define RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD (0xf << 24) +#define RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE (1 << 31) #define RP_LINK_CONTROL_STATUS 0x00000090 #define RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE 0x20000000 #define RP_LINK_CONTROL_STATUS_LINKSTAT_MASK 0x3fff0000 +#define RP_LINK_CONTROL_STATUS_2 0x000000b0 + #define PADS_CTL_SEL 0x0000009c #define PADS_CTL 0x000000a0 @@ -226,14 +265,15 @@ #define PADS_REFCLK_CFG_DRVI_SHIFT 12 /* 15:12 */ #define PME_ACK_TIMEOUT 10000 +#define LINK_RETRAIN_TIMEOUT 100000 /* in usec */ struct tegra_msi { - struct msi_controller chip; DECLARE_BITMAP(used, INT_PCI_MSI_NR); struct irq_domain *domain; - unsigned long pages; - struct mutex lock; - u64 phys; + struct mutex map_lock; + raw_spinlock_t mask_lock; + void *virt; + dma_addr_t phys; int irq; }; @@ -249,10 +289,12 @@ struct tegra_pcie_soc { unsigned int num_ports; const struct tegra_pcie_port_soc *ports; unsigned int msi_base_shift; + unsigned long afi_pex2_ctrl; u32 pads_pll_ctl; u32 tx_ref_sel; u32 pads_refclk_cfg0; u32 pads_refclk_cfg1; + u32 update_fc_threshold; bool has_pex_clkreq_en; bool has_pex_bias_ctrl; bool has_intr_prsnt_sense; @@ -260,13 +302,25 @@ struct tegra_pcie_soc { bool has_gen2; bool force_pca_enable; bool program_uphy; + bool update_clamp_threshold; + bool program_deskew_time; + bool update_fc_timer; + bool has_cache_bars; + struct { + struct { + u32 rp_ectl_2_r1; + u32 rp_ectl_4_r1; + u32 rp_ectl_5_r1; + u32 rp_ectl_6_r1; + u32 rp_ectl_2_r2; + u32 rp_ectl_4_r2; + u32 rp_ectl_5_r2; + u32 rp_ectl_6_r2; + } regs; + bool enable; + } ectl; }; -static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip) -{ - return container_of(chip, struct tegra_msi, chip); -} - struct tegra_pcie { struct device *dev; @@ -276,16 +330,6 @@ struct tegra_pcie { int irq; struct resource cs; - struct resource io; - struct resource pio; - struct resource mem; - struct resource prefetch; - struct resource busn; - - struct { - resource_size_t mem; - resource_size_t io; - } offset; struct clk *pex_clk; struct clk *afi_clk; @@ -311,6 +355,11 @@ struct tegra_pcie { struct dentry *debugfs; }; +static inline struct tegra_pcie *msi_to_pcie(struct tegra_msi *msi) +{ + return container_of(msi, struct tegra_pcie, msi); +} + struct tegra_pcie_port { struct tegra_pcie *pcie; struct device_node *np; @@ -321,11 +370,8 @@ struct tegra_pcie_port { unsigned int lanes; struct phy **phys; -}; -struct tegra_pcie_bus { - struct list_head list; - unsigned int nr; + struct gpio_desc *reset_gpio; }; static inline void afi_writel(struct tegra_pcie *pcie, u32 value, @@ -440,6 +486,7 @@ static struct pci_ops tegra_pcie_ops = { static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port) { + const struct tegra_pcie_soc *soc = port->pcie->soc; unsigned long ret = 0; switch (port->index) { @@ -452,7 +499,7 @@ static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port) break; case 2: - ret = AFI_PEX2_CTRL; + ret = soc->afi_pex2_ctrl; break; } @@ -465,15 +512,145 @@ static void tegra_pcie_port_reset(struct tegra_pcie_port *port) unsigned long value; /* pulse reset signal */ - value = afi_readl(port->pcie, ctrl); - value &= ~AFI_PEX_CTRL_RST; - afi_writel(port->pcie, value, ctrl); + if (port->reset_gpio) { + gpiod_set_value(port->reset_gpio, 1); + } else { + value = afi_readl(port->pcie, ctrl); + value &= ~AFI_PEX_CTRL_RST; + afi_writel(port->pcie, value, ctrl); + } usleep_range(1000, 2000); - value = afi_readl(port->pcie, ctrl); - value |= AFI_PEX_CTRL_RST; - afi_writel(port->pcie, value, ctrl); + if (port->reset_gpio) { + gpiod_set_value(port->reset_gpio, 0); + } else { + value = afi_readl(port->pcie, ctrl); + value |= AFI_PEX_CTRL_RST; + afi_writel(port->pcie, value, ctrl); + } +} + +static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port) +{ + const struct tegra_pcie_soc *soc = port->pcie->soc; + u32 value; + + /* Enable AER capability */ + value = readl(port->base + RP_VEND_CTL1); + value |= RP_VEND_CTL1_ERPT; + writel(value, port->base + RP_VEND_CTL1); + + /* Optimal settings to enhance bandwidth */ + value = readl(port->base + RP_VEND_XP); + value |= RP_VEND_XP_OPPORTUNISTIC_ACK; + value |= RP_VEND_XP_OPPORTUNISTIC_UPDATEFC; + writel(value, port->base + RP_VEND_XP); + + /* + * LTSSM will wait for DLLP to finish before entering L1 or L2, + * to avoid truncation of PM messages which results in receiver errors + */ + value = readl(port->base + RP_VEND_XP_BIST); + value |= RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE; + writel(value, port->base + RP_VEND_XP_BIST); + + value = readl(port->base + RP_PRIV_MISC); + value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE; + value |= RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE; + + if (soc->update_clamp_threshold) { + value &= ~(RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK | + RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK); + value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD | + RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD; + } + + writel(value, port->base + RP_PRIV_MISC); +} + +static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port) +{ + const struct tegra_pcie_soc *soc = port->pcie->soc; + u32 value; + + value = readl(port->base + RP_ECTL_2_R1); + value &= ~RP_ECTL_2_R1_RX_CTLE_1C_MASK; + value |= soc->ectl.regs.rp_ectl_2_r1; + writel(value, port->base + RP_ECTL_2_R1); + + value = readl(port->base + RP_ECTL_4_R1); + value &= ~RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK; + value |= soc->ectl.regs.rp_ectl_4_r1 << + RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT; + writel(value, port->base + RP_ECTL_4_R1); + + value = readl(port->base + RP_ECTL_5_R1); + value &= ~RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK; + value |= soc->ectl.regs.rp_ectl_5_r1; + writel(value, port->base + RP_ECTL_5_R1); + + value = readl(port->base + RP_ECTL_6_R1); + value &= ~RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK; + value |= soc->ectl.regs.rp_ectl_6_r1; + writel(value, port->base + RP_ECTL_6_R1); + + value = readl(port->base + RP_ECTL_2_R2); + value &= ~RP_ECTL_2_R2_RX_CTLE_1C_MASK; + value |= soc->ectl.regs.rp_ectl_2_r2; + writel(value, port->base + RP_ECTL_2_R2); + + value = readl(port->base + RP_ECTL_4_R2); + value &= ~RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK; + value |= soc->ectl.regs.rp_ectl_4_r2 << + RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT; + writel(value, port->base + RP_ECTL_4_R2); + + value = readl(port->base + RP_ECTL_5_R2); + value &= ~RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK; + value |= soc->ectl.regs.rp_ectl_5_r2; + writel(value, port->base + RP_ECTL_5_R2); + + value = readl(port->base + RP_ECTL_6_R2); + value &= ~RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK; + value |= soc->ectl.regs.rp_ectl_6_r2; + writel(value, port->base + RP_ECTL_6_R2); +} + +static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port) +{ + const struct tegra_pcie_soc *soc = port->pcie->soc; + u32 value; + + /* + * Sometimes link speed change from Gen2 to Gen1 fails due to + * instability in deskew logic on lane-0. Increase the deskew + * retry time to resolve this issue. + */ + if (soc->program_deskew_time) { + value = readl(port->base + RP_VEND_CTL0); + value &= ~RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK; + value |= RP_VEND_CTL0_DSK_RST_PULSE_WIDTH; + writel(value, port->base + RP_VEND_CTL0); + } + + if (soc->update_fc_timer) { + value = readl(port->base + RP_VEND_XP); + value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK; + value |= soc->update_fc_threshold; + writel(value, port->base + RP_VEND_XP); + } + + /* + * PCIe link doesn't come up with few legacy PCIe endpoints if + * root port advertises both Gen-1 and Gen-2 speeds in Tegra. + * Hence, the strategy followed here is to initially advertise + * only Gen-1 and after link is up, retrain link to Gen-2 speed + */ + value = readl(port->base + RP_LINK_CONTROL_STATUS_2); + value &= ~PCI_EXP_LNKSTA_CLS; + value |= PCI_EXP_LNKSTA_CLS_2_5GB; + writel(value, port->base + RP_LINK_CONTROL_STATUS_2); } static void tegra_pcie_port_enable(struct tegra_pcie_port *port) @@ -500,6 +677,13 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port) value |= RP_VEND_CTL2_PCA_ENABLE; writel(value, port->base + RP_VEND_CTL2); } + + tegra_pcie_enable_rp_features(port); + + if (soc->ectl.enable) + tegra_pcie_program_ectl_settings(port); + + tegra_pcie_apply_sw_fixup(port); } static void tegra_pcie_port_disable(struct tegra_pcie_port *port) @@ -521,6 +705,12 @@ static void tegra_pcie_port_disable(struct tegra_pcie_port *port) value &= ~AFI_PEX_CTRL_REFCLK_EN; afi_writel(port->pcie, value, ctrl); + + /* disable PCIe port and set CLKREQ# as GPIO to allow PLLE power down */ + value = afi_readl(port->pcie, AFI_PCIE_CONFIG); + value |= AFI_PCIE_CONFIG_PCIE_DISABLE(port->index); + value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index); + afi_writel(port->pcie, value, AFI_PCIE_CONFIG); } static void tegra_pcie_port_free(struct tegra_pcie_port *port) @@ -538,51 +728,22 @@ static void tegra_pcie_port_free(struct tegra_pcie_port *port) /* Tegra PCIE root complex wrongly reports device class */ static void tegra_pcie_fixup_class(struct pci_dev *dev) { - dev->class = PCI_CLASS_BRIDGE_PCI << 8; + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_fixup_class); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_fixup_class); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_fixup_class); -/* Tegra PCIE requires relaxed ordering */ +/* Tegra20 and Tegra30 PCIE requires relaxed ordering */ static void tegra_pcie_relax_enable(struct pci_dev *dev) { pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN); } -DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable); - -static int tegra_pcie_request_resources(struct tegra_pcie *pcie) -{ - struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); - struct list_head *windows = &host->windows; - struct device *dev = pcie->dev; - int err; - - pci_add_resource_offset(windows, &pcie->pio, pcie->offset.io); - pci_add_resource_offset(windows, &pcie->mem, pcie->offset.mem); - pci_add_resource_offset(windows, &pcie->prefetch, pcie->offset.mem); - pci_add_resource(windows, &pcie->busn); - - err = devm_request_pci_bus_resources(dev, windows); - if (err < 0) { - pci_free_resource_list(windows); - return err; - } - - pci_remap_iospace(&pcie->pio, pcie->io.start); - - return 0; -} - -static void tegra_pcie_free_resources(struct tegra_pcie *pcie) -{ - struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); - struct list_head *windows = &host->windows; - - pci_unmap_iospace(&pcie->pio); - pci_free_resource_list(windows); -} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_relax_enable); static int tegra_pcie_map_irq(const struct pci_dev *pdev, u8 slot, u8 pin) { @@ -600,7 +761,7 @@ static int tegra_pcie_map_irq(const struct pci_dev *pdev, u8 slot, u8 pin) static irqreturn_t tegra_pcie_isr(int irq, void *arg) { - const char *err_msg[] = { + static const char * const err_msg[] = { "Unknown", "AXI slave error", "AXI decode error", @@ -635,7 +796,7 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg) * do not pollute kernel log with master abort reports since they * happen a lot during enumeration */ - if (code == AFI_INTR_MASTER_ABORT) + if (code == AFI_INTR_MASTER_ABORT || code == AFI_INTR_PE_PRSNT_SENSE) dev_dbg(dev, "%s, signature: %08x\n", err_msg[code], signature); else dev_err(dev, "%s, signature: %08x\n", err_msg[code], signature); @@ -664,36 +825,49 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg) */ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie) { - u32 fpci_bar, size, axi_address; + u32 size; + struct resource_entry *entry; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); /* Bar 0: type 1 extended configuration space */ size = resource_size(&pcie->cs); afi_writel(pcie, pcie->cs.start, AFI_AXI_BAR0_START); afi_writel(pcie, size >> 12, AFI_AXI_BAR0_SZ); - /* Bar 1: downstream IO bar */ - fpci_bar = 0xfdfc0000; - size = resource_size(&pcie->io); - axi_address = pcie->io.start; - afi_writel(pcie, axi_address, AFI_AXI_BAR1_START); - afi_writel(pcie, size >> 12, AFI_AXI_BAR1_SZ); - afi_writel(pcie, fpci_bar, AFI_FPCI_BAR1); - - /* Bar 2: prefetchable memory BAR */ - fpci_bar = (((pcie->prefetch.start >> 12) & 0x0fffffff) << 4) | 0x1; - size = resource_size(&pcie->prefetch); - axi_address = pcie->prefetch.start; - afi_writel(pcie, axi_address, AFI_AXI_BAR2_START); - afi_writel(pcie, size >> 12, AFI_AXI_BAR2_SZ); - afi_writel(pcie, fpci_bar, AFI_FPCI_BAR2); - - /* Bar 3: non prefetchable memory BAR */ - fpci_bar = (((pcie->mem.start >> 12) & 0x0fffffff) << 4) | 0x1; - size = resource_size(&pcie->mem); - axi_address = pcie->mem.start; - afi_writel(pcie, axi_address, AFI_AXI_BAR3_START); - afi_writel(pcie, size >> 12, AFI_AXI_BAR3_SZ); - afi_writel(pcie, fpci_bar, AFI_FPCI_BAR3); + resource_list_for_each_entry(entry, &bridge->windows) { + u32 fpci_bar, axi_address; + struct resource *res = entry->res; + + size = resource_size(res); + + switch (resource_type(res)) { + case IORESOURCE_IO: + /* Bar 1: downstream IO bar */ + fpci_bar = 0xfdfc0000; + axi_address = pci_pio_to_address(res->start); + afi_writel(pcie, axi_address, AFI_AXI_BAR1_START); + afi_writel(pcie, size >> 12, AFI_AXI_BAR1_SZ); + afi_writel(pcie, fpci_bar, AFI_FPCI_BAR1); + break; + case IORESOURCE_MEM: + fpci_bar = (((res->start >> 12) & 0x0fffffff) << 4) | 0x1; + axi_address = res->start; + + if (res->flags & IORESOURCE_PREFETCH) { + /* Bar 2: prefetchable memory BAR */ + afi_writel(pcie, axi_address, AFI_AXI_BAR2_START); + afi_writel(pcie, size >> 12, AFI_AXI_BAR2_SZ); + afi_writel(pcie, fpci_bar, AFI_FPCI_BAR2); + + } else { + /* Bar 3: non prefetchable memory BAR */ + afi_writel(pcie, axi_address, AFI_AXI_BAR3_START); + afi_writel(pcie, size >> 12, AFI_AXI_BAR3_SZ); + afi_writel(pcie, fpci_bar, AFI_FPCI_BAR3); + } + break; + } + } /* NULL out the remaining BARs as they are not used */ afi_writel(pcie, 0, AFI_AXI_BAR4_START); @@ -704,11 +878,13 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie) afi_writel(pcie, 0, AFI_AXI_BAR5_SZ); afi_writel(pcie, 0, AFI_FPCI_BAR5); - /* map all upstream transactions as uncached */ - afi_writel(pcie, 0, AFI_CACHE_BAR0_ST); - afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ); - afi_writel(pcie, 0, AFI_CACHE_BAR1_ST); - afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ); + if (pcie->soc->has_cache_bars) { + /* map all upstream transactions as uncached */ + afi_writel(pcie, 0, AFI_CACHE_BAR0_ST); + afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ); + afi_writel(pcie, 0, AFI_CACHE_BAR1_ST); + afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ); + } /* MSI translations are setup only when needed */ afi_writel(pcie, 0, AFI_MSI_FPCI_BAR_ST); @@ -852,7 +1028,6 @@ static int tegra_pcie_port_phy_power_off(struct tegra_pcie_port *port) static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie) { struct device *dev = pcie->dev; - const struct tegra_pcie_soc *soc = pcie->soc; struct tegra_pcie_port *port; int err; @@ -878,12 +1053,6 @@ static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie) } } - /* Configure the reference clock driver */ - pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0); - - if (soc->num_ports > 2) - pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1); - return 0; } @@ -918,13 +1087,11 @@ static int tegra_pcie_phy_power_off(struct tegra_pcie *pcie) return 0; } -static int tegra_pcie_enable_controller(struct tegra_pcie *pcie) +static void tegra_pcie_enable_controller(struct tegra_pcie *pcie) { - struct device *dev = pcie->dev; const struct tegra_pcie_soc *soc = pcie->soc; struct tegra_pcie_port *port; unsigned long value; - int err; /* enable PLL power down */ if (pcie->phy) { @@ -942,9 +1109,12 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie) value = afi_readl(pcie, AFI_PCIE_CONFIG); value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK; value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config; + value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL; - list_for_each_entry(port, &pcie->ports, list) + list_for_each_entry(port, &pcie->ports, list) { value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index); + value &= ~AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index); + } afi_writel(pcie, value, AFI_PCIE_CONFIG); @@ -958,20 +1128,10 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie) afi_writel(pcie, value, AFI_FUSE); } - if (soc->program_uphy) { - err = tegra_pcie_phy_power_on(pcie); - if (err < 0) { - dev_err(dev, "failed to power on PHY(s): %d\n", err); - return err; - } - } - - /* take the PCIe interface module out of reset */ - reset_control_deassert(pcie->pcie_xrst); - - /* finally enable PCIe */ + /* Disable AFI dynamic clock gating and enable PCIe */ value = afi_readl(pcie, AFI_CONFIGURATION); value |= AFI_CONFIGURATION_EN_FPCI; + value |= AFI_CONFIGURATION_CLKEN_OVERRIDE; afi_writel(pcie, value, AFI_CONFIGURATION); value = AFI_INTR_EN_INI_SLVERR | AFI_INTR_EN_INI_DECERR | @@ -989,22 +1149,6 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie) /* disable all exceptions */ afi_writel(pcie, 0, AFI_FPCI_ERROR_MASKS); - - return 0; -} - -static void tegra_pcie_disable_controller(struct tegra_pcie *pcie) -{ - int err; - - reset_control_assert(pcie->pcie_xrst); - - if (pcie->soc->program_uphy) { - err = tegra_pcie_phy_power_off(pcie); - if (err < 0) - dev_err(pcie->dev, "failed to power off PHY(s): %d\n", - err); - } } static void tegra_pcie_power_off(struct tegra_pcie *pcie) @@ -1014,13 +1158,11 @@ static void tegra_pcie_power_off(struct tegra_pcie *pcie) int err; reset_control_assert(pcie->afi_rst); - reset_control_assert(pcie->pex_rst); clk_disable_unprepare(pcie->pll_e); if (soc->has_cml_clk) clk_disable_unprepare(pcie->cml_clk); clk_disable_unprepare(pcie->afi_clk); - clk_disable_unprepare(pcie->pex_clk); if (!dev->pm_domain) tegra_powergate_power_off(TEGRA_POWERGATE_PCIE); @@ -1048,46 +1190,66 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie) if (err < 0) dev_err(dev, "failed to enable regulators: %d\n", err); - if (dev->pm_domain) { - err = clk_prepare_enable(pcie->pex_clk); + if (!dev->pm_domain) { + err = tegra_powergate_power_on(TEGRA_POWERGATE_PCIE); if (err) { - dev_err(dev, "failed to enable PEX clock: %d\n", err); - return err; + dev_err(dev, "failed to power ungate: %d\n", err); + goto regulator_disable; } - reset_control_deassert(pcie->pex_rst); - } else { - err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE, - pcie->pex_clk, - pcie->pex_rst); + err = tegra_powergate_remove_clamping(TEGRA_POWERGATE_PCIE); if (err) { - dev_err(dev, "powerup sequence failed: %d\n", err); - return err; + dev_err(dev, "failed to remove clamp: %d\n", err); + goto powergate; } } - reset_control_deassert(pcie->afi_rst); - err = clk_prepare_enable(pcie->afi_clk); if (err < 0) { dev_err(dev, "failed to enable AFI clock: %d\n", err); - return err; + goto powergate; } if (soc->has_cml_clk) { err = clk_prepare_enable(pcie->cml_clk); if (err < 0) { dev_err(dev, "failed to enable CML clock: %d\n", err); - return err; + goto disable_afi_clk; } } err = clk_prepare_enable(pcie->pll_e); if (err < 0) { dev_err(dev, "failed to enable PLLE clock: %d\n", err); - return err; + goto disable_cml_clk; } + reset_control_deassert(pcie->afi_rst); + return 0; + +disable_cml_clk: + if (soc->has_cml_clk) + clk_disable_unprepare(pcie->cml_clk); +disable_afi_clk: + clk_disable_unprepare(pcie->afi_clk); +powergate: + if (!dev->pm_domain) + tegra_powergate_power_off(TEGRA_POWERGATE_PCIE); +regulator_disable: + regulator_bulk_disable(pcie->num_supplies, pcie->supplies); + + return err; +} + +static void tegra_pcie_apply_pad_settings(struct tegra_pcie *pcie) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + + /* Configure the reference clock driver */ + pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0); + + if (soc->num_ports > 2) + pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1); } static int tegra_pcie_clocks_get(struct tegra_pcie *pcie) @@ -1170,12 +1332,9 @@ static struct phy *devm_of_phy_optional_get_index(struct device *dev, if (!name) return ERR_PTR(-ENOMEM); - phy = devm_of_phy_get(dev, np, name); + phy = devm_of_phy_optional_get(dev, np, name); kfree(name); - if (IS_ERR(phy) && PTR_ERR(phy) == -ENODEV) - phy = NULL; - return phy; } @@ -1186,7 +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; @@ -1218,7 +1377,7 @@ static int tegra_pcie_phys_get(struct tegra_pcie *pcie) struct tegra_pcie_port *port; int err; - if (!soc->has_gen2 || of_find_property(np, "phys", NULL) != NULL) + if (!soc->has_gen2 || of_property_present(np, "phys")) return tegra_pcie_phys_get_legacy(pcie); list_for_each_entry(port, &pcie->ports, list) { @@ -1253,12 +1412,11 @@ static void tegra_pcie_phys_put(struct tegra_pcie *pcie) } } - static int tegra_pcie_get_resources(struct tegra_pcie *pcie) { struct device *dev = pcie->dev; struct platform_device *pdev = to_platform_device(dev); - struct resource *pads, *afi, *res; + struct resource *res; const struct tegra_pcie_soc *soc = pcie->soc; int err; @@ -1282,15 +1440,13 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie) } } - pads = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pads"); - pcie->pads = devm_ioremap_resource(dev, pads); + pcie->pads = devm_platform_ioremap_resource_byname(pdev, "pads"); if (IS_ERR(pcie->pads)) { err = PTR_ERR(pcie->pads); goto phys_put; } - afi = platform_get_resource_byname(pdev, IORESOURCE_MEM, "afi"); - pcie->afi = devm_ioremap_resource(dev, afi); + pcie->afi = devm_platform_ioremap_resource_byname(pdev, "afi"); if (IS_ERR(pcie->afi)) { err = PTR_ERR(pcie->afi); goto phys_put; @@ -1306,7 +1462,7 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie) pcie->cs = *res; /* constrain configuration space to 4 KiB */ - pcie->cs.end = pcie->cs.start + SZ_4K - 1; + resource_set_size(&pcie->cs, SZ_4K); pcie->cfg = devm_ioremap_resource(dev, &pcie->cs); if (IS_ERR(pcie->cfg)) { @@ -1316,10 +1472,8 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie) /* request interrupt */ err = platform_get_irq_byname(pdev, "intr"); - if (err < 0) { - dev_err(dev, "failed to get IRQ: %d\n", err); + if (err < 0) goto phys_put; - } pcie->irq = err; @@ -1334,6 +1488,7 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie) phys_put: if (soc->program_uphy) tegra_pcie_phys_put(pcie); + return err; } @@ -1376,187 +1531,228 @@ static void tegra_pcie_pme_turnoff(struct tegra_pcie_port *port) afi_writel(pcie, val, AFI_PCIE_PME); } -static int tegra_msi_alloc(struct tegra_msi *chip) +static void tegra_pcie_msi_irq(struct irq_desc *desc) { - int msi; - - mutex_lock(&chip->lock); - - msi = find_first_zero_bit(chip->used, INT_PCI_MSI_NR); - if (msi < INT_PCI_MSI_NR) - set_bit(msi, chip->used); - else - msi = -ENOSPC; - - mutex_unlock(&chip->lock); - - return msi; -} - -static void tegra_msi_free(struct tegra_msi *chip, unsigned long irq) -{ - struct device *dev = chip->chip.dev; - - mutex_lock(&chip->lock); - - if (!test_bit(irq, chip->used)) - dev_err(dev, "trying to free unused MSI#%lu\n", irq); - else - clear_bit(irq, chip->used); - - mutex_unlock(&chip->lock); -} - -static irqreturn_t tegra_pcie_msi_irq(int irq, void *data) -{ - struct tegra_pcie *pcie = data; - struct device *dev = pcie->dev; + struct tegra_pcie *pcie = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); struct tegra_msi *msi = &pcie->msi; - unsigned int i, processed = 0; + struct device *dev = pcie->dev; + unsigned int i; + + chained_irq_enter(chip, desc); for (i = 0; i < 8; i++) { - unsigned long reg = afi_readl(pcie, AFI_MSI_VEC0 + i * 4); + unsigned long reg = afi_readl(pcie, AFI_MSI_VEC(i)); while (reg) { unsigned int offset = find_first_bit(®, 32); unsigned int index = i * 32 + offset; - unsigned int irq; - - /* clear the interrupt */ - afi_writel(pcie, 1 << offset, AFI_MSI_VEC0 + i * 4); + int ret; - irq = irq_find_mapping(msi->domain, index); - if (irq) { - if (test_bit(index, msi->used)) - generic_handle_irq(irq); - else - dev_info(dev, "unhandled MSI\n"); - } else { + ret = generic_handle_domain_irq(msi->domain, index); + if (ret) { /* * that's weird who triggered this? * just clear it */ dev_info(dev, "unexpected MSI\n"); + afi_writel(pcie, BIT(index % 32), AFI_MSI_VEC(index)); } /* see if there's any more pending in this vector */ - reg = afi_readl(pcie, AFI_MSI_VEC0 + i * 4); - - processed++; + reg = afi_readl(pcie, AFI_MSI_VEC(i)); } } - return processed > 0 ? IRQ_HANDLED : IRQ_NONE; + chained_irq_exit(chip, desc); } -static int tegra_msi_setup_irq(struct msi_controller *chip, - struct pci_dev *pdev, struct msi_desc *desc) +static void tegra_msi_irq_ack(struct irq_data *d) { - struct tegra_msi *msi = to_tegra_msi(chip); - struct msi_msg msg; - unsigned int irq; - int hwirq; - - hwirq = tegra_msi_alloc(msi); - if (hwirq < 0) - return hwirq; + 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; - irq = irq_create_mapping(msi->domain, hwirq); - if (!irq) { - tegra_msi_free(msi, hwirq); - return -EINVAL; - } + /* clear the interrupt */ + afi_writel(pcie, BIT(d->hwirq % 32), AFI_MSI_VEC(index)); +} - irq_set_msi_desc(irq, desc); +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; + u32 value; - msg.address_lo = lower_32_bits(msi->phys); - msg.address_hi = upper_32_bits(msi->phys); - msg.data = hwirq; + 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)); + } +} - pci_write_msi_msg(irq, &msg); +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; + u32 value; - return 0; + 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_teardown_irq(struct msi_controller *chip, - unsigned int irq) +static void tegra_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { - struct tegra_msi *msi = to_tegra_msi(chip); - struct irq_data *d = irq_get_irq_data(irq); - irq_hw_number_t hwirq = irqd_to_hwirq(d); + struct tegra_msi *msi = irq_data_get_irq_chip_data(data); - irq_dispose_mapping(irq); - tegra_msi_free(msi, hwirq); + msg->address_lo = lower_32_bits(msi->phys); + msg->address_hi = upper_32_bits(msi->phys); + msg->data = data->hwirq; } -static struct irq_chip tegra_msi_irq_chip = { - .name = "Tegra 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 irq_chip tegra_msi_bottom_chip = { + .name = "Tegra MSI", + .irq_ack = tegra_msi_irq_ack, + .irq_mask = tegra_msi_irq_mask, + .irq_unmask = tegra_msi_irq_unmask, + .irq_compose_msi_msg = tegra_compose_msi_msg, }; -static int tegra_msi_map(struct irq_domain *domain, unsigned int irq, - irq_hw_number_t hwirq) +static int tegra_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) { - irq_set_chip_and_handler(irq, &tegra_msi_irq_chip, handle_simple_irq); - irq_set_chip_data(irq, domain->host_data); + struct tegra_msi *msi = domain->host_data; + unsigned int i; + int hwirq; + + mutex_lock(&msi->map_lock); + + hwirq = bitmap_find_free_region(msi->used, INT_PCI_MSI_NR, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); + + if (hwirq < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &tegra_msi_bottom_chip, domain->host_data, + handle_edge_irq, NULL, NULL); tegra_cpuidle_pcie_irqs_in_use(); return 0; } -static const struct irq_domain_ops msi_domain_ops = { - .map = tegra_msi_map, +static void tegra_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct tegra_msi *msi = domain->host_data; + + mutex_lock(&msi->map_lock); + + bitmap_release_region(msi->used, d->hwirq, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); +} + +static const struct irq_domain_ops tegra_msi_domain_ops = { + .alloc = tegra_msi_domain_alloc, + .free = tegra_msi_domain_free, +}; + +static 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_info info = { + .fwnode = fwnode, + .ops = &tegra_msi_domain_ops, + .size = INT_PCI_MSI_NR, + .host_data = msi, + }; + + 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"); + return -ENOMEM; + } + return 0; +} + +static void tegra_free_domains(struct tegra_msi *msi) +{ + irq_domain_remove(msi->domain); +} + static int tegra_pcie_msi_setup(struct tegra_pcie *pcie) { - struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); struct platform_device *pdev = to_platform_device(pcie->dev); struct tegra_msi *msi = &pcie->msi; struct device *dev = pcie->dev; int err; - mutex_init(&msi->lock); - - msi->chip.dev = dev; - msi->chip.setup_irq = tegra_msi_setup_irq; - msi->chip.teardown_irq = tegra_msi_teardown_irq; + mutex_init(&msi->map_lock); + raw_spin_lock_init(&msi->mask_lock); - msi->domain = irq_domain_add_linear(dev->of_node, INT_PCI_MSI_NR, - &msi_domain_ops, &msi->chip); - if (!msi->domain) { - dev_err(dev, "failed to create IRQ domain\n"); - return -ENOMEM; + if (IS_ENABLED(CONFIG_PCI_MSI)) { + err = tegra_allocate_domains(msi); + if (err) + return err; } err = platform_get_irq_byname(pdev, "msi"); - if (err < 0) { - dev_err(dev, "failed to get IRQ: %d\n", err); - goto err; - } + if (err < 0) + goto free_irq_domain; msi->irq = err; - err = request_irq(msi->irq, tegra_pcie_msi_irq, IRQF_NO_THREAD, - tegra_msi_irq_chip.name, pcie); + irq_set_chained_handler_and_data(msi->irq, tegra_pcie_msi_irq, pcie); + + /* Though the PCIe controller can address >32-bit address space, to + * facilitate endpoints that support only 32-bit MSI target address, + * the mask is set to 32-bit to make sure that MSI target address is + * always a 32-bit address + */ + err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); if (err < 0) { - dev_err(dev, "failed to request IRQ: %d\n", err); - goto err; + dev_err(dev, "failed to set DMA coherent mask: %d\n", err); + goto free_irq; } - /* setup AFI/FPCI range */ - msi->pages = __get_free_pages(GFP_KERNEL, 0); - msi->phys = virt_to_phys((void *)msi->pages); - host->msi = &msi->chip; + msi->virt = dma_alloc_attrs(dev, PAGE_SIZE, &msi->phys, GFP_KERNEL, + DMA_ATTR_NO_KERNEL_MAPPING); + if (!msi->virt) { + dev_err(dev, "failed to allocate DMA memory for MSI\n"); + err = -ENOMEM; + goto free_irq; + } return 0; -err: - irq_domain_remove(msi->domain); +free_irq: + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); +free_irq_domain: + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_free_domains(msi); + return err; } @@ -1564,22 +1760,18 @@ static void tegra_pcie_enable_msi(struct tegra_pcie *pcie) { const struct tegra_pcie_soc *soc = pcie->soc; struct tegra_msi *msi = &pcie->msi; - u32 reg; + u32 reg, msi_state[INT_PCI_MSI_NR / 32]; + int i; afi_writel(pcie, msi->phys >> soc->msi_base_shift, AFI_MSI_FPCI_BAR_ST); afi_writel(pcie, msi->phys, AFI_MSI_AXI_BAR_ST); /* this register is in 4K increments */ afi_writel(pcie, 1, AFI_MSI_BAR_SZ); - /* enable all MSI vectors */ - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC0); - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC1); - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC2); - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC3); - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC4); - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC5); - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC6); - afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC7); + /* Restore the MSI allocation state */ + bitmap_to_arr32(msi_state, msi->used, INT_PCI_MSI_NR); + for (i = 0; i < ARRAY_SIZE(msi_state); i++) + afi_writel(pcie, msi_state[i], AFI_MSI_EN_VEC(i)); /* and unmask the MSI interrupt */ reg = afi_readl(pcie, AFI_INTR_MASK); @@ -1592,18 +1784,19 @@ static void tegra_pcie_msi_teardown(struct tegra_pcie *pcie) struct tegra_msi *msi = &pcie->msi; unsigned int i, irq; - free_pages(msi->pages, 0); - - if (msi->irq > 0) - free_irq(msi->irq, pcie); + dma_free_attrs(pcie->dev, PAGE_SIZE, msi->virt, msi->phys, + DMA_ATTR_NO_KERNEL_MAPPING); for (i = 0; i < INT_PCI_MSI_NR; i++) { irq = irq_find_mapping(msi->domain, i); if (irq > 0) - irq_dispose_mapping(irq); + irq_domain_free_irqs(irq, 1); } - irq_domain_remove(msi->domain); + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_free_domains(msi); } static int tegra_pcie_disable_msi(struct tegra_pcie *pcie) @@ -1615,19 +1808,18 @@ static int tegra_pcie_disable_msi(struct tegra_pcie *pcie) value &= ~AFI_INTR_MASK_MSI_MASK; afi_writel(pcie, value, AFI_INTR_MASK); - /* disable all MSI vectors */ - afi_writel(pcie, 0, AFI_MSI_EN_VEC0); - afi_writel(pcie, 0, AFI_MSI_EN_VEC1); - afi_writel(pcie, 0, AFI_MSI_EN_VEC2); - afi_writel(pcie, 0, AFI_MSI_EN_VEC3); - afi_writel(pcie, 0, AFI_MSI_EN_VEC4); - afi_writel(pcie, 0, AFI_MSI_EN_VEC5); - afi_writel(pcie, 0, AFI_MSI_EN_VEC6); - afi_writel(pcie, 0, AFI_MSI_EN_VEC7); - return 0; } +static void tegra_pcie_disable_interrupts(struct tegra_pcie *pcie) +{ + u32 value; + + value = afi_readl(pcie, AFI_INTR_MASK); + value &= ~AFI_INTR_MASK_INT_MASK; + afi_writel(pcie, value, AFI_INTR_MASK); +} + static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes, u32 *xbar) { @@ -1720,7 +1912,7 @@ static bool of_regulator_bulk_available(struct device_node *np, for (i = 0; i < num_supplies; i++) { snprintf(property, 32, "%s-supply", supplies[i].supply); - if (of_find_property(np, property, NULL) == NULL) + if (!of_property_present(np, property)) return false; } @@ -1793,7 +1985,7 @@ static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask) pcie->supplies[i++].supply = "hvdd-pex"; pcie->supplies[i++].supply = "vddio-pexctl-aud"; } else if (of_device_is_compatible(np, "nvidia,tegra210-pcie")) { - pcie->num_supplies = 6; + pcie->num_supplies = 3; pcie->supplies = devm_kcalloc(pcie->dev, pcie->num_supplies, sizeof(*pcie->supplies), @@ -1801,14 +1993,11 @@ static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask) if (!pcie->supplies) return -ENOMEM; - pcie->supplies[i++].supply = "avdd-pll-uerefe"; pcie->supplies[i++].supply = "hvddio-pex"; pcie->supplies[i++].supply = "dvddio-pex"; - pcie->supplies[i++].supply = "dvdd-pex-pll"; - pcie->supplies[i++].supply = "hvdd-pex-pll-e"; pcie->supplies[i++].supply = "vddio-pex-ctl"; } else if (of_device_is_compatible(np, "nvidia,tegra124-pcie")) { - pcie->num_supplies = 7; + pcie->num_supplies = 4; pcie->supplies = devm_kcalloc(dev, pcie->num_supplies, sizeof(*pcie->supplies), @@ -1818,11 +2007,8 @@ static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask) pcie->supplies[i++].supply = "avddio-pex"; pcie->supplies[i++].supply = "dvddio-pex"; - pcie->supplies[i++].supply = "avdd-pex-pll"; pcie->supplies[i++].supply = "hvdd-pex"; - pcie->supplies[i++].supply = "hvdd-pex-pll-e"; pcie->supplies[i++].supply = "vddio-pex-ctl"; - pcie->supplies[i++].supply = "avdd-pll-erefe"; } else if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) { bool need_pexa = false, need_pexb = false; @@ -1894,110 +2080,39 @@ static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask) static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) { struct device *dev = pcie->dev; - struct device_node *np = dev->of_node, *port; + struct device_node *np = dev->of_node; const struct tegra_pcie_soc *soc = pcie->soc; - struct of_pci_range_parser parser; - struct of_pci_range range; u32 lanes = 0, mask = 0; unsigned int lane = 0; - struct resource res; int err; - if (of_pci_range_parser_init(&parser, np)) { - dev_err(dev, "missing \"ranges\" property\n"); - return -EINVAL; - } - - for_each_of_pci_range(&parser, &range) { - err = of_pci_range_to_resource(&range, np, &res); - if (err < 0) - return err; - - switch (res.flags & IORESOURCE_TYPE_BITS) { - case IORESOURCE_IO: - /* Track the bus -> CPU I/O mapping offset. */ - pcie->offset.io = res.start - range.pci_addr; - - memcpy(&pcie->pio, &res, sizeof(res)); - pcie->pio.name = np->full_name; - - /* - * The Tegra PCIe host bridge uses this to program the - * mapping of the I/O space to the physical address, - * so we override the .start and .end fields here that - * of_pci_range_to_resource() converted to I/O space. - * We also set the IORESOURCE_MEM type to clarify that - * the resource is in the physical memory space. - */ - pcie->io.start = range.cpu_addr; - pcie->io.end = range.cpu_addr + range.size - 1; - pcie->io.flags = IORESOURCE_MEM; - pcie->io.name = "I/O"; - - memcpy(&res, &pcie->io, sizeof(res)); - break; - - case IORESOURCE_MEM: - /* - * Track the bus -> CPU memory mapping offset. This - * assumes that the prefetchable and non-prefetchable - * regions will be the last of type IORESOURCE_MEM in - * the ranges property. - * */ - pcie->offset.mem = res.start - range.pci_addr; - - if (res.flags & IORESOURCE_PREFETCH) { - memcpy(&pcie->prefetch, &res, sizeof(res)); - pcie->prefetch.name = "prefetchable"; - } else { - memcpy(&pcie->mem, &res, sizeof(res)); - pcie->mem.name = "non-prefetchable"; - } - break; - } - } - - err = of_pci_parse_bus_range(np, &pcie->busn); - if (err < 0) { - dev_err(dev, "failed to parse ranges property: %d\n", err); - pcie->busn.name = np->name; - pcie->busn.start = 0; - pcie->busn.end = 0xff; - pcie->busn.flags = IORESOURCE_BUS; - } - /* parse root ports */ - for_each_child_of_node(np, port) { + for_each_child_of_node_scoped(np, port) { struct tegra_pcie_port *rp; unsigned int index; u32 value; + char *label; err = of_pci_get_devfn(port); - if (err < 0) { - dev_err(dev, "failed to parse address: %d\n", err); - return err; - } + if (err < 0) + return dev_err_probe(dev, err, "failed to parse address\n"); index = PCI_SLOT(err); - if (index < 1 || index > soc->num_ports) { - dev_err(dev, "invalid port number: %d\n", index); - return -EINVAL; - } + if (index < 1 || index > soc->num_ports) + return dev_err_probe(dev, -EINVAL, + "invalid port number: %d\n", index); index--; err = of_property_read_u32(port, "nvidia,num-lanes", &value); - if (err < 0) { - dev_err(dev, "failed to parse # of lanes: %d\n", - err); - return err; - } + if (err < 0) + return dev_err_probe(dev, err, + "failed to parse # of lanes\n"); - if (value > 16) { - dev_err(dev, "invalid # of lanes: %u\n", value); - return -EINVAL; - } + if (value > 16) + return dev_err_probe(dev, -EINVAL, + "invalid # of lanes: %u\n", value); lanes |= value << (index << 3); @@ -2014,10 +2129,8 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) return -ENOMEM; err = of_address_to_resource(port, 0, &rp->regs); - if (err < 0) { - dev_err(dev, "failed to parse address: %d\n", err); - return err; - } + if (err < 0) + return dev_err_probe(dev, err, "failed to parse address\n"); INIT_LIST_HEAD(&rp->list); rp->index = index; @@ -2029,14 +2142,35 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) if (IS_ERR(rp->base)) return PTR_ERR(rp->base); + label = devm_kasprintf(dev, GFP_KERNEL, "pex-reset-%u", index); + if (!label) + return -ENOMEM; + + /* + * Returns -ENOENT if reset-gpios property is not populated + * and in this case fall back to using AFI per port register + * to toggle PERST# SFIO line. + */ + rp->reset_gpio = devm_fwnode_gpiod_get(dev, + of_fwnode_handle(port), + "reset", + GPIOD_OUT_LOW, + label); + if (IS_ERR(rp->reset_gpio)) { + if (PTR_ERR(rp->reset_gpio) == -ENOENT) + rp->reset_gpio = NULL; + else + return dev_err_probe(dev, PTR_ERR(rp->reset_gpio), + "failed to get reset GPIO\n"); + } + list_add_tail(&rp->list, &pcie->ports); } err = tegra_pcie_get_xbar_config(pcie, lanes, &pcie->xbar_config); - if (err < 0) { - dev_err(dev, "invalid lane configuration\n"); - return err; - } + if (err < 0) + return dev_err_probe(dev, err, + "invalid lane configuration\n"); err = tegra_pcie_get_regulators(pcie, mask); if (err < 0) @@ -2076,7 +2210,7 @@ static bool tegra_pcie_port_check_link(struct tegra_pcie_port *port) } while (--timeout); if (!timeout) { - dev_err(dev, "link %u down, retrying\n", port->index); + dev_dbg(dev, "link %u down, retrying\n", port->index); goto retry; } @@ -2098,6 +2232,64 @@ retry: return false; } +static void tegra_pcie_change_link_speed(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct tegra_pcie_port *port; + ktime_t deadline; + u32 value; + + list_for_each_entry(port, &pcie->ports, list) { + /* + * "Supported Link Speeds Vector" in "Link Capabilities 2" + * is not supported by Tegra. tegra_pcie_change_link_speed() + * is called only for Tegra chips which support Gen2. + * So there no harm if supported link speed is not verified. + */ + value = readl(port->base + RP_LINK_CONTROL_STATUS_2); + value &= ~PCI_EXP_LNKSTA_CLS; + value |= PCI_EXP_LNKSTA_CLS_5_0GB; + writel(value, port->base + RP_LINK_CONTROL_STATUS_2); + + /* + * Poll until link comes back from recovery to avoid race + * condition. + */ + deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT); + + while (ktime_before(ktime_get(), deadline)) { + value = readl(port->base + RP_LINK_CONTROL_STATUS); + if ((value & PCI_EXP_LNKSTA_LT) == 0) + break; + + usleep_range(2000, 3000); + } + + if (value & PCI_EXP_LNKSTA_LT) + dev_warn(dev, "PCIe port %u link is in recovery\n", + port->index); + + /* Retrain the link */ + value = readl(port->base + RP_LINK_CONTROL_STATUS); + value |= PCI_EXP_LNKCTL_RL; + writel(value, port->base + RP_LINK_CONTROL_STATUS); + + deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT); + + while (ktime_before(ktime_get(), deadline)) { + value = readl(port->base + RP_LINK_CONTROL_STATUS); + if ((value & PCI_EXP_LNKSTA_LT) == 0) + break; + + usleep_range(2000, 3000); + } + + if (value & PCI_EXP_LNKSTA_LT) + dev_err(dev, "failed to retrain link of port %u\n", + port->index); + } +} + static void tegra_pcie_enable_ports(struct tegra_pcie *pcie) { struct device *dev = pcie->dev; @@ -2108,7 +2300,12 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie) port->index, port->lanes); tegra_pcie_port_enable(port); + } + + /* Start LTSSM from Tegra side */ + reset_control_deassert(pcie->pcie_xrst); + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { if (tegra_pcie_port_check_link(port)) continue; @@ -2117,12 +2314,17 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie) tegra_pcie_port_disable(port); tegra_pcie_port_free(port); } + + if (pcie->soc->has_gen2) + tegra_pcie_change_link_speed(pcie); } static void tegra_pcie_disable_ports(struct tegra_pcie *pcie) { struct tegra_pcie_port *port, *tmp; + reset_control_assert(pcie->pcie_xrst); + list_for_each_entry_safe(port, tmp, &pcie->ports, list) tegra_pcie_port_disable(port); } @@ -2146,6 +2348,11 @@ static const struct tegra_pcie_soc tegra20_pcie = { .has_gen2 = false, .force_pca_enable = false, .program_uphy = true, + .update_clamp_threshold = false, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = true, + .ectl.enable = false, }; static const struct tegra_pcie_port_soc tegra30_pcie_ports[] = { @@ -2158,6 +2365,7 @@ static const struct tegra_pcie_soc tegra30_pcie = { .num_ports = 3, .ports = tegra30_pcie_ports, .msi_base_shift = 8, + .afi_pex2_ctrl = 0x128, .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, .pads_refclk_cfg0 = 0xfa5cfa5c, @@ -2169,6 +2377,11 @@ static const struct tegra_pcie_soc tegra30_pcie = { .has_gen2 = false, .force_pca_enable = false, .program_uphy = true, + .update_clamp_threshold = false, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = false, + .ectl.enable = false, }; static const struct tegra_pcie_soc tegra124_pcie = { @@ -2185,6 +2398,11 @@ static const struct tegra_pcie_soc tegra124_pcie = { .has_gen2 = true, .force_pca_enable = false, .program_uphy = true, + .update_clamp_threshold = true, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = false, + .ectl.enable = false, }; static const struct tegra_pcie_soc tegra210_pcie = { @@ -2194,6 +2412,8 @@ static const struct tegra_pcie_soc tegra210_pcie = { .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, .pads_refclk_cfg0 = 0x90b890b8, + /* FC threshold is bit[25:18] */ + .update_fc_threshold = 0x01800000, .has_pex_clkreq_en = true, .has_pex_bias_ctrl = true, .has_intr_prsnt_sense = true, @@ -2201,6 +2421,23 @@ static const struct tegra_pcie_soc tegra210_pcie = { .has_gen2 = true, .force_pca_enable = true, .program_uphy = true, + .update_clamp_threshold = true, + .program_deskew_time = true, + .update_fc_timer = true, + .has_cache_bars = false, + .ectl = { + .regs = { + .rp_ectl_2_r1 = 0x0000000f, + .rp_ectl_4_r1 = 0x00000067, + .rp_ectl_5_r1 = 0x55010000, + .rp_ectl_6_r1 = 0x00000001, + .rp_ectl_2_r2 = 0x0000008f, + .rp_ectl_4_r2 = 0x000000c7, + .rp_ectl_5_r2 = 0x55010000, + .rp_ectl_6_r2 = 0x00000001, + }, + .enable = true, + }, }; static const struct tegra_pcie_port_soc tegra186_pcie_ports[] = { @@ -2213,6 +2450,7 @@ static const struct tegra_pcie_soc tegra186_pcie = { .num_ports = 3, .ports = tegra186_pcie_ports, .msi_base_shift = 8, + .afi_pex2_ctrl = 0x19c, .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, .pads_refclk_cfg0 = 0x80b880b8, @@ -2224,6 +2462,11 @@ static const struct tegra_pcie_soc tegra186_pcie = { .has_gen2 = true, .force_pca_enable = false, .program_uphy = false, + .update_clamp_threshold = false, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = false, + .ectl.enable = false, }; static const struct of_device_id tegra_pcie_of_match[] = { @@ -2234,6 +2477,7 @@ static const struct of_device_id tegra_pcie_of_match[] = { { .compatible = "nvidia,tegra20-pcie", .data = &tegra20_pcie }, { }, }; +MODULE_DEVICE_TABLE(of, tegra_pcie_of_match); static void *tegra_pcie_ports_seq_start(struct seq_file *s, loff_t *pos) { @@ -2242,7 +2486,7 @@ static void *tegra_pcie_ports_seq_start(struct seq_file *s, loff_t *pos) if (list_empty(&pcie->ports)) return NULL; - seq_printf(s, "Index Status\n"); + seq_puts(s, "Index Status\n"); return seq_list_start(&pcie->ports, *pos); } @@ -2279,49 +2523,27 @@ static int tegra_pcie_ports_seq_show(struct seq_file *s, void *v) seq_printf(s, "%2u ", port->index); if (up) - seq_printf(s, "up"); + seq_puts(s, "up"); if (active) { if (up) - seq_printf(s, ", "); + seq_puts(s, ", "); - seq_printf(s, "active"); + seq_puts(s, "active"); } - seq_printf(s, "\n"); + seq_puts(s, "\n"); return 0; } -static const struct seq_operations tegra_pcie_ports_seq_ops = { +static const struct seq_operations tegra_pcie_ports_sops = { .start = tegra_pcie_ports_seq_start, .next = tegra_pcie_ports_seq_next, .stop = tegra_pcie_ports_seq_stop, .show = tegra_pcie_ports_seq_show, }; -static int tegra_pcie_ports_open(struct inode *inode, struct file *file) -{ - struct tegra_pcie *pcie = inode->i_private; - struct seq_file *s; - int err; - - err = seq_open(file, &tegra_pcie_ports_seq_ops); - if (err) - return err; - - s = file->private_data; - s->private = pcie; - - return 0; -} - -static const struct file_operations tegra_pcie_ports_ops = { - .owner = THIS_MODULE, - .open = tegra_pcie_ports_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; +DEFINE_SEQ_ATTRIBUTE(tegra_pcie_ports); static void tegra_pcie_debugfs_exit(struct tegra_pcie *pcie) { @@ -2329,24 +2551,12 @@ static void tegra_pcie_debugfs_exit(struct tegra_pcie *pcie) pcie->debugfs = NULL; } -static int tegra_pcie_debugfs_init(struct tegra_pcie *pcie) +static void tegra_pcie_debugfs_init(struct tegra_pcie *pcie) { - struct dentry *file; - pcie->debugfs = debugfs_create_dir("pcie", NULL); - if (!pcie->debugfs) - return -ENOMEM; - - file = debugfs_create_file("ports", S_IFREG | S_IRUGO, pcie->debugfs, - pcie, &tegra_pcie_ports_ops); - if (!file) - goto remove; - - return 0; -remove: - tegra_pcie_debugfs_exit(pcie); - return -ENOMEM; + debugfs_create_file("ports", S_IFREG | S_IRUGO, pcie->debugfs, pcie, + &tegra_pcie_ports_fops); } static int tegra_pcie_probe(struct platform_device *pdev) @@ -2354,7 +2564,6 @@ static int tegra_pcie_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct pci_host_bridge *host; struct tegra_pcie *pcie; - struct pci_bus *child; int err; host = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); @@ -2387,56 +2596,35 @@ static int tegra_pcie_probe(struct platform_device *pdev) pm_runtime_enable(pcie->dev); err = pm_runtime_get_sync(pcie->dev); - if (err) { + if (err < 0) { dev_err(dev, "fail to enable pcie controller: %d\n", err); - goto teardown_msi; - } - - err = tegra_pcie_request_resources(pcie); - if (err) goto pm_runtime_put; + } - host->busnr = pcie->busn.start; - host->dev.parent = &pdev->dev; host->ops = &tegra_pcie_ops; host->map_irq = tegra_pcie_map_irq; - host->swizzle_irq = pci_common_swizzle; - err = pci_scan_root_bus_bridge(host); + err = pci_host_probe(host); if (err < 0) { dev_err(dev, "failed to register host: %d\n", err); - goto free_resources; + goto pm_runtime_put; } - pci_bus_size_bridges(host->bus); - pci_bus_assign_resources(host->bus); - - list_for_each_entry(child, &host->bus->children, node) - pcie_bus_configure_settings(child); - - pci_bus_add_devices(host->bus); - - if (IS_ENABLED(CONFIG_DEBUG_FS)) { - err = tegra_pcie_debugfs_init(pcie); - if (err < 0) - dev_err(dev, "failed to setup debugfs: %d\n", err); - } + if (IS_ENABLED(CONFIG_DEBUG_FS)) + tegra_pcie_debugfs_init(pcie); return 0; -free_resources: - tegra_pcie_free_resources(pcie); pm_runtime_put: pm_runtime_put_sync(pcie->dev); pm_runtime_disable(pcie->dev); -teardown_msi: tegra_pcie_msi_teardown(pcie); put_resources: tegra_pcie_put_resources(pcie); return err; } -static int tegra_pcie_remove(struct platform_device *pdev) +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); @@ -2447,7 +2635,6 @@ static int tegra_pcie_remove(struct platform_device *pdev) pci_stop_root_bus(host->bus); pci_remove_root_bus(host->bus); - tegra_pcie_free_resources(pcie); pm_runtime_put_sync(pcie->dev); pm_runtime_disable(pcie->dev); @@ -2458,30 +2645,44 @@ static int tegra_pcie_remove(struct platform_device *pdev) list_for_each_entry_safe(port, tmp, &pcie->ports, list) tegra_pcie_port_free(port); - - return 0; } -static int __maybe_unused tegra_pcie_pm_suspend(struct device *dev) +static int tegra_pcie_pm_suspend(struct device *dev) { struct tegra_pcie *pcie = dev_get_drvdata(dev); struct tegra_pcie_port *port; + int err; list_for_each_entry(port, &pcie->ports, list) tegra_pcie_pme_turnoff(port); tegra_pcie_disable_ports(pcie); + /* + * AFI_INTR is unmasked in tegra_pcie_enable_controller(), mask it to + * avoid unwanted interrupts raised by AFI after pex_rst is asserted. + */ + tegra_pcie_disable_interrupts(pcie); + + if (pcie->soc->program_uphy) { + err = tegra_pcie_phy_power_off(pcie); + if (err < 0) + dev_err(dev, "failed to power off PHY(s): %d\n", err); + } + + reset_control_assert(pcie->pex_rst); + clk_disable_unprepare(pcie->pex_clk); + if (IS_ENABLED(CONFIG_PCI_MSI)) tegra_pcie_disable_msi(pcie); - tegra_pcie_disable_controller(pcie); + pinctrl_pm_select_idle_state(dev); tegra_pcie_power_off(pcie); return 0; } -static int __maybe_unused tegra_pcie_pm_resume(struct device *dev) +static int tegra_pcie_pm_resume(struct device *dev) { struct tegra_pcie *pcie = dev_get_drvdata(dev); int err; @@ -2491,20 +2692,45 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev) dev_err(dev, "tegra pcie power on fail: %d\n", err); return err; } - err = tegra_pcie_enable_controller(pcie); - if (err) { - dev_err(dev, "tegra pcie controller enable fail: %d\n", err); + + err = pinctrl_pm_select_default_state(dev); + if (err < 0) { + dev_err(dev, "failed to disable PCIe IO DPD: %d\n", err); goto poweroff; } + + tegra_pcie_enable_controller(pcie); tegra_pcie_setup_translations(pcie); if (IS_ENABLED(CONFIG_PCI_MSI)) tegra_pcie_enable_msi(pcie); + err = clk_prepare_enable(pcie->pex_clk); + if (err) { + dev_err(dev, "failed to enable PEX clock: %d\n", err); + goto pex_dpd_enable; + } + + reset_control_deassert(pcie->pex_rst); + + if (pcie->soc->program_uphy) { + err = tegra_pcie_phy_power_on(pcie); + if (err < 0) { + dev_err(dev, "failed to power on PHY(s): %d\n", err); + goto disable_pex_clk; + } + } + + tegra_pcie_apply_pad_settings(pcie); tegra_pcie_enable_ports(pcie); return 0; +disable_pex_clk: + reset_control_assert(pcie->pex_rst); + clk_disable_unprepare(pcie->pex_clk); +pex_dpd_enable: + pinctrl_pm_select_idle_state(dev); poweroff: tegra_pcie_power_off(pcie); @@ -2512,9 +2738,8 @@ poweroff: } static const struct dev_pm_ops tegra_pcie_pm_ops = { - SET_RUNTIME_PM_OPS(tegra_pcie_pm_suspend, tegra_pcie_pm_resume, NULL) - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(tegra_pcie_pm_suspend, - tegra_pcie_pm_resume) + RUNTIME_PM_OPS(tegra_pcie_pm_suspend, tegra_pcie_pm_resume, NULL) + NOIRQ_SYSTEM_SLEEP_PM_OPS(tegra_pcie_pm_suspend, tegra_pcie_pm_resume) }; static struct platform_driver tegra_pcie_driver = { @@ -2528,4 +2753,3 @@ static struct platform_driver tegra_pcie_driver = { .remove = tegra_pcie_remove, }; module_platform_driver(tegra_pcie_driver); -MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c index 32d1d7b81ef4..b5b4a958e6a2 100644 --- a/drivers/pci/controller/pci-thunder-ecam.c +++ b/drivers/pci/controller/pci-thunder-ecam.c @@ -11,13 +11,15 @@ #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) { int shift = (where & 3) * 8; - pr_debug("set_val %04x: %08x\n", (unsigned)(where & ~3), v); + pr_debug("set_val %04x: %08x\n", (unsigned int)(where & ~3), v); v >>= shift; if (size == 1) v &= 0xff; @@ -41,10 +43,9 @@ static int handle_ea_bar(u32 e0, int bar, struct pci_bus *bus, } if (where_a == 0x4) { addr = bus->ops->map_bus(bus, devfn, bar); /* BAR 0 */ - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } + v = readl(addr); v &= ~0xf; v |= 2; /* EA entry-1. Base-L */ @@ -56,10 +57,9 @@ static int handle_ea_bar(u32 e0, int bar, struct pci_bus *bus, u32 barl_rb; addr = bus->ops->map_bus(bus, devfn, bar); /* BAR 0 */ - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } + barl_orig = readl(addr + 0); writel(0xffffffff, addr + 0); barl_rb = readl(addr + 0); @@ -72,10 +72,9 @@ static int handle_ea_bar(u32 e0, int bar, struct pci_bus *bus, } if (where_a == 0xc) { addr = bus->ops->map_bus(bus, devfn, bar + 4); /* BAR 1 */ - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } + v = readl(addr); /* EA entry-3. Base-H */ set_val(v, where, size, val); return PCIBIOS_SUCCESSFUL; @@ -104,10 +103,8 @@ static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn, } addr = bus->ops->map_bus(bus, devfn, where_a); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } v = readl(addr); @@ -116,7 +113,7 @@ static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn, * the config space access window. Since we are working with * the high-order 32 bits, shift everything down by 32 bits. */ - node_bits = (cfg->res.start >> 32) & (1 << 12); + node_bits = upper_32_bits(cfg->res.start) & (1 << 12); v |= node_bits; set_val(v, where, size, val); @@ -135,10 +132,8 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, int where_a = where & ~3; addr = bus->ops->map_bus(bus, devfn, 0xc); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } v = readl(addr); @@ -146,10 +141,8 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, cfg_type = (v >> 16) & 0x7f; addr = bus->ops->map_bus(bus, devfn, 8); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } class_rev = readl(addr); if (class_rev == 0xffffffff) @@ -176,10 +169,8 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, } addr = bus->ops->map_bus(bus, devfn, 0); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } vendor_device = readl(addr); if (vendor_device == 0xffffffff) @@ -187,7 +178,7 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, pr_debug("%04x:%04x - Fix pass#: %08x, where: %03x, devfn: %03x\n", vendor_device & 0xffff, vendor_device >> 16, class_rev, - (unsigned) where, devfn); + (unsigned int)where, devfn); /* Check for non type-00 header */ if (cfg_type == 0) { @@ -196,10 +187,9 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, bool is_tns = (vendor_device == 0xa01f177d); addr = bus->ops->map_bus(bus, devfn, 0x70); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } + /* E_CAP */ v = readl(addr); has_msix = (v & 0xff00) != 0; @@ -211,13 +201,12 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, } if (where_a == 0xb0) { addr = bus->ops->map_bus(bus, devfn, where_a); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } + v = readl(addr); if (v & 0xff00) - pr_err("Bad MSIX cap header: %08x\n", v); + pr_err("Bad MSI-X cap header: %08x\n", v); v |= 0xbc00; /* next capability is EA at 0xbc */ set_val(v, where, size, val); return PCIBIOS_SUCCESSFUL; @@ -268,10 +257,9 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, if (where_a == 0x70) { addr = bus->ops->map_bus(bus, devfn, where_a); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } + v = readl(addr); if (v & 0xff00) pr_err("Bad PCIe cap header: %08x\n", v); @@ -345,8 +333,7 @@ static int thunder_ecam_config_write(struct pci_bus *bus, unsigned int devfn, return pci_generic_config_write(bus, devfn, where, size, val); } -struct pci_ecam_ops pci_thunder_ecam_ops = { - .bus_shift = 20, +const struct pci_ecam_ops pci_thunder_ecam_ops = { .pci_ops = { .map_bus = pci_ecam_map_bus, .read = thunder_ecam_config_read, @@ -357,22 +344,20 @@ struct pci_ecam_ops pci_thunder_ecam_ops = { #ifdef CONFIG_PCI_HOST_THUNDER_ECAM static const struct of_device_id thunder_ecam_of_match[] = { - { .compatible = "cavium,pci-host-thunder-ecam" }, + { + .compatible = "cavium,pci-host-thunder-ecam", + .data = &pci_thunder_ecam_ops, + }, { }, }; -static int thunder_ecam_probe(struct platform_device *pdev) -{ - return pci_host_common_probe(pdev, &pci_thunder_ecam_ops); -} - static struct platform_driver thunder_ecam_driver = { .driver = { .name = KBUILD_MODNAME, .of_match_table = thunder_ecam_of_match, .suppress_bind_attrs = true, }, - .probe = thunder_ecam_probe, + .probe = pci_host_common_probe, }; builtin_platform_driver(thunder_ecam_driver); diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c index f127ce8bd4ef..5fa037fb61dc 100644 --- a/drivers/pci/controller/pci-thunder-pem.c +++ b/drivers/pci/controller/pci-thunder-pem.c @@ -6,18 +6,30 @@ #include <linux/bitfield.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/pci.h> #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/pci-acpi.h> #include <linux/pci-ecam.h> #include <linux/platform_device.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include "../pci.h" +#include "pci-host-common.h" #if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) #define PEM_CFG_WR 0x28 #define PEM_CFG_RD 0x30 +/* + * Enhanced Configuration Access Mechanism (ECAM) + * + * N.B. This is a non-standard platform-specific ECAM bus shift value. For + * standard values defined in the PCI Express Base Specification see + * include/linux/pci-ecam.h. + */ +#define THUNDER_PCIE_ECAM_BUS_SHIFT 24 + struct thunder_pem_pci { u32 ea_entry[3]; void __iomem *pem_reg_base; @@ -30,10 +42,8 @@ static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn, struct pci_config_window *cfg = bus->sysdata; struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv; - if (devfn != 0 || where >= 2048) { - *val = ~0; + if (devfn != 0 || where >= 2048) return PCIBIOS_DEVICE_NOT_FOUND; - } /* * 32-bit accesses only. Write the address to the low order @@ -314,9 +324,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg, * structure here for the BAR. */ bar4_start = res_pem->start + 0xf00000; - pem_pci->ea_entry[0] = (u32)bar4_start | 2; - pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u; - pem_pci->ea_entry[2] = (u32)(bar4_start >> 32); + pem_pci->ea_entry[0] = lower_32_bits(bar4_start) | 2; + pem_pci->ea_entry[1] = lower_32_bits(res_pem->end - bar4_start) & ~3u; + pem_pci->ea_entry[2] = upper_32_bits(bar4_start); cfg->priv = pem_pci; return 0; @@ -324,9 +334,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg, #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) -#define PEM_RES_BASE 0x87e0c0000000UL -#define PEM_NODE_MASK GENMASK(45, 44) -#define PEM_INDX_MASK GENMASK(26, 24) +#define PEM_RES_BASE 0x87e0c0000000ULL +#define PEM_NODE_MASK GENMASK_ULL(45, 44) +#define PEM_INDX_MASK GENMASK_ULL(26, 24) #define PEM_MIN_DOM_IN_NODE 4 #define PEM_MAX_DOM_IN_NODE 10 @@ -391,9 +401,9 @@ static int thunder_pem_acpi_init(struct pci_config_window *cfg) * Reserve 64K size PEM specific resources. The full 16M range * size is required for thunder_pem_init() call. */ - res_pem->end = res_pem->start + SZ_64K - 1; + resource_set_size(res_pem, SZ_64K); thunder_pem_reserve_range(dev, root->segment, res_pem); - res_pem->end = res_pem->start + SZ_16M - 1; + resource_set_size(res_pem, SZ_16M); /* Reserve PCI configuration space as well. */ thunder_pem_reserve_range(dev, root->segment, &cfg->res); @@ -402,8 +412,8 @@ static int thunder_pem_acpi_init(struct pci_config_window *cfg) return thunder_pem_init(dev, cfg, res_pem); } -struct pci_ecam_ops thunder_pem_ecam_ops = { - .bus_shift = 24, +const struct pci_ecam_ops thunder_pem_ecam_ops = { + .bus_shift = THUNDER_PCIE_ECAM_BUS_SHIFT, .init = thunder_pem_acpi_init, .pci_ops = { .map_bus = pci_ecam_map_bus, @@ -439,8 +449,8 @@ static int thunder_pem_platform_init(struct pci_config_window *cfg) return thunder_pem_init(dev, cfg, res_pem); } -static struct pci_ecam_ops pci_thunder_pem_ops = { - .bus_shift = 24, +static const struct pci_ecam_ops pci_thunder_pem_ops = { + .bus_shift = THUNDER_PCIE_ECAM_BUS_SHIFT, .init = thunder_pem_platform_init, .pci_ops = { .map_bus = pci_ecam_map_bus, @@ -450,22 +460,20 @@ static struct pci_ecam_ops pci_thunder_pem_ops = { }; static const struct of_device_id thunder_pem_of_match[] = { - { .compatible = "cavium,pci-host-thunder-pem" }, + { + .compatible = "cavium,pci-host-thunder-pem", + .data = &pci_thunder_pem_ops, + }, { }, }; -static int thunder_pem_probe(struct platform_device *pdev) -{ - return pci_host_common_probe(pdev, &pci_thunder_pem_ops); -} - static struct platform_driver thunder_pem_driver = { .driver = { .name = KBUILD_MODNAME, .of_match_table = thunder_pem_of_match, .suppress_bind_attrs = true, }, - .probe = thunder_pem_probe, + .probe = pci_host_common_probe, }; builtin_platform_driver(thunder_pem_driver); diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c index d219404bad92..460a825325dd 100644 --- a/drivers/pci/controller/pci-v3-semi.c +++ b/drivers/pci/controller/pci-v3-semi.c @@ -20,9 +20,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/kernel.h> -#include <linux/of_address.h> -#include <linux/of_device.h> -#include <linux/of_irq.h> +#include <linux/of.h> #include <linux/of_pci.h> #include <linux/pci.h> #include <linux/platform_device.h> @@ -239,12 +237,9 @@ struct v3_pci { struct device *dev; void __iomem *base; void __iomem *config_base; - struct pci_bus *bus; u32 config_mem; - u32 io_mem; u32 non_pre_mem; u32 pre_mem; - phys_addr_t io_bus_addr; phys_addr_t non_pre_bus_addr; phys_addr_t pre_bus_addr; struct regmap *map; @@ -520,35 +515,22 @@ static int v3_integrator_init(struct v3_pci *v3) } static int v3_pci_setup_resource(struct v3_pci *v3, - resource_size_t io_base, struct pci_host_bridge *host, struct resource_entry *win) { struct device *dev = v3->dev; struct resource *mem; struct resource *io; - int ret; switch (resource_type(win->res)) { case IORESOURCE_IO: io = win->res; - io->name = "V3 PCI I/O"; - v3->io_mem = io_base; - v3->io_bus_addr = io->start - win->offset; - dev_dbg(dev, "I/O window %pR, bus addr %pap\n", - io, &v3->io_bus_addr); - ret = devm_pci_remap_iospace(dev, io, io_base); - if (ret) { - dev_warn(dev, - "error %d: failed to map resource %pR\n", - ret, io); - return ret; - } + /* Setup window 2 - PCI I/O */ - writel(v3_addr_to_lb_base2(v3->io_mem) | + writel(v3_addr_to_lb_base2(pci_pio_to_address(io->start)) | V3_LB_BASE2_ENABLE, v3->base + V3_LB_BASE2); - writew(v3_addr_to_lb_map2(v3->io_bus_addr), + writew(v3_addr_to_lb_map2(io->start - win->offset), v3->base + V3_LB_MAP2); break; case IORESOURCE_MEM: @@ -600,8 +582,6 @@ static int v3_pci_setup_resource(struct v3_pci *v3, } break; case IORESOURCE_BUS: - dev_dbg(dev, "BUS %pR\n", win->res); - host->busnr = win->res->start; break; default: dev_info(dev, "Unknown resource type %lu\n", @@ -613,28 +593,30 @@ static int v3_pci_setup_resource(struct v3_pci *v3, } static int v3_get_dma_range_config(struct v3_pci *v3, - struct of_pci_range *range, + struct resource_entry *entry, u32 *pci_base, u32 *pci_map) { struct device *dev = v3->dev; - u64 cpu_end = range->cpu_addr + range->size - 1; - u64 pci_end = range->pci_addr + range->size - 1; + u64 cpu_addr = entry->res->start; + u64 cpu_end = entry->res->end; + u64 pci_end = cpu_end - entry->offset; + u64 pci_addr = entry->res->start - entry->offset; u32 val; - if (range->pci_addr & ~V3_PCI_BASE_M_ADR_BASE) { + if (pci_addr & ~V3_PCI_BASE_M_ADR_BASE) { dev_err(dev, "illegal range, only PCI bits 31..20 allowed\n"); return -EINVAL; } - val = ((u32)range->pci_addr) & V3_PCI_BASE_M_ADR_BASE; + val = ((u32)pci_addr) & V3_PCI_BASE_M_ADR_BASE; *pci_base = val; - if (range->cpu_addr & ~V3_PCI_MAP_M_MAP_ADR) { + if (cpu_addr & ~V3_PCI_MAP_M_MAP_ADR) { dev_err(dev, "illegal range, only CPU bits 31..20 allowed\n"); return -EINVAL; } - val = ((u32)range->cpu_addr) & V3_PCI_MAP_M_MAP_ADR; + val = ((u32)cpu_addr) & V3_PCI_MAP_M_MAP_ADR; - switch (range->size) { + switch (resource_size(entry->res)) { case SZ_1M: val |= V3_LB_BASE_ADR_SIZE_1MB; break; @@ -674,7 +656,6 @@ static int v3_get_dma_range_config(struct v3_pci *v3, default: dev_err(v3->dev, "illegal dma memory chunk size\n"); return -EINVAL; - break; } val |= V3_PCI_MAP_M_REG_EN | V3_PCI_MAP_M_ENABLE; *pci_map = val; @@ -682,8 +663,8 @@ static int v3_get_dma_range_config(struct v3_pci *v3, dev_dbg(dev, "DMA MEM CPU: 0x%016llx -> 0x%016llx => " "PCI: 0x%016llx -> 0x%016llx base %08x map %08x\n", - range->cpu_addr, cpu_end, - range->pci_addr, pci_end, + cpu_addr, cpu_end, + pci_addr, pci_end, *pci_base, *pci_map); return 0; @@ -692,24 +673,16 @@ static int v3_get_dma_range_config(struct v3_pci *v3, static int v3_pci_parse_map_dma_ranges(struct v3_pci *v3, struct device_node *np) { - struct of_pci_range range; - struct of_pci_range_parser parser; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(v3); struct device *dev = v3->dev; + struct resource_entry *entry; int i = 0; - if (of_pci_dma_range_parser_init(&parser, np)) { - dev_err(dev, "missing dma-ranges property\n"); - return -EINVAL; - } - - /* - * Get the dma-ranges from the device tree - */ - for_each_of_pci_range(&parser, &range) { + resource_list_for_each_entry(entry, &bridge->dma_ranges) { int ret; u32 pci_base, pci_map; - ret = v3_get_dma_range_config(v3, &range, &pci_base, &pci_map); + ret = v3_get_dma_range_config(v3, entry, &pci_base, &pci_map); if (ret) return ret; @@ -732,7 +705,6 @@ static int v3_pci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; - resource_size_t io_base; struct resource *regs; struct resource_entry *win; struct v3_pci *v3; @@ -741,18 +713,12 @@ static int v3_pci_probe(struct platform_device *pdev) u16 val; int irq; int ret; - LIST_HEAD(res); - host = pci_alloc_host_bridge(sizeof(*v3)); + host = devm_pci_alloc_host_bridge(dev, sizeof(*v3)); if (!host) return -ENOMEM; - host->dev.parent = dev; host->ops = &v3_pci_ops; - host->busnr = 0; - host->msi = NULL; - host->map_irq = of_irq_parse_and_map_pci; - host->swizzle_irq = pci_common_swizzle; v3 = pci_host_bridge_priv(host); host->sysdata = v3; v3->dev = dev; @@ -769,8 +735,7 @@ static int v3_pci_probe(struct platform_device *pdev) return ret; } - regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - v3->base = devm_ioremap_resource(dev, regs); + v3->base = devm_platform_get_and_ioremap_resource(pdev, 0, ®s); if (IS_ERR(v3->base)) return PTR_ERR(v3->base); /* @@ -793,21 +758,11 @@ static int v3_pci_probe(struct platform_device *pdev) if (IS_ERR(v3->config_base)) return PTR_ERR(v3->config_base); - ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &res, - &io_base); - if (ret) - return ret; - - ret = devm_request_pci_bus_resources(dev, &res); - if (ret) - return ret; - /* Get and request error IRQ resource */ irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(dev, "unable to obtain PCIv3 error IRQ\n"); - return -ENODEV; - } + if (irq < 0) + return irq; + ret = devm_request_irq(dev, irq, v3_irq, 0, "PCIv3 error", v3); if (ret < 0) { @@ -852,8 +807,8 @@ static int v3_pci_probe(struct platform_device *pdev) writew(val, v3->base + V3_PCI_CMD); /* Get the I/O and memory ranges from DT */ - resource_list_for_each_entry(win, &res) { - ret = v3_pci_setup_resource(v3, io_base, host, win); + resource_list_for_each_entry(win, &host->windows) { + ret = v3_pci_setup_resource(v3, host, win); if (ret) { dev_err(dev, "error setting up resources\n"); return ret; @@ -931,18 +886,7 @@ static int v3_pci_probe(struct platform_device *pdev) val |= V3_SYSTEM_M_LOCK; writew(val, v3->base + V3_SYSTEM); - list_splice_init(&res, &host->windows); - ret = pci_scan_root_bus_bridge(host); - if (ret) { - dev_err(dev, "failed to register host: %d\n", ret); - return ret; - } - v3->bus = host->bus; - - pci_bus_assign_resources(v3->bus); - pci_bus_add_devices(v3->bus); - - return 0; + return pci_host_probe(host); } static const struct of_device_id v3_pci_of_match[] = { @@ -955,7 +899,7 @@ static const struct of_device_id v3_pci_of_match[] = { static struct platform_driver v3_pci_driver = { .driver = { .name = "pci-v3-semi", - .of_match_table = of_match_ptr(v3_pci_of_match), + .of_match_table = v3_pci_of_match, .suppress_bind_attrs = true, }, .probe = v3_pci_probe, diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c index f59ad2728c0b..e9a6758fe2c1 100644 --- a/drivers/pci/controller/pci-versatile.c +++ b/drivers/pci/controller/pci-versatile.c @@ -31,10 +31,9 @@ static u32 pci_slot_ignore; static int __init versatile_pci_slot_ignore(char *str) { - int retval; int slot; - while ((retval = get_option(&str, &slot))) { + while (get_option(&str, &slot)) { if ((slot < 0) || (slot > 31)) pr_err("Illegal slot value: %d\n", slot); else @@ -62,77 +61,25 @@ static struct pci_ops pci_versatile_ops = { .write = pci_generic_config_write, }; -static int versatile_pci_parse_request_of_pci_ranges(struct device *dev, - struct list_head *res) -{ - int err, mem = 1, res_valid = 0; - resource_size_t iobase; - struct resource_entry *win, *tmp; - - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, res, &iobase); - if (err) - return err; - - err = devm_request_pci_bus_resources(dev, res); - if (err) - goto out_release_res; - - resource_list_for_each_entry_safe(win, tmp, res) { - struct resource *res = win->res; - - switch (resource_type(res)) { - case IORESOURCE_IO: - err = devm_pci_remap_iospace(dev, res, iobase); - if (err) { - dev_warn(dev, "error %d: failed to map resource %pR\n", - err, res); - resource_list_destroy_entry(win); - } - break; - case IORESOURCE_MEM: - res_valid |= !(res->flags & IORESOURCE_PREFETCH); - - writel(res->start >> 28, PCI_IMAP(mem)); - writel(PHYS_OFFSET >> 28, PCI_SMAP(mem)); - mem++; - - break; - } - } - - if (res_valid) - return 0; - - dev_err(dev, "non-prefetchable memory resource required\n"); - err = -EINVAL; - -out_release_res: - pci_free_resource_list(res); - return err; -} - static int versatile_pci_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct resource *res; - int ret, i, myslot = -1; + struct resource_entry *entry; + int i, myslot = -1, mem = 1; u32 val; void __iomem *local_pci_cfg_base; - struct pci_bus *bus, *child; struct pci_host_bridge *bridge; - LIST_HEAD(pci_res); bridge = devm_pci_alloc_host_bridge(dev, 0); if (!bridge) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - versatile_pci_base = devm_ioremap_resource(dev, res); + versatile_pci_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(versatile_pci_base)) return PTR_ERR(versatile_pci_base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - versatile_cfg_base[0] = devm_ioremap_resource(dev, res); + versatile_cfg_base[0] = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(versatile_cfg_base[0])) return PTR_ERR(versatile_cfg_base[0]); @@ -141,9 +88,13 @@ static int versatile_pci_probe(struct platform_device *pdev) if (IS_ERR(versatile_cfg_base[1])) return PTR_ERR(versatile_cfg_base[1]); - ret = versatile_pci_parse_request_of_pci_ranges(dev, &pci_res); - if (ret) - return ret; + resource_list_for_each_entry(entry, &bridge->windows) { + if (resource_type(entry->res) == IORESOURCE_MEM) { + writel(entry->res->start >> 28, PCI_IMAP(mem)); + writel(__pa(PAGE_OFFSET) >> 28, PCI_SMAP(mem)); + mem++; + } + } /* * We need to discover the PCI core first to configure itself @@ -177,9 +128,9 @@ static int versatile_pci_probe(struct platform_device *pdev) /* * Configure the PCI inbound memory windows to be 1:1 mapped to SDRAM */ - writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_0); - writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_1); - writel(PHYS_OFFSET, local_pci_cfg_base + PCI_BASE_ADDRESS_2); + writel(__pa(PAGE_OFFSET), local_pci_cfg_base + PCI_BASE_ADDRESS_0); + writel(__pa(PAGE_OFFSET), local_pci_cfg_base + PCI_BASE_ADDRESS_1); + writel(__pa(PAGE_OFFSET), local_pci_cfg_base + PCI_BASE_ADDRESS_2); /* * For many years the kernel and QEMU were symbiotically buggy @@ -194,29 +145,11 @@ static int versatile_pci_probe(struct platform_device *pdev) */ writel(0, versatile_cfg_base[0] + PCI_INTERRUPT_LINE); - pci_add_flags(PCI_ENABLE_PROC_DOMAINS); pci_add_flags(PCI_REASSIGN_ALL_BUS); - list_splice_init(&pci_res, &bridge->windows); - bridge->dev.parent = dev; - bridge->sysdata = NULL; - bridge->busnr = 0; bridge->ops = &pci_versatile_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - - ret = pci_scan_root_bus_bridge(bridge); - if (ret < 0) - return ret; - - bus = bridge->bus; - - pci_assign_unassigned_bus_resources(bus); - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); - pci_bus_add_devices(bus); - return 0; + return pci_host_probe(bridge); } static const struct of_device_id versatile_pci_of_match[] = { @@ -236,4 +169,3 @@ static struct platform_driver versatile_pci_driver = { module_platform_driver(versatile_pci_driver); MODULE_DESCRIPTION("Versatile PCI driver"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-xgene-msi.c b/drivers/pci/controller/pci-xgene-msi.c index f4c02da84e59..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/of_irq.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) +static irq_hw_number_t compute_hwirq(u8 frame, u8 index, u8 data) { - return (hwirq / (NR_HW_IRQS * IRQS_PER_IDX)); -} - -static u32 hwirq_to_group(unsigned long hwirq) -{ - return (hwirq % NR_HW_IRQS); -} - -static u32 hwirq_to_msi_data(unsigned long hwirq) -{ - return ((hwirq / NR_HW_IRQS) % IRQS_PER_IDX); + return (FIELD_PREP(BIT(7), FIELD_GET(BIT(3), frame)) | + FIELD_PREP(MSInRx_HWIRQ_MASK, index) | + FIELD_PREP(DATA_HWIRQ_MASK, data)); } static void xgene_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct xgene_msi *msi = irq_data_get_irq_chip_data(data); - u32 reg_set = hwirq_to_reg_set(data->hwirq); - u32 group = hwirq_to_group(data->hwirq); - u64 target_addr = msi->msi_addr + (((8 * group) + reg_set) << 16); + u64 target_addr; + u32 frame, msir; + int cpu; - msg->address_hi = upper_32_bits(target_addr); - msg->address_lo = lower_32_bits(target_addr); - msg->data = hwirq_to_msi_data(data->hwirq); -} + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); + msir = FIELD_GET(MSInRx_HWIRQ_MASK, data->hwirq); + frame = FIELD_PREP(BIT(3), FIELD_GET(BIT(7), data->hwirq)) | cpu; -/* - * X-Gene v1 only has 16 MSI GIC IRQs for 2048 MSI vectors. To maintain - * the expected behaviour of .set_affinity for each MSI interrupt, the 16 - * MSI GIC IRQs are statically allocated to 8 X-Gene v1 cores (2 GIC IRQs - * for each core). The MSI vector is moved fom 1 MSI GIC IRQ to another - * MSI GIC IRQ to steer its MSI interrupt to correct X-Gene v1 core. As a - * consequence, the total MSI vectors that X-Gene v1 supports will be - * reduced to 256 (2048/8) vectors. - */ -static int hwirq_to_cpu(unsigned long hwirq) -{ - return (hwirq % xgene_msi_ctrl.num_cpus); -} + target_addr = msi->msi_addr; + target_addr += (FIELD_PREP(MSI_GROUP_MASK, frame) | + FIELD_PREP(MSI_INTR_MASK, msir)); -static unsigned long hwirq_to_canonical_hwirq(unsigned long hwirq) -{ - return (hwirq - hwirq_to_cpu(hwirq)); + msg->address_hi = upper_32_bits(target_addr); + msg->address_lo = lower_32_bits(target_addr); + msg->data = FIELD_GET(DATA_HWIRQ_MASK, data->hwirq); } static int xgene_msi_set_affinity(struct irq_data *irqdata, const struct cpumask *mask, bool force) { int target_cpu = cpumask_first(mask); - int curr_cpu; - - curr_cpu = hwirq_to_cpu(irqdata->hwirq); - if (curr_cpu == target_cpu) - return IRQ_SET_MASK_OK_DONE; - /* Update MSI number to target the new CPU */ - irqdata->hwirq = hwirq_to_canonical_hwirq(irqdata->hwirq) + target_cpu; + irq_data_update_effective_affinity(irqdata, cpumask_of(target_cpu)); + /* Force the core code to regenerate the message */ return IRQ_SET_MASK_OK; } @@ -195,25 +167,23 @@ static int xgene_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *args) { struct xgene_msi *msi = domain->host_data; - int msi_irq; + irq_hw_number_t hwirq; mutex_lock(&msi->bitmap_lock); - msi_irq = bitmap_find_next_zero_area(msi->bitmap, NR_MSI_VEC, 0, - msi->num_cpus, 0); - if (msi_irq < NR_MSI_VEC) - bitmap_set(msi->bitmap, msi_irq, msi->num_cpus); - else - msi_irq = -ENOSPC; + hwirq = find_first_zero_bit(msi->bitmap, NR_MSI_VEC); + if (hwirq < NR_MSI_VEC) + set_bit(hwirq, msi->bitmap); mutex_unlock(&msi->bitmap_lock); - if (msi_irq < 0) - return msi_irq; + if (hwirq >= NR_MSI_VEC) + return -ENOSPC; - irq_domain_set_info(domain, virq, msi_irq, + irq_domain_set_info(domain, virq, hwirq, &xgene_msi_bottom_irq_chip, domain->host_data, handle_simple_irq, NULL, NULL); + irqd_set_resend_when_in_progress(irq_get_irq_data(virq)); return 0; } @@ -223,215 +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) { - int size = BITS_TO_LONGS(NR_MSI_VEC) * sizeof(long); - - xgene_msi->bitmap = kzalloc(size, 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; - unsigned int virq; - int msir_index, msir_val, hw_irq; - 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 interupts - * 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); - virq = irq_find_mapping(xgene_msi->inner_domain, hw_irq); - WARN_ON(!virq); - if (virq != 0) - generic_handle_irq(virq); - 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); - } - } + msi_grp = irqp - xgene_msi->gic_irq; - chained_irq_exit(chip, desc); -} + grp_pending = xgene_msi_int_read(xgene_msi, msi_grp); -static enum cpuhp_state pci_xgene_online; + for_each_set_bit(msir_idx, &grp_pending, IDX_PER_GROUP) { + unsigned long msir; + int intr_idx; -static int xgene_msi_remove(struct platform_device *pdev) -{ - struct xgene_msi *msi = platform_get_drvdata(pdev); + msir = xgene_msi_ir_read(xgene_msi, msi_grp, msir_idx); - if (pci_xgene_online) - cpuhp_remove_state(pci_xgene_online); - cpuhp_remove_state(CPUHP_PCI_XGENE_DEAD); + for_each_set_bit(intr_idx, &msir, IRQS_PER_IDX) { + irq_hw_number_t hwirq; + int ret; - kfree(msi->msi_groups); + hwirq = compute_hwirq(msi_grp, msir_idx, intr_idx); + ret = generic_handle_domain_irq(xgene_msi->inner_domain, + hwirq); + WARN_ON_ONCE(ret); + } + } - kfree(msi->bitmap); - msi->bitmap = NULL; + chained_irq_exit(chip, desc); +} - xgene_free_domains(msi); +static void xgene_msi_remove(struct platform_device *pdev) +{ + 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); + } - return 0; + 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; - irq_set_chained_handler(msi_group->gic_irq, - xgene_msi_isr); - err = irq_set_handler_data(msi_group->gic_irq, msi_group); - if (err) { - pr_err("failed to register GIC IRQ handler\n"); + /* + * 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 = 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; } @@ -443,85 +347,42 @@ 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; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - xgene_msi->msi_regs = devm_ioremap_resource(&pdev->dev, res); + xgene_msi->msi_regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(xgene_msi->msi_regs)) { - dev_err(&pdev->dev, "no reg space\n"); rc = PTR_ERR(xgene_msi->msi_regs); goto error; } xgene_msi->msi_addr = res->start; - xgene_msi->node = pdev->dev.of_node; - xgene_msi->num_cpus = num_possible_cpus(); - rc = xgene_msi_init_allocator(xgene_msi); + 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) { - dev_err(&pdev->dev, "Cannot translate IRQ index %d\n", - irq_index); - 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++) - msi_val = 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; @@ -535,9 +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 ffda3e8b4742..b95afa35201d 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0+ -/** +/* * APM X-Gene PCIe Driver * * Copyright (c) 2014 Applied Micro Circuits Corporation. @@ -12,9 +12,9 @@ #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_irq.h> #include <linux/of_pci.h> #include <linux/pci.h> #include <linux/pci-acpi.h> @@ -48,20 +48,16 @@ #define EN_COHERENCY 0xF0000000 #define EN_REG 0x00000001 #define OB_LO_IO 0x00000002 -#define XGENE_PCIE_VENDORID 0x10E8 #define XGENE_PCIE_DEVICEID 0xE004 -#define SZ_1T (SZ_1G*1024ULL) #define PIPE_PHY_RATE_RD(src) ((0xc000 & (u32)(src)) >> 0xe) #define XGENE_V1_PCI_EXP_CAP 0x40 /* PCIe IP version */ -#define XGENE_PCIE_IP_VER_UNKN 0 #define XGENE_PCIE_IP_VER_1 1 #define XGENE_PCIE_IP_VER_2 2 -#if defined(CONFIG_PCI_XGENE) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) -struct xgene_pcie_port { +struct xgene_pcie { struct device_node *node; struct device *dev; struct clk *clk; @@ -72,12 +68,12 @@ struct xgene_pcie_port { u32 version; }; -static u32 xgene_pcie_readl(struct xgene_pcie_port *port, u32 reg) +static u32 xgene_pcie_readl(struct xgene_pcie *port, u32 reg) { return readl(port->csr_base + reg); } -static void xgene_pcie_writel(struct xgene_pcie_port *port, u32 reg, u32 val) +static void xgene_pcie_writel(struct xgene_pcie *port, u32 reg, u32 val) { writel(val, port->csr_base + reg); } @@ -87,15 +83,15 @@ static inline u32 pcie_bar_low_val(u32 addr, u32 flags) return (addr & PCI_BASE_ADDRESS_MEM_MASK) | flags; } -static inline struct xgene_pcie_port *pcie_bus_to_port(struct pci_bus *bus) +static inline struct xgene_pcie *pcie_bus_to_port(struct pci_bus *bus) { struct pci_config_window *cfg; if (acpi_disabled) - return (struct xgene_pcie_port *)(bus->sysdata); + return (struct xgene_pcie *)(bus->sysdata); cfg = bus->sysdata; - return (struct xgene_pcie_port *)(cfg->priv); + return (struct xgene_pcie *)(cfg->priv); } /* @@ -104,7 +100,7 @@ static inline struct xgene_pcie_port *pcie_bus_to_port(struct pci_bus *bus) */ static void __iomem *xgene_pcie_get_cfg_base(struct pci_bus *bus) { - struct xgene_pcie_port *port = pcie_bus_to_port(bus); + struct xgene_pcie *port = pcie_bus_to_port(bus); if (bus->number >= (bus->primary + 1)) return port->cfg_base + AXI_EP_CFG_ACCESS; @@ -118,7 +114,7 @@ static void __iomem *xgene_pcie_get_cfg_base(struct pci_bus *bus) */ static void xgene_pcie_set_rtdid_reg(struct pci_bus *bus, uint devfn) { - struct xgene_pcie_port *port = pcie_bus_to_port(bus); + struct xgene_pcie *port = pcie_bus_to_port(bus); unsigned int b, d, f; u32 rtdid_val = 0; @@ -165,31 +161,32 @@ static void __iomem *xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, static int xgene_pcie_config_read32(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { - struct xgene_pcie_port *port = pcie_bus_to_port(bus); + struct xgene_pcie *port = pcie_bus_to_port(bus); + int ret; - if (pci_generic_config_read32(bus, devfn, where & ~0x3, 4, val) != - PCIBIOS_SUCCESSFUL) - return PCIBIOS_DEVICE_NOT_FOUND; + ret = pci_generic_config_read32(bus, devfn, where & ~0x3, 4, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; /* - * The v1 controller has a bug in its Configuration Request - * Retry Status (CRS) logic: when CRS is enabled and we read the - * Vendor and Device ID of a non-existent device, the controller - * fabricates return data of 0xFFFF0001 ("device exists but is not - * ready") instead of 0xFFFFFFFF ("device does not exist"). This - * causes the PCI core to retry the read until it times out. - * Avoid this by not claiming to support CRS. + * The v1 controller has a bug in its Configuration Request Retry + * Status (RRS) logic: when RRS Software Visibility is enabled and + * we read the Vendor and Device ID of a non-existent device, the + * controller fabricates return data of 0xFFFF0001 ("device exists + * but is not ready") instead of 0xFFFFFFFF (PCI_ERROR_RESPONSE) + * ("device does not exist"). This causes the PCI core to retry + * the read until it times out. Avoid this by not claiming to + * support RRS SV. */ if (pci_is_root_bus(bus) && (port->version == XGENE_PCIE_IP_VER_1) && ((where & ~0x3) == XGENE_V1_PCI_EXP_CAP + PCI_EXP_RTCTL)) - *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); + *val &= ~(PCI_EXP_RTCAP_RRS_SV << 16); if (size <= 2) *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); return PCIBIOS_SUCCESSFUL; } -#endif #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) static int xgene_get_csr_resource(struct acpi_device *adev, @@ -227,7 +224,7 @@ static int xgene_pcie_ecam_init(struct pci_config_window *cfg, u32 ipversion) { struct device *dev = cfg->parent; struct acpi_device *adev = to_acpi_device(dev); - struct xgene_pcie_port *port; + struct xgene_pcie *port; struct resource csr; int ret; @@ -256,8 +253,7 @@ static int xgene_v1_pcie_ecam_init(struct pci_config_window *cfg) return xgene_pcie_ecam_init(cfg, XGENE_PCIE_IP_VER_1); } -struct pci_ecam_ops xgene_v1_pcie_ecam_ops = { - .bus_shift = 16, +const struct pci_ecam_ops xgene_v1_pcie_ecam_ops = { .init = xgene_v1_pcie_ecam_init, .pci_ops = { .map_bus = xgene_pcie_map_bus, @@ -271,8 +267,7 @@ static int xgene_v2_pcie_ecam_init(struct pci_config_window *cfg) return xgene_pcie_ecam_init(cfg, XGENE_PCIE_IP_VER_2); } -struct pci_ecam_ops xgene_v2_pcie_ecam_ops = { - .bus_shift = 16, +const struct pci_ecam_ops xgene_v2_pcie_ecam_ops = { .init = xgene_v2_pcie_ecam_init, .pci_ops = { .map_bus = xgene_pcie_map_bus, @@ -282,8 +277,7 @@ 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 *port, u32 addr, +static u64 xgene_pcie_set_ib_mask(struct xgene_pcie *port, u32 addr, u32 flags, u64 size) { u64 mask = (~(size - 1) & PCI_BASE_ADDRESS_MEM_MASK) | flags; @@ -309,7 +303,7 @@ static u64 xgene_pcie_set_ib_mask(struct xgene_pcie_port *port, u32 addr, return mask; } -static void xgene_pcie_linkup(struct xgene_pcie_port *port, +static void xgene_pcie_linkup(struct xgene_pcie *port, u32 *lanes, u32 *speed) { u32 val32; @@ -324,7 +318,7 @@ static void xgene_pcie_linkup(struct xgene_pcie_port *port, } } -static int xgene_pcie_init_port(struct xgene_pcie_port *port) +static int xgene_pcie_init_port(struct xgene_pcie *port) { struct device *dev = port->dev; int rc; @@ -344,7 +338,7 @@ static int xgene_pcie_init_port(struct xgene_pcie_port *port) return 0; } -static int xgene_pcie_map_reg(struct xgene_pcie_port *port, +static int xgene_pcie_map_reg(struct xgene_pcie *port, struct platform_device *pdev) { struct device *dev = port->dev; @@ -364,7 +358,7 @@ static int xgene_pcie_map_reg(struct xgene_pcie_port *port, return 0; } -static void xgene_pcie_setup_ob_reg(struct xgene_pcie_port *port, +static void xgene_pcie_setup_ob_reg(struct xgene_pcie *port, struct resource *res, u32 offset, u64 cpu_addr, u64 pci_addr) { @@ -396,7 +390,7 @@ static void xgene_pcie_setup_ob_reg(struct xgene_pcie_port *port, xgene_pcie_writel(port, offset + 0x14, upper_32_bits(pci_addr)); } -static void xgene_pcie_setup_cfg_reg(struct xgene_pcie_port *port) +static void xgene_pcie_setup_cfg_reg(struct xgene_pcie *port) { u64 addr = port->cfg_addr; @@ -405,15 +399,13 @@ static void xgene_pcie_setup_cfg_reg(struct xgene_pcie_port *port) xgene_pcie_writel(port, CFGCTL, EN_REG); } -static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, - struct list_head *res, - resource_size_t io_base) +static int xgene_pcie_map_ranges(struct xgene_pcie *port) { + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(port); struct resource_entry *window; struct device *dev = port->dev; - int ret; - resource_list_for_each_entry(window, res) { + resource_list_for_each_entry(window, &bridge->windows) { struct resource *res = window->res; u64 restype = resource_type(res); @@ -421,11 +413,9 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, switch (restype) { case IORESOURCE_IO: - xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base, + xgene_pcie_setup_ob_reg(port, res, OMR3BARL, + pci_pio_to_address(res->start), res->start - window->offset); - ret = devm_pci_remap_iospace(dev, res, io_base); - if (ret < 0) - return ret; break; case IORESOURCE_MEM: if (res->flags & IORESOURCE_PREFETCH) @@ -450,7 +440,7 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port, return 0; } -static void xgene_pcie_setup_pims(struct xgene_pcie_port *port, u32 pim_reg, +static void xgene_pcie_setup_pims(struct xgene_pcie *port, u32 pim_reg, u64 pim, u64 size) { xgene_pcie_writel(port, pim_reg, lower_32_bits(pim)); @@ -484,12 +474,12 @@ static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size) return -EINVAL; } -static void xgene_pcie_setup_ib_reg(struct xgene_pcie_port *port, +static void xgene_pcie_setup_ib_reg(struct xgene_pcie *port, struct of_pci_range *range, u8 *ib_reg_mask) { void __iomem *cfg_base = port->cfg_base; struct device *dev = port->dev; - void *bar_addr; + void __iomem *bar_addr; u32 pim_reg; u64 cpu_addr = range->cpu_addr; u64 pci_addr = range->pci_addr; @@ -534,7 +524,7 @@ static void xgene_pcie_setup_ib_reg(struct xgene_pcie_port *port, xgene_pcie_setup_pims(port, pim_reg, pci_addr, ~(size - 1)); } -static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie_port *port) +static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie *port) { struct device_node *np = port->node; struct of_pci_range range; @@ -559,7 +549,7 @@ static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie_port *port) } /* clear BAR configuration which was done by firmware */ -static void xgene_pcie_clear_config(struct xgene_pcie_port *port) +static void xgene_pcie_clear_config(struct xgene_pcie *port) { int i; @@ -567,8 +557,7 @@ static void xgene_pcie_clear_config(struct xgene_pcie_port *port) xgene_pcie_writel(port, i, 0); } -static int xgene_pcie_setup(struct xgene_pcie_port *port, struct list_head *res, - resource_size_t io_base) +static int xgene_pcie_setup(struct xgene_pcie *port) { struct device *dev = port->dev; u32 val, lanes = 0, speed = 0; @@ -577,10 +566,10 @@ static int xgene_pcie_setup(struct xgene_pcie_port *port, struct list_head *res, xgene_pcie_clear_config(port); /* setup the vendor and device IDs correctly */ - val = (XGENE_PCIE_DEVICEID << 16) | XGENE_PCIE_VENDORID; + val = (XGENE_PCIE_DEVICEID << 16) | PCI_VENDOR_ID_AMCC; xgene_pcie_writel(port, BRIDGE_CFG_0, val); - ret = xgene_pcie_map_ranges(port, res, io_base); + ret = xgene_pcie_map_ranges(port); if (ret) return ret; @@ -602,16 +591,35 @@ 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; struct device_node *dn = dev->of_node; - struct xgene_pcie_port *port; - resource_size_t iobase = 0; - struct pci_bus *bus, *child; + struct xgene_pcie *port; struct pci_host_bridge *bridge; int ret; - LIST_HEAD(res); + + 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) @@ -621,10 +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) @@ -634,42 +639,14 @@ static int xgene_pcie_probe(struct platform_device *pdev) if (ret) return ret; - ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &res, - &iobase); + ret = xgene_pcie_setup(port); if (ret) return ret; - ret = devm_request_pci_bus_resources(dev, &res); - if (ret) - goto error; - - ret = xgene_pcie_setup(port, &res, iobase); - if (ret) - goto error; - - list_splice_init(&res, &bridge->windows); - bridge->dev.parent = dev; bridge->sysdata = port; - bridge->busnr = 0; bridge->ops = &xgene_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - - ret = pci_scan_root_bus_bridge(bridge); - if (ret < 0) - goto error; - - bus = bridge->bus; - pci_assign_unassigned_bus_resources(bus); - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); - pci_bus_add_devices(bus); - return 0; - -error: - pci_free_resource_list(&res); - return ret; + return pci_host_probe(bridge); } static const struct of_device_id xgene_pcie_match_table[] = { @@ -680,10 +657,9 @@ static const struct of_device_id xgene_pcie_match_table[] = { static struct platform_driver xgene_pcie_driver = { .driver = { .name = "xgene-pcie", - .of_match_table = of_match_ptr(xgene_pcie_match_table), + .of_match_table = xgene_pcie_match_table, .suppress_bind_attrs = true, }, .probe = xgene_pcie_probe, }; builtin_platform_driver(xgene_pcie_driver); -#endif diff --git a/drivers/pci/controller/pcie-altera-msi.c b/drivers/pci/controller/pcie-altera-msi.c index 025ef7d9a046..ea2ca2e70f20 100644 --- a/drivers/pci/controller/pcie-altera-msi.c +++ b/drivers/pci/controller/pcie-altera-msi.c @@ -9,10 +9,12 @@ #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> #include <linux/msi.h> #include <linux/of_address.h> -#include <linux/of_irq.h> #include <linux/of_pci.h> #include <linux/pci.h> #include <linux/platform_device.h> @@ -28,7 +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; @@ -54,7 +55,7 @@ static void altera_msi_isr(struct irq_desc *desc) struct altera_msi *msi; unsigned long status; u32 bit; - u32 virq; + int ret; chained_irq_enter(chip, desc); msi = irq_desc_get_handler_data(desc); @@ -64,29 +65,29 @@ static void altera_msi_isr(struct irq_desc *desc) /* Dummy read from vector to clear the interrupt */ readl_relaxed(msi->vector_base + (bit * sizeof(u32))); - virq = irq_find_mapping(msi->inner_domain, bit); - if (virq) - generic_handle_irq(virq); - else - dev_err(&msi->pdev->dev, "unexpected MSI\n"); + ret = generic_handle_domain_irq(msi->inner_domain, bit); + if (ret) + dev_err_ratelimited(&msi->pdev->dev, "unexpected MSI\n"); } } chained_irq_exit(chip, desc); } -static struct irq_chip altera_msi_irq_chip = { - .name = "Altera PCIe MSI", - .irq_mask = pci_msi_mask_irq, - .irq_unmask = pci_msi_unmask_irq, -}; +#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_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); @@ -100,16 +101,9 @@ static void altera_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) (int)data->hwirq, msg->address_hi, msg->address_lo); } -static int altera_msi_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) -{ - return -EINVAL; -} - static struct irq_chip altera_msi_bottom_irq_chip = { .name = "Altera MSI", .irq_compose_msi_msg = altera_compose_msi_msg, - .irq_set_affinity = altera_msi_set_affinity, }; static int altera_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, @@ -172,20 +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; } @@ -194,22 +184,19 @@ 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); } -static int altera_msi_remove(struct platform_device *pdev) +static void altera_msi_remove(struct platform_device *pdev) { struct altera_msi *msi = platform_get_drvdata(pdev); msi_writel(msi, 0, MSI_INTMASK); - irq_set_chained_handler(msi->irq, NULL); - irq_set_handler_data(msi->irq, NULL); + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); altera_free_domains(msi); platform_set_drvdata(pdev, NULL); - return 0; } static int altera_msi_probe(struct platform_device *pdev) @@ -227,8 +214,7 @@ static int altera_msi_probe(struct platform_device *pdev) mutex_init(&msi->lock); msi->pdev = pdev; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "csr"); - msi->csr_base = devm_ioremap_resource(&pdev->dev, res); + msi->csr_base = devm_platform_ioremap_resource_byname(pdev, "csr"); if (IS_ERR(msi->csr_base)) { dev_err(&pdev->dev, "failed to map csr memory\n"); return PTR_ERR(msi->csr_base); @@ -237,10 +223,8 @@ static int altera_msi_probe(struct platform_device *pdev) res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "vector_slave"); msi->vector_base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(msi->vector_base)) { - dev_err(&pdev->dev, "failed to map vector_slave memory\n"); + if (IS_ERR(msi->vector_base)) return PTR_ERR(msi->vector_base); - } msi->vector_phy = res->start; @@ -255,7 +239,6 @@ static int altera_msi_probe(struct platform_device *pdev) msi->irq = platform_get_irq(pdev, 0); if (msi->irq < 0) { - dev_err(&pdev->dev, "failed to map IRQ: %d\n", msi->irq); ret = msi->irq; goto err; } @@ -288,4 +271,14 @@ static int __init altera_msi_init(void) { return platform_driver_register(&altera_msi_driver); } + +static void __exit altera_msi_exit(void) +{ + platform_driver_unregister(&altera_msi_driver); +} + subsys_initcall(altera_msi_init); +MODULE_DEVICE_TABLE(of, altera_msi_of_match); +module_exit(altera_msi_exit); +MODULE_DESCRIPTION("Altera PCIe MSI support driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c index 7d05e51205b3..3dbb7adc421c 100644 --- a/drivers/pci/controller/pcie-altera.c +++ b/drivers/pci/controller/pcie-altera.c @@ -6,12 +6,14 @@ * Description: Altera PCIe host controller driver */ +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> #include <linux/init.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> +#include <linux/module.h> +#include <linux/of.h> #include <linux/of_pci.h> #include <linux/pci.h> #include <linux/platform_device.h> @@ -37,7 +39,14 @@ #define RP_LTSSM_MASK 0x1f #define LTSSM_L0 0xf -#define PCIE_CAP_OFFSET 0x80 +#define S10_RP_TX_CNTRL 0x2004 +#define S10_RP_RXCPL_REG 0x2008 +#define S10_RP_RXCPL_STATUS 0x200C +#define S10_RP_CFG_ADDR(pcie, reg) \ + (((pcie)->hip_base) + (reg) + (1 << 20)) +#define S10_RP_SECONDARY(pcie) \ + readb(S10_RP_CFG_ADDR(pcie, PCI_SECONDARY_BUS)) + /* TLP configuration type 0 and 1 */ #define TLP_FMTTYPE_CFGRD0 0x04 /* Configuration Read Type 0 */ #define TLP_FMTTYPE_CFGWR0 0x44 /* Configuration Write Type 0 */ @@ -47,20 +56,15 @@ #define TLP_READ_TAG 0x1d #define TLP_WRITE_TAG 0x10 #define RP_DEVFN 0 -#define TLP_REQ_ID(bus, devfn) (((bus) << 8) | (devfn)) -#define TLP_CFGRD_DW0(pcie, bus) \ - ((((bus == pcie->root_bus_nr) ? TLP_FMTTYPE_CFGRD0 \ - : TLP_FMTTYPE_CFGRD1) << 24) | \ - TLP_PAYLOAD_SIZE) -#define TLP_CFGWR_DW0(pcie, bus) \ - ((((bus == pcie->root_bus_nr) ? TLP_FMTTYPE_CFGWR0 \ - : TLP_FMTTYPE_CFGWR1) << 24) | \ - TLP_PAYLOAD_SIZE) +#define TLP_CFG_DW0(pcie, cfg) \ + (((cfg) << 24) | \ + TLP_PAYLOAD_SIZE) #define TLP_CFG_DW1(pcie, tag, be) \ - (((TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN)) << 16) | (tag << 8) | (be)) + (((PCI_DEVID(pcie->root_bus_nr, RP_DEVFN)) << 16) | (tag << 8) | (be)) #define TLP_CFG_DW2(bus, devfn, offset) \ (((bus) << 24) | ((devfn) << 16) | (offset)) #define TLP_COMP_STATUS(s) (((s) >> 13) & 7) +#define TLP_BYTE_COUNT(s) (((s) >> 0) & 0xfff) #define TLP_HDR_SIZE 3 #define TLP_LOOP 500 @@ -69,14 +73,70 @@ #define DWORD_MASK 3 +#define S10_TLP_FMTTYPE_CFGRD0 0x05 +#define S10_TLP_FMTTYPE_CFGRD1 0x04 +#define S10_TLP_FMTTYPE_CFGWR0 0x45 +#define S10_TLP_FMTTYPE_CFGWR1 0x44 + +#define AGLX_RP_CFG_ADDR(pcie, reg) (((pcie)->hip_base) + (reg)) +#define AGLX_RP_SECONDARY(pcie) \ + readb(AGLX_RP_CFG_ADDR(pcie, PCI_SECONDARY_BUS)) + +#define AGLX_BDF_REG 0x00002004 +#define AGLX_ROOT_PORT_IRQ_STATUS 0x14c +#define AGLX_ROOT_PORT_IRQ_ENABLE 0x150 +#define CFG_AER BIT(4) + +#define AGLX_CFG_TARGET GENMASK(13, 12) +#define AGLX_CFG_TARGET_TYPE0 0 +#define AGLX_CFG_TARGET_TYPE1 1 +#define AGLX_CFG_TARGET_LOCAL_2000 2 +#define AGLX_CFG_TARGET_LOCAL_3000 3 + +enum altera_pcie_version { + ALTERA_PCIE_V1 = 0, + ALTERA_PCIE_V2, + ALTERA_PCIE_V3, +}; + struct altera_pcie { struct platform_device *pdev; - void __iomem *cra_base; /* DT Cra */ + void __iomem *cra_base; + void __iomem *hip_base; int irq; u8 root_bus_nr; struct irq_domain *irq_domain; struct resource bus_range; - struct list_head resources; + const struct altera_pcie_data *pcie_data; +}; + +struct altera_pcie_ops { + int (*tlp_read_pkt)(struct altera_pcie *pcie, u32 *value); + void (*tlp_write_pkt)(struct altera_pcie *pcie, u32 *headers, + u32 data, bool align); + bool (*get_link_status)(struct altera_pcie *pcie); + int (*rp_read_cfg)(struct altera_pcie *pcie, int where, + int size, u32 *value); + int (*rp_write_cfg)(struct altera_pcie *pcie, u8 busno, + int where, int size, u32 value); + int (*ep_read_cfg)(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 *value); + int (*ep_write_cfg)(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 value); + void (*rp_isr)(struct irq_desc *desc); +}; + +struct altera_pcie_data { + const struct altera_pcie_ops *ops; + enum altera_pcie_version version; + u32 cap_offset; /* PCIe capability structure register offset */ + u32 cfgrd0; + u32 cfgrd1; + u32 cfgwr0; + u32 cfgwr1; + u32 port_conf_offset; + u32 port_irq_status_offset; + u32 port_irq_enable_offset; }; struct tlp_rp_regpair_t { @@ -96,16 +156,56 @@ static inline u32 cra_readl(struct altera_pcie *pcie, const u32 reg) return readl_relaxed(pcie->cra_base + reg); } +static inline void cra_writew(struct altera_pcie *pcie, const u32 value, + const u32 reg) +{ + writew_relaxed(value, pcie->cra_base + reg); +} + +static inline u32 cra_readw(struct altera_pcie *pcie, const u32 reg) +{ + return readw_relaxed(pcie->cra_base + reg); +} + +static inline void cra_writeb(struct altera_pcie *pcie, const u32 value, + const u32 reg) +{ + writeb_relaxed(value, pcie->cra_base + reg); +} + +static inline u32 cra_readb(struct altera_pcie *pcie, const u32 reg) +{ + return readb_relaxed(pcie->cra_base + reg); +} + static bool altera_pcie_link_up(struct altera_pcie *pcie) { return !!((cra_readl(pcie, RP_LTSSM) & RP_LTSSM_MASK) == LTSSM_L0); } +static bool s10_altera_pcie_link_up(struct altera_pcie *pcie) +{ + void __iomem *addr = S10_RP_CFG_ADDR(pcie, + pcie->pcie_data->cap_offset + + PCI_EXP_LNKSTA); + + return !!(readw(addr) & PCI_EXP_LNKSTA_DLLLA); +} + +static bool aglx_altera_pcie_link_up(struct altera_pcie *pcie) +{ + void __iomem *addr = AGLX_RP_CFG_ADDR(pcie, + pcie->pcie_data->cap_offset + + PCI_EXP_LNKSTA); + + return (readw_relaxed(addr) & PCI_EXP_LNKSTA_DLLLA); +} + /* * Altera PCIe port uses BAR0 of RC's configuration space as the translation * from PCI bus to native BUS. Entire DDR region is mapped into PCIe space * using these registers, so it can be reached by DMA from EP devices. - * This BAR0 will also access to MSI vector when receiving MSI/MSIX interrupt + * This BAR0 will also access to MSI vector when receiving MSI/MSI-X interrupt * from EP devices, eventually trigger interrupt to GIC. The BAR0 of bridge * should be hidden during enumeration to avoid the sizing and resource * allocation by PCIe core. @@ -128,12 +228,18 @@ static void tlp_write_tx(struct altera_pcie *pcie, cra_writel(pcie, tlp_rp_regdata->ctrl, RP_TX_CNTRL); } +static void s10_tlp_write_tx(struct altera_pcie *pcie, u32 reg0, u32 ctrl) +{ + cra_writel(pcie, reg0, RP_TX_REG0); + cra_writel(pcie, ctrl, S10_RP_TX_CNTRL); +} + static bool altera_pcie_valid_device(struct altera_pcie *pcie, struct pci_bus *bus, int dev) { /* If there is no link, then there is no device */ if (bus->number != pcie->root_bus_nr) { - if (!altera_pcie_link_up(pcie)) + if (!pcie->pcie_data->ops->get_link_status(pcie)) return false; } @@ -141,7 +247,7 @@ static bool altera_pcie_valid_device(struct altera_pcie *pcie, if (bus->number == pcie->root_bus_nr && dev > 0) return false; - return true; + return true; } static int tlp_read_packet(struct altera_pcie *pcie, u32 *value) @@ -183,6 +289,53 @@ static int tlp_read_packet(struct altera_pcie *pcie, u32 *value) return PCIBIOS_DEVICE_NOT_FOUND; } +static int s10_tlp_read_packet(struct altera_pcie *pcie, u32 *value) +{ + u32 ctrl; + u32 comp_status; + u32 dw[4]; + u32 count; + struct device *dev = &pcie->pdev->dev; + + for (count = 0; count < TLP_LOOP; count++) { + ctrl = cra_readl(pcie, S10_RP_RXCPL_STATUS); + if (ctrl & RP_RXCPL_SOP) { + /* Read first DW */ + dw[0] = cra_readl(pcie, S10_RP_RXCPL_REG); + break; + } + + udelay(5); + } + + /* SOP detection failed, return error */ + if (count == TLP_LOOP) + return PCIBIOS_DEVICE_NOT_FOUND; + + count = 1; + + /* Poll for EOP */ + while (count < ARRAY_SIZE(dw)) { + ctrl = cra_readl(pcie, S10_RP_RXCPL_STATUS); + dw[count++] = cra_readl(pcie, S10_RP_RXCPL_REG); + if (ctrl & RP_RXCPL_EOP) { + comp_status = TLP_COMP_STATUS(dw[1]); + if (comp_status) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (value && TLP_BYTE_COUNT(dw[1]) == sizeof(u32) && + count == 4) + *value = dw[3]; + + return PCIBIOS_SUCCESSFUL; + } + } + + dev_warn(dev, "Malformed TLP packet\n"); + + return PCIBIOS_DEVICE_NOT_FOUND; +} + static void tlp_write_packet(struct altera_pcie *pcie, u32 *headers, u32 data, bool align) { @@ -210,18 +363,44 @@ static void tlp_write_packet(struct altera_pcie *pcie, u32 *headers, tlp_write_tx(pcie, &tlp_rp_regdata); } +static void s10_tlp_write_packet(struct altera_pcie *pcie, u32 *headers, + u32 data, bool dummy) +{ + s10_tlp_write_tx(pcie, headers[0], RP_TX_SOP); + s10_tlp_write_tx(pcie, headers[1], 0); + s10_tlp_write_tx(pcie, headers[2], 0); + s10_tlp_write_tx(pcie, data, RP_TX_EOP); +} + +static void get_tlp_header(struct altera_pcie *pcie, u8 bus, u32 devfn, + int where, u8 byte_en, bool read, u32 *headers) +{ + u8 cfg; + u8 cfg0 = read ? pcie->pcie_data->cfgrd0 : pcie->pcie_data->cfgwr0; + u8 cfg1 = read ? pcie->pcie_data->cfgrd1 : pcie->pcie_data->cfgwr1; + u8 tag = read ? TLP_READ_TAG : TLP_WRITE_TAG; + + if (pcie->pcie_data->version == ALTERA_PCIE_V1) + cfg = (bus == pcie->root_bus_nr) ? cfg0 : cfg1; + else + cfg = (bus > S10_RP_SECONDARY(pcie)) ? cfg0 : cfg1; + + headers[0] = TLP_CFG_DW0(pcie, cfg); + headers[1] = TLP_CFG_DW1(pcie, tag, byte_en); + headers[2] = TLP_CFG_DW2(bus, devfn, where); +} + static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn, int where, u8 byte_en, u32 *value) { u32 headers[TLP_HDR_SIZE]; - headers[0] = TLP_CFGRD_DW0(pcie, bus); - headers[1] = TLP_CFG_DW1(pcie, TLP_READ_TAG, byte_en); - headers[2] = TLP_CFG_DW2(bus, devfn, where); + get_tlp_header(pcie, bus, devfn, where, byte_en, true, + headers); - tlp_write_packet(pcie, headers, 0, false); + pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, 0, false); - return tlp_read_packet(pcie, value); + return pcie->pcie_data->ops->tlp_read_pkt(pcie, value); } static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn, @@ -230,17 +409,18 @@ static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn, u32 headers[TLP_HDR_SIZE]; int ret; - headers[0] = TLP_CFGWR_DW0(pcie, bus); - headers[1] = TLP_CFG_DW1(pcie, TLP_WRITE_TAG, byte_en); - headers[2] = TLP_CFG_DW2(bus, devfn, where); + get_tlp_header(pcie, bus, devfn, where, byte_en, false, + headers); /* check alignment to Qword */ if ((where & 0x7) == 0) - tlp_write_packet(pcie, headers, value, true); + pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, + value, true); else - tlp_write_packet(pcie, headers, value, false); + pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, + value, false); - ret = tlp_read_packet(pcie, NULL); + ret = pcie->pcie_data->ops->tlp_read_pkt(pcie, NULL); if (ret != PCIBIOS_SUCCESSFUL) return ret; @@ -254,6 +434,150 @@ static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn, return PCIBIOS_SUCCESSFUL; } +static int s10_rp_read_cfg(struct altera_pcie *pcie, int where, + int size, u32 *value) +{ + void __iomem *addr = S10_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + *value = readb(addr); + break; + case 2: + *value = readw(addr); + break; + default: + *value = readl(addr); + break; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int s10_rp_write_cfg(struct altera_pcie *pcie, u8 busno, + int where, int size, u32 value) +{ + void __iomem *addr = S10_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + writeb(value, addr); + break; + case 2: + writew(value, addr); + break; + default: + writel(value, addr); + break; + } + + /* + * Monitor changes to PCI_PRIMARY_BUS register on root port + * and update local copy of root bus number accordingly. + */ + if (busno == pcie->root_bus_nr && where == PCI_PRIMARY_BUS) + pcie->root_bus_nr = value & 0xff; + + return PCIBIOS_SUCCESSFUL; +} + +static int aglx_rp_read_cfg(struct altera_pcie *pcie, int where, + int size, u32 *value) +{ + void __iomem *addr = AGLX_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + *value = readb_relaxed(addr); + break; + case 2: + *value = readw_relaxed(addr); + break; + default: + *value = readl_relaxed(addr); + break; + } + + /* Interrupt PIN not programmed in hardware, set to INTA. */ + if (where == PCI_INTERRUPT_PIN && size == 1 && !(*value)) + *value = 0x01; + else if (where == PCI_INTERRUPT_LINE && !(*value & 0xff00)) + *value |= 0x0100; + + return PCIBIOS_SUCCESSFUL; +} + +static int aglx_rp_write_cfg(struct altera_pcie *pcie, u8 busno, + int where, int size, u32 value) +{ + void __iomem *addr = AGLX_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + writeb_relaxed(value, addr); + break; + case 2: + writew_relaxed(value, addr); + break; + default: + writel_relaxed(value, addr); + break; + } + + /* + * Monitor changes to PCI_PRIMARY_BUS register on Root Port + * and update local copy of root bus number accordingly. + */ + if (busno == pcie->root_bus_nr && where == PCI_PRIMARY_BUS) + pcie->root_bus_nr = value & 0xff; + + return PCIBIOS_SUCCESSFUL; +} + +static int aglx_ep_write_cfg(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 value) +{ + cra_writel(pcie, ((busno << 8) | devfn), AGLX_BDF_REG); + if (busno > AGLX_RP_SECONDARY(pcie)) + where |= FIELD_PREP(AGLX_CFG_TARGET, AGLX_CFG_TARGET_TYPE1); + + switch (size) { + case 1: + cra_writeb(pcie, value, where); + break; + case 2: + cra_writew(pcie, value, where); + break; + default: + cra_writel(pcie, value, where); + break; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int aglx_ep_read_cfg(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 *value) +{ + cra_writel(pcie, ((busno << 8) | devfn), AGLX_BDF_REG); + if (busno > AGLX_RP_SECONDARY(pcie)) + where |= FIELD_PREP(AGLX_CFG_TARGET, AGLX_CFG_TARGET_TYPE1); + + switch (size) { + case 1: + *value = cra_readb(pcie, where); + break; + case 2: + *value = cra_readw(pcie, where); + break; + default: + *value = cra_readl(pcie, where); + break; + } + + return PCIBIOS_SUCCESSFUL; +} + static int _altera_pcie_cfg_read(struct altera_pcie *pcie, u8 busno, unsigned int devfn, int where, int size, u32 *value) @@ -262,6 +586,14 @@ static int _altera_pcie_cfg_read(struct altera_pcie *pcie, u8 busno, u32 data; u8 byte_en; + if (busno == pcie->root_bus_nr && pcie->pcie_data->ops->rp_read_cfg) + return pcie->pcie_data->ops->rp_read_cfg(pcie, where, + size, value); + + if (pcie->pcie_data->ops->ep_read_cfg) + return pcie->pcie_data->ops->ep_read_cfg(pcie, busno, devfn, + where, size, value); + switch (size) { case 1: byte_en = 1 << (where & 3); @@ -302,6 +634,14 @@ static int _altera_pcie_cfg_write(struct altera_pcie *pcie, u8 busno, u32 shift = 8 * (where & 3); u8 byte_en; + if (busno == pcie->root_bus_nr && pcie->pcie_data->ops->rp_write_cfg) + return pcie->pcie_data->ops->rp_write_cfg(pcie, busno, + where, size, value); + + if (pcie->pcie_data->ops->ep_write_cfg) + return pcie->pcie_data->ops->ep_write_cfg(pcie, busno, devfn, + where, size, value); + switch (size) { case 1: data32 = (value & 0xff) << shift; @@ -329,10 +669,8 @@ static int altera_pcie_cfg_read(struct pci_bus *bus, unsigned int devfn, if (altera_pcie_hide_rc_bar(bus, devfn, where)) return PCIBIOS_BAD_REGISTER_NUMBER; - if (!altera_pcie_valid_device(pcie, bus, PCI_SLOT(devfn))) { - *value = 0xffffffff; + if (!altera_pcie_valid_device(pcie, bus, PCI_SLOT(devfn))) return PCIBIOS_DEVICE_NOT_FOUND; - } return _altera_pcie_cfg_read(pcie, bus->number, devfn, where, size, value); @@ -365,7 +703,8 @@ static int altera_read_cap_word(struct altera_pcie *pcie, u8 busno, int ret; ret = _altera_pcie_cfg_read(pcie, busno, devfn, - PCIE_CAP_OFFSET + offset, sizeof(*value), + pcie->pcie_data->cap_offset + offset, + sizeof(*value), &data); *value = data; return ret; @@ -375,7 +714,8 @@ static int altera_write_cap_word(struct altera_pcie *pcie, u8 busno, unsigned int devfn, int offset, u16 value) { return _altera_pcie_cfg_write(pcie, busno, devfn, - PCIE_CAP_OFFSET + offset, sizeof(value), + pcie->pcie_data->cap_offset + offset, + sizeof(value), value); } @@ -403,7 +743,7 @@ static void altera_wait_link_retrain(struct altera_pcie *pcie) /* Wait for link is up */ start_jiffies = jiffies; for (;;) { - if (altera_pcie_link_up(pcie)) + if (pcie->pcie_data->ops->get_link_status(pcie)) break; if (time_after(jiffies, start_jiffies + LINK_UP_TIMEOUT)) { @@ -418,7 +758,7 @@ static void altera_pcie_retrain(struct altera_pcie *pcie) { u16 linkcap, linkstat, linkctl; - if (!altera_pcie_link_up(pcie)) + if (!pcie->pcie_data->ops->get_link_status(pcie)) return; /* @@ -463,7 +803,7 @@ static void altera_pcie_isr(struct irq_desc *desc) struct device *dev; unsigned long status; u32 bit; - u32 virq; + int ret; chained_irq_enter(chip, desc); pcie = irq_desc_get_handler_data(desc); @@ -475,57 +815,46 @@ static void altera_pcie_isr(struct irq_desc *desc) /* clear interrupts */ cra_writel(pcie, 1 << bit, P2A_INT_STATUS); - virq = irq_find_mapping(pcie->irq_domain, bit); - if (virq) - generic_handle_irq(virq); - else - dev_err(dev, "unexpected IRQ, INT%d\n", bit); + ret = generic_handle_domain_irq(pcie->irq_domain, bit); + if (ret) + dev_err_ratelimited(dev, "unexpected IRQ, INT%d\n", bit); } } - chained_irq_exit(chip, desc); } -static int altera_pcie_parse_request_of_pci_ranges(struct altera_pcie *pcie) +static void aglx_isr(struct irq_desc *desc) { - int err, res_valid = 0; - struct device *dev = &pcie->pdev->dev; - struct resource_entry *win; + struct irq_chip *chip = irq_desc_get_chip(desc); + struct altera_pcie *pcie; + struct device *dev; + u32 status; + int ret; - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, - &pcie->resources, NULL); - if (err) - return err; + chained_irq_enter(chip, desc); + pcie = irq_desc_get_handler_data(desc); + dev = &pcie->pdev->dev; - err = devm_request_pci_bus_resources(dev, &pcie->resources); - if (err) - goto out_release_res; + status = readl(pcie->hip_base + pcie->pcie_data->port_conf_offset + + pcie->pcie_data->port_irq_status_offset); - resource_list_for_each_entry(win, &pcie->resources) { - struct resource *res = win->res; + if (status & CFG_AER) { + writel(CFG_AER, (pcie->hip_base + pcie->pcie_data->port_conf_offset + + pcie->pcie_data->port_irq_status_offset)); - if (resource_type(res) == IORESOURCE_MEM) - res_valid |= !(res->flags & IORESOURCE_PREFETCH); + ret = generic_handle_domain_irq(pcie->irq_domain, 0); + if (ret) + dev_err_ratelimited(dev, "unexpected IRQ %d\n", pcie->irq); } - - if (res_valid) - return 0; - - dev_err(dev, "non-prefetchable memory resource required\n"); - err = -EINVAL; - -out_release_res: - pci_free_resource_list(&pcie->resources); - return err; + chained_irq_exit(chip, desc); } static int altera_pcie_init_irq_domain(struct altera_pcie *pcie) { struct device *dev = &pcie->pdev->dev; - struct device_node *node = dev->of_node; /* Setup INTx */ - pcie->irq_domain = irq_domain_add_linear(node, PCI_NUM_INTX, + pcie->irq_domain = irq_domain_create_linear(dev_fwnode(dev), PCI_NUM_INTX, &intx_domain_ops, pcie); if (!pcie->irq_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); @@ -535,25 +864,34 @@ static int altera_pcie_init_irq_domain(struct altera_pcie *pcie) return 0; } +static void altera_pcie_irq_teardown(struct altera_pcie *pcie) +{ + irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); + irq_domain_remove(pcie->irq_domain); + irq_dispose_mapping(pcie->irq); +} + static int altera_pcie_parse_dt(struct altera_pcie *pcie) { - struct device *dev = &pcie->pdev->dev; struct platform_device *pdev = pcie->pdev; - struct resource *cra; - cra = platform_get_resource_byname(pdev, IORESOURCE_MEM, "Cra"); - pcie->cra_base = devm_ioremap_resource(dev, cra); + pcie->cra_base = devm_platform_ioremap_resource_byname(pdev, "Cra"); if (IS_ERR(pcie->cra_base)) return PTR_ERR(pcie->cra_base); + if (pcie->pcie_data->version == ALTERA_PCIE_V2 || + pcie->pcie_data->version == ALTERA_PCIE_V3) { + pcie->hip_base = devm_platform_ioremap_resource_byname(pdev, "Hip"); + if (IS_ERR(pcie->hip_base)) + return PTR_ERR(pcie->hip_base); + } + /* setup IRQ */ pcie->irq = platform_get_irq(pdev, 0); - if (pcie->irq < 0) { - dev_err(dev, "failed to get IRQ: %d\n", pcie->irq); + if (pcie->irq < 0) return pcie->irq; - } - irq_set_chained_handler_and_data(pcie->irq, altera_pcie_isr, pcie); + irq_set_chained_handler_and_data(pcie->irq, pcie->pcie_data->ops->rp_isr, pcie); return 0; } @@ -562,14 +900,99 @@ static void altera_pcie_host_init(struct altera_pcie *pcie) altera_pcie_retrain(pcie); } +static const struct altera_pcie_ops altera_pcie_ops_1_0 = { + .tlp_read_pkt = tlp_read_packet, + .tlp_write_pkt = tlp_write_packet, + .get_link_status = altera_pcie_link_up, + .rp_isr = altera_pcie_isr, +}; + +static const struct altera_pcie_ops altera_pcie_ops_2_0 = { + .tlp_read_pkt = s10_tlp_read_packet, + .tlp_write_pkt = s10_tlp_write_packet, + .get_link_status = s10_altera_pcie_link_up, + .rp_read_cfg = s10_rp_read_cfg, + .rp_write_cfg = s10_rp_write_cfg, + .rp_isr = altera_pcie_isr, +}; + +static const struct altera_pcie_ops altera_pcie_ops_3_0 = { + .rp_read_cfg = aglx_rp_read_cfg, + .rp_write_cfg = aglx_rp_write_cfg, + .get_link_status = aglx_altera_pcie_link_up, + .ep_read_cfg = aglx_ep_read_cfg, + .ep_write_cfg = aglx_ep_write_cfg, + .rp_isr = aglx_isr, +}; + +static const struct altera_pcie_data altera_pcie_1_0_data = { + .ops = &altera_pcie_ops_1_0, + .cap_offset = 0x80, + .version = ALTERA_PCIE_V1, + .cfgrd0 = TLP_FMTTYPE_CFGRD0, + .cfgrd1 = TLP_FMTTYPE_CFGRD1, + .cfgwr0 = TLP_FMTTYPE_CFGWR0, + .cfgwr1 = TLP_FMTTYPE_CFGWR1, +}; + +static const struct altera_pcie_data altera_pcie_2_0_data = { + .ops = &altera_pcie_ops_2_0, + .version = ALTERA_PCIE_V2, + .cap_offset = 0x70, + .cfgrd0 = S10_TLP_FMTTYPE_CFGRD0, + .cfgrd1 = S10_TLP_FMTTYPE_CFGRD1, + .cfgwr0 = S10_TLP_FMTTYPE_CFGWR0, + .cfgwr1 = S10_TLP_FMTTYPE_CFGWR1, +}; + +static const struct altera_pcie_data altera_pcie_3_0_f_tile_data = { + .ops = &altera_pcie_ops_3_0, + .version = ALTERA_PCIE_V3, + .cap_offset = 0x70, + .port_conf_offset = 0x14000, + .port_irq_status_offset = AGLX_ROOT_PORT_IRQ_STATUS, + .port_irq_enable_offset = AGLX_ROOT_PORT_IRQ_ENABLE, +}; + +static const struct altera_pcie_data altera_pcie_3_0_p_tile_data = { + .ops = &altera_pcie_ops_3_0, + .version = ALTERA_PCIE_V3, + .cap_offset = 0x70, + .port_conf_offset = 0x104000, + .port_irq_status_offset = AGLX_ROOT_PORT_IRQ_STATUS, + .port_irq_enable_offset = AGLX_ROOT_PORT_IRQ_ENABLE, +}; + +static const struct altera_pcie_data altera_pcie_3_0_r_tile_data = { + .ops = &altera_pcie_ops_3_0, + .version = ALTERA_PCIE_V3, + .cap_offset = 0x70, + .port_conf_offset = 0x1300, + .port_irq_status_offset = 0x0, + .port_irq_enable_offset = 0x4, +}; + +static const struct of_device_id altera_pcie_of_match[] = { + {.compatible = "altr,pcie-root-port-1.0", + .data = &altera_pcie_1_0_data }, + {.compatible = "altr,pcie-root-port-2.0", + .data = &altera_pcie_2_0_data }, + {.compatible = "altr,pcie-root-port-3.0-f-tile", + .data = &altera_pcie_3_0_f_tile_data }, + {.compatible = "altr,pcie-root-port-3.0-p-tile", + .data = &altera_pcie_3_0_p_tile_data }, + {.compatible = "altr,pcie-root-port-3.0-r-tile", + .data = &altera_pcie_3_0_r_tile_data }, + {}, +}; + static int altera_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct altera_pcie *pcie; - struct pci_bus *bus; - struct pci_bus *child; struct pci_host_bridge *bridge; int ret; + const struct altera_pcie_data *data; bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); if (!bridge) @@ -577,18 +1000,17 @@ static int altera_pcie_probe(struct platform_device *pdev) pcie = pci_host_bridge_priv(bridge); pcie->pdev = pdev; + platform_set_drvdata(pdev, pcie); - ret = altera_pcie_parse_dt(pcie); - if (ret) { - dev_err(dev, "Parsing DT failed\n"); - return ret; - } + data = of_device_get_match_data(&pdev->dev); + if (!data) + return -ENODEV; - INIT_LIST_HEAD(&pcie->resources); + pcie->pcie_data = data; - ret = altera_pcie_parse_request_of_pci_ranges(pcie); + ret = altera_pcie_parse_dt(pcie); if (ret) { - dev_err(dev, "Failed add resources\n"); + dev_err(dev, "Parsing DT failed\n"); return ret; } @@ -598,48 +1020,46 @@ static int altera_pcie_probe(struct platform_device *pdev) return ret; } - /* clear all interrupts */ - cra_writel(pcie, P2A_INT_STS_ALL, P2A_INT_STATUS); - /* enable all interrupts */ - cra_writel(pcie, P2A_INT_ENA_ALL, P2A_INT_ENABLE); - altera_pcie_host_init(pcie); + if (pcie->pcie_data->version == ALTERA_PCIE_V1 || + pcie->pcie_data->version == ALTERA_PCIE_V2) { + /* clear all interrupts */ + cra_writel(pcie, P2A_INT_STS_ALL, P2A_INT_STATUS); + /* enable all interrupts */ + cra_writel(pcie, P2A_INT_ENA_ALL, P2A_INT_ENABLE); + altera_pcie_host_init(pcie); + } else if (pcie->pcie_data->version == ALTERA_PCIE_V3) { + writel(CFG_AER, + pcie->hip_base + pcie->pcie_data->port_conf_offset + + pcie->pcie_data->port_irq_enable_offset); + } - list_splice_init(&pcie->resources, &bridge->windows); - bridge->dev.parent = dev; bridge->sysdata = pcie; bridge->busnr = pcie->root_bus_nr; bridge->ops = &altera_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - - ret = pci_scan_root_bus_bridge(bridge); - if (ret < 0) - return ret; - - bus = bridge->bus; - pci_assign_unassigned_bus_resources(bus); + return pci_host_probe(bridge); +} - /* Configure PCI Express setting. */ - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); +static void altera_pcie_remove(struct platform_device *pdev) +{ + struct altera_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); - pci_bus_add_devices(bus); - return ret; + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + altera_pcie_irq_teardown(pcie); } -static const struct of_device_id altera_pcie_of_match[] = { - { .compatible = "altr,pcie-root-port-1.0", }, - {}, -}; - static struct platform_driver altera_pcie_driver = { - .probe = altera_pcie_probe, + .probe = altera_pcie_probe, + .remove = altera_pcie_remove, .driver = { - .name = "altera-pcie", + .name = "altera-pcie", .of_match_table = altera_pcie_of_match, - .suppress_bind_attrs = true, }, }; -builtin_platform_driver(altera_pcie_driver); +MODULE_DEVICE_TABLE(of, altera_pcie_of_match); +module_platform_driver(altera_pcie_driver); +MODULE_DESCRIPTION("Altera PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c new file mode 100644 index 000000000000..2d92fc79f6dd --- /dev/null +++ b/drivers/pci/controller/pcie-apple.c @@ -0,0 +1,896 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host bridge driver for Apple system-on-chips. + * + * The HW is ECAM compliant, so once the controller is initialized, + * the driver mostly deals MSI mapping and handling of per-port + * interrupts (INTx, management and error signals). + * + * Initialization requires enabling power and clocks, along with a + * number of register pokes. + * + * Copyright (C) 2021 Alyssa Rosenzweig <alyssa@rosenzweig.io> + * Copyright (C) 2021 Google LLC + * Copyright (C) 2021 Corellium LLC + * Copyright (C) 2021 Mark Kettenis <kettenis@openbsd.org> + * + * Author: Alyssa Rosenzweig <alyssa@rosenzweig.io> + * Author: Marc Zyngier <maz@kernel.org> + */ + +#include <linux/bitfield.h> +#include <linux/gpio/consumer.h> +#include <linux/kernel.h> +#include <linux/iopoll.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> +#include <linux/irqdomain.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/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 +#define CORE_RC_PHYIF_STAT_REFCLK BIT(4) +#define CORE_RC_CTL 0x00050 +#define CORE_RC_CTL_RUN BIT(0) +#define CORE_RC_STAT 0x00058 +#define CORE_RC_STAT_READY BIT(0) +#define CORE_FABRIC_STAT 0x04000 +#define CORE_FABRIC_STAT_MASK 0x001F001F + +#define CORE_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) +#define PORT_INTSTAT 0x00100 +#define PORT_INT_TUNNEL_ERR 31 +#define PORT_INT_CPL_TIMEOUT 23 +#define PORT_INT_RID2SID_MAPERR 22 +#define PORT_INT_CPL_ABORT 21 +#define PORT_INT_MSI_BAD_DATA 19 +#define PORT_INT_MSI_ERR 18 +#define PORT_INT_REQADDR_GT32 17 +#define PORT_INT_AF_TIMEOUT 15 +#define PORT_INT_LINK_DOWN 14 +#define PORT_INT_LINK_UP 12 +#define PORT_INT_LINK_BWMGMT 11 +#define PORT_INT_AER_MASK (15 << 4) +#define PORT_INT_PORT_ERR 4 +#define PORT_INT_INTx(i) i +#define PORT_INT_INTx_MASK 15 +#define PORT_INTMSK 0x00104 +#define PORT_INTMSKSET 0x00108 +#define PORT_INTMSKCLR 0x0010c +#define PORT_MSICFG 0x00124 +#define PORT_MSICFG_EN BIT(0) +#define PORT_MSICFG_L2MSINUM_SHIFT 4 +#define PORT_MSIBASE 0x00128 +#define PORT_MSIBASE_1_SHIFT 16 +#define PORT_MSIADDR 0x00168 +#define PORT_LINKSTS 0x00208 +#define PORT_LINKSTS_UP BIT(0) +#define PORT_LINKSTS_BUSY BIT(2) +#define PORT_LINKCMDSTS 0x00210 +#define PORT_OUTS_NPREQS 0x00284 +#define PORT_OUTS_NPREQS_REQ BIT(24) +#define PORT_OUTS_NPREQS_CPL BIT(16) +#define PORT_RXWR_FIFO 0x00288 +#define PORT_RXWR_FIFO_HDR GENMASK(15, 10) +#define PORT_RXWR_FIFO_DATA GENMASK(9, 0) +#define PORT_RXRD_FIFO 0x0028C +#define PORT_RXRD_FIFO_REQ GENMASK(6, 0) +#define PORT_OUTS_CPLS 0x00290 +#define PORT_OUTS_CPLS_SHRD GENMASK(14, 8) +#define PORT_OUTS_CPLS_WAIT GENMASK(6, 0) +#define PORT_APPCLK 0x00800 +#define PORT_APPCLK_EN BIT(0) +#define PORT_APPCLK_CGDIS BIT(8) +#define PORT_STATUS 0x00804 +#define PORT_STATUS_READY BIT(0) +#define PORT_REFCLK 0x00810 +#define PORT_REFCLK_EN BIT(0) +#define PORT_REFCLK_CGDIS BIT(8) +#define PORT_PERST 0x00814 +#define PORT_PERST_OFF BIT(0) +#define PORT_RID2SID 0x00828 +#define PORT_RID2SID_VALID BIT(31) +#define PORT_RID2SID_SID_SHIFT 16 +#define PORT_RID2SID_BUS_SHIFT 8 +#define PORT_RID2SID_DEV_SHIFT 3 +#define PORT_RID2SID_FUNC_SHIFT 0 +#define PORT_OUTS_PREQS_HDR 0x00980 +#define PORT_OUTS_PREQS_HDR_MASK GENMASK(9, 0) +#define PORT_OUTS_PREQS_DATA 0x00984 +#define PORT_OUTS_PREQS_DATA_MASK GENMASK(15, 0) +#define PORT_TUNCTRL 0x00988 +#define PORT_TUNCTRL_PERST_ON BIT(0) +#define PORT_TUNCTRL_PERST_ACK_REQ BIT(1) +#define PORT_TUNSTAT 0x0098c +#define PORT_TUNSTAT_PERST_ON BIT(0) +#define PORT_TUNSTAT_PERST_ACK_PEND BIT(1) +#define PORT_PREFMEM_ENABLE 0x00994 + +/* 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 + * matches what MacOS does, and it is possible to use any other + * address (in the bottom 4GB, as the base register is only 32bit). + * However, it has to be excluded from the IOVA range, and the DART + * driver has to know about it. + */ +#define DOORBELL_ADDR CONFIG_PCIE_APPLE_MSI_DOORBELL_ADDR + +struct 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; + const struct hw_info *hw; + unsigned long *bitmap; + struct list_head ports; + struct completion event; + struct irq_fwspec fwspec; + u32 nvecs; +}; + +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; + unsigned long *sid_map; + int sid_map_sz; + int idx; +}; + +static void rmw_set(u32 set, void __iomem *addr) +{ + writel_relaxed(readl_relaxed(addr) | set, addr); +} + +static void rmw_clear(u32 clr, void __iomem *addr) +{ + writel_relaxed(readl_relaxed(addr) & ~clr, addr); +} + +static void apple_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + msg->address_hi = upper_32_bits(DOORBELL_ADDR); + msg->address_lo = lower_32_bits(DOORBELL_ADDR); + msg->data = data->hwirq; +} + +static struct irq_chip apple_msi_bottom_chip = { + .name = "MSI", + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_set_type = irq_chip_set_type_parent, + .irq_compose_msi_msg = apple_msi_compose_msg, +}; + +static int apple_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct apple_pcie *pcie = domain->host_data; + struct irq_fwspec fwspec = pcie->fwspec; + unsigned int i; + int ret, hwirq; + + mutex_lock(&pcie->lock); + + hwirq = bitmap_find_free_region(pcie->bitmap, pcie->nvecs, + order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); + + if (hwirq < 0) + return -ENOSPC; + + fwspec.param[fwspec.param_count - 2] += hwirq; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &fwspec); + if (ret) + return ret; + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, + &apple_msi_bottom_chip, pcie); + } + + return 0; +} + +static void apple_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct apple_pcie *pcie = domain->host_data; + + mutex_lock(&pcie->lock); + + bitmap_release_region(pcie->bitmap, d->hwirq, order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); +} + +static const struct irq_domain_ops apple_msi_domain_ops = { + .alloc = apple_msi_domain_alloc, + .free = apple_msi_domain_free, +}; + +static void apple_port_irq_mask(struct irq_data *data) +{ + struct apple_pcie_port *port = irq_data_get_irq_chip_data(data); + + 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); + + guard(raw_spinlock_irqsave)(&port->lock); + rmw_clear(BIT(data->hwirq), port->base + PORT_INTMSK); +} + +static bool hwirq_is_intx(unsigned int hwirq) +{ + return BIT(hwirq) & PORT_INT_INTx_MASK; +} + +static void apple_port_irq_ack(struct irq_data *data) +{ + struct apple_pcie_port *port = irq_data_get_irq_chip_data(data); + + if (!hwirq_is_intx(data->hwirq)) + writel_relaxed(BIT(data->hwirq), port->base + PORT_INTSTAT); +} + +static int apple_port_irq_set_type(struct irq_data *data, unsigned int type) +{ + /* + * It doesn't seem that there is any way to configure the + * trigger, so assume INTx have to be level (as per the spec), + * and the rest is edge (which looks likely). + */ + if (hwirq_is_intx(data->hwirq) ^ !!(type & IRQ_TYPE_LEVEL_MASK)) + return -EINVAL; + + irqd_set_trigger_type(data, type); + return 0; +} + +static struct irq_chip apple_port_irqchip = { + .name = "PCIe", + .irq_ack = apple_port_irq_ack, + .irq_mask = apple_port_irq_mask, + .irq_unmask = apple_port_irq_unmask, + .irq_set_type = apple_port_irq_set_type, +}; + +static int apple_port_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct apple_pcie_port *port = domain->host_data; + struct irq_fwspec *fwspec = args; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_flow_handler_t flow = handle_edge_irq; + unsigned int type = IRQ_TYPE_EDGE_RISING; + + if (hwirq_is_intx(fwspec->param[0] + i)) { + flow = handle_level_irq; + type = IRQ_TYPE_LEVEL_HIGH; + } + + irq_domain_set_info(domain, virq + i, fwspec->param[0] + i, + &apple_port_irqchip, port, flow, + NULL, NULL); + + irq_set_irq_type(virq + i, type); + } + + return 0; +} + +static void apple_port_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + int i; + + for (i = 0; i < nr_irqs; i++) { + struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); + + irq_set_handler(virq + i, NULL); + irq_domain_reset_irq_data(d); + } +} + +static const struct irq_domain_ops apple_port_irq_domain_ops = { + .translate = irq_domain_translate_onecell, + .alloc = apple_port_irq_domain_alloc, + .free = apple_port_irq_domain_free, +}; + +static void apple_port_irq_handler(struct irq_desc *desc) +{ + struct apple_pcie_port *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long stat; + int i; + + chained_irq_enter(chip, desc); + + stat = readl_relaxed(port->base + PORT_INTSTAT); + + for_each_set_bit(i, &stat, 32) + generic_handle_domain_irq(port->domain, i); + + chained_irq_exit(chip, desc); +} + +static int apple_pcie_port_setup_irq(struct apple_pcie_port *port) +{ + struct fwnode_handle *fwnode = &port->np->fwnode; + 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)), + port->idx); + if (!irq) + return -ENXIO; + + port->domain = irq_domain_create_linear(fwnode, 32, + &apple_port_irq_domain_ops, + port); + if (!port->domain) + return -ENOMEM; + + /* Disable all interrupts */ + writel_relaxed(~0, port->base + PORT_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 + 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 */ + 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; +} + +static irqreturn_t apple_pcie_port_irq(int irq, void *data) +{ + struct apple_pcie_port *port = data; + unsigned int hwirq = irq_domain_get_irq_data(port->domain, irq)->hwirq; + + switch (hwirq) { + case PORT_INT_LINK_UP: + dev_info_ratelimited(port->pcie->dev, "Link up on %pOF\n", + port->np); + complete_all(&port->pcie->event); + break; + case PORT_INT_LINK_DOWN: + dev_info_ratelimited(port->pcie->dev, "Link down on %pOF\n", + port->np); + break; + default: + return IRQ_NONE; + } + + return IRQ_HANDLED; +} + +static int apple_pcie_port_register_irqs(struct apple_pcie_port *port) +{ + static struct { + unsigned int hwirq; + const char *name; + } port_irqs[] = { + { PORT_INT_LINK_UP, "Link up", }, + { PORT_INT_LINK_DOWN, "Link down", }, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(port_irqs); i++) { + struct irq_fwspec fwspec = { + .fwnode = &port->np->fwnode, + .param_count = 1, + .param = { + [0] = port_irqs[i].hwirq, + }, + }; + unsigned int irq; + int ret; + + irq = irq_domain_alloc_irqs(port->domain, 1, NUMA_NO_NODE, + &fwspec); + if (WARN_ON(!irq)) + continue; + + ret = request_irq(irq, apple_pcie_port_irq, 0, + port_irqs[i].name, port); + WARN_ON(ret); + } + + return 0; +} + +static int apple_pcie_setup_refclk(struct apple_pcie *pcie, + struct apple_pcie_port *port) +{ + u32 stat; + int res; + + if (pcie->hw->phy_lane_ctl) + rmw_set(PHY_LANE_CTL_CFGACC, port->phy + pcie->hw->phy_lane_ctl); + + rmw_set(PHY_LANE_CFG_REFCLK0REQ, port->phy + PHY_LANE_CFG); + + 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(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; + + if (pcie->hw->phy_lane_ctl) + rmw_clear(PHY_LANE_CTL_CFGACC, port->phy + pcie->hw->phy_lane_ctl); + + rmw_set(PHY_LANE_CFG_REFCLKEN, port->phy + PHY_LANE_CFG); + + 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_rid2sid_addr(port, idx)); + /* Read back to ensure completion of the write */ + return readl_relaxed(port_rid2sid_addr(port, idx)); +} + +static int apple_pcie_setup_port(struct apple_pcie *pcie, + struct device_node *np) +{ + struct platform_device *platform = to_platform_device(pcie->dev); + struct apple_pcie_port *port; + struct gpio_desc *reset; + struct resource *res; + char name[16]; + u32 stat, idx; + int ret, i; + + reset = devm_fwnode_gpiod_get(pcie->dev, of_fwnode_handle(np), "reset", + GPIOD_OUT_LOW, "PERST#"); + if (IS_ERR(reset)) + return PTR_ERR(reset); + + port = devm_kzalloc(pcie->dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + 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; + + /* Use the first reg entry to work out the port index */ + port->idx = idx >> 11; + port->pcie = pcie; + port->np = np; + + 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_cansleep(reset, 1); + + ret = apple_pcie_setup_refclk(pcie, port); + if (ret < 0) + return ret; + + /* The minimal Tperst-clk value is 100us (PCIe CEM r5.0, 2.9.2) */ + usleep_range(100, 200); + + /* Deassert PERST# */ + rmw_set(PORT_PERST_OFF, port->base + pcie->hw->port_perst); + gpiod_set_value_cansleep(reset, 0); + + /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ + msleep(100); + + ret = readl_relaxed_poll_timeout(port->base + PORT_STATUS, stat, + stat & PORT_STATUS_READY, 100, 250000); + if (ret < 0) { + dev_err(pcie->dev, "port %pOF ready wait timeout\n", np); + return ret; + } + + 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); + if (ret) + return ret; + + /* Reset all RID/SID mappings, and check for RAZ/WI registers */ + 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); + } + + dev_dbg(pcie->dev, "%pOF: %d RID/SID mapping entries\n", np, i); + + port->sid_map_sz = i; + + list_add_tail(&port->entry, &pcie->ports); + init_completion(&pcie->event); + + /* 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); + + writel_relaxed(PORT_LTSSMCTL_START, port->base + PORT_LTSSMCTL); + + if (!wait_for_completion_timeout(&pcie->event, HZ / 10)) + dev_warn(pcie->dev, "%pOF link didn't come up\n", np); + + return 0; +} + +static 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 = {}; + int ret; + + ret = of_parse_phandle_with_args(to_of_node(fwnode), "msi-ranges", + "#interrupt-cells", 0, &args); + if (ret) + return ret; + + ret = of_property_read_u32_index(to_of_node(fwnode), "msi-ranges", + args.args_count + 1, &pcie->nvecs); + if (ret) + return ret; + + of_phandle_args_to_fwspec(args.np, args.args, args.args_count, + &pcie->fwspec); + + pcie->bitmap = devm_bitmap_zalloc(pcie->dev, pcie->nvecs, GFP_KERNEL); + if (!pcie->bitmap) + return -ENOMEM; + + 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; + } + + if (!msi_create_parent_irq_domain(&info, &apple_msi_parent_ops)) { + dev_err(pcie->dev, "failed to create IRQ domain\n"); + 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; + 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); + + /* If finding the port itself, nothing to do */ + if (WARN_ON(!port_pdev) || pdev == port_pdev) + return NULL; + + list_for_each_entry(port, &pcie->ports, entry) { + if (port->idx == PCI_SLOT(port_pdev->devfn)) + return port; + } + + return NULL; +} + +static int apple_pcie_enable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) +{ + u32 sid, rid = pci_dev_id(pdev); + struct apple_pcie_port *port; + int idx, err; + + port = apple_pcie_get_port(pdev); + if (!port) + return 0; + + dev_dbg(&pdev->dev, "added to bus %s, index %d\n", + pci_name(pdev->bus->self), port->idx); + + err = of_map_id(port->pcie->dev->of_node, rid, "iommu-map", + "iommu-map-mask", NULL, &sid); + if (err) + return err; + + mutex_lock(&port->pcie->lock); + + idx = bitmap_find_free_region(port->sid_map, port->sid_map_sz, 0); + if (idx >= 0) { + apple_pcie_rid2sid_write(port, idx, + PORT_RID2SID_VALID | + (sid << PORT_RID2SID_SID_SHIFT) | rid); + + dev_dbg(&pdev->dev, "mapping RID%x to SID%x (index %d)\n", + rid, sid, idx); + } + + mutex_unlock(&port->pcie->lock); + + return idx >= 0 ? 0 : -ENOSPC; +} + +static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) +{ + struct apple_pcie_port *port; + u32 rid = pci_dev_id(pdev); + int idx; + + port = apple_pcie_get_port(pdev); + if (!port) + return; + + mutex_lock(&port->pcie->lock); + + for_each_set_bit(idx, port->sid_map, port->sid_map_sz) { + u32 val; + + val = readl_relaxed(port_rid2sid_addr(port, idx)); + if ((val & 0xffff) == rid) { + apple_pcie_rid2sid_write(port, idx, 0); + bitmap_release_region(port->sid_map, idx, 0); + dev_dbg(&pdev->dev, "Released %x (%d)\n", val, idx); + break; + } + } + + mutex_unlock(&port->pcie->lock); +} + +static int apple_pcie_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct apple_pcie *pcie; + int ret; + + pcie = apple_pcie_lookup(dev); + if (WARN_ON(!pcie)) + return -ENOENT; + + for_each_available_child_of_node_scoped(dev->of_node, of_port) { + ret = apple_pcie_setup_port(pcie, of_port); + if (ret) { + dev_err(dev, "Port %pOF setup fail: %d\n", of_port, ret); + return ret; + } + } + + return 0; +} + +static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = { + .init = apple_pcie_init, + .enable_device = apple_pcie_enable_device, + .disable_device = apple_pcie_disable_device, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static int apple_pcie_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,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 = apple_pcie_probe, + .driver = { + .name = "pcie-apple", + .of_match_table = apple_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; +module_platform_driver(apple_pcie_driver); + +MODULE_DESCRIPTION("Apple PCIe host bridge driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c new file mode 100644 index 000000000000..062f55690012 --- /dev/null +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -0,0 +1,2211 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (C) 2009 - 2019 Broadcom */ + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/compiler.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/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> +#include <linux/regulator/consumer.h> +#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" + +/* BRCM_PCIE_CAP_REGS - Offset for the mandatory capability config regs */ +#define BRCM_PCIE_CAP_REGS 0x00ac + +/* Broadcom STB PCIe Register Offsets */ +#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1 0x0188 +#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK 0xc +#define PCIE_RC_CFG_VENDOR_SPECIFIC_REG1_LITTLE_ENDIAN 0x0 + +#define PCIE_RC_CFG_PRIV1_ID_VAL3 0x043c +#define PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK 0xffffff + +#define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY 0x04dc +#define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_MAX_LINK_WIDTH_MASK 0x1f0 + +#define PCIE_RC_CFG_PRIV1_ROOT_CAP 0x4f8 +#define PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK 0xf8 + +#define PCIE_RC_DL_MDIO_ADDR 0x1100 +#define PCIE_RC_DL_MDIO_WR_DATA 0x1104 +#define PCIE_RC_DL_MDIO_RD_DATA 0x1108 + +#define PCIE_RC_PL_REG_PHY_CTL_1 0x1804 +#define PCIE_RC_PL_REG_PHY_CTL_1_REG_P2_POWERDOWN_ENA_NOSYNC_MASK 0x8 + +#define PCIE_RC_PL_PHY_CTL_15 0x184c +#define PCIE_RC_PL_PHY_CTL_15_DIS_PLL_PD_MASK 0x400000 +#define PCIE_RC_PL_PHY_CTL_15_PM_CLK_PERIOD_MASK 0xff + +#define PCIE_MISC_MISC_CTRL 0x4008 +#define PCIE_MISC_MISC_CTRL_PCIE_RCB_64B_MODE_MASK 0x80 +#define PCIE_MISC_MISC_CTRL_PCIE_RCB_MPS_MODE_MASK 0x400 +#define PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_MASK 0x1000 +#define PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_MASK 0x2000 +#define PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_MASK 0x300000 + +#define PCIE_MISC_MISC_CTRL_SCB0_SIZE_MASK 0xf8000000 +#define PCIE_MISC_MISC_CTRL_SCB1_SIZE_MASK 0x07c00000 +#define PCIE_MISC_MISC_CTRL_SCB2_SIZE_MASK 0x0000001f +#define SCB_SIZE_MASK(x) PCIE_MISC_MISC_CTRL_SCB ## x ## _SIZE_MASK + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO 0x400c +#define PCIE_MEM_WIN0_LO(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO + ((win) * 8) + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI 0x4010 +#define PCIE_MEM_WIN0_HI(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI + ((win) * 8) + +/* + * NOTE: You may see the term "BAR" in a number of register names used by + * this driver. The term is an artifact of when the HW core was an + * endpoint device (EP). Now it is a root complex (RC) and anywhere a + * register has the term "BAR" it is related to an inbound window. + */ + +#define PCIE_BRCM_MAX_INBOUND_WINS 16 +#define PCIE_MISC_RC_BAR1_CONFIG_LO 0x402c +#define PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK 0x1f + +#define PCIE_MISC_RC_BAR4_CONFIG_LO 0x40d4 + + +#define PCIE_MISC_MSI_BAR_CONFIG_LO 0x4044 +#define PCIE_MISC_MSI_BAR_CONFIG_HI 0x4048 + +#define PCIE_MISC_MSI_DATA_CONFIG 0x404c +#define PCIE_MISC_MSI_DATA_CONFIG_VAL_32 0xffe06540 +#define PCIE_MISC_MSI_DATA_CONFIG_VAL_8 0xfff86540 + +#define PCIE_MISC_PCIE_CTRL 0x4064 +#define PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK 0x1 +#define PCIE_MISC_PCIE_CTRL_PCIE_PERSTB_MASK 0x4 + +#define PCIE_MISC_PCIE_STATUS 0x4068 +#define PCIE_MISC_PCIE_STATUS_PCIE_PORT_MASK 0x80 +#define PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_MASK 0x20 +#define PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_MASK 0x10 +#define PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK 0x40 + +#define PCIE_MISC_REVISION 0x406c +#define BRCM_PCIE_HW_REV_33 0x0303 +#define BRCM_PCIE_HW_REV_3_20 0x0320 + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT 0x4070 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_MASK 0xfff00000 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK 0xfff0 +#define PCIE_MEM_WIN0_BASE_LIMIT(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT + ((win) * 4) + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI 0x4080 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_MASK 0xff +#define PCIE_MEM_WIN0_BASE_HI(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI + ((win) * 8) + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI 0x4084 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_MASK 0xff +#define PCIE_MEM_WIN0_LIMIT_HI(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI + ((win) * 8) + +#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK 0x2 +#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK 0x200000 +#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK 0x08000000 +#define PCIE_BMIPS_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK 0x00800000 +#define PCIE_CLKREQ_MASK \ + (PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK | \ + PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK) + +#define PCIE_MISC_UBUS_BAR1_CONFIG_REMAP 0x40ac +#define PCIE_MISC_UBUS_BAR1_CONFIG_REMAP_ACCESS_EN_MASK BIT(0) +#define PCIE_MISC_UBUS_BAR4_CONFIG_REMAP 0x410c + +#define PCIE_MSI_INTR2_BASE 0x4500 + +/* Offsets from INTR2_CPU and MSI_INTR2 BASE offsets */ +#define MSI_INT_STATUS 0x0 +#define MSI_INT_CLR 0x8 +#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 RGR1_SW_INIT_1_INIT_GENERIC_MASK 0x2 +#define RGR1_SW_INIT_1_INIT_GENERIC_SHIFT 0x1 +#define RGR1_SW_INIT_1_INIT_7278_MASK 0x1 +#define RGR1_SW_INIT_1_INIT_7278_SHIFT 0x0 + +/* PCIe parameters */ +#define BRCM_NUM_PCIE_OUT_WINS 0x4 +#define BRCM_INT_PCI_MSI_NR 32 +#define BRCM_INT_PCI_MSI_LEGACY_NR 8 +#define BRCM_INT_PCI_MSI_SHIFT 0 +#define BRCM_INT_PCI_MSI_MASK GENMASK(BRCM_INT_PCI_MSI_NR - 1, 0) +#define BRCM_INT_PCI_MSI_LEGACY_MASK GENMASK(31, \ + 32 - BRCM_INT_PCI_MSI_LEGACY_NR) + +/* MSI target addresses */ +#define BRCM_MSI_TARGET_ADDR_LT_4GB 0x0fffffffcULL +#define BRCM_MSI_TARGET_ADDR_GT_4GB 0xffffffffcULL + +/* MDIO registers */ +#define MDIO_PORT0 0x0 +#define MDIO_DATA_MASK 0x7fffffff +#define MDIO_PORT_MASK 0xf0000 +#define MDIO_PORT_EXT_MASK 0x200000 +#define MDIO_REGAD_MASK 0xffff +#define MDIO_CMD_MASK 0x00100000 +#define MDIO_CMD_READ 0x1 +#define MDIO_CMD_WRITE 0x0 +#define MDIO_DATA_DONE_MASK 0x80000000 +#define MDIO_RD_DONE(x) (((x) & MDIO_DATA_DONE_MASK) ? 1 : 0) +#define MDIO_WT_DONE(x) (((x) & MDIO_DATA_DONE_MASK) ? 0 : 1) +#define SSC_REGS_ADDR 0x1100 +#define SET_ADDR_OFFSET 0x1f +#define SSC_CNTL_OFFSET 0x2 +#define SSC_CNTL_OVRD_EN_MASK 0x8000 +#define SSC_CNTL_OVRD_VAL_MASK 0x4000 +#define SSC_STATUS_OFFSET 0x1 +#define SSC_STATUS_SSC_MASK 0x400 +#define SSC_STATUS_PLL_LOCK_MASK 0x800 +#define PCIE_BRCM_MAX_MEMC 3 + +#define IDX_ADDR(pcie) ((pcie)->cfg->offsets[EXT_CFG_INDEX]) +#define DATA_ADDR(pcie) ((pcie)->cfg->offsets[EXT_CFG_DATA]) +#define PCIE_RGR1_SW_INIT_1(pcie) ((pcie)->cfg->offsets[RGR1_SW_INIT_1]) +#define HARD_DEBUG(pcie) ((pcie)->cfg->offsets[PCIE_HARD_DEBUG]) +#define INTR2_CPU_BASE(pcie) ((pcie)->cfg->offsets[PCIE_INTR2_CPU_BASE]) + +/* Rescal registers */ +#define PCIE_DVT_PMU_PCIE_PHY_CTRL 0xc700 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS 0x3 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_MASK 0x4 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_SHIFT 0x2 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_MASK 0x2 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_SHIFT 0x1 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_MASK 0x1 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_SHIFT 0x0 + +/* Forward declarations */ +struct brcm_pcie; + +enum { + RGR1_SW_INIT_1, + EXT_CFG_INDEX, + EXT_CFG_DATA, + PCIE_HARD_DEBUG, + PCIE_INTR2_CPU_BASE, +}; + +enum pcie_soc_base { + GENERIC, + BCM2711, + BCM4908, + BCM7278, + BCM7425, + BCM7435, + BCM7712, +}; + +struct inbound_win { + u64 size; + u64 pci_offset; + u64 cpu_addr; +}; + +/* + * The RESCAL block is tied to PCIe controller #1, regardless of the number of + * controllers, and turning off PCIe controller #1 prevents access to the RESCAL + * register blocks, therefore no other controller can access this register + * space, and depending upon the bus fabric we may get a timeout (UBUS/GISB), + * or a hang (AXI). + */ +#define CFG_QUIRK_AVOID_BRIDGE_SHUTDOWN BIT(0) + +struct pcie_cfg_data { + const int *offsets; + const enum pcie_soc_base soc_base; + const bool has_phy; + const u32 quirks; + u8 num_inbound_wins; + int (*perst_set)(struct brcm_pcie *pcie, u32 val); + int (*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val); + int (*post_setup)(struct brcm_pcie *pcie); + bool has_err_report; +}; + +struct subdev_regulators { + unsigned int num_supplies; + struct regulator_bulk_data supplies[]; +}; + +struct brcm_msi { + struct device *dev; + void __iomem *base; + struct device_node *np; + struct irq_domain *inner_domain; + struct mutex lock; /* guards the alloc/free operations */ + u64 target_addr; + int irq; + DECLARE_BITMAP(used, BRCM_INT_PCI_MSI_NR); + bool legacy; + /* Some chips have MSIs in bits [31..24] of a shared register. */ + int legacy_shift; + int nr; /* No. of MSI available, depends on chip */ + /* This is the base pointer for interrupt status/set/clr regs */ + void __iomem *intr_base; +}; + +/* Internal PCIe Host Controller Information.*/ +struct brcm_pcie { + struct device *dev; + void __iomem *base; + struct clk *clk; + struct device_node *np; + bool ssc; + int gen; + u64 msi_target_addr; + struct brcm_msi *msi; + struct reset_control *rescal; + struct reset_control *perst_reset; + struct reset_control *bridge_reset; + struct reset_control *swinit_reset; + int num_memc; + u64 memc_size[PCIE_BRCM_MAX_MEMC]; + u32 hw_rev; + 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) +{ + 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 + */ +static int brcm_pcie_encode_ibar_size(u64 size) +{ + int log2_in = ilog2(size); + + if (log2_in >= 12 && log2_in <= 15) + /* Covers 4KB to 32KB (inclusive) */ + return (log2_in - 12) + 0x1c; + else if (log2_in >= 16 && log2_in <= 36) + /* Covers 64KB to 64GB, (inclusive) */ + return log2_in - 15; + /* Something is awry so disable */ + return 0; +} + +static u32 brcm_pcie_mdio_form_pkt(int port, int regad, int cmd) +{ + u32 pkt = 0; + + pkt |= FIELD_PREP(MDIO_PORT_EXT_MASK, port >> 4); + pkt |= FIELD_PREP(MDIO_PORT_MASK, port); + pkt |= FIELD_PREP(MDIO_REGAD_MASK, regad); + pkt |= FIELD_PREP(MDIO_CMD_MASK, cmd); + + return pkt; +} + +/* negative return value indicates error */ +static int brcm_pcie_mdio_read(void __iomem *base, u8 port, u8 regad, u32 *val) +{ + u32 data; + int err; + + writel(brcm_pcie_mdio_form_pkt(port, regad, MDIO_CMD_READ), + base + PCIE_RC_DL_MDIO_ADDR); + readl(base + PCIE_RC_DL_MDIO_ADDR); + err = readl_poll_timeout_atomic(base + PCIE_RC_DL_MDIO_RD_DATA, data, + MDIO_RD_DONE(data), 10, 100); + *val = FIELD_GET(MDIO_DATA_MASK, data); + + return err; +} + +/* negative return value indicates error */ +static int brcm_pcie_mdio_write(void __iomem *base, u8 port, + u8 regad, u16 wrdata) +{ + u32 data; + int err; + + writel(brcm_pcie_mdio_form_pkt(port, regad, MDIO_CMD_WRITE), + base + PCIE_RC_DL_MDIO_ADDR); + readl(base + PCIE_RC_DL_MDIO_ADDR); + writel(MDIO_DATA_DONE_MASK | wrdata, base + PCIE_RC_DL_MDIO_WR_DATA); + + err = readl_poll_timeout_atomic(base + PCIE_RC_DL_MDIO_WR_DATA, data, + MDIO_WT_DONE(data), 10, 100); + return err; +} + +/* + * Configures device for Spread Spectrum Clocking (SSC) mode; a negative + * return value indicates error. + */ +static int brcm_pcie_set_ssc(struct brcm_pcie *pcie) +{ + int pll, ssc; + int ret; + u32 tmp; + + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, SET_ADDR_OFFSET, + SSC_REGS_ADDR); + if (ret < 0) + return ret; + + ret = brcm_pcie_mdio_read(pcie->base, MDIO_PORT0, + SSC_CNTL_OFFSET, &tmp); + if (ret < 0) + return ret; + + u32p_replace_bits(&tmp, 1, SSC_CNTL_OVRD_EN_MASK); + u32p_replace_bits(&tmp, 1, SSC_CNTL_OVRD_VAL_MASK); + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, + SSC_CNTL_OFFSET, tmp); + if (ret < 0) + return ret; + + usleep_range(1000, 2000); + ret = brcm_pcie_mdio_read(pcie->base, MDIO_PORT0, + SSC_STATUS_OFFSET, &tmp); + if (ret < 0) + return ret; + + ssc = FIELD_GET(SSC_STATUS_SSC_MASK, tmp); + pll = FIELD_GET(SSC_STATUS_PLL_LOCK_MASK, tmp); + + return ssc && pll ? 0 : -EIO; +} + +/* Limits operation to a specific generation (1, 2, or 3) */ +static void brcm_pcie_set_gen(struct brcm_pcie *pcie, int gen) +{ + u16 lnkctl2 = readw(pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2); + u32 lnkcap = readl(pcie->base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); + + u32p_replace_bits(&lnkcap, gen, PCI_EXP_LNKCAP_SLS); + writel(lnkcap, pcie->base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); + + u16p_replace_bits(&lnkctl2, gen, PCI_EXP_LNKCTL2_TLS); + writew(lnkctl2, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2); +} + +static void brcm_pcie_set_outbound_win(struct brcm_pcie *pcie, + u8 win, u64 cpu_addr, + u64 pcie_addr, u64 size) +{ + u32 cpu_addr_mb_high, limit_addr_mb_high; + phys_addr_t cpu_addr_mb, limit_addr_mb; + int high_addr_shift; + u32 tmp; + + /* Set the base of the pcie_addr window */ + writel(lower_32_bits(pcie_addr), pcie->base + PCIE_MEM_WIN0_LO(win)); + writel(upper_32_bits(pcie_addr), pcie->base + PCIE_MEM_WIN0_HI(win)); + + /* Write the addr base & limit lower bits (in MBs) */ + cpu_addr_mb = cpu_addr / SZ_1M; + limit_addr_mb = (cpu_addr + size - 1) / SZ_1M; + + tmp = readl(pcie->base + PCIE_MEM_WIN0_BASE_LIMIT(win)); + u32p_replace_bits(&tmp, cpu_addr_mb, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK); + u32p_replace_bits(&tmp, limit_addr_mb, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_MASK); + writel(tmp, pcie->base + PCIE_MEM_WIN0_BASE_LIMIT(win)); + + if (is_bmips(pcie)) + return; + + /* Write the cpu & limit addr upper bits */ + high_addr_shift = + HWEIGHT32(PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK); + + cpu_addr_mb_high = cpu_addr_mb >> high_addr_shift; + tmp = readl(pcie->base + PCIE_MEM_WIN0_BASE_HI(win)); + u32p_replace_bits(&tmp, cpu_addr_mb_high, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_MASK); + writel(tmp, pcie->base + PCIE_MEM_WIN0_BASE_HI(win)); + + limit_addr_mb_high = limit_addr_mb >> high_addr_shift; + tmp = readl(pcie->base + PCIE_MEM_WIN0_LIMIT_HI(win)); + u32p_replace_bits(&tmp, limit_addr_mb_high, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_MASK); + writel(tmp, pcie->base + PCIE_MEM_WIN0_LIMIT_HI(win)); +} + +#define BRCM_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) + +#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) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long status; + struct brcm_msi *msi; + struct device *dev; + u32 bit; + + chained_irq_enter(chip, desc); + msi = irq_desc_get_handler_data(desc); + dev = msi->dev; + + status = readl(msi->intr_base + MSI_INT_STATUS); + status >>= msi->legacy_shift; + + for_each_set_bit(bit, &status, msi->nr) { + int ret; + ret = generic_handle_domain_irq(msi->inner_domain, bit); + if (ret) + dev_dbg(dev, "unexpected MSI\n"); + } + + chained_irq_exit(chip, desc); +} + +static void brcm_msi_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct brcm_msi *msi = irq_data_get_irq_chip_data(data); + + msg->address_lo = lower_32_bits(msi->target_addr); + msg->address_hi = upper_32_bits(msi->target_addr); + msg->data = (0xffff & PCIE_MISC_MSI_DATA_CONFIG_VAL_32) | data->hwirq; +} + +static void brcm_msi_ack_irq(struct irq_data *data) +{ + struct brcm_msi *msi = irq_data_get_irq_chip_data(data); + const int shift_amt = data->hwirq + msi->legacy_shift; + + writel(1 << shift_amt, msi->intr_base + MSI_INT_CLR); +} + + +static struct irq_chip brcm_msi_bottom_irq_chip = { + .name = "BRCM STB MSI", + .irq_compose_msi_msg = brcm_msi_compose_msi_msg, + .irq_ack = brcm_msi_ack_irq, +}; + +static int brcm_msi_alloc(struct brcm_msi *msi, unsigned int nr_irqs) +{ + int hwirq; + + mutex_lock(&msi->lock); + hwirq = bitmap_find_free_region(msi->used, msi->nr, + order_base_2(nr_irqs)); + mutex_unlock(&msi->lock); + + return hwirq; +} + +static void brcm_msi_free(struct brcm_msi *msi, unsigned long hwirq, + unsigned int nr_irqs) +{ + mutex_lock(&msi->lock); + bitmap_release_region(msi->used, hwirq, order_base_2(nr_irqs)); + mutex_unlock(&msi->lock); +} + +static int brcm_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct brcm_msi *msi = domain->host_data; + int hwirq, i; + + hwirq = brcm_msi_alloc(msi, nr_irqs); + + if (hwirq < 0) + return hwirq; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, (irq_hw_number_t)hwirq + i, + &brcm_msi_bottom_irq_chip, domain->host_data, + handle_edge_irq, NULL, NULL); + return 0; +} + +static void brcm_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct brcm_msi *msi = irq_data_get_irq_chip_data(d); + + brcm_msi_free(msi, d->hwirq, nr_irqs); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = brcm_irq_domain_alloc, + .free = brcm_irq_domain_free, +}; + +static int brcm_allocate_domains(struct brcm_msi *msi) +{ + struct device *dev = msi->dev; + + struct irq_domain_info info = { + .fwnode = of_fwnode_handle(msi->np), + .ops = &msi_domain_ops, + .host_data = msi, + .size = msi->nr, + }; + + 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"); + return -ENOMEM; + } + + return 0; +} + +static void brcm_free_domains(struct brcm_msi *msi) +{ + irq_domain_remove(msi->inner_domain); +} + +static void brcm_msi_remove(struct brcm_pcie *pcie) +{ + struct brcm_msi *msi = pcie->msi; + + if (!msi) + return; + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); + brcm_free_domains(msi); +} + +static void brcm_msi_set_regs(struct brcm_msi *msi) +{ + u32 val = msi->legacy ? BRCM_INT_PCI_MSI_LEGACY_MASK : + BRCM_INT_PCI_MSI_MASK; + + writel(val, msi->intr_base + MSI_INT_MASK_CLR); + writel(val, msi->intr_base + MSI_INT_CLR); + + /* + * The 0 bit of PCIE_MISC_MSI_BAR_CONFIG_LO is repurposed to MSI + * enable, which we set to 1. + */ + writel(lower_32_bits(msi->target_addr) | 0x1, + msi->base + PCIE_MISC_MSI_BAR_CONFIG_LO); + writel(upper_32_bits(msi->target_addr), + msi->base + PCIE_MISC_MSI_BAR_CONFIG_HI); + + val = msi->legacy ? PCIE_MISC_MSI_DATA_CONFIG_VAL_8 : PCIE_MISC_MSI_DATA_CONFIG_VAL_32; + writel(val, msi->base + PCIE_MISC_MSI_DATA_CONFIG); +} + +static int brcm_pcie_enable_msi(struct brcm_pcie *pcie) +{ + struct brcm_msi *msi; + int irq, ret; + struct device *dev = pcie->dev; + + irq = irq_of_parse_and_map(dev->of_node, 1); + if (irq <= 0) { + dev_err(dev, "cannot map MSI interrupt\n"); + return -ENODEV; + } + + msi = devm_kzalloc(dev, sizeof(struct brcm_msi), GFP_KERNEL); + if (!msi) + return -ENOMEM; + + mutex_init(&msi->lock); + msi->dev = dev; + msi->base = pcie->base; + msi->np = pcie->np; + msi->target_addr = pcie->msi_target_addr; + msi->irq = irq; + msi->legacy = pcie->hw_rev < BRCM_PCIE_HW_REV_33; + + /* + * Sanity check to make sure that the 'used' bitmap in struct brcm_msi + * is large enough. + */ + BUILD_BUG_ON(BRCM_INT_PCI_MSI_LEGACY_NR > BRCM_INT_PCI_MSI_NR); + + if (msi->legacy) { + msi->intr_base = msi->base + INTR2_CPU_BASE(pcie); + msi->nr = BRCM_INT_PCI_MSI_LEGACY_NR; + msi->legacy_shift = 24; + } else { + msi->intr_base = msi->base + PCIE_MSI_INTR2_BASE; + msi->nr = BRCM_INT_PCI_MSI_NR; + msi->legacy_shift = 0; + } + + ret = brcm_allocate_domains(msi); + if (ret) + return ret; + + irq_set_chained_handler_and_data(msi->irq, brcm_pcie_msi_isr, msi); + + brcm_msi_set_regs(msi); + pcie->msi = msi; + + return 0; +} + +/* The controller is capable of serving in both RC and EP roles */ +static bool brcm_pcie_rc_mode(struct brcm_pcie *pcie) +{ + void __iomem *base = pcie->base; + u32 val = readl(base + PCIE_MISC_PCIE_STATUS); + + return !!FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_PORT_MASK, val); +} + +static bool brcm_pcie_link_up(struct brcm_pcie *pcie) +{ + u32 val = readl(pcie->base + PCIE_MISC_PCIE_STATUS); + u32 dla = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_MASK, val); + u32 plu = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_MASK, val); + + return dla && plu; +} + +static void __iomem *brcm_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct brcm_pcie *pcie = bus->sysdata; + void __iomem *base = pcie->base; + int idx; + + /* Accesses to the RC go right to the RC registers if !devfn */ + if (pci_is_root_bus(bus)) + return devfn ? NULL : base + PCIE_ECAM_REG(where); + + /* An access to our HW w/o link-up will cause a CPU Abort */ + if (!brcm_pcie_link_up(pcie)) + return NULL; + + /* For devices, write to the config space index register */ + idx = PCIE_ECAM_OFFSET(bus->number, devfn, 0); + writel(idx, base + IDX_ADDR(pcie)); + return base + DATA_ADDR(pcie) + PCIE_ECAM_REG(where); +} + +static void __iomem *brcm7425_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct brcm_pcie *pcie = bus->sysdata; + void __iomem *base = pcie->base; + int idx; + + /* Accesses to the RC go right to the RC registers if !devfn */ + if (pci_is_root_bus(bus)) + return devfn ? NULL : base + PCIE_ECAM_REG(where); + + /* An access to our HW w/o link-up will cause a CPU Abort */ + if (!brcm_pcie_link_up(pcie)) + return NULL; + + /* For devices, write to the config space index register */ + idx = PCIE_ECAM_OFFSET(bus->number, devfn, where); + writel(idx, base + IDX_ADDR(pcie)); + return base + DATA_ADDR(pcie); +} + +static int brcm_pcie_bridge_sw_init_set_generic(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp, mask = RGR1_SW_INIT_1_INIT_GENERIC_MASK; + u32 shift = RGR1_SW_INIT_1_INIT_GENERIC_SHIFT; + int ret = 0; + + if (pcie->bridge_reset) { + if (val) + ret = reset_control_assert(pcie->bridge_reset); + else + ret = reset_control_deassert(pcie->bridge_reset); + + if (ret) + dev_err(pcie->dev, "failed to %s 'bridge' reset, err=%d\n", + val ? "assert" : "deassert", ret); + + return ret; + } + + tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + tmp = (tmp & ~mask) | ((val << shift) & mask); + writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + + return ret; +} + +static int brcm_pcie_bridge_sw_init_set_7278(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp, mask = RGR1_SW_INIT_1_INIT_7278_MASK; + u32 shift = RGR1_SW_INIT_1_INIT_7278_SHIFT; + + tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + tmp = (tmp & ~mask) | ((val << shift) & mask); + writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + + return 0; +} + +static int brcm_pcie_perst_set_4908(struct brcm_pcie *pcie, u32 val) +{ + int ret; + + if (WARN_ONCE(!pcie->perst_reset, "missing PERST# reset controller\n")) + return -EINVAL; + + if (val) + ret = reset_control_assert(pcie->perst_reset); + else + ret = reset_control_deassert(pcie->perst_reset); + + if (ret) + dev_err(pcie->dev, "failed to %s 'perst' reset, err=%d\n", + val ? "assert" : "deassert", ret); + return ret; +} + +static int brcm_pcie_perst_set_7278(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp; + + /* Perst bit has moved and assert value is 0 */ + tmp = readl(pcie->base + PCIE_MISC_PCIE_CTRL); + u32p_replace_bits(&tmp, !val, PCIE_MISC_PCIE_CTRL_PCIE_PERSTB_MASK); + writel(tmp, pcie->base + PCIE_MISC_PCIE_CTRL); + + return 0; +} + +static int brcm_pcie_perst_set_generic(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp; + + tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + u32p_replace_bits(&tmp, val, PCIE_RGR1_SW_INIT_1_PERST_MASK); + writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + + return 0; +} + +static int brcm_pcie_post_setup_bcm2712(struct brcm_pcie *pcie) +{ + static const u16 data[] = { 0x50b9, 0xbda1, 0x0094, 0x97b4, 0x5030, + 0x5030, 0x0007 }; + static const u8 regs[] = { 0x16, 0x17, 0x18, 0x19, 0x1b, 0x1c, 0x1e }; + int ret, i; + u32 tmp; + + /* Allow a 54MHz (xosc) refclk source */ + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, SET_ADDR_OFFSET, 0x1600); + if (ret < 0) + return ret; + + for (i = 0; i < ARRAY_SIZE(regs); i++) { + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, regs[i], data[i]); + if (ret < 0) + return ret; + } + + usleep_range(100, 200); + + /* + * Set L1SS sub-state timers to avoid lengthy state transitions, + * PM clock period is 18.52ns (1/54MHz, round down). + */ + tmp = readl(pcie->base + PCIE_RC_PL_PHY_CTL_15); + tmp &= ~PCIE_RC_PL_PHY_CTL_15_PM_CLK_PERIOD_MASK; + tmp |= 0x12; + writel(tmp, pcie->base + PCIE_RC_PL_PHY_CTL_15); + + return 0; +} + +static void add_inbound_win(struct inbound_win *b, u8 *count, u64 size, + u64 cpu_addr, u64 pci_offset) +{ + b->size = size; + b->cpu_addr = cpu_addr; + b->pci_offset = pci_offset; + (*count)++; +} + +static int brcm_pcie_get_inbound_wins(struct brcm_pcie *pcie, + struct inbound_win inbound_wins[]) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + u64 pci_offset, cpu_addr, size = 0, tot_size = 0; + struct resource_entry *entry; + struct device *dev = pcie->dev; + u64 lowest_pcie_addr = ~(u64)0; + int ret, i = 0; + u8 n = 0; + + /* + * The HW registers (and PCIe) use order-1 numbering for BARs. As such, + * we have inbound_wins[0] unused and BAR1 starts at inbound_wins[1]. + */ + struct inbound_win *b_begin = &inbound_wins[1]; + struct inbound_win *b = b_begin; + + /* + * STB chips beside 7712 disable the first inbound window default. + * Rather being mapped to system memory it is mapped to the + * internal registers of the SoC. This feature is deprecated, has + * security considerations, and is not implemented in our modern + * SoCs. + */ + if (pcie->cfg->soc_base != BCM7712) + add_inbound_win(b++, &n, 0, 0, 0); + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + u64 pcie_start = entry->res->start - entry->offset; + u64 cpu_start = entry->res->start; + + size = resource_size(entry->res); + tot_size += size; + if (pcie_start < lowest_pcie_addr) + lowest_pcie_addr = pcie_start; + /* + * 7712 and newer chips may have many BARs, with each + * offering a non-overlapping viewport to system memory. + * That being said, each BARs size must still be a power of + * two. + */ + if (pcie->cfg->soc_base == BCM7712) + add_inbound_win(b++, &n, size, cpu_start, pcie_start); + + if (n > pcie->cfg->num_inbound_wins) + break; + } + + if (lowest_pcie_addr == ~(u64)0) { + dev_err(dev, "DT node has no dma-ranges\n"); + return -EINVAL; + } + + /* + * 7712 and newer chips do not have an internal memory mapping system + * that enables multiple memory controllers. As such, it can return + * now w/o doing special configuration. + */ + if (pcie->cfg->soc_base == BCM7712) + return n; + + ret = of_property_read_variable_u64_array(pcie->np, "brcm,scb-sizes", pcie->memc_size, 1, + PCIE_BRCM_MAX_MEMC); + if (ret <= 0) { + /* Make an educated guess */ + pcie->num_memc = 1; + pcie->memc_size[0] = 1ULL << fls64(tot_size - 1); + } else { + pcie->num_memc = ret; + } + + /* Each memc is viewed through a "port" that is a power of 2 */ + for (i = 0, size = 0; i < pcie->num_memc; i++) + size += pcie->memc_size[i]; + + /* Our HW mandates that the window size must be a power of 2 */ + size = 1ULL << fls64(size - 1); + + /* + * For STB chips, the BAR2 cpu_addr is hardwired to the start + * of system memory, so we set it to 0. + */ + cpu_addr = 0; + pci_offset = lowest_pcie_addr; + + /* + * We validate the inbound memory view even though we should trust + * whatever the device-tree provides. This is because of an HW issue on + * early Raspberry Pi 4's revisions (bcm2711). It turns out its + * firmware has to dynamically edit dma-ranges due to a bug on the + * PCIe controller integration, which prohibits any access above the + * lower 3GB of memory. Given this, we decided to keep the dma-ranges + * in check, avoiding hard to debug device-tree related issues in the + * future: + * + * The PCIe host controller by design must set the inbound viewport to + * be a contiguous arrangement of all of the system's memory. In + * addition, its size 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 + * viewport -- we can map the outbound memory in or after 3GB and even + * though the viewport will overlap the outbound memory the controller + * will know to send outbound memory downstream and everything else + * upstream. + * + * For example: + * + * - The best-case scenario, memory up to 3GB, is to place the inbound + * region in the first 4GB of pcie-space, as some legacy devices can + * only address 32bits. We would also like to put the MSI under 4GB + * as well, since some devices require a 32bit MSI target address. + * + * - If the system memory is 4GB or larger we cannot start the inbound + * region at location 0 (since we have to allow some space for + * outbound memory @ 3GB). So instead it will start at the 1x + * multiple of its size + */ + if (!size || (pci_offset & (size - 1)) || + (pci_offset < SZ_4G && pci_offset > SZ_2G)) { + dev_err(dev, "Invalid inbound_win2_offset/size: size 0x%llx, off 0x%llx\n", + size, pci_offset); + return -EINVAL; + } + + /* Enable inbound window 2, the main inbound window for STB chips */ + add_inbound_win(b++, &n, size, cpu_addr, pci_offset); + + /* + * Disable inbound window 3. On some chips presents the same + * window as #2 but the data appears in a settable endianness. + */ + add_inbound_win(b++, &n, 0, 0, 0); + + return n; +} + +static u32 brcm_bar_reg_offset(int bar) +{ + if (bar <= 3) + return PCIE_MISC_RC_BAR1_CONFIG_LO + 8 * (bar - 1); + else + return PCIE_MISC_RC_BAR4_CONFIG_LO + 8 * (bar - 4); +} + +static u32 brcm_ubus_reg_offset(int bar) +{ + if (bar <= 3) + return PCIE_MISC_UBUS_BAR1_CONFIG_REMAP + 8 * (bar - 1); + else + return PCIE_MISC_UBUS_BAR4_CONFIG_REMAP + 8 * (bar - 4); +} + +static void set_inbound_win_registers(struct brcm_pcie *pcie, + const struct inbound_win *inbound_wins, + u8 num_inbound_wins) +{ + void __iomem *base = pcie->base; + int i; + + for (i = 1; i <= num_inbound_wins; i++) { + u64 pci_offset = inbound_wins[i].pci_offset; + u64 cpu_addr = inbound_wins[i].cpu_addr; + u64 size = inbound_wins[i].size; + u32 reg_offset = brcm_bar_reg_offset(i); + u32 tmp = lower_32_bits(pci_offset); + + u32p_replace_bits(&tmp, brcm_pcie_encode_ibar_size(size), + PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK); + + /* Write low */ + writel_relaxed(tmp, base + reg_offset); + /* Write high */ + writel_relaxed(upper_32_bits(pci_offset), base + reg_offset + 4); + + /* + * Most STB chips: + * Do nothing. + * 7712: + * All of their BARs need to be set. + */ + if (pcie->cfg->soc_base == BCM7712) { + /* BUS remap register settings */ + reg_offset = brcm_ubus_reg_offset(i); + tmp = lower_32_bits(cpu_addr) & ~0xfff; + tmp |= PCIE_MISC_UBUS_BAR1_CONFIG_REMAP_ACCESS_EN_MASK; + writel_relaxed(tmp, base + reg_offset); + tmp = upper_32_bits(cpu_addr); + writel_relaxed(tmp, base + reg_offset + 4); + } + } +} + +static int brcm_pcie_setup(struct brcm_pcie *pcie) +{ + struct inbound_win inbound_wins[PCIE_BRCM_MAX_INBOUND_WINS]; + void __iomem *base = pcie->base; + struct pci_host_bridge *bridge; + struct resource_entry *entry; + 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 = brcm_pcie_bridge_sw_init_set(pcie, 1); + if (ret) + return ret; + + /* Ensure that PERST# is asserted; some bootloaders may deassert it. */ + if (pcie->cfg->soc_base == BCM2711) { + ret = pcie->cfg->perst_set(pcie, 1); + if (ret) { + pcie->cfg->bridge_sw_init_set(pcie, 0); + return ret; + } + } + + usleep_range(100, 200); + + /* Take the bridge out of reset */ + ret = brcm_pcie_bridge_sw_init_set(pcie, 0); + if (ret) + return ret; + + tmp = readl(base + HARD_DEBUG(pcie)); + if (is_bmips(pcie)) + tmp &= ~PCIE_BMIPS_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK; + else + tmp &= ~PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK; + writel(tmp, base + HARD_DEBUG(pcie)); + /* Wait for SerDes to be stable */ + usleep_range(100, 200); + + /* + * SCB_MAX_BURST_SIZE is a two bit field. For GENERIC chips it + * is encoded as 0=128, 1=256, 2=512, 3=Rsvd, for BCM7278 it + * is encoded as 0=Rsvd, 1=128, 2=256, 3=512. + */ + if (is_bmips(pcie)) + burst = 0x1; /* 256 bytes */ + else if (pcie->cfg->soc_base == BCM2711) + burst = 0x0; /* 128 bytes */ + else if (pcie->cfg->soc_base == BCM7278) + burst = 0x3; /* 512 bytes */ + else + burst = 0x2; /* 512 bytes */ + + /* + * Set SCB_MAX_BURST_SIZE, CFG_READ_UR_MODE, SCB_ACCESS_EN, + * RCB_MPS_MODE, RCB_64B_MODE + */ + tmp = readl(base + PCIE_MISC_MISC_CTRL); + u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_MASK); + u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_MASK); + u32p_replace_bits(&tmp, burst, PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_MASK); + u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_PCIE_RCB_MPS_MODE_MASK); + u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_PCIE_RCB_64B_MODE_MASK); + writel(tmp, base + PCIE_MISC_MISC_CTRL); + + num_inbound_wins = brcm_pcie_get_inbound_wins(pcie, inbound_wins); + if (num_inbound_wins < 0) + return num_inbound_wins; + + set_inbound_win_registers(pcie, inbound_wins, num_inbound_wins); + + if (!brcm_pcie_rc_mode(pcie)) { + dev_err(pcie->dev, "PCIe RC controller misconfigured as Endpoint\n"); + return -EINVAL; + } + + tmp = readl(base + PCIE_MISC_MISC_CTRL); + for (memc = 0; memc < pcie->num_memc; memc++) { + u32 scb_size_val = ilog2(pcie->memc_size[memc]) - 15; + + if (memc == 0) + u32p_replace_bits(&tmp, scb_size_val, SCB_SIZE_MASK(0)); + else if (memc == 1) + u32p_replace_bits(&tmp, scb_size_val, SCB_SIZE_MASK(1)); + else if (memc == 2) + u32p_replace_bits(&tmp, scb_size_val, SCB_SIZE_MASK(2)); + } + writel(tmp, base + PCIE_MISC_MISC_CTRL); + + /* + * We ideally want the MSI target address to be located in the 32bit + * addressable memory area. Some devices might depend on it. This is + * possible either when the inbound window is located above the lower + * 4GB or when the inbound area is smaller than 4GB (taking into + * account the rounding-up we're forced to perform). + */ + if (inbound_wins[2].pci_offset >= SZ_4G || + (inbound_wins[2].size + inbound_wins[2].pci_offset) < SZ_4G) + pcie->msi_target_addr = BRCM_MSI_TARGET_ADDR_LT_4GB; + else + pcie->msi_target_addr = BRCM_MSI_TARGET_ADDR_GT_4GB; + + + /* Don't advertise L0s capability if 'aspm-no-l0s' */ + tmp = readl(base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); + 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). + */ + tmp = readl(base + PCIE_RC_CFG_PRIV1_ID_VAL3); + u32p_replace_bits(&tmp, 0x060400, + PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK); + writel(tmp, base + PCIE_RC_CFG_PRIV1_ID_VAL3); + + bridge = pci_host_bridge_from_priv(pcie); + resource_list_for_each_entry(entry, &bridge->windows) { + struct resource *res = entry->res; + + if (resource_type(res) != IORESOURCE_MEM) + continue; + + if (num_out_wins >= BRCM_NUM_PCIE_OUT_WINS) { + dev_err(pcie->dev, "too many outbound wins\n"); + return -EINVAL; + } + + if (is_bmips(pcie)) { + u64 start = res->start; + unsigned int j, nwins = resource_size(res) / SZ_128M; + + /* bmips PCIe outbound windows have a 128MB max size */ + if (nwins > BRCM_NUM_PCIE_OUT_WINS) + nwins = BRCM_NUM_PCIE_OUT_WINS; + for (j = 0; j < nwins; j++, start += SZ_128M) + brcm_pcie_set_outbound_win(pcie, j, start, + start - entry->offset, + SZ_128M); + break; + } + brcm_pcie_set_outbound_win(pcie, num_out_wins, res->start, + res->start - entry->offset, + resource_size(res)); + num_out_wins++; + } + + /* PCIe->SCB endian mode for inbound window */ + tmp = readl(base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1); + u32p_replace_bits(&tmp, PCIE_RC_CFG_VENDOR_SPECIFIC_REG1_LITTLE_ENDIAN, + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK); + writel(tmp, base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1); + + if (pcie->cfg->post_setup) { + ret = pcie->cfg->post_setup(pcie); + if (ret < 0) + return ret; + } + + return 0; +} + +/* + * This extends the timeout period for an access to an internal bus. This + * access timeout may occur during L1SS sleep periods, even without the + * presence of a PCIe access. + */ +static void brcm_extend_rbus_timeout(struct brcm_pcie *pcie) +{ + /* TIMEOUT register is two registers before RGR1_SW_INIT_1 */ + const unsigned int REG_OFFSET = PCIE_RGR1_SW_INIT_1(pcie) - 8; + u32 timeout_us = 4000000; /* 4 seconds, our setting for L1SS */ + + /* 7712 does not have this (RGR1) timer */ + if (pcie->cfg->soc_base == BCM7712) + return; + + /* Each unit in timeout register is 1/216,000,000 seconds */ + writel(216 * timeout_us, pcie->base + REG_OFFSET); +} + +static void brcm_config_clkreq(struct brcm_pcie *pcie) +{ + static const char err_msg[] = "invalid 'brcm,clkreq-mode' DT string\n"; + const char *mode = "default"; + u32 clkreq_cntl; + int ret, tmp; + + ret = of_property_read_string(pcie->np, "brcm,clkreq-mode", &mode); + if (ret && ret != -EINVAL) { + dev_err(pcie->dev, err_msg); + mode = "safe"; + } + + /* Start out assuming safe mode (both mode bits cleared) */ + clkreq_cntl = readl(pcie->base + HARD_DEBUG(pcie)); + clkreq_cntl &= ~PCIE_CLKREQ_MASK; + + if (strcmp(mode, "no-l1ss") == 0) { + /* + * "no-l1ss" -- Provides Clock Power Management, L0s, and + * L1, but cannot provide L1 substate (L1SS) power + * savings. If the downstream device connected to the RC is + * L1SS capable AND the OS enables L1SS, all PCIe traffic + * may abruptly halt, potentially hanging the system. + */ + clkreq_cntl |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK; + /* + * We want to un-advertise L1 substates because if the OS + * tries to configure the controller into using L1 substate + * power savings it may fail or hang when the RC HW is in + * "no-l1ss" mode. + */ + tmp = readl(pcie->base + PCIE_RC_CFG_PRIV1_ROOT_CAP); + u32p_replace_bits(&tmp, 2, PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK); + writel(tmp, pcie->base + PCIE_RC_CFG_PRIV1_ROOT_CAP); + + } else if (strcmp(mode, "default") == 0) { + /* + * "default" -- Provides L0s, L1, and L1SS, but not + * compliant to provide Clock Power Management; + * specifically, may not be able to meet the Tclron max + * timing of 400ns as specified in "Dynamic Clock Control", + * section 3.2.5.2.2 of the PCIe spec. This situation is + * atypical and should happen only with older devices. + */ + clkreq_cntl |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_L1SS_ENABLE_MASK; + brcm_extend_rbus_timeout(pcie); + + } else { + /* + * "safe" -- No power savings; refclk is driven by RC + * unconditionally. + */ + if (strcmp(mode, "safe") != 0) + dev_err(pcie->dev, err_msg); + mode = "safe"; + } + writel(clkreq_cntl, pcie->base + HARD_DEBUG(pcie)); + + dev_info(pcie->dev, "clkreq-mode set to %s\n", mode); +} + +static int brcm_pcie_start_link(struct brcm_pcie *pcie) +{ + struct device *dev = pcie->dev; + void __iomem *base = pcie->base; + u16 nlw, cls, lnksta; + bool ssc_good = false; + int ret, i; + + /* Limit the generation if specified */ + if (pcie->gen) + brcm_pcie_set_gen(pcie, pcie->gen); + + /* Unassert the fundamental reset */ + ret = pcie->cfg->perst_set(pcie, 0); + if (ret) + return ret; + + msleep(PCIE_RESET_CONFIG_WAIT_MS); + + /* + * Give the RC/EP even more time to wake up, before trying to + * configure RC. Intermittently check status for link-up, up to a + * total of 100ms. + */ + for (i = 0; i < 100 && !brcm_pcie_link_up(pcie); i += 5) + msleep(5); + + if (!brcm_pcie_link_up(pcie)) { + dev_err(dev, "link down\n"); + return -ENODEV; + } + + brcm_config_clkreq(pcie); + + if (pcie->ssc) { + ret = brcm_pcie_set_ssc(pcie); + if (ret == 0) + ssc_good = true; + else + dev_err(dev, "failed attempt to enter ssc mode\n"); + } + + lnksta = readw(base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKSTA); + cls = FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta); + nlw = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta); + dev_info(dev, "link up, %s x%u %s\n", + pci_speed_string(pcie_link_speed[cls]), nlw, + ssc_good ? "(SSC)" : "(!SSC)"); + + return 0; +} + +static const char * const supplies[] = { + "vpcie3v3", + "vpcie3v3aux", + "vpcie12v", +}; + +static void *alloc_subdev_regulators(struct device *dev) +{ + const size_t size = sizeof(struct subdev_regulators) + + sizeof(struct regulator_bulk_data) * ARRAY_SIZE(supplies); + struct subdev_regulators *sr; + int i; + + sr = devm_kzalloc(dev, size, GFP_KERNEL); + if (sr) { + sr->num_supplies = ARRAY_SIZE(supplies); + for (i = 0; i < ARRAY_SIZE(supplies); i++) + sr->supplies[i].supply = supplies[i]; + } + + return sr; +} + +static int brcm_pcie_add_bus(struct pci_bus *bus) +{ + struct brcm_pcie *pcie = bus->sysdata; + struct device *dev = &bus->dev; + struct subdev_regulators *sr; + int ret; + + if (!bus->parent || !pci_is_root_bus(bus->parent)) + return 0; + + if (dev->of_node) { + sr = alloc_subdev_regulators(dev); + if (!sr) { + dev_info(dev, "Can't allocate regulators for downstream device\n"); + goto no_regulators; + } + + pcie->sr = sr; + + ret = regulator_bulk_get(dev, sr->num_supplies, sr->supplies); + if (ret) { + dev_info(dev, "Did not get regulators, err=%d\n", ret); + pcie->sr = NULL; + goto no_regulators; + } + + ret = regulator_bulk_enable(sr->num_supplies, sr->supplies); + if (ret) { + dev_err(dev, "Can't enable regulators for downstream device\n"); + regulator_bulk_free(sr->num_supplies, sr->supplies); + pcie->sr = NULL; + } + } + +no_regulators: + brcm_pcie_start_link(pcie); + return 0; +} + +static void brcm_pcie_remove_bus(struct pci_bus *bus) +{ + struct brcm_pcie *pcie = bus->sysdata; + struct subdev_regulators *sr = pcie->sr; + struct device *dev = &bus->dev; + + if (!sr || !bus->parent || !pci_is_root_bus(bus->parent)) + return; + + if (regulator_bulk_disable(sr->num_supplies, sr->supplies)) + dev_err(dev, "Failed to disable regulators for downstream device\n"); + regulator_bulk_free(sr->num_supplies, sr->supplies); + pcie->sr = NULL; +} + +/* L23 is a low-power PCIe link state */ +static void brcm_pcie_enter_l23(struct brcm_pcie *pcie) +{ + void __iomem *base = pcie->base; + int l23, i; + u32 tmp; + + /* Assert request for L23 */ + tmp = readl(base + PCIE_MISC_PCIE_CTRL); + u32p_replace_bits(&tmp, 1, PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK); + writel(tmp, base + PCIE_MISC_PCIE_CTRL); + + /* Wait up to 36 msec for L23 */ + tmp = readl(base + PCIE_MISC_PCIE_STATUS); + l23 = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK, tmp); + for (i = 0; i < 15 && !l23; i++) { + usleep_range(2000, 2400); + tmp = readl(base + PCIE_MISC_PCIE_STATUS); + l23 = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK, + tmp); + } + + if (!l23) + dev_err(pcie->dev, "failed to enter low-power link state\n"); +} + +static int brcm_phy_cntl(struct brcm_pcie *pcie, const int start) +{ + static const u32 shifts[PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS] = { + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_SHIFT, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_SHIFT, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_SHIFT,}; + static const u32 masks[PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS] = { + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_MASK, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_MASK, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_MASK,}; + const int beg = start ? 0 : PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS - 1; + const int end = start ? PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS : -1; + u32 tmp, combined_mask = 0; + u32 val; + void __iomem *base = pcie->base; + int i, ret; + + for (i = beg; i != end; start ? i++ : i--) { + val = start ? BIT_MASK(shifts[i]) : 0; + tmp = readl(base + PCIE_DVT_PMU_PCIE_PHY_CTRL); + tmp = (tmp & ~masks[i]) | (val & masks[i]); + writel(tmp, base + PCIE_DVT_PMU_PCIE_PHY_CTRL); + usleep_range(50, 200); + combined_mask |= masks[i]; + } + + tmp = readl(base + PCIE_DVT_PMU_PCIE_PHY_CTRL); + val = start ? combined_mask : 0; + + ret = (tmp & combined_mask) == val ? 0 : -EIO; + if (ret) + dev_err(pcie->dev, "failed to %s phy\n", (start ? "start" : "stop")); + + return ret; +} + +static inline int brcm_phy_start(struct brcm_pcie *pcie) +{ + return pcie->cfg->has_phy ? brcm_phy_cntl(pcie, 1) : 0; +} + +static inline int brcm_phy_stop(struct brcm_pcie *pcie) +{ + return pcie->cfg->has_phy ? brcm_phy_cntl(pcie, 0) : 0; +} + +static int brcm_pcie_turn_off(struct brcm_pcie *pcie) +{ + void __iomem *base = pcie->base; + int tmp, ret; + + if (brcm_pcie_link_up(pcie)) + brcm_pcie_enter_l23(pcie); + /* Assert fundamental reset */ + ret = pcie->cfg->perst_set(pcie, 1); + if (ret) + return ret; + + /* Deassert request for L23 in case it was asserted */ + tmp = readl(base + PCIE_MISC_PCIE_CTRL); + u32p_replace_bits(&tmp, 0, PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK); + writel(tmp, base + PCIE_MISC_PCIE_CTRL); + + /* Turn off SerDes */ + tmp = readl(base + HARD_DEBUG(pcie)); + u32p_replace_bits(&tmp, 1, PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK); + writel(tmp, base + HARD_DEBUG(pcie)); + + if (!(pcie->cfg->quirks & CFG_QUIRK_AVOID_BRIDGE_SHUTDOWN)) + /* Shutdown PCIe bridge */ + ret = brcm_pcie_bridge_sw_init_set(pcie, 1); + + return ret; +} + +static int pci_dev_may_wakeup(struct pci_dev *dev, void *data) +{ + bool *ret = data; + + if (device_may_wakeup(&dev->dev)) { + *ret = true; + dev_info(&dev->dev, "Possible wake-up device; regulators will not be disabled\n"); + } + return (int) *ret; +} + +static int brcm_pcie_suspend_noirq(struct device *dev) +{ + struct brcm_pcie *pcie = dev_get_drvdata(dev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + int ret, rret; + + ret = brcm_pcie_turn_off(pcie); + if (ret) + return ret; + + /* + * If brcm_phy_stop() returns an error, just dev_err(). If we + * return the error it will cause the suspend to fail and this is a + * forgivable offense that will probably be erased on resume. + */ + if (brcm_phy_stop(pcie)) + dev_err(dev, "Could not stop phy for suspend\n"); + + ret = reset_control_rearm(pcie->rescal); + if (ret) { + dev_err(dev, "Could not rearm rescal reset\n"); + return ret; + } + + if (pcie->sr) { + /* + * Now turn off the regulators, but if at least one + * downstream device is enabled as a wake-up source, do not + * turn off regulators. + */ + pcie->ep_wakeup_capable = false; + pci_walk_bus(bridge->bus, pci_dev_may_wakeup, + &pcie->ep_wakeup_capable); + if (!pcie->ep_wakeup_capable) { + ret = regulator_bulk_disable(pcie->sr->num_supplies, + pcie->sr->supplies); + if (ret) { + dev_err(dev, "Could not turn off regulators\n"); + rret = reset_control_reset(pcie->rescal); + if (rret) + dev_err(dev, "failed to reset 'rascal' controller ret=%d\n", + rret); + return ret; + } + } + } + clk_disable_unprepare(pcie->clk); + + return 0; +} + +static int brcm_pcie_resume_noirq(struct device *dev) +{ + struct brcm_pcie *pcie = dev_get_drvdata(dev); + void __iomem *base; + u32 tmp; + int ret, rret; + + base = pcie->base; + ret = clk_prepare_enable(pcie->clk); + if (ret) + return ret; + + ret = reset_control_reset(pcie->rescal); + if (ret) + goto err_disable_clk; + + ret = brcm_phy_start(pcie); + if (ret) + goto err_reset; + + /* Take bridge out of reset so we can access the SERDES reg */ + ret = brcm_pcie_bridge_sw_init_set(pcie, 0); + if (ret) + goto err_reset; + + /* SERDES_IDDQ = 0 */ + tmp = readl(base + HARD_DEBUG(pcie)); + u32p_replace_bits(&tmp, 0, PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK); + writel(tmp, base + HARD_DEBUG(pcie)); + + /* wait for serdes to be stable */ + udelay(100); + + ret = brcm_pcie_setup(pcie); + if (ret) + goto err_reset; + + if (pcie->sr) { + if (pcie->ep_wakeup_capable) { + /* + * We are resuming from a suspend. In the suspend we + * did not disable the power supplies, so there is + * no need to enable them (and falsely increase their + * usage count). + */ + pcie->ep_wakeup_capable = false; + } else { + ret = regulator_bulk_enable(pcie->sr->num_supplies, + pcie->sr->supplies); + if (ret) { + dev_err(dev, "Could not turn on regulators\n"); + goto err_reset; + } + } + } + + ret = brcm_pcie_start_link(pcie); + if (ret) + goto err_regulator; + + if (pcie->msi) + brcm_msi_set_regs(pcie->msi); + + return 0; + +err_regulator: + if (pcie->sr) + regulator_bulk_disable(pcie->sr->num_supplies, pcie->sr->supplies); +err_reset: + rret = reset_control_rearm(pcie->rescal); + if (rret) + dev_err(pcie->dev, "failed to rearm 'rescal' reset, err=%d\n", rret); +err_disable_clk: + clk_disable_unprepare(pcie->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); + brcm_pcie_turn_off(pcie); + if (brcm_phy_stop(pcie)) + dev_err(pcie->dev, "Could not stop phy\n"); + if (reset_control_rearm(pcie->rescal)) + dev_err(pcie->dev, "Could not rearm rescal reset\n"); + clk_disable_unprepare(pcie->clk); +} + +static void brcm_pcie_remove(struct platform_device *pdev) +{ + struct brcm_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + if (pcie->cfg->has_err_report) + brcm_unregister_die_notifiers(pcie); + + __brcm_pcie_remove(pcie); +} + +static const int pcie_offsets[] = { + [RGR1_SW_INIT_1] = 0x9210, + [EXT_CFG_INDEX] = 0x9000, + [EXT_CFG_DATA] = 0x8000, + [PCIE_HARD_DEBUG] = 0x4204, + [PCIE_INTR2_CPU_BASE] = 0x4300, +}; + +static const int pcie_offsets_bcm7278[] = { + [RGR1_SW_INIT_1] = 0xc010, + [EXT_CFG_INDEX] = 0x9000, + [EXT_CFG_DATA] = 0x8000, + [PCIE_HARD_DEBUG] = 0x4204, + [PCIE_INTR2_CPU_BASE] = 0x4300, +}; + +static const int pcie_offsets_bcm7425[] = { + [RGR1_SW_INIT_1] = 0x8010, + [EXT_CFG_INDEX] = 0x8300, + [EXT_CFG_DATA] = 0x8304, + [PCIE_HARD_DEBUG] = 0x4204, + [PCIE_INTR2_CPU_BASE] = 0x4300, +}; + +static const int pcie_offsets_bcm7712[] = { + [RGR1_SW_INIT_1] = 0x9210, + [EXT_CFG_INDEX] = 0x9000, + [EXT_CFG_DATA] = 0x8000, + [PCIE_HARD_DEBUG] = 0x4304, + [PCIE_INTR2_CPU_BASE] = 0x4400, +}; + +static const struct pcie_cfg_data generic_cfg = { + .offsets = pcie_offsets, + .soc_base = GENERIC, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .num_inbound_wins = 3, +}; + +static const struct pcie_cfg_data bcm2711_cfg = { + .offsets = pcie_offsets, + .soc_base = BCM2711, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .num_inbound_wins = 3, +}; + +static const struct pcie_cfg_data bcm2712_cfg = { + .offsets = pcie_offsets_bcm7712, + .soc_base = BCM7712, + .perst_set = brcm_pcie_perst_set_7278, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .post_setup = brcm_pcie_post_setup_bcm2712, + .quirks = CFG_QUIRK_AVOID_BRIDGE_SHUTDOWN, + .num_inbound_wins = 10, +}; + +static const struct pcie_cfg_data bcm4908_cfg = { + .offsets = pcie_offsets, + .soc_base = BCM4908, + .perst_set = brcm_pcie_perst_set_4908, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .num_inbound_wins = 3, +}; + +static const struct pcie_cfg_data bcm7278_cfg = { + .offsets = pcie_offsets_bcm7278, + .soc_base = BCM7278, + .perst_set = brcm_pcie_perst_set_7278, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_7278, + .num_inbound_wins = 3, +}; + +static const struct pcie_cfg_data bcm7425_cfg = { + .offsets = pcie_offsets_bcm7425, + .soc_base = BCM7425, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .num_inbound_wins = 3, +}; + +static const struct pcie_cfg_data bcm7435_cfg = { + .offsets = pcie_offsets, + .soc_base = BCM7435, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .num_inbound_wins = 3, +}; + +static const struct pcie_cfg_data bcm7216_cfg = { + .offsets = pcie_offsets_bcm7278, + .soc_base = BCM7278, + .perst_set = brcm_pcie_perst_set_7278, + .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 = { + .offsets = pcie_offsets_bcm7712, + .perst_set = brcm_pcie_perst_set_7278, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .soc_base = BCM7712, + .num_inbound_wins = 10, +}; + +static const struct of_device_id brcm_pcie_match[] = { + { .compatible = "brcm,bcm2711-pcie", .data = &bcm2711_cfg }, + { .compatible = "brcm,bcm2712-pcie", .data = &bcm2712_cfg }, + { .compatible = "brcm,bcm4908-pcie", .data = &bcm4908_cfg }, + { .compatible = "brcm,bcm7211-pcie", .data = &generic_cfg }, + { .compatible = "brcm,bcm7216-pcie", .data = &bcm7216_cfg }, + { .compatible = "brcm,bcm7278-pcie", .data = &bcm7278_cfg }, + { .compatible = "brcm,bcm7425-pcie", .data = &bcm7425_cfg }, + { .compatible = "brcm,bcm7435-pcie", .data = &bcm7435_cfg }, + { .compatible = "brcm,bcm7445-pcie", .data = &generic_cfg }, + { .compatible = "brcm,bcm7712-pcie", .data = &bcm7712_cfg }, + {}, +}; + +static struct pci_ops brcm_pcie_ops = { + .map_bus = brcm_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + .add_bus = brcm_pcie_add_bus, + .remove_bus = brcm_pcie_remove_bus, +}; + +static struct pci_ops brcm7425_pcie_ops = { + .map_bus = brcm7425_pcie_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, + .add_bus = brcm_pcie_add_bus, + .remove_bus = brcm_pcie_remove_bus, +}; + +static int brcm_pcie_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct pci_host_bridge *bridge; + const struct pcie_cfg_data *data; + struct brcm_pcie *pcie; + int ret; + + bridge = devm_pci_alloc_host_bridge(&pdev->dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + data = of_device_get_match_data(&pdev->dev); + if (!data) { + pr_err("failed to look up compatible string\n"); + return -EINVAL; + } + + pcie = pci_host_bridge_priv(bridge); + pcie->dev = &pdev->dev; + pcie->np = np; + pcie->cfg = data; + + pcie->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + pcie->clk = devm_clk_get_optional(&pdev->dev, "sw_pcie"); + if (IS_ERR(pcie->clk)) + return PTR_ERR(pcie->clk); + + ret = of_pci_get_max_link_speed(np); + pcie->gen = (ret < 0) ? 0 : ret; + + pcie->ssc = of_property_read_bool(np, "brcm,enable-ssc"); + + pcie->rescal = devm_reset_control_get_optional_shared(&pdev->dev, "rescal"); + if (IS_ERR(pcie->rescal)) + return PTR_ERR(pcie->rescal); + + pcie->perst_reset = devm_reset_control_get_optional_exclusive(&pdev->dev, "perst"); + if (IS_ERR(pcie->perst_reset)) + return PTR_ERR(pcie->perst_reset); + + pcie->bridge_reset = devm_reset_control_get_optional_exclusive(&pdev->dev, "bridge"); + if (IS_ERR(pcie->bridge_reset)) + return PTR_ERR(pcie->bridge_reset); + + pcie->swinit_reset = devm_reset_control_get_optional_exclusive(&pdev->dev, "swinit"); + if (IS_ERR(pcie->swinit_reset)) + return PTR_ERR(pcie->swinit_reset); + + ret = clk_prepare_enable(pcie->clk); + if (ret) + return dev_err_probe(&pdev->dev, ret, "could not enable clock\n"); + + 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); + if (ret) { + clk_disable_unprepare(pcie->clk); + return dev_err_probe(&pdev->dev, ret, + "could not assert reset 'swinit'\n"); + } + + /* HW team recommends 1us for proper sync and propagation of reset */ + udelay(1); + + ret = reset_control_deassert(pcie->swinit_reset); + if (ret) { + clk_disable_unprepare(pcie->clk); + return dev_err_probe(&pdev->dev, ret, + "could not de-assert reset 'swinit'\n"); + } + } + + ret = reset_control_reset(pcie->rescal); + if (ret) { + clk_disable_unprepare(pcie->clk); + return dev_err_probe(&pdev->dev, ret, "failed to deassert 'rescal'\n"); + } + + ret = brcm_phy_start(pcie); + if (ret) { + reset_control_rearm(pcie->rescal); + clk_disable_unprepare(pcie->clk); + return ret; + } + + ret = brcm_pcie_setup(pcie); + if (ret) + goto fail; + + pcie->hw_rev = readl(pcie->base + PCIE_MISC_REVISION); + if (pcie->cfg->soc_base == BCM4908 && + pcie->hw_rev >= BRCM_PCIE_HW_REV_3_20) { + dev_err(pcie->dev, "hardware revision with unsupported PERST# setup\n"); + ret = -ENODEV; + goto fail; + } + + if (pci_msi_enabled()) { + struct device_node *msi_np = of_parse_phandle(pcie->np, "msi-parent", 0); + + if (msi_np == pcie->np) + ret = brcm_pcie_enable_msi(pcie); + + of_node_put(msi_np); + + if (ret) { + dev_err(pcie->dev, "probe of internal MSI failed"); + goto fail; + } + } + + bridge->ops = pcie->cfg->soc_base == BCM7425 ? + &brcm7425_pcie_ops : &brcm_pcie_ops; + bridge->sysdata = pcie; + + platform_set_drvdata(pdev, pcie); + + ret = pci_host_probe(bridge); + if (!ret && !brcm_pcie_link_up(pcie)) + ret = -ENODEV; + + if (ret) { + brcm_pcie_remove(pdev); + return ret; + } + + if (pcie->cfg->has_err_report) { + spin_lock_init(&pcie->bridge_lock); + brcm_register_die_notifiers(pcie); + } + + return 0; + +fail: + __brcm_pcie_remove(pcie); + + return ret; +} + +MODULE_DEVICE_TABLE(of, brcm_pcie_match); + +static const struct dev_pm_ops brcm_pcie_pm_ops = { + .suspend_noirq = brcm_pcie_suspend_noirq, + .resume_noirq = brcm_pcie_resume_noirq, +}; + +static struct platform_driver brcm_pcie_driver = { + .probe = brcm_pcie_probe, + .remove = brcm_pcie_remove, + .driver = { + .name = "brcm-pcie", + .of_match_table = brcm_pcie_match, + .pm = &brcm_pcie_pm_ops, + }, +}; +module_platform_driver(brcm_pcie_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Broadcom STB PCIe RC driver"); +MODULE_AUTHOR("Broadcom"); +MODULE_SOFTDEP("pre: irq_bcm2712_mip"); diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c deleted file mode 100644 index c3a088910f48..000000000000 --- a/drivers/pci/controller/pcie-cadence-ep.c +++ /dev/null @@ -1,564 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2017 Cadence -// Cadence PCIe endpoint controller driver. -// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> - -#include <linux/delay.h> -#include <linux/kernel.h> -#include <linux/of.h> -#include <linux/pci-epc.h> -#include <linux/platform_device.h> -#include <linux/pm_runtime.h> -#include <linux/sizes.h> - -#include "pcie-cadence.h" - -#define CDNS_PCIE_EP_MIN_APERTURE 128 /* 128 bytes */ -#define CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE 0x1 -#define CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY 0x3 - -/** - * struct cdns_pcie_ep - private data for this PCIe endpoint controller driver - * @pcie: Cadence PCIe controller - * @max_regions: maximum number of regions supported by hardware - * @ob_region_map: bitmask of mapped outbound regions - * @ob_addr: base addresses in the AXI bus where the outbound regions start - * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ - * dedicated outbound regions is mapped. - * @irq_cpu_addr: base address in the CPU space where a write access triggers - * the sending of a memory write (MSI) / normal message (legacy - * IRQ) TLP through the PCIe bus. - * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ - * dedicated outbound region. - * @irq_pci_fn: the latest PCI function that has updated the mapping of - * the MSI/legacy IRQ dedicated outbound region. - * @irq_pending: bitmask of asserted legacy IRQs. - */ -struct cdns_pcie_ep { - struct cdns_pcie pcie; - u32 max_regions; - unsigned long ob_region_map; - phys_addr_t *ob_addr; - phys_addr_t irq_phys_addr; - void __iomem *irq_cpu_addr; - u64 irq_pci_addr; - u8 irq_pci_fn; - u8 irq_pending; -}; - -static int cdns_pcie_ep_write_header(struct pci_epc *epc, u8 fn, - struct pci_epf_header *hdr) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - struct cdns_pcie *pcie = &ep->pcie; - - cdns_pcie_ep_fn_writew(pcie, fn, PCI_DEVICE_ID, hdr->deviceid); - cdns_pcie_ep_fn_writeb(pcie, fn, PCI_REVISION_ID, hdr->revid); - cdns_pcie_ep_fn_writeb(pcie, fn, PCI_CLASS_PROG, hdr->progif_code); - cdns_pcie_ep_fn_writew(pcie, fn, PCI_CLASS_DEVICE, - hdr->subclass_code | hdr->baseclass_code << 8); - cdns_pcie_ep_fn_writeb(pcie, fn, PCI_CACHE_LINE_SIZE, - hdr->cache_line_size); - cdns_pcie_ep_fn_writew(pcie, fn, PCI_SUBSYSTEM_ID, hdr->subsys_id); - cdns_pcie_ep_fn_writeb(pcie, fn, PCI_INTERRUPT_PIN, hdr->interrupt_pin); - - /* - * Vendor ID can only be modified from function 0, all other functions - * use the same vendor ID as function 0. - */ - if (fn == 0) { - /* Update the vendor IDs. */ - u32 id = CDNS_PCIE_LM_ID_VENDOR(hdr->vendorid) | - CDNS_PCIE_LM_ID_SUBSYS(hdr->subsys_vendor_id); - - cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id); - } - - return 0; -} - -static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, - struct pci_epf_bar *epf_bar) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - struct cdns_pcie *pcie = &ep->pcie; - dma_addr_t bar_phys = epf_bar->phys_addr; - enum pci_barno bar = epf_bar->barno; - int flags = epf_bar->flags; - u32 addr0, addr1, reg, cfg, b, aperture, ctrl; - u64 sz; - - /* BAR size is 2^(aperture + 7) */ - sz = max_t(size_t, epf_bar->size, CDNS_PCIE_EP_MIN_APERTURE); - /* - * roundup_pow_of_two() returns an unsigned long, which is not suited - * for 64bit values. - */ - sz = 1ULL << fls64(sz - 1); - aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */ - - if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) { - ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_IO_32BITS; - } else { - bool is_prefetch = !!(flags & PCI_BASE_ADDRESS_MEM_PREFETCH); - bool is_64bits = sz > SZ_2G; - - if (is_64bits && (bar & 1)) - return -EINVAL; - - if (is_64bits && !(flags & PCI_BASE_ADDRESS_MEM_TYPE_64)) - epf_bar->flags |= PCI_BASE_ADDRESS_MEM_TYPE_64; - - if (is_64bits && is_prefetch) - ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_64BITS; - else if (is_prefetch) - ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_32BITS; - else if (is_64bits) - ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_64BITS; - else - ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_32BITS; - } - - addr0 = lower_32_bits(bar_phys); - addr1 = upper_32_bits(bar_phys); - cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar), - addr0); - cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar), - addr1); - - if (bar < BAR_4) { - reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG0(fn); - b = bar; - } else { - reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG1(fn); - b = bar - BAR_4; - } - - cfg = cdns_pcie_readl(pcie, reg); - cfg &= ~(CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | - CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); - cfg |= (CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE(b, aperture) | - CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl)); - cdns_pcie_writel(pcie, reg, cfg); - - return 0; -} - -static void cdns_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, - struct pci_epf_bar *epf_bar) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - struct cdns_pcie *pcie = &ep->pcie; - enum pci_barno bar = epf_bar->barno; - u32 reg, cfg, b, ctrl; - - if (bar < BAR_4) { - reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG0(fn); - b = bar; - } else { - reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG1(fn); - b = bar - BAR_4; - } - - ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED; - cfg = cdns_pcie_readl(pcie, reg); - cfg &= ~(CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | - CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); - cfg |= CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl); - cdns_pcie_writel(pcie, reg, cfg); - - cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar), 0); - cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar), 0); -} - -static int cdns_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, phys_addr_t addr, - u64 pci_addr, size_t size) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - struct cdns_pcie *pcie = &ep->pcie; - u32 r; - - r = find_first_zero_bit(&ep->ob_region_map, - sizeof(ep->ob_region_map) * BITS_PER_LONG); - if (r >= ep->max_regions - 1) { - dev_err(&epc->dev, "no free outbound region\n"); - return -EINVAL; - } - - cdns_pcie_set_outbound_region(pcie, fn, r, false, addr, pci_addr, size); - - set_bit(r, &ep->ob_region_map); - ep->ob_addr[r] = addr; - - return 0; -} - -static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, - phys_addr_t addr) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - struct cdns_pcie *pcie = &ep->pcie; - u32 r; - - for (r = 0; r < ep->max_regions - 1; r++) - if (ep->ob_addr[r] == addr) - break; - - if (r == ep->max_regions - 1) - return; - - cdns_pcie_reset_outbound_region(pcie, r); - - ep->ob_addr[r] = 0; - clear_bit(r, &ep->ob_region_map); -} - -static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 mmc) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - struct cdns_pcie *pcie = &ep->pcie; - u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET; - u16 flags; - - /* - * Set the Multiple Message Capable bitfield into the Message Control - * register. - */ - flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); - flags = (flags & ~PCI_MSI_FLAGS_QMASK) | (mmc << 1); - flags |= PCI_MSI_FLAGS_64BIT; - flags &= ~PCI_MSI_FLAGS_MASKBIT; - cdns_pcie_ep_fn_writew(pcie, fn, cap + PCI_MSI_FLAGS, flags); - - return 0; -} - -static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) -{ - 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; - - /* Validate that the MSI feature is actually enabled. */ - flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); - if (!(flags & PCI_MSI_FLAGS_ENABLE)) - return -EINVAL; - - /* - * Get the Multiple Message Enable bitfield from the Message Control - * register. - */ - mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4; - - return mme; -} - -static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, - u8 intx, bool is_asserted) -{ - struct cdns_pcie *pcie = &ep->pcie; - u32 offset; - u16 status; - u8 msg_code; - - intx &= 3; - - /* Set the outbound region if needed. */ - if (unlikely(ep->irq_pci_addr != CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY || - ep->irq_pci_fn != fn)) { - /* First region was reserved for IRQ writes. */ - cdns_pcie_set_outbound_region_for_normal_msg(pcie, fn, 0, - ep->irq_phys_addr); - ep->irq_pci_addr = CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY; - ep->irq_pci_fn = fn; - } - - if (is_asserted) { - ep->irq_pending |= BIT(intx); - msg_code = MSG_CODE_ASSERT_INTA + intx; - } else { - ep->irq_pending &= ~BIT(intx); - msg_code = MSG_CODE_DEASSERT_INTA + intx; - } - - status = cdns_pcie_ep_fn_readw(pcie, fn, PCI_STATUS); - if (((status & PCI_STATUS_INTERRUPT) != 0) ^ (ep->irq_pending != 0)) { - status ^= PCI_STATUS_INTERRUPT; - cdns_pcie_ep_fn_writew(pcie, fn, PCI_STATUS, status); - } - - offset = CDNS_PCIE_NORMAL_MSG_ROUTING(MSG_ROUTING_LOCAL) | - CDNS_PCIE_NORMAL_MSG_CODE(msg_code) | - CDNS_PCIE_MSG_NO_DATA; - writel(0, ep->irq_cpu_addr + offset); -} - -static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 intx) -{ - u16 cmd; - - cmd = cdns_pcie_ep_fn_readw(&ep->pcie, fn, PCI_COMMAND); - if (cmd & PCI_COMMAND_INTX_DISABLE) - return -EINVAL; - - cdns_pcie_ep_assert_intx(ep, fn, intx, true); - /* - * The mdelay() value was taken from dra7xx_pcie_raise_legacy_irq() - * from drivers/pci/dwc/pci-dra7xx.c - */ - mdelay(1); - cdns_pcie_ep_assert_intx(ep, fn, intx, false); - return 0; -} - -static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, - u8 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; - - /* Check whether the MSI feature has been enabled by the PCI host. */ - flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); - if (!(flags & PCI_MSI_FLAGS_ENABLE)) - return -EINVAL; - - /* Get the number of enabled MSIs */ - mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4; - msi_count = 1 << mme; - if (!interrupt_num || interrupt_num > msi_count) - return -EINVAL; - - /* Compute the data value to be written. */ - data_mask = msi_count - 1; - data = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_DATA_64); - data = (data & ~data_mask) | ((interrupt_num - 1) & data_mask); - - /* Get the PCI address where to write the data into. */ - pci_addr = cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_HI); - pci_addr <<= 32; - pci_addr |= cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_LO); - pci_addr &= GENMASK_ULL(63, 2); - - /* Set the outbound region if needed. */ - if (unlikely(ep->irq_pci_addr != (pci_addr & ~pci_addr_mask) || - ep->irq_pci_fn != fn)) { - /* First region was reserved for IRQ writes. */ - cdns_pcie_set_outbound_region(pcie, fn, 0, - false, - ep->irq_phys_addr, - pci_addr & ~pci_addr_mask, - pci_addr_mask + 1); - ep->irq_pci_addr = (pci_addr & ~pci_addr_mask); - ep->irq_pci_fn = fn; - } - writel(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask)); - - return 0; -} - -static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, - enum pci_epc_irq_type type, - u16 interrupt_num) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - - switch (type) { - case PCI_EPC_IRQ_LEGACY: - return cdns_pcie_ep_send_legacy_irq(ep, fn, 0); - - case PCI_EPC_IRQ_MSI: - return cdns_pcie_ep_send_msi_irq(ep, fn, interrupt_num); - - default: - break; - } - - return -EINVAL; -} - -static int cdns_pcie_ep_start(struct pci_epc *epc) -{ - struct cdns_pcie_ep *ep = epc_get_drvdata(epc); - struct cdns_pcie *pcie = &ep->pcie; - struct pci_epf *epf; - u32 cfg; - - /* - * BIT(0) is hardwired to 1, hence function 0 is always enabled - * and can't be disabled anyway. - */ - cfg = BIT(0); - list_for_each_entry(epf, &epc->pci_epf, list) - cfg |= BIT(epf->func_no); - cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, cfg); - - /* - * The PCIe links are automatically established by the controller - * once for all at powerup: the software can neither start nor stop - * those links later at runtime. - * - * Then we only have to notify the EP core that our links are already - * established. However we don't call directly pci_epc_linkup() because - * we've already locked the epc->lock. - */ - list_for_each_entry(epf, &epc->pci_epf, list) - pci_epf_linkup(epf); - - return 0; -} - -static const struct pci_epc_ops cdns_pcie_epc_ops = { - .write_header = cdns_pcie_ep_write_header, - .set_bar = cdns_pcie_ep_set_bar, - .clear_bar = cdns_pcie_ep_clear_bar, - .map_addr = cdns_pcie_ep_map_addr, - .unmap_addr = cdns_pcie_ep_unmap_addr, - .set_msi = cdns_pcie_ep_set_msi, - .get_msi = cdns_pcie_ep_get_msi, - .raise_irq = cdns_pcie_ep_raise_irq, - .start = cdns_pcie_ep_start, -}; - -static const struct of_device_id cdns_pcie_ep_of_match[] = { - { .compatible = "cdns,cdns-pcie-ep" }, - - { }, -}; - -static int cdns_pcie_ep_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; - struct cdns_pcie_ep *ep; - struct cdns_pcie *pcie; - struct pci_epc *epc; - struct resource *res; - int ret; - int phy_count; - - ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); - if (!ep) - return -ENOMEM; - - pcie = &ep->pcie; - pcie->is_rc = false; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "reg"); - pcie->reg_base = devm_ioremap_resource(dev, res); - if (IS_ERR(pcie->reg_base)) { - dev_err(dev, "missing \"reg\"\n"); - return PTR_ERR(pcie->reg_base); - } - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mem"); - if (!res) { - dev_err(dev, "missing \"mem\"\n"); - return -EINVAL; - } - pcie->mem_res = res; - - ret = of_property_read_u32(np, "cdns,max-outbound-regions", - &ep->max_regions); - if (ret < 0) { - dev_err(dev, "missing \"cdns,max-outbound-regions\"\n"); - return ret; - } - ep->ob_addr = devm_kcalloc(dev, - ep->max_regions, sizeof(*ep->ob_addr), - GFP_KERNEL); - if (!ep->ob_addr) - return -ENOMEM; - - ret = cdns_pcie_init_phy(dev, pcie); - if (ret) { - dev_err(dev, "failed to init phy\n"); - return ret; - } - platform_set_drvdata(pdev, pcie); - pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); - if (ret < 0) { - dev_err(dev, "pm_runtime_get_sync() failed\n"); - goto err_get_sync; - } - - /* Disable all but function 0 (anyway BIT(0) is hardwired to 1). */ - cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, BIT(0)); - - epc = devm_pci_epc_create(dev, &cdns_pcie_epc_ops); - if (IS_ERR(epc)) { - dev_err(dev, "failed to create epc device\n"); - ret = PTR_ERR(epc); - goto err_init; - } - - epc_set_drvdata(epc, ep); - - if (of_property_read_u8(np, "max-functions", &epc->max_functions) < 0) - epc->max_functions = 1; - - ret = pci_epc_mem_init(epc, pcie->mem_res->start, - resource_size(pcie->mem_res)); - if (ret < 0) { - dev_err(dev, "failed to initialize the memory space\n"); - goto err_init; - } - - ep->irq_cpu_addr = pci_epc_mem_alloc_addr(epc, &ep->irq_phys_addr, - SZ_128K); - if (!ep->irq_cpu_addr) { - dev_err(dev, "failed to reserve memory space for MSI\n"); - ret = -ENOMEM; - goto free_epc_mem; - } - ep->irq_pci_addr = CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE; - /* Reserve region 0 for IRQs */ - set_bit(0, &ep->ob_region_map); - - return 0; - - free_epc_mem: - pci_epc_mem_exit(epc); - - err_init: - pm_runtime_put_sync(dev); - - err_get_sync: - pm_runtime_disable(dev); - cdns_pcie_disable_phy(pcie); - phy_count = pcie->phy_count; - while (phy_count--) - device_link_del(pcie->link[phy_count]); - - return ret; -} - -static void cdns_pcie_ep_shutdown(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct cdns_pcie *pcie = dev_get_drvdata(dev); - int ret; - - ret = pm_runtime_put_sync(dev); - if (ret < 0) - dev_dbg(dev, "pm_runtime_put_sync failed\n"); - - pm_runtime_disable(dev); - - cdns_pcie_disable_phy(pcie); -} - -static struct platform_driver cdns_pcie_ep_driver = { - .driver = { - .name = "cdns-pcie-ep", - .of_match_table = cdns_pcie_ep_of_match, - .pm = &cdns_pcie_pm_ops, - }, - .probe = cdns_pcie_ep_probe, - .shutdown = cdns_pcie_ep_shutdown, -}; -builtin_platform_driver(cdns_pcie_ep_driver); diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c deleted file mode 100644 index 97e251090b4f..000000000000 --- a/drivers/pci/controller/pcie-cadence-host.c +++ /dev/null @@ -1,362 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (c) 2017 Cadence -// Cadence PCIe host controller driver. -// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> - -#include <linux/kernel.h> -#include <linux/of_address.h> -#include <linux/of_pci.h> -#include <linux/platform_device.h> -#include <linux/pm_runtime.h> - -#include "pcie-cadence.h" - -/** - * struct cdns_pcie_rc - private data for this PCIe Root Complex driver - * @pcie: Cadence PCIe controller - * @dev: pointer to PCIe device - * @cfg_res: start/end offsets in the physical system memory to map PCI - * configuration space accesses - * @bus_range: first/last buses behind the PCIe host controller - * @cfg_base: IO mapped window to access the PCI configuration space of a - * single function at a time - * @max_regions: maximum number of regions supported by the hardware - * @no_bar_nbits: Number of bits to keep for inbound (PCIe -> CPU) address - * translation (nbits sets into the "no BAR match" register) - * @vendor_id: PCI vendor ID - * @device_id: PCI device ID - */ -struct cdns_pcie_rc { - struct cdns_pcie pcie; - struct device *dev; - struct resource *cfg_res; - struct resource *bus_range; - void __iomem *cfg_base; - u32 max_regions; - u32 no_bar_nbits; - u16 vendor_id; - u16 device_id; -}; - -static void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, - int where) -{ - struct pci_host_bridge *bridge = pci_find_host_bridge(bus); - struct cdns_pcie_rc *rc = pci_host_bridge_priv(bridge); - struct cdns_pcie *pcie = &rc->pcie; - unsigned int busn = bus->number; - u32 addr0, desc0; - - if (busn == rc->bus_range->start) { - /* - * Only the root port (devfn == 0) is connected to this bus. - * All other PCI devices are behind some bridge hence on another - * bus. - */ - if (devfn) - return NULL; - - return pcie->reg_base + (where & 0xfff); - } - /* Check that the link is up */ - if (!(cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE) & 0x1)) - return NULL; - /* Clear AXI link-down status */ - cdns_pcie_writel(pcie, CDNS_PCIE_AT_LINKDOWN, 0x0); - - /* Update Output registers for AXI region 0. */ - addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(12) | - CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) | - CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_BUS(busn); - cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR0(0), addr0); - - /* Configuration Type 0 or Type 1 access. */ - desc0 = CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID | - CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(0); - /* - * The bus number was already set once for all in desc1 by - * cdns_pcie_host_init_address_translation(). - */ - if (busn == rc->bus_range->start + 1) - desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE0; - else - desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE1; - cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC0(0), desc0); - - return rc->cfg_base + (where & 0xfff); -} - -static struct pci_ops cdns_pcie_host_ops = { - .map_bus = cdns_pci_map_bus, - .read = pci_generic_config_read, - .write = pci_generic_config_write, -}; - -static const struct of_device_id cdns_pcie_host_of_match[] = { - { .compatible = "cdns,cdns-pcie-host" }, - - { }, -}; - -static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) -{ - struct cdns_pcie *pcie = &rc->pcie; - u32 value, ctrl; - - /* - * Set the root complex BAR configuration register: - * - disable both BAR0 and BAR1. - * - enable Prefetchable Memory Base and Limit registers in type 1 - * config space (64 bits). - * - enable IO Base and Limit registers in type 1 config - * space (32 bits). - */ - ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED; - value = CDNS_PCIE_LM_RC_BAR_CFG_BAR0_CTRL(ctrl) | - CDNS_PCIE_LM_RC_BAR_CFG_BAR1_CTRL(ctrl) | - CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE | - CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS | - CDNS_PCIE_LM_RC_BAR_CFG_IO_ENABLE | - CDNS_PCIE_LM_RC_BAR_CFG_IO_32BITS; - cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); - - /* Set root port configuration space */ - if (rc->vendor_id != 0xffff) - cdns_pcie_rp_writew(pcie, PCI_VENDOR_ID, rc->vendor_id); - if (rc->device_id != 0xffff) - cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id); - - cdns_pcie_rp_writeb(pcie, PCI_CLASS_REVISION, 0); - cdns_pcie_rp_writeb(pcie, PCI_CLASS_PROG, 0); - cdns_pcie_rp_writew(pcie, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_PCI); - - return 0; -} - -static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc) -{ - struct cdns_pcie *pcie = &rc->pcie; - struct resource *cfg_res = rc->cfg_res; - struct resource *mem_res = pcie->mem_res; - struct resource *bus_range = rc->bus_range; - struct device *dev = rc->dev; - struct device_node *np = dev->of_node; - struct of_pci_range_parser parser; - struct of_pci_range range; - u32 addr0, addr1, desc1; - u64 cpu_addr; - int r, err; - - /* - * Reserve region 0 for PCI configure space accesses: - * OB_REGION_PCI_ADDR0 and OB_REGION_DESC0 are updated dynamically by - * cdns_pci_map_bus(), other region registers are set here once for all. - */ - addr1 = 0; /* Should be programmed to zero. */ - desc1 = CDNS_PCIE_AT_OB_REGION_DESC1_BUS(bus_range->start); - 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); - - cpu_addr = cfg_res->start - mem_res->start; - addr0 = CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS(12) | - (lower_32_bits(cpu_addr) & GENMASK(31, 8)); - addr1 = upper_32_bits(cpu_addr); - cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(0), addr0); - cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(0), addr1); - - err = of_pci_range_parser_init(&parser, np); - if (err) - return err; - - r = 1; - for_each_of_pci_range(&parser, &range) { - bool is_io; - - if (r >= rc->max_regions) - break; - - if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_MEM) - is_io = false; - else if ((range.flags & IORESOURCE_TYPE_BITS) == IORESOURCE_IO) - is_io = true; - else - continue; - - cdns_pcie_set_outbound_region(pcie, 0, r, is_io, - range.cpu_addr, - range.pci_addr, - range.size); - r++; - } - - /* - * Set Root Port no BAR match Inbound Translation registers: - * needed for MSI and DMA. - * Root Port BAR0 and BAR1 are disabled, hence no need to set their - * inbound translation registers. - */ - addr0 = CDNS_PCIE_AT_IB_RP_BAR_ADDR0_NBITS(rc->no_bar_nbits); - addr1 = 0; - cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR0(RP_NO_BAR), addr0); - cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR1(RP_NO_BAR), addr1); - - return 0; -} - -static int cdns_pcie_host_init(struct device *dev, - struct list_head *resources, - struct cdns_pcie_rc *rc) -{ - struct resource *bus_range = NULL; - int err; - - /* Parse our PCI ranges and request their resources */ - err = pci_parse_request_of_pci_ranges(dev, resources, &bus_range); - if (err) - return err; - - rc->bus_range = bus_range; - rc->pcie.bus = bus_range->start; - - err = cdns_pcie_host_init_root_port(rc); - if (err) - goto err_out; - - err = cdns_pcie_host_init_address_translation(rc); - if (err) - goto err_out; - - return 0; - - err_out: - pci_free_resource_list(resources); - return err; -} - -static int cdns_pcie_host_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct device_node *np = dev->of_node; - struct pci_host_bridge *bridge; - struct list_head resources; - struct cdns_pcie_rc *rc; - struct cdns_pcie *pcie; - struct resource *res; - int ret; - int phy_count; - - bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); - if (!bridge) - return -ENOMEM; - - rc = pci_host_bridge_priv(bridge); - rc->dev = dev; - - pcie = &rc->pcie; - pcie->is_rc = true; - - rc->max_regions = 32; - of_property_read_u32(np, "cdns,max-outbound-regions", &rc->max_regions); - - rc->no_bar_nbits = 32; - of_property_read_u32(np, "cdns,no-bar-match-nbits", &rc->no_bar_nbits); - - rc->vendor_id = 0xffff; - of_property_read_u16(np, "vendor-id", &rc->vendor_id); - - rc->device_id = 0xffff; - of_property_read_u16(np, "device-id", &rc->device_id); - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "reg"); - pcie->reg_base = devm_ioremap_resource(dev, res); - if (IS_ERR(pcie->reg_base)) { - dev_err(dev, "missing \"reg\"\n"); - return PTR_ERR(pcie->reg_base); - } - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); - rc->cfg_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(rc->cfg_base)) { - dev_err(dev, "missing \"cfg\"\n"); - return PTR_ERR(rc->cfg_base); - } - rc->cfg_res = res; - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mem"); - if (!res) { - dev_err(dev, "missing \"mem\"\n"); - return -EINVAL; - } - pcie->mem_res = res; - - ret = cdns_pcie_init_phy(dev, pcie); - if (ret) { - dev_err(dev, "failed to init phy\n"); - return ret; - } - platform_set_drvdata(pdev, pcie); - - pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); - if (ret < 0) { - dev_err(dev, "pm_runtime_get_sync() failed\n"); - goto err_get_sync; - } - - ret = cdns_pcie_host_init(dev, &resources, rc); - if (ret) - goto err_init; - - list_splice_init(&resources, &bridge->windows); - bridge->dev.parent = dev; - bridge->busnr = pcie->bus; - bridge->ops = &cdns_pcie_host_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - - ret = pci_host_probe(bridge); - if (ret < 0) - goto err_host_probe; - - return 0; - - err_host_probe: - pci_free_resource_list(&resources); - - err_init: - pm_runtime_put_sync(dev); - - err_get_sync: - pm_runtime_disable(dev); - cdns_pcie_disable_phy(pcie); - phy_count = pcie->phy_count; - while (phy_count--) - device_link_del(pcie->link[phy_count]); - - return ret; -} - -static void cdns_pcie_shutdown(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct cdns_pcie *pcie = dev_get_drvdata(dev); - int ret; - - ret = pm_runtime_put_sync(dev); - if (ret < 0) - dev_dbg(dev, "pm_runtime_put_sync failed\n"); - - pm_runtime_disable(dev); - cdns_pcie_disable_phy(pcie); -} - -static struct platform_driver cdns_pcie_host_driver = { - .driver = { - .name = "cdns-pcie-host", - .of_match_table = cdns_pcie_host_of_match, - .pm = &cdns_pcie_pm_ops, - }, - .probe = cdns_pcie_host_probe, - .shutdown = cdns_pcie_shutdown, -}; -builtin_platform_driver(cdns_pcie_host_driver); diff --git a/drivers/pci/controller/pcie-hisi-error.c b/drivers/pci/controller/pcie-hisi-error.c new file mode 100644 index 000000000000..aaf1ed2b6e59 --- /dev/null +++ b/drivers/pci/controller/pcie-hisi-error.c @@ -0,0 +1,324 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for handling the PCIe controller errors on + * HiSilicon HIP SoCs. + * + * Copyright (c) 2020 HiSilicon Limited. + */ + +#include <linux/acpi.h> +#include <acpi/ghes.h> +#include <linux/bitops.h> +#include <linux/delay.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/kfifo.h> +#include <linux/spinlock.h> + +/* HISI PCIe controller error definitions */ +#define HISI_PCIE_ERR_MISC_REGS 33 + +#define HISI_PCIE_LOCAL_VALID_VERSION BIT(0) +#define HISI_PCIE_LOCAL_VALID_SOC_ID BIT(1) +#define HISI_PCIE_LOCAL_VALID_SOCKET_ID BIT(2) +#define HISI_PCIE_LOCAL_VALID_NIMBUS_ID BIT(3) +#define HISI_PCIE_LOCAL_VALID_SUB_MODULE_ID BIT(4) +#define HISI_PCIE_LOCAL_VALID_CORE_ID BIT(5) +#define HISI_PCIE_LOCAL_VALID_PORT_ID BIT(6) +#define HISI_PCIE_LOCAL_VALID_ERR_TYPE BIT(7) +#define HISI_PCIE_LOCAL_VALID_ERR_SEVERITY BIT(8) +#define HISI_PCIE_LOCAL_VALID_ERR_MISC 9 + +static guid_t hisi_pcie_sec_guid = + GUID_INIT(0xB2889FC9, 0xE7D7, 0x4F9D, + 0xA8, 0x67, 0xAF, 0x42, 0xE9, 0x8B, 0xE7, 0x72); + +/* + * Firmware reports the socket port ID where the error occurred. These + * macros convert that to the core ID and core port ID required by the + * ACPI reset method. + */ +#define HISI_PCIE_PORT_ID(core, v) (((v) >> 1) + ((core) << 3)) +#define HISI_PCIE_CORE_ID(v) ((v) >> 3) +#define HISI_PCIE_CORE_PORT_ID(v) (((v) & 7) << 1) + +struct hisi_pcie_error_data { + u64 val_bits; + u8 version; + u8 soc_id; + u8 socket_id; + u8 nimbus_id; + u8 sub_module_id; + u8 core_id; + u8 port_id; + u8 err_severity; + u16 err_type; + u8 reserv[2]; + u32 err_misc[HISI_PCIE_ERR_MISC_REGS]; +}; + +struct hisi_pcie_error_private { + struct notifier_block nb; + struct device *dev; +}; + +enum hisi_pcie_submodule_id { + HISI_PCIE_SUB_MODULE_ID_AP, + HISI_PCIE_SUB_MODULE_ID_TL, + HISI_PCIE_SUB_MODULE_ID_MAC, + HISI_PCIE_SUB_MODULE_ID_DL, + HISI_PCIE_SUB_MODULE_ID_SDI, +}; + +static const char * const hisi_pcie_sub_module[] = { + [HISI_PCIE_SUB_MODULE_ID_AP] = "AP Layer", + [HISI_PCIE_SUB_MODULE_ID_TL] = "TL Layer", + [HISI_PCIE_SUB_MODULE_ID_MAC] = "MAC Layer", + [HISI_PCIE_SUB_MODULE_ID_DL] = "DL Layer", + [HISI_PCIE_SUB_MODULE_ID_SDI] = "SDI Layer", +}; + +enum hisi_pcie_err_severity { + HISI_PCIE_ERR_SEV_RECOVERABLE, + HISI_PCIE_ERR_SEV_FATAL, + HISI_PCIE_ERR_SEV_CORRECTED, + HISI_PCIE_ERR_SEV_NONE, +}; + +static const char * const hisi_pcie_error_sev[] = { + [HISI_PCIE_ERR_SEV_RECOVERABLE] = "recoverable", + [HISI_PCIE_ERR_SEV_FATAL] = "fatal", + [HISI_PCIE_ERR_SEV_CORRECTED] = "corrected", + [HISI_PCIE_ERR_SEV_NONE] = "none", +}; + +static const char *hisi_pcie_get_string(const char * const *array, + size_t n, u32 id) +{ + u32 index; + + for (index = 0; index < n; index++) { + if (index == id && array[index]) + return array[index]; + } + + return "unknown"; +} + +static int hisi_pcie_port_reset(struct platform_device *pdev, + u32 chip_id, u32 port_id) +{ + struct device *dev = &pdev->dev; + acpi_handle handle = ACPI_HANDLE(dev); + union acpi_object arg[3]; + struct acpi_object_list arg_list; + acpi_status s; + unsigned long long data = 0; + + arg[0].type = ACPI_TYPE_INTEGER; + arg[0].integer.value = chip_id; + arg[1].type = ACPI_TYPE_INTEGER; + arg[1].integer.value = HISI_PCIE_CORE_ID(port_id); + arg[2].type = ACPI_TYPE_INTEGER; + arg[2].integer.value = HISI_PCIE_CORE_PORT_ID(port_id); + + arg_list.count = 3; + arg_list.pointer = arg; + + s = acpi_evaluate_integer(handle, "RST", &arg_list, &data); + if (ACPI_FAILURE(s)) { + dev_err(dev, "No RST method\n"); + return -EIO; + } + + if (data) { + dev_err(dev, "Failed to Reset\n"); + return -EIO; + } + + return 0; +} + +static int hisi_pcie_port_do_recovery(struct platform_device *dev, + u32 chip_id, u32 port_id) +{ + acpi_status s; + struct device *device = &dev->dev; + acpi_handle root_handle = ACPI_HANDLE(device); + struct acpi_pci_root *pci_root; + struct pci_bus *root_bus; + struct pci_dev *pdev; + u32 domain, busnr, devfn; + + s = acpi_get_parent(root_handle, &root_handle); + if (ACPI_FAILURE(s)) + return -ENODEV; + pci_root = acpi_pci_find_root(root_handle); + if (!pci_root) + return -ENODEV; + root_bus = pci_root->bus; + domain = pci_root->segment; + + busnr = root_bus->number; + devfn = PCI_DEVFN(port_id, 0); + pdev = pci_get_domain_bus_and_slot(domain, busnr, devfn); + if (!pdev) { + dev_info(device, "Fail to get root port %04x:%02x:%02x.%d device\n", + domain, busnr, PCI_SLOT(devfn), PCI_FUNC(devfn)); + return -ENODEV; + } + + pci_stop_and_remove_bus_device_locked(pdev); + pci_dev_put(pdev); + + if (hisi_pcie_port_reset(dev, chip_id, port_id)) + return -EIO; + + /* + * The initialization time of subordinate devices after + * hot reset is no more than 1s, which is required by + * the PCI spec v5.0 sec 6.6.1. The time will shorten + * if Readiness Notifications mechanisms are used. But + * wait 1s here to adapt any conditions. + */ + ssleep(1UL); + + /* add root port and downstream devices */ + pci_lock_rescan_remove(); + pci_rescan_bus(root_bus); + pci_unlock_rescan_remove(); + + return 0; +} + +static void hisi_pcie_handle_error(struct platform_device *pdev, + const struct hisi_pcie_error_data *edata) +{ + struct device *dev = &pdev->dev; + int idx, rc; + const unsigned long valid_bits[] = {BITMAP_FROM_U64(edata->val_bits)}; + + if (edata->val_bits == 0) { + dev_warn(dev, "%s: no valid error information\n", __func__); + return; + } + + dev_info(dev, "\nHISI : HIP : PCIe controller error\n"); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_SOC_ID) + dev_info(dev, "Table version = %d\n", edata->version); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_SOCKET_ID) + dev_info(dev, "Socket ID = %d\n", edata->socket_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_NIMBUS_ID) + dev_info(dev, "Nimbus ID = %d\n", edata->nimbus_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_SUB_MODULE_ID) + dev_info(dev, "Sub Module = %s\n", + hisi_pcie_get_string(hisi_pcie_sub_module, + ARRAY_SIZE(hisi_pcie_sub_module), + edata->sub_module_id)); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_CORE_ID) + dev_info(dev, "Core ID = core%d\n", edata->core_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_PORT_ID) + dev_info(dev, "Port ID = port%d\n", edata->port_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_ERR_SEVERITY) + dev_info(dev, "Error severity = %s\n", + hisi_pcie_get_string(hisi_pcie_error_sev, + ARRAY_SIZE(hisi_pcie_error_sev), + edata->err_severity)); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_ERR_TYPE) + dev_info(dev, "Error type = 0x%x\n", edata->err_type); + + dev_info(dev, "Reg Dump:\n"); + idx = HISI_PCIE_LOCAL_VALID_ERR_MISC; + for_each_set_bit_from(idx, valid_bits, + HISI_PCIE_LOCAL_VALID_ERR_MISC + HISI_PCIE_ERR_MISC_REGS) + dev_info(dev, "ERR_MISC_%d = 0x%x\n", idx - HISI_PCIE_LOCAL_VALID_ERR_MISC, + edata->err_misc[idx - HISI_PCIE_LOCAL_VALID_ERR_MISC]); + + if (edata->err_severity != HISI_PCIE_ERR_SEV_RECOVERABLE) + return; + + /* Recovery for the PCIe controller errors, try reset + * PCI port for the error recovery + */ + rc = hisi_pcie_port_do_recovery(pdev, edata->socket_id, + HISI_PCIE_PORT_ID(edata->core_id, edata->port_id)); + if (rc) + dev_info(dev, "fail to do hisi pcie port reset\n"); +} + +static int hisi_pcie_notify_error(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct acpi_hest_generic_data *gdata = data; + const struct hisi_pcie_error_data *error_data = acpi_hest_get_payload(gdata); + struct hisi_pcie_error_private *priv; + struct device *dev; + struct platform_device *pdev; + guid_t err_sec_guid; + u8 socket; + + import_guid(&err_sec_guid, gdata->section_type); + if (!guid_equal(&err_sec_guid, &hisi_pcie_sec_guid)) + return NOTIFY_DONE; + + priv = container_of(nb, struct hisi_pcie_error_private, nb); + dev = priv->dev; + + if (device_property_read_u8(dev, "socket", &socket)) + return NOTIFY_DONE; + + if (error_data->socket_id != socket) + return NOTIFY_DONE; + + pdev = container_of(dev, struct platform_device, dev); + hisi_pcie_handle_error(pdev, error_data); + + return NOTIFY_OK; +} + +static int hisi_pcie_error_handler_probe(struct platform_device *pdev) +{ + struct hisi_pcie_error_private *priv; + int ret; + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->nb.notifier_call = hisi_pcie_notify_error; + priv->dev = &pdev->dev; + ret = ghes_register_vendor_record_notifier(&priv->nb); + if (ret) { + dev_err(&pdev->dev, + "Failed to register hisi pcie controller error handler with apei\n"); + return ret; + } + + platform_set_drvdata(pdev, priv); + + return 0; +} + +static void hisi_pcie_error_handler_remove(struct platform_device *pdev) +{ + struct hisi_pcie_error_private *priv = platform_get_drvdata(pdev); + + ghes_unregister_vendor_record_notifier(&priv->nb); +} + +static const struct acpi_device_id hisi_pcie_acpi_match[] = { + { "HISI0361", 0 }, + { } +}; + +static struct platform_driver hisi_pcie_error_handler_driver = { + .driver = { + .name = "hisi-pcie-error-handler", + .acpi_match_table = hisi_pcie_acpi_match, + }, + .probe = hisi_pcie_error_handler_probe, + .remove = hisi_pcie_error_handler_remove, +}; +module_platform_driver(hisi_pcie_error_handler_driver); + +MODULE_DESCRIPTION("HiSilicon HIP PCIe controller error handling driver"); diff --git a/drivers/pci/controller/pcie-iproc-bcma.c b/drivers/pci/controller/pcie-iproc-bcma.c index aa55b064f64d..99a99900444d 100644 --- a/drivers/pci/controller/pcie-iproc-bcma.c +++ b/drivers/pci/controller/pcie-iproc-bcma.c @@ -18,12 +18,12 @@ /* NS: CLASS field is R/O, and set to wrong 0x200 value */ static void bcma_pcie2_fixup_class(struct pci_dev *dev) { - dev->class = PCI_CLASS_BRIDGE_PCI << 8; + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8011, bcma_pcie2_fixup_class); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8012, bcma_pcie2_fixup_class); -static int iproc_pcie_bcma_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int iproc_bcma_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { struct iproc_pcie *pcie = dev->sysdata; struct bcma_device *bdev = container_of(pcie->dev, struct bcma_device, dev); @@ -31,11 +31,10 @@ static int iproc_pcie_bcma_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return bcma_core_irq(bdev, 5); } -static int iproc_pcie_bcma_probe(struct bcma_device *bdev) +static int iproc_bcma_pcie_probe(struct bcma_device *bdev) { struct device *dev = &bdev->dev; struct iproc_pcie *pcie; - LIST_HEAD(resources); struct pci_host_bridge *bridge; int ret; @@ -60,52 +59,38 @@ static int iproc_pcie_bcma_probe(struct bcma_device *bdev) pcie->mem.end = bdev->addr_s[0] + SZ_128M - 1; pcie->mem.name = "PCIe MEM space"; pcie->mem.flags = IORESOURCE_MEM; - pci_add_resource(&resources, &pcie->mem); - - pcie->map_irq = iproc_pcie_bcma_map_irq; - - ret = iproc_pcie_setup(pcie, &resources); - if (ret) { - dev_err(dev, "PCIe controller setup failed\n"); - pci_free_resource_list(&resources); + pci_add_resource(&bridge->windows, &pcie->mem); + ret = devm_request_pci_bus_resources(dev, &bridge->windows); + if (ret) return ret; - } + + pcie->map_irq = iproc_bcma_pcie_map_irq; bcma_set_drvdata(bdev, pcie); - return 0; + + return iproc_pcie_setup(pcie, &bridge->windows); } -static void iproc_pcie_bcma_remove(struct bcma_device *bdev) +static void iproc_bcma_pcie_remove(struct bcma_device *bdev) { struct iproc_pcie *pcie = bcma_get_drvdata(bdev); iproc_pcie_remove(pcie); } -static const struct bcma_device_id iproc_pcie_bcma_table[] = { +static const struct bcma_device_id iproc_bcma_pcie_table[] = { BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_NS_PCIEG2, BCMA_ANY_REV, BCMA_ANY_CLASS), {}, }; -MODULE_DEVICE_TABLE(bcma, iproc_pcie_bcma_table); +MODULE_DEVICE_TABLE(bcma, iproc_bcma_pcie_table); -static struct bcma_driver iproc_pcie_bcma_driver = { +static struct bcma_driver iproc_bcma_pcie_driver = { .name = KBUILD_MODNAME, - .id_table = iproc_pcie_bcma_table, - .probe = iproc_pcie_bcma_probe, - .remove = iproc_pcie_bcma_remove, + .id_table = iproc_bcma_pcie_table, + .probe = iproc_bcma_pcie_probe, + .remove = iproc_bcma_pcie_remove, }; - -static int __init iproc_pcie_bcma_init(void) -{ - return bcma_driver_register(&iproc_pcie_bcma_driver); -} -module_init(iproc_pcie_bcma_init); - -static void __exit iproc_pcie_bcma_exit(void) -{ - bcma_driver_unregister(&iproc_pcie_bcma_driver); -} -module_exit(iproc_pcie_bcma_exit); +module_bcma_driver(iproc_bcma_pcie_driver); MODULE_AUTHOR("Hauke Mehrtens"); MODULE_DESCRIPTION("Broadcom iProc PCIe BCMA driver"); diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c index cb3401a931f8..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> @@ -49,7 +50,7 @@ enum iproc_msi_reg { struct iproc_msi; /** - * iProc MSI group + * struct iproc_msi_grp - iProc MSI group * * One MSI group is allocated per GIC interrupt, serviced by one iProc MSI * event queue. @@ -65,7 +66,7 @@ struct iproc_msi_grp { }; /** - * iProc event queue based MSI + * struct iproc_msi - iProc event queue based MSI * * Only meant to be used on platforms without MSI support integrated into the * GIC. @@ -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_MULTI_PCI_MSI | 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. @@ -209,15 +210,20 @@ static int iproc_msi_irq_set_affinity(struct irq_data *data, struct iproc_msi *msi = irq_data_get_irq_chip_data(data); int target_cpu = cpumask_first(mask); int curr_cpu; + int ret; curr_cpu = hwirq_to_cpu(msi, data->hwirq); if (curr_cpu == target_cpu) - return IRQ_SET_MASK_OK_DONE; + ret = IRQ_SET_MASK_OK_DONE; + else { + /* steer MSI to the target CPU */ + data->hwirq = hwirq_to_canonical_hwirq(msi, data->hwirq) + target_cpu; + ret = IRQ_SET_MASK_OK; + } - /* steer MSI to the target CPU */ - data->hwirq = hwirq_to_canonical_hwirq(msi, data->hwirq) + target_cpu; + irq_data_update_effective_affinity(data, cpumask_of(target_cpu)); - return IRQ_SET_MASK_OK; + return ret; } static void iproc_msi_irq_compose_msi_msg(struct irq_data *data, @@ -245,20 +251,23 @@ static int iproc_msi_irq_domain_alloc(struct irq_domain *domain, struct iproc_msi *msi = domain->host_data; int hwirq, i; + if (msi->nr_cpus > 1 && nr_irqs > 1) + return -EINVAL; + mutex_lock(&msi->bitmap_lock); - /* Allocate 'nr_cpus' number of MSI vectors each time */ - hwirq = bitmap_find_next_zero_area(msi->bitmap, msi->nr_msi_vecs, 0, - msi->nr_cpus, 0); - if (hwirq < msi->nr_msi_vecs) { - bitmap_set(msi->bitmap, hwirq, msi->nr_cpus); - } else { - mutex_unlock(&msi->bitmap_lock); - return -ENOSPC; - } + /* + * Allocate 'nr_irqs' multiplied by 'nr_cpus' number of MSI vectors + * each time + */ + hwirq = bitmap_find_free_region(msi->bitmap, msi->nr_msi_vecs, + order_base_2(msi->nr_cpus * nr_irqs)); mutex_unlock(&msi->bitmap_lock); + if (hwirq < 0) + return -ENOSPC; + for (i = 0; i < nr_irqs; i++) { irq_domain_set_info(domain, virq + i, hwirq + i, &iproc_msi_bottom_irq_chip, @@ -266,7 +275,7 @@ static int iproc_msi_irq_domain_alloc(struct irq_domain *domain, NULL, NULL); } - return hwirq; + return 0; } static void iproc_msi_irq_domain_free(struct irq_domain *domain, @@ -279,7 +288,8 @@ static void iproc_msi_irq_domain_free(struct irq_domain *domain, mutex_lock(&msi->bitmap_lock); hwirq = hwirq_to_canonical_hwirq(msi, data->hwirq); - bitmap_clear(msi->bitmap, hwirq, msi->nr_cpus); + bitmap_release_region(msi->bitmap, hwirq, + order_base_2(msi->nr_cpus * nr_irqs)); mutex_unlock(&msi->bitmap_lock); @@ -293,11 +303,12 @@ static const struct irq_domain_ops msi_domain_ops = { static inline u32 decode_msi_hwirq(struct iproc_msi *msi, u32 eq, u32 head) { - u32 *msg, hwirq; + u32 __iomem *msg; + u32 hwirq; unsigned int offs; offs = iproc_msi_eq_offset(msi, eq) + head * sizeof(u32); - msg = (u32 *)(msi->eq_cpu + offs); + msg = (u32 __iomem *)(msi->eq_cpu + offs); hwirq = readl(msg); hwirq = (hwirq >> 5) + (hwirq & 0x1f); @@ -316,7 +327,6 @@ static void iproc_msi_handler(struct irq_desc *desc) struct iproc_msi *msi; u32 eq, head, tail, nr_events; unsigned long hwirq; - int virq; chained_irq_enter(chip, desc); @@ -352,8 +362,7 @@ static void iproc_msi_handler(struct irq_desc *desc) /* process all outstanding events */ while (nr_events--) { hwirq = decode_msi_hwirq(msi, eq, head); - virq = irq_find_mapping(msi->inner_domain, hwirq); - generic_handle_irq(virq); + generic_handle_domain_irq(msi->inner_domain, hwirq); head++; head %= EQ_LEN; @@ -367,7 +376,7 @@ static void iproc_msi_handler(struct irq_desc *desc) /* * Now go read the tail pointer again to see if there are new - * oustanding events that came in during the above window. + * outstanding events that came in during the above window. */ } while (true); @@ -438,27 +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); } @@ -517,7 +521,7 @@ int iproc_msi_init(struct iproc_pcie *pcie, struct device_node *node) if (!of_device_is_compatible(node, "brcm,iproc-msi")) return -ENODEV; - if (!of_find_property(node, "msi-controller", NULL)) + if (!of_property_read_bool(node, "msi-controller")) return -ENODEV; if (pcie->msi) @@ -533,6 +537,9 @@ int iproc_msi_init(struct iproc_pcie *pcie, struct device_node *node) mutex_init(&msi->bitmap_lock); msi->nr_cpus = num_possible_cpus(); + if (msi->nr_cpus == 1) + iproc_msi_parent_ops.supported_flags |= MSI_FLAG_MULTI_PCI_MSI; + msi->nr_irqs = of_irq_count(node); if (!msi->nr_irqs) { dev_err(pcie->dev, "found no MSI GIC interrupt\n"); @@ -574,12 +581,11 @@ int iproc_msi_init(struct iproc_pcie *pcie, struct device_node *node) return -EINVAL; } - if (of_find_property(node, "brcm,pcie-msi-inten", NULL)) - msi->has_inten_reg = true; + msi->has_inten_reg = of_property_read_bool(node, "brcm,pcie-msi-inten"); msi->nr_msi_vecs = msi->nr_irqs * EQ_LEN; - msi->bitmap = devm_kcalloc(pcie->dev, BITS_TO_LONGS(msi->nr_msi_vecs), - sizeof(*msi->bitmap), GFP_KERNEL); + msi->bitmap = devm_bitmap_zalloc(pcie->dev, msi->nr_msi_vecs, + GFP_KERNEL); if (!msi->bitmap) return -ENOMEM; diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c index f30f5f3fb5c1..0cb78c583c7e 100644 --- a/drivers/pci/controller/pcie-iproc-platform.c +++ b/drivers/pci/controller/pcie-iproc-platform.c @@ -12,7 +12,6 @@ #include <linux/platform_device.h> #include <linux/of_address.h> #include <linux/of_pci.h> -#include <linux/of_irq.h> #include <linux/of_platform.h> #include <linux/phy/phy.h> @@ -37,14 +36,12 @@ static const struct of_device_id iproc_pcie_of_match_table[] = { }; MODULE_DEVICE_TABLE(of, iproc_pcie_of_match_table); -static int iproc_pcie_pltfm_probe(struct platform_device *pdev) +static int iproc_pltfm_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct iproc_pcie *pcie; struct device_node *np = dev->of_node; struct resource reg; - resource_size_t iobase = 0; - LIST_HEAD(resources); struct pci_host_bridge *bridge; int ret; @@ -55,7 +52,7 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev) pcie = pci_host_bridge_priv(bridge); pcie->dev = dev; - pcie->type = (enum iproc_pcie_type) of_device_get_match_data(dev); + pcie->type = (uintptr_t)of_device_get_match_data(dev); ret = of_address_to_resource(np, 0, ®); if (ret < 0) { @@ -87,39 +84,29 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev) /* * DT nodes are not used by all platforms that use the iProc PCIe - * core driver. For platforms that require explict inbound mapping + * core driver. For platforms that require explicit inbound mapping * configuration, "dma-ranges" would have been present in DT */ pcie->need_ib_cfg = of_property_read_bool(np, "dma-ranges"); /* PHY use is optional */ - pcie->phy = devm_phy_get(dev, "pcie-phy"); - if (IS_ERR(pcie->phy)) { - if (PTR_ERR(pcie->phy) == -EPROBE_DEFER) - return -EPROBE_DEFER; - pcie->phy = NULL; - } - - ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &resources, - &iobase); - if (ret) { - dev_err(dev, "unable to get PCI host bridge resources\n"); - return ret; - } + pcie->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(pcie->phy)) + return PTR_ERR(pcie->phy); /* PAXC doesn't support legacy IRQs, skip mapping */ switch (pcie->type) { case IPROC_PCIE_PAXC: case IPROC_PCIE_PAXC_V2: + pcie->map_irq = NULL; break; default: - pcie->map_irq = of_irq_parse_and_map_pci; + break; } - ret = iproc_pcie_setup(pcie, &resources); + ret = iproc_pcie_setup(pcie, &bridge->windows); if (ret) { dev_err(dev, "PCIe controller setup failed\n"); - pci_free_resource_list(&resources); return ret; } @@ -127,30 +114,30 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev) return 0; } -static int iproc_pcie_pltfm_remove(struct platform_device *pdev) +static void iproc_pltfm_pcie_remove(struct platform_device *pdev) { struct iproc_pcie *pcie = platform_get_drvdata(pdev); - return iproc_pcie_remove(pcie); + iproc_pcie_remove(pcie); } -static void iproc_pcie_pltfm_shutdown(struct platform_device *pdev) +static void iproc_pltfm_pcie_shutdown(struct platform_device *pdev) { struct iproc_pcie *pcie = platform_get_drvdata(pdev); iproc_pcie_shutdown(pcie); } -static struct platform_driver iproc_pcie_pltfm_driver = { +static struct platform_driver iproc_pltfm_pcie_driver = { .driver = { .name = "iproc-pcie", .of_match_table = of_match_ptr(iproc_pcie_of_match_table), }, - .probe = iproc_pcie_pltfm_probe, - .remove = iproc_pcie_pltfm_remove, - .shutdown = iproc_pcie_pltfm_shutdown, + .probe = iproc_pltfm_pcie_probe, + .remove = iproc_pltfm_pcie_remove, + .shutdown = iproc_pltfm_pcie_shutdown, }; -module_platform_driver(iproc_pcie_pltfm_driver); +module_platform_driver(iproc_pltfm_pcie_driver); MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>"); MODULE_DESCRIPTION("Broadcom iPROC PCIe platform driver"); diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c index c20fd6bd68fd..ccf71993ea35 100644 --- a/drivers/pci/controller/pcie-iproc.c +++ b/drivers/pci/controller/pcie-iproc.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> #include <linux/msi.h> #include <linux/clk.h> #include <linux/module.h> @@ -16,8 +17,8 @@ #include <linux/irqchip/arm-gic-v3.h> #include <linux/platform_device.h> #include <linux/of_address.h> -#include <linux/of_pci.h> #include <linux/of_irq.h> +#include <linux/of_pci.h> #include <linux/of_platform.h> #include <linux/phy/phy.h> @@ -39,16 +40,8 @@ #define CFG_IND_ADDR_MASK 0x00001ffc -#define CFG_ADDR_BUS_NUM_SHIFT 20 -#define CFG_ADDR_BUS_NUM_MASK 0x0ff00000 -#define CFG_ADDR_DEV_NUM_SHIFT 15 -#define CFG_ADDR_DEV_NUM_MASK 0x000f8000 -#define CFG_ADDR_FUNC_NUM_SHIFT 12 -#define CFG_ADDR_FUNC_NUM_MASK 0x00007000 -#define CFG_ADDR_REG_NUM_SHIFT 2 #define CFG_ADDR_REG_NUM_MASK 0x00000ffc -#define CFG_ADDR_CFG_TYPE_SHIFT 0 -#define CFG_ADDR_CFG_TYPE_MASK 0x00000003 +#define CFG_ADDR_CFG_TYPE_1 1 #define SYS_RC_INTX_MASK 0xf @@ -60,6 +53,10 @@ #define APB_ERR_EN_SHIFT 0 #define APB_ERR_EN BIT(APB_ERR_EN_SHIFT) +#define CFG_RD_SUCCESS 0 +#define CFG_RD_UR 1 +#define CFG_RD_RRS 2 +#define CFG_RD_CA 3 #define CFG_RETRY_STATUS 0xffff0001 #define CFG_RETRY_STATUS_TIMEOUT_US 500000 /* 500 milliseconds */ @@ -92,8 +89,8 @@ #define IPROC_PCIE_REG_INVALID 0xffff /** - * iProc PCIe outbound mapping controller specific parameters - * + * struct iproc_pcie_ob_map - iProc PCIe outbound mapping controller-specific + * parameters * @window_sizes: list of supported outbound mapping window sizes in MB * @nr_sizes: number of supported outbound mapping window sizes */ @@ -139,27 +136,25 @@ static const struct iproc_pcie_ob_map paxb_v2_ob_map[] = { }; /** - * iProc PCIe inbound mapping type + * enum iproc_pcie_ib_map_type - iProc PCIe inbound mapping type + * @IPROC_PCIE_IB_MAP_MEM: DDR memory + * @IPROC_PCIE_IB_MAP_IO: device I/O memory + * @IPROC_PCIE_IB_MAP_INVALID: invalid or unused */ enum iproc_pcie_ib_map_type { - /* for DDR memory */ IPROC_PCIE_IB_MAP_MEM = 0, - - /* for device I/O memory */ IPROC_PCIE_IB_MAP_IO, - - /* invalid or unused */ IPROC_PCIE_IB_MAP_INVALID }; /** - * iProc PCIe inbound mapping controller specific parameters - * + * struct iproc_pcie_ib_map - iProc PCIe inbound mapping controller-specific + * parameters * @type: inbound mapping region type * @size_unit: inbound mapping region size unit, could be SZ_1K, SZ_1M, or * SZ_1G * @region_sizes: list of supported inbound mapping region sizes in KB, MB, or - * GB, depedning on the size unit + * GB, depending on the size unit * @nr_sizes: number of supported inbound mapping region sizes * @nr_windows: number of supported inbound mapping windows for the region * @imap_addr_offset: register offset between the upper and lower 32-bit @@ -188,8 +183,15 @@ static const struct iproc_pcie_ib_map paxb_v2_ib_map[] = { .imap_window_offset = 0x4, }, { - /* IARR1/IMAP1 (currently unused) */ - .type = IPROC_PCIE_IB_MAP_INVALID, + /* IARR1/IMAP1 */ + .type = IPROC_PCIE_IB_MAP_MEM, + .size_unit = SZ_1M, + .region_sizes = { 8 }, + .nr_sizes = 1, + .nr_windows = 8, + .imap_addr_offset = 0x4, + .imap_window_offset = 0x8, + }, { /* IARR2/IMAP2 */ @@ -247,7 +249,7 @@ enum iproc_pcie_reg { /* * To hold the address of the register where the MSI writes are - * programed. When ARM GICv3 ITS is used, this should be programmed + * programmed. When ARM GICv3 ITS is used, this should be programmed * with the address of the GITS_TRANSLATER register. */ IPROC_PCIE_MSI_ADDR_LO, @@ -289,6 +291,9 @@ enum iproc_pcie_reg { IPROC_PCIE_IARR4, IPROC_PCIE_IMAP4, + /* config read status */ + IPROC_PCIE_CFG_RD_STATUS, + /* link status */ IPROC_PCIE_LINK_STATUS, @@ -300,7 +305,7 @@ enum iproc_pcie_reg { }; /* iProc PCIe PAXB BCMA registers */ -static const u16 iproc_pcie_reg_paxb_bcma[] = { +static const u16 iproc_pcie_reg_paxb_bcma[IPROC_PCIE_MAX_NUM_REG] = { [IPROC_PCIE_CLK_CTRL] = 0x000, [IPROC_PCIE_CFG_IND_ADDR] = 0x120, [IPROC_PCIE_CFG_IND_DATA] = 0x124, @@ -311,7 +316,7 @@ static const u16 iproc_pcie_reg_paxb_bcma[] = { }; /* iProc PCIe PAXB registers */ -static const u16 iproc_pcie_reg_paxb[] = { +static const u16 iproc_pcie_reg_paxb[IPROC_PCIE_MAX_NUM_REG] = { [IPROC_PCIE_CLK_CTRL] = 0x000, [IPROC_PCIE_CFG_IND_ADDR] = 0x120, [IPROC_PCIE_CFG_IND_DATA] = 0x124, @@ -327,7 +332,7 @@ static const u16 iproc_pcie_reg_paxb[] = { }; /* iProc PCIe PAXB v2 registers */ -static const u16 iproc_pcie_reg_paxb_v2[] = { +static const u16 iproc_pcie_reg_paxb_v2[IPROC_PCIE_MAX_NUM_REG] = { [IPROC_PCIE_CLK_CTRL] = 0x000, [IPROC_PCIE_CFG_IND_ADDR] = 0x120, [IPROC_PCIE_CFG_IND_DATA] = 0x124, @@ -344,18 +349,21 @@ static const u16 iproc_pcie_reg_paxb_v2[] = { [IPROC_PCIE_OMAP3] = 0xdf8, [IPROC_PCIE_IARR0] = 0xd00, [IPROC_PCIE_IMAP0] = 0xc00, + [IPROC_PCIE_IARR1] = 0xd08, + [IPROC_PCIE_IMAP1] = 0xd70, [IPROC_PCIE_IARR2] = 0xd10, [IPROC_PCIE_IMAP2] = 0xcc0, [IPROC_PCIE_IARR3] = 0xe00, [IPROC_PCIE_IMAP3] = 0xe08, [IPROC_PCIE_IARR4] = 0xe68, [IPROC_PCIE_IMAP4] = 0xe70, + [IPROC_PCIE_CFG_RD_STATUS] = 0xee0, [IPROC_PCIE_LINK_STATUS] = 0xf0c, [IPROC_PCIE_APB_ERR_EN] = 0xf40, }; /* iProc PCIe PAXC v1 registers */ -static const u16 iproc_pcie_reg_paxc[] = { +static const u16 iproc_pcie_reg_paxc[IPROC_PCIE_MAX_NUM_REG] = { [IPROC_PCIE_CLK_CTRL] = 0x000, [IPROC_PCIE_CFG_IND_ADDR] = 0x1f0, [IPROC_PCIE_CFG_IND_DATA] = 0x1f4, @@ -364,7 +372,7 @@ static const u16 iproc_pcie_reg_paxc[] = { }; /* iProc PCIe PAXC v2 registers */ -static const u16 iproc_pcie_reg_paxc_v2[] = { +static const u16 iproc_pcie_reg_paxc_v2[IPROC_PCIE_MAX_NUM_REG] = { [IPROC_PCIE_MSI_GIC_MODE] = 0x050, [IPROC_PCIE_MSI_BASE_ADDR] = 0x074, [IPROC_PCIE_MSI_WINDOW_SIZE] = 0x078, @@ -427,7 +435,7 @@ static inline void iproc_pcie_write_reg(struct iproc_pcie *pcie, writel(val, pcie->base + offset); } -/** +/* * APB error forwarding can be disabled during access of configuration * registers of the endpoint device, to prevent unsupported requests * (typically seen during enumeration with multi-function devices) from @@ -451,19 +459,15 @@ static inline void iproc_pcie_apb_err_disable(struct pci_bus *bus, static void __iomem *iproc_pcie_map_ep_cfg_reg(struct iproc_pcie *pcie, unsigned int busno, - unsigned int slot, - unsigned int fn, + unsigned int devfn, int where) { u16 offset; u32 val; /* EP device access */ - val = (busno << CFG_ADDR_BUS_NUM_SHIFT) | - (slot << CFG_ADDR_DEV_NUM_SHIFT) | - (fn << CFG_ADDR_FUNC_NUM_SHIFT) | - (where & CFG_ADDR_REG_NUM_MASK) | - (1 & CFG_ADDR_CFG_TYPE_MASK); + val = ALIGN_DOWN(PCIE_ECAM_OFFSET(busno, devfn, where), 4) | + CFG_ADDR_CFG_TYPE_1; iproc_pcie_write_reg(pcie, IPROC_PCIE_CFG_ADDR, val); offset = iproc_pcie_reg_offset(pcie, IPROC_PCIE_CFG_DATA); @@ -474,30 +478,41 @@ static void __iomem *iproc_pcie_map_ep_cfg_reg(struct iproc_pcie *pcie, return (pcie->base + offset); } -static unsigned int iproc_pcie_cfg_retry(void __iomem *cfg_data_p) +static unsigned int iproc_pcie_cfg_retry(struct iproc_pcie *pcie, + void __iomem *cfg_data_p) { int timeout = CFG_RETRY_STATUS_TIMEOUT_US; unsigned int data; + u32 status; /* - * As per PCIe spec r3.1, sec 2.3.2, CRS Software Visibility only + * As per PCIe r6.0, sec 2.3.2, Config RRS Software Visibility only * affects config reads of the Vendor ID. For config writes or any * other config reads, the Root may automatically reissue the * configuration request again as a new request. * * For config reads, this hardware returns CFG_RETRY_STATUS data - * when it receives a CRS completion, regardless of the address of - * the read or the CRS Software Visibility Enable bit. As a + * when it receives a RRS completion, regardless of the address of + * the read or the RRS Software Visibility Enable bit. As a * partial workaround for this, we retry in software any read that * returns CFG_RETRY_STATUS. * * Note that a non-Vendor ID config register may have a value of * CFG_RETRY_STATUS. If we read that, we can't distinguish it from - * a CRS completion, so we will incorrectly retry the read and + * a RRS completion, so we will incorrectly retry the read and * eventually return the wrong data (0xffffffff). */ data = readl(cfg_data_p); while (data == CFG_RETRY_STATUS && timeout--) { + /* + * RRS state is set in CFG_RD status register + * This will handle the case where CFG_RETRY_STATUS is + * valid config data. + */ + status = iproc_pcie_read_reg(pcie, IPROC_PCIE_CFG_RD_STATUS); + if (status != CFG_RD_RRS) + return data; + udelay(1); data = readl(cfg_data_p); } @@ -542,8 +557,8 @@ static void iproc_pcie_fix_cap(struct iproc_pcie *pcie, int where, u32 *val) break; case IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL: - /* Don't advertise CRS SV support */ - *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); + /* Don't advertise RRS SV support */ + *val &= ~(PCI_EXP_RTCAP_RRS_SV << 16); break; default: @@ -555,8 +570,6 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn, int where, int size, u32 *val) { struct iproc_pcie *pcie = iproc_data(bus); - unsigned int slot = PCI_SLOT(devfn); - unsigned int fn = PCI_FUNC(devfn); unsigned int busno = bus->number; void __iomem *cfg_data_p; unsigned int data; @@ -571,12 +584,12 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn, return ret; } - cfg_data_p = iproc_pcie_map_ep_cfg_reg(pcie, busno, slot, fn, where); + cfg_data_p = iproc_pcie_map_ep_cfg_reg(pcie, busno, devfn, where); if (!cfg_data_p) return PCIBIOS_DEVICE_NOT_FOUND; - data = iproc_pcie_cfg_retry(cfg_data_p); + data = iproc_pcie_cfg_retry(pcie, cfg_data_p); *val = data; if (size <= 2) @@ -604,7 +617,7 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn, return PCIBIOS_SUCCESSFUL; } -/** +/* * Note access to the configuration registers are protected at the higher layer * by 'pci_lock' in drivers/pci/access.c */ @@ -612,13 +625,11 @@ static void __iomem *iproc_pcie_map_cfg_bus(struct iproc_pcie *pcie, int busno, unsigned int devfn, int where) { - unsigned slot = PCI_SLOT(devfn); - unsigned fn = PCI_FUNC(devfn); u16 offset; /* root complex access */ if (busno == 0) { - if (slot > 0 || fn > 0) + if (PCIE_ECAM_DEVFN(devfn) > 0) return NULL; iproc_pcie_write_reg(pcie, IPROC_PCIE_CFG_IND_ADDR, @@ -630,7 +641,7 @@ static void __iomem *iproc_pcie_map_cfg_bus(struct iproc_pcie *pcie, return (pcie->base + offset); } - return iproc_pcie_map_ep_cfg_reg(pcie, busno, slot, fn, where); + return iproc_pcie_map_ep_cfg_reg(pcie, busno, devfn, where); } static void __iomem *iproc_pcie_bus_map_cfg_bus(struct pci_bus *bus, @@ -648,10 +659,8 @@ static int iproc_pci_raw_config_read32(struct iproc_pcie *pcie, void __iomem *addr; addr = iproc_pcie_map_cfg_bus(pcie, 0, devfn, where & ~0x3); - if (!addr) { - *val = ~0; + if (!addr) return PCIBIOS_DEVICE_NOT_FOUND; - } *val = readl(addr); @@ -775,19 +784,18 @@ static int iproc_pcie_check_link(struct iproc_pcie *pcie) /* make sure we are not in EP mode */ iproc_pci_raw_config_read32(pcie, 0, PCI_HEADER_TYPE, 1, &hdr_type); - if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE) { + if ((hdr_type & PCI_HEADER_TYPE_MASK) != PCI_HEADER_TYPE_BRIDGE) { dev_err(dev, "in EP mode, hdr=%#02x\n", hdr_type); return -EFAULT; } - /* force class to PCI_CLASS_BRIDGE_PCI (0x0604) */ + /* force class to PCI_CLASS_BRIDGE_PCI_NORMAL (0x060400) */ #define PCI_BRIDGE_CTRL_REG_OFFSET 0x43c -#define PCI_CLASS_BRIDGE_MASK 0xffff00 -#define PCI_CLASS_BRIDGE_SHIFT 8 +#define PCI_BRIDGE_CTRL_REG_CLASS_MASK 0xffffff iproc_pci_raw_config_read32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET, 4, &class); - class &= ~PCI_CLASS_BRIDGE_MASK; - class |= (PCI_CLASS_BRIDGE_PCI << PCI_CLASS_BRIDGE_SHIFT); + class &= ~PCI_BRIDGE_CTRL_REG_CLASS_MASK; + class |= PCI_CLASS_BRIDGE_PCI_NORMAL; iproc_pci_raw_config_write32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET, 4, class); @@ -884,7 +892,7 @@ static inline int iproc_pcie_ob_write(struct iproc_pcie *pcie, int window_idx, return 0; } -/** +/* * Some iProc SoCs require the SW to configure the outbound address mapping * * Outbound address translation: @@ -936,8 +944,25 @@ static int iproc_pcie_setup_ob(struct iproc_pcie *pcie, u64 axi_addr, resource_size_t window_size = ob_map->window_sizes[size_idx] * SZ_1M; - if (size < window_size) - continue; + /* + * Keep iterating until we reach the last window and + * with the minimal window size at index zero. In this + * case, we take a compromise by mapping it using the + * minimum window size that can be supported + */ + if (size < window_size) { + if (size_idx > 0 || window_idx > 0) + continue; + + /* + * For the corner case of reaching the minimal + * window size that can be supported on the + * last window + */ + axi_addr = ALIGN_DOWN(axi_addr, window_size); + pci_addr = ALIGN_DOWN(pci_addr, window_size); + size = window_size; + } if (!IS_ALIGNED(axi_addr, window_size) || !IS_ALIGNED(pci_addr, window_size)) { @@ -1086,15 +1111,16 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx, } static int iproc_pcie_setup_ib(struct iproc_pcie *pcie, - struct of_pci_range *range, + struct resource_entry *entry, enum iproc_pcie_ib_map_type type) { struct device *dev = pcie->dev; struct iproc_pcie_ib *ib = &pcie->ib; int ret; unsigned int region_idx, size_idx; - u64 axi_addr = range->cpu_addr, pci_addr = range->pci_addr; - resource_size_t size = range->size; + u64 axi_addr = entry->res->start; + u64 pci_addr = entry->res->start - entry->offset; + resource_size_t size = resource_size(entry->res); /* iterate through all IARR mapping regions */ for (region_idx = 0; region_idx < ib->nr_regions; region_idx++) { @@ -1148,23 +1174,44 @@ err_ib: static int iproc_pcie_map_dma_ranges(struct iproc_pcie *pcie) { - struct of_pci_range range; - struct of_pci_range_parser parser; - int ret; - - /* Get the dma-ranges from DT */ - ret = of_pci_dma_range_parser_init(&parser, pcie->dev->of_node); - if (ret) - return ret; + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct resource_entry *entry; + int ret = 0; - for_each_of_pci_range(&parser, &range) { + resource_list_for_each_entry(entry, &host->dma_ranges) { /* Each range entry corresponds to an inbound mapping region */ - ret = iproc_pcie_setup_ib(pcie, &range, IPROC_PCIE_IB_MAP_MEM); + ret = iproc_pcie_setup_ib(pcie, entry, IPROC_PCIE_IB_MAP_MEM); if (ret) - return ret; + break; } - return 0; + return ret; +} + +static void iproc_pcie_invalidate_mapping(struct iproc_pcie *pcie) +{ + struct iproc_pcie_ib *ib = &pcie->ib; + struct iproc_pcie_ob *ob = &pcie->ob; + int idx; + + if (pcie->ep_is_internal) + return; + + if (pcie->need_ob_cfg) { + /* iterate through all OARR mapping regions */ + for (idx = ob->nr_windows - 1; idx >= 0; idx--) { + iproc_pcie_write_reg(pcie, + MAP_REG(IPROC_PCIE_OARR0, idx), 0); + } + } + + if (pcie->need_ib_cfg) { + /* iterate through all IARR mapping regions */ + for (idx = 0; idx < ib->nr_regions; idx++) { + iproc_pcie_write_reg(pcie, + MAP_REG(IPROC_PCIE_IARR0, idx), 0); + } + } } static int iproce_pcie_get_msi(struct iproc_pcie *pcie, @@ -1198,13 +1245,16 @@ static int iproce_pcie_get_msi(struct iproc_pcie *pcie, static int iproc_pcie_paxb_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr) { int ret; - struct of_pci_range range; + struct resource_entry entry; - memset(&range, 0, sizeof(range)); - range.size = SZ_32K; - range.pci_addr = range.cpu_addr = msi_addr & ~(range.size - 1); + memset(&entry, 0, sizeof(entry)); + entry.res = &entry.__res; - ret = iproc_pcie_setup_ib(pcie, &range, IPROC_PCIE_IB_MAP_IO); + msi_addr &= ~(SZ_32K - 1); + entry.res->start = msi_addr; + entry.res->end = msi_addr + SZ_32K - 1; + + ret = iproc_pcie_setup_ib(pcie, &entry, IPROC_PCIE_IB_MAP_IO); return ret; } @@ -1288,29 +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 @@ -1320,14 +1357,18 @@ static int iproc_pcie_msi_enable(struct iproc_pcie *pcie) if (pcie->need_msi_steer) { ret = iproc_pcie_msi_steer(pcie, msi_node); if (ret) - return ret; + goto out_put_node; } /* * If another MSI controller is being used, the call below should fail * but that is okay */ - return iproc_msi_init(pcie, msi_node); + ret = iproc_msi_init(pcie, msi_node); + +out_put_node: + of_node_put(msi_node); + return ret; } static void iproc_pcie_msi_disable(struct iproc_pcie *pcie) @@ -1347,7 +1388,6 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie) break; case IPROC_PCIE_PAXB: regs = iproc_pcie_reg_paxb; - pcie->iproc_cfg_read = true; pcie->has_apb_err_disable = true; if (pcie->need_ob_cfg) { pcie->ob_map = paxb_ob_map; @@ -1356,6 +1396,7 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie) break; case IPROC_PCIE_PAXB_V2: regs = iproc_pcie_reg_paxb_v2; + pcie->iproc_cfg_read = true; pcie->has_apb_err_disable = true; if (pcie->need_ob_cfg) { pcie->ob_map = paxb_v2_ob_map; @@ -1405,7 +1446,7 @@ int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res) { struct device *dev; int ret; - struct pci_bus *child; + struct pci_dev *pdev; struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); dev = pcie->dev; @@ -1416,10 +1457,6 @@ int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res) return ret; } - ret = devm_request_pci_bus_resources(dev, res); - if (ret) - return ret; - ret = phy_init(pcie->phy); if (ret) { dev_err(dev, "unable to initialize PCIe PHY\n"); @@ -1435,6 +1472,8 @@ int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res) iproc_pcie_perst_ctrl(pcie, true); iproc_pcie_perst_ctrl(pcie, false); + iproc_pcie_invalidate_mapping(pcie); + if (pcie->need_ob_cfg) { ret = iproc_pcie_map_ranges(pcie, res); if (ret) { @@ -1461,28 +1500,20 @@ int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res) if (iproc_pcie_msi_enable(pcie)) dev_info(dev, "not using iProc MSI\n"); - list_splice_init(res, &host->windows); - host->busnr = 0; - host->dev.parent = dev; host->ops = &iproc_pcie_ops; host->sysdata = pcie; host->map_irq = pcie->map_irq; - host->swizzle_irq = pci_common_swizzle; - ret = pci_scan_root_bus_bridge(host); + ret = pci_host_probe(host); if (ret < 0) { dev_err(dev, "failed to scan host: %d\n", ret); goto err_power_off_phy; } - pci_assign_unassigned_bus_resources(host->bus); - - pcie->root_bus = host->bus; - - list_for_each_entry(child, &host->bus->children, node) - pcie_bus_configure_settings(child); - - pci_bus_add_devices(host->bus); + for_each_pci_bridge(pdev, host->bus) { + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) + pcie_print_link_status(pdev); + } return 0; @@ -1494,17 +1525,17 @@ err_exit_phy: } EXPORT_SYMBOL(iproc_pcie_setup); -int iproc_pcie_remove(struct iproc_pcie *pcie) +void iproc_pcie_remove(struct iproc_pcie *pcie) { - pci_stop_root_bus(pcie->root_bus); - pci_remove_root_bus(pcie->root_bus); + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + + pci_stop_root_bus(host->bus); + pci_remove_root_bus(host->bus); iproc_pcie_msi_disable(pcie); phy_power_off(pcie->phy); phy_exit(pcie->phy); - - return 0; } EXPORT_SYMBOL(iproc_pcie_remove); @@ -1526,6 +1557,30 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_disable_msi_parsing); +static void quirk_paxc_bridge(struct pci_dev *pdev) +{ + /* + * The PCI config space is shared with the PAXC root port and the first + * Ethernet device. So, we need to workaround this by telling the PCI + * code that the bridge is not an Ethernet device. + */ + if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + pdev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; + + /* + * MPSS is not being set properly (as it is currently 0). This is + * because that area of the PCI config space is hard coded to zero, and + * is not modifiable by firmware. Set this to 2 (e.g., 512 byte MPS) + * so that the MPS can be set to the real max value. + */ + pdev->pcie_mpss = 2; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge); + MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>"); MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-iproc.h b/drivers/pci/controller/pcie-iproc.h index 4f03ea539805..969ded03b8c2 100644 --- a/drivers/pci/controller/pcie-iproc.h +++ b/drivers/pci/controller/pcie-iproc.h @@ -7,7 +7,13 @@ #define _PCIE_IPROC_H /** - * iProc PCIe interface type + * enum iproc_pcie_type - iProc PCIe interface type + * @IPROC_PCIE_PAXB_BCMA: BCMA-based host controllers + * @IPROC_PCIE_PAXB: PAXB-based host controllers for + * NS, NSP, Cygnus, NS2, and Pegasus SOCs + * @IPROC_PCIE_PAXB_V2: PAXB-based host controllers for Stingray SoCs + * @IPROC_PCIE_PAXC: PAXC-based host controllers + * @IPROC_PCIE_PAXC_V2: PAXC-based host controllers (second generation) * * PAXB is the wrapper used in root complex that can be connected to an * external endpoint device. @@ -24,7 +30,7 @@ enum iproc_pcie_type { }; /** - * iProc PCIe outbound mapping + * struct iproc_pcie_ob - iProc PCIe outbound mapping * @axi_offset: offset from the AXI address to the internal address used by * the iProc PCIe core * @nr_windows: total number of supported outbound mapping windows @@ -35,7 +41,7 @@ struct iproc_pcie_ob { }; /** - * iProc PCIe inbound mapping + * struct iproc_pcie_ib - iProc PCIe inbound mapping * @nr_regions: total number of supported inbound mapping regions */ struct iproc_pcie_ib { @@ -47,14 +53,13 @@ struct iproc_pcie_ib_map; struct iproc_msi; /** - * iProc PCIe device - * + * struct iproc_pcie - iProc PCIe device * @dev: pointer to device data structure * @type: iProc PCIe interface type * @reg_offsets: register offsets * @base: PCIe host controller I/O register base * @base_addr: PCIe host controller register base physical address - * @root_bus: pointer to root bus + * @mem: host bridge memory window resource * @phy: optional PHY device that controls the Serdes * @map_irq: function callback to map interrupts * @ep_is_internal: indicates an internal emulated endpoint device is connected @@ -85,7 +90,6 @@ struct iproc_pcie { void __iomem *base; phys_addr_t base_addr; struct resource mem; - struct pci_bus *root_bus; struct phy *phy; int (*map_irq)(const struct pci_dev *, u8, u8); bool ep_is_internal; @@ -107,7 +111,7 @@ struct iproc_pcie { }; int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res); -int iproc_pcie_remove(struct iproc_pcie *pcie); +void iproc_pcie_remove(struct iproc_pcie *pcie); int iproc_pcie_shutdown(struct iproc_pcie *pcie); #ifdef CONFIG_PCIE_IPROC_MSI diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c new file mode 100644 index 000000000000..75ddb8bee168 --- /dev/null +++ b/drivers/pci/controller/pcie-mediatek-gen3.c @@ -0,0 +1,1384 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MediaTek PCIe host controller driver. + * + * Copyright (c) 2020 MediaTek Inc. + * Author: Jianjun Wang <jianjun.wang@mediatek.com> + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_device.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include "../pci.h" + +#define PCIE_BASE_CFG_REG 0x14 +#define PCIE_BASE_CFG_SPEED GENMASK(15, 8) + +#define PCIE_SETTING_REG 0x80 +#define PCIE_SETTING_LINK_WIDTH GENMASK(11, 8) +#define PCIE_SETTING_GEN_SUPPORT GENMASK(14, 12) +#define PCIE_PCI_IDS_1 0x9c +#define PCI_CLASS(class) (class << 8) +#define PCIE_RC_MODE BIT(0) + +#define PCIE_EQ_PRESET_01_REG 0x100 +#define PCIE_VAL_LN0_DOWNSTREAM GENMASK(6, 0) +#define PCIE_VAL_LN0_UPSTREAM GENMASK(14, 8) +#define PCIE_VAL_LN1_DOWNSTREAM GENMASK(22, 16) +#define PCIE_VAL_LN1_UPSTREAM GENMASK(30, 24) + +#define PCIE_CFGNUM_REG 0x140 +#define PCIE_CFG_DEVFN(devfn) ((devfn) & GENMASK(7, 0)) +#define PCIE_CFG_BUS(bus) (((bus) << 8) & GENMASK(15, 8)) +#define PCIE_CFG_BYTE_EN(bytes) (((bytes) << 16) & GENMASK(19, 16)) +#define PCIE_CFG_FORCE_BYTE_EN BIT(20) +#define PCIE_CFG_OFFSET_ADDR 0x1000 +#define PCIE_CFG_HEADER(bus, devfn) \ + (PCIE_CFG_BUS(bus) | PCIE_CFG_DEVFN(devfn)) + +#define PCIE_RST_CTRL_REG 0x148 +#define PCIE_MAC_RSTB BIT(0) +#define PCIE_PHY_RSTB BIT(1) +#define PCIE_BRG_RSTB BIT(2) +#define PCIE_PE_RSTB BIT(3) + +#define PCIE_LTSSM_STATUS_REG 0x150 +#define PCIE_LTSSM_STATE_MASK GENMASK(28, 24) +#define PCIE_LTSSM_STATE(val) ((val & PCIE_LTSSM_STATE_MASK) >> 24) +#define PCIE_LTSSM_STATE_L2_IDLE 0x14 + +#define PCIE_LINK_STATUS_REG 0x154 +#define PCIE_PORT_LINKUP BIT(8) + +#define PCIE_MSI_SET_NUM 8 +#define PCIE_MSI_IRQS_PER_SET 32 +#define PCIE_MSI_IRQS_NUM \ + (PCIE_MSI_IRQS_PER_SET * PCIE_MSI_SET_NUM) + +#define PCIE_INT_ENABLE_REG 0x180 +#define PCIE_MSI_ENABLE GENMASK(PCIE_MSI_SET_NUM + 8 - 1, 8) +#define PCIE_MSI_SHIFT 8 +#define PCIE_INTX_SHIFT 24 +#define PCIE_INTX_ENABLE \ + GENMASK(PCIE_INTX_SHIFT + PCI_NUM_INTX - 1, PCIE_INTX_SHIFT) + +#define PCIE_INT_STATUS_REG 0x184 +#define PCIE_MSI_SET_ENABLE_REG 0x190 +#define PCIE_MSI_SET_ENABLE GENMASK(PCIE_MSI_SET_NUM - 1, 0) + +#define PCIE_PIPE4_PIE8_REG 0x338 +#define PCIE_K_FINETUNE_MAX GENMASK(5, 0) +#define PCIE_K_FINETUNE_ERR GENMASK(7, 6) +#define PCIE_K_PRESET_TO_USE GENMASK(18, 8) +#define PCIE_K_PHYPARAM_QUERY BIT(19) +#define PCIE_K_QUERY_TIMEOUT BIT(20) +#define PCIE_K_PRESET_TO_USE_16G GENMASK(31, 21) + +#define PCIE_MSI_SET_BASE_REG 0xc00 +#define PCIE_MSI_SET_OFFSET 0x10 +#define PCIE_MSI_SET_STATUS_OFFSET 0x04 +#define PCIE_MSI_SET_ENABLE_OFFSET 0x08 + +#define PCIE_MSI_SET_ADDR_HI_BASE 0xc80 +#define PCIE_MSI_SET_ADDR_HI_OFFSET 0x04 + +#define PCIE_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) + +#define PCIE_MISC_CTRL_REG 0x348 +#define PCIE_DISABLE_DVFSRC_VLT_REQ BIT(1) + +#define PCIE_TRANS_TABLE_BASE_REG 0x800 +#define PCIE_ATR_SRC_ADDR_MSB_OFFSET 0x4 +#define PCIE_ATR_TRSL_ADDR_LSB_OFFSET 0x8 +#define PCIE_ATR_TRSL_ADDR_MSB_OFFSET 0xc +#define PCIE_ATR_TRSL_PARAM_OFFSET 0x10 +#define PCIE_ATR_TLB_SET_OFFSET 0x20 + +#define PCIE_MAX_TRANS_TABLES 8 +#define PCIE_ATR_EN BIT(0) +#define PCIE_ATR_SIZE(size) \ + (((((size) - 1) << 1) & GENMASK(6, 1)) | PCIE_ATR_EN) +#define PCIE_ATR_ID(id) ((id) & GENMASK(3, 0)) +#define PCIE_ATR_TYPE_MEM PCIE_ATR_ID(0) +#define PCIE_ATR_TYPE_IO PCIE_ATR_ID(1) +#define PCIE_ATR_TLP_TYPE(type) (((type) << 16) & GENMASK(18, 16)) +#define PCIE_ATR_TLP_TYPE_MEM PCIE_ATR_TLP_TYPE(0) +#define PCIE_ATR_TLP_TYPE_IO PCIE_ATR_TLP_TYPE(2) + +#define MAX_NUM_PHY_RESETS 3 + +#define PCIE_MTK_RESET_TIME_US 10 + +/* Time in ms needed to complete PCIe reset on EN7581 SoC */ +#define PCIE_EN7581_RESET_TIME_MS 100 + +struct mtk_gen3_pcie; + +#define PCIE_CONF_LINK2_CTL_STS (PCIE_CFG_OFFSET_ADDR + 0xb0) +#define PCIE_CONF_LINK2_LCR2_LINK_SPEED GENMASK(3, 0) + +enum mtk_gen3_pcie_flags { + SKIP_PCIE_RSTB = BIT(0), /* Skip PERST# assertion during device + * probing or suspend/resume phase to + * avoid hw bugs/issues. + */ +}; + +/** + * struct mtk_gen3_pcie_pdata - differentiate between host generations + * @power_up: pcie power_up callback + * @phy_resets: phy reset lines SoC data. + * @sys_clk_rdy_time_us: System clock ready time override (microseconds) + * @flags: pcie device flags. + */ +struct mtk_gen3_pcie_pdata { + int (*power_up)(struct mtk_gen3_pcie *pcie); + struct { + const char *id[MAX_NUM_PHY_RESETS]; + int num_resets; + } phy_resets; + u8 sys_clk_rdy_time_us; + u32 flags; +}; + +/** + * struct mtk_msi_set - MSI information for each set + * @base: IO mapped register base + * @msg_addr: MSI message address + * @saved_irq_state: IRQ enable state saved at suspend time + */ +struct mtk_msi_set { + void __iomem *base; + phys_addr_t msg_addr; + u32 saved_irq_state; +}; + +/** + * struct mtk_gen3_pcie - PCIe port information + * @dev: pointer to PCIe device + * @base: IO mapped register base + * @reg_base: physical register base + * @mac_reset: MAC reset control + * @phy_resets: PHY reset controllers + * @phy: PHY controller block + * @clks: PCIe clocks + * @num_clks: PCIe clocks count for this port + * @max_link_speed: Maximum link speed (PCIe Gen) for this port + * @num_lanes: Number of PCIe lanes for this port + * @irq: PCIe controller interrupt number + * @saved_irq_state: IRQ enable state saved at suspend time + * @irq_lock: lock protecting IRQ register access + * @intx_domain: legacy INTx IRQ domain + * @msi_bottom_domain: MSI IRQ bottom domain + * @msi_sets: MSI sets information + * @lock: lock protecting IRQ bit map + * @msi_irq_in_use: bit map for assigned MSI IRQ + * @soc: pointer to SoC-dependent operations + */ +struct mtk_gen3_pcie { + struct device *dev; + void __iomem *base; + phys_addr_t reg_base; + struct reset_control *mac_reset; + struct reset_control_bulk_data phy_resets[MAX_NUM_PHY_RESETS]; + struct phy *phy; + struct clk_bulk_data *clks; + int num_clks; + u8 max_link_speed; + u8 num_lanes; + + int irq; + u32 saved_irq_state; + raw_spinlock_t irq_lock; + struct irq_domain *intx_domain; + struct irq_domain *msi_bottom_domain; + struct mtk_msi_set msi_sets[PCIE_MSI_SET_NUM]; + struct mutex lock; + DECLARE_BITMAP(msi_irq_in_use, PCIE_MSI_IRQS_NUM); + + const struct mtk_gen3_pcie_pdata *soc; +}; + +/* LTSSM state in PCIE_LTSSM_STATUS_REG bit[28:24] */ +static const char *const ltssm_str[] = { + "detect.quiet", /* 0x00 */ + "detect.active", /* 0x01 */ + "polling.active", /* 0x02 */ + "polling.compliance", /* 0x03 */ + "polling.configuration", /* 0x04 */ + "config.linkwidthstart", /* 0x05 */ + "config.linkwidthaccept", /* 0x06 */ + "config.lanenumwait", /* 0x07 */ + "config.lanenumaccept", /* 0x08 */ + "config.complete", /* 0x09 */ + "config.idle", /* 0x0A */ + "recovery.receiverlock", /* 0x0B */ + "recovery.equalization", /* 0x0C */ + "recovery.speed", /* 0x0D */ + "recovery.receiverconfig", /* 0x0E */ + "recovery.idle", /* 0x0F */ + "L0", /* 0x10 */ + "L0s", /* 0x11 */ + "L1.entry", /* 0x12 */ + "L1.idle", /* 0x13 */ + "L2.idle", /* 0x14 */ + "L2.transmitwake", /* 0x15 */ + "disable", /* 0x16 */ + "loopback.entry", /* 0x17 */ + "loopback.active", /* 0x18 */ + "loopback.exit", /* 0x19 */ + "hotreset", /* 0x1A */ +}; + +/** + * mtk_pcie_config_tlp_header() - Configure a configuration TLP header + * @bus: PCI bus to query + * @devfn: device/function number + * @where: offset in config space + * @size: data size in TLP header + * + * Set byte enable field and device information in configuration TLP header. + */ +static void mtk_pcie_config_tlp_header(struct pci_bus *bus, unsigned int devfn, + int where, int size) +{ + struct mtk_gen3_pcie *pcie = bus->sysdata; + int bytes; + u32 val; + + bytes = (GENMASK(size - 1, 0) & 0xf) << (where & 0x3); + + val = PCIE_CFG_FORCE_BYTE_EN | PCIE_CFG_BYTE_EN(bytes) | + PCIE_CFG_HEADER(bus->number, devfn); + + writel_relaxed(val, pcie->base + PCIE_CFGNUM_REG); +} + +static void __iomem *mtk_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct mtk_gen3_pcie *pcie = bus->sysdata; + + return pcie->base + PCIE_CFG_OFFSET_ADDR + where; +} + +static int mtk_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + mtk_pcie_config_tlp_header(bus, devfn, where, size); + + return pci_generic_config_read32(bus, devfn, where, size, val); +} + +static int mtk_pcie_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + mtk_pcie_config_tlp_header(bus, devfn, where, size); + + if (size <= 2) + val <<= (where & 0x3) * 8; + + return pci_generic_config_write32(bus, devfn, where, 4, val); +} + +static struct pci_ops mtk_pcie_ops = { + .map_bus = mtk_pcie_map_bus, + .read = mtk_pcie_config_read, + .write = mtk_pcie_config_write, +}; + +static int mtk_pcie_set_trans_table(struct mtk_gen3_pcie *pcie, + resource_size_t cpu_addr, + resource_size_t pci_addr, + resource_size_t size, + unsigned long type, int *num) +{ + resource_size_t remaining = size; + resource_size_t table_size; + resource_size_t addr_align; + const char *range_type; + void __iomem *table; + u32 val; + + while (remaining && (*num < PCIE_MAX_TRANS_TABLES)) { + /* Table size needs to be a power of 2 */ + table_size = BIT(fls(remaining) - 1); + + if (cpu_addr > 0) { + addr_align = BIT(ffs(cpu_addr) - 1); + table_size = min(table_size, addr_align); + } + + /* Minimum size of translate table is 4KiB */ + if (table_size < 0x1000) { + dev_err(pcie->dev, "illegal table size %#llx\n", + (unsigned long long)table_size); + return -EINVAL; + } + + table = pcie->base + PCIE_TRANS_TABLE_BASE_REG + *num * PCIE_ATR_TLB_SET_OFFSET; + writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(table_size) - 1), table); + writel_relaxed(upper_32_bits(cpu_addr), table + PCIE_ATR_SRC_ADDR_MSB_OFFSET); + writel_relaxed(lower_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET); + writel_relaxed(upper_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET); + + if (type == IORESOURCE_IO) { + val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO; + range_type = "IO"; + } else { + val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM; + range_type = "MEM"; + } + + writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET); + + dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n", + range_type, *num, (unsigned long long)cpu_addr, + (unsigned long long)pci_addr, + (unsigned long long)table_size); + + cpu_addr += table_size; + pci_addr += table_size; + remaining -= table_size; + (*num)++; + } + + if (remaining) + dev_warn(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n", + (unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES); + + return 0; +} + +static void mtk_pcie_enable_msi(struct mtk_gen3_pcie *pcie) +{ + int i; + u32 val; + + for (i = 0; i < PCIE_MSI_SET_NUM; i++) { + struct mtk_msi_set *msi_set = &pcie->msi_sets[i]; + + msi_set->base = pcie->base + PCIE_MSI_SET_BASE_REG + + i * PCIE_MSI_SET_OFFSET; + msi_set->msg_addr = pcie->reg_base + PCIE_MSI_SET_BASE_REG + + i * PCIE_MSI_SET_OFFSET; + + /* Configure the MSI capture address */ + writel_relaxed(lower_32_bits(msi_set->msg_addr), msi_set->base); + writel_relaxed(upper_32_bits(msi_set->msg_addr), + pcie->base + PCIE_MSI_SET_ADDR_HI_BASE + + i * PCIE_MSI_SET_ADDR_HI_OFFSET); + } + + val = readl_relaxed(pcie->base + PCIE_MSI_SET_ENABLE_REG); + val |= PCIE_MSI_SET_ENABLE; + writel_relaxed(val, pcie->base + PCIE_MSI_SET_ENABLE_REG); + + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val |= PCIE_MSI_ENABLE; + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); +} + +static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) +{ + struct resource_entry *entry; + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + unsigned int table_index = 0; + int err; + u32 val; + + /* Set as RC mode and set controller PCIe Gen speed restriction, if any */ + val = readl_relaxed(pcie->base + PCIE_SETTING_REG); + val |= PCIE_RC_MODE; + if (pcie->max_link_speed) { + val &= ~PCIE_SETTING_GEN_SUPPORT; + + /* Can enable link speed support only from Gen2 onwards */ + if (pcie->max_link_speed >= 2) + val |= FIELD_PREP(PCIE_SETTING_GEN_SUPPORT, + GENMASK(pcie->max_link_speed - 2, 0)); + } + if (pcie->num_lanes) { + val &= ~PCIE_SETTING_LINK_WIDTH; + + /* Zero means one lane, each bit activates x2/x4/x8/x16 */ + if (pcie->num_lanes > 1) + val |= FIELD_PREP(PCIE_SETTING_LINK_WIDTH, + GENMASK(fls(pcie->num_lanes >> 2), 0)); + } + writel_relaxed(val, pcie->base + PCIE_SETTING_REG); + + /* Set Link Control 2 (LNKCTL2) speed restriction, if any */ + if (pcie->max_link_speed) { + val = readl_relaxed(pcie->base + PCIE_CONF_LINK2_CTL_STS); + val &= ~PCIE_CONF_LINK2_LCR2_LINK_SPEED; + val |= FIELD_PREP(PCIE_CONF_LINK2_LCR2_LINK_SPEED, pcie->max_link_speed); + writel_relaxed(val, pcie->base + PCIE_CONF_LINK2_CTL_STS); + } + + /* If parameter is present, adjust SYS_CLK_RDY_TIME to avoid glitching */ + if (pcie->soc->sys_clk_rdy_time_us) { + val = readl_relaxed(pcie->base + PCIE_RESOURCE_CTRL_REG); + FIELD_MODIFY(PCIE_RSRC_SYS_CLK_RDY_TIME_MASK, &val, + pcie->soc->sys_clk_rdy_time_us); + writel_relaxed(val, pcie->base + PCIE_RESOURCE_CTRL_REG); + } + + /* Set class code */ + val = readl_relaxed(pcie->base + PCIE_PCI_IDS_1); + val &= ~GENMASK(31, 8); + val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI_NORMAL); + writel_relaxed(val, pcie->base + PCIE_PCI_IDS_1); + + /* Mask all INTx interrupts */ + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val &= ~PCIE_INTX_ENABLE; + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); + + /* Disable DVFSRC voltage request */ + val = readl_relaxed(pcie->base + PCIE_MISC_CTRL_REG); + val |= PCIE_DISABLE_DVFSRC_VLT_REQ; + writel_relaxed(val, pcie->base + PCIE_MISC_CTRL_REG); + + /* + * Airoha EN7581 has a hw bug asserting/releasing PCIE_PE_RSTB signal + * causing occasional PCIe link down. In order to overcome the issue, + * PCIE_RSTB signals are not asserted/released at this stage and the + * PCIe block is reset using en7523_reset_assert() and + * en7581_pci_enable(). + */ + if (!(pcie->soc->flags & SKIP_PCIE_RSTB)) { + /* Assert all reset signals */ + val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); + val |= PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | + PCIE_PE_RSTB; + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + + /* + * Described in PCIe CEM specification revision 6.0. + * + * The deassertion of PERST# should be delayed 100ms (TPVPERL) + * for the power and clock to become stable. + */ + msleep(PCIE_T_PVPERL_MS); + + /* De-assert reset signals */ + val &= ~(PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | + PCIE_PE_RSTB); + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + } + + /* Check if the link is up or not */ + err = readl_poll_timeout(pcie->base + PCIE_LINK_STATUS_REG, val, + !!(val & PCIE_PORT_LINKUP), 20, + PCI_PM_D3COLD_WAIT * USEC_PER_MSEC); + if (err) { + const char *ltssm_state; + int ltssm_index; + + val = readl_relaxed(pcie->base + PCIE_LTSSM_STATUS_REG); + ltssm_index = PCIE_LTSSM_STATE(val); + ltssm_state = ltssm_index >= ARRAY_SIZE(ltssm_str) ? + "Unknown state" : ltssm_str[ltssm_index]; + dev_err(pcie->dev, + "PCIe link down, current LTSSM state: %s (%#x)\n", + ltssm_state, val); + return err; + } + + mtk_pcie_enable_msi(pcie); + + /* Set PCIe translation windows */ + resource_list_for_each_entry(entry, &host->windows) { + struct resource *res = entry->res; + unsigned long type = resource_type(res); + resource_size_t cpu_addr; + resource_size_t pci_addr; + resource_size_t size; + + if (type == IORESOURCE_IO) + cpu_addr = pci_pio_to_address(res->start); + else if (type == IORESOURCE_MEM) + cpu_addr = res->start; + else + continue; + + pci_addr = res->start - entry->offset; + size = resource_size(res); + err = mtk_pcie_set_trans_table(pcie, cpu_addr, pci_addr, size, + type, &table_index); + if (err) + return err; + } + + return 0; +} + +#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) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + struct mtk_gen3_pcie *pcie = data->domain->host_data; + unsigned long hwirq; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + msg->address_hi = upper_32_bits(msi_set->msg_addr); + msg->address_lo = lower_32_bits(msi_set->msg_addr); + msg->data = hwirq; + dev_dbg(pcie->dev, "msi#%#lx address_hi %#x address_lo %#x data %d\n", + hwirq, msg->address_hi, msg->address_lo, msg->data); +} + +static void mtk_msi_bottom_irq_ack(struct irq_data *data) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + unsigned long hwirq; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + writel_relaxed(BIT(hwirq), msi_set->base + PCIE_MSI_SET_STATUS_OFFSET); +} + +static void mtk_msi_bottom_irq_mask(struct irq_data *data) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + struct mtk_gen3_pcie *pcie = data->domain->host_data; + unsigned long hwirq, flags; + u32 val; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + val &= ~BIT(hwirq); + writel_relaxed(val, msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static void mtk_msi_bottom_irq_unmask(struct irq_data *data) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + struct mtk_gen3_pcie *pcie = data->domain->host_data; + unsigned long hwirq, flags; + u32 val; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + val |= BIT(hwirq); + writel_relaxed(val, msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static struct irq_chip mtk_msi_bottom_irq_chip = { + .irq_ack = mtk_msi_bottom_irq_ack, + .irq_mask = mtk_msi_bottom_irq_mask, + .irq_unmask = mtk_msi_bottom_irq_unmask, + .irq_compose_msi_msg = mtk_compose_msi_msg, + .name = "MSI", +}; + +static int mtk_msi_bottom_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *arg) +{ + struct mtk_gen3_pcie *pcie = domain->host_data; + struct mtk_msi_set *msi_set; + int i, hwirq, set_idx; + + mutex_lock(&pcie->lock); + + hwirq = bitmap_find_free_region(pcie->msi_irq_in_use, PCIE_MSI_IRQS_NUM, + order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); + + if (hwirq < 0) + return -ENOSPC; + + set_idx = hwirq / PCIE_MSI_IRQS_PER_SET; + msi_set = &pcie->msi_sets[set_idx]; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &mtk_msi_bottom_irq_chip, msi_set, + handle_edge_irq, NULL, NULL); + + return 0; +} + +static void mtk_msi_bottom_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct mtk_gen3_pcie *pcie = domain->host_data; + struct irq_data *data = irq_domain_get_irq_data(domain, virq); + + mutex_lock(&pcie->lock); + + bitmap_release_region(pcie->msi_irq_in_use, data->hwirq, + order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); + + irq_domain_free_irqs_common(domain, virq, nr_irqs); +} + +static const struct irq_domain_ops mtk_msi_bottom_domain_ops = { + .alloc = mtk_msi_bottom_domain_alloc, + .free = mtk_msi_bottom_domain_free, +}; + +static void mtk_intx_mask(struct irq_data *data) +{ + struct mtk_gen3_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val &= ~BIT(data->hwirq + PCIE_INTX_SHIFT); + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static void mtk_intx_unmask(struct irq_data *data) +{ + struct mtk_gen3_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val |= BIT(data->hwirq + PCIE_INTX_SHIFT); + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +/** + * mtk_intx_eoi() - Clear INTx IRQ status at the end of interrupt + * @data: pointer to chip specific data + * + * As an emulated level IRQ, its interrupt status will remain + * until the corresponding de-assert message is received; hence that + * the status can only be cleared when the interrupt has been serviced. + */ +static void mtk_intx_eoi(struct irq_data *data) +{ + struct mtk_gen3_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long hwirq; + + hwirq = data->hwirq + PCIE_INTX_SHIFT; + writel_relaxed(BIT(hwirq), pcie->base + PCIE_INT_STATUS_REG); +} + +static struct irq_chip mtk_intx_irq_chip = { + .irq_mask = mtk_intx_mask, + .irq_unmask = mtk_intx_unmask, + .irq_eoi = mtk_intx_eoi, + .name = "INTx", +}; + +static int mtk_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_data(irq, domain->host_data); + irq_set_chip_and_handler_name(irq, &mtk_intx_irq_chip, + handle_fasteoi_irq, "INTx"); + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = mtk_pcie_intx_map, +}; + +static int mtk_pcie_init_irq_domains(struct mtk_gen3_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *intc_node, *node = dev->of_node; + int ret; + + raw_spin_lock_init(&pcie->irq_lock); + + /* Setup INTx */ + intc_node = of_get_child_by_name(node, "interrupt-controller"); + if (!intc_node) { + dev_err(dev, "missing interrupt-controller node\n"); + return -ENODEV; + } + + pcie->intx_domain = irq_domain_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; + goto out_put_node; + } + + /* Setup MSI */ + mutex_init(&pcie->lock); + + 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; + } + + of_node_put(intc_node); + return 0; + +err_msi_bottom_domain: + irq_domain_remove(pcie->intx_domain); +out_put_node: + of_node_put(intc_node); + return ret; +} + +static void mtk_pcie_irq_teardown(struct mtk_gen3_pcie *pcie) +{ + irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); + + if (pcie->intx_domain) + irq_domain_remove(pcie->intx_domain); + + if (pcie->msi_bottom_domain) + irq_domain_remove(pcie->msi_bottom_domain); + + irq_dispose_mapping(pcie->irq); +} + +static void mtk_pcie_msi_handler(struct mtk_gen3_pcie *pcie, int set_idx) +{ + struct mtk_msi_set *msi_set = &pcie->msi_sets[set_idx]; + unsigned long msi_enable, msi_status; + irq_hw_number_t bit, hwirq; + + msi_enable = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + + do { + msi_status = readl_relaxed(msi_set->base + + PCIE_MSI_SET_STATUS_OFFSET); + msi_status &= msi_enable; + if (!msi_status) + break; + + for_each_set_bit(bit, &msi_status, PCIE_MSI_IRQS_PER_SET) { + hwirq = bit + set_idx * PCIE_MSI_IRQS_PER_SET; + generic_handle_domain_irq(pcie->msi_bottom_domain, hwirq); + } + } while (true); +} + +static void mtk_pcie_irq_handler(struct irq_desc *desc) +{ + struct mtk_gen3_pcie *pcie = irq_desc_get_handler_data(desc); + struct irq_chip *irqchip = irq_desc_get_chip(desc); + unsigned long status; + irq_hw_number_t irq_bit = PCIE_INTX_SHIFT; + + chained_irq_enter(irqchip, desc); + + status = readl_relaxed(pcie->base + PCIE_INT_STATUS_REG); + for_each_set_bit_from(irq_bit, &status, PCI_NUM_INTX + + PCIE_INTX_SHIFT) + generic_handle_domain_irq(pcie->intx_domain, + irq_bit - PCIE_INTX_SHIFT); + + irq_bit = PCIE_MSI_SHIFT; + for_each_set_bit_from(irq_bit, &status, PCIE_MSI_SET_NUM + + PCIE_MSI_SHIFT) { + mtk_pcie_msi_handler(pcie, irq_bit - PCIE_MSI_SHIFT); + + writel_relaxed(BIT(irq_bit), pcie->base + PCIE_INT_STATUS_REG); + } + + chained_irq_exit(irqchip, desc); +} + +static int mtk_pcie_setup_irq(struct mtk_gen3_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + int err; + + err = mtk_pcie_init_irq_domains(pcie); + if (err) + return err; + + pcie->irq = platform_get_irq(pdev, 0); + if (pcie->irq < 0) + return pcie->irq; + + irq_set_chained_handler_and_data(pcie->irq, mtk_pcie_irq_handler, pcie); + + return 0; +} + +static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie) +{ + int i, ret, num_resets = pcie->soc->phy_resets.num_resets; + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource *regs; + u32 num_lanes; + + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pcie-mac"); + if (!regs) + return -EINVAL; + pcie->base = devm_ioremap_resource(dev, regs); + if (IS_ERR(pcie->base)) { + dev_err(dev, "failed to map register base\n"); + return PTR_ERR(pcie->base); + } + + pcie->reg_base = regs->start; + + for (i = 0; i < num_resets; i++) + pcie->phy_resets[i].id = pcie->soc->phy_resets.id[i]; + + ret = devm_reset_control_bulk_get_optional_shared(dev, num_resets, + pcie->phy_resets); + if (ret) { + dev_err(dev, "failed to get PHY bulk reset\n"); + return ret; + } + + pcie->mac_reset = devm_reset_control_get_optional_exclusive(dev, "mac"); + if (IS_ERR(pcie->mac_reset)) { + ret = PTR_ERR(pcie->mac_reset); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to get MAC reset\n"); + + return ret; + } + + pcie->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(pcie->phy)) { + ret = PTR_ERR(pcie->phy); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to get PHY\n"); + + return ret; + } + + pcie->num_clks = devm_clk_bulk_get_all(dev, &pcie->clks); + if (pcie->num_clks < 0) { + dev_err(dev, "failed to get clocks\n"); + return pcie->num_clks; + } + + ret = of_property_read_u32(dev->of_node, "num-lanes", &num_lanes); + if (ret == 0) { + if (num_lanes == 0 || num_lanes > 16 || + (num_lanes != 1 && num_lanes % 2)) + dev_warn(dev, "invalid num-lanes, using controller defaults\n"); + else + pcie->num_lanes = num_lanes; + } + + return 0; +} + +static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) +{ + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct device *dev = pcie->dev; + struct resource_entry *entry; + struct regmap *pbus_regmap; + u32 val, args[2], size; + resource_size_t addr; + int err; + + /* + * The controller may have been left out of reset by the bootloader + * so make sure that we get a clean start by asserting resets here. + */ + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + + /* Wait for the time needed to complete the reset lines assert. */ + msleep(PCIE_EN7581_RESET_TIME_MS); + + /* + * Configure PBus base address and base address mask to allow the + * hw to detect if a given address is accessible on PCIe controller. + */ + pbus_regmap = syscon_regmap_lookup_by_phandle_args(dev->of_node, + "mediatek,pbus-csr", + ARRAY_SIZE(args), + args); + if (IS_ERR(pbus_regmap)) + return PTR_ERR(pbus_regmap); + + entry = resource_list_first_type(&host->windows, IORESOURCE_MEM); + if (!entry) + return -ENODEV; + + addr = entry->res->start - entry->offset; + regmap_write(pbus_regmap, args[0], lower_32_bits(addr)); + size = lower_32_bits(resource_size(entry->res)); + regmap_write(pbus_regmap, args[1], GENMASK(31, __fls(size))); + + /* + * Unlike the other MediaTek Gen3 controllers, the Airoha EN7581 + * requires PHY initialization and power-on before PHY reset deassert. + */ + err = phy_init(pcie->phy); + if (err) { + dev_err(dev, "failed to initialize PHY\n"); + return err; + } + + err = phy_power_on(pcie->phy); + if (err) { + dev_err(dev, "failed to power on PHY\n"); + goto err_phy_on; + } + + err = reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + if (err) { + dev_err(dev, "failed to deassert PHYs\n"); + goto err_phy_deassert; + } + + /* + * Wait for the time needed to complete the bulk de-assert above. + * This time is specific for EN7581 SoC. + */ + msleep(PCIE_EN7581_RESET_TIME_MS); + + pm_runtime_enable(dev); + pm_runtime_get_sync(dev); + + val = FIELD_PREP(PCIE_VAL_LN0_DOWNSTREAM, 0x47) | + FIELD_PREP(PCIE_VAL_LN1_DOWNSTREAM, 0x47) | + FIELD_PREP(PCIE_VAL_LN0_UPSTREAM, 0x41) | + FIELD_PREP(PCIE_VAL_LN1_UPSTREAM, 0x41); + writel_relaxed(val, pcie->base + PCIE_EQ_PRESET_01_REG); + + val = PCIE_K_PHYPARAM_QUERY | PCIE_K_QUERY_TIMEOUT | + FIELD_PREP(PCIE_K_PRESET_TO_USE_16G, 0x80) | + FIELD_PREP(PCIE_K_PRESET_TO_USE, 0x2) | + FIELD_PREP(PCIE_K_FINETUNE_MAX, 0xf); + writel_relaxed(val, pcie->base + PCIE_PIPE4_PIE8_REG); + + err = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks); + if (err) { + dev_err(dev, "failed to prepare clock\n"); + goto err_clk_prepare_enable; + } + + /* + * Airoha EN7581 performs PCIe reset via clk callbacks since it has a + * hw issue with PCIE_PE_RSTB signal. Add wait for the time needed to + * complete the PCIe reset. + */ + msleep(PCIE_T_PVPERL_MS); + + return 0; + +err_clk_prepare_enable: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); +err_phy_deassert: + phy_power_off(pcie->phy); +err_phy_on: + phy_exit(pcie->phy); + + return err; +} + +static int mtk_pcie_power_up(struct mtk_gen3_pcie *pcie) +{ + struct device *dev = pcie->dev; + int err; + + /* + * The controller may have been left out of reset by the bootloader + * so make sure that we get a clean start by asserting resets here. + */ + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + reset_control_assert(pcie->mac_reset); + usleep_range(PCIE_MTK_RESET_TIME_US, 2 * PCIE_MTK_RESET_TIME_US); + + /* PHY power on and enable pipe clock */ + err = reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + if (err) { + dev_err(dev, "failed to deassert PHYs\n"); + return err; + } + + err = phy_init(pcie->phy); + if (err) { + dev_err(dev, "failed to initialize PHY\n"); + goto err_phy_init; + } + + err = phy_power_on(pcie->phy); + if (err) { + dev_err(dev, "failed to power on PHY\n"); + goto err_phy_on; + } + + /* MAC power on and enable transaction layer clocks */ + reset_control_deassert(pcie->mac_reset); + + pm_runtime_enable(dev); + pm_runtime_get_sync(dev); + + err = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks); + if (err) { + dev_err(dev, "failed to enable clocks\n"); + goto err_clk_init; + } + + return 0; + +err_clk_init: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + reset_control_assert(pcie->mac_reset); + phy_power_off(pcie->phy); +err_phy_on: + phy_exit(pcie->phy); +err_phy_init: + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + + return err; +} + +static void mtk_pcie_power_down(struct mtk_gen3_pcie *pcie) +{ + clk_bulk_disable_unprepare(pcie->num_clks, pcie->clks); + + pm_runtime_put_sync(pcie->dev); + pm_runtime_disable(pcie->dev); + reset_control_assert(pcie->mac_reset); + + phy_power_off(pcie->phy); + phy_exit(pcie->phy); + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); +} + +static int mtk_pcie_get_controller_max_link_speed(struct mtk_gen3_pcie *pcie) +{ + u32 val; + int ret; + + val = readl_relaxed(pcie->base + PCIE_BASE_CFG_REG); + val = FIELD_GET(PCIE_BASE_CFG_SPEED, val); + ret = fls(val); + + return ret > 0 ? ret : -EINVAL; +} + +static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie) +{ + int err, max_speed; + + err = mtk_pcie_parse_port(pcie); + if (err) + return err; + + /* + * Deassert the line in order to avoid unbalance in deassert_count + * counter since the bulk is shared. + */ + reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + + /* Don't touch the hardware registers before power up */ + err = pcie->soc->power_up(pcie); + if (err) + return err; + + err = of_pci_get_max_link_speed(pcie->dev->of_node); + if (err) { + /* Get the maximum speed supported by the controller */ + max_speed = mtk_pcie_get_controller_max_link_speed(pcie); + + /* Set max_link_speed only if the controller supports it */ + if (max_speed >= 0 && max_speed <= err) { + pcie->max_link_speed = err; + dev_info(pcie->dev, + "maximum controller link speed Gen%d, overriding to Gen%u", + max_speed, pcie->max_link_speed); + } + } + + /* Try link up */ + err = mtk_pcie_startup_port(pcie); + if (err) + goto err_setup; + + err = mtk_pcie_setup_irq(pcie); + if (err) + goto err_setup; + + return 0; + +err_setup: + mtk_pcie_power_down(pcie); + + return err; +} + +static int mtk_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_gen3_pcie *pcie; + struct pci_host_bridge *host; + int err; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!host) + return -ENOMEM; + + pcie = pci_host_bridge_priv(host); + + pcie->dev = dev; + pcie->soc = device_get_match_data(dev); + platform_set_drvdata(pdev, pcie); + + err = mtk_pcie_setup(pcie); + if (err) + return err; + + host->ops = &mtk_pcie_ops; + host->sysdata = pcie; + + err = pci_host_probe(host); + if (err) { + mtk_pcie_irq_teardown(pcie); + mtk_pcie_power_down(pcie); + return err; + } + + return 0; +} + +static void mtk_pcie_remove(struct platform_device *pdev) +{ + struct mtk_gen3_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + + pci_lock_rescan_remove(); + pci_stop_root_bus(host->bus); + pci_remove_root_bus(host->bus); + pci_unlock_rescan_remove(); + + mtk_pcie_irq_teardown(pcie); + mtk_pcie_power_down(pcie); +} + +static void mtk_pcie_irq_save(struct mtk_gen3_pcie *pcie) +{ + int i; + + raw_spin_lock(&pcie->irq_lock); + + pcie->saved_irq_state = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + + for (i = 0; i < PCIE_MSI_SET_NUM; i++) { + struct mtk_msi_set *msi_set = &pcie->msi_sets[i]; + + msi_set->saved_irq_state = readl_relaxed(msi_set->base + + PCIE_MSI_SET_ENABLE_OFFSET); + } + + raw_spin_unlock(&pcie->irq_lock); +} + +static void mtk_pcie_irq_restore(struct mtk_gen3_pcie *pcie) +{ + int i; + + raw_spin_lock(&pcie->irq_lock); + + writel_relaxed(pcie->saved_irq_state, pcie->base + PCIE_INT_ENABLE_REG); + + for (i = 0; i < PCIE_MSI_SET_NUM; i++) { + struct mtk_msi_set *msi_set = &pcie->msi_sets[i]; + + writel_relaxed(msi_set->saved_irq_state, + msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + } + + raw_spin_unlock(&pcie->irq_lock); +} + +static int mtk_pcie_turn_off_link(struct mtk_gen3_pcie *pcie) +{ + u32 val; + + val = readl_relaxed(pcie->base + PCIE_ICMD_PM_REG); + val |= PCIE_TURN_OFF_LINK; + writel_relaxed(val, pcie->base + PCIE_ICMD_PM_REG); + + /* Check the link is L2 */ + return readl_poll_timeout(pcie->base + PCIE_LTSSM_STATUS_REG, val, + (PCIE_LTSSM_STATE(val) == + PCIE_LTSSM_STATE_L2_IDLE), 20, + 50 * USEC_PER_MSEC); +} + +static int mtk_pcie_suspend_noirq(struct device *dev) +{ + struct mtk_gen3_pcie *pcie = dev_get_drvdata(dev); + int err; + u32 val; + + /* Trigger link to L2 state */ + err = mtk_pcie_turn_off_link(pcie); + if (err) { + dev_err(pcie->dev, "cannot enter L2 state\n"); + return err; + } + + if (!(pcie->soc->flags & SKIP_PCIE_RSTB)) { + /* Assert the PERST# pin */ + val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); + val |= PCIE_PE_RSTB; + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + } + + dev_dbg(pcie->dev, "entered L2 states successfully"); + + mtk_pcie_irq_save(pcie); + mtk_pcie_power_down(pcie); + + return 0; +} + +static int mtk_pcie_resume_noirq(struct device *dev) +{ + struct mtk_gen3_pcie *pcie = dev_get_drvdata(dev); + int err; + + err = pcie->soc->power_up(pcie); + if (err) + return err; + + err = mtk_pcie_startup_port(pcie); + if (err) { + mtk_pcie_power_down(pcie); + return err; + } + + mtk_pcie_irq_restore(pcie); + + return 0; +} + +static const struct dev_pm_ops mtk_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_pcie_suspend_noirq, + mtk_pcie_resume_noirq) +}; + +static const struct mtk_gen3_pcie_pdata mtk_pcie_soc_mt8192 = { + .power_up = mtk_pcie_power_up, + .phy_resets = { + .id[0] = "phy", + .num_resets = 1, + }, +}; + +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 = { + .id[0] = "phy-lane0", + .id[1] = "phy-lane1", + .id[2] = "phy-lane2", + .num_resets = 3, + }, + .flags = SKIP_PCIE_RSTB, +}; + +static const struct of_device_id mtk_pcie_of_match[] = { + { .compatible = "airoha,en7581-pcie", .data = &mtk_pcie_soc_en7581 }, + { .compatible = "mediatek,mt8192-pcie", .data = &mtk_pcie_soc_mt8192 }, + { .compatible = "mediatek,mt8196-pcie", .data = &mtk_pcie_soc_mt8196 }, + {}, +}; +MODULE_DEVICE_TABLE(of, mtk_pcie_of_match); + +static struct platform_driver mtk_pcie_driver = { + .probe = mtk_pcie_probe, + .remove = mtk_pcie_remove, + .driver = { + .name = "mtk-pcie-gen3", + .of_match_table = mtk_pcie_of_match, + .pm = &mtk_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +module_platform_driver(mtk_pcie_driver); +MODULE_DESCRIPTION("MediaTek Gen3 PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 55e471c18e8d..4b78b6528f9f 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -12,8 +12,10 @@ #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> #include <linux/msi.h> #include <linux/module.h> #include <linux/of_address.h> @@ -23,6 +25,7 @@ #include <linux/phy/phy.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> +#include <linux/regmap.h> #include <linux/reset.h> #include "../pci.h" @@ -73,6 +76,7 @@ #define PCIE_MSI_VECTOR 0x0c0 #define PCIE_CONF_VEND_ID 0x100 +#define PCIE_CONF_DEVICE_ID 0x102 #define PCIE_CONF_CLASS_ID 0x106 #define PCIE_INT_MASK 0x420 @@ -90,6 +94,12 @@ #define AHB2PCIE_SIZE(x) ((x) & GENMASK(4, 0)) #define PCIE_AXI_WINDOW0 0x448 #define WIN_ENABLE BIT(7) +/* + * Define PCIe to AHB window size as 2^33 to support max 8GB address space + * translate, support least 4GB DRAM size access from EP DMA(physical DRAM + * start from 0x40000000). + */ +#define PCIE2AHB_SIZE 0x21 /* PCIe V2 configuration transaction header */ #define PCIE_CFG_HEADER0 0x460 @@ -133,17 +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 + * @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; + 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; }; /** @@ -165,7 +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 */ @@ -185,7 +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); }; @@ -194,21 +218,19 @@ struct mtk_pcie_port { * struct mtk_pcie - PCIe host information * @dev: pointer to PCIe device * @base: IO mapped register base + * @cfg: IO mapped register map for PCIe config * @free_ck: free-run reference clock - * @mem: non-prefetchable memory resource * @ports: pointer to PCIe port information * @soc: pointer to SoC-dependent operations - * @busnr: root bus number */ struct mtk_pcie { struct device *dev; void __iomem *base; + struct regmap *cfg; struct clk *free_ck; - struct resource mem; struct list_head ports; const struct mtk_pcie_soc *soc; - unsigned int busnr; }; static void mtk_pcie_subsys_powerdown(struct mtk_pcie *pcie) @@ -351,19 +373,12 @@ static int mtk_pcie_config_read(struct pci_bus *bus, unsigned int devfn, { struct mtk_pcie_port *port; u32 bn = bus->number; - int ret; port = mtk_pcie_find_port(bus, devfn); - if (!port) { - *val = ~0; + if (!port) return PCIBIOS_DEVICE_NOT_FOUND; - } - ret = mtk_pcie_hw_rd_cfg(port, bn, devfn, where, size, val); - if (ret) - *val = ~0; - - return ret; + return mtk_pcie_hw_rd_cfg(port, bn, devfn, where, size, val); } static int mtk_pcie_config_write(struct pci_bus *bus, unsigned int devfn, @@ -400,12 +415,6 @@ static void mtk_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) (int)data->hwirq, msg->address_hi, msg->address_lo); } -static int mtk_msi_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) -{ - return -EINVAL; -} - static void mtk_msi_ack_irq(struct irq_data *data) { struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data); @@ -417,7 +426,6 @@ static void mtk_msi_ack_irq(struct irq_data *data) static struct irq_chip mtk_msi_bottom_irq_chip = { .name = "MTK MSI", .irq_compose_msi_msg = mtk_compose_msi_msg, - .irq_set_affinity = mtk_msi_set_affinity, .irq_ack = mtk_msi_ack_irq, }; @@ -471,40 +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) + +#define MTK_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX) -static struct msi_domain_info mtk_msi_domain_info = { - .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX), - .chip = &mtk_msi_irq_chip, +static 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; } @@ -533,8 +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); } @@ -570,8 +575,9 @@ 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"); return -ENODEV; @@ -591,7 +597,6 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc) struct mtk_pcie_port *port = irq_desc_get_handler_data(desc); struct irq_chip *irqchip = irq_desc_get_chip(desc); unsigned long status; - u32 virq; u32 bit = INTX_SHIFT; chained_irq_enter(irqchip, desc); @@ -601,9 +606,8 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc) for_each_set_bit_from(bit, &status, PCI_NUM_INTX + INTX_SHIFT) { /* Clear the INTx */ writel(1 << bit, port->base + PCIE_INT_STATUS); - virq = irq_find_mapping(port->irq_domain, - bit - INTX_SHIFT); - generic_handle_irq(virq); + generic_handle_domain_irq(port->irq_domain, + bit - INTX_SHIFT); } } @@ -611,20 +615,22 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc) if (status & MSI_STATUS){ unsigned long imsi_status; + /* + * The interrupt status can be cleared even if the + * MSI status remains pending. As such, given the + * edge-triggered interrupt type, its status should + * be cleared before being dispatched to the + * handler of the underlying device. + */ + writel(MSI_STATUS, port->base + PCIE_INT_STATUS); while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) { - for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM) { - virq = irq_find_mapping(port->inner_domain, bit); - generic_handle_irq(virq); - } + for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM) + generic_handle_domain_irq(port->inner_domain, bit); } - /* Clear MSI interrupt status */ - writel(MSI_STATUS, port->base + PCIE_INT_STATUS); } } chained_irq_exit(irqchip, desc); - - return; } static int mtk_pcie_setup_irq(struct mtk_pcie_port *port, @@ -641,7 +647,14 @@ static int mtk_pcie_setup_irq(struct mtk_pcie_port *port, return err; } - port->irq = platform_get_irq(pdev, port->slot); + if (of_property_present(dev->of_node, "interrupt-names")) + port->irq = platform_get_irq_byname(pdev, "pcie_irq"); + else + port->irq = platform_get_irq(pdev, port->slot); + + if (port->irq < 0) + return port->irq; + irq_set_chained_handler_and_data(port->irq, mtk_pcie_intr_handler, port); @@ -651,38 +664,53 @@ static int mtk_pcie_setup_irq(struct mtk_pcie_port *port, static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) { struct mtk_pcie *pcie = port->pcie; - struct resource *mem = &pcie->mem; + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct resource *mem = NULL; + struct resource_entry *entry; const struct mtk_pcie_soc *soc = port->pcie->soc; u32 val; - size_t size; int err; + entry = resource_list_first_type(&host->windows, IORESOURCE_MEM); + if (entry) + mem = entry->res; + if (!mem) + return -EINVAL; + /* MT7622 platforms need to enable LTSSM and ASPM from PCIe subsys */ if (pcie->base) { val = readl(pcie->base + PCIE_SYS_CFG_V2); val |= PCIE_CSR_LTSSM_EN(port->slot) | PCIE_CSR_ASPM_L1_EN(port->slot); writel(val, pcie->base + PCIE_SYS_CFG_V2); + } else if (pcie->cfg) { + val = PCIE_CSR_LTSSM_EN(port->slot) | + PCIE_CSR_ASPM_L1_EN(port->slot); + regmap_update_bits(pcie->cfg, PCIE_SYS_CFG_V2, val, val); } - /* Assert all reset signals */ - writel(0, port->base + PCIE_RST_CTRL); + 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); + + 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); @@ -690,6 +718,9 @@ static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) writew(val, port->base + PCIE_CONF_CLASS_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 */ err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_V2, val, !!(val & PCIE_PORT_LINKUP_V2), 20, @@ -706,15 +737,15 @@ static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) mtk_pcie_enable_msi(port); /* Set AHB to PCIe translation windows */ - size = mem->end - mem->start; - val = lower_32_bits(mem->start) | AHB2PCIE_SIZE(fls(size)); + val = lower_32_bits(mem->start) | + AHB2PCIE_SIZE(fls(resource_size(mem))); writel(val, port->base + PCIE_AHB_TRANS_BASE0_L); val = upper_32_bits(mem->start); writel(val, port->base + PCIE_AHB_TRANS_BASE0_H); /* Set PCIe to AXI translation memory space.*/ - val = fls(0xffffffff) | WIN_ENABLE; + val = PCIE2AHB_SIZE | WIN_ENABLE; writel(val, port->base + PCIE_AXI_WINDOW0); return 0; @@ -740,7 +771,7 @@ static struct pci_ops mtk_pcie_ops = { static int mtk_pcie_startup_port(struct mtk_pcie_port *port) { struct mtk_pcie *pcie = port->pcie; - u32 func = PCI_FUNC(port->slot << 3); + u32 func = PCI_FUNC(port->slot); u32 slot = PCI_SLOT(port->slot << 3); u32 val; int err; @@ -797,6 +828,41 @@ static int mtk_pcie_startup_port(struct mtk_pcie_port *port) return 0; } +static int mtk_pcie_startup_port_an7583(struct mtk_pcie_port *port) +{ + struct mtk_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + struct pci_host_bridge *host; + struct resource_entry *entry; + struct regmap *pbus_regmap; + resource_size_t addr; + u32 args[2], size; + + /* + * Configure PBus base address and base address mask to allow + * the hw to detect if a given address is accessible on PCIe + * controller. + */ + pbus_regmap = syscon_regmap_lookup_by_phandle_args(dev->of_node, + "mediatek,pbus-csr", + ARRAY_SIZE(args), + args); + if (IS_ERR(pbus_regmap)) + return PTR_ERR(pbus_regmap); + + host = pci_host_bridge_from_priv(pcie); + entry = resource_list_first_type(&host->windows, IORESOURCE_MEM); + if (!entry) + return -ENODEV; + + addr = entry->res->start - entry->offset; + regmap_write(pbus_regmap, args[0], lower_32_bits(addr)); + size = lower_32_bits(resource_size(entry->res)); + regmap_write(pbus_regmap, args[1], GENMASK(31, __fls(size))); + + return mtk_pcie_startup_port_v2(port); +} + static void mtk_pcie_enable_port(struct mtk_pcie_port *port) { struct mtk_pcie *pcie = port->pcie; @@ -883,7 +949,6 @@ static int mtk_pcie_parse_port(struct mtk_pcie *pcie, int slot) { struct mtk_pcie_port *port; - struct resource *regs; struct device *dev = pcie->dev; struct platform_device *pdev = to_platform_device(dev); char name[10]; @@ -894,8 +959,7 @@ static int mtk_pcie_parse_port(struct mtk_pcie *pcie, return -ENOMEM; snprintf(name, sizeof(name), "port%d", slot); - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, name); - port->base = devm_ioremap_resource(dev, regs); + port->base = devm_platform_ioremap_resource_byname(pdev, name); if (IS_ERR(port->base)) { dev_err(dev, "failed to map port%d base\n", slot); return PTR_ERR(port->base); @@ -910,49 +974,29 @@ static int mtk_pcie_parse_port(struct mtk_pcie *pcie, /* sys_ck might be divided into the following parts in some chips */ snprintf(name, sizeof(name), "ahb_ck%d", slot); - port->ahb_ck = devm_clk_get(dev, name); - if (IS_ERR(port->ahb_ck)) { - if (PTR_ERR(port->ahb_ck) == -EPROBE_DEFER) - return -EPROBE_DEFER; - - port->ahb_ck = NULL; - } + port->ahb_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->ahb_ck)) + return PTR_ERR(port->ahb_ck); snprintf(name, sizeof(name), "axi_ck%d", slot); - port->axi_ck = devm_clk_get(dev, name); - if (IS_ERR(port->axi_ck)) { - if (PTR_ERR(port->axi_ck) == -EPROBE_DEFER) - return -EPROBE_DEFER; - - port->axi_ck = NULL; - } + port->axi_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->axi_ck)) + return PTR_ERR(port->axi_ck); snprintf(name, sizeof(name), "aux_ck%d", slot); - port->aux_ck = devm_clk_get(dev, name); - if (IS_ERR(port->aux_ck)) { - if (PTR_ERR(port->aux_ck) == -EPROBE_DEFER) - return -EPROBE_DEFER; - - port->aux_ck = NULL; - } + port->aux_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->aux_ck)) + return PTR_ERR(port->aux_ck); snprintf(name, sizeof(name), "obff_ck%d", slot); - port->obff_ck = devm_clk_get(dev, name); - if (IS_ERR(port->obff_ck)) { - if (PTR_ERR(port->obff_ck) == -EPROBE_DEFER) - return -EPROBE_DEFER; - - port->obff_ck = NULL; - } + port->obff_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->obff_ck)) + return PTR_ERR(port->obff_ck); snprintf(name, sizeof(name), "pipe_ck%d", slot); - port->pipe_ck = devm_clk_get(dev, name); - if (IS_ERR(port->pipe_ck)) { - if (PTR_ERR(port->pipe_ck) == -EPROBE_DEFER) - return -EPROBE_DEFER; - - port->pipe_ck = NULL; - } + port->pipe_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->pipe_ck)) + return PTR_ERR(port->pipe_ck); snprintf(name, sizeof(name), "pcie-rst%d", slot); port->reset = devm_reset_control_get_optional_exclusive(dev, name); @@ -985,16 +1029,24 @@ static int mtk_pcie_subsys_powerup(struct mtk_pcie *pcie) struct device *dev = pcie->dev; struct platform_device *pdev = to_platform_device(dev); struct resource *regs; + struct device_node *cfg_node; int err; /* get shared registers, which are optional */ regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "subsys"); if (regs) { pcie->base = devm_ioremap_resource(dev, regs); - if (IS_ERR(pcie->base)) { - dev_err(dev, "failed to map shared register\n"); + if (IS_ERR(pcie->base)) return PTR_ERR(pcie->base); - } + } + + cfg_node = of_find_compatible_node(NULL, NULL, + "mediatek,generic-pciecfg"); + if (cfg_node) { + pcie->cfg = syscon_node_to_regmap(cfg_node); + of_node_put(cfg_node); + if (IS_ERR(pcie->cfg)) + return PTR_ERR(pcie->cfg); } pcie->free_ck = devm_clk_get(dev, "free_ck"); @@ -1027,56 +1079,25 @@ err_free_ck: static int mtk_pcie_setup(struct mtk_pcie *pcie) { struct device *dev = pcie->dev; - struct device_node *node = dev->of_node, *child; + struct device_node *node = dev->of_node; struct mtk_pcie_port *port, *tmp; - struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); - struct list_head *windows = &host->windows; - struct resource_entry *win, *tmp_win; - resource_size_t io_base; - int err; + int err, slot; - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, - windows, &io_base); - if (err) - return err; + slot = of_get_pci_domain_nr(dev->of_node); + if (slot < 0) { + for_each_available_child_of_node_scoped(node, child) { + err = of_pci_get_devfn(child); + if (err < 0) + return dev_err_probe(dev, err, "failed to get devfn\n"); - err = devm_request_pci_bus_resources(dev, windows); - if (err < 0) - return err; + slot = PCI_SLOT(err); - /* Get the I/O and memory ranges from DT */ - resource_list_for_each_entry_safe(win, tmp_win, windows) { - switch (resource_type(win->res)) { - case IORESOURCE_IO: - err = devm_pci_remap_iospace(dev, win->res, io_base); - if (err) { - dev_warn(dev, "error %d: failed to map resource %pR\n", - err, win->res); - resource_list_destroy_entry(win); - } - break; - case IORESOURCE_MEM: - memcpy(&pcie->mem, win->res, sizeof(*win->res)); - pcie->mem.name = "non-prefetchable"; - break; - case IORESOURCE_BUS: - pcie->busnr = win->res->start; - break; + err = mtk_pcie_parse_port(pcie, child, slot); + if (err) + return err; } - } - - for_each_available_child_of_node(node, child) { - int slot; - - err = of_pci_get_devfn(child); - if (err < 0) { - dev_err(dev, "failed to parse devfn: %d\n", err); - return err; - } - - slot = PCI_SLOT(err); - - err = mtk_pcie_parse_port(pcie, child, slot); + } else { + err = mtk_pcie_parse_port(pcie, node, slot); if (err) return err; } @@ -1118,12 +1139,9 @@ static int mtk_pcie_probe(struct platform_device *pdev) if (err) return err; - host->busnr = pcie->busnr; - host->dev.parent = pcie->dev; host->ops = pcie->soc->ops; - host->map_irq = of_irq_parse_and_map_pci; - host->swizzle_irq = pci_common_swizzle; host->sysdata = pcie; + host->msi_domain = !!(pcie->soc->quirks & MTK_PCIE_NO_MSI); err = pci_host_probe(host); if (err) @@ -1147,7 +1165,7 @@ static void mtk_pcie_free_resources(struct mtk_pcie *pcie) pci_free_resource_list(windows); } -static int mtk_pcie_remove(struct platform_device *pdev) +static void mtk_pcie_remove(struct platform_device *pdev) { struct mtk_pcie *pcie = platform_get_drvdata(pdev); struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); @@ -1159,11 +1177,9 @@ static int mtk_pcie_remove(struct platform_device *pdev) mtk_pcie_irq_teardown(pcie); mtk_pcie_put_resources(pcie); - - return 0; } -static int __maybe_unused mtk_pcie_suspend_noirq(struct device *dev) +static int mtk_pcie_suspend_noirq(struct device *dev) { struct mtk_pcie *pcie = dev_get_drvdata(dev); struct mtk_pcie_port *port; @@ -1187,7 +1203,7 @@ static int __maybe_unused mtk_pcie_suspend_noirq(struct device *dev) return 0; } -static int __maybe_unused mtk_pcie_resume_noirq(struct device *dev) +static int mtk_pcie_resume_noirq(struct device *dev) { struct mtk_pcie *pcie = dev_get_drvdata(dev); struct mtk_pcie_port *port, *tmp; @@ -1208,13 +1224,14 @@ static int __maybe_unused mtk_pcie_resume_noirq(struct device *dev) } static const struct dev_pm_ops mtk_pcie_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_pcie_suspend_noirq, - mtk_pcie_resume_noirq) + NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_pcie_suspend_noirq, + mtk_pcie_resume_noirq) }; static const struct mtk_pcie_soc mtk_pcie_soc_v1 = { .ops = &mtk_pcie_ops, .startup = mtk_pcie_startup_port, + .quirks = MTK_PCIE_NO_MSI, }; static const struct mtk_pcie_soc mtk_pcie_soc_mt2712 = { @@ -1224,19 +1241,37 @@ 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 = { + .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 }, { .compatible = "mediatek,mt7622-pcie", .data = &mtk_pcie_soc_mt7622 }, + { .compatible = "mediatek,mt7629-pcie", .data = &mtk_pcie_soc_mt7629 }, {}, }; +MODULE_DEVICE_TABLE(of, mtk_pcie_ids); static struct platform_driver mtk_pcie_driver = { .probe = mtk_pcie_probe, @@ -1249,4 +1284,5 @@ static struct platform_driver mtk_pcie_driver = { }, }; module_platform_driver(mtk_pcie_driver); +MODULE_DESCRIPTION("MediaTek PCIe host controller driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c deleted file mode 100644 index 77052a0712d0..000000000000 --- a/drivers/pci/controller/pcie-mobiveil.c +++ /dev/null @@ -1,861 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * PCIe host controller driver for Mobiveil PCIe Host controller - * - * Copyright (c) 2018 Mobiveil Inc. - * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> - */ - -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/irqchip/chained_irq.h> -#include <linux/irqdomain.h> -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/msi.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/of_platform.h> -#include <linux/of_pci.h> -#include <linux/pci.h> -#include <linux/platform_device.h> -#include <linux/slab.h> - -#include "../pci.h" - -/* register offsets and bit positions */ - -/* - * translation tables are grouped into windows, each window registers are - * grouped into blocks of 4 or 16 registers each - */ -#define PAB_REG_BLOCK_SIZE 16 -#define PAB_EXT_REG_BLOCK_SIZE 4 - -#define PAB_REG_ADDR(offset, win) (offset + (win * PAB_REG_BLOCK_SIZE)) -#define PAB_EXT_REG_ADDR(offset, win) (offset + (win * PAB_EXT_REG_BLOCK_SIZE)) - -#define LTSSM_STATUS 0x0404 -#define LTSSM_STATUS_L0_MASK 0x3f -#define LTSSM_STATUS_L0 0x2d - -#define PAB_CTRL 0x0808 -#define AMBA_PIO_ENABLE_SHIFT 0 -#define PEX_PIO_ENABLE_SHIFT 1 -#define PAGE_SEL_SHIFT 13 -#define PAGE_SEL_MASK 0x3f -#define PAGE_LO_MASK 0x3ff -#define PAGE_SEL_EN 0xc00 -#define PAGE_SEL_OFFSET_SHIFT 10 - -#define PAB_AXI_PIO_CTRL 0x0840 -#define APIO_EN_MASK 0xf - -#define PAB_PEX_PIO_CTRL 0x08c0 -#define PIO_ENABLE_SHIFT 0 - -#define PAB_INTP_AMBA_MISC_ENB 0x0b0c -#define PAB_INTP_AMBA_MISC_STAT 0x0b1c -#define PAB_INTP_INTX_MASK 0x01e0 -#define PAB_INTP_MSI_MASK 0x8 - -#define PAB_AXI_AMAP_CTRL(win) PAB_REG_ADDR(0x0ba0, win) -#define WIN_ENABLE_SHIFT 0 -#define WIN_TYPE_SHIFT 1 - -#define PAB_EXT_AXI_AMAP_SIZE(win) PAB_EXT_REG_ADDR(0xbaf0, win) - -#define PAB_AXI_AMAP_AXI_WIN(win) PAB_REG_ADDR(0x0ba4, win) -#define AXI_WINDOW_ALIGN_MASK 3 - -#define PAB_AXI_AMAP_PEX_WIN_L(win) PAB_REG_ADDR(0x0ba8, win) -#define PAB_BUS_SHIFT 24 -#define PAB_DEVICE_SHIFT 19 -#define PAB_FUNCTION_SHIFT 16 - -#define PAB_AXI_AMAP_PEX_WIN_H(win) PAB_REG_ADDR(0x0bac, win) -#define PAB_INTP_AXI_PIO_CLASS 0x474 - -#define PAB_PEX_AMAP_CTRL(win) PAB_REG_ADDR(0x4ba0, win) -#define AMAP_CTRL_EN_SHIFT 0 -#define AMAP_CTRL_TYPE_SHIFT 1 - -#define PAB_EXT_PEX_AMAP_SIZEN(win) PAB_EXT_REG_ADDR(0xbef0, win) -#define PAB_PEX_AMAP_AXI_WIN(win) PAB_REG_ADDR(0x4ba4, win) -#define PAB_PEX_AMAP_PEX_WIN_L(win) PAB_REG_ADDR(0x4ba8, win) -#define PAB_PEX_AMAP_PEX_WIN_H(win) PAB_REG_ADDR(0x4bac, win) - -/* starting offset of INTX bits in status register */ -#define PAB_INTX_START 5 - -/* supported number of MSI interrupts */ -#define PCI_NUM_MSI 16 - -/* MSI registers */ -#define MSI_BASE_LO_OFFSET 0x04 -#define MSI_BASE_HI_OFFSET 0x08 -#define MSI_SIZE_OFFSET 0x0c -#define MSI_ENABLE_OFFSET 0x14 -#define MSI_STATUS_OFFSET 0x18 -#define MSI_DATA_OFFSET 0x20 -#define MSI_ADDR_L_OFFSET 0x24 -#define MSI_ADDR_H_OFFSET 0x28 - -/* outbound and inbound window definitions */ -#define WIN_NUM_0 0 -#define WIN_NUM_1 1 -#define CFG_WINDOW_TYPE 0 -#define IO_WINDOW_TYPE 1 -#define MEM_WINDOW_TYPE 2 -#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024) -#define MAX_PIO_WINDOWS 8 - -/* Parameters for the waiting for link up routine */ -#define LINK_WAIT_MAX_RETRIES 10 -#define LINK_WAIT_MIN 90000 -#define LINK_WAIT_MAX 100000 - -struct mobiveil_msi { /* MSI information */ - struct mutex lock; /* protect bitmap variable */ - struct irq_domain *msi_domain; - struct irq_domain *dev_domain; - phys_addr_t msi_pages_phys; - int num_of_vectors; - DECLARE_BITMAP(msi_irq_in_use, PCI_NUM_MSI); -}; - -struct mobiveil_pcie { - struct platform_device *pdev; - struct list_head resources; - void __iomem *config_axi_slave_base; /* endpoint config base */ - void __iomem *csr_axi_slave_base; /* root port config base */ - void __iomem *apb_csr_base; /* MSI register base */ - phys_addr_t pcie_reg_base; /* Physical PCIe Controller Base */ - struct irq_domain *intx_domain; - raw_spinlock_t intx_mask_lock; - int irq; - int apio_wins; - int ppio_wins; - int ob_wins_configured; /* configured outbound windows */ - int ib_wins_configured; /* configured inbound windows */ - struct resource *ob_io_res; - char root_bus_nr; - struct mobiveil_msi msi; -}; - -static inline void csr_writel(struct mobiveil_pcie *pcie, const u32 value, - const u32 reg) -{ - writel_relaxed(value, pcie->csr_axi_slave_base + reg); -} - -static inline u32 csr_readl(struct mobiveil_pcie *pcie, const u32 reg) -{ - return readl_relaxed(pcie->csr_axi_slave_base + reg); -} - -static bool mobiveil_pcie_link_up(struct mobiveil_pcie *pcie) -{ - return (csr_readl(pcie, LTSSM_STATUS) & - LTSSM_STATUS_L0_MASK) == LTSSM_STATUS_L0; -} - -static bool mobiveil_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) -{ - struct mobiveil_pcie *pcie = bus->sysdata; - - /* Only one device down on each root port */ - if ((bus->number == pcie->root_bus_nr) && (devfn > 0)) - return false; - - /* - * Do not read more than one device on the bus directly - * attached to RC - */ - if ((bus->primary == pcie->root_bus_nr) && (devfn > 0)) - return false; - - return true; -} - -/* - * mobiveil_pcie_map_bus - routine to get the configuration base of either - * root port or endpoint - */ -static void __iomem *mobiveil_pcie_map_bus(struct pci_bus *bus, - unsigned int devfn, int where) -{ - struct mobiveil_pcie *pcie = bus->sysdata; - - if (!mobiveil_pcie_valid_device(bus, devfn)) - return NULL; - - if (bus->number == pcie->root_bus_nr) { - /* RC config access */ - return pcie->csr_axi_slave_base + where; - } - - /* - * EP config access (in Config/APIO space) - * Program PEX Address base (31..16 bits) with appropriate value - * (BDF) in PAB_AXI_AMAP_PEX_WIN_L0 Register. - * Relies on pci_lock serialization - */ - csr_writel(pcie, bus->number << PAB_BUS_SHIFT | - PCI_SLOT(devfn) << PAB_DEVICE_SHIFT | - PCI_FUNC(devfn) << PAB_FUNCTION_SHIFT, - PAB_AXI_AMAP_PEX_WIN_L(WIN_NUM_0)); - return pcie->config_axi_slave_base + where; -} - -static struct pci_ops mobiveil_pcie_ops = { - .map_bus = mobiveil_pcie_map_bus, - .read = pci_generic_config_read, - .write = pci_generic_config_write, -}; - -static void mobiveil_pcie_isr(struct irq_desc *desc) -{ - struct irq_chip *chip = irq_desc_get_chip(desc); - struct mobiveil_pcie *pcie = irq_desc_get_handler_data(desc); - struct device *dev = &pcie->pdev->dev; - struct mobiveil_msi *msi = &pcie->msi; - u32 msi_data, msi_addr_lo, msi_addr_hi; - u32 intr_status, msi_status; - unsigned long shifted_status; - u32 bit, virq, val, mask; - - /* - * The core provides a single interrupt for both INTx/MSI messages. - * So we'll read both INTx and MSI status - */ - - chained_irq_enter(chip, desc); - - /* read INTx status */ - val = csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT); - mask = csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); - intr_status = val & mask; - - /* Handle INTx */ - if (intr_status & PAB_INTP_INTX_MASK) { - shifted_status = csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT) >> - PAB_INTX_START; - do { - for_each_set_bit(bit, &shifted_status, PCI_NUM_INTX) { - virq = irq_find_mapping(pcie->intx_domain, - bit + 1); - if (virq) - generic_handle_irq(virq); - else - dev_err_ratelimited(dev, - "unexpected IRQ, INT%d\n", bit); - - /* clear interrupt */ - csr_writel(pcie, - shifted_status << PAB_INTX_START, - PAB_INTP_AMBA_MISC_STAT); - } - } while ((shifted_status >> PAB_INTX_START) != 0); - } - - /* read extra MSI status register */ - msi_status = readl_relaxed(pcie->apb_csr_base + MSI_STATUS_OFFSET); - - /* handle MSI interrupts */ - while (msi_status & 1) { - msi_data = readl_relaxed(pcie->apb_csr_base - + MSI_DATA_OFFSET); - - /* - * MSI_STATUS_OFFSET register gets updated to zero - * once we pop not only the MSI data but also address - * from MSI hardware FIFO. So keeping these following - * two dummy reads. - */ - msi_addr_lo = readl_relaxed(pcie->apb_csr_base + - MSI_ADDR_L_OFFSET); - msi_addr_hi = readl_relaxed(pcie->apb_csr_base + - MSI_ADDR_H_OFFSET); - dev_dbg(dev, "MSI registers, data: %08x, addr: %08x:%08x\n", - msi_data, msi_addr_hi, msi_addr_lo); - - virq = irq_find_mapping(msi->dev_domain, msi_data); - if (virq) - generic_handle_irq(virq); - - msi_status = readl_relaxed(pcie->apb_csr_base + - MSI_STATUS_OFFSET); - } - - /* Clear the interrupt status */ - csr_writel(pcie, intr_status, PAB_INTP_AMBA_MISC_STAT); - chained_irq_exit(chip, desc); -} - -static int mobiveil_pcie_parse_dt(struct mobiveil_pcie *pcie) -{ - struct device *dev = &pcie->pdev->dev; - struct platform_device *pdev = pcie->pdev; - struct device_node *node = dev->of_node; - struct resource *res; - - /* map config resource */ - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "config_axi_slave"); - pcie->config_axi_slave_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(pcie->config_axi_slave_base)) - return PTR_ERR(pcie->config_axi_slave_base); - pcie->ob_io_res = res; - - /* map csr resource */ - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "csr_axi_slave"); - pcie->csr_axi_slave_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(pcie->csr_axi_slave_base)) - return PTR_ERR(pcie->csr_axi_slave_base); - pcie->pcie_reg_base = res->start; - - /* map MSI config resource */ - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "apb_csr"); - pcie->apb_csr_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(pcie->apb_csr_base)) - return PTR_ERR(pcie->apb_csr_base); - - /* read the number of windows requested */ - if (of_property_read_u32(node, "apio-wins", &pcie->apio_wins)) - pcie->apio_wins = MAX_PIO_WINDOWS; - - if (of_property_read_u32(node, "ppio-wins", &pcie->ppio_wins)) - pcie->ppio_wins = MAX_PIO_WINDOWS; - - pcie->irq = platform_get_irq(pdev, 0); - if (pcie->irq <= 0) { - dev_err(dev, "failed to map IRQ: %d\n", pcie->irq); - return -ENODEV; - } - - irq_set_chained_handler_and_data(pcie->irq, mobiveil_pcie_isr, pcie); - - return 0; -} - -/* - * select_paged_register - routine to access paged register of root complex - * - * registers of RC are paged, for this scheme to work - * extracted higher 6 bits of the offset will be written to pg_sel - * field of PAB_CTRL register and rest of the lower 10 bits enabled with - * PAGE_SEL_EN are used as offset of the register. - */ -static void select_paged_register(struct mobiveil_pcie *pcie, u32 offset) -{ - int pab_ctrl_dw, pg_sel; - - /* clear pg_sel field */ - pab_ctrl_dw = csr_readl(pcie, PAB_CTRL); - pab_ctrl_dw = (pab_ctrl_dw & ~(PAGE_SEL_MASK << PAGE_SEL_SHIFT)); - - /* set pg_sel field */ - pg_sel = (offset >> PAGE_SEL_OFFSET_SHIFT) & PAGE_SEL_MASK; - pab_ctrl_dw |= ((pg_sel << PAGE_SEL_SHIFT)); - csr_writel(pcie, pab_ctrl_dw, PAB_CTRL); -} - -static void write_paged_register(struct mobiveil_pcie *pcie, - u32 val, u32 offset) -{ - u32 off = (offset & PAGE_LO_MASK) | PAGE_SEL_EN; - - select_paged_register(pcie, offset); - csr_writel(pcie, val, off); -} - -static u32 read_paged_register(struct mobiveil_pcie *pcie, u32 offset) -{ - u32 off = (offset & PAGE_LO_MASK) | PAGE_SEL_EN; - - select_paged_register(pcie, offset); - return csr_readl(pcie, off); -} - -static void program_ib_windows(struct mobiveil_pcie *pcie, int win_num, - int pci_addr, u32 type, u64 size) -{ - int pio_ctrl_val; - int amap_ctrl_dw; - u64 size64 = ~(size - 1); - - if ((pcie->ib_wins_configured + 1) > pcie->ppio_wins) { - dev_err(&pcie->pdev->dev, - "ERROR: max inbound windows reached !\n"); - return; - } - - pio_ctrl_val = csr_readl(pcie, PAB_PEX_PIO_CTRL); - csr_writel(pcie, - pio_ctrl_val | (1 << PIO_ENABLE_SHIFT), PAB_PEX_PIO_CTRL); - amap_ctrl_dw = read_paged_register(pcie, PAB_PEX_AMAP_CTRL(win_num)); - amap_ctrl_dw = (amap_ctrl_dw | (type << AMAP_CTRL_TYPE_SHIFT)); - amap_ctrl_dw = (amap_ctrl_dw | (1 << AMAP_CTRL_EN_SHIFT)); - - write_paged_register(pcie, amap_ctrl_dw | lower_32_bits(size64), - PAB_PEX_AMAP_CTRL(win_num)); - - write_paged_register(pcie, upper_32_bits(size64), - PAB_EXT_PEX_AMAP_SIZEN(win_num)); - - write_paged_register(pcie, pci_addr, PAB_PEX_AMAP_AXI_WIN(win_num)); - write_paged_register(pcie, pci_addr, PAB_PEX_AMAP_PEX_WIN_L(win_num)); - write_paged_register(pcie, 0, PAB_PEX_AMAP_PEX_WIN_H(win_num)); -} - -/* - * routine to program the outbound windows - */ -static void program_ob_windows(struct mobiveil_pcie *pcie, int win_num, - u64 cpu_addr, u64 pci_addr, u32 config_io_bit, u64 size) -{ - - u32 value, type; - u64 size64 = ~(size - 1); - - if ((pcie->ob_wins_configured + 1) > pcie->apio_wins) { - dev_err(&pcie->pdev->dev, - "ERROR: max outbound windows reached !\n"); - return; - } - - /* - * program Enable Bit to 1, Type Bit to (00) base 2, AXI Window Size Bit - * to 4 KB in PAB_AXI_AMAP_CTRL register - */ - type = config_io_bit; - value = csr_readl(pcie, PAB_AXI_AMAP_CTRL(win_num)); - csr_writel(pcie, 1 << WIN_ENABLE_SHIFT | type << WIN_TYPE_SHIFT | - lower_32_bits(size64), PAB_AXI_AMAP_CTRL(win_num)); - - write_paged_register(pcie, upper_32_bits(size64), - PAB_EXT_AXI_AMAP_SIZE(win_num)); - - /* - * program AXI window base with appropriate value in - * PAB_AXI_AMAP_AXI_WIN0 register - */ - value = csr_readl(pcie, PAB_AXI_AMAP_AXI_WIN(win_num)); - csr_writel(pcie, cpu_addr & (~AXI_WINDOW_ALIGN_MASK), - PAB_AXI_AMAP_AXI_WIN(win_num)); - - value = csr_readl(pcie, PAB_AXI_AMAP_PEX_WIN_H(win_num)); - - csr_writel(pcie, lower_32_bits(pci_addr), - PAB_AXI_AMAP_PEX_WIN_L(win_num)); - csr_writel(pcie, upper_32_bits(pci_addr), - PAB_AXI_AMAP_PEX_WIN_H(win_num)); - - pcie->ob_wins_configured++; -} - -static int mobiveil_bringup_link(struct mobiveil_pcie *pcie) -{ - int retries; - - /* check if the link is up or not */ - for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { - if (mobiveil_pcie_link_up(pcie)) - return 0; - - usleep_range(LINK_WAIT_MIN, LINK_WAIT_MAX); - } - dev_err(&pcie->pdev->dev, "link never came up\n"); - return -ETIMEDOUT; -} - -static void mobiveil_pcie_enable_msi(struct mobiveil_pcie *pcie) -{ - phys_addr_t msg_addr = pcie->pcie_reg_base; - struct mobiveil_msi *msi = &pcie->msi; - - pcie->msi.num_of_vectors = PCI_NUM_MSI; - msi->msi_pages_phys = (phys_addr_t)msg_addr; - - writel_relaxed(lower_32_bits(msg_addr), - pcie->apb_csr_base + MSI_BASE_LO_OFFSET); - writel_relaxed(upper_32_bits(msg_addr), - pcie->apb_csr_base + MSI_BASE_HI_OFFSET); - writel_relaxed(4096, pcie->apb_csr_base + MSI_SIZE_OFFSET); - writel_relaxed(1, pcie->apb_csr_base + MSI_ENABLE_OFFSET); -} - -static int mobiveil_host_init(struct mobiveil_pcie *pcie) -{ - u32 value, pab_ctrl, type = 0; - int err; - struct resource_entry *win, *tmp; - - err = mobiveil_bringup_link(pcie); - if (err) { - dev_info(&pcie->pdev->dev, "link bring-up failed\n"); - return err; - } - - /* - * program Bus Master Enable Bit in Command Register in PAB Config - * Space - */ - value = csr_readl(pcie, PCI_COMMAND); - csr_writel(pcie, value | PCI_COMMAND_IO | PCI_COMMAND_MEMORY | - PCI_COMMAND_MASTER, PCI_COMMAND); - - /* - * program PIO Enable Bit to 1 (and PEX PIO Enable to 1) in PAB_CTRL - * register - */ - pab_ctrl = csr_readl(pcie, PAB_CTRL); - csr_writel(pcie, pab_ctrl | (1 << AMBA_PIO_ENABLE_SHIFT) | - (1 << PEX_PIO_ENABLE_SHIFT), PAB_CTRL); - - csr_writel(pcie, (PAB_INTP_INTX_MASK | PAB_INTP_MSI_MASK), - PAB_INTP_AMBA_MISC_ENB); - - /* - * program PIO Enable Bit to 1 and Config Window Enable Bit to 1 in - * PAB_AXI_PIO_CTRL Register - */ - value = csr_readl(pcie, PAB_AXI_PIO_CTRL); - csr_writel(pcie, value | APIO_EN_MASK, PAB_AXI_PIO_CTRL); - - /* - * we'll program one outbound window for config reads and - * another default inbound window for all the upstream traffic - * rest of the outbound windows will be configured according to - * the "ranges" field defined in device tree - */ - - /* config outbound translation window */ - program_ob_windows(pcie, pcie->ob_wins_configured, - pcie->ob_io_res->start, 0, CFG_WINDOW_TYPE, - resource_size(pcie->ob_io_res)); - - /* memory inbound translation window */ - program_ib_windows(pcie, WIN_NUM_1, 0, MEM_WINDOW_TYPE, IB_WIN_SIZE); - - /* Get the I/O and memory ranges from DT */ - resource_list_for_each_entry_safe(win, tmp, &pcie->resources) { - type = 0; - if (resource_type(win->res) == IORESOURCE_MEM) - type = MEM_WINDOW_TYPE; - if (resource_type(win->res) == IORESOURCE_IO) - type = IO_WINDOW_TYPE; - if (type) { - /* configure outbound translation window */ - program_ob_windows(pcie, pcie->ob_wins_configured, - win->res->start, 0, type, - resource_size(win->res)); - } - } - - /* setup MSI hardware registers */ - mobiveil_pcie_enable_msi(pcie); - - return err; -} - -static void mobiveil_mask_intx_irq(struct irq_data *data) -{ - struct irq_desc *desc = irq_to_desc(data->irq); - struct mobiveil_pcie *pcie; - unsigned long flags; - u32 mask, shifted_val; - - pcie = irq_desc_get_chip_data(desc); - mask = 1 << ((data->hwirq + PAB_INTX_START) - 1); - raw_spin_lock_irqsave(&pcie->intx_mask_lock, flags); - shifted_val = csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); - csr_writel(pcie, (shifted_val & (~mask)), PAB_INTP_AMBA_MISC_ENB); - raw_spin_unlock_irqrestore(&pcie->intx_mask_lock, flags); -} - -static void mobiveil_unmask_intx_irq(struct irq_data *data) -{ - struct irq_desc *desc = irq_to_desc(data->irq); - struct mobiveil_pcie *pcie; - unsigned long flags; - u32 shifted_val, mask; - - pcie = irq_desc_get_chip_data(desc); - mask = 1 << ((data->hwirq + PAB_INTX_START) - 1); - raw_spin_lock_irqsave(&pcie->intx_mask_lock, flags); - shifted_val = csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); - csr_writel(pcie, (shifted_val | mask), PAB_INTP_AMBA_MISC_ENB); - raw_spin_unlock_irqrestore(&pcie->intx_mask_lock, flags); -} - -static struct irq_chip intx_irq_chip = { - .name = "mobiveil_pcie:intx", - .irq_enable = mobiveil_unmask_intx_irq, - .irq_disable = mobiveil_mask_intx_irq, - .irq_mask = mobiveil_mask_intx_irq, - .irq_unmask = mobiveil_unmask_intx_irq, -}; - -/* routine to setup the INTx related data */ -static int mobiveil_pcie_intx_map(struct irq_domain *domain, unsigned int irq, - irq_hw_number_t hwirq) -{ - irq_set_chip_and_handler(irq, &intx_irq_chip, handle_level_irq); - irq_set_chip_data(irq, domain->host_data); - return 0; -} - -/* INTx domain operations structure */ -static const struct irq_domain_ops intx_domain_ops = { - .map = mobiveil_pcie_intx_map, -}; - -static struct irq_chip mobiveil_msi_irq_chip = { - .name = "Mobiveil PCIe MSI", - .irq_mask = pci_msi_mask_irq, - .irq_unmask = pci_msi_unmask_irq, -}; - -static struct msi_domain_info mobiveil_msi_domain_info = { - .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX), - .chip = &mobiveil_msi_irq_chip, -}; - -static void mobiveil_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) -{ - struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data); - phys_addr_t addr = pcie->pcie_reg_base + (data->hwirq * sizeof(int)); - - msg->address_lo = lower_32_bits(addr); - msg->address_hi = upper_32_bits(addr); - msg->data = data->hwirq; - - dev_dbg(&pcie->pdev->dev, "msi#%d address_hi %#x address_lo %#x\n", - (int)data->hwirq, msg->address_hi, msg->address_lo); -} - -static int mobiveil_msi_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) -{ - return -EINVAL; -} - -static struct irq_chip mobiveil_msi_bottom_irq_chip = { - .name = "Mobiveil MSI", - .irq_compose_msi_msg = mobiveil_compose_msi_msg, - .irq_set_affinity = mobiveil_msi_set_affinity, -}; - -static int mobiveil_irq_msi_domain_alloc(struct irq_domain *domain, - unsigned int virq, unsigned int nr_irqs, void *args) -{ - struct mobiveil_pcie *pcie = domain->host_data; - struct mobiveil_msi *msi = &pcie->msi; - unsigned long bit; - - WARN_ON(nr_irqs != 1); - mutex_lock(&msi->lock); - - bit = find_first_zero_bit(msi->msi_irq_in_use, msi->num_of_vectors); - if (bit >= msi->num_of_vectors) { - mutex_unlock(&msi->lock); - return -ENOSPC; - } - - set_bit(bit, msi->msi_irq_in_use); - - mutex_unlock(&msi->lock); - - irq_domain_set_info(domain, virq, bit, &mobiveil_msi_bottom_irq_chip, - domain->host_data, handle_level_irq, - NULL, NULL); - return 0; -} - -static void mobiveil_irq_msi_domain_free(struct irq_domain *domain, - unsigned int virq, unsigned int nr_irqs) -{ - struct irq_data *d = irq_domain_get_irq_data(domain, virq); - struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(d); - struct mobiveil_msi *msi = &pcie->msi; - - mutex_lock(&msi->lock); - - if (!test_bit(d->hwirq, msi->msi_irq_in_use)) { - dev_err(&pcie->pdev->dev, "trying to free unused MSI#%lu\n", - d->hwirq); - } else { - __clear_bit(d->hwirq, msi->msi_irq_in_use); - } - - mutex_unlock(&msi->lock); -} -static const struct irq_domain_ops msi_domain_ops = { - .alloc = mobiveil_irq_msi_domain_alloc, - .free = mobiveil_irq_msi_domain_free, -}; - -static int mobiveil_allocate_msi_domains(struct mobiveil_pcie *pcie) -{ - struct device *dev = &pcie->pdev->dev; - struct fwnode_handle *fwnode = of_node_to_fwnode(dev->of_node); - struct mobiveil_msi *msi = &pcie->msi; - - mutex_init(&pcie->msi.lock); - msi->dev_domain = irq_domain_add_linear(NULL, msi->num_of_vectors, - &msi_domain_ops, pcie); - if (!msi->dev_domain) { - dev_err(dev, "failed to create IRQ domain\n"); - return -ENOMEM; - } - - msi->msi_domain = pci_msi_create_irq_domain(fwnode, - &mobiveil_msi_domain_info, msi->dev_domain); - if (!msi->msi_domain) { - dev_err(dev, "failed to create MSI domain\n"); - irq_domain_remove(msi->dev_domain); - return -ENOMEM; - } - return 0; -} - -static int mobiveil_pcie_init_irq_domain(struct mobiveil_pcie *pcie) -{ - struct device *dev = &pcie->pdev->dev; - struct device_node *node = dev->of_node; - int ret; - - /* setup INTx */ - pcie->intx_domain = irq_domain_add_linear(node, - PCI_NUM_INTX, &intx_domain_ops, pcie); - - if (!pcie->intx_domain) { - dev_err(dev, "Failed to get a INTx IRQ domain\n"); - return -ENODEV; - } - - raw_spin_lock_init(&pcie->intx_mask_lock); - - /* setup MSI */ - ret = mobiveil_allocate_msi_domains(pcie); - if (ret) - return ret; - - return 0; -} - -static int mobiveil_pcie_probe(struct platform_device *pdev) -{ - struct mobiveil_pcie *pcie; - struct pci_bus *bus; - struct pci_bus *child; - struct pci_host_bridge *bridge; - struct device *dev = &pdev->dev; - resource_size_t iobase; - int ret; - - /* allocate the PCIe port */ - bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); - if (!bridge) - return -ENODEV; - - pcie = pci_host_bridge_priv(bridge); - if (!pcie) - return -ENOMEM; - - pcie->pdev = pdev; - - ret = mobiveil_pcie_parse_dt(pcie); - if (ret) { - dev_err(dev, "Parsing DT failed, ret: %x\n", ret); - return ret; - } - - INIT_LIST_HEAD(&pcie->resources); - - /* parse the host bridge base addresses from the device tree file */ - ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, - &pcie->resources, &iobase); - if (ret) { - dev_err(dev, "Getting bridge resources failed\n"); - return -ENOMEM; - } - - /* - * configure all inbound and outbound windows and prepare the RC for - * config access - */ - ret = mobiveil_host_init(pcie); - if (ret) { - dev_err(dev, "Failed to initialize host\n"); - goto error; - } - - /* fixup for PCIe class register */ - csr_writel(pcie, 0x060402ab, PAB_INTP_AXI_PIO_CLASS); - - /* initialize the IRQ domains */ - ret = mobiveil_pcie_init_irq_domain(pcie); - if (ret) { - dev_err(dev, "Failed creating IRQ Domain\n"); - goto error; - } - - ret = devm_request_pci_bus_resources(dev, &pcie->resources); - if (ret) - goto error; - - /* Initialize bridge */ - list_splice_init(&pcie->resources, &bridge->windows); - bridge->dev.parent = dev; - bridge->sysdata = pcie; - bridge->busnr = pcie->root_bus_nr; - bridge->ops = &mobiveil_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - - /* setup the kernel resources for the newly added PCIe root bus */ - ret = pci_scan_root_bus_bridge(bridge); - if (ret) - goto error; - - bus = bridge->bus; - - pci_assign_unassigned_bus_resources(bus); - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); - pci_bus_add_devices(bus); - - return 0; -error: - pci_free_resource_list(&pcie->resources); - return ret; -} - -static const struct of_device_id mobiveil_pcie_of_match[] = { - {.compatible = "mbvl,gpex40-pcie",}, - {}, -}; - -MODULE_DEVICE_TABLE(of, mobiveil_pcie_of_match); - -static struct platform_driver mobiveil_pcie_driver = { - .probe = mobiveil_pcie_probe, - .driver = { - .name = "mobiveil-pcie", - .of_match_table = mobiveil_pcie_of_match, - .suppress_bind_attrs = true, - }, -}; - -builtin_platform_driver(mobiveil_pcie_driver); - -MODULE_LICENSE("GPL v2"); -MODULE_DESCRIPTION("Mobiveil PCIe host controller driver"); -MODULE_AUTHOR("Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>"); diff --git a/drivers/pci/controller/pcie-mt7621.c b/drivers/pci/controller/pcie-mt7621.c new file mode 100644 index 000000000000..01ead2f92e87 --- /dev/null +++ b/drivers/pci/controller/pcie-mt7621.c @@ -0,0 +1,548 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * BRIEF MODULE DESCRIPTION + * PCI init for Ralink RT2880 solution + * + * Copyright 2007 Ralink Inc. (bruce_chang@ralinktech.com.tw) + * + * May 2007 Bruce Chang + * Initial Release + * + * May 2009 Bruce Chang + * support RT2880/RT3883 PCIe + * + * May 2011 Bruce Chang + * support RT6855/MT7620 PCIe + */ + +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> +#include <linux/sys_soc.h> + +#include "../pci.h" + +/* MediaTek-specific configuration registers */ +#define PCIE_FTS_NUM 0x70c +#define PCIE_FTS_NUM_MASK GENMASK(15, 8) +#define PCIE_FTS_NUM_L0(x) (((x) & 0xff) << 8) + +/* Host-PCI bridge registers */ +#define RALINK_PCI_PCICFG_ADDR 0x0000 +#define RALINK_PCI_PCIMSK_ADDR 0x000c +#define RALINK_PCI_CONFIG_ADDR 0x0020 +#define RALINK_PCI_CONFIG_DATA 0x0024 +#define RALINK_PCI_MEMBASE 0x0028 +#define RALINK_PCI_IOBASE 0x002c + +/* PCIe RC control registers */ +#define RALINK_PCI_ID 0x0030 +#define RALINK_PCI_CLASS 0x0034 +#define RALINK_PCI_SUBID 0x0038 +#define RALINK_PCI_STATUS 0x0050 + +/* Some definition values */ +#define PCIE_REVISION_ID BIT(0) +#define PCIE_CLASS_CODE (0x60400 << 8) +#define PCIE_BAR_MAP_MAX GENMASK(30, 16) +#define PCIE_BAR_ENABLE BIT(0) +#define PCIE_PORT_INT_EN(x) BIT(20 + (x)) +#define PCIE_PORT_LINKUP BIT(0) +#define PCIE_PORT_CNT 3 + +#define INIT_PORTS_DELAY_MS 100 +#define PERST_DELAY_MS 100 + +/** + * struct mt7621_pcie_port - PCIe port information + * @base: I/O mapped register base + * @list: port list + * @pcie: pointer to PCIe host info + * @clk: pointer to the port clock gate + * @phy: pointer to PHY control block + * @pcie_rst: pointer to port reset control + * @gpio_rst: gpio reset + * @slot: port slot + * @enabled: indicates if port is enabled + */ +struct mt7621_pcie_port { + void __iomem *base; + struct list_head list; + struct mt7621_pcie *pcie; + struct clk *clk; + struct phy *phy; + struct reset_control *pcie_rst; + struct gpio_desc *gpio_rst; + u32 slot; + bool enabled; +}; + +/** + * struct mt7621_pcie - PCIe host information + * @base: IO Mapped Register Base + * @dev: Pointer to PCIe device + * @ports: pointer to PCIe port information + * @resets_inverted: depends on chip revision + * reset lines are inverted. + */ +struct mt7621_pcie { + struct device *dev; + void __iomem *base; + struct list_head ports; + bool resets_inverted; +}; + +static inline u32 pcie_read(struct mt7621_pcie *pcie, u32 reg) +{ + return readl_relaxed(pcie->base + reg); +} + +static inline void pcie_write(struct mt7621_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->base + reg); +} + +static inline u32 pcie_port_read(struct mt7621_pcie_port *port, u32 reg) +{ + return readl_relaxed(port->base + reg); +} + +static inline void pcie_port_write(struct mt7621_pcie_port *port, + u32 val, u32 reg) +{ + writel_relaxed(val, port->base + reg); +} + +static void __iomem *mt7621_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct mt7621_pcie *pcie = bus->sysdata; + u32 address = PCI_CONF1_EXT_ADDRESS(bus->number, PCI_SLOT(devfn), + PCI_FUNC(devfn), where); + + writel_relaxed(address, pcie->base + RALINK_PCI_CONFIG_ADDR); + + return pcie->base + RALINK_PCI_CONFIG_DATA + (where & 3); +} + +static struct pci_ops mt7621_pcie_ops = { + .map_bus = mt7621_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static u32 read_config(struct mt7621_pcie *pcie, unsigned int dev, u32 reg) +{ + u32 address = PCI_CONF1_EXT_ADDRESS(0, dev, 0, reg); + + pcie_write(pcie, address, RALINK_PCI_CONFIG_ADDR); + return pcie_read(pcie, RALINK_PCI_CONFIG_DATA); +} + +static void write_config(struct mt7621_pcie *pcie, unsigned int dev, + u32 reg, u32 val) +{ + u32 address = PCI_CONF1_EXT_ADDRESS(0, dev, 0, reg); + + pcie_write(pcie, address, RALINK_PCI_CONFIG_ADDR); + pcie_write(pcie, val, RALINK_PCI_CONFIG_DATA); +} + +static inline void mt7621_rst_gpio_pcie_assert(struct mt7621_pcie_port *port) +{ + if (port->gpio_rst) + gpiod_set_value(port->gpio_rst, 1); +} + +static inline void mt7621_rst_gpio_pcie_deassert(struct mt7621_pcie_port *port) +{ + if (port->gpio_rst) + gpiod_set_value(port->gpio_rst, 0); +} + +static inline bool mt7621_pcie_port_is_linkup(struct mt7621_pcie_port *port) +{ + return (pcie_port_read(port, RALINK_PCI_STATUS) & PCIE_PORT_LINKUP) != 0; +} + +static inline void mt7621_control_assert(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + + if (pcie->resets_inverted) + reset_control_assert(port->pcie_rst); + else + reset_control_deassert(port->pcie_rst); +} + +static inline void mt7621_control_deassert(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + + if (pcie->resets_inverted) + reset_control_deassert(port->pcie_rst); + else + reset_control_assert(port->pcie_rst); +} + +static int mt7621_pcie_parse_port(struct mt7621_pcie *pcie, + struct device_node *node, + int slot) +{ + struct mt7621_pcie_port *port; + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + char name[11]; + int err; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->base = devm_platform_ioremap_resource(pdev, slot + 1); + if (IS_ERR(port->base)) + return PTR_ERR(port->base); + + port->clk = devm_get_clk_from_child(dev, node, NULL); + if (IS_ERR(port->clk)) { + dev_err(dev, "failed to get pcie%d clock\n", slot); + return PTR_ERR(port->clk); + } + + port->pcie_rst = of_reset_control_get_exclusive(node, NULL); + if (PTR_ERR(port->pcie_rst) == -EPROBE_DEFER) { + dev_err(dev, "failed to get pcie%d reset control\n", slot); + return PTR_ERR(port->pcie_rst); + } + + snprintf(name, sizeof(name), "pcie-phy%d", slot); + port->phy = devm_of_phy_get(dev, node, name); + if (IS_ERR(port->phy)) { + dev_err(dev, "failed to get pcie-phy%d\n", slot); + err = PTR_ERR(port->phy); + goto remove_reset; + } + + port->gpio_rst = devm_gpiod_get_index_optional(dev, "reset", slot, + GPIOD_OUT_LOW); + if (IS_ERR(port->gpio_rst)) { + dev_err(dev, "failed to get GPIO for PCIe%d\n", slot); + err = PTR_ERR(port->gpio_rst); + goto remove_reset; + } + + port->slot = slot; + port->pcie = pcie; + + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + return 0; + +remove_reset: + reset_control_put(port->pcie_rst); + return err; +} + +static int mt7621_pcie_parse_dt(struct mt7621_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *node = dev->of_node; + int err; + + pcie->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + for_each_available_child_of_node_scoped(node, child) { + int slot; + + err = of_pci_get_devfn(child); + if (err < 0) + return dev_err_probe(dev, err, "failed to parse devfn\n"); + + slot = PCI_SLOT(err); + + err = mt7621_pcie_parse_port(pcie, child, slot); + if (err) + return err; + } + + return 0; +} + +static int mt7621_pcie_init_port(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + u32 slot = port->slot; + int err; + + err = phy_init(port->phy); + if (err) { + dev_err(dev, "failed to initialize port%d phy\n", slot); + return err; + } + + err = phy_power_on(port->phy); + if (err) { + dev_err(dev, "failed to power on port%d phy\n", slot); + phy_exit(port->phy); + return err; + } + + port->enabled = true; + + return 0; +} + +static void mt7621_pcie_reset_assert(struct mt7621_pcie *pcie) +{ + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) { + /* PCIe RC reset assert */ + mt7621_control_assert(port); + + /* PCIe EP reset assert */ + mt7621_rst_gpio_pcie_assert(port); + } + + msleep(PERST_DELAY_MS); +} + +static void mt7621_pcie_reset_rc_deassert(struct mt7621_pcie *pcie) +{ + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) + mt7621_control_deassert(port); +} + +static void mt7621_pcie_reset_ep_deassert(struct mt7621_pcie *pcie) +{ + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) + mt7621_rst_gpio_pcie_deassert(port); + + msleep(PERST_DELAY_MS); +} + +static int mt7621_pcie_init_ports(struct mt7621_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct mt7621_pcie_port *port, *tmp; + u8 num_disabled = 0; + int err; + + mt7621_pcie_reset_assert(pcie); + mt7621_pcie_reset_rc_deassert(pcie); + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + u32 slot = port->slot; + + if (slot == 1) { + port->enabled = true; + continue; + } + + err = mt7621_pcie_init_port(port); + if (err) { + dev_err(dev, "initializing port %d failed\n", slot); + list_del(&port->list); + } + } + + msleep(INIT_PORTS_DELAY_MS); + mt7621_pcie_reset_ep_deassert(pcie); + + tmp = NULL; + list_for_each_entry(port, &pcie->ports, list) { + u32 slot = port->slot; + + if (!mt7621_pcie_port_is_linkup(port)) { + dev_info(dev, "pcie%d no card, disable it (RST & CLK)\n", + slot); + mt7621_control_assert(port); + port->enabled = false; + num_disabled++; + + if (slot == 0) { + tmp = port; + continue; + } + + if (slot == 1 && tmp && !tmp->enabled) + phy_power_off(tmp->phy); + } + } + + return (num_disabled != PCIE_PORT_CNT) ? 0 : -ENODEV; +} + +static void mt7621_pcie_enable_port(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + u32 slot = port->slot; + u32 val; + + /* enable pcie interrupt */ + val = pcie_read(pcie, RALINK_PCI_PCIMSK_ADDR); + val |= PCIE_PORT_INT_EN(slot); + pcie_write(pcie, val, RALINK_PCI_PCIMSK_ADDR); + + /* map 2G DDR region */ + pcie_port_write(port, PCIE_BAR_MAP_MAX | PCIE_BAR_ENABLE, + PCI_BASE_ADDRESS_0); + + /* configure class code and revision ID */ + pcie_port_write(port, PCIE_CLASS_CODE | PCIE_REVISION_ID, + RALINK_PCI_CLASS); + + /* configure RC FTS number to 250 when it leaves L0s */ + val = read_config(pcie, slot, PCIE_FTS_NUM); + val &= ~PCIE_FTS_NUM_MASK; + val |= PCIE_FTS_NUM_L0(0x50); + write_config(pcie, slot, PCIE_FTS_NUM, val); +} + +static int mt7621_pcie_enable_ports(struct pci_host_bridge *host) +{ + struct mt7621_pcie *pcie = pci_host_bridge_priv(host); + struct device *dev = pcie->dev; + struct mt7621_pcie_port *port; + struct resource_entry *entry; + int err; + + entry = resource_list_first_type(&host->windows, IORESOURCE_IO); + if (!entry) { + dev_err(dev, "cannot get io resource\n"); + return -EINVAL; + } + + /* Setup MEMWIN and IOWIN */ + pcie_write(pcie, 0xffffffff, RALINK_PCI_MEMBASE); + pcie_write(pcie, entry->res->start - entry->offset, RALINK_PCI_IOBASE); + + list_for_each_entry(port, &pcie->ports, list) { + if (port->enabled) { + err = clk_prepare_enable(port->clk); + if (err) { + dev_err(dev, "enabling clk pcie%d\n", + port->slot); + return err; + } + + mt7621_pcie_enable_port(port); + dev_info(dev, "PCIE%d enabled\n", port->slot); + } + } + + return 0; +} + +static int mt7621_pcie_register_host(struct pci_host_bridge *host) +{ + struct mt7621_pcie *pcie = pci_host_bridge_priv(host); + + host->ops = &mt7621_pcie_ops; + host->sysdata = pcie; + return pci_host_probe(host); +} + +static const struct soc_device_attribute mt7621_pcie_quirks_match[] = { + { .soc_id = "mt7621", .revision = "E2" }, + { /* sentinel */ } +}; + +static int mt7621_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct soc_device_attribute *attr; + struct mt7621_pcie_port *port; + struct mt7621_pcie *pcie; + struct pci_host_bridge *bridge; + int err; + + if (!dev->of_node) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->dev = dev; + platform_set_drvdata(pdev, pcie); + INIT_LIST_HEAD(&pcie->ports); + + attr = soc_device_match(mt7621_pcie_quirks_match); + if (attr) + pcie->resets_inverted = true; + + err = mt7621_pcie_parse_dt(pcie); + if (err) { + dev_err(dev, "parsing DT failed\n"); + return err; + } + + err = mt7621_pcie_init_ports(pcie); + if (err) { + dev_err(dev, "nothing connected in virtual bridges\n"); + return 0; + } + + err = mt7621_pcie_enable_ports(bridge); + if (err) { + dev_err(dev, "error enabling pcie ports\n"); + goto remove_resets; + } + + return mt7621_pcie_register_host(bridge); + +remove_resets: + list_for_each_entry(port, &pcie->ports, list) + reset_control_put(port->pcie_rst); + + return err; +} + +static void mt7621_pcie_remove(struct platform_device *pdev) +{ + struct mt7621_pcie *pcie = platform_get_drvdata(pdev); + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) + reset_control_put(port->pcie_rst); +} + +static const struct of_device_id mt7621_pcie_ids[] = { + { .compatible = "mediatek,mt7621-pci" }, + {}, +}; +MODULE_DEVICE_TABLE(of, mt7621_pcie_ids); + +static struct platform_driver mt7621_pcie_driver = { + .probe = mt7621_pcie_probe, + .remove = mt7621_pcie_remove, + .driver = { + .name = "mt7621-pci", + .of_match_table = mt7621_pcie_ids, + }, +}; +builtin_platform_driver(mt7621_pcie_driver); + +MODULE_DESCRIPTION("MediaTek MT7621 PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c new file mode 100644 index 000000000000..657875ef4657 --- /dev/null +++ b/drivers/pci/controller/pcie-rcar-ep.c @@ -0,0 +1,564 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe endpoint driver for Renesas R-Car SoCs + * Copyright (c) 2020 Renesas Electronics Europe GmbH + * + * Author: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> + */ + +#include <linux/delay.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/pci-epc.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> + +#include "pcie-rcar.h" + +#define RCAR_EPC_MAX_FUNCTIONS 1 + +/* Structure representing the PCIe interface */ +struct rcar_pcie_endpoint { + struct rcar_pcie pcie; + phys_addr_t *ob_mapped_addr; + struct pci_epc_mem_window *ob_window; + u8 max_functions; + unsigned int bar_to_atu[MAX_NR_INBOUND_MAPS]; + unsigned long *ib_window_map; + u32 num_ib_windows; + u32 num_ob_windows; +}; + +static void rcar_pcie_ep_hw_init(struct rcar_pcie *pcie) +{ + u32 val; + + rcar_pci_write_reg(pcie, 0, PCIETCTLR); + + /* Set endpoint mode */ + rcar_pci_write_reg(pcie, 0, PCIEMSR); + + /* Initialize default capabilities. */ + rcar_rmw32(pcie, REXPCAP(0), 0xff, PCI_CAP_ID_EXP); + rcar_rmw32(pcie, REXPCAP(PCI_EXP_FLAGS), + PCI_EXP_FLAGS_TYPE, PCI_EXP_TYPE_ENDPOINT << 4); + rcar_rmw32(pcie, RCONF(PCI_HEADER_TYPE), PCI_HEADER_TYPE_MASK, + PCI_HEADER_TYPE_NORMAL); + + /* Write out the physical slot number = 0 */ + rcar_rmw32(pcie, REXPCAP(PCI_EXP_SLTCAP), PCI_EXP_SLTCAP_PSN, 0); + + val = rcar_pci_read_reg(pcie, EXPCAP(1)); + /* device supports fixed 128 bytes MPSS */ + val &= ~GENMASK(2, 0); + rcar_pci_write_reg(pcie, val, EXPCAP(1)); + + val = rcar_pci_read_reg(pcie, EXPCAP(2)); + /* read requests size 128 bytes */ + val &= ~GENMASK(14, 12); + /* payload size 128 bytes */ + val &= ~GENMASK(7, 5); + rcar_pci_write_reg(pcie, val, EXPCAP(2)); + + /* Set target link speed to 5.0 GT/s */ + rcar_rmw32(pcie, EXPCAP(12), PCI_EXP_LNKSTA_CLS, + PCI_EXP_LNKSTA_CLS_5_0GB); + + /* Set the completion timer timeout to the maximum 50ms. */ + rcar_rmw32(pcie, TLCTLR + 1, 0x3f, 50); + + /* Terminate list of capabilities (Next Capability Offset=0) */ + rcar_rmw32(pcie, RVCCAP(0), 0xfff00000, 0); + + /* flush modifications */ + wmb(); +} + +static int rcar_pcie_ep_get_window(struct rcar_pcie_endpoint *ep, + phys_addr_t addr) +{ + int i; + + for (i = 0; i < ep->num_ob_windows; i++) + if (ep->ob_window[i].phys_base == addr) + return i; + + return -EINVAL; +} + +static int rcar_pcie_parse_outbound_ranges(struct rcar_pcie_endpoint *ep, + struct platform_device *pdev) +{ + struct rcar_pcie *pcie = &ep->pcie; + char outbound_name[10]; + struct resource *res; + unsigned int i = 0; + + ep->num_ob_windows = 0; + for (i = 0; i < RCAR_PCI_MAX_RESOURCES; i++) { + sprintf(outbound_name, "memory%u", i); + res = platform_get_resource_byname(pdev, + IORESOURCE_MEM, + outbound_name); + if (!res) { + dev_err(pcie->dev, "missing outbound window %u\n", i); + return -EINVAL; + } + if (!devm_request_mem_region(&pdev->dev, res->start, + resource_size(res), + res->name)) { + dev_err(pcie->dev, "Cannot request memory region %s.\n", + outbound_name); + return -EIO; + } + + ep->ob_window[i].phys_base = res->start; + ep->ob_window[i].size = resource_size(res); + /* controller doesn't support multiple allocation + * from same window, so set page_size to window size + */ + ep->ob_window[i].page_size = resource_size(res); + } + ep->num_ob_windows = i; + + return 0; +} + +static int rcar_pcie_ep_get_pdata(struct rcar_pcie_endpoint *ep, + struct platform_device *pdev) +{ + struct rcar_pcie *pcie = &ep->pcie; + struct pci_epc_mem_window *window; + struct device *dev = pcie->dev; + struct resource res; + int err; + + err = of_address_to_resource(dev->of_node, 0, &res); + if (err) + return err; + pcie->base = devm_ioremap_resource(dev, &res); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + ep->ob_window = devm_kcalloc(dev, RCAR_PCI_MAX_RESOURCES, + sizeof(*window), GFP_KERNEL); + if (!ep->ob_window) + return -ENOMEM; + + rcar_pcie_parse_outbound_ranges(ep, pdev); + + err = of_property_read_u8(dev->of_node, "max-functions", + &ep->max_functions); + if (err < 0 || ep->max_functions > RCAR_EPC_MAX_FUNCTIONS) + ep->max_functions = RCAR_EPC_MAX_FUNCTIONS; + + return 0; +} + +static int rcar_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_header *hdr) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct rcar_pcie *pcie = &ep->pcie; + u32 val; + + if (!fn) + val = hdr->vendorid; + else + val = rcar_pci_read_reg(pcie, IDSETR0); + val |= hdr->deviceid << 16; + rcar_pci_write_reg(pcie, val, IDSETR0); + + val = hdr->revid; + val |= hdr->progif_code << 8; + val |= hdr->subclass_code << 16; + val |= hdr->baseclass_code << 24; + rcar_pci_write_reg(pcie, val, IDSETR1); + + if (!fn) + val = hdr->subsys_vendor_id; + else + val = rcar_pci_read_reg(pcie, SUBIDSETR); + val |= hdr->subsys_id << 16; + rcar_pci_write_reg(pcie, val, SUBIDSETR); + + if (hdr->interrupt_pin > PCI_INTERRUPT_INTA) + return -EINVAL; + val = rcar_pci_read_reg(pcie, PCICONF(15)); + val |= (hdr->interrupt_pin << 8); + rcar_pci_write_reg(pcie, val, PCICONF(15)); + + return 0; +} + +static int rcar_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + struct pci_epf_bar *epf_bar) +{ + int flags = epf_bar->flags | LAR_ENABLE | LAM_64BIT; + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + u64 size = 1ULL << fls64(epf_bar->size - 1); + dma_addr_t cpu_addr = epf_bar->phys_addr; + enum pci_barno bar = epf_bar->barno; + struct rcar_pcie *pcie = &ep->pcie; + u32 mask; + int idx; + int err; + + idx = find_first_zero_bit(ep->ib_window_map, ep->num_ib_windows); + if (idx >= ep->num_ib_windows) { + dev_err(pcie->dev, "no free inbound window\n"); + return -EINVAL; + } + + if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) + flags |= IO_SPACE; + + ep->bar_to_atu[bar] = idx; + /* use 64-bit BARs */ + set_bit(idx, ep->ib_window_map); + set_bit(idx + 1, ep->ib_window_map); + + if (cpu_addr > 0) { + unsigned long nr_zeros = __ffs64(cpu_addr); + u64 alignment = 1ULL << nr_zeros; + + size = min(size, alignment); + } + + size = min(size, 1ULL << 32); + + mask = roundup_pow_of_two(size) - 1; + mask &= ~0xf; + + rcar_pcie_set_inbound(pcie, cpu_addr, + 0x0, mask | flags, idx, false); + + err = rcar_pcie_wait_for_phyrdy(pcie); + if (err) { + dev_err(pcie->dev, "phy not ready\n"); + return -EINVAL; + } + + return 0; +} + +static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + enum pci_barno bar = epf_bar->barno; + u32 atu_index = ep->bar_to_atu[bar]; + + rcar_pcie_set_inbound(&ep->pcie, 0x0, 0x0, 0x0, bar, false); + + clear_bit(atu_index, ep->ib_window_map); + clear_bit(atu_index + 1, ep->ib_window_map); +} + +static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 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 |= mmc << MSICAP0_MMESCAP_OFFSET; + rcar_pci_write_reg(pcie, flags, MSICAP(fn)); + + return 0; +} + +static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct rcar_pcie *pcie = &ep->pcie; + u32 flags; + + flags = rcar_pci_read_reg(pcie, MSICAP(fn)); + if (!(flags & MSICAP0_MSIE)) + return -EINVAL; + + return 1 << ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET); +} + +static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u64 pci_addr, size_t size) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct rcar_pcie *pcie = &ep->pcie; + struct resource_entry win; + struct resource res; + int window; + int err; + + /* check if we have a link. */ + err = rcar_pcie_wait_for_dl(pcie); + if (err) { + dev_err(pcie->dev, "link not up\n"); + return err; + } + + window = rcar_pcie_ep_get_window(ep, addr); + if (window < 0) { + dev_err(pcie->dev, "failed to get corresponding window\n"); + return -EINVAL; + } + + memset(&win, 0x0, sizeof(win)); + memset(&res, 0x0, sizeof(res)); + res.start = pci_addr; + res.end = pci_addr + size - 1; + res.flags = IORESOURCE_MEM; + win.res = &res; + + rcar_pcie_set_outbound(pcie, window, &win); + + ep->ob_mapped_addr[window] = addr; + + return 0; +} + +static void rcar_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct resource_entry win; + struct resource res; + int idx; + + for (idx = 0; idx < ep->num_ob_windows; idx++) + if (ep->ob_mapped_addr[idx] == addr) + break; + + if (idx >= ep->num_ob_windows) + return; + + memset(&win, 0x0, sizeof(win)); + memset(&res, 0x0, sizeof(res)); + win.res = &res; + rcar_pcie_set_outbound(&ep->pcie, idx, &win); + + ep->ob_mapped_addr[idx] = 0; +} + +static int rcar_pcie_ep_assert_intx(struct rcar_pcie_endpoint *ep, + u8 fn, u8 intx) +{ + struct rcar_pcie *pcie = &ep->pcie; + u32 val; + + val = rcar_pci_read_reg(pcie, PCIEMSITXR); + if ((val & PCI_MSI_FLAGS_ENABLE)) { + dev_err(pcie->dev, "MSI is enabled, cannot assert INTx\n"); + return -EINVAL; + } + + val = rcar_pci_read_reg(pcie, PCICONF(1)); + if ((val & INTDIS)) { + dev_err(pcie->dev, "INTx message transmission is disabled\n"); + return -EINVAL; + } + + val = rcar_pci_read_reg(pcie, PCIEINTXR); + if ((val & ASTINTX)) { + dev_err(pcie->dev, "INTx is already asserted\n"); + return -EINVAL; + } + + val |= ASTINTX; + rcar_pci_write_reg(pcie, val, PCIEINTXR); + usleep_range(1000, 1001); + val = rcar_pci_read_reg(pcie, PCIEINTXR); + val &= ~ASTINTX; + rcar_pci_write_reg(pcie, val, PCIEINTXR); + + return 0; +} + +static int rcar_pcie_ep_assert_msi(struct rcar_pcie *pcie, + u8 fn, u8 interrupt_num) +{ + u16 msi_count; + u32 val; + + /* Check MSI enable bit */ + val = rcar_pci_read_reg(pcie, MSICAP(fn)); + if (!(val & MSICAP0_MSIE)) + return -EINVAL; + + /* Get MSI numbers from MME */ + msi_count = ((val & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET); + msi_count = 1 << msi_count; + + if (!interrupt_num || interrupt_num > msi_count) + return -EINVAL; + + val = rcar_pci_read_reg(pcie, PCIEMSITXR); + rcar_pci_write_reg(pcie, val | (interrupt_num - 1), PCIEMSITXR); + + return 0; +} + +static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, + unsigned int type, u16 interrupt_num) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + + switch (type) { + case PCI_IRQ_INTX: + return rcar_pcie_ep_assert_intx(ep, fn, 0); + + case PCI_IRQ_MSI: + return rcar_pcie_ep_assert_msi(&ep->pcie, fn, interrupt_num); + + default: + return -EINVAL; + } +} + +static int rcar_pcie_ep_start(struct pci_epc *epc) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + + rcar_pci_write_reg(&ep->pcie, MACCTLR_INIT_VAL, MACCTLR); + rcar_pci_write_reg(&ep->pcie, CFINIT, PCIETCTLR); + + return 0; +} + +static void rcar_pcie_ep_stop(struct pci_epc *epc) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + + rcar_pci_write_reg(&ep->pcie, 0, PCIETCTLR); +} + +static const struct pci_epc_features rcar_pcie_epc_features = { + .msi_capable = true, + /* use 64-bit BARs so mark BAR[1,3,5] as reserved */ + .bar[BAR_0] = { .type = BAR_FIXED, .fixed_size = 128, + .only_64bit = true, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .type = BAR_FIXED, .fixed_size = 256, + .only_64bit = true, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256, + .only_64bit = true, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, +}; + +static const struct pci_epc_features* +rcar_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + return &rcar_pcie_epc_features; +} + +static const struct pci_epc_ops rcar_pcie_epc_ops = { + .write_header = rcar_pcie_ep_write_header, + .set_bar = rcar_pcie_ep_set_bar, + .clear_bar = rcar_pcie_ep_clear_bar, + .set_msi = rcar_pcie_ep_set_msi, + .get_msi = rcar_pcie_ep_get_msi, + .map_addr = rcar_pcie_ep_map_addr, + .unmap_addr = rcar_pcie_ep_unmap_addr, + .raise_irq = rcar_pcie_ep_raise_irq, + .start = rcar_pcie_ep_start, + .stop = rcar_pcie_ep_stop, + .get_features = rcar_pcie_ep_get_features, +}; + +static const struct of_device_id rcar_pcie_ep_of_match[] = { + { .compatible = "renesas,r8a774c0-pcie-ep", }, + { .compatible = "renesas,rcar-gen3-pcie-ep" }, + { }, +}; + +static int rcar_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rcar_pcie_endpoint *ep; + struct rcar_pcie *pcie; + struct pci_epc *epc; + int err; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + pcie = &ep->pcie; + pcie->dev = dev; + + pm_runtime_enable(dev); + err = pm_runtime_resume_and_get(dev); + if (err < 0) { + dev_err(dev, "pm_runtime_resume_and_get failed\n"); + goto err_pm_disable; + } + + err = rcar_pcie_ep_get_pdata(ep, pdev); + if (err < 0) { + dev_err(dev, "failed to request resources: %d\n", err); + goto err_pm_put; + } + + ep->num_ib_windows = MAX_NR_INBOUND_MAPS; + ep->ib_window_map = + devm_kcalloc(dev, BITS_TO_LONGS(ep->num_ib_windows), + sizeof(long), GFP_KERNEL); + if (!ep->ib_window_map) { + err = -ENOMEM; + dev_err(dev, "failed to allocate memory for inbound map\n"); + goto err_pm_put; + } + + ep->ob_mapped_addr = devm_kcalloc(dev, ep->num_ob_windows, + sizeof(*ep->ob_mapped_addr), + GFP_KERNEL); + if (!ep->ob_mapped_addr) { + err = -ENOMEM; + dev_err(dev, "failed to allocate memory for outbound memory pointers\n"); + goto err_pm_put; + } + + epc = devm_pci_epc_create(dev, &rcar_pcie_epc_ops); + if (IS_ERR(epc)) { + dev_err(dev, "failed to create epc device\n"); + err = PTR_ERR(epc); + goto err_pm_put; + } + + epc->max_functions = ep->max_functions; + epc_set_drvdata(epc, ep); + + rcar_pcie_ep_hw_init(pcie); + + err = pci_epc_multi_mem_init(epc, ep->ob_window, ep->num_ob_windows); + if (err < 0) { + dev_err(dev, "failed to initialize the epc memory space\n"); + goto err_pm_put; + } + + pci_epc_init_notify(epc); + + return 0; + +err_pm_put: + pm_runtime_put(dev); + +err_pm_disable: + pm_runtime_disable(dev); + + return err; +} + +static struct platform_driver rcar_pcie_ep_driver = { + .driver = { + .name = "rcar-pcie-ep", + .of_match_table = rcar_pcie_ep_of_match, + .suppress_bind_attrs = true, + }, + .probe = rcar_pcie_ep_probe, +}; +builtin_platform_driver(rcar_pcie_ep_driver); diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c new file mode 100644 index 000000000000..213028052aa5 --- /dev/null +++ b/drivers/pci/controller/pcie-rcar-host.c @@ -0,0 +1,1141 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe driver for Renesas R-Car SoCs + * Copyright (C) 2014-2020 Renesas Electronics Europe Ltd + * + * Based on: + * arch/sh/drivers/pci/pcie-sh7786.c + * arch/sh/drivers/pci/ops-sh7786.c + * Copyright (C) 2009 - 2011 Paul Mundt + * + * Author: Phil Edworthy <phil.edworthy@renesas.com> + */ + +#include <linux/bitops.h> +#include <linux/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> +#include <linux/iopoll.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regulator/consumer.h> + +#include "pcie-rcar.h" + +struct rcar_msi { + DECLARE_BITMAP(used, INT_PCI_MSI_NR); + struct irq_domain *domain; + struct mutex map_lock; + raw_spinlock_t mask_lock; + int irq1; + int irq2; +}; + +/* Structure representing the PCIe interface */ +struct rcar_pcie_host { + struct rcar_pcie pcie; + struct phy *phy; + struct clk *bus_clk; + struct rcar_msi msi; + int (*phy_init_fn)(struct rcar_pcie_host *host); +}; + +static int rcar_pcie_wakeup(struct device *pcie_dev, void __iomem *pcie_base) +{ + u32 pmsr, val; + int ret = 0; + + if (!pcie_base || pm_runtime_suspended(pcie_dev)) + return -EINVAL; + + pmsr = readl(pcie_base + PMSR); + + /* + * Test if the PCIe controller received PM_ENTER_L1 DLLP and + * the PCIe controller is not in L1 link state. If true, apply + * fix, which will put the controller into L1 link state, from + * which it can return to L0s/L0 on its own. + */ + if ((pmsr & PMEL1RX) && ((pmsr & PMSTATE) != PMSTATE_L1)) { + writel(L1IATN, pcie_base + PMCTLR); + ret = readl_poll_timeout_atomic(pcie_base + PMSR, val, + val & L1FAEG, 10, 1000); + if (ret) { + dev_warn_ratelimited(pcie_dev, + "Timeout waiting for L1 link state, ret=%d\n", + ret); + } + writel(L1FAEG | PMEL1RX, pcie_base + PMSR); + } + + return ret; +} + +static struct rcar_pcie_host *msi_to_host(struct rcar_msi *msi) +{ + return container_of(msi, struct rcar_pcie_host, msi); +} + +static u32 rcar_read_conf(struct rcar_pcie *pcie, int where) +{ + unsigned int shift = BITS_PER_BYTE * (where & 3); + u32 val = rcar_pci_read_reg(pcie, where & ~3); + + return val >> shift; +} + +#ifdef CONFIG_ARM +#define __rcar_pci_rw_reg_workaround(instr) \ + " .arch armv7-a\n" \ + "1: " instr " %1, [%2]\n" \ + "2: isb\n" \ + "3: .pushsection .text.fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: mov %0, #" __stringify(PCIBIOS_SET_FAILED) "\n" \ + " b 3b\n" \ + " .popsection\n" \ + " .pushsection __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .popsection\n" +#endif + +static int rcar_pci_write_reg_workaround(struct rcar_pcie *pcie, u32 val, + unsigned int reg) +{ + int error = PCIBIOS_SUCCESSFUL; +#ifdef CONFIG_ARM + asm volatile( + __rcar_pci_rw_reg_workaround("str") + : "+r"(error):"r"(val), "r"(pcie->base + reg) : "memory"); +#else + rcar_pci_write_reg(pcie, val, reg); +#endif + return error; +} + +static int rcar_pci_read_reg_workaround(struct rcar_pcie *pcie, u32 *val, + unsigned int reg) +{ + int error = PCIBIOS_SUCCESSFUL; +#ifdef CONFIG_ARM + asm volatile( + __rcar_pci_rw_reg_workaround("ldr") + : "+r"(error), "=r"(*val) : "r"(pcie->base + reg) : "memory"); + + if (error != PCIBIOS_SUCCESSFUL) + PCI_SET_ERROR_RESPONSE(val); +#else + *val = rcar_pci_read_reg(pcie, reg); +#endif + return error; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rcar_pcie_config_access(struct rcar_pcie_host *host, + unsigned char access_type, struct pci_bus *bus, + unsigned int devfn, int where, u32 *data) +{ + struct rcar_pcie *pcie = &host->pcie; + unsigned int dev, func, reg, index; + int ret; + + /* Wake the bus up in case it is in L1 state. */ + ret = rcar_pcie_wakeup(pcie->dev, pcie->base); + if (ret) { + PCI_SET_ERROR_RESPONSE(data); + return PCIBIOS_SET_FAILED; + } + + dev = PCI_SLOT(devfn); + func = PCI_FUNC(devfn); + reg = where & ~3; + index = reg / 4; + + /* + * While each channel has its own memory-mapped extended config + * space, it's generally only accessible when in endpoint mode. + * When in root complex mode, the controller is unable to target + * itself with either type 0 or type 1 accesses, and indeed, any + * controller-initiated target transfer to its own config space + * results in a completer abort. + * + * Each channel effectively only supports a single device, but as + * the same channel <-> device access works for any PCI_SLOT() + * value, we cheat a bit here and bind the controller's config + * space to devfn 0 in order to enable self-enumeration. In this + * case the regular ECAR/ECDR path is sidelined and the mangled + * config access itself is initiated as an internal bus transaction. + */ + if (pci_is_root_bus(bus)) { + if (dev != 0) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (access_type == RCAR_PCI_ACCESS_READ) + *data = rcar_pci_read_reg(pcie, PCICONF(index)); + else + rcar_pci_write_reg(pcie, *data, PCICONF(index)); + + return PCIBIOS_SUCCESSFUL; + } + + /* Clear errors */ + rcar_pci_write_reg(pcie, rcar_pci_read_reg(pcie, PCIEERRFR), PCIEERRFR); + + /* Set the PIO address */ + rcar_pci_write_reg(pcie, PCIE_CONF_BUS(bus->number) | + PCIE_CONF_DEV(dev) | PCIE_CONF_FUNC(func) | reg, PCIECAR); + + /* Enable the configuration access */ + if (pci_is_root_bus(bus->parent)) + rcar_pci_write_reg(pcie, PCIECCTLR_CCIE | TYPE0, PCIECCTLR); + else + rcar_pci_write_reg(pcie, PCIECCTLR_CCIE | TYPE1, PCIECCTLR); + + /* Check for errors */ + if (rcar_pci_read_reg(pcie, PCIEERRFR) & UNSUPPORTED_REQUEST) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* Check for master and target aborts */ + if (rcar_read_conf(pcie, RCONF(PCI_STATUS)) & + (PCI_STATUS_REC_MASTER_ABORT | PCI_STATUS_REC_TARGET_ABORT)) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (access_type == RCAR_PCI_ACCESS_READ) + ret = rcar_pci_read_reg_workaround(pcie, data, PCIECDR); + else + ret = rcar_pci_write_reg_workaround(pcie, *data, PCIECDR); + + /* Disable the configuration access */ + rcar_pci_write_reg(pcie, 0, PCIECCTLR); + + return ret; +} + +static int rcar_pcie_read_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct rcar_pcie_host *host = bus->sysdata; + int ret; + + ret = rcar_pcie_config_access(host, RCAR_PCI_ACCESS_READ, + bus, devfn, where, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (size == 1) + *val = (*val >> (BITS_PER_BYTE * (where & 3))) & 0xff; + else if (size == 2) + *val = (*val >> (BITS_PER_BYTE * (where & 2))) & 0xffff; + + dev_dbg(&bus->dev, "pcie-config-read: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08x\n", + bus->number, devfn, where, size, *val); + + return ret; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rcar_pcie_write_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct rcar_pcie_host *host = bus->sysdata; + unsigned int shift; + u32 data; + int ret; + + ret = rcar_pcie_config_access(host, RCAR_PCI_ACCESS_READ, + bus, devfn, where, &data); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + dev_dbg(&bus->dev, "pcie-config-write: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08x\n", + bus->number, devfn, where, size, val); + + if (size == 1) { + shift = BITS_PER_BYTE * (where & 3); + data &= ~(0xff << shift); + data |= ((val & 0xff) << shift); + } else if (size == 2) { + shift = BITS_PER_BYTE * (where & 2); + data &= ~(0xffff << shift); + data |= ((val & 0xffff) << shift); + } else + data = val; + + ret = rcar_pcie_config_access(host, RCAR_PCI_ACCESS_WRITE, + bus, devfn, where, &data); + + return ret; +} + +static struct pci_ops rcar_pcie_ops = { + .read = rcar_pcie_read_conf, + .write = rcar_pcie_write_conf, +}; + +static void rcar_pcie_force_speedup(struct rcar_pcie *pcie) +{ + struct device *dev = pcie->dev; + unsigned int timeout = 1000; + u32 macsr; + + if ((rcar_pci_read_reg(pcie, MACS2R) & LINK_SPEED) != LINK_SPEED_5_0GTS) + return; + + if (rcar_pci_read_reg(pcie, MACCTLR) & SPEED_CHANGE) { + dev_err(dev, "Speed change already in progress\n"); + return; + } + + macsr = rcar_pci_read_reg(pcie, MACSR); + if ((macsr & LINK_SPEED) == LINK_SPEED_5_0GTS) + goto done; + + /* Set target link speed to 5.0 GT/s */ + rcar_rmw32(pcie, EXPCAP(12), PCI_EXP_LNKSTA_CLS, + PCI_EXP_LNKSTA_CLS_5_0GB); + + /* Set speed change reason as intentional factor */ + rcar_rmw32(pcie, MACCGSPSETR, SPCNGRSN, 0); + + /* Clear SPCHGFIN, SPCHGSUC, and SPCHGFAIL */ + if (macsr & (SPCHGFIN | SPCHGSUC | SPCHGFAIL)) + rcar_pci_write_reg(pcie, macsr, MACSR); + + /* Start link speed change */ + rcar_rmw32(pcie, MACCTLR, SPEED_CHANGE, SPEED_CHANGE); + + while (timeout--) { + macsr = rcar_pci_read_reg(pcie, MACSR); + if (macsr & SPCHGFIN) { + /* Clear the interrupt bits */ + rcar_pci_write_reg(pcie, macsr, MACSR); + + if (macsr & SPCHGFAIL) + dev_err(dev, "Speed change failed\n"); + + goto done; + } + + msleep(1); + } + + dev_err(dev, "Speed change timed out\n"); + +done: + dev_info(dev, "Current link speed is %s GT/s\n", + (macsr & LINK_SPEED) == LINK_SPEED_5_0GTS ? "5" : "2.5"); +} + +static void rcar_pcie_hw_enable(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *win; + LIST_HEAD(res); + int i = 0; + + /* Try setting 5 GT/s link speed */ + rcar_pcie_force_speedup(pcie); + + /* Setup PCI resources */ + resource_list_for_each_entry(win, &bridge->windows) { + struct resource *res = win->res; + + if (!res->flags) + continue; + + switch (resource_type(res)) { + case IORESOURCE_IO: + case IORESOURCE_MEM: + rcar_pcie_set_outbound(pcie, i, win); + i++; + break; + } + } +} + +static int rcar_pcie_enable(struct rcar_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + + rcar_pcie_hw_enable(host); + + pci_add_flags(PCI_REASSIGN_ALL_BUS); + + bridge->sysdata = host; + bridge->ops = &rcar_pcie_ops; + + return pci_host_probe(bridge); +} + +static int phy_wait_for_ack(struct rcar_pcie *pcie) +{ + struct device *dev = pcie->dev; + unsigned int timeout = 100; + + while (timeout--) { + if (rcar_pci_read_reg(pcie, H1_PCIEPHYADRR) & PHY_ACK) + return 0; + + udelay(100); + } + + dev_err(dev, "Access to PCIe phy timed out\n"); + + return -ETIMEDOUT; +} + +static void phy_write_reg(struct rcar_pcie *pcie, + unsigned int rate, u32 addr, + unsigned int lane, u32 data) +{ + u32 phyaddr; + + phyaddr = WRITE_CMD | + ((rate & 1) << RATE_POS) | + ((lane & 0xf) << LANE_POS) | + ((addr & 0xff) << ADR_POS); + + /* Set write data */ + rcar_pci_write_reg(pcie, data, H1_PCIEPHYDOUTR); + rcar_pci_write_reg(pcie, phyaddr, H1_PCIEPHYADRR); + + /* Ignore errors as they will be dealt with if the data link is down */ + phy_wait_for_ack(pcie); + + /* Clear command */ + rcar_pci_write_reg(pcie, 0, H1_PCIEPHYDOUTR); + rcar_pci_write_reg(pcie, 0, H1_PCIEPHYADRR); + + /* Ignore errors as they will be dealt with if the data link is down */ + phy_wait_for_ack(pcie); +} + +static int rcar_pcie_hw_init(struct rcar_pcie *pcie) +{ + int err; + + /* Begin initialization */ + rcar_pci_write_reg(pcie, 0, PCIETCTLR); + + /* Set mode */ + rcar_pci_write_reg(pcie, 1, PCIEMSR); + + err = rcar_pcie_wait_for_phyrdy(pcie); + if (err) + return err; + + /* + * Initial header for port config space is type 1, set the device + * class to match. Hardware takes care of propagating the IDSETR + * settings, so there is no need to bother with a quirk. + */ + rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI_NORMAL << 8, IDSETR1); + + /* + * Setup Secondary Bus Number & Subordinate Bus Number, even though + * they aren't used, to avoid bridge being detected as broken. + */ + rcar_rmw32(pcie, RCONF(PCI_SECONDARY_BUS), 0xff, 1); + rcar_rmw32(pcie, RCONF(PCI_SUBORDINATE_BUS), 0xff, 1); + + /* Initialize default capabilities. */ + rcar_rmw32(pcie, REXPCAP(0), 0xff, PCI_CAP_ID_EXP); + rcar_rmw32(pcie, REXPCAP(PCI_EXP_FLAGS), + PCI_EXP_FLAGS_TYPE, PCI_EXP_TYPE_ROOT_PORT << 4); + rcar_rmw32(pcie, RCONF(PCI_HEADER_TYPE), PCI_HEADER_TYPE_MASK, + PCI_HEADER_TYPE_BRIDGE); + + /* Enable data link layer active state reporting */ + rcar_rmw32(pcie, REXPCAP(PCI_EXP_LNKCAP), PCI_EXP_LNKCAP_DLLLARC, + PCI_EXP_LNKCAP_DLLLARC); + + /* Write out the physical slot number = 0 */ + rcar_rmw32(pcie, REXPCAP(PCI_EXP_SLTCAP), PCI_EXP_SLTCAP_PSN, 0); + + /* Set the completion timer timeout to the maximum 50ms. */ + rcar_rmw32(pcie, TLCTLR + 1, 0x3f, 50); + + /* Terminate list of capabilities (Next Capability Offset=0) */ + rcar_rmw32(pcie, RVCCAP(0), 0xfff00000, 0); + + /* Enable MSI */ + if (IS_ENABLED(CONFIG_PCI_MSI)) + rcar_pci_write_reg(pcie, 0x801f0000, PCIEMSITXR); + + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); + + /* Finish initialization - establish a PCI Express link */ + rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); + + /* This will timeout if we don't have a link. */ + err = rcar_pcie_wait_for_dl(pcie); + if (err) + return err; + + /* Enable INTx interrupts */ + rcar_rmw32(pcie, PCIEINTXR, 0, 0xF << 8); + + wmb(); + + return 0; +} + +static int rcar_pcie_phy_init_h1(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + + /* Initialize the phy */ + phy_write_reg(pcie, 0, 0x42, 0x1, 0x0EC34191); + phy_write_reg(pcie, 1, 0x42, 0x1, 0x0EC34180); + phy_write_reg(pcie, 0, 0x43, 0x1, 0x00210188); + phy_write_reg(pcie, 1, 0x43, 0x1, 0x00210188); + phy_write_reg(pcie, 0, 0x44, 0x1, 0x015C0014); + phy_write_reg(pcie, 1, 0x44, 0x1, 0x015C0014); + phy_write_reg(pcie, 1, 0x4C, 0x1, 0x786174A0); + phy_write_reg(pcie, 1, 0x4D, 0x1, 0x048000BB); + phy_write_reg(pcie, 0, 0x51, 0x1, 0x079EC062); + phy_write_reg(pcie, 0, 0x52, 0x1, 0x20000000); + phy_write_reg(pcie, 1, 0x52, 0x1, 0x20000000); + phy_write_reg(pcie, 1, 0x56, 0x1, 0x00003806); + + phy_write_reg(pcie, 0, 0x60, 0x1, 0x004B03A5); + phy_write_reg(pcie, 0, 0x64, 0x1, 0x3F0F1F0F); + phy_write_reg(pcie, 0, 0x66, 0x1, 0x00008000); + + return 0; +} + +static int rcar_pcie_phy_init_gen2(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + + /* + * These settings come from the R-Car Series, 2nd Generation User's + * Manual, section 50.3.1 (2) Initialization of the physical layer. + */ + rcar_pci_write_reg(pcie, 0x000f0030, GEN2_PCIEPHYADDR); + rcar_pci_write_reg(pcie, 0x00381203, GEN2_PCIEPHYDATA); + rcar_pci_write_reg(pcie, 0x00000001, GEN2_PCIEPHYCTRL); + rcar_pci_write_reg(pcie, 0x00000006, GEN2_PCIEPHYCTRL); + + rcar_pci_write_reg(pcie, 0x000f0054, GEN2_PCIEPHYADDR); + /* The following value is for DC connection, no termination resistor */ + rcar_pci_write_reg(pcie, 0x13802007, GEN2_PCIEPHYDATA); + rcar_pci_write_reg(pcie, 0x00000001, GEN2_PCIEPHYCTRL); + rcar_pci_write_reg(pcie, 0x00000006, GEN2_PCIEPHYCTRL); + + return 0; +} + +static int rcar_pcie_phy_init_gen3(struct rcar_pcie_host *host) +{ + int err; + + err = phy_init(host->phy); + if (err) + return err; + + err = phy_power_on(host->phy); + if (err) + phy_exit(host->phy); + + return err; +} + +static irqreturn_t rcar_pcie_msi_irq(int irq, void *data) +{ + struct rcar_pcie_host *host = data; + struct rcar_pcie *pcie = &host->pcie; + struct rcar_msi *msi = &host->msi; + struct device *dev = pcie->dev; + unsigned long reg; + + reg = rcar_pci_read_reg(pcie, PCIEMSIFR); + + /* MSI & INTx share an interrupt - we only handle MSI here */ + if (!reg) + return IRQ_NONE; + + while (reg) { + unsigned int index = find_first_bit(®, 32); + int ret; + + ret = generic_handle_domain_irq(msi->domain, index); + if (ret) { + /* Unknown MSI, just clear it */ + dev_dbg(dev, "unexpected MSI\n"); + rcar_pci_write_reg(pcie, BIT(index), PCIEMSIFR); + } + + /* see if there's any more pending in this vector */ + reg = rcar_pci_read_reg(pcie, PCIEMSIFR); + } + + return IRQ_HANDLED; +} + +static void rcar_msi_irq_ack(struct irq_data *d) +{ + struct rcar_msi *msi = irq_data_get_irq_chip_data(d); + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + + /* clear the interrupt */ + rcar_pci_write_reg(pcie, BIT(d->hwirq), PCIEMSIFR); +} + +static void rcar_msi_irq_mask(struct irq_data *d) +{ + struct rcar_msi *msi = irq_data_get_irq_chip_data(d); + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + u32 value; + + 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; + u32 value; + + 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) +{ + struct rcar_msi *msi = irq_data_get_irq_chip_data(data); + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + + msg->address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE; + msg->address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR); + msg->data = data->hwirq; +} + +static struct irq_chip rcar_msi_bottom_chip = { + .name = "R-Car MSI", + .irq_ack = rcar_msi_irq_ack, + .irq_mask = rcar_msi_irq_mask, + .irq_unmask = rcar_msi_irq_unmask, + .irq_compose_msi_msg = rcar_compose_msi_msg, +}; + +static int rcar_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct rcar_msi *msi = domain->host_data; + unsigned int i; + int hwirq; + + mutex_lock(&msi->map_lock); + + hwirq = bitmap_find_free_region(msi->used, INT_PCI_MSI_NR, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); + + if (hwirq < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &rcar_msi_bottom_chip, domain->host_data, + handle_edge_irq, NULL, NULL); + + return 0; +} + +static void rcar_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct rcar_msi *msi = domain->host_data; + + mutex_lock(&msi->map_lock); + + bitmap_release_region(msi->used, d->hwirq, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); +} + +static const struct irq_domain_ops rcar_msi_domain_ops = { + .alloc = rcar_msi_domain_alloc, + .free = rcar_msi_domain_free, +}; + +#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 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 IRQ domain\n"); + return -ENOMEM; + } + + return 0; +} + +static void rcar_free_domains(struct rcar_msi *msi) +{ + irq_domain_remove(msi->domain); +} + +static int rcar_pcie_enable_msi(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + struct device *dev = pcie->dev; + struct rcar_msi *msi = &host->msi; + struct resource res; + int err; + + mutex_init(&msi->map_lock); + raw_spin_lock_init(&msi->mask_lock); + + err = of_address_to_resource(dev->of_node, 0, &res); + if (err) + return err; + + err = rcar_allocate_domains(msi); + if (err) + return err; + + /* Two IRQs are for MSI, but they are also used for non-MSI IRQs */ + err = devm_request_irq(dev, msi->irq1, rcar_pcie_msi_irq, + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_bottom_chip.name, host); + if (err < 0) { + dev_err(dev, "failed to request IRQ: %d\n", err); + goto err; + } + + err = devm_request_irq(dev, msi->irq2, rcar_pcie_msi_irq, + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_bottom_chip.name, host); + if (err < 0) { + dev_err(dev, "failed to request IRQ: %d\n", err); + goto err; + } + + /* Disable all MSIs */ + rcar_pci_write_reg(pcie, 0, PCIEMSIIER); + + /* + * Setup MSI data target using RC base address, which is guaranteed + * to be in the low 32bit range on any R-Car HW. + */ + rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR); + rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR); + + return 0; + +err: + rcar_free_domains(msi); + return err; +} + +static void rcar_pcie_teardown_msi(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + + /* Disable all MSI interrupts */ + rcar_pci_write_reg(pcie, 0, PCIEMSIIER); + + /* Disable address decoding of the MSI interrupt, MSIFE */ + rcar_pci_write_reg(pcie, 0, PCIEMSIALR); + + rcar_free_domains(&host->msi); +} + +static int rcar_pcie_get_resources(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + struct device *dev = pcie->dev; + struct resource res; + int err, i; + + host->phy = devm_phy_optional_get(dev, "pcie"); + if (IS_ERR(host->phy)) + return PTR_ERR(host->phy); + + err = of_address_to_resource(dev->of_node, 0, &res); + if (err) + return err; + + pcie->base = devm_ioremap_resource(dev, &res); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + host->bus_clk = devm_clk_get(dev, "pcie_bus"); + if (IS_ERR(host->bus_clk)) { + dev_err(dev, "cannot get pcie bus clock\n"); + return PTR_ERR(host->bus_clk); + } + + i = irq_of_parse_and_map(dev->of_node, 0); + if (!i) { + dev_err(dev, "cannot get platform resources for msi interrupt\n"); + err = -ENOENT; + goto err_irq1; + } + host->msi.irq1 = i; + + i = irq_of_parse_and_map(dev->of_node, 1); + if (!i) { + dev_err(dev, "cannot get platform resources for msi interrupt\n"); + err = -ENOENT; + goto err_irq2; + } + host->msi.irq2 = i; + + return 0; + +err_irq2: + irq_dispose_mapping(host->msi.irq1); +err_irq1: + return err; +} + +static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie, + struct resource_entry *entry, + int *index) +{ + u64 restype = entry->res->flags; + u64 cpu_addr = entry->res->start; + u64 cpu_end = entry->res->end; + u64 pci_addr = entry->res->start - entry->offset; + u32 flags = LAM_64BIT | LAR_ENABLE; + u64 mask; + u64 size = resource_size(entry->res); + int idx = *index; + + if (restype & IORESOURCE_PREFETCH) + flags |= LAM_PREFETCH; + + while (cpu_addr < cpu_end) { + if (idx >= MAX_NR_INBOUND_MAPS - 1) { + dev_err(pcie->dev, "Failed to map inbound regions!\n"); + return -EINVAL; + } + + /* + * If the size of the range is larger than the alignment of + * the start address, we have to use multiple entries to + * perform the mapping. + */ + if (cpu_addr > 0) { + unsigned long nr_zeros = __ffs64(cpu_addr); + u64 alignment = 1ULL << nr_zeros; + + size = min(size, alignment); + } + + /* Hardware supports max 4GiB inbound region */ + size = min(size, 1ULL << 32); + + mask = roundup_pow_of_two(size) - 1; + mask &= ~0xf; + + rcar_pcie_set_inbound(pcie, cpu_addr, pci_addr, + lower_32_bits(mask) | flags, idx, true); + + pci_addr += size; + cpu_addr += size; + idx += 2; + } + *index = idx; + + return 0; +} + +static int rcar_pcie_parse_map_dma_ranges(struct rcar_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *entry; + int index = 0, err = 0; + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + err = rcar_pcie_inbound_ranges(&host->pcie, entry, &index); + if (err) + break; + } + + return err; +} + +static const struct of_device_id rcar_pcie_of_match[] = { + { .compatible = "renesas,pcie-r8a7779", + .data = rcar_pcie_phy_init_h1 }, + { .compatible = "renesas,pcie-r8a7790", + .data = rcar_pcie_phy_init_gen2 }, + { .compatible = "renesas,pcie-r8a7791", + .data = rcar_pcie_phy_init_gen2 }, + { .compatible = "renesas,pcie-rcar-gen2", + .data = rcar_pcie_phy_init_gen2 }, + { .compatible = "renesas,pcie-r8a7795", + .data = rcar_pcie_phy_init_gen3 }, + { .compatible = "renesas,pcie-rcar-gen3", + .data = rcar_pcie_phy_init_gen3 }, + {}, +}; + +/* Design note 346 from Linear Technology says order is not important. */ +static const char * const rcar_pcie_supplies[] = { + "vpcie1v5", + "vpcie3v3", + "vpcie12v", +}; + +static int rcar_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct rcar_pcie_host *host; + struct rcar_pcie *pcie; + unsigned int i; + u32 data; + int err; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*host)); + if (!bridge) + return -ENOMEM; + + host = pci_host_bridge_priv(bridge); + pcie = &host->pcie; + pcie->dev = dev; + platform_set_drvdata(pdev, host); + + for (i = 0; i < ARRAY_SIZE(rcar_pcie_supplies); i++) { + err = devm_regulator_get_enable_optional(dev, rcar_pcie_supplies[i]); + if (err < 0 && err != -ENODEV) + return dev_err_probe(dev, err, "failed to enable regulator: %s\n", + rcar_pcie_supplies[i]); + } + + pm_runtime_enable(pcie->dev); + err = pm_runtime_get_sync(pcie->dev); + if (err < 0) { + dev_err(pcie->dev, "pm_runtime_get_sync failed\n"); + goto err_pm_put; + } + + err = rcar_pcie_get_resources(host); + if (err < 0) { + dev_err(dev, "failed to request resources: %d\n", err); + goto err_pm_put; + } + + err = clk_prepare_enable(host->bus_clk); + if (err) { + dev_err(dev, "failed to enable bus clock: %d\n", err); + goto err_unmap_msi_irqs; + } + + err = rcar_pcie_parse_map_dma_ranges(host); + if (err) + goto err_clk_disable; + + host->phy_init_fn = of_device_get_match_data(dev); + err = host->phy_init_fn(host); + if (err) { + dev_err(dev, "failed to init PCIe PHY\n"); + goto err_clk_disable; + } + + /* Failure to get a link might just be that no cards are inserted */ + if (rcar_pcie_hw_init(pcie)) { + dev_info(dev, "PCIe link down\n"); + err = -ENODEV; + goto err_phy_shutdown; + } + + data = rcar_pci_read_reg(pcie, MACSR); + dev_info(dev, "PCIe x%d: link up\n", (data >> 20) & 0x3f); + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + err = rcar_pcie_enable_msi(host); + if (err < 0) { + dev_err(dev, + "failed to enable MSI support: %d\n", + err); + goto err_phy_shutdown; + } + } + + err = rcar_pcie_enable(host); + if (err) + goto err_msi_teardown; + + return 0; + +err_msi_teardown: + if (IS_ENABLED(CONFIG_PCI_MSI)) + rcar_pcie_teardown_msi(host); + +err_phy_shutdown: + if (host->phy) { + phy_power_off(host->phy); + phy_exit(host->phy); + } + +err_clk_disable: + clk_disable_unprepare(host->bus_clk); + +err_unmap_msi_irqs: + irq_dispose_mapping(host->msi.irq2); + irq_dispose_mapping(host->msi.irq1); + +err_pm_put: + pm_runtime_put(dev); + pm_runtime_disable(dev); + + return err; +} + +static int rcar_pcie_resume(struct device *dev) +{ + struct rcar_pcie_host *host = dev_get_drvdata(dev); + struct rcar_pcie *pcie = &host->pcie; + unsigned int data; + int err; + + err = rcar_pcie_parse_map_dma_ranges(host); + if (err) + return 0; + + /* Failure to get a link might just be that no cards are inserted */ + err = host->phy_init_fn(host); + if (err) { + dev_info(dev, "PCIe link down\n"); + return 0; + } + + data = rcar_pci_read_reg(pcie, MACSR); + dev_info(dev, "PCIe x%d: link up\n", (data >> 20) & 0x3f); + + /* Enable MSI */ + if (IS_ENABLED(CONFIG_PCI_MSI)) { + struct resource res; + u32 val; + + of_address_to_resource(dev->of_node, 0, &res); + rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR); + rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR); + + bitmap_to_arr32(&val, host->msi.used, INT_PCI_MSI_NR); + rcar_pci_write_reg(pcie, val, PCIEMSIIER); + } + + rcar_pcie_hw_enable(host); + + return 0; +} + +static int rcar_pcie_resume_noirq(struct device *dev) +{ + struct rcar_pcie_host *host = dev_get_drvdata(dev); + struct rcar_pcie *pcie = &host->pcie; + + if (rcar_pci_read_reg(pcie, PMSR) && + !(rcar_pci_read_reg(pcie, PCIETCTLR) & DL_DOWN)) + return 0; + + /* Re-establish the PCIe link */ + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); + rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); + return rcar_pcie_wait_for_dl(pcie); +} + +static const struct dev_pm_ops rcar_pcie_pm_ops = { + SYSTEM_SLEEP_PM_OPS(NULL, rcar_pcie_resume) + .resume_noirq = rcar_pcie_resume_noirq, +}; + +static struct platform_driver rcar_pcie_driver = { + .driver = { + .name = "rcar-pcie", + .of_match_table = rcar_pcie_of_match, + .pm = &rcar_pcie_pm_ops, + .suppress_bind_attrs = true, + }, + .probe = rcar_pcie_probe, +}; + +#ifdef CONFIG_ARM +static int rcar_pcie_aarch32_abort_handler(unsigned long addr, + unsigned int fsr, struct pt_regs *regs) +{ + return !fixup_exception(regs); +} + +static const struct of_device_id rcar_pcie_abort_handler_of_match[] __initconst = { + { .compatible = "renesas,pcie-r8a7779" }, + { .compatible = "renesas,pcie-r8a7790" }, + { .compatible = "renesas,pcie-r8a7791" }, + { .compatible = "renesas,pcie-rcar-gen2" }, + {}, +}; + +static int __init rcar_pcie_init(void) +{ + if (of_find_matching_node(NULL, rcar_pcie_abort_handler_of_match)) { +#ifdef CONFIG_ARM_LPAE + hook_fault_code(17, rcar_pcie_aarch32_abort_handler, SIGBUS, 0, + "asynchronous external abort"); +#else + hook_fault_code(22, rcar_pcie_aarch32_abort_handler, SIGBUS, 0, + "imprecise external abort"); +#endif + } + + return platform_driver_register(&rcar_pcie_driver); +} +device_initcall(rcar_pcie_init); +#else +builtin_platform_driver(rcar_pcie_driver); +#endif diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c index c8febb009454..7583699ef7b6 100644 --- a/drivers/pci/controller/pcie-rcar.c +++ b/drivers/pci/controller/pcie-rcar.c @@ -1,177 +1,29 @@ // SPDX-License-Identifier: GPL-2.0 /* * PCIe driver for Renesas R-Car SoCs - * Copyright (C) 2014 Renesas Electronics Europe Ltd - * - * Based on: - * arch/sh/drivers/pci/pcie-sh7786.c - * arch/sh/drivers/pci/ops-sh7786.c - * Copyright (C) 2009 - 2011 Paul Mundt + * Copyright (C) 2014-2020 Renesas Electronics Europe Ltd * * Author: Phil Edworthy <phil.edworthy@renesas.com> */ -#include <linux/bitops.h> -#include <linux/clk.h> #include <linux/delay.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/irqdomain.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/msi.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> -#include <linux/of_pci.h> -#include <linux/of_platform.h> #include <linux/pci.h> -#include <linux/phy/phy.h> -#include <linux/platform_device.h> -#include <linux/pm_runtime.h> -#include <linux/slab.h> - -#include "../pci.h" - -#define PCIECAR 0x000010 -#define PCIECCTLR 0x000018 -#define CONFIG_SEND_ENABLE BIT(31) -#define TYPE0 (0 << 8) -#define TYPE1 BIT(8) -#define PCIECDR 0x000020 -#define PCIEMSR 0x000028 -#define PCIEINTXR 0x000400 -#define PCIEPHYSR 0x0007f0 -#define PHYRDY BIT(0) -#define PCIEMSITXR 0x000840 - -/* Transfer control */ -#define PCIETCTLR 0x02000 -#define CFINIT 1 -#define PCIETSTR 0x02004 -#define DATA_LINK_ACTIVE 1 -#define PCIEERRFR 0x02020 -#define UNSUPPORTED_REQUEST BIT(4) -#define PCIEMSIFR 0x02044 -#define PCIEMSIALR 0x02048 -#define MSIFE 1 -#define PCIEMSIAUR 0x0204c -#define PCIEMSIIER 0x02050 - -/* root port address */ -#define PCIEPRAR(x) (0x02080 + ((x) * 0x4)) - -/* local address reg & mask */ -#define PCIELAR(x) (0x02200 + ((x) * 0x20)) -#define PCIELAMR(x) (0x02208 + ((x) * 0x20)) -#define LAM_PREFETCH BIT(3) -#define LAM_64BIT BIT(2) -#define LAR_ENABLE BIT(1) - -/* PCIe address reg & mask */ -#define PCIEPALR(x) (0x03400 + ((x) * 0x20)) -#define PCIEPAUR(x) (0x03404 + ((x) * 0x20)) -#define PCIEPAMR(x) (0x03408 + ((x) * 0x20)) -#define PCIEPTCTLR(x) (0x0340c + ((x) * 0x20)) -#define PAR_ENABLE BIT(31) -#define IO_SPACE BIT(8) - -/* Configuration */ -#define PCICONF(x) (0x010000 + ((x) * 0x4)) -#define PMCAP(x) (0x010040 + ((x) * 0x4)) -#define EXPCAP(x) (0x010070 + ((x) * 0x4)) -#define VCCAP(x) (0x010100 + ((x) * 0x4)) - -/* link layer */ -#define IDSETR1 0x011004 -#define TLCTLR 0x011048 -#define MACSR 0x011054 -#define SPCHGFIN BIT(4) -#define SPCHGFAIL BIT(6) -#define SPCHGSUC BIT(7) -#define LINK_SPEED (0xf << 16) -#define LINK_SPEED_2_5GTS (1 << 16) -#define LINK_SPEED_5_0GTS (2 << 16) -#define MACCTLR 0x011058 -#define SPEED_CHANGE BIT(24) -#define SCRAMBLE_DISABLE BIT(27) -#define MACS2R 0x011078 -#define MACCGSPSETR 0x011084 -#define SPCNGRSN BIT(31) - -/* R-Car H1 PHY */ -#define H1_PCIEPHYADRR 0x04000c -#define WRITE_CMD BIT(16) -#define PHY_ACK BIT(24) -#define RATE_POS 12 -#define LANE_POS 8 -#define ADR_POS 0 -#define H1_PCIEPHYDOUTR 0x040014 - -/* R-Car Gen2 PHY */ -#define GEN2_PCIEPHYADDR 0x780 -#define GEN2_PCIEPHYDATA 0x784 -#define GEN2_PCIEPHYCTRL 0x78c - -#define INT_PCI_MSI_NR 32 -#define RCONF(x) (PCICONF(0) + (x)) -#define RPMCAP(x) (PMCAP(0) + (x)) -#define REXPCAP(x) (EXPCAP(0) + (x)) -#define RVCCAP(x) (VCCAP(0) + (x)) +#include "pcie-rcar.h" -#define PCIE_CONF_BUS(b) (((b) & 0xff) << 24) -#define PCIE_CONF_DEV(d) (((d) & 0x1f) << 19) -#define PCIE_CONF_FUNC(f) (((f) & 0x7) << 16) - -#define RCAR_PCI_MAX_RESOURCES 4 -#define MAX_NR_INBOUND_MAPS 6 - -struct rcar_msi { - DECLARE_BITMAP(used, INT_PCI_MSI_NR); - struct irq_domain *domain; - struct msi_controller chip; - unsigned long pages; - struct mutex lock; - int irq1; - int irq2; -}; - -static inline struct rcar_msi *to_rcar_msi(struct msi_controller *chip) -{ - return container_of(chip, struct rcar_msi, chip); -} - -/* Structure representing the PCIe interface */ -struct rcar_pcie { - struct device *dev; - struct phy *phy; - void __iomem *base; - struct list_head resources; - int root_bus_nr; - struct clk *bus_clk; - struct rcar_msi msi; -}; - -static void rcar_pci_write_reg(struct rcar_pcie *pcie, unsigned long val, - unsigned long reg) +void rcar_pci_write_reg(struct rcar_pcie *pcie, u32 val, unsigned int reg) { writel(val, pcie->base + reg); } -static unsigned long rcar_pci_read_reg(struct rcar_pcie *pcie, - unsigned long reg) +u32 rcar_pci_read_reg(struct rcar_pcie *pcie, unsigned int reg) { return readl(pcie->base + reg); } -enum { - RCAR_PCI_ACCESS_READ, - RCAR_PCI_ACCESS_WRITE, -}; - -static void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data) +void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data) { - int shift = 8 * (where & 3); + unsigned int shift = BITS_PER_BYTE * (where & 3); u32 val = rcar_pci_read_reg(pcie, where & ~3); val &= ~(mask << shift); @@ -179,162 +31,42 @@ static void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data) rcar_pci_write_reg(pcie, val, where & ~3); } -static u32 rcar_read_conf(struct rcar_pcie *pcie, int where) +int rcar_pcie_wait_for_phyrdy(struct rcar_pcie *pcie) { - int shift = 8 * (where & 3); - u32 val = rcar_pci_read_reg(pcie, where & ~3); - - return val >> shift; -} - -/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ -static int rcar_pcie_config_access(struct rcar_pcie *pcie, - unsigned char access_type, struct pci_bus *bus, - unsigned int devfn, int where, u32 *data) -{ - int dev, func, reg, index; - - dev = PCI_SLOT(devfn); - func = PCI_FUNC(devfn); - reg = where & ~3; - index = reg / 4; - - /* - * While each channel has its own memory-mapped extended config - * space, it's generally only accessible when in endpoint mode. - * When in root complex mode, the controller is unable to target - * itself with either type 0 or type 1 accesses, and indeed, any - * controller initiated target transfer to its own config space - * result in a completer abort. - * - * Each channel effectively only supports a single device, but as - * the same channel <-> device access works for any PCI_SLOT() - * value, we cheat a bit here and bind the controller's config - * space to devfn 0 in order to enable self-enumeration. In this - * case the regular ECAR/ECDR path is sidelined and the mangled - * config access itself is initiated as an internal bus transaction. - */ - if (pci_is_root_bus(bus)) { - if (dev != 0) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (access_type == RCAR_PCI_ACCESS_READ) { - *data = rcar_pci_read_reg(pcie, PCICONF(index)); - } else { - /* Keep an eye out for changes to the root bus number */ - if (pci_is_root_bus(bus) && (reg == PCI_PRIMARY_BUS)) - pcie->root_bus_nr = *data & 0xff; - - rcar_pci_write_reg(pcie, *data, PCICONF(index)); - } - - return PCIBIOS_SUCCESSFUL; - } - - if (pcie->root_bus_nr < 0) - return PCIBIOS_DEVICE_NOT_FOUND; - - /* Clear errors */ - rcar_pci_write_reg(pcie, rcar_pci_read_reg(pcie, PCIEERRFR), PCIEERRFR); - - /* Set the PIO address */ - rcar_pci_write_reg(pcie, PCIE_CONF_BUS(bus->number) | - PCIE_CONF_DEV(dev) | PCIE_CONF_FUNC(func) | reg, PCIECAR); - - /* Enable the configuration access */ - if (bus->parent->number == pcie->root_bus_nr) - rcar_pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE0, PCIECCTLR); - else - rcar_pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE1, PCIECCTLR); - - /* Check for errors */ - if (rcar_pci_read_reg(pcie, PCIEERRFR) & UNSUPPORTED_REQUEST) - return PCIBIOS_DEVICE_NOT_FOUND; - - /* Check for master and target aborts */ - if (rcar_read_conf(pcie, RCONF(PCI_STATUS)) & - (PCI_STATUS_REC_MASTER_ABORT | PCI_STATUS_REC_TARGET_ABORT)) - return PCIBIOS_DEVICE_NOT_FOUND; - - if (access_type == RCAR_PCI_ACCESS_READ) - *data = rcar_pci_read_reg(pcie, PCIECDR); - else - rcar_pci_write_reg(pcie, *data, PCIECDR); - - /* Disable the configuration access */ - rcar_pci_write_reg(pcie, 0, PCIECCTLR); - - return PCIBIOS_SUCCESSFUL; -} + unsigned int timeout = 10; -static int rcar_pcie_read_conf(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 *val) -{ - struct rcar_pcie *pcie = bus->sysdata; - int ret; + while (timeout--) { + if (rcar_pci_read_reg(pcie, PCIEPHYSR) & PHYRDY) + return 0; - ret = rcar_pcie_config_access(pcie, RCAR_PCI_ACCESS_READ, - bus, devfn, where, val); - if (ret != PCIBIOS_SUCCESSFUL) { - *val = 0xffffffff; - return ret; + msleep(5); } - if (size == 1) - *val = (*val >> (8 * (where & 3))) & 0xff; - else if (size == 2) - *val = (*val >> (8 * (where & 2))) & 0xffff; - - dev_dbg(&bus->dev, "pcie-config-read: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08lx\n", - bus->number, devfn, where, size, (unsigned long)*val); - - return ret; + return -ETIMEDOUT; } -/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ -static int rcar_pcie_write_conf(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 val) +int rcar_pcie_wait_for_dl(struct rcar_pcie *pcie) { - struct rcar_pcie *pcie = bus->sysdata; - int shift, ret; - u32 data; - - ret = rcar_pcie_config_access(pcie, RCAR_PCI_ACCESS_READ, - bus, devfn, where, &data); - if (ret != PCIBIOS_SUCCESSFUL) - return ret; - - dev_dbg(&bus->dev, "pcie-config-write: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08lx\n", - bus->number, devfn, where, size, (unsigned long)val); + unsigned int timeout = 10000; - if (size == 1) { - shift = 8 * (where & 3); - data &= ~(0xff << shift); - data |= ((val & 0xff) << shift); - } else if (size == 2) { - shift = 8 * (where & 2); - data &= ~(0xffff << shift); - data |= ((val & 0xffff) << shift); - } else - data = val; + while (timeout--) { + if ((rcar_pci_read_reg(pcie, PCIETSTR) & DATA_LINK_ACTIVE)) + return 0; - ret = rcar_pcie_config_access(pcie, RCAR_PCI_ACCESS_WRITE, - bus, devfn, where, &data); + udelay(5); + cpu_relax(); + } - return ret; + return -ETIMEDOUT; } -static struct pci_ops rcar_pcie_ops = { - .read = rcar_pcie_read_conf, - .write = rcar_pcie_write_conf, -}; - -static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie, - struct resource *res) +void rcar_pcie_set_outbound(struct rcar_pcie *pcie, int win, + struct resource_entry *window) { /* Setup PCIe address space mappings for each resource */ - resource_size_t size; + struct resource *res = window->res; resource_size_t res_start; + resource_size_t size; u32 mask; rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win)); @@ -344,13 +76,16 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie, * keeps things pretty simple. */ size = resource_size(res); - mask = (roundup_pow_of_two(size) / SZ_128) - 1; + if (size > 128) + mask = (roundup_pow_of_two(size) / SZ_128) - 1; + else + mask = 0x0; rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win)); if (res->flags & IORESOURCE_IO) - res_start = pci_pio_to_address(res->start); + res_start = pci_pio_to_address(res->start) - window->offset; else - res_start = res->start; + res_start = res->start - window->offset; rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPAUR(win)); rcar_pci_write_reg(pcie, lower_32_bits(res_start) & ~0x7F, @@ -364,869 +99,22 @@ static void rcar_pcie_setup_window(int win, struct rcar_pcie *pcie, rcar_pci_write_reg(pcie, mask, PCIEPTCTLR(win)); } -static int rcar_pcie_setup(struct list_head *resource, struct rcar_pcie *pci) +void rcar_pcie_set_inbound(struct rcar_pcie *pcie, u64 cpu_addr, + u64 pci_addr, u64 flags, int idx, bool host) { - struct resource_entry *win; - int i = 0; - - /* Setup PCI resources */ - resource_list_for_each_entry(win, &pci->resources) { - struct resource *res = win->res; - - if (!res->flags) - continue; - - switch (resource_type(res)) { - case IORESOURCE_IO: - case IORESOURCE_MEM: - rcar_pcie_setup_window(i, pci, res); - i++; - break; - case IORESOURCE_BUS: - pci->root_bus_nr = res->start; - break; - default: - continue; - } - - pci_add_resource(resource, res); - } - - return 1; -} - -static void rcar_pcie_force_speedup(struct rcar_pcie *pcie) -{ - struct device *dev = pcie->dev; - unsigned int timeout = 1000; - u32 macsr; - - if ((rcar_pci_read_reg(pcie, MACS2R) & LINK_SPEED) != LINK_SPEED_5_0GTS) - return; - - if (rcar_pci_read_reg(pcie, MACCTLR) & SPEED_CHANGE) { - dev_err(dev, "Speed change already in progress\n"); - return; - } - - macsr = rcar_pci_read_reg(pcie, MACSR); - if ((macsr & LINK_SPEED) == LINK_SPEED_5_0GTS) - goto done; - - /* Set target link speed to 5.0 GT/s */ - rcar_rmw32(pcie, EXPCAP(12), PCI_EXP_LNKSTA_CLS, - PCI_EXP_LNKSTA_CLS_5_0GB); - - /* Set speed change reason as intentional factor */ - rcar_rmw32(pcie, MACCGSPSETR, SPCNGRSN, 0); - - /* Clear SPCHGFIN, SPCHGSUC, and SPCHGFAIL */ - if (macsr & (SPCHGFIN | SPCHGSUC | SPCHGFAIL)) - rcar_pci_write_reg(pcie, macsr, MACSR); - - /* Start link speed change */ - rcar_rmw32(pcie, MACCTLR, SPEED_CHANGE, SPEED_CHANGE); - - while (timeout--) { - macsr = rcar_pci_read_reg(pcie, MACSR); - if (macsr & SPCHGFIN) { - /* Clear the interrupt bits */ - rcar_pci_write_reg(pcie, macsr, MACSR); - - if (macsr & SPCHGFAIL) - dev_err(dev, "Speed change failed\n"); - - goto done; - } - - msleep(1); - } - - dev_err(dev, "Speed change timed out\n"); - -done: - dev_info(dev, "Current link speed is %s GT/s\n", - (macsr & LINK_SPEED) == LINK_SPEED_5_0GTS ? "5" : "2.5"); -} - -static int rcar_pcie_enable(struct rcar_pcie *pcie) -{ - struct device *dev = pcie->dev; - struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); - struct pci_bus *bus, *child; - int ret; - - /* Try setting 5 GT/s link speed */ - rcar_pcie_force_speedup(pcie); - - rcar_pcie_setup(&bridge->windows, pcie); - - pci_add_flags(PCI_REASSIGN_ALL_BUS); - - bridge->dev.parent = dev; - bridge->sysdata = pcie; - bridge->busnr = pcie->root_bus_nr; - bridge->ops = &rcar_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - if (IS_ENABLED(CONFIG_PCI_MSI)) - bridge->msi = &pcie->msi.chip; - - ret = pci_scan_root_bus_bridge(bridge); - if (ret < 0) - return ret; - - bus = bridge->bus; - - pci_bus_size_bridges(bus); - pci_bus_assign_resources(bus); - - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); - - pci_bus_add_devices(bus); - - return 0; -} - -static int phy_wait_for_ack(struct rcar_pcie *pcie) -{ - struct device *dev = pcie->dev; - unsigned int timeout = 100; - - while (timeout--) { - if (rcar_pci_read_reg(pcie, H1_PCIEPHYADRR) & PHY_ACK) - return 0; - - udelay(100); - } - - dev_err(dev, "Access to PCIe phy timed out\n"); - - return -ETIMEDOUT; -} - -static void phy_write_reg(struct rcar_pcie *pcie, - unsigned int rate, unsigned int addr, - unsigned int lane, unsigned int data) -{ - unsigned long phyaddr; - - phyaddr = WRITE_CMD | - ((rate & 1) << RATE_POS) | - ((lane & 0xf) << LANE_POS) | - ((addr & 0xff) << ADR_POS); - - /* Set write data */ - rcar_pci_write_reg(pcie, data, H1_PCIEPHYDOUTR); - rcar_pci_write_reg(pcie, phyaddr, H1_PCIEPHYADRR); - - /* Ignore errors as they will be dealt with if the data link is down */ - phy_wait_for_ack(pcie); - - /* Clear command */ - rcar_pci_write_reg(pcie, 0, H1_PCIEPHYDOUTR); - rcar_pci_write_reg(pcie, 0, H1_PCIEPHYADRR); - - /* Ignore errors as they will be dealt with if the data link is down */ - phy_wait_for_ack(pcie); -} - -static int rcar_pcie_wait_for_phyrdy(struct rcar_pcie *pcie) -{ - unsigned int timeout = 10; - - while (timeout--) { - if (rcar_pci_read_reg(pcie, PCIEPHYSR) & PHYRDY) - return 0; - - msleep(5); - } - - return -ETIMEDOUT; -} - -static int rcar_pcie_wait_for_dl(struct rcar_pcie *pcie) -{ - unsigned int timeout = 10000; - - while (timeout--) { - if ((rcar_pci_read_reg(pcie, PCIETSTR) & DATA_LINK_ACTIVE)) - return 0; - - udelay(5); - cpu_relax(); - } - - return -ETIMEDOUT; -} - -static int rcar_pcie_hw_init(struct rcar_pcie *pcie) -{ - int err; - - /* Begin initialization */ - rcar_pci_write_reg(pcie, 0, PCIETCTLR); - - /* Set mode */ - rcar_pci_write_reg(pcie, 1, PCIEMSR); - - err = rcar_pcie_wait_for_phyrdy(pcie); - if (err) - return err; - /* - * Initial header for port config space is type 1, set the device - * class to match. Hardware takes care of propagating the IDSETR - * settings, so there is no need to bother with a quirk. + * Set up 64-bit inbound regions as the range parser doesn't + * distinguish between 32 and 64-bit types. */ - rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI << 16, IDSETR1); - - /* - * Setup Secondary Bus Number & Subordinate Bus Number, even though - * they aren't used, to avoid bridge being detected as broken. - */ - rcar_rmw32(pcie, RCONF(PCI_SECONDARY_BUS), 0xff, 1); - rcar_rmw32(pcie, RCONF(PCI_SUBORDINATE_BUS), 0xff, 1); - - /* Initialize default capabilities. */ - rcar_rmw32(pcie, REXPCAP(0), 0xff, PCI_CAP_ID_EXP); - rcar_rmw32(pcie, REXPCAP(PCI_EXP_FLAGS), - PCI_EXP_FLAGS_TYPE, PCI_EXP_TYPE_ROOT_PORT << 4); - rcar_rmw32(pcie, RCONF(PCI_HEADER_TYPE), 0x7f, - PCI_HEADER_TYPE_BRIDGE); - - /* Enable data link layer active state reporting */ - rcar_rmw32(pcie, REXPCAP(PCI_EXP_LNKCAP), PCI_EXP_LNKCAP_DLLLARC, - PCI_EXP_LNKCAP_DLLLARC); - - /* Write out the physical slot number = 0 */ - rcar_rmw32(pcie, REXPCAP(PCI_EXP_SLTCAP), PCI_EXP_SLTCAP_PSN, 0); - - /* Set the completion timer timeout to the maximum 50ms. */ - rcar_rmw32(pcie, TLCTLR + 1, 0x3f, 50); - - /* Terminate list of capabilities (Next Capability Offset=0) */ - rcar_rmw32(pcie, RVCCAP(0), 0xfff00000, 0); - - /* Enable MSI */ - if (IS_ENABLED(CONFIG_PCI_MSI)) - rcar_pci_write_reg(pcie, 0x801f0000, PCIEMSITXR); - - /* Finish initialization - establish a PCI Express link */ - rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); - - /* This will timeout if we don't have a link. */ - err = rcar_pcie_wait_for_dl(pcie); - if (err) - return err; - - /* Enable INTx interrupts */ - rcar_rmw32(pcie, PCIEINTXR, 0, 0xF << 8); - - wmb(); - - return 0; -} - -static int rcar_pcie_phy_init_h1(struct rcar_pcie *pcie) -{ - /* Initialize the phy */ - phy_write_reg(pcie, 0, 0x42, 0x1, 0x0EC34191); - phy_write_reg(pcie, 1, 0x42, 0x1, 0x0EC34180); - phy_write_reg(pcie, 0, 0x43, 0x1, 0x00210188); - phy_write_reg(pcie, 1, 0x43, 0x1, 0x00210188); - phy_write_reg(pcie, 0, 0x44, 0x1, 0x015C0014); - phy_write_reg(pcie, 1, 0x44, 0x1, 0x015C0014); - phy_write_reg(pcie, 1, 0x4C, 0x1, 0x786174A0); - phy_write_reg(pcie, 1, 0x4D, 0x1, 0x048000BB); - phy_write_reg(pcie, 0, 0x51, 0x1, 0x079EC062); - phy_write_reg(pcie, 0, 0x52, 0x1, 0x20000000); - phy_write_reg(pcie, 1, 0x52, 0x1, 0x20000000); - phy_write_reg(pcie, 1, 0x56, 0x1, 0x00003806); - - phy_write_reg(pcie, 0, 0x60, 0x1, 0x004B03A5); - phy_write_reg(pcie, 0, 0x64, 0x1, 0x3F0F1F0F); - phy_write_reg(pcie, 0, 0x66, 0x1, 0x00008000); - - return 0; -} - -static int rcar_pcie_phy_init_gen2(struct rcar_pcie *pcie) -{ - /* - * These settings come from the R-Car Series, 2nd Generation User's - * Manual, section 50.3.1 (2) Initialization of the physical layer. - */ - rcar_pci_write_reg(pcie, 0x000f0030, GEN2_PCIEPHYADDR); - rcar_pci_write_reg(pcie, 0x00381203, GEN2_PCIEPHYDATA); - rcar_pci_write_reg(pcie, 0x00000001, GEN2_PCIEPHYCTRL); - rcar_pci_write_reg(pcie, 0x00000006, GEN2_PCIEPHYCTRL); - - rcar_pci_write_reg(pcie, 0x000f0054, GEN2_PCIEPHYADDR); - /* The following value is for DC connection, no termination resistor */ - rcar_pci_write_reg(pcie, 0x13802007, GEN2_PCIEPHYDATA); - rcar_pci_write_reg(pcie, 0x00000001, GEN2_PCIEPHYCTRL); - rcar_pci_write_reg(pcie, 0x00000006, GEN2_PCIEPHYCTRL); - - return 0; -} - -static int rcar_pcie_phy_init_gen3(struct rcar_pcie *pcie) -{ - int err; - - err = phy_init(pcie->phy); - if (err) - return err; - - err = phy_power_on(pcie->phy); - if (err) - phy_exit(pcie->phy); - - return err; -} - -static int rcar_msi_alloc(struct rcar_msi *chip) -{ - int msi; - - mutex_lock(&chip->lock); - - msi = find_first_zero_bit(chip->used, INT_PCI_MSI_NR); - if (msi < INT_PCI_MSI_NR) - set_bit(msi, chip->used); - else - msi = -ENOSPC; - - mutex_unlock(&chip->lock); - - return msi; -} - -static int rcar_msi_alloc_region(struct rcar_msi *chip, int no_irqs) -{ - int msi; - - mutex_lock(&chip->lock); - msi = bitmap_find_free_region(chip->used, INT_PCI_MSI_NR, - order_base_2(no_irqs)); - mutex_unlock(&chip->lock); - - return msi; -} - -static void rcar_msi_free(struct rcar_msi *chip, unsigned long irq) -{ - mutex_lock(&chip->lock); - clear_bit(irq, chip->used); - mutex_unlock(&chip->lock); -} - -static irqreturn_t rcar_pcie_msi_irq(int irq, void *data) -{ - struct rcar_pcie *pcie = data; - struct rcar_msi *msi = &pcie->msi; - struct device *dev = pcie->dev; - unsigned long reg; - - reg = rcar_pci_read_reg(pcie, PCIEMSIFR); - - /* MSI & INTx share an interrupt - we only handle MSI here */ - if (!reg) - return IRQ_NONE; - - while (reg) { - unsigned int index = find_first_bit(®, 32); - unsigned int irq; - - /* clear the interrupt */ - rcar_pci_write_reg(pcie, 1 << index, PCIEMSIFR); - - irq = irq_find_mapping(msi->domain, index); - if (irq) { - if (test_bit(index, msi->used)) - generic_handle_irq(irq); - else - dev_info(dev, "unhandled MSI\n"); - } else { - /* Unknown MSI, just clear it */ - dev_dbg(dev, "unexpected MSI\n"); - } - - /* see if there's any more pending in this vector */ - reg = rcar_pci_read_reg(pcie, PCIEMSIFR); - } - - return IRQ_HANDLED; -} - -static int rcar_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev, - struct msi_desc *desc) -{ - struct rcar_msi *msi = to_rcar_msi(chip); - struct rcar_pcie *pcie = container_of(chip, struct rcar_pcie, msi.chip); - struct msi_msg msg; - unsigned int irq; - int hwirq; - - hwirq = rcar_msi_alloc(msi); - if (hwirq < 0) - return hwirq; - - irq = irq_find_mapping(msi->domain, hwirq); - if (!irq) { - rcar_msi_free(msi, hwirq); - return -EINVAL; - } - - irq_set_msi_desc(irq, desc); - - msg.address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE; - msg.address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR); - msg.data = hwirq; - - pci_write_msi_msg(irq, &msg); - - return 0; -} - -static int rcar_msi_setup_irqs(struct msi_controller *chip, - struct pci_dev *pdev, int nvec, int type) -{ - struct rcar_pcie *pcie = container_of(chip, struct rcar_pcie, msi.chip); - struct rcar_msi *msi = to_rcar_msi(chip); - struct msi_desc *desc; - struct msi_msg msg; - unsigned int irq; - int hwirq; - int i; - - /* MSI-X interrupts are not supported */ - if (type == PCI_CAP_ID_MSIX) - return -EINVAL; - - WARN_ON(!list_is_singular(&pdev->dev.msi_list)); - desc = list_entry(pdev->dev.msi_list.next, struct msi_desc, list); - - hwirq = rcar_msi_alloc_region(msi, nvec); - if (hwirq < 0) - return -ENOSPC; - - irq = irq_find_mapping(msi->domain, hwirq); - if (!irq) - return -ENOSPC; - - for (i = 0; i < nvec; i++) { - /* - * irq_create_mapping() called from rcar_pcie_probe() pre- - * allocates descs, so there is no need to allocate descs here. - * We can therefore assume that if irq_find_mapping() above - * returns non-zero, then the descs are also successfully - * allocated. - */ - if (irq_set_msi_desc_off(irq, i, desc)) { - /* TODO: clear */ - return -EINVAL; - } - } - - desc->nvec_used = nvec; - desc->msi_attrib.multiple = order_base_2(nvec); - - msg.address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE; - msg.address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR); - msg.data = hwirq; - - pci_write_msi_msg(irq, &msg); - - return 0; -} - -static void rcar_msi_teardown_irq(struct msi_controller *chip, unsigned int irq) -{ - struct rcar_msi *msi = to_rcar_msi(chip); - struct irq_data *d = irq_get_irq_data(irq); - - rcar_msi_free(msi, d->hwirq); -} - -static struct irq_chip rcar_msi_irq_chip = { - .name = "R-Car 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 int rcar_msi_map(struct irq_domain *domain, unsigned int irq, - irq_hw_number_t hwirq) -{ - irq_set_chip_and_handler(irq, &rcar_msi_irq_chip, handle_simple_irq); - irq_set_chip_data(irq, domain->host_data); - - return 0; -} - -static const struct irq_domain_ops msi_domain_ops = { - .map = rcar_msi_map, -}; - -static void rcar_pcie_unmap_msi(struct rcar_pcie *pcie) -{ - struct rcar_msi *msi = &pcie->msi; - int i, irq; - - for (i = 0; i < INT_PCI_MSI_NR; i++) { - irq = irq_find_mapping(msi->domain, i); - if (irq > 0) - irq_dispose_mapping(irq); - } - - irq_domain_remove(msi->domain); -} - -static int rcar_pcie_enable_msi(struct rcar_pcie *pcie) -{ - struct device *dev = pcie->dev; - struct rcar_msi *msi = &pcie->msi; - unsigned long base; - int err, i; - - mutex_init(&msi->lock); - - msi->chip.dev = dev; - msi->chip.setup_irq = rcar_msi_setup_irq; - msi->chip.setup_irqs = rcar_msi_setup_irqs; - msi->chip.teardown_irq = rcar_msi_teardown_irq; - - msi->domain = irq_domain_add_linear(dev->of_node, INT_PCI_MSI_NR, - &msi_domain_ops, &msi->chip); - if (!msi->domain) { - dev_err(dev, "failed to create IRQ domain\n"); - return -ENOMEM; - } - - for (i = 0; i < INT_PCI_MSI_NR; i++) - irq_create_mapping(msi->domain, i); - - /* Two irqs are for MSI, but they are also used for non-MSI irqs */ - err = devm_request_irq(dev, msi->irq1, rcar_pcie_msi_irq, - IRQF_SHARED | IRQF_NO_THREAD, - rcar_msi_irq_chip.name, pcie); - if (err < 0) { - dev_err(dev, "failed to request IRQ: %d\n", err); - goto err; - } - - err = devm_request_irq(dev, msi->irq2, rcar_pcie_msi_irq, - IRQF_SHARED | IRQF_NO_THREAD, - rcar_msi_irq_chip.name, pcie); - if (err < 0) { - dev_err(dev, "failed to request IRQ: %d\n", err); - goto err; - } - - /* setup MSI data target */ - msi->pages = __get_free_pages(GFP_KERNEL, 0); - base = virt_to_phys((void *)msi->pages); - - rcar_pci_write_reg(pcie, base | MSIFE, PCIEMSIALR); - rcar_pci_write_reg(pcie, 0, PCIEMSIAUR); - - /* enable all MSI interrupts */ - rcar_pci_write_reg(pcie, 0xffffffff, PCIEMSIIER); - - return 0; - -err: - rcar_pcie_unmap_msi(pcie); - return err; -} - -static void rcar_pcie_teardown_msi(struct rcar_pcie *pcie) -{ - struct rcar_msi *msi = &pcie->msi; - - /* Disable all MSI interrupts */ - rcar_pci_write_reg(pcie, 0, PCIEMSIIER); - - /* Disable address decoding of the MSI interrupt, MSIFE */ - rcar_pci_write_reg(pcie, 0, PCIEMSIALR); - - free_pages(msi->pages, 0); - - rcar_pcie_unmap_msi(pcie); -} - -static int rcar_pcie_get_resources(struct rcar_pcie *pcie) -{ - struct device *dev = pcie->dev; - struct resource res; - int err, i; - - pcie->phy = devm_phy_optional_get(dev, "pcie"); - if (IS_ERR(pcie->phy)) - return PTR_ERR(pcie->phy); - - err = of_address_to_resource(dev->of_node, 0, &res); - if (err) - return err; - - pcie->base = devm_ioremap_resource(dev, &res); - if (IS_ERR(pcie->base)) - return PTR_ERR(pcie->base); - - pcie->bus_clk = devm_clk_get(dev, "pcie_bus"); - if (IS_ERR(pcie->bus_clk)) { - dev_err(dev, "cannot get pcie bus clock\n"); - return PTR_ERR(pcie->bus_clk); - } - - i = irq_of_parse_and_map(dev->of_node, 0); - if (!i) { - dev_err(dev, "cannot get platform resources for msi interrupt\n"); - err = -ENOENT; - goto err_irq1; - } - pcie->msi.irq1 = i; - - i = irq_of_parse_and_map(dev->of_node, 1); - if (!i) { - dev_err(dev, "cannot get platform resources for msi interrupt\n"); - err = -ENOENT; - goto err_irq2; - } - pcie->msi.irq2 = i; - - return 0; - -err_irq2: - irq_dispose_mapping(pcie->msi.irq1); -err_irq1: - return err; -} - -static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie, - struct of_pci_range *range, - int *index) -{ - u64 restype = range->flags; - u64 cpu_addr = range->cpu_addr; - u64 cpu_end = range->cpu_addr + range->size; - u64 pci_addr = range->pci_addr; - u32 flags = LAM_64BIT | LAR_ENABLE; - u64 mask; - u64 size; - int idx = *index; - - if (restype & IORESOURCE_PREFETCH) - flags |= LAM_PREFETCH; - - /* - * If the size of the range is larger than the alignment of the start - * address, we have to use multiple entries to perform the mapping. - */ - if (cpu_addr > 0) { - unsigned long nr_zeros = __ffs64(cpu_addr); - u64 alignment = 1ULL << nr_zeros; - - size = min(range->size, alignment); - } else { - size = range->size; - } - /* Hardware supports max 4GiB inbound region */ - size = min(size, 1ULL << 32); - - mask = roundup_pow_of_two(size) - 1; - mask &= ~0xf; - - while (cpu_addr < cpu_end) { - /* - * Set up 64-bit inbound regions as the range parser doesn't - * distinguish between 32 and 64-bit types. - */ + if (host) rcar_pci_write_reg(pcie, lower_32_bits(pci_addr), PCIEPRAR(idx)); - rcar_pci_write_reg(pcie, lower_32_bits(cpu_addr), PCIELAR(idx)); - rcar_pci_write_reg(pcie, lower_32_bits(mask) | flags, - PCIELAMR(idx)); + rcar_pci_write_reg(pcie, lower_32_bits(cpu_addr), PCIELAR(idx)); + rcar_pci_write_reg(pcie, flags, PCIELAMR(idx)); + if (host) rcar_pci_write_reg(pcie, upper_32_bits(pci_addr), PCIEPRAR(idx + 1)); - rcar_pci_write_reg(pcie, upper_32_bits(cpu_addr), - PCIELAR(idx + 1)); - rcar_pci_write_reg(pcie, 0, PCIELAMR(idx + 1)); - - pci_addr += size; - cpu_addr += size; - idx += 2; - - if (idx > MAX_NR_INBOUND_MAPS) { - dev_err(pcie->dev, "Failed to map inbound regions!\n"); - return -EINVAL; - } - } - *index = idx; - - return 0; -} - -static int rcar_pcie_parse_map_dma_ranges(struct rcar_pcie *pcie, - struct device_node *np) -{ - struct of_pci_range range; - struct of_pci_range_parser parser; - int index = 0; - int err; - - if (of_pci_dma_range_parser_init(&parser, np)) - return -EINVAL; - - /* Get the dma-ranges from DT */ - for_each_of_pci_range(&parser, &range) { - u64 end = range.cpu_addr + range.size - 1; - - dev_dbg(pcie->dev, "0x%08x 0x%016llx..0x%016llx -> 0x%016llx\n", - range.flags, range.cpu_addr, end, range.pci_addr); - - err = rcar_pcie_inbound_ranges(pcie, &range, &index); - if (err) - return err; - } - - return 0; -} - -static const struct of_device_id rcar_pcie_of_match[] = { - { .compatible = "renesas,pcie-r8a7779", - .data = rcar_pcie_phy_init_h1 }, - { .compatible = "renesas,pcie-r8a7790", - .data = rcar_pcie_phy_init_gen2 }, - { .compatible = "renesas,pcie-r8a7791", - .data = rcar_pcie_phy_init_gen2 }, - { .compatible = "renesas,pcie-rcar-gen2", - .data = rcar_pcie_phy_init_gen2 }, - { .compatible = "renesas,pcie-r8a7795", - .data = rcar_pcie_phy_init_gen3 }, - { .compatible = "renesas,pcie-rcar-gen3", - .data = rcar_pcie_phy_init_gen3 }, - {}, -}; - -static int rcar_pcie_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct rcar_pcie *pcie; - unsigned int data; - int err; - int (*phy_init_fn)(struct rcar_pcie *); - struct pci_host_bridge *bridge; - - bridge = pci_alloc_host_bridge(sizeof(*pcie)); - if (!bridge) - return -ENOMEM; - - pcie = pci_host_bridge_priv(bridge); - - pcie->dev = dev; - - err = pci_parse_request_of_pci_ranges(dev, &pcie->resources, NULL); - if (err) - goto err_free_bridge; - - pm_runtime_enable(pcie->dev); - err = pm_runtime_get_sync(pcie->dev); - if (err < 0) { - dev_err(pcie->dev, "pm_runtime_get_sync failed\n"); - goto err_pm_disable; - } - - err = rcar_pcie_get_resources(pcie); - if (err < 0) { - dev_err(dev, "failed to request resources: %d\n", err); - goto err_pm_put; - } - - err = clk_prepare_enable(pcie->bus_clk); - if (err) { - dev_err(dev, "failed to enable bus clock: %d\n", err); - goto err_unmap_msi_irqs; - } - - err = rcar_pcie_parse_map_dma_ranges(pcie, dev->of_node); - if (err) - goto err_clk_disable; - - phy_init_fn = of_device_get_match_data(dev); - err = phy_init_fn(pcie); - if (err) { - dev_err(dev, "failed to init PCIe PHY\n"); - goto err_clk_disable; - } - - /* Failure to get a link might just be that no cards are inserted */ - if (rcar_pcie_hw_init(pcie)) { - dev_info(dev, "PCIe link down\n"); - err = -ENODEV; - goto err_phy_shutdown; - } - - data = rcar_pci_read_reg(pcie, MACSR); - dev_info(dev, "PCIe x%d: link up\n", (data >> 20) & 0x3f); - - if (IS_ENABLED(CONFIG_PCI_MSI)) { - err = rcar_pcie_enable_msi(pcie); - if (err < 0) { - dev_err(dev, - "failed to enable MSI support: %d\n", - err); - goto err_phy_shutdown; - } - } - - err = rcar_pcie_enable(pcie); - if (err) - goto err_msi_teardown; - - return 0; - -err_msi_teardown: - if (IS_ENABLED(CONFIG_PCI_MSI)) - rcar_pcie_teardown_msi(pcie); - -err_phy_shutdown: - if (pcie->phy) { - phy_power_off(pcie->phy); - phy_exit(pcie->phy); - } - -err_clk_disable: - clk_disable_unprepare(pcie->bus_clk); - -err_unmap_msi_irqs: - irq_dispose_mapping(pcie->msi.irq2); - irq_dispose_mapping(pcie->msi.irq1); - -err_pm_put: - pm_runtime_put(dev); - -err_pm_disable: - pm_runtime_disable(dev); - pci_free_resource_list(&pcie->resources); - -err_free_bridge: - pci_free_host_bridge(bridge); - - return err; + rcar_pci_write_reg(pcie, upper_32_bits(cpu_addr), PCIELAR(idx + 1)); + rcar_pci_write_reg(pcie, 0, PCIELAMR(idx + 1)); } - -static struct platform_driver rcar_pcie_driver = { - .driver = { - .name = "rcar-pcie", - .of_match_table = rcar_pcie_of_match, - .suppress_bind_attrs = true, - }, - .probe = rcar_pcie_probe, -}; -builtin_platform_driver(rcar_pcie_driver); diff --git a/drivers/pci/controller/pcie-rcar.h b/drivers/pci/controller/pcie-rcar.h new file mode 100644 index 000000000000..6799f81392fc --- /dev/null +++ b/drivers/pci/controller/pcie-rcar.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCIe driver for Renesas R-Car SoCs + * Copyright (C) 2014-2020 Renesas Electronics Europe Ltd + * + * Author: Phil Edworthy <phil.edworthy@renesas.com> + */ + +#ifndef _PCIE_RCAR_H +#define _PCIE_RCAR_H + +#define PCIECAR 0x000010 +#define PCIECCTLR 0x000018 +#define PCIECCTLR_CCIE BIT(31) +#define TYPE0 (0 << 8) +#define TYPE1 BIT(8) +#define PCIECDR 0x000020 +#define PCIEMSR 0x000028 +#define PCIEINTXR 0x000400 +#define ASTINTX BIT(16) +#define PCIEPHYSR 0x0007f0 +#define PHYRDY BIT(0) +#define PCIEMSITXR 0x000840 + +/* Transfer control */ +#define PCIETCTLR 0x02000 +#define DL_DOWN BIT(3) +#define CFINIT BIT(0) +#define PCIETSTR 0x02004 +#define DATA_LINK_ACTIVE BIT(0) +#define PCIEERRFR 0x02020 +#define UNSUPPORTED_REQUEST BIT(4) +#define PCIEMSIFR 0x02044 +#define PCIEMSIALR 0x02048 +#define MSIFE BIT(0) +#define PCIEMSIAUR 0x0204c +#define PCIEMSIIER 0x02050 + +/* root port address */ +#define PCIEPRAR(x) (0x02080 + ((x) * 0x4)) + +/* local address reg & mask */ +#define PCIELAR(x) (0x02200 + ((x) * 0x20)) +#define PCIELAMR(x) (0x02208 + ((x) * 0x20)) +#define LAM_PREFETCH BIT(3) +#define LAM_64BIT BIT(2) +#define LAR_ENABLE BIT(1) + +/* PCIe address reg & mask */ +#define PCIEPALR(x) (0x03400 + ((x) * 0x20)) +#define PCIEPAUR(x) (0x03404 + ((x) * 0x20)) +#define PCIEPAMR(x) (0x03408 + ((x) * 0x20)) +#define PCIEPTCTLR(x) (0x0340c + ((x) * 0x20)) +#define PAR_ENABLE BIT(31) +#define IO_SPACE BIT(8) + +/* Configuration */ +#define PCICONF(x) (0x010000 + ((x) * 0x4)) +#define INTDIS BIT(10) +#define PMCAP(x) (0x010040 + ((x) * 0x4)) +#define MSICAP(x) (0x010050 + ((x) * 0x4)) +#define MSICAP0_MSIE BIT(16) +#define MSICAP0_MMESCAP_OFFSET 17 +#define MSICAP0_MMESE_OFFSET 20 +#define MSICAP0_MMESE_MASK GENMASK(22, 20) +#define EXPCAP(x) (0x010070 + ((x) * 0x4)) +#define VCCAP(x) (0x010100 + ((x) * 0x4)) + +/* link layer */ +#define IDSETR0 0x011000 +#define IDSETR1 0x011004 +#define SUBIDSETR 0x011024 +#define TLCTLR 0x011048 +#define MACSR 0x011054 +#define SPCHGFIN BIT(4) +#define SPCHGFAIL BIT(6) +#define SPCHGSUC BIT(7) +#define LINK_SPEED (0xf << 16) +#define LINK_SPEED_2_5GTS (1 << 16) +#define LINK_SPEED_5_0GTS (2 << 16) +#define MACCTLR 0x011058 +#define MACCTLR_NFTS_MASK GENMASK(23, 16) /* The name is from SH7786 */ +#define SPEED_CHANGE BIT(24) +#define SCRAMBLE_DISABLE BIT(27) +#define LTSMDIS BIT(31) +#define MACCTLR_INIT_VAL (LTSMDIS | MACCTLR_NFTS_MASK) +#define PMSR 0x01105c +#define L1FAEG BIT(31) +#define PMEL1RX BIT(23) +#define PMSTATE GENMASK(18, 16) +#define PMSTATE_L1 (3 << 16) +#define PMCTLR 0x011060 +#define L1IATN BIT(31) + +#define MACS2R 0x011078 +#define MACCGSPSETR 0x011084 +#define SPCNGRSN BIT(31) + +/* R-Car H1 PHY */ +#define H1_PCIEPHYADRR 0x04000c +#define WRITE_CMD BIT(16) +#define PHY_ACK BIT(24) +#define RATE_POS 12 +#define LANE_POS 8 +#define ADR_POS 0 +#define H1_PCIEPHYDOUTR 0x040014 + +/* R-Car Gen2 PHY */ +#define GEN2_PCIEPHYADDR 0x780 +#define GEN2_PCIEPHYDATA 0x784 +#define GEN2_PCIEPHYCTRL 0x78c + +#define INT_PCI_MSI_NR 32 + +#define RCONF(x) (PCICONF(0) + (x)) +#define RPMCAP(x) (PMCAP(0) + (x)) +#define REXPCAP(x) (EXPCAP(0) + (x)) +#define RVCCAP(x) (VCCAP(0) + (x)) + +#define PCIE_CONF_BUS(b) (((b) & 0xff) << 24) +#define PCIE_CONF_DEV(d) (((d) & 0x1f) << 19) +#define PCIE_CONF_FUNC(f) (((f) & 0x7) << 16) + +#define RCAR_PCI_MAX_RESOURCES 4 +#define MAX_NR_INBOUND_MAPS 6 + +struct rcar_pcie { + struct device *dev; + void __iomem *base; +}; + +enum { + RCAR_PCI_ACCESS_READ, + RCAR_PCI_ACCESS_WRITE, +}; + +void rcar_pci_write_reg(struct rcar_pcie *pcie, u32 val, unsigned int reg); +u32 rcar_pci_read_reg(struct rcar_pcie *pcie, unsigned int reg); +void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data); +int rcar_pcie_wait_for_phyrdy(struct rcar_pcie *pcie); +int rcar_pcie_wait_for_dl(struct rcar_pcie *pcie); +void rcar_pcie_set_outbound(struct rcar_pcie *pcie, int win, + struct resource_entry *window); +void rcar_pcie_set_inbound(struct rcar_pcie *pcie, u64 cpu_addr, + u64 pci_addr, u64 flags, int idx, bool host); + +#endif diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index b8163c56a142..799461335762 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -10,31 +10,40 @@ #include <linux/configfs.h> #include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/iopoll.h> #include <linux/kernel.h> +#include <linux/irq.h> #include <linux/of.h> #include <linux/pci-epc.h> #include <linux/platform_device.h> #include <linux/pci-epf.h> #include <linux/sizes.h> +#include <linux/workqueue.h> #include "pcie-rockchip.h" /** * struct rockchip_pcie_ep - private data for PCIe endpoint controller driver * @rockchip: Rockchip PCIe controller + * @epc: PCI EPC device * @max_regions: maximum number of regions supported by hardware * @ob_region_map: bitmask of mapped outbound regions * @ob_addr: base addresses in the AXI bus where the outbound regions start - * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ + * @irq_phys_addr: base address on the AXI bus where the MSI/INTX IRQ * dedicated outbound regions is mapped. * @irq_cpu_addr: base address in the CPU space where a write access triggers - * the sending of a memory write (MSI) / normal message (legacy + * the sending of a memory write (MSI) / normal message (INTX * IRQ) TLP through the PCIe bus. - * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ + * @irq_pci_addr: used to save the current mapping of the MSI/INTX IRQ * dedicated outbound region. * @irq_pci_fn: the latest PCI function that has updated the mapping of - * the MSI/legacy IRQ dedicated outbound region. - * @irq_pending: bitmask of asserted legacy IRQs. + * the MSI/INTX IRQ dedicated outbound region. + * @irq_pending: bitmask of asserted INTX IRQs. + * @perst_irq: IRQ used for the PERST# signal. + * @perst_asserted: True if the PERST# signal was asserted. + * @link_up: True if the PCI link is up. + * @link_training: Work item to execute PCI link training. */ struct rockchip_pcie_ep { struct rockchip_pcie rockchip; @@ -47,6 +56,10 @@ struct rockchip_pcie_ep { u64 irq_pci_addr; u8 irq_pci_fn; u8 irq_pending; + int perst_irq; + bool perst_asserted; + bool link_up; + struct delayed_work link_training; }; static void rockchip_pcie_clear_ep_ob_atu(struct rockchip_pcie *rockchip, @@ -60,84 +73,61 @@ static void rockchip_pcie_clear_ep_ob_atu(struct rockchip_pcie *rockchip, ROCKCHIP_PCIE_AT_OB_REGION_DESC0(region)); rockchip_pcie_write(rockchip, 0, ROCKCHIP_PCIE_AT_OB_REGION_DESC1(region)); - rockchip_pcie_write(rockchip, 0, - ROCKCHIP_PCIE_AT_OB_REGION_CPU_ADDR0(region)); - rockchip_pcie_write(rockchip, 0, - ROCKCHIP_PCIE_AT_OB_REGION_CPU_ADDR1(region)); +} + +static int rockchip_pcie_ep_ob_atu_num_bits(struct rockchip_pcie *rockchip, + u64 pci_addr, size_t size) +{ + int num_pass_bits = fls64(pci_addr ^ (pci_addr + size - 1)); + + return clamp(num_pass_bits, + ROCKCHIP_PCIE_AT_MIN_NUM_BITS, + ROCKCHIP_PCIE_AT_MAX_NUM_BITS); } static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn, - u32 r, u32 type, u64 cpu_addr, - u64 pci_addr, size_t size) + u32 r, u64 cpu_addr, u64 pci_addr, + size_t size) { - u64 sz = 1ULL << fls64(size - 1); - int num_pass_bits = ilog2(sz); - u32 addr0, addr1, desc0, desc1; - bool is_nor_msg = (type == AXI_WRAPPER_NOR_MSG); - - /* The minimal region size is 1MB */ - if (num_pass_bits < 8) - num_pass_bits = 8; - - cpu_addr -= rockchip->mem_res->start; - addr0 = ((is_nor_msg ? 0x10 : (num_pass_bits - 1)) & - PCIE_CORE_OB_REGION_ADDR0_NUM_BITS) | - (lower_32_bits(cpu_addr) & PCIE_CORE_OB_REGION_ADDR0_LO_ADDR); - addr1 = upper_32_bits(is_nor_msg ? cpu_addr : pci_addr); - desc0 = ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN(fn) | type; - desc1 = 0; - - if (is_nor_msg) { - rockchip_pcie_write(rockchip, 0, - ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(r)); - rockchip_pcie_write(rockchip, 0, - ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR1(r)); - rockchip_pcie_write(rockchip, desc0, - ROCKCHIP_PCIE_AT_OB_REGION_DESC0(r)); - rockchip_pcie_write(rockchip, desc1, - ROCKCHIP_PCIE_AT_OB_REGION_DESC1(r)); - } else { - /* PCI bus address region */ - rockchip_pcie_write(rockchip, addr0, - ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(r)); - rockchip_pcie_write(rockchip, addr1, - ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR1(r)); - rockchip_pcie_write(rockchip, desc0, - ROCKCHIP_PCIE_AT_OB_REGION_DESC0(r)); - rockchip_pcie_write(rockchip, desc1, - ROCKCHIP_PCIE_AT_OB_REGION_DESC1(r)); - - addr0 = - ((num_pass_bits - 1) & PCIE_CORE_OB_REGION_ADDR0_NUM_BITS) | - (lower_32_bits(cpu_addr) & - PCIE_CORE_OB_REGION_ADDR0_LO_ADDR); - addr1 = upper_32_bits(cpu_addr); - } + int num_pass_bits; + u32 addr0, addr1, desc0; + + num_pass_bits = rockchip_pcie_ep_ob_atu_num_bits(rockchip, + pci_addr, size); + + addr0 = ((num_pass_bits - 1) & PCIE_CORE_OB_REGION_ADDR0_NUM_BITS) | + (lower_32_bits(pci_addr) & PCIE_CORE_OB_REGION_ADDR0_LO_ADDR); + addr1 = upper_32_bits(pci_addr); + desc0 = ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN(fn) | AXI_WRAPPER_MEM_WRITE; - /* CPU bus address region */ + /* PCI bus address region */ rockchip_pcie_write(rockchip, addr0, - ROCKCHIP_PCIE_AT_OB_REGION_CPU_ADDR0(r)); + ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(r)); rockchip_pcie_write(rockchip, addr1, - ROCKCHIP_PCIE_AT_OB_REGION_CPU_ADDR1(r)); + ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR1(r)); + rockchip_pcie_write(rockchip, desc0, + ROCKCHIP_PCIE_AT_OB_REGION_DESC0(r)); + rockchip_pcie_write(rockchip, 0, + ROCKCHIP_PCIE_AT_OB_REGION_DESC1(r)); } -static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, +static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_header *hdr) { + u32 reg; struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; /* All functions share the same vendor ID with function 0 */ if (fn == 0) { - u32 vid_regs = (hdr->vendorid & GENMASK(15, 0)) | - (hdr->subsys_vendor_id & GENMASK(31, 16)) << 16; - - rockchip_pcie_write(rockchip, vid_regs, + rockchip_pcie_write(rockchip, + hdr->vendorid | hdr->subsys_vendor_id << 16, PCIE_CORE_CONFIG_VENDOR); } - rockchip_pcie_write(rockchip, hdr->deviceid << 16, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + PCI_VENDOR_ID); + reg = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_DID_VID); + reg = (reg & 0xFFFF) | (hdr->deviceid << 16); + rockchip_pcie_write(rockchip, reg, PCIE_EP_CONFIG_DID_VID); rockchip_pcie_write(rockchip, hdr->revid | @@ -158,7 +148,7 @@ static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, return 0; } -static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, +static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_bar *epf_bar) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); @@ -183,7 +173,7 @@ static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, ctrl = ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_IO_32BITS; } else { bool is_prefetch = !!(flags & PCI_BASE_ADDRESS_MEM_PREFETCH); - bool is_64bits = sz > SZ_2G; + bool is_64bits = !!(flags & PCI_BASE_ADDRESS_MEM_TYPE_64); if (is_64bits && (bar & 1)) return -EINVAL; @@ -226,7 +216,7 @@ static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, return 0; } -static void rockchip_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, +static void rockchip_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, struct pci_epf_bar *epf_bar) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); @@ -255,27 +245,45 @@ static void rockchip_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar)); } -static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, +static inline u32 rockchip_ob_region(phys_addr_t addr) +{ + return (addr >> ilog2(SZ_1M)) & 0x1f; +} + +static u64 rockchip_pcie_ep_align_addr(struct pci_epc *epc, u64 pci_addr, + size_t *pci_size, size_t *addr_offset) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + size_t size = *pci_size; + u64 offset, mask; + int num_bits; + + num_bits = rockchip_pcie_ep_ob_atu_num_bits(&ep->rockchip, + pci_addr, size); + mask = (1ULL << num_bits) - 1; + + offset = pci_addr & mask; + if (size + offset > SZ_1M) + size = SZ_1M - offset; + + *pci_size = ALIGN(offset + size, ROCKCHIP_PCIE_AT_SIZE_ALIGN); + *addr_offset = offset; + + return pci_addr & ~mask; +} + +static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr, u64 pci_addr, size_t size) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *pcie = &ep->rockchip; - u32 r; + u32 r = rockchip_ob_region(addr); - r = find_first_zero_bit(&ep->ob_region_map, - sizeof(ep->ob_region_map) * BITS_PER_LONG); - /* - * Region 0 is reserved for configuration space and shouldn't - * be used elsewhere per TRM, so leave it out. - */ - if (r >= ep->max_regions - 1) { - dev_err(&epc->dev, "no free outbound region\n"); - return -EINVAL; - } + if (test_bit(r, &ep->ob_region_map)) + return -EBUSY; - rockchip_pcie_prog_ep_ob_atu(pcie, fn, r, AXI_WRAPPER_MEM_WRITE, addr, - pci_addr, size); + rockchip_pcie_prog_ep_ob_atu(pcie, fn, r, addr, pci_addr, size); set_bit(r, &ep->ob_region_map); ep->ob_addr[r] = addr; @@ -283,22 +291,14 @@ static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, return 0; } -static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, +static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, phys_addr_t addr) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; - u32 r; - - for (r = 0; r < ep->max_regions - 1; r++) - if (ep->ob_addr[r] == addr) - break; + u32 r = rockchip_ob_region(addr); - /* - * Region 0 is reserved for configuration space and shouldn't - * be used elsewhere per TRM, so leave it out. - */ - if (r == ep->max_regions - 1) + if (addr != ep->ob_addr[r] || !test_bit(r, &ep->ob_region_map)) return; rockchip_pcie_clear_ep_ob_atu(rockchip, r); @@ -307,20 +307,21 @@ static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, clear_bit(r, &ep->ob_region_map); } -static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, - u8 multi_msg_cap) +static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, + u8 nr_irqs) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags; + u8 mmc = order_base_2(nr_irqs); + u32 flags; flags = rockchip_pcie_read(rockchip, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK; flags |= - ((multi_msg_cap << 1) << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) | - PCI_MSI_FLAGS_64BIT; + (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, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + @@ -328,11 +329,11 @@ static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, return 0; } -static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) +static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags; + u32 flags; flags = rockchip_pcie_read(rockchip, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + @@ -340,57 +341,34 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn) 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, - u8 intx, bool is_asserted) + u8 intx, bool do_assert) { struct rockchip_pcie *rockchip = &ep->rockchip; - u32 r = ep->max_regions - 1; - u32 offset; - u16 status; - u8 msg_code; - - if (unlikely(ep->irq_pci_addr != ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR || - ep->irq_pci_fn != fn)) { - rockchip_pcie_prog_ep_ob_atu(rockchip, fn, r, - AXI_WRAPPER_NOR_MSG, - ep->irq_phys_addr, 0, 0); - ep->irq_pci_addr = ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR; - ep->irq_pci_fn = fn; - } intx &= 3; - if (is_asserted) { + + if (do_assert) { ep->irq_pending |= BIT(intx); - msg_code = ROCKCHIP_PCIE_MSG_CODE_ASSERT_INTA + intx; + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_ASSERT | + PCIE_CLIENT_INT_PEND_ST_PEND, + PCIE_CLIENT_LEGACY_INT_CTRL); } else { ep->irq_pending &= ~BIT(intx); - msg_code = ROCKCHIP_PCIE_MSG_CODE_DEASSERT_INTA + intx; - } - - status = rockchip_pcie_read(rockchip, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + - ROCKCHIP_PCIE_EP_CMD_STATUS); - status &= ROCKCHIP_PCIE_EP_CMD_STATUS_IS; - - if ((status != 0) ^ (ep->irq_pending != 0)) { - status ^= ROCKCHIP_PCIE_EP_CMD_STATUS_IS; - rockchip_pcie_write(rockchip, status, - ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + - ROCKCHIP_PCIE_EP_CMD_STATUS); + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_DEASSERT | + PCIE_CLIENT_INT_PEND_ST_NORMAL, + PCIE_CLIENT_LEGACY_INT_CTRL); } - - offset = - ROCKCHIP_PCIE_MSG_ROUTING(ROCKCHIP_PCIE_MSG_ROUTING_LOCAL_INTX) | - ROCKCHIP_PCIE_MSG_CODE(msg_code) | ROCKCHIP_PCIE_MSG_NO_DATA; - writel(0, ep->irq_cpu_addr + offset); } -static int rockchip_pcie_ep_send_legacy_irq(struct rockchip_pcie_ep *ep, u8 fn, - u8 intx) +static int rockchip_pcie_ep_send_intx_irq(struct rockchip_pcie_ep *ep, u8 fn, + u8 intx) { u16 cmd; @@ -416,9 +394,11 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, u8 interrupt_num) { struct rockchip_pcie *rockchip = &ep->rockchip; - u16 flags, mme, data, data_mask; + u32 flags, mme, data, data_mask; + size_t irq_pci_size, offset; + u64 irq_pci_addr; u8 msi_count; - u64 pci_addr, pci_addr_mask = 0xff; + u64 pci_addr; /* Check MSI enable bit */ flags = rockchip_pcie_read(&ep->rockchip, @@ -452,34 +432,35 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + ROCKCHIP_PCIE_EP_MSI_CTRL_REG + PCI_MSI_ADDRESS_LO); - pci_addr &= GENMASK_ULL(63, 2); /* Set the outbound region if needed. */ - if (unlikely(ep->irq_pci_addr != (pci_addr & ~pci_addr_mask) || + irq_pci_size = ~PCIE_ADDR_MASK + 1; + irq_pci_addr = rockchip_pcie_ep_align_addr(ep->epc, + pci_addr & PCIE_ADDR_MASK, + &irq_pci_size, &offset); + if (unlikely(ep->irq_pci_addr != irq_pci_addr || ep->irq_pci_fn != fn)) { - rockchip_pcie_prog_ep_ob_atu(rockchip, fn, ep->max_regions - 1, - AXI_WRAPPER_MEM_WRITE, - ep->irq_phys_addr, - pci_addr & ~pci_addr_mask, - pci_addr_mask + 1); - ep->irq_pci_addr = (pci_addr & ~pci_addr_mask); + rockchip_pcie_prog_ep_ob_atu(rockchip, fn, + rockchip_ob_region(ep->irq_phys_addr), + ep->irq_phys_addr, + irq_pci_addr, irq_pci_size); + ep->irq_pci_addr = irq_pci_addr; ep->irq_pci_fn = fn; } - writew(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask)); + writew(data, ep->irq_cpu_addr + offset + (pci_addr & ~PCIE_ADDR_MASK)); return 0; } -static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, - enum pci_epc_irq_type type, - u16 interrupt_num) +static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, + unsigned int type, u16 interrupt_num) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); switch (type) { - case PCI_EPC_IRQ_LEGACY: - return rockchip_pcie_ep_send_legacy_irq(ep, fn, 0); - case PCI_EPC_IRQ_MSI: + case PCI_IRQ_INTX: + return rockchip_pcie_ep_send_intx_irq(ep, fn, 0); + case PCI_IRQ_MSI: return rockchip_pcie_ep_send_msi_irq(ep, fn, interrupt_num); default: return -EINVAL; @@ -499,26 +480,247 @@ static int rockchip_pcie_ep_start(struct pci_epc *epc) rockchip_pcie_write(rockchip, cfg, PCIE_CORE_PHY_FUNC_CFG); - list_for_each_entry(epf, &epc->pci_epf, list) - pci_epf_linkup(epf); + if (rockchip->perst_gpio) + enable_irq(ep->perst_irq); + + /* Enable configuration and start link training */ + rockchip_pcie_write(rockchip, + PCIE_CLIENT_LINK_TRAIN_ENABLE | + PCIE_CLIENT_CONF_ENABLE, + PCIE_CLIENT_CONFIG); + + if (!rockchip->perst_gpio) + schedule_delayed_work(&ep->link_training, 0); return 0; } +static void rockchip_pcie_ep_stop(struct pci_epc *epc) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + + if (rockchip->perst_gpio) { + ep->perst_asserted = true; + disable_irq(ep->perst_irq); + } + + cancel_delayed_work_sync(&ep->link_training); + + /* Stop link training and disable configuration */ + rockchip_pcie_write(rockchip, + PCIE_CLIENT_CONF_DISABLE | + PCIE_CLIENT_LINK_TRAIN_DISABLE, + PCIE_CLIENT_CONFIG); +} + +static void rockchip_pcie_ep_retrain_link(struct rockchip_pcie *rockchip) +{ + u32 status; + + status = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE + PCI_EXP_LNKCTL); + status |= PCI_EXP_LNKCTL_RL; + rockchip_pcie_write(rockchip, status, PCIE_EP_CONFIG_BASE + PCI_EXP_LNKCTL); +} + +static bool rockchip_pcie_ep_link_up(struct rockchip_pcie *rockchip) +{ + u32 val = rockchip_pcie_read(rockchip, PCIE_CLIENT_BASIC_STATUS1); + + return PCIE_LINK_UP(val); +} + +static void rockchip_pcie_ep_link_training(struct work_struct *work) +{ + struct rockchip_pcie_ep *ep = + container_of(work, struct rockchip_pcie_ep, link_training.work); + struct rockchip_pcie *rockchip = &ep->rockchip; + struct device *dev = rockchip->dev; + u32 val; + int ret; + + /* Enable Gen1 training and wait for its completion */ + ret = readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL, + val, PCIE_LINK_TRAINING_DONE(val), 50, + LINK_TRAIN_TIMEOUT); + if (ret) + goto again; + + /* Make sure that the link is up */ + ret = readl_poll_timeout(rockchip->apb_base + PCIE_CLIENT_BASIC_STATUS1, + val, PCIE_LINK_UP(val), 50, + LINK_TRAIN_TIMEOUT); + if (ret) + goto again; + + /* + * Check the current speed: if gen2 speed was requested and we are not + * at gen2 speed yet, retrain again for gen2. + */ + val = rockchip_pcie_read(rockchip, PCIE_CORE_CTRL); + if (!PCIE_LINK_IS_GEN2(val) && rockchip->link_gen == 2) { + /* Enable retrain for gen2 */ + rockchip_pcie_ep_retrain_link(rockchip); + readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL, + val, PCIE_LINK_IS_GEN2(val), 50, + LINK_TRAIN_TIMEOUT); + } + + /* Check again that the link is up */ + if (!rockchip_pcie_ep_link_up(rockchip)) + goto again; + + /* + * If PERST# was asserted while polling the link, do not notify + * the function. + */ + if (ep->perst_asserted) + return; + + val = rockchip_pcie_read(rockchip, PCIE_CLIENT_BASIC_STATUS0); + dev_info(dev, + "link up (negotiated speed: %sGT/s, width: x%lu)\n", + (val & PCIE_CLIENT_NEG_LINK_SPEED) ? "5" : "2.5", + ((val & PCIE_CLIENT_NEG_LINK_WIDTH_MASK) >> + PCIE_CLIENT_NEG_LINK_WIDTH_SHIFT) << 1); + + /* Notify the function */ + pci_epc_linkup(ep->epc); + ep->link_up = true; + + return; + +again: + schedule_delayed_work(&ep->link_training, msecs_to_jiffies(5)); +} + +static void rockchip_pcie_ep_perst_assert(struct rockchip_pcie_ep *ep) +{ + struct rockchip_pcie *rockchip = &ep->rockchip; + + dev_dbg(rockchip->dev, "PERST# asserted, link down\n"); + + if (ep->perst_asserted) + return; + + ep->perst_asserted = true; + + cancel_delayed_work_sync(&ep->link_training); + + if (ep->link_up) { + pci_epc_linkdown(ep->epc); + ep->link_up = false; + } +} + +static void rockchip_pcie_ep_perst_deassert(struct rockchip_pcie_ep *ep) +{ + struct rockchip_pcie *rockchip = &ep->rockchip; + + dev_dbg(rockchip->dev, "PERST# de-asserted, starting link training\n"); + + if (!ep->perst_asserted) + return; + + ep->perst_asserted = false; + + /* Enable link re-training */ + rockchip_pcie_ep_retrain_link(rockchip); + + /* Start link training */ + schedule_delayed_work(&ep->link_training, 0); +} + +static irqreturn_t rockchip_pcie_ep_perst_irq_thread(int irq, void *data) +{ + struct pci_epc *epc = data; + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + u32 perst = gpiod_get_value(rockchip->perst_gpio); + + if (perst) + rockchip_pcie_ep_perst_assert(ep); + else + rockchip_pcie_ep_perst_deassert(ep); + + irq_set_irq_type(ep->perst_irq, + (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW)); + + return IRQ_HANDLED; +} + +static int rockchip_pcie_ep_setup_irq(struct pci_epc *epc) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + struct device *dev = rockchip->dev; + int ret; + + if (!rockchip->perst_gpio) + return 0; + + /* PCIe reset interrupt */ + ep->perst_irq = gpiod_to_irq(rockchip->perst_gpio); + if (ep->perst_irq < 0) { + dev_err(dev, + "failed to get IRQ for PERST# GPIO: %d\n", + ep->perst_irq); + + return ep->perst_irq; + } + + /* + * The perst_gpio is active low, so when it is inactive on start, it + * is high and will trigger the perst_irq handler. So treat this initial + * IRQ as a dummy one by faking the host asserting PERST#. + */ + ep->perst_asserted = true; + irq_set_status_flags(ep->perst_irq, IRQ_NOAUTOEN); + ret = devm_request_threaded_irq(dev, ep->perst_irq, NULL, + rockchip_pcie_ep_perst_irq_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "pcie-ep-perst", epc); + if (ret) { + dev_err(dev, + "failed to request IRQ for PERST# GPIO: %d\n", + ret); + + return ret; + } + + return 0; +} + +static const struct pci_epc_features rockchip_pcie_epc_features = { + .linkup_notifier = true, + .msi_capable = true, + .intx_capable = true, + .align = ROCKCHIP_PCIE_AT_SIZE_ALIGN, +}; + +static const struct pci_epc_features* +rockchip_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + return &rockchip_pcie_epc_features; +} + static const struct pci_epc_ops rockchip_pcie_epc_ops = { .write_header = rockchip_pcie_ep_write_header, .set_bar = rockchip_pcie_ep_set_bar, .clear_bar = rockchip_pcie_ep_clear_bar, + .align_addr = rockchip_pcie_ep_align_addr, .map_addr = rockchip_pcie_ep_map_addr, .unmap_addr = rockchip_pcie_ep_unmap_addr, .set_msi = rockchip_pcie_ep_set_msi, .get_msi = rockchip_pcie_ep_get_msi, .raise_irq = rockchip_pcie_ep_raise_irq, .start = rockchip_pcie_ep_start, + .stop = rockchip_pcie_ep_stop, + .get_features = rockchip_pcie_ep_get_features, }; -static int rockchip_pcie_parse_ep_dt(struct rockchip_pcie *rockchip, - struct rockchip_pcie_ep *ep) +static int rockchip_pcie_ep_get_resources(struct rockchip_pcie *rockchip, + struct rockchip_pcie_ep *ep) { struct device *dev = rockchip->dev; int err; @@ -537,6 +739,8 @@ static int rockchip_pcie_parse_ep_dt(struct rockchip_pcie *rockchip, if (err < 0 || ep->max_regions > MAX_REGION_LIMIT) ep->max_regions = MAX_REGION_LIMIT; + ep->ob_region_map = 0; + err = of_property_read_u8(dev->of_node, "max-functions", &ep->epc->max_functions); if (err < 0) @@ -550,13 +754,94 @@ static const struct of_device_id rockchip_pcie_ep_of_match[] = { {}, }; +static int rockchip_pcie_ep_init_ob_mem(struct rockchip_pcie_ep *ep) +{ + struct rockchip_pcie *rockchip = &ep->rockchip; + struct device *dev = rockchip->dev; + struct pci_epc_mem_window *windows = NULL; + int err, i; + + ep->ob_addr = devm_kcalloc(dev, ep->max_regions, sizeof(*ep->ob_addr), + GFP_KERNEL); + + if (!ep->ob_addr) + return -ENOMEM; + + windows = devm_kcalloc(dev, ep->max_regions, + sizeof(struct pci_epc_mem_window), GFP_KERNEL); + if (!windows) + return -ENOMEM; + + for (i = 0; i < ep->max_regions; i++) { + windows[i].phys_base = rockchip->mem_res->start + (SZ_1M * i); + windows[i].size = SZ_1M; + windows[i].page_size = SZ_1M; + } + err = pci_epc_multi_mem_init(ep->epc, windows, ep->max_regions); + devm_kfree(dev, windows); + + if (err < 0) { + dev_err(dev, "failed to initialize the memory space\n"); + return err; + } + + ep->irq_cpu_addr = pci_epc_mem_alloc_addr(ep->epc, &ep->irq_phys_addr, + SZ_1M); + if (!ep->irq_cpu_addr) { + dev_err(dev, "failed to reserve memory space for MSI\n"); + err = -ENOMEM; + goto err_epc_mem_exit; + } + + ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR; + + return 0; + +err_epc_mem_exit: + pci_epc_mem_exit(ep->epc); + + return err; +} + +static void rockchip_pcie_ep_exit_ob_mem(struct rockchip_pcie_ep *ep) +{ + pci_epc_mem_exit(ep->epc); +} + +static void rockchip_pcie_ep_hide_broken_msix_cap(struct rockchip_pcie *rockchip) +{ + u32 cfg_msi, cfg_msix_cp; + + /* + * MSI-X is not supported but the controller still advertises the MSI-X + * capability by default, which can lead to the Root Complex side + * allocating MSI-X vectors which cannot be used. Avoid this by skipping + * the MSI-X capability entry in the PCIe capabilities linked-list: get + * the next pointer from the MSI-X entry and set that in the MSI + * capability entry (which is the previous entry). This way the MSI-X + * entry is skipped (left out of the linked-list) and not advertised. + */ + cfg_msi = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); + + cfg_msi &= ~ROCKCHIP_PCIE_EP_MSI_CP1_MASK; + + cfg_msix_cp = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE + + ROCKCHIP_PCIE_EP_MSIX_CAP_REG) & + ROCKCHIP_PCIE_EP_MSIX_CAP_CP_MASK; + + cfg_msi |= cfg_msix_cp; + + rockchip_pcie_write(rockchip, cfg_msi, + PCIE_EP_CONFIG_BASE + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); +} + static int rockchip_pcie_ep_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct rockchip_pcie_ep *ep; struct rockchip_pcie *rockchip; struct pci_epc *epc; - size_t max_regions; int err; ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); @@ -566,68 +851,51 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev) rockchip = &ep->rockchip; rockchip->is_rc = false; rockchip->dev = dev; + INIT_DELAYED_WORK(&ep->link_training, rockchip_pcie_ep_link_training); epc = devm_pci_epc_create(dev, &rockchip_pcie_epc_ops); if (IS_ERR(epc)) { - dev_err(dev, "failed to create epc device\n"); + dev_err(dev, "failed to create EPC device\n"); return PTR_ERR(epc); } ep->epc = epc; epc_set_drvdata(epc, ep); - err = rockchip_pcie_parse_ep_dt(rockchip, ep); + err = rockchip_pcie_ep_get_resources(rockchip, ep); if (err) return err; - err = rockchip_pcie_enable_clocks(rockchip); + err = rockchip_pcie_ep_init_ob_mem(ep); if (err) return err; + err = rockchip_pcie_enable_clocks(rockchip); + if (err) + goto err_exit_ob_mem; + err = rockchip_pcie_init_port(rockchip); if (err) goto err_disable_clocks; - /* Establish the link automatically */ - rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE, - PCIE_CLIENT_CONFIG); - - max_regions = ep->max_regions; - ep->ob_addr = devm_kcalloc(dev, max_regions, sizeof(*ep->ob_addr), - GFP_KERNEL); - - if (!ep->ob_addr) { - err = -ENOMEM; - goto err_uninit_port; - } + rockchip_pcie_ep_hide_broken_msix_cap(rockchip); /* Only enable function 0 by default */ rockchip_pcie_write(rockchip, BIT(0), PCIE_CORE_PHY_FUNC_CFG); - err = pci_epc_mem_init(epc, rockchip->mem_res->start, - resource_size(rockchip->mem_res)); - if (err < 0) { - dev_err(dev, "failed to initialize the memory space\n"); - goto err_uninit_port; - } - - ep->irq_cpu_addr = pci_epc_mem_alloc_addr(epc, &ep->irq_phys_addr, - SZ_128K); - if (!ep->irq_cpu_addr) { - dev_err(dev, "failed to reserve memory space for MSI\n"); - err = -ENOMEM; - goto err_epc_mem_exit; - } + pci_epc_init_notify(epc); - ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR; + err = rockchip_pcie_ep_setup_irq(epc); + if (err < 0) + goto err_uninit_port; return 0; -err_epc_mem_exit: - pci_epc_mem_exit(epc); err_uninit_port: rockchip_pcie_deinit_phys(rockchip); err_disable_clocks: rockchip_pcie_disable_clocks(rockchip); +err_exit_ob_mem: + rockchip_pcie_ep_exit_ob_mem(ep); return err; } diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index 1372d270764f..ee1822ca01db 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -11,30 +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_address.h> -#include <linux/of_device.h> +#include <linux/of.h> #include <linux/of_pci.h> -#include <linux/of_platform.h> -#include <linux/of_irq.h> -#include <linux/pci.h> -#include <linux/pci_ids.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> -#include <linux/reset.h> -#include <linux/regmap.h> #include "../pci.h" #include "pcie-rockchip.h" @@ -43,18 +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) @@ -71,16 +60,13 @@ static void rockchip_pcie_update_txcredit_mui(struct rockchip_pcie *rockchip) static int rockchip_pcie_valid_device(struct rockchip_pcie *rockchip, struct pci_bus *bus, int dev) { - /* access only one slot on each root port */ - if (bus->number == rockchip->root_bus_nr && dev > 0) - return 0; - /* - * do not read more than one device on the bus directly attached + * Access only one slot on each root port. + * Do not read more than one device on the bus directly attached * to RC's downstream side. */ - if (bus->primary == rockchip->root_bus_nr && dev > 0) - return 0; + if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) + return dev == 0; return 1; } @@ -160,17 +146,16 @@ static int rockchip_pcie_rd_other_conf(struct rockchip_pcie *rockchip, struct pci_bus *bus, u32 devfn, int where, int size, u32 *val) { - u32 busdev; + void __iomem *addr; - busdev = PCIE_ECAM_ADDR(bus->number, PCI_SLOT(devfn), - PCI_FUNC(devfn), where); + addr = rockchip->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); - if (!IS_ALIGNED(busdev, size)) { + if (!IS_ALIGNED((uintptr_t)addr, size)) { *val = 0; return PCIBIOS_BAD_REGISTER_NUMBER; } - if (bus->parent->number == rockchip->root_bus_nr) + if (pci_is_root_bus(bus->parent)) rockchip_pcie_cfg_configuration_accesses(rockchip, AXI_WRAPPER_TYPE0_CFG); else @@ -178,11 +163,11 @@ static int rockchip_pcie_rd_other_conf(struct rockchip_pcie *rockchip, AXI_WRAPPER_TYPE1_CFG); if (size == 4) { - *val = readl(rockchip->reg_base + busdev); + *val = readl(addr); } else if (size == 2) { - *val = readw(rockchip->reg_base + busdev); + *val = readw(addr); } else if (size == 1) { - *val = readb(rockchip->reg_base + busdev); + *val = readb(addr); } else { *val = 0; return PCIBIOS_BAD_REGISTER_NUMBER; @@ -194,14 +179,14 @@ static int rockchip_pcie_wr_other_conf(struct rockchip_pcie *rockchip, struct pci_bus *bus, u32 devfn, int where, int size, u32 val) { - u32 busdev; + void __iomem *addr; + + addr = rockchip->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); - busdev = PCIE_ECAM_ADDR(bus->number, PCI_SLOT(devfn), - PCI_FUNC(devfn), where); - if (!IS_ALIGNED(busdev, size)) + if (!IS_ALIGNED((uintptr_t)addr, size)) return PCIBIOS_BAD_REGISTER_NUMBER; - if (bus->parent->number == rockchip->root_bus_nr) + if (pci_is_root_bus(bus->parent)) rockchip_pcie_cfg_configuration_accesses(rockchip, AXI_WRAPPER_TYPE0_CFG); else @@ -209,11 +194,11 @@ static int rockchip_pcie_wr_other_conf(struct rockchip_pcie *rockchip, AXI_WRAPPER_TYPE1_CFG); if (size == 4) - writel(val, rockchip->reg_base + busdev); + writel(val, addr); else if (size == 2) - writew(val, rockchip->reg_base + busdev); + writew(val, addr); else if (size == 1) - writeb(val, rockchip->reg_base + busdev); + writeb(val, addr); else return PCIBIOS_BAD_REGISTER_NUMBER; @@ -225,12 +210,10 @@ static int rockchip_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, { struct rockchip_pcie *rockchip = bus->sysdata; - if (!rockchip_pcie_valid_device(rockchip, bus, PCI_SLOT(devfn))) { - *val = 0xffffffff; + if (!rockchip_pcie_valid_device(rockchip, bus, PCI_SLOT(devfn))) return PCIBIOS_DEVICE_NOT_FOUND; - } - if (bus->number == rockchip->root_bus_nr) + if (pci_is_root_bus(bus)) return rockchip_pcie_rd_own_conf(rockchip, where, size, val); return rockchip_pcie_rd_other_conf(rockchip, bus, devfn, where, size, @@ -245,7 +228,7 @@ static int rockchip_pcie_wr_conf(struct pci_bus *bus, u32 devfn, if (!rockchip_pcie_valid_device(rockchip, bus, PCI_SLOT(devfn))) return PCIBIOS_DEVICE_NOT_FOUND; - if (bus->number == rockchip->root_bus_nr) + if (pci_is_root_bus(bus)) return rockchip_pcie_wr_own_conf(rockchip, where, size, val); return rockchip_pcie_wr_other_conf(rockchip, bus, devfn, where, size, @@ -278,7 +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; @@ -287,10 +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); } /** @@ -303,7 +286,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) int err, i = MAX_LANE_NUM; u32 status; - gpiod_set_value_cansleep(rockchip->ep_gpio, 0); + gpiod_set_value_cansleep(rockchip->perst_gpio, 0); err = rockchip_pcie_init_port(rockchip); if (err) @@ -318,20 +301,23 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) rockchip_pcie_set_power_limit(rockchip); /* Set RC's clock architecture as common clock */ - status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); status |= PCI_EXP_LNKSTA_SLC << 16; - rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); /* Set RC's RCB to 128 */ - status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); status |= PCI_EXP_LNKCTL_RCB; - rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); /* Enable Gen1 training */ rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE, PCIE_CLIENT_CONFIG); - gpiod_set_value_cansleep(rockchip->ep_gpio, 1); + msleep(PCIE_T_PVPERL_MS); + gpiod_set_value_cansleep(rockchip->perst_gpio, 1); + + 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, @@ -347,9 +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, @@ -373,10 +363,10 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) } } - rockchip_pcie_write(rockchip, ROCKCHIP_VENDOR_ID, + rockchip_pcie_write(rockchip, PCI_VENDOR_ID_ROCKCHIP, PCIE_CORE_CONFIG_VENDOR); rockchip_pcie_write(rockchip, - PCI_CLASS_BRIDGE_PCI << PCIE_RC_CONFIG_SCC_SHIFT, + PCI_CLASS_BRIDGE_PCI_NORMAL << 8, PCIE_RC_CONFIG_RID_CCR); /* Clear THP cap's next cap pointer to remove L1 substate cap */ @@ -386,15 +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: @@ -445,7 +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"); @@ -495,7 +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"); @@ -514,14 +504,14 @@ static irqreturn_t rockchip_pcie_client_irq_handler(int irq, void *arg) return IRQ_HANDLED; } -static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc) +static void rockchip_pcie_intx_handler(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc); struct device *dev = rockchip->dev; u32 reg; u32 hwirq; - u32 virq; + int ret; chained_irq_enter(chip, desc); @@ -532,10 +522,8 @@ static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc) hwirq = ffs(reg) - 1; reg &= ~BIT(hwirq); - virq = irq_find_mapping(rockchip->irq_domain, hwirq); - if (virq) - generic_handle_irq(virq); - else + ret = generic_handle_domain_irq(rockchip->irq_domain, hwirq); + if (ret) dev_err(dev, "unexpected IRQ, INT%d\n", hwirq); } @@ -549,10 +537,8 @@ static int rockchip_pcie_setup_irq(struct rockchip_pcie *rockchip) struct platform_device *pdev = to_platform_device(dev); irq = platform_get_irq_byname(pdev, "sys"); - if (irq < 0) { - dev_err(dev, "missing sys IRQ resource\n"); + if (irq < 0) return irq; - } err = devm_request_irq(dev, irq, rockchip_pcie_subsys_irq_handler, IRQF_SHARED, "pcie-sys", rockchip); @@ -562,20 +548,16 @@ static int rockchip_pcie_setup_irq(struct rockchip_pcie *rockchip) } irq = platform_get_irq_byname(pdev, "legacy"); - if (irq < 0) { - dev_err(dev, "missing legacy IRQ resource\n"); + if (irq < 0) return irq; - } irq_set_chained_handler_and_data(irq, - rockchip_pcie_legacy_int_handler, + rockchip_pcie_intx_handler, rockchip); irq = platform_get_irq_byname(pdev, "client"); - if (irq < 0) { - dev_err(dev, "missing client IRQ resource\n"); + if (irq < 0) return irq; - } err = devm_request_irq(dev, irq, rockchip_pcie_client_irq_handler, IRQF_SHARED, "pcie-client", rockchip); @@ -602,37 +584,27 @@ static int rockchip_pcie_parse_host_dt(struct rockchip_pcie *rockchip) if (err) return err; - err = rockchip_pcie_setup_irq(rockchip); - if (err) - return err; - rockchip->vpcie12v = devm_regulator_get_optional(dev, "vpcie12v"); if (IS_ERR(rockchip->vpcie12v)) { - if (PTR_ERR(rockchip->vpcie12v) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(rockchip->vpcie12v) != -ENODEV) + return PTR_ERR(rockchip->vpcie12v); dev_info(dev, "no vpcie12v regulator found\n"); } rockchip->vpcie3v3 = devm_regulator_get_optional(dev, "vpcie3v3"); if (IS_ERR(rockchip->vpcie3v3)) { - if (PTR_ERR(rockchip->vpcie3v3) == -EPROBE_DEFER) - return -EPROBE_DEFER; + if (PTR_ERR(rockchip->vpcie3v3) != -ENODEV) + return PTR_ERR(rockchip->vpcie3v3); dev_info(dev, "no vpcie3v3 regulator found\n"); } - rockchip->vpcie1v8 = devm_regulator_get_optional(dev, "vpcie1v8"); - if (IS_ERR(rockchip->vpcie1v8)) { - if (PTR_ERR(rockchip->vpcie1v8) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dev_info(dev, "no vpcie1v8 regulator found\n"); - } + rockchip->vpcie1v8 = devm_regulator_get(dev, "vpcie1v8"); + if (IS_ERR(rockchip->vpcie1v8)) + return PTR_ERR(rockchip->vpcie1v8); - rockchip->vpcie0v9 = devm_regulator_get_optional(dev, "vpcie0v9"); - if (IS_ERR(rockchip->vpcie0v9)) { - if (PTR_ERR(rockchip->vpcie0v9) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dev_info(dev, "no vpcie0v9 regulator found\n"); - } + rockchip->vpcie0v9 = devm_regulator_get(dev, "vpcie0v9"); + if (IS_ERR(rockchip->vpcie0v9)) + return PTR_ERR(rockchip->vpcie0v9); return 0; } @@ -658,27 +630,22 @@ static int rockchip_pcie_set_vpcie(struct rockchip_pcie *rockchip) } } - if (!IS_ERR(rockchip->vpcie1v8)) { - err = regulator_enable(rockchip->vpcie1v8); - if (err) { - dev_err(dev, "fail to enable vpcie1v8 regulator\n"); - goto err_disable_3v3; - } + err = regulator_enable(rockchip->vpcie1v8); + if (err) { + dev_err(dev, "fail to enable vpcie1v8 regulator\n"); + goto err_disable_3v3; } - if (!IS_ERR(rockchip->vpcie0v9)) { - err = regulator_enable(rockchip->vpcie0v9); - if (err) { - dev_err(dev, "fail to enable vpcie0v9 regulator\n"); - goto err_disable_1v8; - } + err = regulator_enable(rockchip->vpcie0v9); + if (err) { + dev_err(dev, "fail to enable vpcie0v9 regulator\n"); + goto err_disable_1v8; } return 0; err_disable_1v8: - if (!IS_ERR(rockchip->vpcie1v8)) - regulator_disable(rockchip->vpcie1v8); + regulator_disable(rockchip->vpcie1v8); err_disable_3v3: if (!IS_ERR(rockchip->vpcie3v3)) regulator_disable(rockchip->vpcie3v3); @@ -722,8 +689,9 @@ 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"); return -EINVAL; @@ -805,19 +773,28 @@ static int rockchip_pcie_prog_ib_atu(struct rockchip_pcie *rockchip, static int rockchip_pcie_cfg_atu(struct rockchip_pcie *rockchip) { struct device *dev = rockchip->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rockchip); + struct resource_entry *entry; + u64 pci_addr, size; int offset; int err; int reg_no; rockchip_pcie_cfg_configuration_accesses(rockchip, AXI_WRAPPER_TYPE0_CFG); + entry = resource_list_first_type(&bridge->windows, IORESOURCE_MEM); + if (!entry) + return -ENODEV; + + size = resource_size(entry->res); + pci_addr = entry->res->start - entry->offset; + rockchip->msg_bus_addr = pci_addr; - for (reg_no = 0; reg_no < (rockchip->mem_size >> 20); reg_no++) { + for (reg_no = 0; reg_no < (size >> 20); reg_no++) { err = rockchip_pcie_prog_ob_atu(rockchip, reg_no + 1, AXI_WRAPPER_MEM_WRITE, 20 - 1, - rockchip->mem_bus_addr + - (reg_no << 20), + pci_addr + (reg_no << 20), 0); if (err) { dev_err(dev, "program RC mem outbound ATU failed\n"); @@ -831,14 +808,22 @@ static int rockchip_pcie_cfg_atu(struct rockchip_pcie *rockchip) return err; } - offset = rockchip->mem_size >> 20; - for (reg_no = 0; reg_no < (rockchip->io_size >> 20); reg_no++) { + entry = resource_list_first_type(&bridge->windows, IORESOURCE_IO); + if (!entry) + return -ENODEV; + + /* store the register number offset to program RC io outbound ATU */ + offset = size >> 20; + + size = resource_size(entry->res); + pci_addr = entry->res->start - entry->offset; + + for (reg_no = 0; reg_no < (size >> 20); reg_no++) { err = rockchip_pcie_prog_ob_atu(rockchip, reg_no + 1 + offset, AXI_WRAPPER_IO_WRITE, 20 - 1, - rockchip->io_bus_addr + - (reg_no << 20), + pci_addr + (reg_no << 20), 0); if (err) { dev_err(dev, "program RC io outbound ATU failed\n"); @@ -851,8 +836,7 @@ static int rockchip_pcie_cfg_atu(struct rockchip_pcie *rockchip) AXI_WRAPPER_NOR_MSG, 20 - 1, 0, 0); - rockchip->msg_bus_addr = rockchip->mem_bus_addr + - ((reg_no + offset) << 20); + rockchip->msg_bus_addr += ((reg_no + offset) << 20); return err; } @@ -876,7 +860,7 @@ static int rockchip_pcie_wait_l2(struct rockchip_pcie *rockchip) return 0; } -static int __maybe_unused rockchip_pcie_suspend_noirq(struct device *dev) +static int rockchip_pcie_suspend_noirq(struct device *dev) { struct rockchip_pcie *rockchip = dev_get_drvdata(dev); int ret; @@ -896,23 +880,20 @@ static int __maybe_unused rockchip_pcie_suspend_noirq(struct device *dev) rockchip_pcie_disable_clocks(rockchip); - if (!IS_ERR(rockchip->vpcie0v9)) - regulator_disable(rockchip->vpcie0v9); + regulator_disable(rockchip->vpcie0v9); return ret; } -static int __maybe_unused rockchip_pcie_resume_noirq(struct device *dev) +static int rockchip_pcie_resume_noirq(struct device *dev) { struct rockchip_pcie *rockchip = dev_get_drvdata(dev); int err; - if (!IS_ERR(rockchip->vpcie0v9)) { - err = regulator_enable(rockchip->vpcie0v9); - if (err) { - dev_err(dev, "fail to enable vpcie0v9 regulator\n"); - return err; - } + err = regulator_enable(rockchip->vpcie0v9); + if (err) { + dev_err(dev, "fail to enable vpcie0v9 regulator\n"); + return err; } err = rockchip_pcie_enable_clocks(rockchip); @@ -938,8 +919,7 @@ err_err_deinit_port: err_pcie_resume: rockchip_pcie_disable_clocks(rockchip); err_disable_0v9: - if (!IS_ERR(rockchip->vpcie0v9)) - regulator_disable(rockchip->vpcie0v9); + regulator_disable(rockchip->vpcie0v9); return err; } @@ -947,16 +927,9 @@ static int rockchip_pcie_probe(struct platform_device *pdev) { struct rockchip_pcie *rockchip; struct device *dev = &pdev->dev; - struct pci_bus *bus, *child; struct pci_host_bridge *bridge; - struct resource_entry *win; - resource_size_t io_base; - struct resource *mem; - struct resource *io; int err; - LIST_HEAD(res); - if (!dev->of_node) return -ENODEV; @@ -988,89 +961,35 @@ static int rockchip_pcie_probe(struct platform_device *pdev) if (err) goto err_vpcie; - rockchip_pcie_enable_interrupts(rockchip); - err = rockchip_pcie_init_irq_domain(rockchip); if (err < 0) goto err_deinit_port; - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, - &res, &io_base); - if (err) - goto err_remove_irq_domain; - - err = devm_request_pci_bus_resources(dev, &res); - if (err) - goto err_free_res; - - /* Get the I/O and memory ranges from DT */ - resource_list_for_each_entry(win, &res) { - switch (resource_type(win->res)) { - case IORESOURCE_IO: - io = win->res; - io->name = "I/O"; - rockchip->io_size = resource_size(io); - rockchip->io_bus_addr = io->start - win->offset; - err = pci_remap_iospace(io, io_base); - if (err) { - dev_warn(dev, "error %d: failed to map resource %pR\n", - err, io); - continue; - } - rockchip->io = io; - break; - case IORESOURCE_MEM: - mem = win->res; - mem->name = "MEM"; - rockchip->mem_size = resource_size(mem); - rockchip->mem_bus_addr = mem->start - win->offset; - break; - case IORESOURCE_BUS: - rockchip->root_bus_nr = win->res->start; - break; - default: - continue; - } - } - err = rockchip_pcie_cfg_atu(rockchip); if (err) - goto err_unmap_iospace; + goto err_remove_irq_domain; rockchip->msg_region = devm_ioremap(dev, rockchip->msg_bus_addr, SZ_1M); if (!rockchip->msg_region) { err = -ENOMEM; - goto err_unmap_iospace; + goto err_remove_irq_domain; } - list_splice_init(&res, &bridge->windows); - bridge->dev.parent = dev; bridge->sysdata = rockchip; - bridge->busnr = 0; bridge->ops = &rockchip_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - - err = pci_scan_root_bus_bridge(bridge); - if (err < 0) - goto err_unmap_iospace; - bus = bridge->bus; + err = rockchip_pcie_setup_irq(rockchip); + if (err) + goto err_remove_irq_domain; - rockchip->root_bus = bus; + rockchip_pcie_enable_interrupts(rockchip); - pci_bus_size_bridges(bus); - pci_bus_assign_resources(bus); - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); + err = pci_host_probe(bridge); + if (err < 0) + goto err_remove_irq_domain; - pci_bus_add_devices(bus); return 0; -err_unmap_iospace: - pci_unmap_iospace(rockchip->io); -err_free_res: - pci_free_resource_list(&res); err_remove_irq_domain: irq_domain_remove(rockchip->irq_domain); err_deinit_port: @@ -1080,23 +999,21 @@ err_vpcie: regulator_disable(rockchip->vpcie12v); if (!IS_ERR(rockchip->vpcie3v3)) regulator_disable(rockchip->vpcie3v3); - if (!IS_ERR(rockchip->vpcie1v8)) - regulator_disable(rockchip->vpcie1v8); - if (!IS_ERR(rockchip->vpcie0v9)) - regulator_disable(rockchip->vpcie0v9); + regulator_disable(rockchip->vpcie1v8); + regulator_disable(rockchip->vpcie0v9); err_set_vpcie: rockchip_pcie_disable_clocks(rockchip); return err; } -static int rockchip_pcie_remove(struct platform_device *pdev) +static void rockchip_pcie_remove(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct rockchip_pcie *rockchip = dev_get_drvdata(dev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rockchip); - pci_stop_root_bus(rockchip->root_bus); - pci_remove_root_bus(rockchip->root_bus); - pci_unmap_iospace(rockchip->io); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); irq_domain_remove(rockchip->irq_domain); rockchip_pcie_deinit_phys(rockchip); @@ -1107,17 +1024,13 @@ static int rockchip_pcie_remove(struct platform_device *pdev) regulator_disable(rockchip->vpcie12v); if (!IS_ERR(rockchip->vpcie3v3)) regulator_disable(rockchip->vpcie3v3); - if (!IS_ERR(rockchip->vpcie1v8)) - regulator_disable(rockchip->vpcie1v8); - if (!IS_ERR(rockchip->vpcie0v9)) - regulator_disable(rockchip->vpcie0v9); - - return 0; + regulator_disable(rockchip->vpcie1v8); + regulator_disable(rockchip->vpcie0v9); } static const struct dev_pm_ops rockchip_pcie_pm_ops = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(rockchip_pcie_suspend_noirq, - rockchip_pcie_resume_noirq) + NOIRQ_SYSTEM_SLEEP_PM_OPS(rockchip_pcie_suspend_noirq, + rockchip_pcie_resume_noirq) }; static const struct of_device_id rockchip_pcie_of_match[] = { diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c index c53d1322a3d6..0f88da378805 100644 --- a/drivers/pci/controller/pcie-rockchip.c +++ b/drivers/pci/controller/pcie-rockchip.c @@ -14,6 +14,8 @@ #include <linux/clk.h> #include <linux/delay.h> #include <linux/gpio/consumer.h> +#include <linux/iopoll.h> +#include <linux/of.h> #include <linux/of_pci.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> @@ -28,7 +30,7 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) struct platform_device *pdev = to_platform_device(dev); struct device_node *node = dev->of_node; struct resource *regs; - int err; + int err, i; if (rockchip->is_rc) { regs = platform_get_resource_byname(pdev, @@ -45,9 +47,8 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) return -EINVAL; } - regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, - "apb-base"); - rockchip->apb_base = devm_ioremap_resource(dev, regs); + rockchip->apb_base = + devm_platform_ioremap_resource_byname(pdev, "apb-base"); if (IS_ERR(rockchip->apb_base)) return PTR_ERR(rockchip->apb_base); @@ -68,115 +69,59 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) if (rockchip->link_gen < 0 || rockchip->link_gen > 2) rockchip->link_gen = 2; - rockchip->core_rst = devm_reset_control_get_exclusive(dev, "core"); - if (IS_ERR(rockchip->core_rst)) { - if (PTR_ERR(rockchip->core_rst) != -EPROBE_DEFER) - dev_err(dev, "missing core reset property in node\n"); - return PTR_ERR(rockchip->core_rst); - } - - rockchip->mgmt_rst = devm_reset_control_get_exclusive(dev, "mgmt"); - if (IS_ERR(rockchip->mgmt_rst)) { - if (PTR_ERR(rockchip->mgmt_rst) != -EPROBE_DEFER) - dev_err(dev, "missing mgmt reset property in node\n"); - return PTR_ERR(rockchip->mgmt_rst); - } - - rockchip->mgmt_sticky_rst = devm_reset_control_get_exclusive(dev, - "mgmt-sticky"); - if (IS_ERR(rockchip->mgmt_sticky_rst)) { - if (PTR_ERR(rockchip->mgmt_sticky_rst) != -EPROBE_DEFER) - dev_err(dev, "missing mgmt-sticky reset property in node\n"); - return PTR_ERR(rockchip->mgmt_sticky_rst); - } - - rockchip->pipe_rst = devm_reset_control_get_exclusive(dev, "pipe"); - if (IS_ERR(rockchip->pipe_rst)) { - if (PTR_ERR(rockchip->pipe_rst) != -EPROBE_DEFER) - dev_err(dev, "missing pipe reset property in node\n"); - return PTR_ERR(rockchip->pipe_rst); - } - - rockchip->pm_rst = devm_reset_control_get_exclusive(dev, "pm"); - if (IS_ERR(rockchip->pm_rst)) { - if (PTR_ERR(rockchip->pm_rst) != -EPROBE_DEFER) - dev_err(dev, "missing pm reset property in node\n"); - return PTR_ERR(rockchip->pm_rst); - } + for (i = 0; i < ROCKCHIP_NUM_PM_RSTS; i++) + rockchip->pm_rsts[i].id = rockchip_pci_pm_rsts[i]; - rockchip->pclk_rst = devm_reset_control_get_exclusive(dev, "pclk"); - if (IS_ERR(rockchip->pclk_rst)) { - if (PTR_ERR(rockchip->pclk_rst) != -EPROBE_DEFER) - dev_err(dev, "missing pclk reset property in node\n"); - return PTR_ERR(rockchip->pclk_rst); - } - - rockchip->aclk_rst = devm_reset_control_get_exclusive(dev, "aclk"); - if (IS_ERR(rockchip->aclk_rst)) { - if (PTR_ERR(rockchip->aclk_rst) != -EPROBE_DEFER) - dev_err(dev, "missing aclk reset property in node\n"); - return PTR_ERR(rockchip->aclk_rst); - } - - if (rockchip->is_rc) { - rockchip->ep_gpio = devm_gpiod_get(dev, "ep", GPIOD_OUT_HIGH); - if (IS_ERR(rockchip->ep_gpio)) { - dev_err(dev, "missing ep-gpios property in node\n"); - return PTR_ERR(rockchip->ep_gpio); - } - } + err = devm_reset_control_bulk_get_exclusive(dev, + ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); + if (err) + return dev_err_probe(dev, err, "Cannot get the PM reset\n"); - rockchip->aclk_pcie = devm_clk_get(dev, "aclk"); - if (IS_ERR(rockchip->aclk_pcie)) { - dev_err(dev, "aclk clock not found\n"); - return PTR_ERR(rockchip->aclk_pcie); - } + for (i = 0; i < ROCKCHIP_NUM_CORE_RSTS; i++) + rockchip->core_rsts[i].id = rockchip_pci_core_rsts[i]; - rockchip->aclk_perf_pcie = devm_clk_get(dev, "aclk-perf"); - if (IS_ERR(rockchip->aclk_perf_pcie)) { - dev_err(dev, "aclk_perf clock not found\n"); - return PTR_ERR(rockchip->aclk_perf_pcie); - } + err = devm_reset_control_bulk_get_exclusive(dev, + ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); + if (err) + return dev_err_probe(dev, err, "Cannot get the Core resets\n"); - rockchip->hclk_pcie = devm_clk_get(dev, "hclk"); - if (IS_ERR(rockchip->hclk_pcie)) { - dev_err(dev, "hclk clock not found\n"); - return PTR_ERR(rockchip->hclk_pcie); - } + if (rockchip->is_rc) + rockchip->perst_gpio = devm_gpiod_get_optional(dev, "ep", + GPIOD_OUT_LOW); + else + rockchip->perst_gpio = devm_gpiod_get_optional(dev, "reset", + GPIOD_IN); + if (IS_ERR(rockchip->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(rockchip->perst_gpio), + "failed to get PERST# GPIO\n"); - rockchip->clk_pcie_pm = devm_clk_get(dev, "pm"); - if (IS_ERR(rockchip->clk_pcie_pm)) { - dev_err(dev, "pm clock not found\n"); - return PTR_ERR(rockchip->clk_pcie_pm); - } + rockchip->num_clks = devm_clk_bulk_get_all(dev, &rockchip->clks); + if (rockchip->num_clks < 0) + return dev_err_probe(dev, rockchip->num_clks, + "failed to get clocks\n"); return 0; } EXPORT_SYMBOL_GPL(rockchip_pcie_parse_dt); +#define rockchip_pcie_read_addr(addr) rockchip_pcie_read(rockchip, addr) +/* 100 ms max wait time for PHY PLLs to lock */ +#define RK_PHY_PLL_LOCK_TIMEOUT_US 100000 +/* Sleep should be less than 20ms */ +#define RK_PHY_PLL_LOCK_SLEEP_US 1000 + int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) { struct device *dev = rockchip->dev; int err, i; u32 regs; - err = reset_control_assert(rockchip->aclk_rst); - if (err) { - dev_err(dev, "assert aclk_rst err %d\n", err); - return err; - } - - err = reset_control_assert(rockchip->pclk_rst); - if (err) { - dev_err(dev, "assert pclk_rst err %d\n", err); - return err; - } - - err = reset_control_assert(rockchip->pm_rst); - if (err) { - dev_err(dev, "assert pm_rst err %d\n", err); - return err; - } + err = reset_control_bulk_assert(ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); + if (err) + return dev_err_probe(dev, err, "Couldn't assert PM resets\n"); for (i = 0; i < MAX_LANE_NUM; i++) { err = phy_init(rockchip->phys[i]); @@ -186,47 +131,19 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) } } - err = reset_control_assert(rockchip->core_rst); - if (err) { - dev_err(dev, "assert core_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_assert(rockchip->mgmt_rst); - if (err) { - dev_err(dev, "assert mgmt_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_assert(rockchip->mgmt_sticky_rst); + err = reset_control_bulk_assert(ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); if (err) { - dev_err(dev, "assert mgmt_sticky_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_assert(rockchip->pipe_rst); - if (err) { - dev_err(dev, "assert pipe_rst err %d\n", err); + dev_err_probe(dev, err, "Couldn't assert Core resets\n"); goto err_exit_phy; } udelay(10); - err = reset_control_deassert(rockchip->pm_rst); + err = reset_control_bulk_deassert(ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); if (err) { - dev_err(dev, "deassert pm_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_deassert(rockchip->aclk_rst); - if (err) { - dev_err(dev, "deassert aclk_rst err %d\n", err); - goto err_exit_phy; - } - - err = reset_control_deassert(rockchip->pclk_rst); - if (err) { - dev_err(dev, "deassert pclk_rst err %d\n", err); + dev_err(dev, "Couldn't deassert PM resets %d\n", err); goto err_exit_phy; } @@ -237,11 +154,12 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) rockchip_pcie_write(rockchip, PCIE_CLIENT_GEN_SEL_1, PCIE_CLIENT_CONFIG); - regs = PCIE_CLIENT_LINK_TRAIN_ENABLE | PCIE_CLIENT_ARI_ENABLE | + regs = PCIE_CLIENT_ARI_ENABLE | PCIE_CLIENT_CONF_LANE_NUM(rockchip->lanes); if (rockchip->is_rc) - regs |= PCIE_CLIENT_CONF_ENABLE | PCIE_CLIENT_MODE_RC; + regs |= PCIE_CLIENT_LINK_TRAIN_ENABLE | + PCIE_CLIENT_CONF_ENABLE | PCIE_CLIENT_MODE_RC; else regs |= PCIE_CLIENT_CONF_DISABLE | PCIE_CLIENT_MODE_EP; @@ -255,31 +173,20 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) } } - /* - * Please don't reorder the deassert sequence of the following - * four reset pins. - */ - err = reset_control_deassert(rockchip->mgmt_sticky_rst); + err = readx_poll_timeout(rockchip_pcie_read_addr, + PCIE_CLIENT_SIDE_BAND_STATUS, + regs, !(regs & PCIE_CLIENT_PHY_ST), + RK_PHY_PLL_LOCK_SLEEP_US, + RK_PHY_PLL_LOCK_TIMEOUT_US); if (err) { - dev_err(dev, "deassert mgmt_sticky_rst err %d\n", err); + dev_err(dev, "PHY PLLs could not lock, %d\n", err); goto err_power_off_phy; } - err = reset_control_deassert(rockchip->core_rst); + err = reset_control_bulk_deassert(ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); if (err) { - dev_err(dev, "deassert core_rst err %d\n", err); - goto err_power_off_phy; - } - - err = reset_control_deassert(rockchip->mgmt_rst); - if (err) { - dev_err(dev, "deassert mgmt_rst err %d\n", err); - goto err_power_off_phy; - } - - err = reset_control_deassert(rockchip->pipe_rst); - if (err) { - dev_err(dev, "deassert pipe_rst err %d\n", err); + dev_err(dev, "Couldn't deassert Core reset %d\n", err); goto err_power_off_phy; } @@ -355,50 +262,18 @@ int rockchip_pcie_enable_clocks(struct rockchip_pcie *rockchip) struct device *dev = rockchip->dev; int err; - err = clk_prepare_enable(rockchip->aclk_pcie); - if (err) { - dev_err(dev, "unable to enable aclk_pcie clock\n"); - return err; - } - - err = clk_prepare_enable(rockchip->aclk_perf_pcie); - if (err) { - dev_err(dev, "unable to enable aclk_perf_pcie clock\n"); - goto err_aclk_perf_pcie; - } - - err = clk_prepare_enable(rockchip->hclk_pcie); - if (err) { - dev_err(dev, "unable to enable hclk_pcie clock\n"); - goto err_hclk_pcie; - } - - err = clk_prepare_enable(rockchip->clk_pcie_pm); - if (err) { - dev_err(dev, "unable to enable clk_pcie_pm clock\n"); - goto err_clk_pcie_pm; - } + err = clk_bulk_prepare_enable(rockchip->num_clks, rockchip->clks); + if (err) + return dev_err_probe(dev, err, "failed to enable clocks\n"); return 0; - -err_clk_pcie_pm: - clk_disable_unprepare(rockchip->hclk_pcie); -err_hclk_pcie: - clk_disable_unprepare(rockchip->aclk_perf_pcie); -err_aclk_perf_pcie: - clk_disable_unprepare(rockchip->aclk_pcie); - return err; } EXPORT_SYMBOL_GPL(rockchip_pcie_enable_clocks); -void rockchip_pcie_disable_clocks(void *data) +void rockchip_pcie_disable_clocks(struct rockchip_pcie *rockchip) { - struct rockchip_pcie *rockchip = data; - clk_disable_unprepare(rockchip->clk_pcie_pm); - clk_disable_unprepare(rockchip->hclk_pcie); - clk_disable_unprepare(rockchip->aclk_perf_pcie); - clk_disable_unprepare(rockchip->aclk_pcie); + clk_bulk_disable_unprepare(rockchip->num_clks, rockchip->clks); } EXPORT_SYMBOL_GPL(rockchip_pcie_disable_clocks); diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index 8e87a059ce73..3e82a69b9c00 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Rockchip AXI PCIe controller driver * @@ -11,36 +11,53 @@ #ifndef _PCIE_ROCKCHIP_H #define _PCIE_ROCKCHIP_H +#include <linux/clk.h> +#include <linux/hw_bitfield.h> #include <linux/kernel.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/reset.h> /* * The upper 16 bits of PCIE_CLIENT_CONFIG are a write mask for the lower 16 * bits. This allows atomic updates of the register without locking. */ -#define HIWORD_UPDATE(mask, val) (((mask) << 16) | (val)) -#define HIWORD_UPDATE_BIT(val) HIWORD_UPDATE(val, val) +#define HWORD_SET_BIT(val) (FIELD_PREP_WM16_CONST((val), 1)) +#define HWORD_CLR_BIT(val) (FIELD_PREP_WM16_CONST((val), 0)) -#define ENCODE_LANES(x) ((((x) >> 1) & 3) << 4) +#define ENCODE_LANES(x) ((((x) >> 1) & 3)) #define MAX_LANE_NUM 4 #define MAX_REGION_LIMIT 32 #define MIN_EP_APERTURE 28 +#define LINK_TRAIN_TIMEOUT (500 * USEC_PER_MSEC) #define PCIE_CLIENT_BASE 0x0 #define PCIE_CLIENT_CONFIG (PCIE_CLIENT_BASE + 0x00) -#define PCIE_CLIENT_CONF_ENABLE HIWORD_UPDATE_BIT(0x0001) -#define PCIE_CLIENT_CONF_DISABLE HIWORD_UPDATE(0x0001, 0) -#define PCIE_CLIENT_LINK_TRAIN_ENABLE HIWORD_UPDATE_BIT(0x0002) -#define PCIE_CLIENT_ARI_ENABLE HIWORD_UPDATE_BIT(0x0008) -#define PCIE_CLIENT_CONF_LANE_NUM(x) HIWORD_UPDATE(0x0030, ENCODE_LANES(x)) -#define PCIE_CLIENT_MODE_RC HIWORD_UPDATE_BIT(0x0040) -#define PCIE_CLIENT_MODE_EP HIWORD_UPDATE(0x0040, 0) -#define PCIE_CLIENT_GEN_SEL_1 HIWORD_UPDATE(0x0080, 0) -#define PCIE_CLIENT_GEN_SEL_2 HIWORD_UPDATE_BIT(0x0080) +#define PCIE_CLIENT_CONF_ENABLE HWORD_SET_BIT(0x0001) +#define PCIE_CLIENT_CONF_DISABLE HWORD_CLR_BIT(0x0001) +#define PCIE_CLIENT_LINK_TRAIN_ENABLE HWORD_SET_BIT(0x0002) +#define PCIE_CLIENT_LINK_TRAIN_DISABLE HWORD_CLR_BIT(0x0002) +#define PCIE_CLIENT_ARI_ENABLE HWORD_SET_BIT(0x0008) +#define PCIE_CLIENT_CONF_LANE_NUM(x) FIELD_PREP_WM16(0x0030, ENCODE_LANES(x)) +#define PCIE_CLIENT_MODE_RC HWORD_SET_BIT(0x0040) +#define PCIE_CLIENT_MODE_EP HWORD_CLR_BIT(0x0040) +#define PCIE_CLIENT_GEN_SEL_1 HWORD_CLR_BIT(0x0080) +#define PCIE_CLIENT_GEN_SEL_2 HWORD_SET_BIT(0x0080) +#define PCIE_CLIENT_LEGACY_INT_CTRL (PCIE_CLIENT_BASE + 0x0c) +#define PCIE_CLIENT_INT_IN_ASSERT HWORD_SET_BIT(0x0002) +#define PCIE_CLIENT_INT_IN_DEASSERT HWORD_CLR_BIT(0x0002) +#define PCIE_CLIENT_INT_PEND_ST_PEND HWORD_SET_BIT(0x0001) +#define PCIE_CLIENT_INT_PEND_ST_NORMAL HWORD_CLR_BIT(0x0001) +#define PCIE_CLIENT_SIDE_BAND_STATUS (PCIE_CLIENT_BASE + 0x20) +#define PCIE_CLIENT_PHY_ST BIT(12) #define PCIE_CLIENT_DEBUG_OUT_0 (PCIE_CLIENT_BASE + 0x3c) #define PCIE_CLIENT_DEBUG_LTSSM_MASK GENMASK(5, 0) #define PCIE_CLIENT_DEBUG_LTSSM_L1 0x18 #define PCIE_CLIENT_DEBUG_LTSSM_L2 0x19 +#define PCIE_CLIENT_BASIC_STATUS0 (PCIE_CLIENT_BASE + 0x44) +#define PCIE_CLIENT_NEG_LINK_WIDTH_MASK GENMASK(7, 6) +#define PCIE_CLIENT_NEG_LINK_WIDTH_SHIFT 6 +#define PCIE_CLIENT_NEG_LINK_SPEED BIT(5) #define PCIE_CLIENT_BASIC_STATUS1 (PCIE_CLIENT_BASE + 0x48) #define PCIE_CLIENT_LINK_STATUS_UP 0x00300000 #define PCIE_CLIENT_LINK_STATUS_MASK 0x00300000 @@ -78,6 +95,8 @@ #define PCIE_CORE_CTRL_MGMT_BASE 0x900000 #define PCIE_CORE_CTRL (PCIE_CORE_CTRL_MGMT_BASE + 0x000) +#define PCIE_CORE_PL_CONF_LS_MASK 0x00000001 +#define PCIE_CORE_PL_CONF_LS_READY 0x00000001 #define PCIE_CORE_PL_CONF_SPEED_5G 0x00000008 #define PCIE_CORE_PL_CONF_SPEED_MASK 0x00000018 #define PCIE_CORE_PL_CONF_LANE_MASK 0x00000006 @@ -131,27 +150,24 @@ #define PCIE_RC_RP_ATS_BASE 0x400000 #define PCIE_RC_CONFIG_NORMAL_BASE 0x800000 +#define PCIE_EP_PF_CONFIG_REGS_BASE 0x800000 #define PCIE_RC_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_DID_VID (PCIE_EP_CONFIG_BASE + 0x00) +#define PCIE_EP_CONFIG_LCS (PCIE_EP_CONFIG_BASE + 0xd0) #define PCIE_RC_CONFIG_RID_CCR (PCIE_RC_CONFIG_BASE + 0x08) -#define PCIE_RC_CONFIG_SCC_SHIFT 16 -#define PCIE_RC_CONFIG_DCR (PCIE_RC_CONFIG_BASE + 0xc4) -#define PCIE_RC_CONFIG_DCR_CSPL_SHIFT 18 -#define PCIE_RC_CONFIG_DCR_CSPL_LIMIT 0xff -#define PCIE_RC_CONFIG_DCR_CPLS_SHIFT 26 -#define PCIE_RC_CONFIG_DCSR (PCIE_RC_CONFIG_BASE + 0xc8) -#define PCIE_RC_CONFIG_DCSR_MPS_MASK GENMASK(7, 5) -#define PCIE_RC_CONFIG_DCSR_MPS_256 (0x1 << 5) -#define PCIE_RC_CONFIG_LINK_CAP (PCIE_RC_CONFIG_BASE + 0xcc) -#define PCIE_RC_CONFIG_LINK_CAP_L0S BIT(10) -#define PCIE_RC_CONFIG_LCS (PCIE_RC_CONFIG_BASE + 0xd0) +#define PCIE_RC_CONFIG_CR (PCIE_RC_CONFIG_BASE + 0xc0) #define PCIE_RC_CONFIG_L1_SUBSTATE_CTRL2 (PCIE_RC_CONFIG_BASE + 0x90c) #define PCIE_RC_CONFIG_THP_CAP (PCIE_RC_CONFIG_BASE + 0x274) #define PCIE_RC_CONFIG_THP_CAP_NEXT_MASK GENMASK(31, 20) +#define MAX_AXI_IB_ROOTPORT_REGION_NUM 3 +#define MIN_AXI_ADDR_BITS_PASSED 8 +#define PCIE_ADDR_MASK GENMASK_ULL(63, MIN_AXI_ADDR_BITS_PASSED) #define PCIE_CORE_AXI_CONF_BASE 0xc00000 #define PCIE_CORE_OB_REGION_ADDR0 (PCIE_CORE_AXI_CONF_BASE + 0x0) #define PCIE_CORE_OB_REGION_ADDR0_NUM_BITS 0x3f -#define PCIE_CORE_OB_REGION_ADDR0_LO_ADDR 0xffffff00 +#define PCIE_CORE_OB_REGION_ADDR0_LO_ADDR PCIE_ADDR_MASK #define PCIE_CORE_OB_REGION_ADDR1 (PCIE_CORE_AXI_CONF_BASE + 0x4) #define PCIE_CORE_OB_REGION_DESC0 (PCIE_CORE_AXI_CONF_BASE + 0x8) #define PCIE_CORE_OB_REGION_DESC1 (PCIE_CORE_AXI_CONF_BASE + 0xc) @@ -159,7 +175,7 @@ #define PCIE_CORE_AXI_INBOUND_BASE 0xc00800 #define PCIE_RP_IB_ADDR0 (PCIE_CORE_AXI_INBOUND_BASE + 0x0) #define PCIE_CORE_IB_REGION_ADDR0_NUM_BITS 0x3f -#define PCIE_CORE_IB_REGION_ADDR0_LO_ADDR 0xffffff00 +#define PCIE_CORE_IB_REGION_ADDR0_LO_ADDR PCIE_ADDR_MASK #define PCIE_RP_IB_ADDR1 (PCIE_CORE_AXI_INBOUND_BASE + 0x4) /* Size of one AXI Region (not Region 0) */ @@ -174,19 +190,11 @@ #define AXI_WRAPPER_TYPE1_CFG 0xb #define AXI_WRAPPER_NOR_MSG 0xc -#define MAX_AXI_IB_ROOTPORT_REGION_NUM 3 -#define MIN_AXI_ADDR_BITS_PASSED 8 #define PCIE_RC_SEND_PME_OFF 0x11960 -#define ROCKCHIP_VENDOR_ID 0x1d87 -#define PCIE_ECAM_BUS(x) (((x) & 0xff) << 20) -#define PCIE_ECAM_DEV(x) (((x) & 0x1f) << 15) -#define PCIE_ECAM_FUNC(x) (((x) & 0x7) << 12) -#define PCIE_ECAM_REG(x) (((x) & 0xfff) << 0) -#define PCIE_ECAM_ADDR(bus, dev, func, reg) \ - (PCIE_ECAM_BUS(bus) | PCIE_ECAM_DEV(dev) | \ - PCIE_ECAM_FUNC(func) | PCIE_ECAM_REG(reg)) #define PCIE_LINK_IS_L2(x) \ (((x) & PCIE_CLIENT_DEBUG_LTSSM_MASK) == PCIE_CLIENT_DEBUG_LTSSM_L2) +#define PCIE_LINK_TRAINING_DONE(x) \ + (((x) & PCIE_CORE_PL_CONF_LS_MASK) == PCIE_CORE_PL_CONF_LS_READY) #define PCIE_LINK_UP(x) \ (((x) & PCIE_CLIENT_LINK_STATUS_MASK) == PCIE_CLIENT_LINK_STATUS_UP) #define PCIE_LINK_IS_GEN2(x) \ @@ -198,20 +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) @@ -223,21 +217,38 @@ #define ROCKCHIP_PCIE_EP_CMD_STATUS 0x4 #define ROCKCHIP_PCIE_EP_CMD_STATUS_IS BIT(19) #define ROCKCHIP_PCIE_EP_MSI_CTRL_REG 0x90 +#define ROCKCHIP_PCIE_EP_MSI_CP1_OFFSET 8 +#define ROCKCHIP_PCIE_EP_MSI_CP1_MASK GENMASK(15, 8) +#define ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET 16 #define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET 17 #define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK GENMASK(19, 17) #define ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET 20 #define ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK GENMASK(22, 20) #define ROCKCHIP_PCIE_EP_MSI_CTRL_ME BIT(16) #define ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP BIT(24) +#define ROCKCHIP_PCIE_EP_MSIX_CAP_REG 0xb0 +#define ROCKCHIP_PCIE_EP_MSIX_CAP_CP_OFFSET 8 +#define ROCKCHIP_PCIE_EP_MSIX_CAP_CP_MASK GENMASK(15, 8) #define ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR 0x1 #define ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR 0x3 -#define ROCKCHIP_PCIE_EP_FUNC_BASE(fn) (((fn) << 12) & GENMASK(19, 12)) + +#define ROCKCHIP_PCIE_AT_MIN_NUM_BITS 8 +#define ROCKCHIP_PCIE_AT_MAX_NUM_BITS 20 +#define ROCKCHIP_PCIE_AT_SIZE_ALIGN (1UL << ROCKCHIP_PCIE_AT_MIN_NUM_BITS) + +#define ROCKCHIP_PCIE_EP_FUNC_BASE(fn) \ + (PCIE_EP_PF_CONFIG_REGS_BASE + (((fn) << 12) & GENMASK(19, 12))) +#define ROCKCHIP_PCIE_EP_VIRT_FUNC_BASE(fn) \ + (PCIE_EP_PF_CONFIG_REGS_BASE + 0x10000 + (((fn) << 12) & GENMASK(19, 12))) + +#define ROCKCHIP_PCIE_AT_MIN_NUM_BITS 8 +#define ROCKCHIP_PCIE_AT_MAX_NUM_BITS 20 +#define ROCKCHIP_PCIE_AT_SIZE_ALIGN (1UL << ROCKCHIP_PCIE_AT_MIN_NUM_BITS) + #define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) \ - (PCIE_RC_RP_ATS_BASE + 0x0840 + (fn) * 0x0040 + (bar) * 0x0008) + (PCIE_CORE_AXI_CONF_BASE + 0x0828 + (fn) * 0x0040 + (bar) * 0x0008) #define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar) \ - (PCIE_RC_RP_ATS_BASE + 0x0844 + (fn) * 0x0040 + (bar) * 0x0008) -#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(r) \ - (PCIE_RC_RP_ATS_BASE + 0x0000 + ((r) & 0x1f) * 0x0020) + (PCIE_CORE_AXI_CONF_BASE + 0x082c + (fn) * 0x0040 + (bar) * 0x0008) #define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN_MASK GENMASK(19, 12) #define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) \ (((devfn) << 12) & \ @@ -245,20 +256,21 @@ #define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_BUS_MASK GENMASK(27, 20) #define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_BUS(bus) \ (((bus) << 20) & ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_BUS_MASK) +#define PCIE_RC_EP_ATR_OB_REGIONS_1_32 (PCIE_CORE_AXI_CONF_BASE + 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0000 + ((r) & 0x1f) * 0x0020) #define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR1(r) \ - (PCIE_RC_RP_ATS_BASE + 0x0004 + ((r) & 0x1f) * 0x0020) + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0004 + ((r) & 0x1f) * 0x0020) #define ROCKCHIP_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID BIT(23) #define ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN_MASK GENMASK(31, 24) #define ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN(devfn) \ (((devfn) << 24) & ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN_MASK) #define ROCKCHIP_PCIE_AT_OB_REGION_DESC0(r) \ - (PCIE_RC_RP_ATS_BASE + 0x0008 + ((r) & 0x1f) * 0x0020) -#define ROCKCHIP_PCIE_AT_OB_REGION_DESC1(r) \ - (PCIE_RC_RP_ATS_BASE + 0x000c + ((r) & 0x1f) * 0x0020) -#define ROCKCHIP_PCIE_AT_OB_REGION_CPU_ADDR0(r) \ - (PCIE_RC_RP_ATS_BASE + 0x0018 + ((r) & 0x1f) * 0x0020) -#define ROCKCHIP_PCIE_AT_OB_REGION_CPU_ADDR1(r) \ - (PCIE_RC_RP_ATS_BASE + 0x001c + ((r) & 0x1f) * 0x0020) + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0008 + ((r) & 0x1f) * 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC1(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x000c + ((r) & 0x1f) * 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC2(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0010 + ((r) & 0x1f) * 0x0020) #define ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG0(fn) \ (PCIE_CORE_CTRL_MGMT_BASE + 0x0240 + (fn) * 0x0008) @@ -275,42 +287,45 @@ (((c) << ((b) * 8 + 5)) & \ ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)) +#define ROCKCHIP_NUM_PM_RSTS ARRAY_SIZE(rockchip_pci_pm_rsts) +#define ROCKCHIP_NUM_CORE_RSTS ARRAY_SIZE(rockchip_pci_core_rsts) + +static const char * const rockchip_pci_pm_rsts[] = { + "pm", + "pclk", + "aclk", +}; + +/* NOTE: Do not reorder the deassert sequence of the following reset pins */ +static const char * const rockchip_pci_core_rsts[] = { + "pipe", + "mgmt", + "core", + "mgmt-sticky", +}; + struct rockchip_pcie { void __iomem *reg_base; /* DT axi-base */ void __iomem *apb_base; /* DT apb-base */ bool legacy_phy; struct phy *phys[MAX_LANE_NUM]; - struct reset_control *core_rst; - struct reset_control *mgmt_rst; - struct reset_control *mgmt_sticky_rst; - struct reset_control *pipe_rst; - struct reset_control *pm_rst; - struct reset_control *aclk_rst; - struct reset_control *pclk_rst; - struct clk *aclk_pcie; - struct clk *aclk_perf_pcie; - struct clk *hclk_pcie; - struct clk *clk_pcie_pm; + struct reset_control_bulk_data pm_rsts[ROCKCHIP_NUM_PM_RSTS]; + struct reset_control_bulk_data core_rsts[ROCKCHIP_NUM_CORE_RSTS]; + struct clk_bulk_data *clks; + int num_clks; struct regulator *vpcie12v; /* 12V power supply */ struct regulator *vpcie3v3; /* 3.3V power supply */ struct regulator *vpcie1v8; /* 1.8V power supply */ struct regulator *vpcie0v9; /* 0.9V power supply */ - struct gpio_desc *ep_gpio; + struct gpio_desc *perst_gpio; u32 lanes; u8 lanes_map; - u8 root_bus_nr; int link_gen; struct device *dev; struct irq_domain *irq_domain; int offset; - struct pci_bus *root_bus; - struct resource *io; - phys_addr_t io_bus_addr; - u32 io_size; void __iomem *msg_region; - u32 mem_size; phys_addr_t msg_bus_addr; - phys_addr_t mem_bus_addr; bool is_rc; struct resource *mem_res; }; @@ -331,7 +346,7 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip); int rockchip_pcie_get_phys(struct rockchip_pcie *rockchip); void rockchip_pcie_deinit_phys(struct rockchip_pcie *rockchip); int rockchip_pcie_enable_clocks(struct rockchip_pcie *rockchip); -void rockchip_pcie_disable_clocks(void *data); +void rockchip_pcie_disable_clocks(struct rockchip_pcie *rockchip); void rockchip_pcie_cfg_configuration_accesses( struct rockchip_pcie *rockchip, u32 type); diff --git a/drivers/pci/controller/pcie-rzg3s-host.c b/drivers/pci/controller/pcie-rzg3s-host.c new file mode 100644 index 000000000000..667e6d629474 --- /dev/null +++ b/drivers/pci/controller/pcie-rzg3s-host.c @@ -0,0 +1,1761 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe driver for Renesas RZ/G3S SoCs + * + * Copyright (C) 2025 Renesas Electronics Corp. + * + * Based on: + * drivers/pci/controller/pcie-rcar-host.c + * Copyright (C) 2009 - 2011 Paul Mundt + */ + +#include <linux/bitfield.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/cleanup.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/mutex.h> +#include <linux/msi.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/sizes.h> +#include <linux/slab.h> +#include <linux/units.h> + +#include "../pci.h" + +/* AXI registers */ +#define RZG3S_PCI_REQDATA(id) (0x80 + (id) * 0x4) +#define RZG3S_PCI_REQRCVDAT 0x8c + +#define RZG3S_PCI_REQADR1 0x90 +#define RZG3S_PCI_REQADR1_BUS GENMASK(31, 24) +#define RZG3S_PCI_REQADR1_DEV GENMASK(23, 19) +#define RZG3S_PCI_REQADR1_FUNC GENMASK(18, 16) +#define RZG3S_PCI_REQADR1_REG GENMASK(11, 0) + +#define RZG3S_PCI_REQBE 0x98 +#define RZG3S_PCI_REQBE_BYTE_EN GENMASK(3, 0) + +#define RZG3S_PCI_REQISS 0x9c +#define RZG3S_PCI_REQISS_MOR_STATUS GENMASK(18, 16) +#define RZG3S_PCI_REQISS_TR_TYPE GENMASK(11, 8) +#define RZG3S_PCI_REQISS_TR_TP0_RD FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x4) +#define RZG3S_PCI_REQISS_TR_TP0_WR FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x5) +#define RZG3S_PCI_REQISS_TR_TP1_RD FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x6) +#define RZG3S_PCI_REQISS_TR_TP1_WR FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x7) +#define RZG3S_PCI_REQISS_REQ_ISSUE BIT(0) + +#define RZG3S_PCI_MSIRCVWADRL 0x100 +#define RZG3S_PCI_MSIRCVWADRL_MASK GENMASK(31, 3) +#define RZG3S_PCI_MSIRCVWADRL_MSG_DATA_ENA BIT(1) +#define RZG3S_PCI_MSIRCVWADRL_ENA BIT(0) + +#define RZG3S_PCI_MSIRCVWADRU 0x104 + +#define RZG3S_PCI_MSIRCVWMSKL 0x108 +#define RZG3S_PCI_MSIRCVWMSKL_MASK GENMASK(31, 2) + +#define RZG3S_PCI_PINTRCVIE 0x110 +#define RZG3S_PCI_PINTRCVIE_INTX(i) BIT(i) +#define RZG3S_PCI_PINTRCVIE_MSI BIT(4) + +#define RZG3S_PCI_PINTRCVIS 0x114 +#define RZG3S_PCI_PINTRCVIS_INTX(i) BIT(i) +#define RZG3S_PCI_PINTRCVIS_MSI BIT(4) + +#define RZG3S_PCI_MSGRCVIE 0x120 +#define RZG3S_PCI_MSGRCVIE_MSG_RCV BIT(24) + +#define RZG3S_PCI_MSGRCVIS 0x124 +#define RZG3S_PCI_MSGRCVIS_MRI BIT(24) + +#define RZG3S_PCI_PEIE0 0x200 + +#define RZG3S_PCI_PEIS0 0x204 +#define RZG3S_PCI_PEIS0_RX_DLLP_PM_ENTER BIT(12) +#define RZG3S_PCI_PEIS0_DL_UPDOWN BIT(9) + +#define RZG3S_PCI_PEIE1 0x208 +#define RZG3S_PCI_PEIS1 0x20c +#define RZG3S_PCI_AMEIS 0x214 +#define RZG3S_PCI_ASEIS1 0x224 + +#define RZG3S_PCI_PCSTAT1 0x408 +#define RZG3S_PCI_PCSTAT1_LTSSM_STATE GENMASK(14, 10) +#define RZG3S_PCI_PCSTAT1_DL_DOWN_STS BIT(0) + +#define RZG3S_PCI_PCCTRL2 0x410 +#define RZG3S_PCI_PCCTRL2_LS_CHG GENMASK(9, 8) +#define RZG3S_PCI_PCCTRL2_LS_CHG_REQ BIT(0) + +#define RZG3S_PCI_PCSTAT2 0x414 +#define RZG3S_PCI_PCSTAT2_LS_CHG_DONE BIT(28) +#define RZG3S_PCI_PCSTAT2_SDRIRE GENMASK(7, 1) + +#define RZG3S_PCI_PERM 0x300 +#define RZG3S_PCI_PERM_CFG_HWINIT_EN BIT(2) +#define RZG3S_PCI_PERM_PIPE_PHY_REG_EN BIT(1) + +#define RZG3S_PCI_MSIRE(id) (0x600 + (id) * 0x10) +#define RZG3S_PCI_MSIRE_ENA BIT(0) + +#define RZG3S_PCI_MSIRM(id) (0x608 + (id) * 0x10) +#define RZG3S_PCI_MSIRS(id) (0x60c + (id) * 0x10) + +#define RZG3S_PCI_AWBASEL(id) (0x1000 + (id) * 0x20) +#define RZG3S_PCI_AWBASEL_WIN_ENA BIT(0) + +#define RZG3S_PCI_AWBASEU(id) (0x1004 + (id) * 0x20) +#define RZG3S_PCI_AWMASKL(id) (0x1008 + (id) * 0x20) +#define RZG3S_PCI_AWMASKU(id) (0x100c + (id) * 0x20) +#define RZG3S_PCI_ADESTL(id) (0x1010 + (id) * 0x20) +#define RZG3S_PCI_ADESTU(id) (0x1014 + (id) * 0x20) + +#define RZG3S_PCI_PWBASEL(id) (0x1100 + (id) * 0x20) +#define RZG3S_PCI_PWBASEL_ENA BIT(0) + +#define RZG3S_PCI_PWBASEU(id) (0x1104 + (id) * 0x20) +#define RZG3S_PCI_PDESTL(id) (0x1110 + (id) * 0x20) +#define RZG3S_PCI_PDESTU(id) (0x1114 + (id) * 0x20) +#define RZG3S_PCI_PWMASKL(id) (0x1108 + (id) * 0x20) +#define RZG3S_PCI_PWMASKU(id) (0x110c + (id) * 0x20) + +/* PHY control registers */ +#define RZG3S_PCI_PHY_XCFGD(id) (0x2000 + (id) * 0x10) +#define RZG3S_PCI_PHY_XCFGD_NUM 39 + +#define RZG3S_PCI_PHY_XCFGA_CMN(id) (0x2400 + (id) * 0x10) +#define RZG3S_PCI_PHY_XCFGA_CMN_NUM 16 + +#define RZG3S_PCI_PHY_XCFGA_RX(id) (0x2500 + (id) * 0x10) +#define RZG3S_PCI_PHY_XCFGA_RX_NUM 13 + +#define RZG3S_PCI_PHY_XCFGA_TX 0x25d0 + +#define RZG3S_PCI_PHY_XCFG_CTRL 0x2a20 +#define RZG3S_PCI_PHY_XCFG_CTRL_PHYREG_SEL BIT(0) + +/* PCIe registers */ +#define RZG3S_PCI_CFG_BASE 0x6000 +#define RZG3S_PCI_CFG_BARMSK00L 0xa0 +#define RZG3S_PCI_CFG_BARMSK00U 0xa4 + +#define RZG3S_PCI_CFG_PCIEC 0x60 + +/* System controller registers */ +#define RZG3S_SYS_PCIE_RST_RSM_B 0xd74 +#define RZG3S_SYS_PCIE_RST_RSM_B_MASK BIT(0) + +/* Maximum number of windows */ +#define RZG3S_MAX_WINDOWS 8 + +/* Number of MSI interrupts per register */ +#define RZG3S_PCI_MSI_INT_PER_REG 32 +/* The number of MSI interrupts */ +#define RZG3S_PCI_MSI_INT_NR RZG3S_PCI_MSI_INT_PER_REG + +/* Timeouts experimentally determined */ +#define RZG3S_REQ_ISSUE_TIMEOUT_US 2500 + +/** + * struct rzg3s_pcie_msi - RZ/G3S PCIe MSI data structure + * @domain: IRQ domain + * @map: bitmap with the allocated MSIs + * @dma_addr: address of the allocated MSI window + * @window_base: base address of the MSI window + * @pages: allocated pages for MSI window mapping + * @map_lock: lock for bitmap with the allocated MSIs + * @irq: MSI interrupt + */ +struct rzg3s_pcie_msi { + struct irq_domain *domain; + DECLARE_BITMAP(map, RZG3S_PCI_MSI_INT_NR); + dma_addr_t dma_addr; + dma_addr_t window_base; + unsigned long pages; + struct mutex map_lock; + int irq; +}; + +struct rzg3s_pcie_host; + +/** + * struct rzg3s_pcie_soc_data - SoC specific data + * @init_phy: PHY initialization function + * @power_resets: array with the resets that need to be de-asserted after + * power-on + * @cfg_resets: array with the resets that need to be de-asserted after + * configuration + * @num_power_resets: number of power resets + * @num_cfg_resets: number of configuration resets + */ +struct rzg3s_pcie_soc_data { + int (*init_phy)(struct rzg3s_pcie_host *host); + const char * const *power_resets; + const char * const *cfg_resets; + u8 num_power_resets; + u8 num_cfg_resets; +}; + +/** + * struct rzg3s_pcie_port - RZ/G3S PCIe Root Port data structure + * @refclk: PCIe reference clock + * @vendor_id: Vendor ID + * @device_id: Device ID + */ +struct rzg3s_pcie_port { + struct clk *refclk; + u32 vendor_id; + u32 device_id; +}; + +/** + * struct rzg3s_pcie_host - RZ/G3S PCIe data structure + * @axi: base address for AXI registers + * @pcie: base address for PCIe registers + * @dev: struct device + * @power_resets: reset control signals that should be set after power up + * @cfg_resets: reset control signals that should be set after configuration + * @sysc: SYSC regmap + * @intx_domain: INTx IRQ domain + * @data: SoC specific data + * @msi: MSI data structure + * @port: PCIe Root Port + * @hw_lock: lock for access to the HW resources + * @intx_irqs: INTx interrupts + * @max_link_speed: maximum supported link speed + */ +struct rzg3s_pcie_host { + void __iomem *axi; + void __iomem *pcie; + struct device *dev; + struct reset_control_bulk_data *power_resets; + struct reset_control_bulk_data *cfg_resets; + struct regmap *sysc; + struct irq_domain *intx_domain; + const struct rzg3s_pcie_soc_data *data; + struct rzg3s_pcie_msi msi; + struct rzg3s_pcie_port port; + raw_spinlock_t hw_lock; + int intx_irqs[PCI_NUM_INTX]; + int max_link_speed; +}; + +#define rzg3s_msi_to_host(_msi) container_of(_msi, struct rzg3s_pcie_host, msi) + +static void rzg3s_pcie_update_bits(void __iomem *base, u32 offset, u32 mask, + u32 val) +{ + u32 tmp; + + tmp = readl_relaxed(base + offset); + tmp &= ~mask; + tmp |= val & mask; + writel_relaxed(tmp, base + offset); +} + +static int rzg3s_pcie_child_issue_request(struct rzg3s_pcie_host *host) +{ + u32 val; + int ret; + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_REQISS, + RZG3S_PCI_REQISS_REQ_ISSUE, + RZG3S_PCI_REQISS_REQ_ISSUE); + ret = readl_poll_timeout_atomic(host->axi + RZG3S_PCI_REQISS, val, + !(val & RZG3S_PCI_REQISS_REQ_ISSUE), + 5, RZG3S_REQ_ISSUE_TIMEOUT_US); + + if (val & RZG3S_PCI_REQISS_MOR_STATUS) + return -EIO; + + return ret; +} + +static void rzg3s_pcie_child_prepare_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + unsigned int dev, func, reg; + + dev = PCI_SLOT(devfn); + func = PCI_FUNC(devfn); + reg = where & ~0x3; + + /* Set the destination */ + writel_relaxed(FIELD_PREP(RZG3S_PCI_REQADR1_BUS, bus->number) | + FIELD_PREP(RZG3S_PCI_REQADR1_DEV, dev) | + FIELD_PREP(RZG3S_PCI_REQADR1_FUNC, func) | + FIELD_PREP(RZG3S_PCI_REQADR1_REG, reg), + host->axi + RZG3S_PCI_REQADR1); + + /* Set byte enable */ + writel_relaxed(RZG3S_PCI_REQBE_BYTE_EN, host->axi + RZG3S_PCI_REQBE); +} + +static int rzg3s_pcie_child_read_conf(struct rzg3s_pcie_host *host, + struct pci_bus *bus, unsigned int devfn, + int where, u32 *data) +{ + bool type0 = pci_is_root_bus(bus->parent) ? true : false; + int ret; + + rzg3s_pcie_child_prepare_bus(bus, devfn, where); + + /* Set the type of request */ + writel_relaxed(type0 ? RZG3S_PCI_REQISS_TR_TP0_RD : + RZG3S_PCI_REQISS_TR_TP1_RD, + host->axi + RZG3S_PCI_REQISS); + + /* Issue the request and wait to finish */ + ret = rzg3s_pcie_child_issue_request(host); + if (ret) + return PCIBIOS_SET_FAILED; + + /* Read the data */ + *data = readl_relaxed(host->axi + RZG3S_PCI_REQRCVDAT); + + return PCIBIOS_SUCCESSFUL; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rzg3s_pcie_child_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + int ret; + + ret = rzg3s_pcie_child_read_conf(host, bus, devfn, where, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + + return PCIBIOS_SUCCESSFUL; +} + +static int rzg3s_pcie_child_write_conf(struct rzg3s_pcie_host *host, + struct pci_bus *bus, unsigned int devfn, + int where, u32 data) +{ + bool type0 = pci_is_root_bus(bus->parent) ? true : false; + int ret; + + rzg3s_pcie_child_prepare_bus(bus, devfn, where); + + /* Set the write data */ + writel_relaxed(0, host->axi + RZG3S_PCI_REQDATA(0)); + writel_relaxed(0, host->axi + RZG3S_PCI_REQDATA(1)); + writel_relaxed(data, host->axi + RZG3S_PCI_REQDATA(2)); + + /* Set the type of request */ + writel_relaxed(type0 ? RZG3S_PCI_REQISS_TR_TP0_WR : + RZG3S_PCI_REQISS_TR_TP1_WR, + host->axi + RZG3S_PCI_REQISS); + + /* Issue the request and wait to finish */ + ret = rzg3s_pcie_child_issue_request(host); + if (ret) + return PCIBIOS_SET_FAILED; + + return PCIBIOS_SUCCESSFUL; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rzg3s_pcie_child_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + u32 data, shift; + int ret; + + if (size == 4) + return rzg3s_pcie_child_write_conf(host, bus, devfn, where, val); + + /* + * Controller does 32 bit accesses. To do byte accesses software need + * to do read/modify/write. This may have potential side effects. For + * example, software may perform a 16-bit write. If the hardware only + * supports 32-bit accesses, we must do a 32-bit read, merge in the 16 + * bits we intend to write, followed by a 32-bit write. If the 16 bits + * we *don't* intend to write happen to have any RW1C + * (write-one-to-clear) bits set, we just inadvertently cleared + * something we shouldn't have. + */ + if (!bus->unsafe_warn) { + dev_warn(&bus->dev, "%d-byte config write to %04x:%02x:%02x.%d offset %#x may corrupt adjacent RW1C bits\n", + size, pci_domain_nr(bus), bus->number, + PCI_SLOT(devfn), PCI_FUNC(devfn), where); + bus->unsafe_warn = 1; + } + + ret = rzg3s_pcie_child_read_conf(host, bus, devfn, where, &data); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (size == 1) { + shift = BITS_PER_BYTE * (where & 3); + data &= ~(0xff << shift); + data |= ((val & 0xff) << shift); + } else if (size == 2) { + shift = BITS_PER_BYTE * (where & 2); + data &= ~(0xffff << shift); + data |= ((val & 0xffff) << shift); + } else { + data = val; + } + + return rzg3s_pcie_child_write_conf(host, bus, devfn, where, data); +} + +static struct pci_ops rzg3s_pcie_child_ops = { + .read = rzg3s_pcie_child_read, + .write = rzg3s_pcie_child_write, +}; + +static void __iomem *rzg3s_pcie_root_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + + if (devfn) + return NULL; + + return host->pcie + where; +} + +/* Serialized by 'pci_lock' */ +static int rzg3s_pcie_root_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + int ret; + + /* Enable access control to the CFGU */ + writel_relaxed(RZG3S_PCI_PERM_CFG_HWINIT_EN, + host->axi + RZG3S_PCI_PERM); + + ret = pci_generic_config_write(bus, devfn, where, size, val); + + /* Disable access control to the CFGU */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + return ret; +} + +static struct pci_ops rzg3s_pcie_root_ops = { + .read = pci_generic_config_read, + .write = rzg3s_pcie_root_write, + .map_bus = rzg3s_pcie_root_map_bus, +}; + +static void rzg3s_pcie_intx_irq_handler(struct irq_desc *desc) +{ + struct rzg3s_pcie_host *host = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned int irq = irq_desc_get_irq(desc); + u32 intx = irq - host->intx_irqs[0]; + + chained_irq_enter(chip, desc); + generic_handle_domain_irq(host->intx_domain, intx); + chained_irq_exit(chip, desc); +} + +static irqreturn_t rzg3s_pcie_msi_irq(int irq, void *data) +{ + u8 regs = RZG3S_PCI_MSI_INT_NR / RZG3S_PCI_MSI_INT_PER_REG; + DECLARE_BITMAP(bitmap, RZG3S_PCI_MSI_INT_NR); + struct rzg3s_pcie_host *host = data; + struct rzg3s_pcie_msi *msi = &host->msi; + unsigned long bit; + u32 status; + + status = readl_relaxed(host->axi + RZG3S_PCI_PINTRCVIS); + if (!(status & RZG3S_PCI_PINTRCVIS_MSI)) + return IRQ_NONE; + + /* Clear the MSI */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIS, + RZG3S_PCI_PINTRCVIS_MSI, + RZG3S_PCI_PINTRCVIS_MSI); + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSGRCVIS, + RZG3S_PCI_MSGRCVIS_MRI, RZG3S_PCI_MSGRCVIS_MRI); + + for (u8 reg_id = 0; reg_id < regs; reg_id++) { + status = readl_relaxed(host->axi + RZG3S_PCI_MSIRS(reg_id)); + bitmap_write(bitmap, status, reg_id * RZG3S_PCI_MSI_INT_PER_REG, + RZG3S_PCI_MSI_INT_PER_REG); + } + + for_each_set_bit(bit, bitmap, RZG3S_PCI_MSI_INT_NR) { + int ret; + + ret = generic_handle_domain_irq(msi->domain, bit); + if (ret) { + u8 reg_bit = bit % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = bit / RZG3S_PCI_MSI_INT_PER_REG; + + /* Unknown MSI, just clear it */ + writel_relaxed(BIT(reg_bit), + host->axi + RZG3S_PCI_MSIRS(reg_id)); + } + } + + return IRQ_HANDLED; +} + +static void rzg3s_pcie_msi_irq_ack(struct irq_data *d) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(d); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u8 reg_bit = d->hwirq % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = d->hwirq / RZG3S_PCI_MSI_INT_PER_REG; + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + writel_relaxed(BIT(reg_bit), host->axi + RZG3S_PCI_MSIRS(reg_id)); +} + +static void rzg3s_pcie_msi_irq_mask(struct irq_data *d) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(d); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u8 reg_bit = d->hwirq % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = d->hwirq / RZG3S_PCI_MSI_INT_PER_REG; + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSIRM(reg_id), BIT(reg_bit), + BIT(reg_bit)); +} + +static void rzg3s_pcie_msi_irq_unmask(struct irq_data *d) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(d); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u8 reg_bit = d->hwirq % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = d->hwirq / RZG3S_PCI_MSI_INT_PER_REG; + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSIRM(reg_id), BIT(reg_bit), + 0); +} + +static void rzg3s_pcie_irq_compose_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(data); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u32 lo, hi; + + /* + * Enable and msg data enable bits are part of the address lo. Drop + * them along with the unused bit. + */ + lo = readl_relaxed(host->axi + RZG3S_PCI_MSIRCVWADRL) & + RZG3S_PCI_MSIRCVWADRL_MASK; + hi = readl_relaxed(host->axi + RZG3S_PCI_MSIRCVWADRU); + + msg->address_lo = lo; + msg->address_hi = hi; + msg->data = data->hwirq; +} + +static struct irq_chip rzg3s_pcie_msi_bottom_chip = { + .name = "rzg3s-pcie-msi", + .irq_ack = rzg3s_pcie_msi_irq_ack, + .irq_mask = rzg3s_pcie_msi_irq_mask, + .irq_unmask = rzg3s_pcie_msi_irq_unmask, + .irq_compose_msi_msg = rzg3s_pcie_irq_compose_msi_msg, +}; + +static int rzg3s_pcie_msi_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct rzg3s_pcie_msi *msi = domain->host_data; + int hwirq; + + scoped_guard(mutex, &msi->map_lock) { + hwirq = bitmap_find_free_region(msi->map, RZG3S_PCI_MSI_INT_NR, + order_base_2(nr_irqs)); + } + + if (hwirq < 0) + return -ENOSPC; + + for (unsigned int i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, hwirq + i, + &rzg3s_pcie_msi_bottom_chip, + domain->host_data, handle_edge_irq, NULL, + NULL); + } + + return 0; +} + +static void rzg3s_pcie_msi_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct rzg3s_pcie_msi *msi = domain->host_data; + + guard(mutex)(&msi->map_lock); + + bitmap_release_region(msi->map, d->hwirq, order_base_2(nr_irqs)); +} + +static const struct irq_domain_ops rzg3s_pcie_msi_domain_ops = { + .alloc = rzg3s_pcie_msi_domain_alloc, + .free = rzg3s_pcie_msi_domain_free, +}; + +#define RZG3S_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) + +#define RZG3S_PCIE_MSI_FLAGS_SUPPORTED (MSI_FLAG_MULTI_PCI_MSI | \ + MSI_GENERIC_FLAGS_MASK) + +static const struct msi_parent_ops rzg3s_pcie_msi_parent_ops = { + .required_flags = RZG3S_PCIE_MSI_FLAGS_REQUIRED, + .supported_flags = RZG3S_PCIE_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "RZG3S-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, +}; + +static int rzg3s_pcie_msi_allocate_domains(struct rzg3s_pcie_msi *msi) +{ + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + struct device *dev = host->dev; + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &rzg3s_pcie_msi_domain_ops, + .size = RZG3S_PCI_MSI_INT_NR, + .host_data = msi, + }; + + msi->domain = msi_create_parent_irq_domain(&info, + &rzg3s_pcie_msi_parent_ops); + if (!msi->domain) + return dev_err_probe(dev, -ENOMEM, + "failed to create IRQ domain\n"); + + return 0; +} + +static int rzg3s_pcie_msi_hw_setup(struct rzg3s_pcie_host *host) +{ + u8 regs = RZG3S_PCI_MSI_INT_NR / RZG3S_PCI_MSI_INT_PER_REG; + struct rzg3s_pcie_msi *msi = &host->msi; + + /* + * Set MSI window size. HW will set the window to + * RZG3S_PCI_MSI_INT_NR * 4 bytes. + */ + writel_relaxed(FIELD_PREP(RZG3S_PCI_MSIRCVWMSKL_MASK, + RZG3S_PCI_MSI_INT_NR - 1), + host->axi + RZG3S_PCI_MSIRCVWMSKL); + + /* Set MSI window address and enable MSI window */ + writel_relaxed(upper_32_bits(msi->window_base), + host->axi + RZG3S_PCI_MSIRCVWADRU); + writel_relaxed(lower_32_bits(msi->window_base) | + RZG3S_PCI_MSIRCVWADRL_ENA | + RZG3S_PCI_MSIRCVWADRL_MSG_DATA_ENA, + host->axi + RZG3S_PCI_MSIRCVWADRL); + + /* Set MSI receive enable */ + for (u8 reg_id = 0; reg_id < regs; reg_id++) { + writel_relaxed(RZG3S_PCI_MSIRE_ENA, + host->axi + RZG3S_PCI_MSIRE(reg_id)); + } + + /* Enable message receive interrupts */ + writel_relaxed(RZG3S_PCI_MSGRCVIE_MSG_RCV, + host->axi + RZG3S_PCI_MSGRCVIE); + + /* Enable MSI */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_MSI, + RZG3S_PCI_PINTRCVIE_MSI); + + return 0; +} + +static int rzg3s_pcie_msi_setup(struct rzg3s_pcie_host *host) +{ + size_t size = RZG3S_PCI_MSI_INT_NR * sizeof(u32); + struct rzg3s_pcie_msi *msi = &host->msi; + struct device *dev = host->dev; + int id, ret; + + msi->pages = __get_free_pages(GFP_KERNEL | GFP_DMA, 0); + if (!msi->pages) + return -ENOMEM; + + msi->dma_addr = dma_map_single(dev, (void *)msi->pages, size * 2, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, msi->dma_addr)) { + ret = -ENOMEM; + goto free_pages; + } + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.4.5.2 Setting + * the MSI Window) the MSI window needs to fall within one of the + * enabled AXI windows. Find an enabled AXI window to setup the MSI + * window. + */ + for (id = 0; id < RZG3S_MAX_WINDOWS; id++) { + u64 base, basel, baseu; + u64 mask, maskl, masku; + + basel = readl_relaxed(host->axi + RZG3S_PCI_AWBASEL(id)); + /* Skip checking this AXI window if it's not enabled */ + if (!(basel & RZG3S_PCI_AWBASEL_WIN_ENA)) + continue; + + baseu = readl_relaxed(host->axi + RZG3S_PCI_AWBASEU(id)); + base = baseu << 32 | basel; + + maskl = readl_relaxed(host->axi + RZG3S_PCI_AWMASKL(id)); + masku = readl_relaxed(host->axi + RZG3S_PCI_AWMASKU(id)); + mask = masku << 32 | maskl; + + if (msi->dma_addr < base || msi->dma_addr > base + mask) + continue; + + break; + } + + if (id == RZG3S_MAX_WINDOWS) { + ret = -EINVAL; + goto dma_unmap; + } + + /* The MSI base address must be aligned to the MSI size */ + msi->window_base = ALIGN(msi->dma_addr, size); + if (msi->window_base < msi->dma_addr) { + ret = -EINVAL; + goto dma_unmap; + } + + rzg3s_pcie_msi_hw_setup(host); + + return 0; + +dma_unmap: + dma_unmap_single(dev, msi->dma_addr, size * 2, DMA_BIDIRECTIONAL); +free_pages: + free_pages(msi->pages, 0); + return ret; +} + +static void rzg3s_pcie_msi_hw_teardown(struct rzg3s_pcie_host *host) +{ + u8 regs = RZG3S_PCI_MSI_INT_NR / RZG3S_PCI_MSI_INT_PER_REG; + + /* Disable MSI */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_MSI, 0); + + /* Disable message receive interrupts */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSGRCVIE, + RZG3S_PCI_MSGRCVIE_MSG_RCV, 0); + + /* Disable MSI receive enable */ + for (u8 reg_id = 0; reg_id < regs; reg_id++) + writel_relaxed(0, host->axi + RZG3S_PCI_MSIRE(reg_id)); + + /* Disable MSI window */ + writel_relaxed(0, host->axi + RZG3S_PCI_MSIRCVWADRL); +} + +static void rzg3s_pcie_teardown_msi(struct rzg3s_pcie_host *host) +{ + size_t size = RZG3S_PCI_MSI_INT_NR * sizeof(u32); + struct rzg3s_pcie_msi *msi = &host->msi; + + rzg3s_pcie_msi_hw_teardown(host); + + free_irq(msi->irq, host); + irq_domain_remove(msi->domain); + + /* Free unused memory */ + dma_unmap_single(host->dev, msi->dma_addr, size * 2, DMA_BIDIRECTIONAL); + free_pages(msi->pages, 0); +} + +static int rzg3s_pcie_init_msi(struct rzg3s_pcie_host *host) +{ + struct platform_device *pdev = to_platform_device(host->dev); + struct rzg3s_pcie_msi *msi = &host->msi; + struct device *dev = host->dev; + const char *devname; + int ret; + + ret = devm_mutex_init(dev, &msi->map_lock); + if (ret) + return ret; + + msi->irq = platform_get_irq_byname(pdev, "msi"); + if (msi->irq < 0) + return dev_err_probe(dev, msi->irq, "Failed to get MSI IRQ!\n"); + + devname = devm_kasprintf(dev, GFP_KERNEL, "%s-msi", dev_name(dev)); + if (!devname) + return -ENOMEM; + + ret = rzg3s_pcie_msi_allocate_domains(msi); + if (ret) + return ret; + + /* + * Don't use devm_request_irq() as the driver uses non-devm helpers + * to control clocks. Mixing them may lead to subtle bugs. + */ + ret = request_irq(msi->irq, rzg3s_pcie_msi_irq, 0, devname, host); + if (ret) { + dev_err_probe(dev, ret, "Failed to request IRQ: %d\n", ret); + goto free_domains; + } + + ret = rzg3s_pcie_msi_setup(host); + if (ret) { + dev_err_probe(dev, ret, "Failed to setup MSI!\n"); + goto free_irq; + } + + return 0; + +free_irq: + free_irq(msi->irq, host); +free_domains: + irq_domain_remove(msi->domain); + return ret; +} + +static void rzg3s_pcie_intx_irq_ack(struct irq_data *d) +{ + struct rzg3s_pcie_host *host = irq_data_get_irq_chip_data(d); + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIS, + RZG3S_PCI_PINTRCVIS_INTX(d->hwirq), + RZG3S_PCI_PINTRCVIS_INTX(d->hwirq)); +} + +static void rzg3s_pcie_intx_irq_mask(struct irq_data *d) +{ + struct rzg3s_pcie_host *host = irq_data_get_irq_chip_data(d); + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_INTX(d->hwirq), 0); +} + +static void rzg3s_pcie_intx_irq_unmask(struct irq_data *d) +{ + struct rzg3s_pcie_host *host = irq_data_get_irq_chip_data(d); + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_INTX(d->hwirq), + RZG3S_PCI_PINTRCVIE_INTX(d->hwirq)); +} + +static struct irq_chip rzg3s_pcie_intx_irq_chip = { + .name = "PCIe INTx", + .irq_ack = rzg3s_pcie_intx_irq_ack, + .irq_mask = rzg3s_pcie_intx_irq_mask, + .irq_unmask = rzg3s_pcie_intx_irq_unmask, +}; + +static int rzg3s_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &rzg3s_pcie_intx_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops rzg3s_pcie_intx_domain_ops = { + .map = rzg3s_pcie_intx_map, + .xlate = irq_domain_xlate_onetwocell, +}; + +static int rzg3s_pcie_init_irqdomain(struct rzg3s_pcie_host *host) +{ + struct device *dev = host->dev; + struct platform_device *pdev = to_platform_device(dev); + + for (int i = 0; i < PCI_NUM_INTX; i++) { + char irq_name[5] = {0}; + int irq; + + scnprintf(irq_name, ARRAY_SIZE(irq_name), "int%c", 'a' + i); + + irq = platform_get_irq_byname(pdev, irq_name); + if (irq < 0) + return dev_err_probe(dev, -EINVAL, + "Failed to parse and map INT%c IRQ\n", + 'A' + i); + + host->intx_irqs[i] = irq; + irq_set_chained_handler_and_data(irq, + rzg3s_pcie_intx_irq_handler, + host); + } + + host->intx_domain = irq_domain_create_linear(dev_fwnode(dev), + PCI_NUM_INTX, + &rzg3s_pcie_intx_domain_ops, + host); + if (!host->intx_domain) + return dev_err_probe(dev, -EINVAL, + "Failed to add irq domain for INTx IRQs\n"); + irq_domain_update_bus_token(host->intx_domain, DOMAIN_BUS_WIRED); + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + int ret = rzg3s_pcie_init_msi(host); + + if (ret) { + irq_domain_remove(host->intx_domain); + return ret; + } + } + + return 0; +} + +static void rzg3s_pcie_teardown_irqdomain(struct rzg3s_pcie_host *host) +{ + if (IS_ENABLED(CONFIG_PCI_MSI)) + rzg3s_pcie_teardown_msi(host); + + irq_domain_remove(host->intx_domain); +} + +static int rzg3s_pcie_set_max_link_speed(struct rzg3s_pcie_host *host) +{ + u32 remote_supported_link_speeds, max_supported_link_speeds; + u32 cs2, tmp, pcie_cap = RZG3S_PCI_CFG_PCIEC; + u32 cur_link_speed, link_speed; + u8 ltssm_state_l0 = 0xc; + int ret; + u16 ls; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.6.3 Caution + * when Changing the Speed Spontaneously) link speed change can be done + * only when the LTSSM is in L0. + */ + ret = readl_poll_timeout(host->axi + RZG3S_PCI_PCSTAT1, tmp, + FIELD_GET(RZG3S_PCI_PCSTAT1_LTSSM_STATE, tmp) == ltssm_state_l0, + PCIE_LINK_WAIT_SLEEP_MS * MILLI, + PCIE_LINK_WAIT_SLEEP_MS * MILLI * + PCIE_LINK_WAIT_MAX_RETRIES); + if (ret) + return ret; + + ls = readw_relaxed(host->pcie + pcie_cap + PCI_EXP_LNKSTA); + cs2 = readl_relaxed(host->axi + RZG3S_PCI_PCSTAT2); + + switch (pcie_link_speed[host->max_link_speed]) { + case PCIE_SPEED_5_0GT: + max_supported_link_speeds = GENMASK(PCI_EXP_LNKSTA_CLS_5_0GB - 1, 0); + link_speed = PCI_EXP_LNKCTL2_TLS_5_0GT; + break; + default: + /* Should not happen */ + return -EINVAL; + } + + cur_link_speed = FIELD_GET(PCI_EXP_LNKSTA_CLS, ls); + remote_supported_link_speeds = FIELD_GET(RZG3S_PCI_PCSTAT2_SDRIRE, cs2); + /* Drop reserved bits */ + remote_supported_link_speeds &= max_supported_link_speeds; + + /* + * Return if max link speed is already set or the connected device + * doesn't support it. + */ + if (cur_link_speed == host->max_link_speed || + remote_supported_link_speeds != max_supported_link_speeds) + return 0; + + /* Set target Link speed */ + rzg3s_pcie_update_bits(host->pcie, pcie_cap + PCI_EXP_LNKCTL2, + PCI_EXP_LNKCTL2_TLS, + FIELD_PREP(PCI_EXP_LNKCTL2_TLS, link_speed)); + + /* Request link speed change */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PCCTRL2, + RZG3S_PCI_PCCTRL2_LS_CHG_REQ | + RZG3S_PCI_PCCTRL2_LS_CHG, + RZG3S_PCI_PCCTRL2_LS_CHG_REQ | + FIELD_PREP(RZG3S_PCI_PCCTRL2_LS_CHG, + link_speed - 1)); + + ret = readl_poll_timeout(host->axi + RZG3S_PCI_PCSTAT2, cs2, + (cs2 & RZG3S_PCI_PCSTAT2_LS_CHG_DONE), + PCIE_LINK_WAIT_SLEEP_MS * MILLI, + PCIE_LINK_WAIT_SLEEP_MS * MILLI * + PCIE_LINK_WAIT_MAX_RETRIES); + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.6.3 Caution + * when Changing the Speed Spontaneously) the PCI_PCCTRL2_LS_CHG_REQ + * should be de-asserted after checking for PCI_PCSTAT2_LS_CHG_DONE. + */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PCCTRL2, + RZG3S_PCI_PCCTRL2_LS_CHG_REQ, 0); + + return ret; +} + +static int rzg3s_pcie_config_init(struct rzg3s_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *ft; + struct resource *bus; + u8 subordinate_bus; + u8 secondary_bus; + u8 primary_bus; + + ft = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!ft) + return -ENODEV; + + bus = ft->res; + primary_bus = bus->start; + secondary_bus = bus->start + 1; + subordinate_bus = bus->end; + + /* Enable access control to the CFGU */ + writel_relaxed(RZG3S_PCI_PERM_CFG_HWINIT_EN, + host->axi + RZG3S_PCI_PERM); + + /* HW manual recommends to write 0xffffffff on initialization */ + writel_relaxed(0xffffffff, host->pcie + RZG3S_PCI_CFG_BARMSK00L); + writel_relaxed(0xffffffff, host->pcie + RZG3S_PCI_CFG_BARMSK00U); + + /* Update bus info */ + writeb_relaxed(primary_bus, host->pcie + PCI_PRIMARY_BUS); + writeb_relaxed(secondary_bus, host->pcie + PCI_SECONDARY_BUS); + writeb_relaxed(subordinate_bus, host->pcie + PCI_SUBORDINATE_BUS); + + /* Disable access control to the CFGU */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + return 0; +} + +static void rzg3s_pcie_irq_init(struct rzg3s_pcie_host *host) +{ + /* + * According to the HW manual of the RZ/G3S (Rev.1.10, sections + * corresponding to all registers written with ~0U), the hardware + * ignores value written to unused bits. Writing ~0U to these registers + * should be safe. + */ + + /* Clear the link state and PM transitions */ + writel_relaxed(RZG3S_PCI_PEIS0_DL_UPDOWN | + RZG3S_PCI_PEIS0_RX_DLLP_PM_ENTER, + host->axi + RZG3S_PCI_PEIS0); + + /* Disable all interrupts */ + writel_relaxed(0, host->axi + RZG3S_PCI_PEIE0); + + /* Clear all parity and ecc error interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_PEIS1); + + /* Disable all parity and ecc error interrupts */ + writel_relaxed(0, host->axi + RZG3S_PCI_PEIE1); + + /* Clear all AXI master error interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_AMEIS); + + /* Clear all AXI slave error interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_ASEIS1); + + /* Clear all message receive interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_MSGRCVIS); +} + +static int rzg3s_pcie_power_resets_deassert(struct rzg3s_pcie_host *host) +{ + const struct rzg3s_pcie_soc_data *data = host->data; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section + * 34.5.1.2 De-asserting the Reset) the PCIe IP needs to wait 5ms from + * power on to the de-assertion of reset. + */ + fsleep(5000); + return reset_control_bulk_deassert(data->num_power_resets, + host->power_resets); +} + +static int rzg3s_pcie_resets_prepare_and_get(struct rzg3s_pcie_host *host) +{ + const struct rzg3s_pcie_soc_data *data = host->data; + unsigned int i; + int ret; + + host->power_resets = devm_kmalloc_array(host->dev, + data->num_power_resets, + sizeof(*host->power_resets), + GFP_KERNEL); + if (!host->power_resets) + return -ENOMEM; + + for (i = 0; i < data->num_power_resets; i++) + host->power_resets[i].id = data->power_resets[i]; + + host->cfg_resets = devm_kmalloc_array(host->dev, + data->num_cfg_resets, + sizeof(*host->cfg_resets), + GFP_KERNEL); + if (!host->cfg_resets) + return -ENOMEM; + + for (i = 0; i < data->num_cfg_resets; i++) + host->cfg_resets[i].id = data->cfg_resets[i]; + + ret = devm_reset_control_bulk_get_exclusive(host->dev, + data->num_power_resets, + host->power_resets); + if (ret) + return ret; + + return devm_reset_control_bulk_get_exclusive(host->dev, + data->num_cfg_resets, + host->cfg_resets); +} + +static int rzg3s_pcie_host_parse_port(struct rzg3s_pcie_host *host) +{ + struct device_node *of_port = of_get_next_child(host->dev->of_node, NULL); + struct rzg3s_pcie_port *port = &host->port; + int ret; + + ret = of_property_read_u32(of_port, "vendor-id", &port->vendor_id); + if (ret) + return ret; + + ret = of_property_read_u32(of_port, "device-id", &port->device_id); + if (ret) + return ret; + + port->refclk = of_clk_get_by_name(of_port, "ref"); + if (IS_ERR(port->refclk)) + return PTR_ERR(port->refclk); + + return 0; +} + +static int rzg3s_pcie_host_init_port(struct rzg3s_pcie_host *host) +{ + struct rzg3s_pcie_port *port = &host->port; + struct device *dev = host->dev; + int ret; + + /* Enable access control to the CFGU */ + writel_relaxed(RZG3S_PCI_PERM_CFG_HWINIT_EN, + host->axi + RZG3S_PCI_PERM); + + /* Update vendor ID and device ID */ + writew_relaxed(port->vendor_id, host->pcie + PCI_VENDOR_ID); + writew_relaxed(port->device_id, host->pcie + PCI_DEVICE_ID); + + /* Disable access control to the CFGU */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + ret = clk_prepare_enable(port->refclk); + if (ret) + return dev_err_probe(dev, ret, "Failed to enable refclk!\n"); + + /* Set the PHY, if any */ + if (host->data->init_phy) { + ret = host->data->init_phy(host); + if (ret) { + dev_err_probe(dev, ret, "Failed to set the PHY!\n"); + goto refclk_disable; + } + } + + return 0; + +refclk_disable: + clk_disable_unprepare(port->refclk); + return ret; +} + +static int rzg3s_pcie_host_init(struct rzg3s_pcie_host *host) +{ + u32 val; + int ret; + + /* Initialize the PCIe related registers */ + ret = rzg3s_pcie_config_init(host); + if (ret) + return ret; + + ret = rzg3s_pcie_host_init_port(host); + if (ret) + return ret; + + /* Initialize the interrupts */ + rzg3s_pcie_irq_init(host); + + ret = reset_control_bulk_deassert(host->data->num_cfg_resets, + host->cfg_resets); + if (ret) + goto disable_port_refclk; + + /* Wait for link up */ + ret = readl_poll_timeout(host->axi + RZG3S_PCI_PCSTAT1, val, + !(val & RZG3S_PCI_PCSTAT1_DL_DOWN_STS), + PCIE_LINK_WAIT_SLEEP_MS * MILLI, + PCIE_LINK_WAIT_SLEEP_MS * MILLI * + PCIE_LINK_WAIT_MAX_RETRIES); + if (ret) + goto cfg_resets_deassert; + + val = readl_relaxed(host->axi + RZG3S_PCI_PCSTAT2); + dev_info(host->dev, "PCIe link status [0x%x]\n", val); + + return 0; + +cfg_resets_deassert: + reset_control_bulk_assert(host->data->num_cfg_resets, + host->cfg_resets); +disable_port_refclk: + clk_disable_unprepare(host->port.refclk); + return ret; +} + +static void rzg3s_pcie_set_inbound_window(struct rzg3s_pcie_host *host, + u64 cpu_addr, u64 pci_addr, u64 size, + int id) +{ + /* Set CPU window base address */ + writel_relaxed(upper_32_bits(cpu_addr), + host->axi + RZG3S_PCI_ADESTU(id)); + writel_relaxed(lower_32_bits(cpu_addr), + host->axi + RZG3S_PCI_ADESTL(id)); + + /* Set window size */ + writel_relaxed(upper_32_bits(size), host->axi + RZG3S_PCI_AWMASKU(id)); + writel_relaxed(lower_32_bits(size), host->axi + RZG3S_PCI_AWMASKL(id)); + + /* Set PCIe window base address and enable the window */ + writel_relaxed(upper_32_bits(pci_addr), + host->axi + RZG3S_PCI_AWBASEU(id)); + writel_relaxed(lower_32_bits(pci_addr) | RZG3S_PCI_AWBASEL_WIN_ENA, + host->axi + RZG3S_PCI_AWBASEL(id)); +} + +static int rzg3s_pcie_set_inbound_windows(struct rzg3s_pcie_host *host, + struct resource_entry *entry, + int *index) +{ + u64 pci_addr = entry->res->start - entry->offset; + u64 cpu_addr = entry->res->start; + u64 cpu_end = entry->res->end; + u64 size_id = 0; + int id = *index; + u64 size; + + while (cpu_addr < cpu_end) { + if (id >= RZG3S_MAX_WINDOWS) + return dev_err_probe(host->dev, -ENOSPC, + "Failed to map inbound window for resource (%s)\n", + entry->res->name); + + size = resource_size(entry->res) - size_id; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, + * section 34.3.1.71 AXI Window Mask (Lower) Registers) the min + * size is 4K. + */ + size = max(size, SZ_4K); + + /* + * According the RZ/G3S HW manual (Rev.1.10, sections: + * - 34.3.1.69 AXI Window Base (Lower) Registers + * - 34.3.1.71 AXI Window Mask (Lower) Registers + * - 34.3.1.73 AXI Destination (Lower) Registers) + * the CPU addr, PCIe addr, size should be 4K aligned and be a + * power of 2. + */ + size = ALIGN(size, SZ_4K); + size = roundup_pow_of_two(size); + + cpu_addr = ALIGN(cpu_addr, SZ_4K); + pci_addr = ALIGN(pci_addr, SZ_4K); + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section + * 34.3.1.71 AXI Window Mask (Lower) Registers) HW expects first + * 12 LSB bits to be 0xfff. Subtract 1 from size for this. + */ + rzg3s_pcie_set_inbound_window(host, cpu_addr, pci_addr, + size - 1, id); + + pci_addr += size; + cpu_addr += size; + size_id = size; + id++; + } + *index = id; + + return 0; +} + +static int rzg3s_pcie_parse_map_dma_ranges(struct rzg3s_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *entry; + int i = 0, ret; + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + ret = rzg3s_pcie_set_inbound_windows(host, entry, &i); + if (ret) + return ret; + } + + return 0; +} + +static void rzg3s_pcie_set_outbound_window(struct rzg3s_pcie_host *host, + struct resource_entry *win, int id) +{ + struct resource *res = win->res; + resource_size_t size = resource_size(res); + resource_size_t res_start; + + if (res->flags & IORESOURCE_IO) + res_start = pci_pio_to_address(res->start) - win->offset; + else + res_start = res->start - win->offset; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.3.1.75 PCIe + * Window Base (Lower) Registers) the window base address need to be 4K + * aligned. + */ + res_start = ALIGN(res_start, SZ_4K); + + size = ALIGN(size, SZ_4K); + size = roundup_pow_of_two(size) - 1; + + /* Set PCIe destination */ + writel_relaxed(upper_32_bits(res_start), + host->axi + RZG3S_PCI_PDESTU(id)); + writel_relaxed(lower_32_bits(res_start), + host->axi + RZG3S_PCI_PDESTL(id)); + + /* Set PCIe window mask */ + writel_relaxed(upper_32_bits(size), host->axi + RZG3S_PCI_PWMASKU(id)); + writel_relaxed(lower_32_bits(size), host->axi + RZG3S_PCI_PWMASKL(id)); + + /* Set PCIe window base and enable the window */ + writel_relaxed(upper_32_bits(res_start), + host->axi + RZG3S_PCI_PWBASEU(id)); + writel_relaxed(lower_32_bits(res_start) | RZG3S_PCI_PWBASEL_ENA, + host->axi + RZG3S_PCI_PWBASEL(id)); +} + +static int rzg3s_pcie_parse_map_ranges(struct rzg3s_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *win; + int i = 0; + + resource_list_for_each_entry(win, &bridge->windows) { + struct resource *res = win->res; + + if (i >= RZG3S_MAX_WINDOWS) + return dev_err_probe(host->dev, -ENOSPC, + "Failed to map outbound window for resource (%s)\n", + res->name); + + if (!res->flags) + continue; + + switch (resource_type(res)) { + case IORESOURCE_IO: + case IORESOURCE_MEM: + rzg3s_pcie_set_outbound_window(host, win, i); + i++; + break; + } + } + + return 0; +} + +static int rzg3s_soc_pcie_init_phy(struct rzg3s_pcie_host *host) +{ + static const u32 xcfgd_settings[RZG3S_PCI_PHY_XCFGD_NUM] = { + [8] = 0xe0006801, 0x007f7e30, 0x183e0000, 0x978ff500, + 0xec000000, 0x009f1400, 0x0000d009, + [17] = 0x78000000, + [19] = 0x00880000, 0x000005c0, 0x07000000, 0x00780920, + 0xc9400ce2, 0x90000c0c, 0x000c1414, 0x00005034, + 0x00006000, 0x00000001, + }; + static const u32 xcfga_cmn_settings[RZG3S_PCI_PHY_XCFGA_CMN_NUM] = { + 0x00000d10, 0x08310100, 0x00c21404, 0x013c0010, 0x01874440, + 0x1a216082, 0x00103440, 0x00000080, 0x00000010, 0x0c1000c1, + 0x1000c100, 0x0222000c, 0x00640019, 0x00a00028, 0x01d11228, + 0x0201001d, + }; + static const u32 xcfga_rx_settings[RZG3S_PCI_PHY_XCFGA_RX_NUM] = { + 0x07d55000, 0x030e3f00, 0x00000288, 0x102c5880, 0x0000000b, + 0x04141441, 0x00641641, 0x00d63d63, 0x00641641, 0x01970377, + 0x00190287, 0x00190028, 0x00000028, + }; + unsigned int i; + + /* + * Enable access permission for physical layer control and status + * registers. + */ + writel_relaxed(RZG3S_PCI_PERM_PIPE_PHY_REG_EN, + host->axi + RZG3S_PCI_PERM); + + for (i = 0; i < RZG3S_PCI_PHY_XCFGD_NUM; i++) { + writel_relaxed(xcfgd_settings[i], + host->axi + RZG3S_PCI_PHY_XCFGD(i)); + } + + for (i = 0; i < RZG3S_PCI_PHY_XCFGA_CMN_NUM; i++) { + writel_relaxed(xcfga_cmn_settings[i], + host->axi + RZG3S_PCI_PHY_XCFGA_CMN(i)); + } + + for (i = 0; i < RZG3S_PCI_PHY_XCFGA_RX_NUM; i++) { + writel_relaxed(xcfga_rx_settings[i], + host->axi + RZG3S_PCI_PHY_XCFGA_RX(i)); + } + + writel_relaxed(0x107, host->axi + RZG3S_PCI_PHY_XCFGA_TX); + + /* Select PHY settings values */ + writel_relaxed(RZG3S_PCI_PHY_XCFG_CTRL_PHYREG_SEL, + host->axi + RZG3S_PCI_PHY_XCFG_CTRL); + + /* + * Disable access permission for physical layer control and status + * registers. + */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + return 0; +} + +static int +rzg3s_pcie_host_setup(struct rzg3s_pcie_host *host, + int (*init_irqdomain)(struct rzg3s_pcie_host *host), + void (*teardown_irqdomain)(struct rzg3s_pcie_host *host)) +{ + struct device *dev = host->dev; + int ret; + + /* Set inbound windows */ + ret = rzg3s_pcie_parse_map_dma_ranges(host); + if (ret) + return dev_err_probe(dev, ret, + "Failed to set inbound windows!\n"); + + /* Set outbound windows */ + ret = rzg3s_pcie_parse_map_ranges(host); + if (ret) + return dev_err_probe(dev, ret, + "Failed to set outbound windows!\n"); + + ret = init_irqdomain(host); + if (ret) + return dev_err_probe(dev, ret, "Failed to init IRQ domain\n"); + + ret = rzg3s_pcie_host_init(host); + if (ret) { + dev_err_probe(dev, ret, "Failed to initialize the HW!\n"); + goto teardown_irqdomain; + } + + ret = rzg3s_pcie_set_max_link_speed(host); + if (ret) + dev_info(dev, "Failed to set max link speed\n"); + + msleep(PCIE_RESET_CONFIG_WAIT_MS); + + return 0; + +teardown_irqdomain: + teardown_irqdomain(host); + + return ret; +} + +static int rzg3s_pcie_probe(struct platform_device *pdev) +{ + struct pci_host_bridge *bridge; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct device_node *sysc_np __free(device_node) = + of_parse_phandle(np, "renesas,sysc", 0); + struct rzg3s_pcie_host *host; + int ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*host)); + if (!bridge) + return -ENOMEM; + + host = pci_host_bridge_priv(bridge); + host->dev = dev; + host->data = device_get_match_data(dev); + platform_set_drvdata(pdev, host); + + host->axi = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(host->axi)) + return PTR_ERR(host->axi); + host->pcie = host->axi + RZG3S_PCI_CFG_BASE; + + host->max_link_speed = of_pci_get_max_link_speed(np); + if (host->max_link_speed < 0) + host->max_link_speed = 2; + + ret = rzg3s_pcie_host_parse_port(host); + if (ret) + return ret; + + host->sysc = syscon_node_to_regmap(sysc_np); + if (IS_ERR(host->sysc)) { + ret = PTR_ERR(host->sysc); + goto port_refclk_put; + } + + ret = regmap_update_bits(host->sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 1)); + if (ret) + goto port_refclk_put; + + ret = rzg3s_pcie_resets_prepare_and_get(host); + if (ret) + goto sysc_signal_restore; + + ret = rzg3s_pcie_power_resets_deassert(host); + if (ret) + goto sysc_signal_restore; + + pm_runtime_enable(dev); + + /* + * Controller clocks are part of a clock power domain. Enable them + * through runtime PM. + */ + ret = pm_runtime_resume_and_get(dev); + if (ret) + goto rpm_disable; + + raw_spin_lock_init(&host->hw_lock); + + ret = rzg3s_pcie_host_setup(host, rzg3s_pcie_init_irqdomain, + rzg3s_pcie_teardown_irqdomain); + if (ret) + goto rpm_put; + + bridge->sysdata = host; + bridge->ops = &rzg3s_pcie_root_ops; + bridge->child_ops = &rzg3s_pcie_child_ops; + ret = pci_host_probe(bridge); + if (ret) + goto host_probe_teardown; + + return 0; + +host_probe_teardown: + rzg3s_pcie_teardown_irqdomain(host); + reset_control_bulk_deassert(host->data->num_cfg_resets, + host->cfg_resets); +rpm_put: + pm_runtime_put_sync(dev); +rpm_disable: + pm_runtime_disable(dev); + reset_control_bulk_assert(host->data->num_power_resets, + host->power_resets); +sysc_signal_restore: + /* + * SYSC RST_RSM_B signal need to be asserted before turning off the + * power to the PHY. + */ + regmap_update_bits(host->sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 0)); +port_refclk_put: + clk_put(host->port.refclk); + + return ret; +} + +static int rzg3s_pcie_suspend_noirq(struct device *dev) +{ + struct rzg3s_pcie_host *host = dev_get_drvdata(dev); + const struct rzg3s_pcie_soc_data *data = host->data; + struct rzg3s_pcie_port *port = &host->port; + struct regmap *sysc = host->sysc; + int ret; + + ret = pm_runtime_put_sync(dev); + if (ret) + return ret; + + clk_disable_unprepare(port->refclk); + + ret = reset_control_bulk_assert(data->num_power_resets, + host->power_resets); + if (ret) + goto refclk_restore; + + ret = reset_control_bulk_assert(data->num_cfg_resets, + host->cfg_resets); + if (ret) + goto power_resets_restore; + + ret = regmap_update_bits(sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 0)); + if (ret) + goto cfg_resets_restore; + + return 0; + + /* Restore the previous state if any error happens */ +cfg_resets_restore: + reset_control_bulk_deassert(data->num_cfg_resets, + host->cfg_resets); +power_resets_restore: + reset_control_bulk_deassert(data->num_power_resets, + host->power_resets); +refclk_restore: + clk_prepare_enable(port->refclk); + pm_runtime_resume_and_get(dev); + return ret; +} + +static int rzg3s_pcie_resume_noirq(struct device *dev) +{ + struct rzg3s_pcie_host *host = dev_get_drvdata(dev); + const struct rzg3s_pcie_soc_data *data = host->data; + struct regmap *sysc = host->sysc; + int ret; + + ret = regmap_update_bits(sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 1)); + if (ret) + return ret; + + ret = rzg3s_pcie_power_resets_deassert(host); + if (ret) + goto assert_rst_rsm_b; + + ret = pm_runtime_resume_and_get(dev); + if (ret) + goto assert_power_resets; + + ret = rzg3s_pcie_host_setup(host, rzg3s_pcie_msi_hw_setup, + rzg3s_pcie_msi_hw_teardown); + if (ret) + goto rpm_put; + + return 0; + + /* + * If any error happens there is no way to recover the IP. Put it in the + * lowest possible power state. + */ +rpm_put: + pm_runtime_put_sync(dev); +assert_power_resets: + reset_control_bulk_assert(data->num_power_resets, + host->power_resets); +assert_rst_rsm_b: + regmap_update_bits(sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 0)); + return ret; +} + +static const struct dev_pm_ops rzg3s_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(rzg3s_pcie_suspend_noirq, + rzg3s_pcie_resume_noirq) +}; + +static const char * const rzg3s_soc_power_resets[] = { + "aresetn", "rst_cfg_b", "rst_load_b", +}; + +static const char * const rzg3s_soc_cfg_resets[] = { + "rst_b", "rst_ps_b", "rst_gp_b", "rst_rsm_b", +}; + +static const struct rzg3s_pcie_soc_data rzg3s_soc_data = { + .power_resets = rzg3s_soc_power_resets, + .num_power_resets = ARRAY_SIZE(rzg3s_soc_power_resets), + .cfg_resets = rzg3s_soc_cfg_resets, + .num_cfg_resets = ARRAY_SIZE(rzg3s_soc_cfg_resets), + .init_phy = rzg3s_soc_pcie_init_phy, +}; + +static const struct of_device_id rzg3s_pcie_of_match[] = { + { + .compatible = "renesas,r9a08g045-pcie", + .data = &rzg3s_soc_data, + }, + {} +}; + +static struct platform_driver rzg3s_pcie_driver = { + .driver = { + .name = "rzg3s-pcie-host", + .of_match_table = rzg3s_pcie_of_match, + .pm = pm_ptr(&rzg3s_pcie_pm_ops), + .suppress_bind_attrs = true, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = rzg3s_pcie_probe, +}; +builtin_platform_driver(rzg3s_pcie_driver); diff --git a/drivers/pci/controller/pcie-tango.c b/drivers/pci/controller/pcie-tango.c deleted file mode 100644 index 21a208da3f59..000000000000 --- a/drivers/pci/controller/pcie-tango.c +++ /dev/null @@ -1,341 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/irqchip/chained_irq.h> -#include <linux/irqdomain.h> -#include <linux/pci-ecam.h> -#include <linux/delay.h> -#include <linux/msi.h> -#include <linux/of_address.h> - -#define MSI_MAX 256 - -#define SMP8759_MUX 0x48 -#define SMP8759_TEST_OUT 0x74 -#define SMP8759_DOORBELL 0x7c -#define SMP8759_STATUS 0x80 -#define SMP8759_ENABLE 0xa0 - -struct tango_pcie { - DECLARE_BITMAP(used_msi, MSI_MAX); - u64 msi_doorbell; - spinlock_t used_msi_lock; - void __iomem *base; - struct irq_domain *dom; -}; - -static void tango_msi_isr(struct irq_desc *desc) -{ - struct irq_chip *chip = irq_desc_get_chip(desc); - struct tango_pcie *pcie = irq_desc_get_handler_data(desc); - unsigned long status, base, virq, idx, pos = 0; - - chained_irq_enter(chip, desc); - spin_lock(&pcie->used_msi_lock); - - while ((pos = find_next_bit(pcie->used_msi, MSI_MAX, pos)) < MSI_MAX) { - base = round_down(pos, 32); - status = readl_relaxed(pcie->base + SMP8759_STATUS + base / 8); - for_each_set_bit(idx, &status, 32) { - virq = irq_find_mapping(pcie->dom, base + idx); - generic_handle_irq(virq); - } - pos = base + 32; - } - - spin_unlock(&pcie->used_msi_lock); - chained_irq_exit(chip, desc); -} - -static void tango_ack(struct irq_data *d) -{ - struct tango_pcie *pcie = d->chip_data; - u32 offset = (d->hwirq / 32) * 4; - u32 bit = BIT(d->hwirq % 32); - - writel_relaxed(bit, pcie->base + SMP8759_STATUS + offset); -} - -static void update_msi_enable(struct irq_data *d, bool unmask) -{ - unsigned long flags; - struct tango_pcie *pcie = d->chip_data; - u32 offset = (d->hwirq / 32) * 4; - u32 bit = BIT(d->hwirq % 32); - u32 val; - - spin_lock_irqsave(&pcie->used_msi_lock, flags); - val = readl_relaxed(pcie->base + SMP8759_ENABLE + offset); - val = unmask ? val | bit : val & ~bit; - writel_relaxed(val, pcie->base + SMP8759_ENABLE + offset); - spin_unlock_irqrestore(&pcie->used_msi_lock, flags); -} - -static void tango_mask(struct irq_data *d) -{ - update_msi_enable(d, false); -} - -static void tango_unmask(struct irq_data *d) -{ - update_msi_enable(d, true); -} - -static int tango_set_affinity(struct irq_data *d, const struct cpumask *mask, - bool force) -{ - return -EINVAL; -} - -static void tango_compose_msi_msg(struct irq_data *d, struct msi_msg *msg) -{ - struct tango_pcie *pcie = d->chip_data; - msg->address_lo = lower_32_bits(pcie->msi_doorbell); - msg->address_hi = upper_32_bits(pcie->msi_doorbell); - msg->data = d->hwirq; -} - -static struct irq_chip tango_chip = { - .irq_ack = tango_ack, - .irq_mask = tango_mask, - .irq_unmask = tango_unmask, - .irq_set_affinity = tango_set_affinity, - .irq_compose_msi_msg = tango_compose_msi_msg, -}; - -static void msi_ack(struct irq_data *d) -{ - irq_chip_ack_parent(d); -} - -static void msi_mask(struct irq_data *d) -{ - pci_msi_mask_irq(d); - irq_chip_mask_parent(d); -} - -static void msi_unmask(struct irq_data *d) -{ - pci_msi_unmask_irq(d); - irq_chip_unmask_parent(d); -} - -static struct irq_chip msi_chip = { - .name = "MSI", - .irq_ack = msi_ack, - .irq_mask = msi_mask, - .irq_unmask = msi_unmask, -}; - -static struct msi_domain_info msi_dom_info = { - .flags = MSI_FLAG_PCI_MSIX - | MSI_FLAG_USE_DEF_DOM_OPS - | MSI_FLAG_USE_DEF_CHIP_OPS, - .chip = &msi_chip, -}; - -static int tango_irq_domain_alloc(struct irq_domain *dom, unsigned int virq, - unsigned int nr_irqs, void *args) -{ - struct tango_pcie *pcie = dom->host_data; - unsigned long flags; - int pos; - - spin_lock_irqsave(&pcie->used_msi_lock, flags); - pos = find_first_zero_bit(pcie->used_msi, MSI_MAX); - if (pos >= MSI_MAX) { - spin_unlock_irqrestore(&pcie->used_msi_lock, flags); - return -ENOSPC; - } - __set_bit(pos, pcie->used_msi); - spin_unlock_irqrestore(&pcie->used_msi_lock, flags); - irq_domain_set_info(dom, virq, pos, &tango_chip, - pcie, handle_edge_irq, NULL, NULL); - - return 0; -} - -static void tango_irq_domain_free(struct irq_domain *dom, unsigned int virq, - unsigned int nr_irqs) -{ - unsigned long flags; - struct irq_data *d = irq_domain_get_irq_data(dom, virq); - struct tango_pcie *pcie = d->chip_data; - - spin_lock_irqsave(&pcie->used_msi_lock, flags); - __clear_bit(d->hwirq, pcie->used_msi); - spin_unlock_irqrestore(&pcie->used_msi_lock, flags); -} - -static const struct irq_domain_ops dom_ops = { - .alloc = tango_irq_domain_alloc, - .free = tango_irq_domain_free, -}; - -static int smp8759_config_read(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 *val) -{ - struct pci_config_window *cfg = bus->sysdata; - struct tango_pcie *pcie = dev_get_drvdata(cfg->parent); - int ret; - - /* Reads in configuration space outside devfn 0 return garbage */ - if (devfn != 0) - return PCIBIOS_FUNC_NOT_SUPPORTED; - - /* - * PCI config and MMIO accesses are muxed. Linux doesn't have a - * mutual exclusion mechanism for config vs. MMIO accesses, so - * concurrent accesses may cause corruption. - */ - writel_relaxed(1, pcie->base + SMP8759_MUX); - ret = pci_generic_config_read(bus, devfn, where, size, val); - writel_relaxed(0, pcie->base + SMP8759_MUX); - - return ret; -} - -static int smp8759_config_write(struct pci_bus *bus, unsigned int devfn, - int where, int size, u32 val) -{ - struct pci_config_window *cfg = bus->sysdata; - struct tango_pcie *pcie = dev_get_drvdata(cfg->parent); - int ret; - - writel_relaxed(1, pcie->base + SMP8759_MUX); - ret = pci_generic_config_write(bus, devfn, where, size, val); - writel_relaxed(0, pcie->base + SMP8759_MUX); - - return ret; -} - -static struct pci_ecam_ops smp8759_ecam_ops = { - .bus_shift = 20, - .pci_ops = { - .map_bus = pci_ecam_map_bus, - .read = smp8759_config_read, - .write = smp8759_config_write, - } -}; - -static int tango_pcie_link_up(struct tango_pcie *pcie) -{ - void __iomem *test_out = pcie->base + SMP8759_TEST_OUT; - int i; - - writel_relaxed(16, test_out); - for (i = 0; i < 10; ++i) { - u32 ltssm_state = readl_relaxed(test_out) >> 8; - if ((ltssm_state & 0x1f) == 0xf) /* L0 */ - return 1; - usleep_range(3000, 4000); - } - - return 0; -} - -static int tango_pcie_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - struct tango_pcie *pcie; - struct resource *res; - struct fwnode_handle *fwnode = of_node_to_fwnode(dev->of_node); - struct irq_domain *msi_dom, *irq_dom; - struct of_pci_range_parser parser; - struct of_pci_range range; - int virq, offset; - - dev_warn(dev, "simultaneous PCI config and MMIO accesses may cause data corruption\n"); - add_taint(TAINT_CRAP, LOCKDEP_STILL_OK); - - pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); - if (!pcie) - return -ENOMEM; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - pcie->base = devm_ioremap_resource(dev, res); - if (IS_ERR(pcie->base)) - return PTR_ERR(pcie->base); - - platform_set_drvdata(pdev, pcie); - - if (!tango_pcie_link_up(pcie)) - return -ENODEV; - - if (of_pci_dma_range_parser_init(&parser, dev->of_node) < 0) - return -ENOENT; - - if (of_pci_range_parser_one(&parser, &range) == NULL) - return -ENOENT; - - range.pci_addr += range.size; - pcie->msi_doorbell = range.pci_addr + res->start + SMP8759_DOORBELL; - - for (offset = 0; offset < MSI_MAX / 8; offset += 4) - writel_relaxed(0, pcie->base + SMP8759_ENABLE + offset); - - virq = platform_get_irq(pdev, 1); - if (virq <= 0) { - dev_err(dev, "Failed to map IRQ\n"); - return -ENXIO; - } - - irq_dom = irq_domain_create_linear(fwnode, MSI_MAX, &dom_ops, pcie); - if (!irq_dom) { - dev_err(dev, "Failed to create IRQ domain\n"); - return -ENOMEM; - } - - msi_dom = pci_msi_create_irq_domain(fwnode, &msi_dom_info, irq_dom); - if (!msi_dom) { - dev_err(dev, "Failed to create MSI domain\n"); - irq_domain_remove(irq_dom); - return -ENOMEM; - } - - pcie->dom = irq_dom; - spin_lock_init(&pcie->used_msi_lock); - irq_set_chained_handler_and_data(virq, tango_msi_isr, pcie); - - return pci_host_common_probe(pdev, &smp8759_ecam_ops); -} - -static const struct of_device_id tango_pcie_ids[] = { - { .compatible = "sigma,smp8759-pcie" }, - { }, -}; - -static struct platform_driver tango_pcie_driver = { - .probe = tango_pcie_probe, - .driver = { - .name = KBUILD_MODNAME, - .of_match_table = tango_pcie_ids, - .suppress_bind_attrs = true, - }, -}; -builtin_platform_driver(tango_pcie_driver); - -/* - * The root complex advertises the wrong device class. - * Header Type 1 is for PCI-to-PCI bridges. - */ -static void tango_fixup_class(struct pci_dev *dev) -{ - dev->class = PCI_CLASS_BRIDGE_PCI << 8; -} -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIGMA, 0x0024, tango_fixup_class); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIGMA, 0x0028, tango_fixup_class); - -/* - * The root complex exposes a "fake" BAR, which is used to filter - * bus-to-system accesses. Only accesses within the range defined by this - * BAR are forwarded to the host, others are ignored. - * - * By default, the DMA framework expects an identity mapping, and DRAM0 is - * mapped at 0x80000000. - */ -static void tango_fixup_bar(struct pci_dev *dev) -{ - dev->non_compliant_bars = true; - pci_write_config_dword(dev, PCI_BASE_ADDRESS_0, 0x80000000); -} -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIGMA, 0x0024, tango_fixup_bar); -DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIGMA, 0x0028, tango_fixup_bar); diff --git a/drivers/pci/controller/pcie-xilinx-common.h b/drivers/pci/controller/pcie-xilinx-common.h new file mode 100644 index 000000000000..1832770f3308 --- /dev/null +++ b/drivers/pci/controller/pcie-xilinx-common.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * (C) Copyright 2023, Xilinx, Inc. + */ + +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> + +/* Interrupt registers definitions */ +#define XILINX_PCIE_INTR_LINK_DOWN 0 +#define XILINX_PCIE_INTR_HOT_RESET 3 +#define XILINX_PCIE_INTR_CFG_PCIE_TIMEOUT 4 +#define XILINX_PCIE_INTR_CFG_TIMEOUT 8 +#define XILINX_PCIE_INTR_CORRECTABLE 9 +#define XILINX_PCIE_INTR_NONFATAL 10 +#define XILINX_PCIE_INTR_FATAL 11 +#define XILINX_PCIE_INTR_CFG_ERR_POISON 12 +#define XILINX_PCIE_INTR_PME_TO_ACK_RCVD 15 +#define XILINX_PCIE_INTR_INTX 16 +#define XILINX_PCIE_INTR_PM_PME_RCVD 17 +#define XILINX_PCIE_INTR_MSI 17 +#define XILINX_PCIE_INTR_SLV_UNSUPP 20 +#define XILINX_PCIE_INTR_SLV_UNEXP 21 +#define XILINX_PCIE_INTR_SLV_COMPL 22 +#define XILINX_PCIE_INTR_SLV_ERRP 23 +#define XILINX_PCIE_INTR_SLV_CMPABT 24 +#define XILINX_PCIE_INTR_SLV_ILLBUR 25 +#define XILINX_PCIE_INTR_MST_DECERR 26 +#define XILINX_PCIE_INTR_MST_SLVERR 27 +#define XILINX_PCIE_INTR_SLV_PCIE_TIMEOUT 28 diff --git a/drivers/pci/controller/pcie-xilinx-cpm.c b/drivers/pci/controller/pcie-xilinx-cpm.c new file mode 100644 index 000000000000..d38f27e20761 --- /dev/null +++ b/drivers/pci/controller/pcie-xilinx-cpm.c @@ -0,0 +1,686 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for Xilinx Versal CPM DMA Bridge + * + * (C) Copyright 2019 - 2020, Xilinx, Inc. + */ + +#include <linux/bitfield.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqchip.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> + +#include "../pci.h" +#include "pcie-xilinx-common.h" + +/* Register definitions */ +#define XILINX_CPM_PCIE_REG_IDR 0x00000E10 +#define XILINX_CPM_PCIE_REG_IMR 0x00000E14 +#define XILINX_CPM_PCIE_REG_PSCR 0x00000E1C +#define XILINX_CPM_PCIE_REG_RPSC 0x00000E20 +#define XILINX_CPM_PCIE_REG_RPEFR 0x00000E2C +#define XILINX_CPM_PCIE_REG_IDRN 0x00000E38 +#define XILINX_CPM_PCIE_REG_IDRN_MASK 0x00000E3C +#define XILINX_CPM_PCIE_MISC_IR_STATUS 0x00000340 +#define XILINX_CPM_PCIE_MISC_IR_ENABLE 0x00000348 +#define XILINX_CPM_PCIE0_MISC_IR_LOCAL BIT(1) +#define XILINX_CPM_PCIE1_MISC_IR_LOCAL BIT(2) + +#define XILINX_CPM_PCIE0_IR_STATUS 0x000002A0 +#define XILINX_CPM_PCIE1_IR_STATUS 0x000002B4 +#define XILINX_CPM_PCIE0_IR_ENABLE 0x000002A8 +#define XILINX_CPM_PCIE1_IR_ENABLE 0x000002BC +#define XILINX_CPM_PCIE_IR_LOCAL BIT(0) + +#define IMR(x) BIT(XILINX_PCIE_INTR_ ##x) + +#define XILINX_CPM_PCIE_IMR_ALL_MASK \ + ( \ + IMR(LINK_DOWN) | \ + IMR(HOT_RESET) | \ + IMR(CFG_PCIE_TIMEOUT) | \ + IMR(CFG_TIMEOUT) | \ + IMR(CORRECTABLE) | \ + IMR(NONFATAL) | \ + IMR(FATAL) | \ + IMR(CFG_ERR_POISON) | \ + IMR(PME_TO_ACK_RCVD) | \ + IMR(INTX) | \ + IMR(PM_PME_RCVD) | \ + IMR(SLV_UNSUPP) | \ + IMR(SLV_UNEXP) | \ + IMR(SLV_COMPL) | \ + IMR(SLV_ERRP) | \ + IMR(SLV_CMPABT) | \ + IMR(SLV_ILLBUR) | \ + IMR(MST_DECERR) | \ + IMR(MST_SLVERR) | \ + IMR(SLV_PCIE_TIMEOUT) \ + ) + +#define XILINX_CPM_PCIE_IDR_ALL_MASK 0xFFFFFFFF +#define XILINX_CPM_PCIE_IDRN_MASK GENMASK(19, 16) +#define XILINX_CPM_PCIE_IDRN_SHIFT 16 + +/* Root Port Error FIFO Read Register definitions */ +#define XILINX_CPM_PCIE_RPEFR_ERR_VALID BIT(18) +#define XILINX_CPM_PCIE_RPEFR_REQ_ID GENMASK(15, 0) +#define XILINX_CPM_PCIE_RPEFR_ALL_MASK 0xFFFFFFFF + +/* Root Port Status/control Register definitions */ +#define XILINX_CPM_PCIE_REG_RPSC_BEN BIT(0) + +/* Phy Status/Control Register definitions */ +#define XILINX_CPM_PCIE_REG_PSCR_LNKUP BIT(11) + +enum xilinx_cpm_version { + CPM, + CPM5, + CPM5_HOST1, + CPM5NC_HOST, +}; + +/** + * struct xilinx_cpm_variant - CPM variant information + * @version: CPM version + * @ir_status: Offset for the error interrupt status register + * @ir_enable: Offset for the CPM5 local error interrupt enable register + * @ir_misc_value: A bitmask for the miscellaneous interrupt status + */ +struct xilinx_cpm_variant { + enum xilinx_cpm_version version; + u32 ir_status; + u32 ir_enable; + u32 ir_misc_value; +}; + +/** + * struct xilinx_cpm_pcie - PCIe port information + * @dev: Device pointer + * @reg_base: Bridge Register Base + * @cpm_base: CPM System Level Control and Status Register(SLCR) Base + * @intx_domain: Legacy IRQ domain pointer + * @cpm_domain: CPM IRQ domain pointer + * @cfg: Holds mappings of config space window + * @intx_irq: legacy interrupt number + * @irq: Error interrupt number + * @lock: lock protecting shared register access + * @variant: CPM version check pointer + */ +struct xilinx_cpm_pcie { + struct device *dev; + void __iomem *reg_base; + void __iomem *cpm_base; + struct irq_domain *intx_domain; + struct irq_domain *cpm_domain; + struct pci_config_window *cfg; + int intx_irq; + int irq; + raw_spinlock_t lock; + const struct xilinx_cpm_variant *variant; +}; + +static u32 pcie_read(struct xilinx_cpm_pcie *port, u32 reg) +{ + return readl_relaxed(port->reg_base + reg); +} + +static void pcie_write(struct xilinx_cpm_pcie *port, + u32 val, u32 reg) +{ + writel_relaxed(val, port->reg_base + reg); +} + +static bool cpm_pcie_link_up(struct xilinx_cpm_pcie *port) +{ + return (pcie_read(port, XILINX_CPM_PCIE_REG_PSCR) & + XILINX_CPM_PCIE_REG_PSCR_LNKUP); +} + +static void cpm_pcie_clear_err_interrupts(struct xilinx_cpm_pcie *port) +{ + unsigned long val = pcie_read(port, XILINX_CPM_PCIE_REG_RPEFR); + + if (val & XILINX_CPM_PCIE_RPEFR_ERR_VALID) { + dev_dbg(port->dev, "Requester ID %lu\n", + val & XILINX_CPM_PCIE_RPEFR_REQ_ID); + pcie_write(port, XILINX_CPM_PCIE_RPEFR_ALL_MASK, + XILINX_CPM_PCIE_REG_RPEFR); + } +} + +static void xilinx_cpm_mask_leg_irq(struct irq_data *data) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask; + u32 val; + + mask = BIT(data->hwirq + XILINX_CPM_PCIE_IDRN_SHIFT); + raw_spin_lock_irqsave(&port->lock, flags); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IDRN_MASK); + pcie_write(port, (val & (~mask)), XILINX_CPM_PCIE_REG_IDRN_MASK); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void xilinx_cpm_unmask_leg_irq(struct irq_data *data) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask; + u32 val; + + mask = BIT(data->hwirq + XILINX_CPM_PCIE_IDRN_SHIFT); + raw_spin_lock_irqsave(&port->lock, flags); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IDRN_MASK); + pcie_write(port, (val | mask), XILINX_CPM_PCIE_REG_IDRN_MASK); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip xilinx_cpm_leg_irq_chip = { + .name = "INTx", + .irq_mask = xilinx_cpm_mask_leg_irq, + .irq_unmask = xilinx_cpm_unmask_leg_irq, +}; + +/** + * xilinx_cpm_pcie_intx_map - Set the handler for the INTx and mark IRQ as valid + * @domain: IRQ domain + * @irq: Virtual IRQ number + * @hwirq: HW interrupt number + * + * Return: Always returns 0. + */ +static int xilinx_cpm_pcie_intx_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &xilinx_cpm_leg_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + + return 0; +} + +/* INTx IRQ Domain operations */ +static const struct irq_domain_ops intx_domain_ops = { + .map = xilinx_cpm_pcie_intx_map, +}; + +static void xilinx_cpm_pcie_intx_flow(struct irq_desc *desc) +{ + struct xilinx_cpm_pcie *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long val; + int i; + + chained_irq_enter(chip, desc); + + val = FIELD_GET(XILINX_CPM_PCIE_IDRN_MASK, + pcie_read(port, XILINX_CPM_PCIE_REG_IDRN)); + + for_each_set_bit(i, &val, PCI_NUM_INTX) + generic_handle_domain_irq(port->intx_domain, i); + + chained_irq_exit(chip, desc); +} + +static void xilinx_cpm_mask_event_irq(struct irq_data *d) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(d); + u32 val; + + raw_spin_lock(&port->lock); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IMR); + val &= ~BIT(d->hwirq); + pcie_write(port, val, XILINX_CPM_PCIE_REG_IMR); + raw_spin_unlock(&port->lock); +} + +static void xilinx_cpm_unmask_event_irq(struct irq_data *d) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(d); + u32 val; + + raw_spin_lock(&port->lock); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IMR); + val |= BIT(d->hwirq); + pcie_write(port, val, XILINX_CPM_PCIE_REG_IMR); + raw_spin_unlock(&port->lock); +} + +static struct irq_chip xilinx_cpm_event_irq_chip = { + .name = "RC-Event", + .irq_mask = xilinx_cpm_mask_event_irq, + .irq_unmask = xilinx_cpm_unmask_event_irq, +}; + +static int xilinx_cpm_pcie_event_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &xilinx_cpm_event_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + return 0; +} + +static const struct irq_domain_ops event_domain_ops = { + .map = xilinx_cpm_pcie_event_map, +}; + +static void xilinx_cpm_pcie_event_flow(struct irq_desc *desc) +{ + struct xilinx_cpm_pcie *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + const struct xilinx_cpm_variant *variant = port->variant; + unsigned long val; + int i; + + chained_irq_enter(chip, desc); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IDR); + val &= pcie_read(port, XILINX_CPM_PCIE_REG_IMR); + for_each_set_bit(i, &val, 32) + generic_handle_domain_irq(port->cpm_domain, i); + pcie_write(port, val, XILINX_CPM_PCIE_REG_IDR); + + if (variant->ir_status) { + val = readl_relaxed(port->cpm_base + variant->ir_status); + if (val) + writel_relaxed(val, port->cpm_base + + variant->ir_status); + } + + /* + * XILINX_CPM_PCIE_MISC_IR_STATUS register is mapped to + * CPM SLCR block. + */ + val = readl_relaxed(port->cpm_base + XILINX_CPM_PCIE_MISC_IR_STATUS); + if (val) + writel_relaxed(val, + port->cpm_base + XILINX_CPM_PCIE_MISC_IR_STATUS); + + chained_irq_exit(chip, desc); +} + +#define _IC(x, s) \ + [XILINX_PCIE_INTR_ ## x] = { __stringify(x), s } + +static const struct { + const char *sym; + const char *str; +} intr_cause[32] = { + _IC(LINK_DOWN, "Link Down"), + _IC(HOT_RESET, "Hot reset"), + _IC(CFG_TIMEOUT, "ECAM access timeout"), + _IC(CORRECTABLE, "Correctable error message"), + _IC(NONFATAL, "Non fatal error message"), + _IC(FATAL, "Fatal error message"), + _IC(SLV_UNSUPP, "Slave unsupported request"), + _IC(SLV_UNEXP, "Slave unexpected completion"), + _IC(SLV_COMPL, "Slave completion timeout"), + _IC(SLV_ERRP, "Slave Error Poison"), + _IC(SLV_CMPABT, "Slave Completer Abort"), + _IC(SLV_ILLBUR, "Slave Illegal Burst"), + _IC(MST_DECERR, "Master decode error"), + _IC(MST_SLVERR, "Master slave error"), + _IC(CFG_PCIE_TIMEOUT, "PCIe ECAM access timeout"), + _IC(CFG_ERR_POISON, "ECAM poisoned completion received"), + _IC(PME_TO_ACK_RCVD, "PME_TO_ACK message received"), + _IC(PM_PME_RCVD, "PM_PME message received"), + _IC(SLV_PCIE_TIMEOUT, "PCIe completion timeout received"), +}; + +static irqreturn_t xilinx_cpm_pcie_intr_handler(int irq, void *dev_id) +{ + struct xilinx_cpm_pcie *port = dev_id; + struct device *dev = port->dev; + struct irq_data *d; + + d = irq_domain_get_irq_data(port->cpm_domain, irq); + + switch (d->hwirq) { + case XILINX_PCIE_INTR_CORRECTABLE: + case XILINX_PCIE_INTR_NONFATAL: + case XILINX_PCIE_INTR_FATAL: + cpm_pcie_clear_err_interrupts(port); + fallthrough; + + default: + if (intr_cause[d->hwirq].str) + dev_warn(dev, "%s\n", intr_cause[d->hwirq].str); + else + dev_warn(dev, "Unknown IRQ %ld\n", d->hwirq); + } + + return IRQ_HANDLED; +} + +static void xilinx_cpm_free_irq_domains(struct xilinx_cpm_pcie *port) +{ + if (port->intx_domain) { + irq_domain_remove(port->intx_domain); + port->intx_domain = NULL; + } + + if (port->cpm_domain) { + irq_domain_remove(port->cpm_domain); + port->cpm_domain = NULL; + } +} + +/** + * xilinx_cpm_pcie_init_irq_domain - Initialize IRQ domain + * @port: PCIe port information + * + * Return: '0' on success and error value on failure + */ +static int xilinx_cpm_pcie_init_irq_domain(struct xilinx_cpm_pcie *port) +{ + struct device *dev = port->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + + /* Setup INTx */ + pcie_intc_node = of_get_next_child(node, NULL); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -EINVAL; + } + + port->cpm_domain = irq_domain_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_create_linear(of_fwnode_handle(pcie_intc_node), PCI_NUM_INTX, + &intx_domain_ops, port); + if (!port->intx_domain) + goto out; + + irq_domain_update_bus_token(port->intx_domain, DOMAIN_BUS_WIRED); + + of_node_put(pcie_intc_node); + raw_spin_lock_init(&port->lock); + + return 0; +out: + xilinx_cpm_free_irq_domains(port); + of_node_put(pcie_intc_node); + dev_err(dev, "Failed to allocate IRQ domains\n"); + + return -ENOMEM; +} + +static int xilinx_cpm_setup_irq(struct xilinx_cpm_pcie *port) +{ + struct device *dev = port->dev; + struct platform_device *pdev = to_platform_device(dev); + int i, irq; + + port->irq = platform_get_irq(pdev, 0); + if (port->irq < 0) + return port->irq; + + for (i = 0; i < ARRAY_SIZE(intr_cause); i++) { + int err; + + if (!intr_cause[i].str) + continue; + + irq = irq_create_mapping(port->cpm_domain, i); + if (!irq) { + dev_err(dev, "Failed to map interrupt\n"); + return -ENXIO; + } + + err = devm_request_irq(dev, irq, xilinx_cpm_pcie_intr_handler, + 0, intr_cause[i].sym, port); + if (err) { + dev_err(dev, "Failed to request IRQ %d\n", irq); + return err; + } + } + + port->intx_irq = irq_create_mapping(port->cpm_domain, + XILINX_PCIE_INTR_INTX); + if (!port->intx_irq) { + dev_err(dev, "Failed to map INTx interrupt\n"); + return -ENXIO; + } + + /* Plug the INTx chained handler */ + irq_set_chained_handler_and_data(port->intx_irq, + xilinx_cpm_pcie_intx_flow, port); + + /* Plug the main event chained handler */ + irq_set_chained_handler_and_data(port->irq, + xilinx_cpm_pcie_event_flow, port); + + return 0; +} + +/** + * xilinx_cpm_pcie_init_port - Initialize hardware + * @port: PCIe port information + */ +static void xilinx_cpm_pcie_init_port(struct xilinx_cpm_pcie *port) +{ + const struct xilinx_cpm_variant *variant = port->variant; + + if (variant->version == CPM5NC_HOST) + return; + + if (cpm_pcie_link_up(port)) + dev_info(port->dev, "PCIe Link is UP\n"); + else + dev_info(port->dev, "PCIe Link is DOWN\n"); + + /* Disable all interrupts */ + pcie_write(port, ~XILINX_CPM_PCIE_IDR_ALL_MASK, + XILINX_CPM_PCIE_REG_IMR); + + /* Clear pending interrupts */ + pcie_write(port, pcie_read(port, XILINX_CPM_PCIE_REG_IDR) & + XILINX_CPM_PCIE_IMR_ALL_MASK, + XILINX_CPM_PCIE_REG_IDR); + + /* + * XILINX_CPM_PCIE_MISC_IR_ENABLE register is mapped to + * CPM SLCR block. + */ + writel(variant->ir_misc_value, + port->cpm_base + XILINX_CPM_PCIE_MISC_IR_ENABLE); + + if (variant->ir_enable) { + writel(XILINX_CPM_PCIE_IR_LOCAL, + port->cpm_base + variant->ir_enable); + } + + /* Set Bridge enable bit */ + pcie_write(port, pcie_read(port, XILINX_CPM_PCIE_REG_RPSC) | + XILINX_CPM_PCIE_REG_RPSC_BEN, + XILINX_CPM_PCIE_REG_RPSC); +} + +/** + * xilinx_cpm_pcie_parse_dt - Parse Device tree + * @port: PCIe port information + * @bus_range: Bus resource + * + * Return: '0' on success and error value on failure + */ +static int xilinx_cpm_pcie_parse_dt(struct xilinx_cpm_pcie *port, + struct resource *bus_range) +{ + struct device *dev = port->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource *res; + + port->cpm_base = devm_platform_ioremap_resource_byname(pdev, + "cpm_slcr"); + if (IS_ERR(port->cpm_base)) + return PTR_ERR(port->cpm_base); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + if (!res) + return -ENXIO; + + port->cfg = pci_ecam_create(dev, res, bus_range, + &pci_generic_ecam_ops); + if (IS_ERR(port->cfg)) + return PTR_ERR(port->cfg); + + if (port->variant->version == CPM5 || + port->variant->version == CPM5_HOST1) { + port->reg_base = devm_platform_ioremap_resource_byname(pdev, + "cpm_csr"); + if (IS_ERR(port->reg_base)) + return PTR_ERR(port->reg_base); + } else { + port->reg_base = port->cfg->win; + } + + return 0; +} + +static void xilinx_cpm_free_interrupts(struct xilinx_cpm_pcie *port) +{ + irq_set_chained_handler_and_data(port->intx_irq, NULL, NULL); + irq_set_chained_handler_and_data(port->irq, NULL, NULL); +} + +/** + * xilinx_cpm_pcie_probe - Probe function + * @pdev: Platform device pointer + * + * Return: '0' on success and error value on failure + */ +static int xilinx_cpm_pcie_probe(struct platform_device *pdev) +{ + struct xilinx_cpm_pcie *port; + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct resource_entry *bus; + int err; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*port)); + if (!bridge) + return -ENODEV; + + port = pci_host_bridge_priv(bridge); + + port->dev = dev; + + port->variant = of_device_get_match_data(dev); + + if (port->variant->version != CPM5NC_HOST) { + err = xilinx_cpm_pcie_init_irq_domain(port); + if (err) + return err; + } + + bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!bus) { + err = -ENODEV; + goto err_free_irq_domains; + } + + err = xilinx_cpm_pcie_parse_dt(port, bus->res); + if (err) { + dev_err(dev, "Parsing DT failed\n"); + goto err_free_irq_domains; + } + + xilinx_cpm_pcie_init_port(port); + + if (port->variant->version != CPM5NC_HOST) { + err = xilinx_cpm_setup_irq(port); + if (err) { + dev_err(dev, "Failed to set up interrupts\n"); + goto err_setup_irq; + } + } + + bridge->sysdata = port->cfg; + bridge->ops = (struct pci_ops *)&pci_generic_ecam_ops.pci_ops; + + err = pci_host_probe(bridge); + if (err < 0) + goto err_host_bridge; + + return 0; + +err_host_bridge: + if (port->variant->version != CPM5NC_HOST) + xilinx_cpm_free_interrupts(port); +err_setup_irq: + pci_ecam_free(port->cfg); +err_free_irq_domains: + if (port->variant->version != CPM5NC_HOST) + xilinx_cpm_free_irq_domains(port); + return err; +} + +static const struct xilinx_cpm_variant cpm_host = { + .version = CPM, + .ir_misc_value = XILINX_CPM_PCIE0_MISC_IR_LOCAL, +}; + +static const struct xilinx_cpm_variant cpm5_host = { + .version = CPM5, + .ir_misc_value = XILINX_CPM_PCIE0_MISC_IR_LOCAL, + .ir_status = XILINX_CPM_PCIE0_IR_STATUS, + .ir_enable = XILINX_CPM_PCIE0_IR_ENABLE, +}; + +static const struct xilinx_cpm_variant cpm5_host1 = { + .version = CPM5_HOST1, + .ir_misc_value = XILINX_CPM_PCIE1_MISC_IR_LOCAL, + .ir_status = XILINX_CPM_PCIE1_IR_STATUS, + .ir_enable = XILINX_CPM_PCIE1_IR_ENABLE, +}; + +static const struct xilinx_cpm_variant cpm5n_host = { + .version = CPM5NC_HOST, +}; + +static const struct of_device_id xilinx_cpm_pcie_of_match[] = { + { + .compatible = "xlnx,versal-cpm-host-1.00", + .data = &cpm_host, + }, + { + .compatible = "xlnx,versal-cpm5-host", + .data = &cpm5_host, + }, + { + .compatible = "xlnx,versal-cpm5-host1", + .data = &cpm5_host1, + }, + { + .compatible = "xlnx,versal-cpm5nc-host", + .data = &cpm5n_host, + }, + {} +}; + +static struct platform_driver xilinx_cpm_pcie_driver = { + .driver = { + .name = "xilinx-cpm-pcie", + .of_match_table = xilinx_cpm_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = xilinx_cpm_pcie_probe, +}; + +builtin_platform_driver(xilinx_cpm_pcie_driver); diff --git a/drivers/pci/controller/pcie-xilinx-dma-pl.c b/drivers/pci/controller/pcie-xilinx-dma-pl.c new file mode 100644 index 000000000000..b037c8f315e4 --- /dev/null +++ b/drivers/pci/controller/pcie-xilinx-dma-pl.c @@ -0,0 +1,847 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PCIe host controller driver for Xilinx XDMA PCIe Bridge + * + * Copyright (C) 2023 Xilinx, Inc. All rights reserved. + */ +#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> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> + +#include "../pci.h" +#include "pcie-xilinx-common.h" + +/* Register definitions */ +#define XILINX_PCIE_DMA_REG_IDR 0x00000138 +#define XILINX_PCIE_DMA_REG_IMR 0x0000013c +#define XILINX_PCIE_DMA_REG_PSCR 0x00000144 +#define XILINX_PCIE_DMA_REG_RPSC 0x00000148 +#define XILINX_PCIE_DMA_REG_MSIBASE1 0x0000014c +#define XILINX_PCIE_DMA_REG_MSIBASE2 0x00000150 +#define XILINX_PCIE_DMA_REG_RPEFR 0x00000154 +#define XILINX_PCIE_DMA_REG_IDRN 0x00000160 +#define XILINX_PCIE_DMA_REG_IDRN_MASK 0x00000164 +#define XILINX_PCIE_DMA_REG_MSI_LOW 0x00000170 +#define XILINX_PCIE_DMA_REG_MSI_HI 0x00000174 +#define XILINX_PCIE_DMA_REG_MSI_LOW_MASK 0x00000178 +#define XILINX_PCIE_DMA_REG_MSI_HI_MASK 0x0000017c + +#define IMR(x) BIT(XILINX_PCIE_INTR_ ##x) + +#define XILINX_PCIE_INTR_IMR_ALL_MASK \ + ( \ + IMR(LINK_DOWN) | \ + IMR(HOT_RESET) | \ + IMR(CFG_TIMEOUT) | \ + IMR(CORRECTABLE) | \ + IMR(NONFATAL) | \ + IMR(FATAL) | \ + IMR(INTX) | \ + IMR(MSI) | \ + IMR(SLV_UNSUPP) | \ + IMR(SLV_UNEXP) | \ + IMR(SLV_COMPL) | \ + IMR(SLV_ERRP) | \ + IMR(SLV_CMPABT) | \ + IMR(SLV_ILLBUR) | \ + IMR(MST_DECERR) | \ + IMR(MST_SLVERR) | \ + ) + +#define XILINX_PCIE_DMA_IMR_ALL_MASK 0x0ff30fe9 +#define XILINX_PCIE_DMA_IDR_ALL_MASK 0xffffffff +#define XILINX_PCIE_DMA_IDRN_MASK GENMASK(19, 16) + +/* Root Port Error Register definitions */ +#define XILINX_PCIE_DMA_RPEFR_ERR_VALID BIT(18) +#define XILINX_PCIE_DMA_RPEFR_REQ_ID GENMASK(15, 0) +#define XILINX_PCIE_DMA_RPEFR_ALL_MASK 0xffffffff + +/* Root Port Interrupt Register definitions */ +#define XILINX_PCIE_DMA_IDRN_SHIFT 16 + +/* Root Port Status/control Register definitions */ +#define XILINX_PCIE_DMA_REG_RPSC_BEN BIT(0) + +/* Phy Status/Control Register definitions */ +#define XILINX_PCIE_DMA_REG_PSCR_LNKUP BIT(11) +#define QDMA_BRIDGE_BASE_OFF 0xcd8 + +/* Number of MSI IRQs */ +#define XILINX_NUM_MSI_IRQS 64 + +enum xilinx_pl_dma_version { + XDMA, + QDMA, +}; + +/** + * struct xilinx_pl_dma_variant - PL DMA PCIe variant information + * @version: DMA version + */ +struct xilinx_pl_dma_variant { + enum xilinx_pl_dma_version version; +}; + +struct xilinx_msi { + unsigned long *bitmap; + struct irq_domain *dev_domain; + struct mutex lock; /* Protect bitmap variable */ + int irq_msi0; + int irq_msi1; +}; + +/** + * struct pl_dma_pcie - PCIe port information + * @dev: Device pointer + * @reg_base: IO Mapped Register Base + * @cfg_base: IO Mapped Configuration Base + * @irq: Interrupt number + * @cfg: Holds mappings of config space window + * @phys_reg_base: Physical address of reg base + * @intx_domain: Legacy IRQ domain pointer + * @pldma_domain: PL DMA IRQ domain pointer + * @resources: Bus Resources + * @msi: MSI information + * @intx_irq: INTx error interrupt number + * @lock: Lock protecting shared register access + * @variant: PL DMA PCIe version check pointer + */ +struct pl_dma_pcie { + struct device *dev; + void __iomem *reg_base; + void __iomem *cfg_base; + int irq; + struct pci_config_window *cfg; + phys_addr_t phys_reg_base; + struct irq_domain *intx_domain; + struct irq_domain *pldma_domain; + struct list_head resources; + struct xilinx_msi msi; + int intx_irq; + raw_spinlock_t lock; + const struct xilinx_pl_dma_variant *variant; +}; + +static inline u32 pcie_read(struct pl_dma_pcie *port, u32 reg) +{ + if (port->variant->version == QDMA) + return readl(port->reg_base + reg + QDMA_BRIDGE_BASE_OFF); + + return readl(port->reg_base + reg); +} + +static inline void pcie_write(struct pl_dma_pcie *port, u32 val, u32 reg) +{ + if (port->variant->version == QDMA) + writel(val, port->reg_base + reg + QDMA_BRIDGE_BASE_OFF); + else + writel(val, port->reg_base + reg); +} + +static inline bool xilinx_pl_dma_pcie_link_up(struct pl_dma_pcie *port) +{ + return (pcie_read(port, XILINX_PCIE_DMA_REG_PSCR) & + XILINX_PCIE_DMA_REG_PSCR_LNKUP) ? true : false; +} + +static void xilinx_pl_dma_pcie_clear_err_interrupts(struct pl_dma_pcie *port) +{ + unsigned long val = pcie_read(port, XILINX_PCIE_DMA_REG_RPEFR); + + if (val & XILINX_PCIE_DMA_RPEFR_ERR_VALID) { + dev_dbg(port->dev, "Requester ID %lu\n", + val & XILINX_PCIE_DMA_RPEFR_REQ_ID); + pcie_write(port, XILINX_PCIE_DMA_RPEFR_ALL_MASK, + XILINX_PCIE_DMA_REG_RPEFR); + } +} + +static bool xilinx_pl_dma_pcie_valid_device(struct pci_bus *bus, + unsigned int devfn) +{ + struct pl_dma_pcie *port = bus->sysdata; + + if (!pci_is_root_bus(bus)) { + /* + * Checking whether the link is up is the last line of + * defense, and this check is inherently racy by definition. + * Sending a PIO request to a downstream device when the link is + * down causes an unrecoverable error, and a reset of the entire + * PCIe controller will be needed. We can reduce the likelihood + * of that unrecoverable error by checking whether the link is + * up, but we can't completely prevent it because the link may + * go down between the link-up check and the PIO request. + */ + if (!xilinx_pl_dma_pcie_link_up(port)) + return false; + } else if (devfn > 0) + /* Only one device down on each root port */ + return false; + + return true; +} + +static void __iomem *xilinx_pl_dma_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct pl_dma_pcie *port = bus->sysdata; + + if (!xilinx_pl_dma_pcie_valid_device(bus, devfn)) + return NULL; + + if (port->variant->version == QDMA) + return port->cfg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); + + return port->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); +} + +/* PCIe operations */ +static struct pci_ecam_ops xilinx_pl_dma_pcie_ops = { + .pci_ops = { + .map_bus = xilinx_pl_dma_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static void xilinx_pl_dma_pcie_enable_msi(struct pl_dma_pcie *port) +{ + phys_addr_t msi_addr = port->phys_reg_base; + + pcie_write(port, upper_32_bits(msi_addr), XILINX_PCIE_DMA_REG_MSIBASE1); + pcie_write(port, lower_32_bits(msi_addr), XILINX_PCIE_DMA_REG_MSIBASE2); +} + +static void xilinx_mask_intx_irq(struct irq_data *data) +{ + struct pl_dma_pcie *port = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask, val; + + mask = BIT(data->hwirq + XILINX_PCIE_DMA_IDRN_SHIFT); + raw_spin_lock_irqsave(&port->lock, flags); + val = pcie_read(port, XILINX_PCIE_DMA_REG_IDRN_MASK); + pcie_write(port, (val & (~mask)), XILINX_PCIE_DMA_REG_IDRN_MASK); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void xilinx_unmask_intx_irq(struct irq_data *data) +{ + struct pl_dma_pcie *port = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask, val; + + mask = BIT(data->hwirq + XILINX_PCIE_DMA_IDRN_SHIFT); + raw_spin_lock_irqsave(&port->lock, flags); + val = pcie_read(port, XILINX_PCIE_DMA_REG_IDRN_MASK); + pcie_write(port, (val | mask), XILINX_PCIE_DMA_REG_IDRN_MASK); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip xilinx_leg_irq_chip = { + .name = "pl_dma:INTx", + .irq_mask = xilinx_mask_intx_irq, + .irq_unmask = xilinx_unmask_intx_irq, +}; + +static int xilinx_pl_dma_pcie_intx_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &xilinx_leg_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + + return 0; +} + +/* INTx IRQ Domain operations */ +static const struct irq_domain_ops intx_domain_ops = { + .map = xilinx_pl_dma_pcie_intx_map, +}; + +static irqreturn_t xilinx_pl_dma_pcie_msi_handler_high(int irq, void *args) +{ + struct xilinx_msi *msi; + unsigned long status; + u32 bit, virq; + struct pl_dma_pcie *port = args; + + msi = &port->msi; + + while ((status = pcie_read(port, XILINX_PCIE_DMA_REG_MSI_HI)) != 0) { + for_each_set_bit(bit, &status, 32) { + pcie_write(port, 1 << bit, XILINX_PCIE_DMA_REG_MSI_HI); + bit = bit + 32; + virq = irq_find_mapping(msi->dev_domain, bit); + if (virq) + generic_handle_irq(virq); + } + } + + return IRQ_HANDLED; +} + +static irqreturn_t xilinx_pl_dma_pcie_msi_handler_low(int irq, void *args) +{ + struct pl_dma_pcie *port = args; + struct xilinx_msi *msi; + unsigned long status; + u32 bit, virq; + + msi = &port->msi; + + while ((status = pcie_read(port, XILINX_PCIE_DMA_REG_MSI_LOW)) != 0) { + for_each_set_bit(bit, &status, 32) { + pcie_write(port, 1 << bit, XILINX_PCIE_DMA_REG_MSI_LOW); + virq = irq_find_mapping(msi->dev_domain, bit); + if (virq) + generic_handle_irq(virq); + } + } + + return IRQ_HANDLED; +} + +static irqreturn_t xilinx_pl_dma_pcie_event_flow(int irq, void *args) +{ + struct pl_dma_pcie *port = args; + unsigned long val; + int i; + + val = pcie_read(port, XILINX_PCIE_DMA_REG_IDR); + val &= pcie_read(port, XILINX_PCIE_DMA_REG_IMR); + for_each_set_bit(i, &val, 32) + generic_handle_domain_irq(port->pldma_domain, i); + + pcie_write(port, val, XILINX_PCIE_DMA_REG_IDR); + + return IRQ_HANDLED; +} + +#define _IC(x, s) \ + [XILINX_PCIE_INTR_ ## x] = { __stringify(x), s } + +static const struct { + const char *sym; + const char *str; +} intr_cause[32] = { + _IC(LINK_DOWN, "Link Down"), + _IC(HOT_RESET, "Hot reset"), + _IC(CFG_TIMEOUT, "ECAM access timeout"), + _IC(CORRECTABLE, "Correctable error message"), + _IC(NONFATAL, "Non fatal error message"), + _IC(FATAL, "Fatal error message"), + _IC(SLV_UNSUPP, "Slave unsupported request"), + _IC(SLV_UNEXP, "Slave unexpected completion"), + _IC(SLV_COMPL, "Slave completion timeout"), + _IC(SLV_ERRP, "Slave Error Poison"), + _IC(SLV_CMPABT, "Slave Completer Abort"), + _IC(SLV_ILLBUR, "Slave Illegal Burst"), + _IC(MST_DECERR, "Master decode error"), + _IC(MST_SLVERR, "Master slave error"), +}; + +static irqreturn_t xilinx_pl_dma_pcie_intr_handler(int irq, void *dev_id) +{ + struct pl_dma_pcie *port = (struct pl_dma_pcie *)dev_id; + struct device *dev = port->dev; + struct irq_data *d; + + d = irq_domain_get_irq_data(port->pldma_domain, irq); + switch (d->hwirq) { + case XILINX_PCIE_INTR_CORRECTABLE: + case XILINX_PCIE_INTR_NONFATAL: + case XILINX_PCIE_INTR_FATAL: + xilinx_pl_dma_pcie_clear_err_interrupts(port); + fallthrough; + + default: + if (intr_cause[d->hwirq].str) + dev_warn(dev, "%s\n", intr_cause[d->hwirq].str); + else + dev_warn(dev, "Unknown IRQ %ld\n", d->hwirq); + } + + return IRQ_HANDLED; +} + +#define XILINX_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) + +#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); + phys_addr_t msi_addr = pcie->phys_reg_base; + + msg->address_lo = lower_32_bits(msi_addr); + msg->address_hi = upper_32_bits(msi_addr); + msg->data = data->hwirq; +} + +static struct irq_chip xilinx_irq_chip = { + .name = "pl_dma:MSI", + .irq_compose_msi_msg = xilinx_compose_msi_msg, +}; + +static int xilinx_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct pl_dma_pcie *pcie = domain->host_data; + struct xilinx_msi *msi = &pcie->msi; + int bit, i; + + mutex_lock(&msi->lock); + bit = bitmap_find_free_region(msi->bitmap, XILINX_NUM_MSI_IRQS, + get_count_order(nr_irqs)); + if (bit < 0) { + mutex_unlock(&msi->lock); + return -ENOSPC; + } + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, bit + i, &xilinx_irq_chip, + domain->host_data, handle_simple_irq, + NULL, NULL); + } + mutex_unlock(&msi->lock); + + return 0; +} + +static void xilinx_irq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *data = irq_domain_get_irq_data(domain, virq); + struct pl_dma_pcie *pcie = irq_data_get_irq_chip_data(data); + struct xilinx_msi *msi = &pcie->msi; + + mutex_lock(&msi->lock); + bitmap_release_region(msi->bitmap, data->hwirq, + get_count_order(nr_irqs)); + mutex_unlock(&msi->lock); +} + +static const struct irq_domain_ops dev_msi_domain_ops = { + .alloc = xilinx_irq_domain_alloc, + .free = xilinx_irq_domain_free, +}; + +static void xilinx_pl_dma_pcie_free_irq_domains(struct pl_dma_pcie *port) +{ + struct xilinx_msi *msi = &port->msi; + + if (port->intx_domain) { + irq_domain_remove(port->intx_domain); + port->intx_domain = NULL; + } + + if (msi->dev_domain) { + irq_domain_remove(msi->dev_domain); + msi->dev_domain = NULL; + } +} + +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 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; + + mutex_init(&msi->lock); + msi->bitmap = kzalloc(size, GFP_KERNEL); + if (!msi->bitmap) + goto out; + + raw_spin_lock_init(&port->lock); + xilinx_pl_dma_pcie_enable_msi(port); + + return 0; + +out: + xilinx_pl_dma_pcie_free_irq_domains(port); + dev_err(dev, "Failed to allocate MSI IRQ domains\n"); + + return -ENOMEM; +} + +/* + * INTx error interrupts are Xilinx controller specific interrupt, used to + * notify user about errors such as cfg timeout, slave unsupported requests, + * fatal and non fatal error etc. + */ + +static irqreturn_t xilinx_pl_dma_pcie_intx_flow(int irq, void *args) +{ + unsigned long val; + int i; + struct pl_dma_pcie *port = args; + + val = FIELD_GET(XILINX_PCIE_DMA_IDRN_MASK, + pcie_read(port, XILINX_PCIE_DMA_REG_IDRN)); + + for_each_set_bit(i, &val, PCI_NUM_INTX) + generic_handle_domain_irq(port->intx_domain, i); + return IRQ_HANDLED; +} + +static void xilinx_pl_dma_pcie_mask_event_irq(struct irq_data *d) +{ + struct pl_dma_pcie *port = irq_data_get_irq_chip_data(d); + u32 val; + + raw_spin_lock(&port->lock); + val = pcie_read(port, XILINX_PCIE_DMA_REG_IMR); + val &= ~BIT(d->hwirq); + pcie_write(port, val, XILINX_PCIE_DMA_REG_IMR); + raw_spin_unlock(&port->lock); +} + +static void xilinx_pl_dma_pcie_unmask_event_irq(struct irq_data *d) +{ + struct pl_dma_pcie *port = irq_data_get_irq_chip_data(d); + u32 val; + + raw_spin_lock(&port->lock); + val = pcie_read(port, XILINX_PCIE_DMA_REG_IMR); + val |= BIT(d->hwirq); + pcie_write(port, val, XILINX_PCIE_DMA_REG_IMR); + raw_spin_unlock(&port->lock); +} + +static struct irq_chip xilinx_pl_dma_pcie_event_irq_chip = { + .name = "pl_dma:RC-Event", + .irq_mask = xilinx_pl_dma_pcie_mask_event_irq, + .irq_unmask = xilinx_pl_dma_pcie_unmask_event_irq, +}; + +static int xilinx_pl_dma_pcie_event_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &xilinx_pl_dma_pcie_event_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + + return 0; +} + +static const struct irq_domain_ops event_domain_ops = { + .map = xilinx_pl_dma_pcie_event_map, +}; + +/** + * xilinx_pl_dma_pcie_init_irq_domain - Initialize IRQ domain + * @port: PCIe port information + * + * Return: '0' on success and error value on failure. + */ +static int xilinx_pl_dma_pcie_init_irq_domain(struct pl_dma_pcie *port) +{ + struct device *dev = port->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + int ret; + + /* Setup INTx */ + 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 -EINVAL; + } + + 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_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; + } + + irq_domain_update_bus_token(port->intx_domain, DOMAIN_BUS_WIRED); + + ret = xilinx_pl_dma_pcie_init_msi_irq_domain(port); + if (ret != 0) { + irq_domain_remove(port->intx_domain); + return -ENOMEM; + } + + of_node_put(pcie_intc_node); + raw_spin_lock_init(&port->lock); + + return 0; +} + +static int xilinx_pl_dma_pcie_setup_irq(struct pl_dma_pcie *port) +{ + struct device *dev = port->dev; + struct platform_device *pdev = to_platform_device(dev); + int i, irq, err; + + port->irq = platform_get_irq(pdev, 0); + if (port->irq < 0) + return port->irq; + + for (i = 0; i < ARRAY_SIZE(intr_cause); i++) { + int err; + + if (!intr_cause[i].str) + continue; + + irq = irq_create_mapping(port->pldma_domain, i); + if (!irq) { + dev_err(dev, "Failed to map interrupt\n"); + return -ENXIO; + } + + err = devm_request_irq(dev, irq, + xilinx_pl_dma_pcie_intr_handler, + IRQF_SHARED | IRQF_NO_THREAD, + intr_cause[i].sym, port); + if (err) { + dev_err(dev, "Failed to request IRQ %d\n", irq); + return err; + } + } + + port->intx_irq = irq_create_mapping(port->pldma_domain, + XILINX_PCIE_INTR_INTX); + if (!port->intx_irq) { + dev_err(dev, "Failed to map INTx interrupt\n"); + return -ENXIO; + } + + err = devm_request_irq(dev, port->intx_irq, xilinx_pl_dma_pcie_intx_flow, + IRQF_SHARED | IRQF_NO_THREAD, NULL, port); + if (err) { + dev_err(dev, "Failed to request INTx IRQ %d\n", port->intx_irq); + return err; + } + + err = devm_request_irq(dev, port->irq, xilinx_pl_dma_pcie_event_flow, + IRQF_SHARED | IRQF_NO_THREAD, NULL, port); + if (err) { + dev_err(dev, "Failed to request event IRQ %d\n", port->irq); + return err; + } + + return 0; +} + +static void xilinx_pl_dma_pcie_init_port(struct pl_dma_pcie *port) +{ + if (xilinx_pl_dma_pcie_link_up(port)) + dev_info(port->dev, "PCIe Link is UP\n"); + else + dev_info(port->dev, "PCIe Link is DOWN\n"); + + /* Disable all interrupts */ + pcie_write(port, ~XILINX_PCIE_DMA_IDR_ALL_MASK, + XILINX_PCIE_DMA_REG_IMR); + + /* Clear pending interrupts */ + pcie_write(port, pcie_read(port, XILINX_PCIE_DMA_REG_IDR) & + XILINX_PCIE_DMA_IMR_ALL_MASK, + XILINX_PCIE_DMA_REG_IDR); + + /* Needed for MSI DECODE MODE */ + pcie_write(port, XILINX_PCIE_DMA_IDR_ALL_MASK, + XILINX_PCIE_DMA_REG_MSI_LOW_MASK); + pcie_write(port, XILINX_PCIE_DMA_IDR_ALL_MASK, + XILINX_PCIE_DMA_REG_MSI_HI_MASK); + + /* Set the Bridge enable bit */ + pcie_write(port, pcie_read(port, XILINX_PCIE_DMA_REG_RPSC) | + XILINX_PCIE_DMA_REG_RPSC_BEN, + XILINX_PCIE_DMA_REG_RPSC); +} + +static int xilinx_request_msi_irq(struct pl_dma_pcie *port) +{ + struct device *dev = port->dev; + struct platform_device *pdev = to_platform_device(dev); + int ret; + + port->msi.irq_msi0 = platform_get_irq_byname(pdev, "msi0"); + if (port->msi.irq_msi0 <= 0) + return port->msi.irq_msi0; + + ret = devm_request_irq(dev, port->msi.irq_msi0, xilinx_pl_dma_pcie_msi_handler_low, + IRQF_SHARED | IRQF_NO_THREAD, "xlnx-pcie-dma-pl", + port); + if (ret) { + dev_err(dev, "Failed to register interrupt\n"); + return ret; + } + + port->msi.irq_msi1 = platform_get_irq_byname(pdev, "msi1"); + if (port->msi.irq_msi1 <= 0) + return port->msi.irq_msi1; + + ret = devm_request_irq(dev, port->msi.irq_msi1, xilinx_pl_dma_pcie_msi_handler_high, + IRQF_SHARED | IRQF_NO_THREAD, "xlnx-pcie-dma-pl", + port); + if (ret) { + dev_err(dev, "Failed to register interrupt\n"); + return ret; + } + + return 0; +} + +static int xilinx_pl_dma_pcie_parse_dt(struct pl_dma_pcie *port, + struct resource *bus_range) +{ + struct device *dev = port->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource *res; + int err; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "Missing \"reg\" property\n"); + return -ENXIO; + } + port->phys_reg_base = res->start; + + port->cfg = pci_ecam_create(dev, res, bus_range, &xilinx_pl_dma_pcie_ops); + if (IS_ERR(port->cfg)) + return PTR_ERR(port->cfg); + + port->reg_base = port->cfg->win; + + if (port->variant->version == QDMA) { + port->cfg_base = port->cfg->win; + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "breg"); + port->reg_base = devm_ioremap_resource(dev, res); + if (IS_ERR(port->reg_base)) + return PTR_ERR(port->reg_base); + port->phys_reg_base = res->start; + } + + err = xilinx_request_msi_irq(port); + if (err) { + pci_ecam_free(port->cfg); + return err; + } + + return 0; +} + +static int xilinx_pl_dma_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pl_dma_pcie *port; + struct pci_host_bridge *bridge; + struct resource_entry *bus; + int err; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*port)); + if (!bridge) + return -ENODEV; + + port = pci_host_bridge_priv(bridge); + + port->dev = dev; + + bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!bus) + return -ENODEV; + + port->variant = of_device_get_match_data(dev); + + err = xilinx_pl_dma_pcie_parse_dt(port, bus->res); + if (err) { + dev_err(dev, "Parsing DT failed\n"); + return err; + } + + xilinx_pl_dma_pcie_init_port(port); + + err = xilinx_pl_dma_pcie_init_irq_domain(port); + if (err) + goto err_irq_domain; + + err = xilinx_pl_dma_pcie_setup_irq(port); + + bridge->sysdata = port; + bridge->ops = &xilinx_pl_dma_pcie_ops.pci_ops; + + err = pci_host_probe(bridge); + if (err < 0) + goto err_host_bridge; + + return 0; + +err_host_bridge: + xilinx_pl_dma_pcie_free_irq_domains(port); + +err_irq_domain: + pci_ecam_free(port->cfg); + return err; +} + +static const struct xilinx_pl_dma_variant xdma_host = { + .version = XDMA, +}; + +static const struct xilinx_pl_dma_variant qdma_host = { + .version = QDMA, +}; + +static const struct of_device_id xilinx_pl_dma_pcie_of_match[] = { + { + .compatible = "xlnx,xdma-host-3.00", + .data = &xdma_host, + }, + { + .compatible = "xlnx,qdma-host-3.00", + .data = &qdma_host, + }, + {} +}; + +static struct platform_driver xilinx_pl_dma_pcie_driver = { + .driver = { + .name = "xilinx-xdma-pcie", + .of_match_table = xilinx_pl_dma_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = xilinx_pl_dma_pcie_probe, +}; + +builtin_platform_driver(xilinx_pl_dma_pcie_driver); diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c index 81538d77f790..7db2c96c6cec 100644 --- a/drivers/pci/controller/pcie-xilinx-nwl.c +++ b/drivers/pci/controller/pcie-xilinx-nwl.c @@ -6,9 +6,11 @@ * (C) Copyright 2014 - 2015, Xilinx, Inc. */ +#include <linux/clk.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> @@ -16,8 +18,9 @@ #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/of_platform.h> -#include <linux/of_irq.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/phy/phy.h> #include <linux/platform_device.h> #include <linux/irqchip/chained_irq.h> @@ -25,6 +28,7 @@ /* Bridge core config registers */ #define BRCFG_PCIE_RX0 0x00000000 +#define BRCFG_PCIE_RX1 0x00000004 #define BRCFG_INTERRUPT 0x00000010 #define BRCFG_PCIE_RX_MSG_FILTER 0x00000020 @@ -78,8 +82,8 @@ #define MSGF_MISC_SR_NON_FATAL_DEV BIT(22) #define MSGF_MISC_SR_FATAL_DEV BIT(23) #define MSGF_MISC_SR_LINK_DOWN BIT(24) -#define MSGF_MSIC_SR_LINK_AUTO_BWIDTH BIT(25) -#define MSGF_MSIC_SR_LINK_BWIDTH BIT(26) +#define MSGF_MISC_SR_LINK_AUTO_BWIDTH BIT(25) +#define MSGF_MISC_SR_LINK_BWIDTH BIT(26) #define MSGF_MISC_SR_MASKALL (MSGF_MISC_SR_RXMSG_AVAIL | \ MSGF_MISC_SR_RXMSG_OVER | \ @@ -94,8 +98,8 @@ MSGF_MISC_SR_NON_FATAL_DEV | \ MSGF_MISC_SR_FATAL_DEV | \ MSGF_MISC_SR_LINK_DOWN | \ - MSGF_MSIC_SR_LINK_AUTO_BWIDTH | \ - MSGF_MSIC_SR_LINK_BWIDTH) + MSGF_MISC_SR_LINK_AUTO_BWIDTH | \ + MSGF_MISC_SR_LINK_BWIDTH) /* Legacy interrupt status mask bits */ #define MSGF_LEG_SR_INTA BIT(0) @@ -124,11 +128,10 @@ #define E_ECAM_CR_ENABLE BIT(0) #define E_ECAM_SIZE_LOC GENMASK(20, 16) #define E_ECAM_SIZE_SHIFT 16 -#define ECAM_BUS_LOC_SHIFT 20 -#define ECAM_DEV_LOC_SHIFT 12 -#define NWL_ECAM_VALUE_DEFAULT 12 +#define NWL_ECAM_MAX_SIZE 16 #define CFG_DMA_REG_BAR GENMASK(2, 0) +#define CFG_PCIE_CACHE GENMASK(7, 0) #define INT_PCI_MSI_NR (2 * 32) @@ -143,8 +146,7 @@ #define LINK_WAIT_USLEEP_MAX 100000 struct nwl_msi { /* MSI information */ - struct irq_domain *msi_domain; - unsigned long *bitmap; + DECLARE_BITMAP(bitmap, INT_PCI_MSI_NR); struct irq_domain *dev_domain; struct mutex lock; /* protect bitmap variable */ int irq_msi0; @@ -156,6 +158,7 @@ struct nwl_pcie { void __iomem *breg_base; void __iomem *pcireg_base; void __iomem *ecam_base; + struct phy *phy[4]; phys_addr_t phys_breg_base; /* Physical Bridge Register Base */ phys_addr_t phys_pcie_reg_base; /* Physical PCIe Controller Base */ phys_addr_t phys_ecam_base; /* Physical Configuration Base */ @@ -164,11 +167,9 @@ struct nwl_pcie { u32 ecam_size; int irq_intx; int irq_misc; - u32 ecam_value; - u8 last_busno; - u8 root_busno; struct nwl_msi msi; - struct irq_domain *legacy_irq_domain; + struct irq_domain *intx_irq_domain; + struct clk *clk; raw_spinlock_t leg_mask_lock; }; @@ -217,13 +218,11 @@ static bool nwl_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) struct nwl_pcie *pcie = bus->sysdata; /* Check link before accessing downstream ports */ - if (bus->number != pcie->root_busno) { + if (!pci_is_root_bus(bus)) { if (!nwl_pcie_link_up(pcie)) return false; - } - - /* Only one device down on each root port */ - if (bus->number == pcie->root_busno && devfn > 0) + } else if (devfn > 0) + /* Only one device down on each root port */ return false; return true; @@ -243,15 +242,11 @@ static void __iomem *nwl_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, int where) { struct nwl_pcie *pcie = bus->sysdata; - int relbus; if (!nwl_pcie_valid_device(bus, devfn)) return NULL; - relbus = (bus->number << ECAM_BUS_LOC_SHIFT) | - (devfn << ECAM_DEV_LOC_SHIFT); - - return pcie->ecam_base + relbus + where; + return pcie->ecam_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); } /* PCIe operations */ @@ -274,42 +269,42 @@ static irqreturn_t nwl_pcie_misc_handler(int irq, void *data) return IRQ_NONE; if (misc_stat & MSGF_MISC_SR_RXMSG_OVER) - dev_err(dev, "Received Message FIFO Overflow\n"); + dev_err_ratelimited(dev, "Received Message FIFO Overflow\n"); if (misc_stat & MSGF_MISC_SR_SLAVE_ERR) - dev_err(dev, "Slave error\n"); + dev_err_ratelimited(dev, "Slave error\n"); if (misc_stat & MSGF_MISC_SR_MASTER_ERR) - dev_err(dev, "Master error\n"); + dev_err_ratelimited(dev, "Master error\n"); if (misc_stat & MSGF_MISC_SR_I_ADDR_ERR) - dev_err(dev, "In Misc Ingress address translation error\n"); + dev_err_ratelimited(dev, "In Misc Ingress address translation error\n"); if (misc_stat & MSGF_MISC_SR_E_ADDR_ERR) - dev_err(dev, "In Misc Egress address translation error\n"); + dev_err_ratelimited(dev, "In Misc Egress address translation error\n"); if (misc_stat & MSGF_MISC_SR_FATAL_AER) - dev_err(dev, "Fatal Error in AER Capability\n"); + dev_err_ratelimited(dev, "Fatal Error in AER Capability\n"); if (misc_stat & MSGF_MISC_SR_NON_FATAL_AER) - dev_err(dev, "Non-Fatal Error in AER Capability\n"); + dev_err_ratelimited(dev, "Non-Fatal Error in AER Capability\n"); if (misc_stat & MSGF_MISC_SR_CORR_AER) - dev_err(dev, "Correctable Error in AER Capability\n"); + dev_err_ratelimited(dev, "Correctable Error in AER Capability\n"); if (misc_stat & MSGF_MISC_SR_UR_DETECT) - dev_err(dev, "Unsupported request Detected\n"); + dev_err_ratelimited(dev, "Unsupported request Detected\n"); if (misc_stat & MSGF_MISC_SR_NON_FATAL_DEV) - dev_err(dev, "Non-Fatal Error Detected\n"); + dev_err_ratelimited(dev, "Non-Fatal Error Detected\n"); if (misc_stat & MSGF_MISC_SR_FATAL_DEV) - dev_err(dev, "Fatal Error Detected\n"); + dev_err_ratelimited(dev, "Fatal Error Detected\n"); - if (misc_stat & MSGF_MSIC_SR_LINK_AUTO_BWIDTH) + if (misc_stat & MSGF_MISC_SR_LINK_AUTO_BWIDTH) dev_info(dev, "Link Autonomous Bandwidth Management Status bit set\n"); - if (misc_stat & MSGF_MSIC_SR_LINK_BWIDTH) + if (misc_stat & MSGF_MISC_SR_LINK_BWIDTH) dev_info(dev, "Link Bandwidth Management Status bit set\n"); /* Clear misc interrupt status */ @@ -324,18 +319,14 @@ static void nwl_pcie_leg_handler(struct irq_desc *desc) struct nwl_pcie *pcie; unsigned long status; u32 bit; - u32 virq; chained_irq_enter(chip, desc); pcie = irq_desc_get_handler_data(desc); while ((status = nwl_bridge_readl(pcie, MSGF_LEG_STATUS) & MSGF_LEG_SR_MASKALL) != 0) { - for_each_set_bit(bit, &status, PCI_NUM_INTX) { - virq = irq_find_mapping(pcie->legacy_irq_domain, bit); - if (virq) - generic_handle_irq(virq); - } + for_each_set_bit(bit, &status, PCI_NUM_INTX) + generic_handle_domain_irq(pcie->intx_irq_domain, bit); } chained_irq_exit(chip, desc); @@ -343,19 +334,14 @@ static void nwl_pcie_leg_handler(struct irq_desc *desc) static void nwl_pcie_handle_msi_irq(struct nwl_pcie *pcie, u32 status_reg) { - struct nwl_msi *msi; + struct nwl_msi *msi = &pcie->msi; unsigned long status; u32 bit; - u32 virq; - - msi = &pcie->msi; while ((status = nwl_bridge_readl(pcie, status_reg)) != 0) { for_each_set_bit(bit, &status, 32) { nwl_bridge_writel(pcie, 1 << bit, status_reg); - virq = irq_find_mapping(msi->dev_domain, bit); - if (virq) - generic_handle_irq(virq); + generic_handle_domain_irq(msi->dev_domain, bit); } } } @@ -380,76 +366,74 @@ static void nwl_pcie_msi_handler_low(struct irq_desc *desc) chained_irq_exit(chip, desc); } -static void nwl_mask_leg_irq(struct irq_data *data) +static void nwl_mask_intx_irq(struct irq_data *data) { - struct irq_desc *desc = irq_to_desc(data->irq); - struct nwl_pcie *pcie; + struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data); unsigned long flags; u32 mask; u32 val; - pcie = irq_desc_get_chip_data(desc); - mask = 1 << (data->hwirq - 1); + mask = 1 << data->hwirq; raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags); val = nwl_bridge_readl(pcie, MSGF_LEG_MASK); nwl_bridge_writel(pcie, (val & (~mask)), MSGF_LEG_MASK); raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags); } -static void nwl_unmask_leg_irq(struct irq_data *data) +static void nwl_unmask_intx_irq(struct irq_data *data) { - struct irq_desc *desc = irq_to_desc(data->irq); - struct nwl_pcie *pcie; + struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data); unsigned long flags; u32 mask; u32 val; - pcie = irq_desc_get_chip_data(desc); - mask = 1 << (data->hwirq - 1); + mask = 1 << data->hwirq; raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags); val = nwl_bridge_readl(pcie, MSGF_LEG_MASK); nwl_bridge_writel(pcie, (val | mask), MSGF_LEG_MASK); raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags); } -static struct irq_chip nwl_leg_irq_chip = { +static struct irq_chip nwl_intx_irq_chip = { .name = "nwl_pcie:legacy", - .irq_enable = nwl_unmask_leg_irq, - .irq_disable = nwl_mask_leg_irq, - .irq_mask = nwl_mask_leg_irq, - .irq_unmask = nwl_unmask_leg_irq, + .irq_enable = nwl_unmask_intx_irq, + .irq_disable = nwl_mask_intx_irq, + .irq_mask = nwl_mask_intx_irq, + .irq_unmask = nwl_unmask_intx_irq, }; -static int nwl_legacy_map(struct irq_domain *domain, unsigned int irq, - irq_hw_number_t hwirq) +static int nwl_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) { - irq_set_chip_and_handler(irq, &nwl_leg_irq_chip, handle_level_irq); + irq_set_chip_and_handler(irq, &nwl_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 legacy_domain_ops = { - .map = nwl_legacy_map, +static const struct irq_domain_ops intx_domain_ops = { + .map = nwl_intx_map, .xlate = pci_irqd_intx_xlate, }; #ifdef CONFIG_PCI_MSI -static struct irq_chip nwl_msi_irq_chip = { - .name = "nwl_pcie:msi", - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, -}; +#define NWL_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) -static struct msi_domain_info nwl_msi_domain_info = { - .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_MULTI_PCI_MSI), - .chip = &nwl_msi_irq_chip, +#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) @@ -462,16 +446,9 @@ static void nwl_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) msg->data = data->hwirq; } -static int nwl_msi_set_affinity(struct irq_data *irq_data, - const struct cpumask *mask, bool force) -{ - return -EINVAL; -} - static struct irq_chip nwl_irq_chip = { .name = "Xilinx MSI", .irq_compose_msi_msg = nwl_compose_msi_msg, - .irq_set_affinity = nwl_msi_set_affinity, }; static int nwl_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, @@ -483,33 +460,32 @@ static int nwl_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, int i; mutex_lock(&msi->lock); - bit = bitmap_find_next_zero_area(msi->bitmap, INT_PCI_MSI_NR, 0, - nr_irqs, 0); - if (bit >= INT_PCI_MSI_NR) { + bit = bitmap_find_free_region(msi->bitmap, INT_PCI_MSI_NR, + get_count_order(nr_irqs)); + if (bit < 0) { mutex_unlock(&msi->lock); return -ENOSPC; } - bitmap_set(msi->bitmap, bit, nr_irqs); - for (i = 0; i < nr_irqs; i++) { irq_domain_set_info(domain, virq + i, bit + i, &nwl_irq_chip, - domain->host_data, handle_simple_irq, - NULL, NULL); + domain->host_data, handle_simple_irq, + NULL, NULL); } mutex_unlock(&msi->lock); return 0; } static void nwl_irq_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs) + unsigned int nr_irqs) { struct irq_data *data = irq_domain_get_irq_data(domain, virq); struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data); struct nwl_msi *msi = &pcie->msi; mutex_lock(&msi->lock); - bitmap_clear(msi->bitmap, data->hwirq, nr_irqs); + bitmap_release_region(msi->bitmap, data->hwirq, + get_count_order(nr_irqs)); mutex_unlock(&msi->lock); } @@ -522,45 +498,93 @@ 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; } +static void nwl_pcie_phy_power_off(struct nwl_pcie *pcie, int i) +{ + int err = phy_power_off(pcie->phy[i]); + + if (err) + dev_err(pcie->dev, "could not power off phy %d (err=%d)\n", i, + err); +} + +static void nwl_pcie_phy_exit(struct nwl_pcie *pcie, int i) +{ + int err = phy_exit(pcie->phy[i]); + + if (err) + dev_err(pcie->dev, "could not exit phy %d (err=%d)\n", i, err); +} + +static int nwl_pcie_phy_enable(struct nwl_pcie *pcie) +{ + int i, ret; + + for (i = 0; i < ARRAY_SIZE(pcie->phy); i++) { + ret = phy_init(pcie->phy[i]); + if (ret) + goto err; + + ret = phy_power_on(pcie->phy[i]); + if (ret) { + nwl_pcie_phy_exit(pcie, i); + goto err; + } + } + + return 0; + +err: + while (i--) { + nwl_pcie_phy_power_off(pcie, i); + nwl_pcie_phy_exit(pcie, i); + } + + return ret; +} + +static void nwl_pcie_phy_disable(struct nwl_pcie *pcie) +{ + int i; + + for (i = ARRAY_SIZE(pcie->phy); i--;) { + nwl_pcie_phy_power_off(pcie, i); + nwl_pcie_phy_exit(pcie, i); + } +} + static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie) { struct device *dev = pcie->dev; struct device_node *node = dev->of_node; - struct device_node *legacy_intc_node; + struct device_node *intc_node; - legacy_intc_node = of_get_next_child(node, NULL); - if (!legacy_intc_node) { + intc_node = of_get_next_child(node, NULL); + if (!intc_node) { dev_err(dev, "No legacy intc node found\n"); return -EINVAL; } - pcie->legacy_irq_domain = irq_domain_add_linear(legacy_intc_node, - PCI_NUM_INTX, - &legacy_domain_ops, - pcie); - of_node_put(legacy_intc_node); - if (!pcie->legacy_irq_domain) { + 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"); return -ENOMEM; } @@ -577,32 +601,21 @@ static int nwl_pcie_enable_msi(struct nwl_pcie *pcie) struct nwl_msi *msi = &pcie->msi; unsigned long base; int ret; - int size = BITS_TO_LONGS(INT_PCI_MSI_NR) * sizeof(long); mutex_init(&msi->lock); - msi->bitmap = kzalloc(size, GFP_KERNEL); - if (!msi->bitmap) - return -ENOMEM; - /* Get msi_1 IRQ number */ msi->irq_msi1 = platform_get_irq_byname(pdev, "msi1"); - if (msi->irq_msi1 < 0) { - dev_err(dev, "failed to get IRQ#%d\n", msi->irq_msi1); - ret = -EINVAL; - goto err; - } + if (msi->irq_msi1 < 0) + return -EINVAL; irq_set_chained_handler_and_data(msi->irq_msi1, nwl_pcie_msi_handler_high, pcie); /* Get msi_0 IRQ number */ msi->irq_msi0 = platform_get_irq_byname(pdev, "msi0"); - if (msi->irq_msi0 < 0) { - dev_err(dev, "failed to get IRQ#%d\n", msi->irq_msi0); - ret = -EINVAL; - goto err; - } + if (msi->irq_msi0 < 0) + return -EINVAL; irq_set_chained_handler_and_data(msi->irq_msi0, nwl_pcie_msi_handler_low, pcie); @@ -611,8 +624,7 @@ static int nwl_pcie_enable_msi(struct nwl_pcie *pcie) ret = nwl_bridge_readl(pcie, I_MSII_CAPABILITIES) & MSII_PRESENT; if (!ret) { dev_err(dev, "MSI not present\n"); - ret = -EIO; - goto err; + return -EIO; } /* Enable MSII */ @@ -651,17 +663,13 @@ static int nwl_pcie_enable_msi(struct nwl_pcie *pcie) nwl_bridge_writel(pcie, MSGF_MSI_SR_LO_MASK, MSGF_MSI_MASK_LO); return 0; -err: - kfree(msi->bitmap); - msi->bitmap = NULL; - return ret; } static int nwl_pcie_bridge_init(struct nwl_pcie *pcie) { struct device *dev = pcie->dev; struct platform_device *pdev = to_platform_device(dev); - u32 breg_val, ecam_val, first_busno = 0; + u32 breg_val, ecam_val; int err; breg_val = nwl_bridge_readl(pcie, E_BREG_CAPABILITIES) & BREG_PRESENT; @@ -691,6 +699,11 @@ static int nwl_pcie_bridge_init(struct nwl_pcie *pcie) nwl_bridge_writel(pcie, CFG_ENABLE_MSG_FILTER_MASK, BRCFG_PCIE_RX_MSG_FILTER); + /* This routes the PCIe DMA traffic to go through CCI path */ + if (of_dma_is_coherent(dev->of_node)) + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, BRCFG_PCIE_RX1) | + CFG_PCIE_CACHE, BRCFG_PCIE_RX1); + err = nwl_wait_for_link(pcie); if (err) return err; @@ -705,24 +718,16 @@ 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) | - (pcie->ecam_value << 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); nwl_bridge_writel(pcie, upper_32_bits(pcie->phys_ecam_base), E_ECAM_BASE_HI); - /* Get bus range */ - ecam_val = nwl_bridge_readl(pcie, E_ECAM_CONTROL); - pcie->last_busno = (ecam_val & E_ECAM_SIZE_LOC) >> E_ECAM_SIZE_SHIFT; - /* Write primary, secondary and subordinate bus numbers */ - ecam_val = first_busno; - ecam_val |= (first_busno + 1) << 8; - ecam_val |= (pcie->last_busno << E_ECAM_SIZE_SHIFT); - writel(ecam_val, (pcie->ecam_base + PCI_PRIMARY_BUS)); - if (nwl_pcie_link_up(pcie)) dev_info(dev, "Link is UP\n"); else @@ -730,11 +735,8 @@ static int nwl_pcie_bridge_init(struct nwl_pcie *pcie) /* Get misc IRQ number */ pcie->irq_misc = platform_get_irq_byname(pdev, "misc"); - if (pcie->irq_misc < 0) { - dev_err(dev, "failed to get misc IRQ %d\n", - pcie->irq_misc); + if (pcie->irq_misc < 0) return -EINVAL; - } err = devm_request_irq(dev, pcie->irq_misc, nwl_pcie_misc_handler, IRQF_SHARED, @@ -755,15 +757,14 @@ static int nwl_pcie_bridge_init(struct nwl_pcie *pcie) /* Enable all misc interrupts */ nwl_bridge_writel(pcie, MSGF_MISC_SR_MASKALL, MSGF_MISC_MASK); - - /* Disable all legacy interrupts */ + /* Disable all INTX interrupts */ nwl_bridge_writel(pcie, (u32)~MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK); - /* Clear pending legacy interrupts */ + /* Clear pending INTX interrupts */ nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_LEG_STATUS) & MSGF_LEG_SR_MASKALL, MSGF_LEG_STATUS); - /* Enable all legacy interrupts */ + /* Enable all INTX interrupts */ nwl_bridge_writel(pcie, MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK); /* Enable the bridge config interrupt */ @@ -778,6 +779,7 @@ static int nwl_pcie_parse_dt(struct nwl_pcie *pcie, { struct device *dev = pcie->dev; struct resource *res; + int i; res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "breg"); pcie->breg_base = devm_ioremap_resource(dev, res); @@ -799,14 +801,24 @@ static int nwl_pcie_parse_dt(struct nwl_pcie *pcie, /* Get intx IRQ number */ pcie->irq_intx = platform_get_irq_byname(pdev, "intx"); - if (pcie->irq_intx < 0) { - dev_err(dev, "failed to get intx IRQ %d\n", pcie->irq_intx); + if (pcie->irq_intx < 0) return pcie->irq_intx; - } irq_set_chained_handler_and_data(pcie->irq_intx, nwl_pcie_leg_handler, pcie); + + for (i = 0; i < ARRAY_SIZE(pcie->phy); i++) { + pcie->phy[i] = devm_of_phy_get_by_index(dev, dev->of_node, i); + if (PTR_ERR(pcie->phy[i]) == -ENODEV) { + pcie->phy[i] = NULL; + break; + } + + if (IS_ERR(pcie->phy[i])) + return PTR_ERR(pcie->phy[i]); + } + return 0; } @@ -819,21 +831,17 @@ static int nwl_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct nwl_pcie *pcie; - struct pci_bus *bus; - struct pci_bus *child; struct pci_host_bridge *bridge; int err; - resource_size_t iobase = 0; - LIST_HEAD(res); bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); if (!bridge) return -ENODEV; pcie = pci_host_bridge_priv(bridge); + platform_set_drvdata(pdev, pcie); pcie->dev = dev; - pcie->ecam_value = NWL_ECAM_VALUE_DEFAULT; err = nwl_pcie_parse_dt(pcie, pdev); if (err) { @@ -841,60 +849,62 @@ static int nwl_pcie_probe(struct platform_device *pdev) return err; } - err = nwl_pcie_bridge_init(pcie); + pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(pcie->clk)) + return PTR_ERR(pcie->clk); + + err = clk_prepare_enable(pcie->clk); if (err) { - dev_err(dev, "HW Initialization failed\n"); + dev_err(dev, "can't enable PCIe ref clock\n"); return err; } - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &res, - &iobase); + err = nwl_pcie_phy_enable(pcie); if (err) { - dev_err(dev, "Getting bridge resources failed\n"); - return err; + dev_err(dev, "could not enable PHYs\n"); + goto err_clk; } - err = devm_request_pci_bus_resources(dev, &res); - if (err) - goto error; + err = nwl_pcie_bridge_init(pcie); + if (err) { + dev_err(dev, "HW Initialization failed\n"); + goto err_phy; + } err = nwl_pcie_init_irq_domain(pcie); if (err) { dev_err(dev, "Failed creating IRQ Domain\n"); - goto error; + goto err_phy; } - list_splice_init(&res, &bridge->windows); - bridge->dev.parent = dev; bridge->sysdata = pcie; - bridge->busnr = pcie->root_busno; bridge->ops = &nwl_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; if (IS_ENABLED(CONFIG_PCI_MSI)) { err = nwl_pcie_enable_msi(pcie); if (err < 0) { dev_err(dev, "failed to enable MSI support: %d\n", err); - goto error; + goto err_phy; } } - err = pci_scan_root_bus_bridge(bridge); - if (err) - goto error; + err = pci_host_probe(bridge); + if (!err) + return 0; - bus = bridge->bus; +err_phy: + nwl_pcie_phy_disable(pcie); +err_clk: + clk_disable_unprepare(pcie->clk); + return err; +} - pci_assign_unassigned_bus_resources(bus); - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); - pci_bus_add_devices(bus); - return 0; +static void nwl_pcie_remove(struct platform_device *pdev) +{ + struct nwl_pcie *pcie = platform_get_drvdata(pdev); -error: - pci_free_resource_list(&res); - return err; + nwl_pcie_phy_disable(pcie); + clk_disable_unprepare(pcie->clk); } static struct platform_driver nwl_pcie_driver = { @@ -904,5 +914,6 @@ static struct platform_driver nwl_pcie_driver = { .of_match_table = nwl_pcie_of_match, }, .probe = nwl_pcie_probe, + .remove = nwl_pcie_remove, }; builtin_platform_driver(nwl_pcie_driver); diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index 9bd1a35cd5d8..937ea6ae1ac4 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/init.h> @@ -21,6 +22,7 @@ #include <linux/of_platform.h> #include <linux/of_irq.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> #include <linux/platform_device.h> #include "../pci.h" @@ -86,66 +88,58 @@ /* Phy Status/Control Register definitions */ #define XILINX_PCIE_REG_PSCR_LNKUP BIT(11) -/* ECAM definitions */ -#define ECAM_BUS_NUM_SHIFT 20 -#define ECAM_DEV_NUM_SHIFT 12 - /* Number of MSI IRQs */ #define XILINX_NUM_MSI_IRQS 128 /** - * struct xilinx_pcie_port - PCIe port information - * @reg_base: IO Mapped Register Base - * @irq: Interrupt number - * @msi_pages: MSI pages - * @root_busno: Root Bus number + * struct xilinx_pcie - PCIe port information * @dev: Device pointer + * @reg_base: IO Mapped Register Base + * @msi_map: Bitmap of allocated MSIs + * @map_lock: Mutex protecting the MSI allocation * @msi_domain: MSI IRQ domain pointer * @leg_domain: Legacy IRQ domain pointer * @resources: Bus Resources */ -struct xilinx_pcie_port { - void __iomem *reg_base; - u32 irq; - unsigned long msi_pages; - u8 root_busno; +struct xilinx_pcie { struct device *dev; + void __iomem *reg_base; + unsigned long msi_map[BITS_TO_LONGS(XILINX_NUM_MSI_IRQS)]; + struct mutex map_lock; struct irq_domain *msi_domain; struct irq_domain *leg_domain; struct list_head resources; }; -static DECLARE_BITMAP(msi_irq_in_use, XILINX_NUM_MSI_IRQS); - -static inline u32 pcie_read(struct xilinx_pcie_port *port, u32 reg) +static inline u32 pcie_read(struct xilinx_pcie *pcie, u32 reg) { - return readl(port->reg_base + reg); + return readl(pcie->reg_base + reg); } -static inline void pcie_write(struct xilinx_pcie_port *port, u32 val, u32 reg) +static inline void pcie_write(struct xilinx_pcie *pcie, u32 val, u32 reg) { - writel(val, port->reg_base + reg); + writel(val, pcie->reg_base + reg); } -static inline bool xilinx_pcie_link_up(struct xilinx_pcie_port *port) +static inline bool xilinx_pcie_link_up(struct xilinx_pcie *pcie) { - return (pcie_read(port, XILINX_PCIE_REG_PSCR) & + return (pcie_read(pcie, XILINX_PCIE_REG_PSCR) & XILINX_PCIE_REG_PSCR_LNKUP) ? 1 : 0; } /** * xilinx_pcie_clear_err_interrupts - Clear Error Interrupts - * @port: PCIe port information + * @pcie: PCIe port information */ -static void xilinx_pcie_clear_err_interrupts(struct xilinx_pcie_port *port) +static void xilinx_pcie_clear_err_interrupts(struct xilinx_pcie *pcie) { - struct device *dev = port->dev; - unsigned long val = pcie_read(port, XILINX_PCIE_REG_RPEFR); + struct device *dev = pcie->dev; + unsigned long val = pcie_read(pcie, XILINX_PCIE_REG_RPEFR); if (val & XILINX_PCIE_RPEFR_ERR_VALID) { dev_dbg(dev, "Requester ID %lu\n", val & XILINX_PCIE_RPEFR_REQ_ID); - pcie_write(port, XILINX_PCIE_RPEFR_ALL_MASK, + pcie_write(pcie, XILINX_PCIE_RPEFR_ALL_MASK, XILINX_PCIE_REG_RPEFR); } } @@ -159,17 +153,16 @@ static void xilinx_pcie_clear_err_interrupts(struct xilinx_pcie_port *port) */ static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) { - struct xilinx_pcie_port *port = bus->sysdata; + struct xilinx_pcie *pcie = bus->sysdata; - /* Check if link is up when trying to access downstream ports */ - if (bus->number != port->root_busno) - if (!xilinx_pcie_link_up(port)) + /* Check if link is up when trying to access downstream pcie ports */ + if (!pci_is_root_bus(bus)) { + if (!xilinx_pcie_link_up(pcie)) return false; - - /* Only one device down on each root port */ - if (bus->number == port->root_busno && devfn > 0) + } else if (devfn > 0) { + /* Only one device down on each root port */ return false; - + } return true; } @@ -185,16 +178,12 @@ static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) static void __iomem *xilinx_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, int where) { - struct xilinx_pcie_port *port = bus->sysdata; - int relbus; + struct xilinx_pcie *pcie = bus->sysdata; if (!xilinx_pcie_valid_device(bus, devfn)) return NULL; - relbus = (bus->number << ECAM_BUS_NUM_SHIFT) | - (devfn << ECAM_DEV_NUM_SHIFT); - - return port->reg_base + relbus + where; + return pcie->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); } /* PCIe operations */ @@ -206,144 +195,116 @@ static struct pci_ops xilinx_pcie_ops = { /* MSI functions */ -/** - * xilinx_pcie_destroy_msi - Free MSI number - * @irq: IRQ to be freed - */ -static void xilinx_pcie_destroy_msi(unsigned int irq) +static void xilinx_msi_top_irq_ack(struct irq_data *d) { - struct msi_desc *msi; - struct xilinx_pcie_port *port; - struct irq_data *d = irq_get_irq_data(irq); - irq_hw_number_t hwirq = irqd_to_hwirq(d); - - if (!test_bit(hwirq, msi_irq_in_use)) { - msi = irq_get_msi_desc(irq); - port = msi_desc_to_pci_sysdata(msi); - dev_err(port->dev, "Trying to free unused MSI#%d\n", irq); - } else { - clear_bit(hwirq, msi_irq_in_use); - } + /* + * xilinx_pcie_intr_handler() will have performed the Ack. + * Eventually, this should be fixed and the Ack be moved in + * the respective callbacks for INTx and MSI. + */ } -/** - * xilinx_pcie_assign_msi - Allocate MSI number - * - * Return: A valid IRQ on success and error value on failure. - */ -static int xilinx_pcie_assign_msi(void) +static void xilinx_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { - int pos; - - pos = find_first_zero_bit(msi_irq_in_use, XILINX_NUM_MSI_IRQS); - if (pos < XILINX_NUM_MSI_IRQS) - set_bit(pos, msi_irq_in_use); - else - return -ENOSPC; + struct xilinx_pcie *pcie = irq_data_get_irq_chip_data(data); + phys_addr_t pa = ALIGN_DOWN(virt_to_phys(pcie), SZ_4K); - return pos; + msg->address_lo = lower_32_bits(pa); + msg->address_hi = upper_32_bits(pa); + msg->data = data->hwirq; } -/** - * xilinx_msi_teardown_irq - Destroy the MSI - * @chip: MSI Chip descriptor - * @irq: MSI IRQ to destroy - */ -static void xilinx_msi_teardown_irq(struct msi_controller *chip, - unsigned int irq) -{ - xilinx_pcie_destroy_msi(irq); - irq_dispose_mapping(irq); -} +static struct irq_chip xilinx_msi_bottom_chip = { + .name = "Xilinx MSI", + .irq_compose_msi_msg = xilinx_compose_msi_msg, +}; -/** - * xilinx_pcie_msi_setup_irq - Setup MSI request - * @chip: MSI chip pointer - * @pdev: PCIe device pointer - * @desc: MSI descriptor pointer - * - * Return: '0' on success and error value on failure - */ -static int xilinx_pcie_msi_setup_irq(struct msi_controller *chip, - struct pci_dev *pdev, - struct msi_desc *desc) +static int xilinx_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) { - struct xilinx_pcie_port *port = pdev->bus->sysdata; - unsigned int irq; - int hwirq; - struct msi_msg msg; - phys_addr_t msg_addr; - - hwirq = xilinx_pcie_assign_msi(); - if (hwirq < 0) - return hwirq; + struct xilinx_pcie *pcie = domain->host_data; + int hwirq, i; - irq = irq_create_mapping(port->msi_domain, hwirq); - if (!irq) - return -EINVAL; + mutex_lock(&pcie->map_lock); - irq_set_msi_desc(irq, desc); + hwirq = bitmap_find_free_region(pcie->msi_map, XILINX_NUM_MSI_IRQS, order_base_2(nr_irqs)); - msg_addr = virt_to_phys((void *)port->msi_pages); + mutex_unlock(&pcie->map_lock); - msg.address_hi = 0; - msg.address_lo = msg_addr; - msg.data = irq; + if (hwirq < 0) + return -ENOSPC; - pci_write_msi_msg(irq, &msg); + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &xilinx_msi_bottom_chip, domain->host_data, + handle_edge_irq, NULL, NULL); return 0; } -/* MSI Chip Descriptor */ -static struct msi_controller xilinx_pcie_msi_chip = { - .setup_irq = xilinx_pcie_msi_setup_irq, - .teardown_irq = xilinx_msi_teardown_irq, -}; +static void xilinx_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct xilinx_pcie *pcie = domain->host_data; + + mutex_lock(&pcie->map_lock); + + bitmap_release_region(pcie->msi_map, d->hwirq, order_base_2(nr_irqs)); -/* HW Interrupt Chip Descriptor */ -static struct irq_chip xilinx_msi_irq_chip = { - .name = "Xilinx 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, + mutex_unlock(&pcie->map_lock); +} + +static const struct irq_domain_ops xilinx_msi_domain_ops = { + .alloc = xilinx_msi_domain_alloc, + .free = xilinx_msi_domain_free, }; -/** - * xilinx_pcie_msi_map - Set the handler for the MSI and mark IRQ as valid - * @domain: IRQ domain - * @irq: Virtual IRQ number - * @hwirq: HW interrupt number - * - * Return: Always returns 0. - */ -static int xilinx_pcie_msi_map(struct irq_domain *domain, unsigned int irq, - irq_hw_number_t hwirq) +static bool xilinx_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, struct msi_domain_info *info) { - irq_set_chip_and_handler(irq, &xilinx_msi_irq_chip, handle_simple_irq); - irq_set_chip_data(irq, domain->host_data); + struct irq_chip *chip = info->chip; - return 0; + if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) + return false; + + chip->irq_ack = xilinx_msi_top_irq_ack; + return true; } -/* IRQ Domain operations */ -static const struct irq_domain_ops msi_domain_ops = { - .map = xilinx_pcie_msi_map, +#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, }; -/** - * xilinx_pcie_enable_msi - Enable MSI support - * @port: PCIe port information - */ -static void xilinx_pcie_enable_msi(struct xilinx_pcie_port *port) +static int xilinx_allocate_msi_domains(struct xilinx_pcie *pcie) { - phys_addr_t msg_addr; + 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"); + return -ENOMEM; + } - port->msi_pages = __get_free_pages(GFP_KERNEL, 0); - msg_addr = virt_to_phys((void *)port->msi_pages); - pcie_write(port, 0x0, XILINX_PCIE_REG_MSIBASE1); - pcie_write(port, msg_addr, XILINX_PCIE_REG_MSIBASE2); + return 0; +} + +static void xilinx_free_msi_domains(struct xilinx_pcie *pcie) +{ + irq_domain_remove(pcie->msi_domain); } /* INTx Functions */ @@ -382,13 +343,13 @@ static const struct irq_domain_ops intx_domain_ops = { */ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) { - struct xilinx_pcie_port *port = (struct xilinx_pcie_port *)data; - struct device *dev = port->dev; + struct xilinx_pcie *pcie = (struct xilinx_pcie *)data; + struct device *dev = pcie->dev; u32 val, mask, status; /* Read interrupt decode and mask registers */ - val = pcie_read(port, XILINX_PCIE_REG_IDR); - mask = pcie_read(port, XILINX_PCIE_REG_IMR); + val = pcie_read(pcie, XILINX_PCIE_REG_IDR); + mask = pcie_read(pcie, XILINX_PCIE_REG_IMR); status = val & mask; if (!status) @@ -411,21 +372,23 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) if (status & XILINX_PCIE_INTR_CORRECTABLE) { dev_warn(dev, "Correctable error message\n"); - xilinx_pcie_clear_err_interrupts(port); + xilinx_pcie_clear_err_interrupts(pcie); } if (status & XILINX_PCIE_INTR_NONFATAL) { dev_warn(dev, "Non fatal error message\n"); - xilinx_pcie_clear_err_interrupts(port); + xilinx_pcie_clear_err_interrupts(pcie); } if (status & XILINX_PCIE_INTR_FATAL) { dev_warn(dev, "Fatal error message\n"); - xilinx_pcie_clear_err_interrupts(port); + xilinx_pcie_clear_err_interrupts(pcie); } if (status & (XILINX_PCIE_INTR_INTX | XILINX_PCIE_INTR_MSI)) { - val = pcie_read(port, XILINX_PCIE_REG_RPIFR1); + struct irq_domain *domain; + + val = pcie_read(pcie, XILINX_PCIE_REG_RPIFR1); /* Check whether interrupt valid */ if (!(val & XILINX_PCIE_RPIFR1_INTR_VALID)) { @@ -435,22 +398,20 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) /* Decode the IRQ number */ if (val & XILINX_PCIE_RPIFR1_MSI_INTR) { - val = pcie_read(port, XILINX_PCIE_REG_RPIFR2) & + val = pcie_read(pcie, XILINX_PCIE_REG_RPIFR2) & XILINX_PCIE_RPIFR2_MSG_DATA; + domain = pcie->msi_domain; } else { val = (val & XILINX_PCIE_RPIFR1_INTR_MASK) >> XILINX_PCIE_RPIFR1_INTR_SHIFT; - val = irq_find_mapping(port->leg_domain, val); + domain = pcie->leg_domain; } /* Clear interrupt FIFO register 1 */ - pcie_write(port, XILINX_PCIE_RPIFR1_ALL_MASK, + pcie_write(pcie, XILINX_PCIE_RPIFR1_ALL_MASK, XILINX_PCIE_REG_RPIFR1); - /* Handle the interrupt */ - if (IS_ENABLED(CONFIG_PCI_MSI) || - !(val & XILINX_PCIE_RPIFR1_MSI_INTR)) - generic_handle_irq(val); + generic_handle_domain_irq(domain, val); } if (status & XILINX_PCIE_INTR_SLV_UNSUPP) @@ -482,51 +443,48 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) error: /* Clear the Interrupt Decode register */ - pcie_write(port, status, XILINX_PCIE_REG_IDR); + pcie_write(pcie, status, XILINX_PCIE_REG_IDR); return IRQ_HANDLED; } /** * xilinx_pcie_init_irq_domain - Initialize IRQ domain - * @port: PCIe port information + * @pcie: PCIe port information * * Return: '0' on success and error value on failure */ -static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port) +static int xilinx_pcie_init_irq_domain(struct xilinx_pcie *pcie) { - struct device *dev = port->dev; - struct device_node *node = dev->of_node; + struct device *dev = pcie->dev; struct device_node *pcie_intc_node; + int ret; /* Setup INTx */ - pcie_intc_node = of_get_next_child(node, NULL); + pcie_intc_node = of_get_next_child(dev->of_node, NULL); if (!pcie_intc_node) { dev_err(dev, "No PCIe Intc node found\n"); return -ENODEV; } - port->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, - &intx_domain_ops, - port); + 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 (!port->leg_domain) { + if (!pcie->leg_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); return -ENODEV; } /* Setup MSI */ if (IS_ENABLED(CONFIG_PCI_MSI)) { - port->msi_domain = irq_domain_add_linear(node, - XILINX_NUM_MSI_IRQS, - &msi_domain_ops, - &xilinx_pcie_msi_chip); - if (!port->msi_domain) { - dev_err(dev, "Failed to get a MSI IRQ domain\n"); - return -ENODEV; - } + phys_addr_t pa = ALIGN_DOWN(virt_to_phys(pcie), SZ_4K); + + ret = xilinx_allocate_msi_domains(pcie); + if (ret) + return ret; - xilinx_pcie_enable_msi(port); + pcie_write(pcie, upper_32_bits(pa), XILINX_PCIE_REG_MSIBASE1); + pcie_write(pcie, lower_32_bits(pa), XILINX_PCIE_REG_MSIBASE2); } return 0; @@ -534,46 +492,47 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port) /** * xilinx_pcie_init_port - Initialize hardware - * @port: PCIe port information + * @pcie: PCIe port information */ -static void xilinx_pcie_init_port(struct xilinx_pcie_port *port) +static void xilinx_pcie_init_port(struct xilinx_pcie *pcie) { - struct device *dev = port->dev; + struct device *dev = pcie->dev; - if (xilinx_pcie_link_up(port)) + if (xilinx_pcie_link_up(pcie)) dev_info(dev, "PCIe Link is UP\n"); else dev_info(dev, "PCIe Link is DOWN\n"); /* Disable all interrupts */ - pcie_write(port, ~XILINX_PCIE_IDR_ALL_MASK, + pcie_write(pcie, ~XILINX_PCIE_IDR_ALL_MASK, XILINX_PCIE_REG_IMR); /* Clear pending interrupts */ - pcie_write(port, pcie_read(port, XILINX_PCIE_REG_IDR) & + pcie_write(pcie, pcie_read(pcie, XILINX_PCIE_REG_IDR) & XILINX_PCIE_IMR_ALL_MASK, XILINX_PCIE_REG_IDR); /* Enable all interrupts we handle */ - pcie_write(port, XILINX_PCIE_IMR_ENABLE_MASK, XILINX_PCIE_REG_IMR); + pcie_write(pcie, XILINX_PCIE_IMR_ENABLE_MASK, XILINX_PCIE_REG_IMR); /* Enable the Bridge enable bit */ - pcie_write(port, pcie_read(port, XILINX_PCIE_REG_RPSC) | + pcie_write(pcie, pcie_read(pcie, XILINX_PCIE_REG_RPSC) | XILINX_PCIE_REG_RPSC_BEN, XILINX_PCIE_REG_RPSC); } /** * xilinx_pcie_parse_dt - Parse Device tree - * @port: PCIe port information + * @pcie: PCIe port information * * Return: '0' on success and error value on failure */ -static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port) +static int xilinx_pcie_parse_dt(struct xilinx_pcie *pcie) { - struct device *dev = port->dev; + struct device *dev = pcie->dev; struct device_node *node = dev->of_node; struct resource regs; + unsigned int irq; int err; err = of_address_to_resource(node, 0, ®s); @@ -582,16 +541,16 @@ static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port) return err; } - port->reg_base = devm_pci_remap_cfg_resource(dev, ®s); - if (IS_ERR(port->reg_base)) - return PTR_ERR(port->reg_base); + pcie->reg_base = devm_pci_remap_cfg_resource(dev, ®s); + if (IS_ERR(pcie->reg_base)) + return PTR_ERR(pcie->reg_base); - port->irq = irq_of_parse_and_map(node, 0); - err = devm_request_irq(dev, port->irq, xilinx_pcie_intr_handler, + irq = irq_of_parse_and_map(node, 0); + err = devm_request_irq(dev, irq, xilinx_pcie_intr_handler, IRQF_SHARED | IRQF_NO_THREAD, - "xilinx-pcie", port); + "xilinx-pcie", pcie); if (err) { - dev_err(dev, "unable to request irq %d\n", port->irq); + dev_err(dev, "unable to request irq %d\n", irq); return err; } @@ -607,76 +566,42 @@ static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port) static int xilinx_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct xilinx_pcie_port *port; - struct pci_bus *bus, *child; + struct xilinx_pcie *pcie; struct pci_host_bridge *bridge; int err; - resource_size_t iobase = 0; - LIST_HEAD(res); if (!dev->of_node) return -ENODEV; - bridge = devm_pci_alloc_host_bridge(dev, sizeof(*port)); + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); if (!bridge) return -ENODEV; - port = pci_host_bridge_priv(bridge); - - port->dev = dev; + pcie = pci_host_bridge_priv(bridge); + mutex_init(&pcie->map_lock); + pcie->dev = dev; - err = xilinx_pcie_parse_dt(port); + err = xilinx_pcie_parse_dt(pcie); if (err) { dev_err(dev, "Parsing DT failed\n"); return err; } - xilinx_pcie_init_port(port); + xilinx_pcie_init_port(pcie); - err = xilinx_pcie_init_irq_domain(port); + err = xilinx_pcie_init_irq_domain(pcie); if (err) { dev_err(dev, "Failed creating IRQ Domain\n"); return err; } - err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &res, - &iobase); - if (err) { - dev_err(dev, "Getting bridge resources failed\n"); - return err; - } + bridge->sysdata = pcie; + bridge->ops = &xilinx_pcie_ops; - err = devm_request_pci_bus_resources(dev, &res); + err = pci_host_probe(bridge); if (err) - goto error; - + xilinx_free_msi_domains(pcie); - list_splice_init(&res, &bridge->windows); - bridge->dev.parent = dev; - bridge->sysdata = port; - bridge->busnr = 0; - bridge->ops = &xilinx_pcie_ops; - bridge->map_irq = of_irq_parse_and_map_pci; - bridge->swizzle_irq = pci_common_swizzle; - -#ifdef CONFIG_PCI_MSI - xilinx_pcie_msi_chip.dev = dev; - bridge->msi = &xilinx_pcie_msi_chip; -#endif - err = pci_scan_root_bus_bridge(bridge); - if (err < 0) - goto error; - - bus = bridge->bus; - - pci_assign_unassigned_bus_resources(bus); - list_for_each_entry(child, &bus->children, node) - pcie_bus_configure_settings(child); - pci_bus_add_devices(bus); - return 0; - -error: - pci_free_resource_list(&res); return err; } diff --git a/drivers/pci/controller/plda/Kconfig b/drivers/pci/controller/plda/Kconfig new file mode 100644 index 000000000000..62120101139c --- /dev/null +++ b/drivers/pci/controller/plda/Kconfig @@ -0,0 +1,31 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "PLDA-based PCIe controllers" + depends on PCI + +config PCIE_PLDA_HOST + bool + select IRQ_MSI_LIB + +config PCIE_MICROCHIP_HOST + tristate "Microchip AXI PCIe controller" + depends on PCI_MSI && OF + select PCI_HOST_COMMON + select PCIE_PLDA_HOST + help + Say Y here if you want kernel to support the Microchip AXI PCIe + Host Bridge driver. + +config PCIE_STARFIVE_HOST + tristate "StarFive PCIe host controller" + depends on PCI_MSI && OF + depends on ARCH_STARFIVE || COMPILE_TEST + select PCIE_PLDA_HOST + help + Say Y here if you want to support the StarFive PCIe controller in + host mode. StarFive PCIe controller uses PLDA PCIe core. + + If you choose to build this driver as module it will be dynamically + linked and module will be called pcie-starfive.ko. + +endmenu diff --git a/drivers/pci/controller/plda/Makefile b/drivers/pci/controller/plda/Makefile new file mode 100644 index 000000000000..0ac6851bed48 --- /dev/null +++ b/drivers/pci/controller/plda/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_PCIE_PLDA_HOST) += pcie-plda-host.o +obj-$(CONFIG_PCIE_MICROCHIP_HOST) += pcie-microchip-host.o +obj-$(CONFIG_PCIE_STARFIVE_HOST) += pcie-starfive.o diff --git a/drivers/pci/controller/plda/pcie-microchip-host.c b/drivers/pci/controller/plda/pcie-microchip-host.c new file mode 100644 index 000000000000..24bbf93b8051 --- /dev/null +++ b/drivers/pci/controller/plda/pcie-microchip-host.c @@ -0,0 +1,834 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Microchip AXI PCIe Bridge host controller driver + * + * Copyright (c) 2018 - 2020 Microchip Corporation. All rights reserved. + * + * Author: Daire McNamara <daire.mcnamara@microchip.com> + */ + +#include <linux/align.h> +#include <linux/bits.h> +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/log2.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> +#include <linux/wordpart.h> + +#include "../../pci.h" +#include "../pci-host-common.h" +#include "pcie-plda.h" + +#define MC_MAX_NUM_INBOUND_WINDOWS 8 +#define MPFS_NC_BOUNCE_ADDR 0x80000000 + +/* PCIe Bridge Phy and Controller Phy offsets */ +#define MC_PCIE1_BRIDGE_ADDR 0x00008000u +#define MC_PCIE1_CTRL_ADDR 0x0000a000u + +/* PCIe Controller Phy Regs */ +#define SEC_ERROR_EVENT_CNT 0x20 +#define DED_ERROR_EVENT_CNT 0x24 +#define SEC_ERROR_INT 0x28 +#define SEC_ERROR_INT_TX_RAM_SEC_ERR_INT GENMASK(3, 0) +#define SEC_ERROR_INT_RX_RAM_SEC_ERR_INT GENMASK(7, 4) +#define SEC_ERROR_INT_PCIE2AXI_RAM_SEC_ERR_INT GENMASK(11, 8) +#define SEC_ERROR_INT_AXI2PCIE_RAM_SEC_ERR_INT GENMASK(15, 12) +#define SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT GENMASK(15, 0) +#define NUM_SEC_ERROR_INTS (4) +#define SEC_ERROR_INT_MASK 0x2c +#define DED_ERROR_INT 0x30 +#define DED_ERROR_INT_TX_RAM_DED_ERR_INT GENMASK(3, 0) +#define DED_ERROR_INT_RX_RAM_DED_ERR_INT GENMASK(7, 4) +#define DED_ERROR_INT_PCIE2AXI_RAM_DED_ERR_INT GENMASK(11, 8) +#define DED_ERROR_INT_AXI2PCIE_RAM_DED_ERR_INT GENMASK(15, 12) +#define DED_ERROR_INT_ALL_RAM_DED_ERR_INT GENMASK(15, 0) +#define NUM_DED_ERROR_INTS (4) +#define DED_ERROR_INT_MASK 0x34 +#define ECC_CONTROL 0x38 +#define ECC_CONTROL_TX_RAM_INJ_ERROR_0 BIT(0) +#define ECC_CONTROL_TX_RAM_INJ_ERROR_1 BIT(1) +#define ECC_CONTROL_TX_RAM_INJ_ERROR_2 BIT(2) +#define ECC_CONTROL_TX_RAM_INJ_ERROR_3 BIT(3) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_0 BIT(4) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_1 BIT(5) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_2 BIT(6) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_3 BIT(7) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_0 BIT(8) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_1 BIT(9) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_2 BIT(10) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_3 BIT(11) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_0 BIT(12) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_1 BIT(13) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_2 BIT(14) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_3 BIT(15) +#define ECC_CONTROL_TX_RAM_ECC_BYPASS BIT(24) +#define ECC_CONTROL_RX_RAM_ECC_BYPASS BIT(25) +#define ECC_CONTROL_PCIE2AXI_RAM_ECC_BYPASS BIT(26) +#define ECC_CONTROL_AXI2PCIE_RAM_ECC_BYPASS BIT(27) +#define PCIE_EVENT_INT 0x14c +#define PCIE_EVENT_INT_L2_EXIT_INT BIT(0) +#define PCIE_EVENT_INT_HOTRST_EXIT_INT BIT(1) +#define PCIE_EVENT_INT_DLUP_EXIT_INT BIT(2) +#define PCIE_EVENT_INT_MASK GENMASK(2, 0) +#define PCIE_EVENT_INT_L2_EXIT_INT_MASK BIT(16) +#define PCIE_EVENT_INT_HOTRST_EXIT_INT_MASK BIT(17) +#define PCIE_EVENT_INT_DLUP_EXIT_INT_MASK BIT(18) +#define PCIE_EVENT_INT_ENB_MASK GENMASK(18, 16) +#define PCIE_EVENT_INT_ENB_SHIFT 16 +#define NUM_PCIE_EVENTS (3) + +/* PCIe Config space MSI capability structure */ +#define MC_MSI_CAP_CTRL_OFFSET 0xe0u + +/* Events */ +#define EVENT_PCIE_L2_EXIT 0 +#define EVENT_PCIE_HOTRST_EXIT 1 +#define EVENT_PCIE_DLUP_EXIT 2 +#define EVENT_SEC_TX_RAM_SEC_ERR 3 +#define EVENT_SEC_RX_RAM_SEC_ERR 4 +#define EVENT_SEC_PCIE2AXI_RAM_SEC_ERR 5 +#define EVENT_SEC_AXI2PCIE_RAM_SEC_ERR 6 +#define EVENT_DED_TX_RAM_DED_ERR 7 +#define EVENT_DED_RX_RAM_DED_ERR 8 +#define EVENT_DED_PCIE2AXI_RAM_DED_ERR 9 +#define EVENT_DED_AXI2PCIE_RAM_DED_ERR 10 +#define EVENT_LOCAL_DMA_END_ENGINE_0 11 +#define EVENT_LOCAL_DMA_END_ENGINE_1 12 +#define EVENT_LOCAL_DMA_ERROR_ENGINE_0 13 +#define EVENT_LOCAL_DMA_ERROR_ENGINE_1 14 +#define NUM_MC_EVENTS 15 +#define EVENT_LOCAL_A_ATR_EVT_POST_ERR (NUM_MC_EVENTS + PLDA_AXI_POST_ERR) +#define EVENT_LOCAL_A_ATR_EVT_FETCH_ERR (NUM_MC_EVENTS + PLDA_AXI_FETCH_ERR) +#define EVENT_LOCAL_A_ATR_EVT_DISCARD_ERR (NUM_MC_EVENTS + PLDA_AXI_DISCARD_ERR) +#define EVENT_LOCAL_A_ATR_EVT_DOORBELL (NUM_MC_EVENTS + PLDA_AXI_DOORBELL) +#define EVENT_LOCAL_P_ATR_EVT_POST_ERR (NUM_MC_EVENTS + PLDA_PCIE_POST_ERR) +#define EVENT_LOCAL_P_ATR_EVT_FETCH_ERR (NUM_MC_EVENTS + PLDA_PCIE_FETCH_ERR) +#define EVENT_LOCAL_P_ATR_EVT_DISCARD_ERR (NUM_MC_EVENTS + PLDA_PCIE_DISCARD_ERR) +#define EVENT_LOCAL_P_ATR_EVT_DOORBELL (NUM_MC_EVENTS + PLDA_PCIE_DOORBELL) +#define EVENT_LOCAL_PM_MSI_INT_INTX (NUM_MC_EVENTS + PLDA_INTX) +#define EVENT_LOCAL_PM_MSI_INT_MSI (NUM_MC_EVENTS + PLDA_MSI) +#define EVENT_LOCAL_PM_MSI_INT_AER_EVT (NUM_MC_EVENTS + PLDA_AER_EVENT) +#define EVENT_LOCAL_PM_MSI_INT_EVENTS (NUM_MC_EVENTS + PLDA_MISC_EVENTS) +#define EVENT_LOCAL_PM_MSI_INT_SYS_ERR (NUM_MC_EVENTS + PLDA_SYS_ERR) +#define NUM_EVENTS (NUM_MC_EVENTS + PLDA_INT_EVENT_NUM) + +#define PCIE_EVENT_CAUSE(x, s) \ + [EVENT_PCIE_ ## x] = { __stringify(x), s } + +#define SEC_ERROR_CAUSE(x, s) \ + [EVENT_SEC_ ## x] = { __stringify(x), s } + +#define DED_ERROR_CAUSE(x, s) \ + [EVENT_DED_ ## x] = { __stringify(x), s } + +#define LOCAL_EVENT_CAUSE(x, s) \ + [EVENT_LOCAL_ ## x] = { __stringify(x), s } + +#define PCIE_EVENT(x) \ + .offset = PCIE_EVENT_INT, \ + .mask_offset = PCIE_EVENT_INT, \ + .mask_high = 1, \ + .mask = PCIE_EVENT_INT_ ## x ## _INT, \ + .enb_mask = PCIE_EVENT_INT_ENB_MASK + +#define SEC_EVENT(x) \ + .offset = SEC_ERROR_INT, \ + .mask_offset = SEC_ERROR_INT_MASK, \ + .mask = SEC_ERROR_INT_ ## x ## _INT, \ + .mask_high = 1, \ + .enb_mask = 0 + +#define DED_EVENT(x) \ + .offset = DED_ERROR_INT, \ + .mask_offset = DED_ERROR_INT_MASK, \ + .mask_high = 1, \ + .mask = DED_ERROR_INT_ ## x ## _INT, \ + .enb_mask = 0 + +#define LOCAL_EVENT(x) \ + .offset = ISTATUS_LOCAL, \ + .mask_offset = IMASK_LOCAL, \ + .mask_high = 0, \ + .mask = x ## _MASK, \ + .enb_mask = 0 + +#define PCIE_EVENT_TO_EVENT_MAP(x) \ + { PCIE_EVENT_INT_ ## x ## _INT, EVENT_PCIE_ ## x } + +#define SEC_ERROR_TO_EVENT_MAP(x) \ + { SEC_ERROR_INT_ ## x ## _INT, EVENT_SEC_ ## x } + +#define DED_ERROR_TO_EVENT_MAP(x) \ + { DED_ERROR_INT_ ## x ## _INT, EVENT_DED_ ## x } + +#define LOCAL_STATUS_TO_EVENT_MAP(x) \ + { x ## _MASK, EVENT_LOCAL_ ## x } + +struct event_map { + u32 reg_mask; + u32 event_bit; +}; + + +struct mc_pcie { + struct plda_pcie_rp plda; + void __iomem *bridge_base_addr; + void __iomem *ctrl_base_addr; +}; + +struct cause { + const char *sym; + const char *str; +}; + +static const struct cause event_cause[NUM_EVENTS] = { + PCIE_EVENT_CAUSE(L2_EXIT, "L2 exit event"), + PCIE_EVENT_CAUSE(HOTRST_EXIT, "Hot reset exit event"), + PCIE_EVENT_CAUSE(DLUP_EXIT, "DLUP exit event"), + SEC_ERROR_CAUSE(TX_RAM_SEC_ERR, "sec error in tx buffer"), + SEC_ERROR_CAUSE(RX_RAM_SEC_ERR, "sec error in rx buffer"), + SEC_ERROR_CAUSE(PCIE2AXI_RAM_SEC_ERR, "sec error in pcie2axi buffer"), + SEC_ERROR_CAUSE(AXI2PCIE_RAM_SEC_ERR, "sec error in axi2pcie buffer"), + DED_ERROR_CAUSE(TX_RAM_DED_ERR, "ded error in tx buffer"), + DED_ERROR_CAUSE(RX_RAM_DED_ERR, "ded error in rx buffer"), + DED_ERROR_CAUSE(PCIE2AXI_RAM_DED_ERR, "ded error in pcie2axi buffer"), + DED_ERROR_CAUSE(AXI2PCIE_RAM_DED_ERR, "ded error in axi2pcie buffer"), + LOCAL_EVENT_CAUSE(DMA_ERROR_ENGINE_0, "dma engine 0 error"), + LOCAL_EVENT_CAUSE(DMA_ERROR_ENGINE_1, "dma engine 1 error"), + LOCAL_EVENT_CAUSE(A_ATR_EVT_POST_ERR, "axi write request error"), + LOCAL_EVENT_CAUSE(A_ATR_EVT_FETCH_ERR, "axi read request error"), + LOCAL_EVENT_CAUSE(A_ATR_EVT_DISCARD_ERR, "axi read timeout"), + LOCAL_EVENT_CAUSE(P_ATR_EVT_POST_ERR, "pcie write request error"), + LOCAL_EVENT_CAUSE(P_ATR_EVT_FETCH_ERR, "pcie read request error"), + LOCAL_EVENT_CAUSE(P_ATR_EVT_DISCARD_ERR, "pcie read timeout"), + LOCAL_EVENT_CAUSE(PM_MSI_INT_AER_EVT, "aer event"), + LOCAL_EVENT_CAUSE(PM_MSI_INT_EVENTS, "pm/ltr/hotplug event"), + LOCAL_EVENT_CAUSE(PM_MSI_INT_SYS_ERR, "system error"), +}; + +static struct event_map pcie_event_to_event[] = { + PCIE_EVENT_TO_EVENT_MAP(L2_EXIT), + PCIE_EVENT_TO_EVENT_MAP(HOTRST_EXIT), + PCIE_EVENT_TO_EVENT_MAP(DLUP_EXIT), +}; + +static struct event_map sec_error_to_event[] = { + SEC_ERROR_TO_EVENT_MAP(TX_RAM_SEC_ERR), + SEC_ERROR_TO_EVENT_MAP(RX_RAM_SEC_ERR), + SEC_ERROR_TO_EVENT_MAP(PCIE2AXI_RAM_SEC_ERR), + SEC_ERROR_TO_EVENT_MAP(AXI2PCIE_RAM_SEC_ERR), +}; + +static struct event_map ded_error_to_event[] = { + DED_ERROR_TO_EVENT_MAP(TX_RAM_DED_ERR), + DED_ERROR_TO_EVENT_MAP(RX_RAM_DED_ERR), + DED_ERROR_TO_EVENT_MAP(PCIE2AXI_RAM_DED_ERR), + DED_ERROR_TO_EVENT_MAP(AXI2PCIE_RAM_DED_ERR), +}; + +static struct event_map local_status_to_event[] = { + LOCAL_STATUS_TO_EVENT_MAP(DMA_END_ENGINE_0), + LOCAL_STATUS_TO_EVENT_MAP(DMA_END_ENGINE_1), + LOCAL_STATUS_TO_EVENT_MAP(DMA_ERROR_ENGINE_0), + LOCAL_STATUS_TO_EVENT_MAP(DMA_ERROR_ENGINE_1), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_POST_ERR), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_FETCH_ERR), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_DISCARD_ERR), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_DOORBELL), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_POST_ERR), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_FETCH_ERR), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_DISCARD_ERR), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_DOORBELL), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_INTX), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_MSI), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_AER_EVT), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_EVENTS), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_SYS_ERR), +}; + +static struct { + u32 offset; + u32 mask; + u32 shift; + u32 enb_mask; + u32 mask_high; + u32 mask_offset; +} event_descs[] = { + { PCIE_EVENT(L2_EXIT) }, + { PCIE_EVENT(HOTRST_EXIT) }, + { PCIE_EVENT(DLUP_EXIT) }, + { SEC_EVENT(TX_RAM_SEC_ERR) }, + { SEC_EVENT(RX_RAM_SEC_ERR) }, + { SEC_EVENT(PCIE2AXI_RAM_SEC_ERR) }, + { SEC_EVENT(AXI2PCIE_RAM_SEC_ERR) }, + { DED_EVENT(TX_RAM_DED_ERR) }, + { DED_EVENT(RX_RAM_DED_ERR) }, + { DED_EVENT(PCIE2AXI_RAM_DED_ERR) }, + { DED_EVENT(AXI2PCIE_RAM_DED_ERR) }, + { LOCAL_EVENT(DMA_END_ENGINE_0) }, + { LOCAL_EVENT(DMA_END_ENGINE_1) }, + { LOCAL_EVENT(DMA_ERROR_ENGINE_0) }, + { LOCAL_EVENT(DMA_ERROR_ENGINE_1) }, + { LOCAL_EVENT(A_ATR_EVT_POST_ERR) }, + { LOCAL_EVENT(A_ATR_EVT_FETCH_ERR) }, + { LOCAL_EVENT(A_ATR_EVT_DISCARD_ERR) }, + { LOCAL_EVENT(A_ATR_EVT_DOORBELL) }, + { LOCAL_EVENT(P_ATR_EVT_POST_ERR) }, + { LOCAL_EVENT(P_ATR_EVT_FETCH_ERR) }, + { LOCAL_EVENT(P_ATR_EVT_DISCARD_ERR) }, + { LOCAL_EVENT(P_ATR_EVT_DOORBELL) }, + { LOCAL_EVENT(PM_MSI_INT_INTX) }, + { LOCAL_EVENT(PM_MSI_INT_MSI) }, + { LOCAL_EVENT(PM_MSI_INT_AER_EVT) }, + { LOCAL_EVENT(PM_MSI_INT_EVENTS) }, + { LOCAL_EVENT(PM_MSI_INT_SYS_ERR) }, +}; + +static char poss_clks[][5] = { "fic0", "fic1", "fic2", "fic3" }; + +static struct mc_pcie *port; + +static void mc_pcie_enable_msi(struct mc_pcie *port, void __iomem *ecam) +{ + struct plda_msi *msi = &port->plda.msi; + u16 reg; + u8 queue_size; + + /* Fixup MSI enable flag */ + reg = readw_relaxed(ecam + MC_MSI_CAP_CTRL_OFFSET + PCI_MSI_FLAGS); + reg |= PCI_MSI_FLAGS_ENABLE; + writew_relaxed(reg, ecam + MC_MSI_CAP_CTRL_OFFSET + PCI_MSI_FLAGS); + + /* Fixup PCI MSI queue flags */ + queue_size = FIELD_GET(PCI_MSI_FLAGS_QMASK, reg); + reg |= FIELD_PREP(PCI_MSI_FLAGS_QSIZE, queue_size); + writew_relaxed(reg, ecam + MC_MSI_CAP_CTRL_OFFSET + PCI_MSI_FLAGS); + + /* Fixup MSI addr fields */ + writel_relaxed(lower_32_bits(msi->vector_phy), + ecam + MC_MSI_CAP_CTRL_OFFSET + PCI_MSI_ADDRESS_LO); + writel_relaxed(upper_32_bits(msi->vector_phy), + ecam + MC_MSI_CAP_CTRL_OFFSET + PCI_MSI_ADDRESS_HI); +} + +static inline u32 reg_to_event(u32 reg, struct event_map field) +{ + return (reg & field.reg_mask) ? BIT(field.event_bit) : 0; +} + +static u32 pcie_events(struct mc_pcie *port) +{ + u32 reg = readl_relaxed(port->ctrl_base_addr + PCIE_EVENT_INT); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(pcie_event_to_event); i++) + val |= reg_to_event(reg, pcie_event_to_event[i]); + + return val; +} + +static u32 sec_errors(struct mc_pcie *port) +{ + u32 reg = readl_relaxed(port->ctrl_base_addr + SEC_ERROR_INT); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(sec_error_to_event); i++) + val |= reg_to_event(reg, sec_error_to_event[i]); + + return val; +} + +static u32 ded_errors(struct mc_pcie *port) +{ + u32 reg = readl_relaxed(port->ctrl_base_addr + DED_ERROR_INT); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(ded_error_to_event); i++) + val |= reg_to_event(reg, ded_error_to_event[i]); + + return val; +} + +static u32 local_events(struct mc_pcie *port) +{ + u32 reg = readl_relaxed(port->bridge_base_addr + ISTATUS_LOCAL); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(local_status_to_event); i++) + val |= reg_to_event(reg, local_status_to_event[i]); + + return val; +} + +static u32 mc_get_events(struct plda_pcie_rp *port) +{ + struct mc_pcie *mc_port = container_of(port, struct mc_pcie, plda); + u32 events = 0; + + events |= pcie_events(mc_port); + events |= sec_errors(mc_port); + events |= ded_errors(mc_port); + events |= local_events(mc_port); + + return events; +} + +static irqreturn_t mc_event_handler(int irq, void *dev_id) +{ + struct plda_pcie_rp *port = dev_id; + struct device *dev = port->dev; + struct irq_data *data; + + data = irq_domain_get_irq_data(port->event_domain, irq); + + if (event_cause[data->hwirq].str) + dev_err_ratelimited(dev, "%s\n", event_cause[data->hwirq].str); + else + dev_err_ratelimited(dev, "bad event IRQ %ld\n", data->hwirq); + + return IRQ_HANDLED; +} + +static void mc_ack_event_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + struct mc_pcie *mc_port = container_of(port, struct mc_pcie, plda); + u32 event = data->hwirq; + void __iomem *addr; + u32 mask; + + if (event_descs[event].offset == ISTATUS_LOCAL) + addr = mc_port->bridge_base_addr; + else + addr = mc_port->ctrl_base_addr; + + addr += event_descs[event].offset; + mask = event_descs[event].mask; + mask |= event_descs[event].enb_mask; + + writel_relaxed(mask, addr); +} + +static void mc_mask_event_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + struct mc_pcie *mc_port = container_of(port, struct mc_pcie, plda); + u32 event = data->hwirq; + void __iomem *addr; + u32 mask; + u32 val; + + if (event_descs[event].offset == ISTATUS_LOCAL) + addr = mc_port->bridge_base_addr; + else + addr = mc_port->ctrl_base_addr; + + addr += event_descs[event].mask_offset; + mask = event_descs[event].mask; + if (event_descs[event].enb_mask) { + mask <<= PCIE_EVENT_INT_ENB_SHIFT; + mask &= PCIE_EVENT_INT_ENB_MASK; + } + + if (!event_descs[event].mask_high) + mask = ~mask; + + raw_spin_lock(&port->lock); + val = readl_relaxed(addr); + if (event_descs[event].mask_high) + val |= mask; + else + val &= mask; + + writel_relaxed(val, addr); + raw_spin_unlock(&port->lock); +} + +static void mc_unmask_event_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + struct mc_pcie *mc_port = container_of(port, struct mc_pcie, plda); + u32 event = data->hwirq; + void __iomem *addr; + u32 mask; + u32 val; + + if (event_descs[event].offset == ISTATUS_LOCAL) + addr = mc_port->bridge_base_addr; + else + addr = mc_port->ctrl_base_addr; + + addr += event_descs[event].mask_offset; + mask = event_descs[event].mask; + + if (event_descs[event].enb_mask) + mask <<= PCIE_EVENT_INT_ENB_SHIFT; + + if (event_descs[event].mask_high) + mask = ~mask; + + if (event_descs[event].enb_mask) + mask &= PCIE_EVENT_INT_ENB_MASK; + + raw_spin_lock(&port->lock); + val = readl_relaxed(addr); + if (event_descs[event].mask_high) + val &= mask; + else + val |= mask; + writel_relaxed(val, addr); + raw_spin_unlock(&port->lock); +} + +static struct irq_chip mc_event_irq_chip = { + .name = "Microchip PCIe EVENT", + .irq_ack = mc_ack_event_irq, + .irq_mask = mc_mask_event_irq, + .irq_unmask = mc_unmask_event_irq, +}; + +static inline void mc_pcie_deinit_clk(void *data) +{ + struct clk *clk = data; + + clk_disable_unprepare(clk); +} + +static inline struct clk *mc_pcie_init_clk(struct device *dev, const char *id) +{ + struct clk *clk; + int ret; + + clk = devm_clk_get_optional(dev, id); + if (IS_ERR(clk)) + return clk; + if (!clk) + return clk; + + ret = clk_prepare_enable(clk); + if (ret) + return ERR_PTR(ret); + + devm_add_action_or_reset(dev, mc_pcie_deinit_clk, clk); + + return clk; +} + +static int mc_pcie_init_clks(struct device *dev) +{ + int i; + struct clk *fic; + + /* + * PCIe may be clocked via Fabric Interface using between 1 and 4 + * clocks. Scan DT for clocks and enable them if present + */ + for (i = 0; i < ARRAY_SIZE(poss_clks); i++) { + fic = mc_pcie_init_clk(dev, poss_clks[i]); + if (IS_ERR(fic)) + return PTR_ERR(fic); + } + + return 0; +} + +static int mc_request_event_irq(struct plda_pcie_rp *plda, int event_irq, + int event) +{ + return devm_request_irq(plda->dev, event_irq, mc_event_handler, + 0, event_cause[event].sym, plda); +} + +static const struct plda_event_ops mc_event_ops = { + .get_events = mc_get_events, +}; + +static const struct plda_event mc_event = { + .request_event_irq = mc_request_event_irq, + .intx_event = EVENT_LOCAL_PM_MSI_INT_INTX, + .msi_event = EVENT_LOCAL_PM_MSI_INT_MSI, +}; + +static inline void mc_clear_secs(struct mc_pcie *port) +{ + writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, + port->ctrl_base_addr + SEC_ERROR_INT); + writel_relaxed(0, port->ctrl_base_addr + SEC_ERROR_EVENT_CNT); +} + +static inline void mc_clear_deds(struct mc_pcie *port) +{ + writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, + port->ctrl_base_addr + DED_ERROR_INT); + writel_relaxed(0, port->ctrl_base_addr + DED_ERROR_EVENT_CNT); +} + +static void mc_disable_interrupts(struct mc_pcie *port) +{ + u32 val; + + /* Ensure ECC bypass is enabled */ + val = ECC_CONTROL_TX_RAM_ECC_BYPASS | + ECC_CONTROL_RX_RAM_ECC_BYPASS | + ECC_CONTROL_PCIE2AXI_RAM_ECC_BYPASS | + ECC_CONTROL_AXI2PCIE_RAM_ECC_BYPASS; + writel_relaxed(val, port->ctrl_base_addr + ECC_CONTROL); + + /* Disable SEC errors and clear any outstanding */ + writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, + port->ctrl_base_addr + SEC_ERROR_INT_MASK); + mc_clear_secs(port); + + /* Disable DED errors and clear any outstanding */ + writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, + port->ctrl_base_addr + DED_ERROR_INT_MASK); + mc_clear_deds(port); + + /* Disable local interrupts and clear any outstanding */ + writel_relaxed(0, port->bridge_base_addr + IMASK_LOCAL); + writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_LOCAL); + writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_MSI); + + /* Disable PCIe events and clear any outstanding */ + val = PCIE_EVENT_INT_L2_EXIT_INT | + PCIE_EVENT_INT_HOTRST_EXIT_INT | + PCIE_EVENT_INT_DLUP_EXIT_INT | + PCIE_EVENT_INT_L2_EXIT_INT_MASK | + PCIE_EVENT_INT_HOTRST_EXIT_INT_MASK | + PCIE_EVENT_INT_DLUP_EXIT_INT_MASK; + writel_relaxed(val, port->ctrl_base_addr + PCIE_EVENT_INT); + + /* Disable host interrupts and clear any outstanding */ + writel_relaxed(0, port->bridge_base_addr + IMASK_HOST); + writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_HOST); +} + +static void mc_pcie_setup_inbound_atr(struct mc_pcie *port, int window_index, + u64 axi_addr, u64 pcie_addr, u64 size) +{ + u32 table_offset = window_index * ATR_ENTRY_SIZE; + void __iomem *table_addr = port->bridge_base_addr + table_offset; + u32 atr_sz; + u32 val; + + atr_sz = ilog2(size) - 1; + + val = ALIGN_DOWN(lower_32_bits(pcie_addr), SZ_4K); + val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz); + val |= ATR_IMPL_ENABLE; + + writel(val, table_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); + + writel(upper_32_bits(pcie_addr), table_addr + ATR0_PCIE_WIN0_SRC_ADDR); + + writel(lower_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_LSB); + writel(upper_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_UDW); + + writel(TRSL_ID_AXI4_MASTER_0, table_addr + ATR0_PCIE_WIN0_TRSL_PARAM); +} + +static int mc_pcie_setup_inbound_ranges(struct platform_device *pdev, + struct mc_pcie *port) +{ + struct device *dev = &pdev->dev; + struct device_node *dn = dev->of_node; + struct of_range_parser parser; + struct of_range range; + int atr_index = 0; + + /* + * MPFS PCIe Root Port is 32-bit only, behind a Fabric Interface + * Controller FPGA logic block which contains the AXI-S interface. + * + * From the point of view of the PCIe Root Port, there are only two + * supported Root Port configurations: + * + * Configuration 1: for use with fully coherent designs; supports a + * window from 0x0 (CPU space) to specified PCIe space. + * + * Configuration 2: for use with non-coherent designs; supports two + * 1 GB windows to CPU space; one mapping CPU space 0 to PCIe space + * 0x80000000 and a second mapping CPU space 0x40000000 to PCIe + * space 0xc0000000. This cfg needs two windows because of how the + * MSI space is allocated in the AXI-S range on MPFS. + * + * The FIC interface outside the PCIe block *must* complete the + * inbound address translation as per MCHP MPFS FPGA design + * guidelines. + */ + if (device_property_read_bool(dev, "dma-noncoherent")) { + /* + * Always need same two tables in this case. Need two tables + * due to hardware interactions between address and size. + */ + mc_pcie_setup_inbound_atr(port, 0, 0, + MPFS_NC_BOUNCE_ADDR, SZ_1G); + mc_pcie_setup_inbound_atr(port, 1, SZ_1G, + MPFS_NC_BOUNCE_ADDR + SZ_1G, SZ_1G); + } else { + /* Find any DMA ranges */ + if (of_pci_dma_range_parser_init(&parser, dn)) { + /* No DMA range property - setup default */ + mc_pcie_setup_inbound_atr(port, 0, 0, 0, SZ_4G); + return 0; + } + + for_each_of_range(&parser, &range) { + if (atr_index >= MC_MAX_NUM_INBOUND_WINDOWS) { + dev_err(dev, "too many inbound ranges; %d available tables\n", + MC_MAX_NUM_INBOUND_WINDOWS); + return -EINVAL; + } + mc_pcie_setup_inbound_atr(port, atr_index, 0, + range.pci_addr, range.size); + atr_index++; + } + } + + return 0; +} + +static int mc_platform_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct platform_device *pdev = to_platform_device(dev); + struct pci_host_bridge *bridge = platform_get_drvdata(pdev); + int ret; + + /* Configure address translation table 0 for PCIe config space */ + plda_pcie_setup_window(port->bridge_base_addr, 0, cfg->res.start, + cfg->res.start, + resource_size(&cfg->res)); + + /* Need some fixups in config space */ + mc_pcie_enable_msi(port, cfg->win); + + /* Configure non-config space outbound ranges */ + ret = plda_pcie_setup_iomems(bridge, &port->plda); + if (ret) + return ret; + + ret = mc_pcie_setup_inbound_ranges(pdev, port); + if (ret) + return ret; + + port->plda.event_ops = &mc_event_ops; + port->plda.event_irq_chip = &mc_event_irq_chip; + port->plda.events_bitmap = GENMASK(NUM_EVENTS - 1, 0); + + /* Address translation is up; safe to enable interrupts */ + ret = plda_init_interrupts(pdev, &port->plda, &mc_event); + if (ret) + return ret; + + return 0; +} + +static int mc_host_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + void __iomem *apb_base_addr; + struct plda_pcie_rp *plda; + int ret; + u32 val; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + plda = &port->plda; + plda->dev = dev; + + port->bridge_base_addr = devm_platform_ioremap_resource_byname(pdev, + "bridge"); + port->ctrl_base_addr = devm_platform_ioremap_resource_byname(pdev, + "ctrl"); + if (!IS_ERR(port->bridge_base_addr) && !IS_ERR(port->ctrl_base_addr)) + goto addrs_set; + + /* + * The original, incorrect, binding that lumped the control and + * bridge addresses together still needs to be handled by the driver. + */ + apb_base_addr = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(apb_base_addr)) + return dev_err_probe(dev, PTR_ERR(apb_base_addr), + "both legacy apb register and ctrl/bridge regions missing"); + + port->bridge_base_addr = apb_base_addr + MC_PCIE1_BRIDGE_ADDR; + port->ctrl_base_addr = apb_base_addr + MC_PCIE1_CTRL_ADDR; + +addrs_set: + mc_disable_interrupts(port); + + plda->bridge_addr = port->bridge_base_addr; + plda->num_events = NUM_EVENTS; + + /* Allow enabling MSI by disabling MSI-X */ + val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0); + val &= ~MSIX_CAP_MASK; + writel(val, port->bridge_base_addr + PCIE_PCI_IRQ_DW0); + + /* Pick num vectors from bitfile programmed onto FPGA fabric */ + val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0); + val &= NUM_MSI_MSGS_MASK; + val >>= NUM_MSI_MSGS_SHIFT; + + plda->msi.num_vectors = 1 << val; + + /* Pick vector address from design */ + plda->msi.vector_phy = readl_relaxed(port->bridge_base_addr + IMSI_ADDR); + + ret = mc_pcie_init_clks(dev); + if (ret) { + dev_err(dev, "failed to get clock resources, error %d\n", ret); + return -ENODEV; + } + + return pci_host_common_probe(pdev); +} + +static const struct pci_ecam_ops mc_ecam_ops = { + .init = mc_platform_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static const struct of_device_id mc_pcie_of_match[] = { + { + .compatible = "microchip,pcie-host-1.0", + .data = &mc_ecam_ops, + }, + {}, +}; + +MODULE_DEVICE_TABLE(of, mc_pcie_of_match); + +static struct platform_driver mc_pcie_driver = { + .probe = mc_host_probe, + .driver = { + .name = "microchip-pcie", + .of_match_table = mc_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; + +builtin_platform_driver(mc_pcie_driver); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Microchip PCIe host controller driver"); +MODULE_AUTHOR("Daire McNamara <daire.mcnamara@microchip.com>"); diff --git a/drivers/pci/controller/plda/pcie-plda-host.c b/drivers/pci/controller/plda/pcie-plda-host.c new file mode 100644 index 000000000000..3c2f68383010 --- /dev/null +++ b/drivers/pci/controller/plda/pcie-plda-host.c @@ -0,0 +1,651 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PLDA PCIe XpressRich host controller driver + * + * Copyright (C) 2023 Microchip Co. Ltd + * StarFive Co. Ltd + * + * Author: Daire McNamara <daire.mcnamara@microchip.com> + */ + +#include <linux/align.h> +#include <linux/bitfield.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> +#include <linux/irqdomain.h> +#include <linux/msi.h> +#include <linux/pci_regs.h> +#include <linux/pci-ecam.h> +#include <linux/wordpart.h> + +#include "pcie-plda.h" + +void __iomem *plda_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct plda_pcie_rp *pcie = bus->sysdata; + + return pcie->config_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); +} +EXPORT_SYMBOL_GPL(plda_pcie_map_bus); + +static void plda_handle_msi(struct irq_desc *desc) +{ + struct plda_pcie_rp *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct device *dev = port->dev; + struct plda_msi *msi = &port->msi; + void __iomem *bridge_base_addr = port->bridge_addr; + unsigned long status; + u32 bit; + int ret; + + chained_irq_enter(chip, desc); + + status = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL); + if (status & PM_MSI_INT_MSI_MASK) { + writel_relaxed(status & PM_MSI_INT_MSI_MASK, + bridge_base_addr + ISTATUS_LOCAL); + status = readl_relaxed(bridge_base_addr + ISTATUS_MSI); + for_each_set_bit(bit, &status, msi->num_vectors) { + ret = generic_handle_domain_irq(msi->dev_domain, bit); + if (ret) + dev_err_ratelimited(dev, "bad MSI IRQ %d\n", + bit); + } + } + + chained_irq_exit(chip, desc); +} + +static void plda_msi_bottom_irq_ack(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = port->bridge_addr; + u32 bitpos = data->hwirq; + + writel_relaxed(BIT(bitpos), bridge_base_addr + ISTATUS_MSI); +} + +static void plda_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + phys_addr_t addr = port->msi.vector_phy; + + msg->address_lo = lower_32_bits(addr); + msg->address_hi = upper_32_bits(addr); + msg->data = data->hwirq; + + dev_dbg(port->dev, "msi#%x address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); +} + +static struct irq_chip plda_msi_bottom_irq_chip = { + .name = "PLDA MSI", + .irq_ack = plda_msi_bottom_irq_ack, + .irq_compose_msi_msg = plda_compose_msi_msg, +}; + +static int plda_irq_msi_domain_alloc(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs, + void *args) +{ + struct plda_pcie_rp *port = domain->host_data; + struct plda_msi *msi = &port->msi; + unsigned long bit; + + mutex_lock(&msi->lock); + bit = find_first_zero_bit(msi->used, msi->num_vectors); + if (bit >= msi->num_vectors) { + mutex_unlock(&msi->lock); + return -ENOSPC; + } + + set_bit(bit, msi->used); + + irq_domain_set_info(domain, virq, bit, &plda_msi_bottom_irq_chip, + domain->host_data, handle_edge_irq, NULL, NULL); + + mutex_unlock(&msi->lock); + + return 0; +} + +static void plda_irq_msi_domain_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(d); + struct plda_msi *msi = &port->msi; + + mutex_lock(&msi->lock); + + if (test_bit(d->hwirq, msi->used)) + __clear_bit(d->hwirq, msi->used); + else + dev_err(port->dev, "trying to free unused MSI%lu\n", d->hwirq); + + mutex_unlock(&msi->lock); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = plda_irq_msi_domain_alloc, + .free = plda_irq_msi_domain_free, +}; + +#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 plda_msi *msi = &port->msi; + + mutex_init(&port->msi.lock); + + 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; + } + + return 0; +} + +static void plda_handle_intx(struct irq_desc *desc) +{ + struct plda_pcie_rp *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct device *dev = port->dev; + void __iomem *bridge_base_addr = port->bridge_addr; + unsigned long status; + u32 bit; + int ret; + + chained_irq_enter(chip, desc); + + status = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL); + if (status & PM_MSI_INT_INTX_MASK) { + status &= PM_MSI_INT_INTX_MASK; + status >>= PM_MSI_INT_INTX_SHIFT; + for_each_set_bit(bit, &status, PCI_NUM_INTX) { + ret = generic_handle_domain_irq(port->intx_domain, bit); + if (ret) + dev_err_ratelimited(dev, "bad INTx IRQ %d\n", + bit); + } + } + + chained_irq_exit(chip, desc); +} + +static void plda_ack_intx_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = port->bridge_addr; + u32 mask = BIT(data->hwirq + PM_MSI_INT_INTX_SHIFT); + + writel_relaxed(mask, bridge_base_addr + ISTATUS_LOCAL); +} + +static void plda_mask_intx_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = port->bridge_addr; + unsigned long flags; + u32 mask = BIT(data->hwirq + PM_MSI_INT_INTX_SHIFT); + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = readl_relaxed(bridge_base_addr + IMASK_LOCAL); + val &= ~mask; + writel_relaxed(val, bridge_base_addr + IMASK_LOCAL); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void plda_unmask_intx_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = port->bridge_addr; + unsigned long flags; + u32 mask = BIT(data->hwirq + PM_MSI_INT_INTX_SHIFT); + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = readl_relaxed(bridge_base_addr + IMASK_LOCAL); + val |= mask; + writel_relaxed(val, bridge_base_addr + IMASK_LOCAL); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip plda_intx_irq_chip = { + .name = "PLDA PCIe INTx", + .irq_ack = plda_ack_intx_irq, + .irq_mask = plda_mask_intx_irq, + .irq_unmask = plda_unmask_intx_irq, +}; + +static int plda_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &plda_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 = plda_pcie_intx_map, +}; + +static u32 plda_get_events(struct plda_pcie_rp *port) +{ + u32 events, val, origin; + + origin = readl_relaxed(port->bridge_addr + ISTATUS_LOCAL); + + /* MSI event and sys events */ + val = (origin & SYS_AND_MSI_MASK) >> PM_MSI_INT_MSI_SHIFT; + events = val << (PM_MSI_INT_MSI_SHIFT - PCI_NUM_INTX + 1); + + /* INTx events */ + if (origin & PM_MSI_INT_INTX_MASK) + events |= BIT(PM_MSI_INT_INTX_SHIFT); + + /* remains are same with register */ + events |= origin & GENMASK(P_ATR_EVT_DOORBELL_SHIFT, 0); + + return events; +} + +static irqreturn_t plda_event_handler(int irq, void *dev_id) +{ + return IRQ_HANDLED; +} + +static void plda_handle_event(struct irq_desc *desc) +{ + struct plda_pcie_rp *port = irq_desc_get_handler_data(desc); + unsigned long events; + u32 bit; + struct irq_chip *chip = irq_desc_get_chip(desc); + + chained_irq_enter(chip, desc); + + events = port->event_ops->get_events(port); + + events &= port->events_bitmap; + for_each_set_bit(bit, &events, port->num_events) + generic_handle_domain_irq(port->event_domain, bit); + + chained_irq_exit(chip, desc); +} + +static u32 plda_hwirq_to_mask(int hwirq) +{ + u32 mask; + + /* hwirq 23 - 0 are the same with register */ + if (hwirq < EVENT_PM_MSI_INT_INTX) + mask = BIT(hwirq); + else if (hwirq == EVENT_PM_MSI_INT_INTX) + mask = PM_MSI_INT_INTX_MASK; + else + mask = BIT(hwirq + PCI_NUM_INTX - 1); + + return mask; +} + +static void plda_ack_event_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + + writel_relaxed(plda_hwirq_to_mask(data->hwirq), + port->bridge_addr + ISTATUS_LOCAL); +} + +static void plda_mask_event_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + u32 mask, val; + + mask = plda_hwirq_to_mask(data->hwirq); + + raw_spin_lock(&port->lock); + val = readl_relaxed(port->bridge_addr + IMASK_LOCAL); + val &= ~mask; + writel_relaxed(val, port->bridge_addr + IMASK_LOCAL); + raw_spin_unlock(&port->lock); +} + +static void plda_unmask_event_irq(struct irq_data *data) +{ + struct plda_pcie_rp *port = irq_data_get_irq_chip_data(data); + u32 mask, val; + + mask = plda_hwirq_to_mask(data->hwirq); + + raw_spin_lock(&port->lock); + val = readl_relaxed(port->bridge_addr + IMASK_LOCAL); + val |= mask; + writel_relaxed(val, port->bridge_addr + IMASK_LOCAL); + raw_spin_unlock(&port->lock); +} + +static struct irq_chip plda_event_irq_chip = { + .name = "PLDA PCIe EVENT", + .irq_ack = plda_ack_event_irq, + .irq_mask = plda_mask_event_irq, + .irq_unmask = plda_unmask_event_irq, +}; + +static const struct plda_event_ops plda_event_ops = { + .get_events = plda_get_events, +}; + +static int plda_pcie_event_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + struct plda_pcie_rp *port = (void *)domain->host_data; + + irq_set_chip_and_handler(irq, port->event_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops plda_event_domain_ops = { + .map = plda_pcie_event_map, +}; + +static int plda_pcie_init_irq_domains(struct plda_pcie_rp *port) +{ + struct device *dev = port->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + + /* Setup INTx */ + pcie_intc_node = of_get_next_child(node, NULL); + if (!pcie_intc_node) { + dev_err(dev, "failed to find PCIe Intc node\n"); + return -EINVAL; + } + + port->event_domain = irq_domain_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); + return -ENOMEM; + } + + irq_domain_update_bus_token(port->event_domain, DOMAIN_BUS_NEXUS); + + 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); + return -ENOMEM; + } + + irq_domain_update_bus_token(port->intx_domain, DOMAIN_BUS_WIRED); + + of_node_put(pcie_intc_node); + raw_spin_lock_init(&port->lock); + + return plda_allocate_msi_domains(port); +} + +int plda_init_interrupts(struct platform_device *pdev, + struct plda_pcie_rp *port, + const struct plda_event *event) +{ + struct device *dev = &pdev->dev; + int event_irq, ret; + u32 i; + + if (!port->event_ops) + port->event_ops = &plda_event_ops; + + if (!port->event_irq_chip) + port->event_irq_chip = &plda_event_irq_chip; + + ret = plda_pcie_init_irq_domains(port); + if (ret) { + dev_err(dev, "failed creating IRQ domains\n"); + return ret; + } + + port->irq = platform_get_irq(pdev, 0); + if (port->irq < 0) + return -ENODEV; + + for_each_set_bit(i, &port->events_bitmap, port->num_events) { + event_irq = irq_create_mapping(port->event_domain, i); + if (!event_irq) { + dev_err(dev, "failed to map hwirq %d\n", i); + return -ENXIO; + } + + if (event->request_event_irq) + ret = event->request_event_irq(port, event_irq, i); + else + ret = devm_request_irq(dev, event_irq, + plda_event_handler, + 0, NULL, port); + + if (ret) { + dev_err(dev, "failed to request IRQ %d\n", event_irq); + return ret; + } + } + + port->intx_irq = irq_create_mapping(port->event_domain, + event->intx_event); + if (!port->intx_irq) { + dev_err(dev, "failed to map INTx interrupt\n"); + return -ENXIO; + } + + /* Plug the INTx chained handler */ + irq_set_chained_handler_and_data(port->intx_irq, plda_handle_intx, port); + + port->msi_irq = irq_create_mapping(port->event_domain, + event->msi_event); + if (!port->msi_irq) + return -ENXIO; + + /* Plug the MSI chained handler */ + irq_set_chained_handler_and_data(port->msi_irq, plda_handle_msi, port); + + /* Plug the main event chained handler */ + irq_set_chained_handler_and_data(port->irq, plda_handle_event, port); + + return 0; +} +EXPORT_SYMBOL_GPL(plda_init_interrupts); + +void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, + phys_addr_t axi_addr, phys_addr_t pci_addr, + size_t size) +{ + u32 atr_sz = ilog2(size) - 1; + u32 val; + + if (index == 0) + val = PCIE_CONFIG_INTERFACE; + else + val = PCIE_TX_RX_INTERFACE; + + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_TRSL_PARAM); + + val = ALIGN_DOWN(lower_32_bits(axi_addr), SZ_4K); + val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz); + val |= ATR_IMPL_ENABLE; + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_SRCADDR_PARAM); + + val = upper_32_bits(axi_addr); + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_SRC_ADDR); + + val = lower_32_bits(pci_addr); + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_TRSL_ADDR_LSB); + + val = upper_32_bits(pci_addr); + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_TRSL_ADDR_UDW); +} +EXPORT_SYMBOL_GPL(plda_pcie_setup_window); + +void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port) +{ + void __iomem *bridge_base_addr = port->bridge_addr; + u32 val; + + val = readl(bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); + val |= (ATR0_PCIE_ATR_SIZE << ATR0_PCIE_ATR_SIZE_SHIFT); + writel(val, bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); + writel(0, bridge_base_addr + ATR0_PCIE_WIN0_SRC_ADDR); +} +EXPORT_SYMBOL_GPL(plda_pcie_setup_inbound_address_translation); + +int plda_pcie_setup_iomems(struct pci_host_bridge *bridge, + struct plda_pcie_rp *port) +{ + void __iomem *bridge_base_addr = port->bridge_addr; + struct resource_entry *entry; + u64 pci_addr; + u32 index = 1; + + resource_list_for_each_entry(entry, &bridge->windows) { + if (resource_type(entry->res) == IORESOURCE_MEM) { + pci_addr = entry->res->start - entry->offset; + plda_pcie_setup_window(bridge_base_addr, index, + entry->res->start, pci_addr, + resource_size(entry->res)); + index++; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(plda_pcie_setup_iomems); + +static void plda_pcie_irq_domain_deinit(struct plda_pcie_rp *pcie) +{ + irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); + 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.dev_domain); + + irq_domain_remove(pcie->intx_domain); + irq_domain_remove(pcie->event_domain); +} + +int plda_pcie_host_init(struct plda_pcie_rp *port, struct pci_ops *ops, + const struct plda_event *plda_event) +{ + struct device *dev = port->dev; + struct pci_host_bridge *bridge; + struct platform_device *pdev = to_platform_device(dev); + struct resource *cfg_res; + int ret; + + pdev = to_platform_device(dev); + + port->bridge_addr = + devm_platform_ioremap_resource_byname(pdev, "apb"); + + if (IS_ERR(port->bridge_addr)) + return dev_err_probe(dev, PTR_ERR(port->bridge_addr), + "failed to map reg memory\n"); + + cfg_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + if (!cfg_res) + return dev_err_probe(dev, -ENODEV, + "failed to get config memory\n"); + + port->config_base = devm_ioremap_resource(dev, cfg_res); + if (IS_ERR(port->config_base)) + return dev_err_probe(dev, PTR_ERR(port->config_base), + "failed to map config memory\n"); + + bridge = devm_pci_alloc_host_bridge(dev, 0); + if (!bridge) + return -ENOMEM; + + if (port->host_ops && port->host_ops->host_init) { + ret = port->host_ops->host_init(port); + if (ret) + return ret; + } + + port->bridge = bridge; + plda_pcie_setup_window(port->bridge_addr, 0, cfg_res->start, 0, + resource_size(cfg_res)); + plda_pcie_setup_iomems(bridge, port); + plda_set_default_msi(&port->msi); + ret = plda_init_interrupts(pdev, port, plda_event); + if (ret) + goto err_host; + + /* Set default bus ops */ + bridge->ops = ops; + bridge->sysdata = port; + + ret = pci_host_probe(bridge); + if (ret < 0) { + dev_err_probe(dev, ret, "failed to probe pci host\n"); + goto err_probe; + } + + return ret; + +err_probe: + plda_pcie_irq_domain_deinit(port); +err_host: + if (port->host_ops && port->host_ops->host_deinit) + port->host_ops->host_deinit(port); + + return ret; +} +EXPORT_SYMBOL_GPL(plda_pcie_host_init); + +void plda_pcie_host_deinit(struct plda_pcie_rp *port) +{ + pci_stop_root_bus(port->bridge->bus); + pci_remove_root_bus(port->bridge->bus); + + plda_pcie_irq_domain_deinit(port); + + if (port->host_ops && port->host_ops->host_deinit) + port->host_ops->host_deinit(port); +} +EXPORT_SYMBOL_GPL(plda_pcie_host_deinit); diff --git a/drivers/pci/controller/plda/pcie-plda.h b/drivers/pci/controller/plda/pcie-plda.h new file mode 100644 index 000000000000..6b8665df7bf0 --- /dev/null +++ b/drivers/pci/controller/plda/pcie-plda.h @@ -0,0 +1,274 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PLDA PCIe host controller driver + */ + +#ifndef _PCIE_PLDA_H +#define _PCIE_PLDA_H + +/* Number of MSI IRQs */ +#define PLDA_MAX_NUM_MSI_IRQS 32 + +/* PCIe Bridge Phy Regs */ +#define GEN_SETTINGS 0x80 +#define RP_ENABLE 1 +#define PCIE_PCI_IDS_DW1 0x9c +#define IDS_CLASS_CODE_SHIFT 16 +#define REVISION_ID_MASK GENMASK(7, 0) +#define CLASS_CODE_ID_MASK GENMASK(31, 8) +#define PCIE_PCI_IRQ_DW0 0xa8 +#define MSIX_CAP_MASK BIT(31) +#define NUM_MSI_MSGS_MASK GENMASK(6, 4) +#define NUM_MSI_MSGS_SHIFT 4 +#define PCI_MISC 0xb4 +#define PHY_FUNCTION_DIS BIT(15) +#define PCIE_WINROM 0xfc +#define PREF_MEM_WIN_64_SUPPORT BIT(3) + +#define IMASK_LOCAL 0x180 +#define DMA_END_ENGINE_0_MASK 0x00000000u +#define DMA_END_ENGINE_0_SHIFT 0 +#define DMA_END_ENGINE_1_MASK 0x00000000u +#define DMA_END_ENGINE_1_SHIFT 1 +#define DMA_ERROR_ENGINE_0_MASK 0x00000100u +#define DMA_ERROR_ENGINE_0_SHIFT 8 +#define DMA_ERROR_ENGINE_1_MASK 0x00000200u +#define DMA_ERROR_ENGINE_1_SHIFT 9 +#define A_ATR_EVT_POST_ERR_MASK 0x00010000u +#define A_ATR_EVT_POST_ERR_SHIFT 16 +#define A_ATR_EVT_FETCH_ERR_MASK 0x00020000u +#define A_ATR_EVT_FETCH_ERR_SHIFT 17 +#define A_ATR_EVT_DISCARD_ERR_MASK 0x00040000u +#define A_ATR_EVT_DISCARD_ERR_SHIFT 18 +#define A_ATR_EVT_DOORBELL_MASK 0x00000000u +#define A_ATR_EVT_DOORBELL_SHIFT 19 +#define P_ATR_EVT_POST_ERR_MASK 0x00100000u +#define P_ATR_EVT_POST_ERR_SHIFT 20 +#define P_ATR_EVT_FETCH_ERR_MASK 0x00200000u +#define P_ATR_EVT_FETCH_ERR_SHIFT 21 +#define P_ATR_EVT_DISCARD_ERR_MASK 0x00400000u +#define P_ATR_EVT_DISCARD_ERR_SHIFT 22 +#define P_ATR_EVT_DOORBELL_MASK 0x00000000u +#define P_ATR_EVT_DOORBELL_SHIFT 23 +#define PM_MSI_INT_INTA_MASK 0x01000000u +#define PM_MSI_INT_INTA_SHIFT 24 +#define PM_MSI_INT_INTB_MASK 0x02000000u +#define PM_MSI_INT_INTB_SHIFT 25 +#define PM_MSI_INT_INTC_MASK 0x04000000u +#define PM_MSI_INT_INTC_SHIFT 26 +#define PM_MSI_INT_INTD_MASK 0x08000000u +#define PM_MSI_INT_INTD_SHIFT 27 +#define PM_MSI_INT_INTX_MASK 0x0f000000u +#define PM_MSI_INT_INTX_SHIFT 24 +#define PM_MSI_INT_MSI_MASK 0x10000000u +#define PM_MSI_INT_MSI_SHIFT 28 +#define PM_MSI_INT_AER_EVT_MASK 0x20000000u +#define PM_MSI_INT_AER_EVT_SHIFT 29 +#define PM_MSI_INT_EVENTS_MASK 0x40000000u +#define PM_MSI_INT_EVENTS_SHIFT 30 +#define PM_MSI_INT_SYS_ERR_MASK 0x80000000u +#define PM_MSI_INT_SYS_ERR_SHIFT 31 +#define SYS_AND_MSI_MASK GENMASK(31, 28) +#define NUM_LOCAL_EVENTS 15 +#define ISTATUS_LOCAL 0x184 +#define IMASK_HOST 0x188 +#define ISTATUS_HOST 0x18c +#define IMSI_ADDR 0x190 +#define ISTATUS_MSI 0x194 +#define PMSG_SUPPORT_RX 0x3f0 +#define PMSG_LTR_SUPPORT BIT(2) + +/* PCIe Master table init defines */ +#define ATR0_PCIE_WIN0_SRCADDR_PARAM 0x600u +#define ATR0_PCIE_ATR_SIZE 0x25 +#define ATR0_PCIE_ATR_SIZE_SHIFT 1 +#define ATR0_PCIE_WIN0_SRC_ADDR 0x604u +#define ATR0_PCIE_WIN0_TRSL_ADDR_LSB 0x608u +#define ATR0_PCIE_WIN0_TRSL_ADDR_UDW 0x60cu +#define ATR0_PCIE_WIN0_TRSL_PARAM 0x610u + +/* PCIe AXI slave table init defines */ +#define ATR0_AXI4_SLV0_SRCADDR_PARAM 0x800u +#define ATR_SIZE_MASK GENMASK(6, 1) +#define ATR_IMPL_ENABLE BIT(0) +#define ATR0_AXI4_SLV0_SRC_ADDR 0x804u +#define ATR0_AXI4_SLV0_TRSL_ADDR_LSB 0x808u +#define ATR0_AXI4_SLV0_TRSL_ADDR_UDW 0x80cu +#define ATR0_AXI4_SLV0_TRSL_PARAM 0x810u +#define PCIE_TX_RX_INTERFACE 0x00000000u +#define PCIE_CONFIG_INTERFACE 0x00000001u +#define TRSL_ID_AXI4_MASTER_0 0x00000004u + +#define CONFIG_SPACE_ADDR_OFFSET 0x1000u + +#define ATR_ENTRY_SIZE 32 + +enum plda_int_event { + PLDA_AXI_POST_ERR, + PLDA_AXI_FETCH_ERR, + PLDA_AXI_DISCARD_ERR, + PLDA_AXI_DOORBELL, + PLDA_PCIE_POST_ERR, + PLDA_PCIE_FETCH_ERR, + PLDA_PCIE_DISCARD_ERR, + PLDA_PCIE_DOORBELL, + PLDA_INTX, + PLDA_MSI, + PLDA_AER_EVENT, + PLDA_MISC_EVENTS, + PLDA_SYS_ERR, + PLDA_INT_EVENT_NUM +}; + +#define PLDA_NUM_DMA_EVENTS 16 + +#define EVENT_PM_MSI_INT_INTX (PLDA_NUM_DMA_EVENTS + PLDA_INTX) +#define EVENT_PM_MSI_INT_MSI (PLDA_NUM_DMA_EVENTS + PLDA_MSI) +#define PLDA_MAX_EVENT_NUM (PLDA_NUM_DMA_EVENTS + PLDA_INT_EVENT_NUM) + +/* + * PLDA interrupt register + * + * 31 27 23 15 7 0 + * +--+--+--+-+------+-+-+-+-+-+-+-+-+-----------+-----------+ + * |12|11|10|9| intx |7|6|5|4|3|2|1|0| DMA error | DMA end | + * +--+--+--+-+------+-+-+-+-+-+-+-+-+-----------+-----------+ + * event bit + * 0-7 (0-7) DMA interrupt end : reserved for vendor implement + * 8-15 (8-15) DMA error : reserved for vendor implement + * 16 (16) AXI post error (PLDA_AXI_POST_ERR) + * 17 (17) AXI fetch error (PLDA_AXI_FETCH_ERR) + * 18 (18) AXI discard error (PLDA_AXI_DISCARD_ERR) + * 19 (19) AXI doorbell (PLDA_PCIE_DOORBELL) + * 20 (20) PCIe post error (PLDA_PCIE_POST_ERR) + * 21 (21) PCIe fetch error (PLDA_PCIE_FETCH_ERR) + * 22 (22) PCIe discard error (PLDA_PCIE_DISCARD_ERR) + * 23 (23) PCIe doorbell (PLDA_PCIE_DOORBELL) + * 24 (27-24) INTx interruts (PLDA_INTX) + * 25 (28): MSI interrupt (PLDA_MSI) + * 26 (29): AER event (PLDA_AER_EVENT) + * 27 (30): PM/LTR/Hotplug (PLDA_MISC_EVENTS) + * 28 (31): System error (PLDA_SYS_ERR) + */ + +struct plda_pcie_rp; + +struct plda_event_ops { + u32 (*get_events)(struct plda_pcie_rp *pcie); +}; + +struct plda_pcie_host_ops { + int (*host_init)(struct plda_pcie_rp *pcie); + void (*host_deinit)(struct plda_pcie_rp *pcie); +}; + +struct plda_msi { + struct mutex lock; /* Protect used bitmap */ + struct irq_domain *dev_domain; + u32 num_vectors; + u64 vector_phy; + DECLARE_BITMAP(used, PLDA_MAX_NUM_MSI_IRQS); +}; + +struct plda_pcie_rp { + struct device *dev; + struct pci_host_bridge *bridge; + struct irq_domain *intx_domain; + struct irq_domain *event_domain; + raw_spinlock_t lock; + struct plda_msi msi; + const struct plda_event_ops *event_ops; + const struct irq_chip *event_irq_chip; + const struct plda_pcie_host_ops *host_ops; + void __iomem *bridge_addr; + void __iomem *config_base; + unsigned long events_bitmap; + int irq; + int msi_irq; + int intx_irq; + int num_events; +}; + +struct plda_event { + int (*request_event_irq)(struct plda_pcie_rp *pcie, + int event_irq, int event); + int intx_event; + int msi_event; +}; + +void __iomem *plda_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where); +int plda_init_interrupts(struct platform_device *pdev, + struct plda_pcie_rp *port, + const struct plda_event *event); +void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, + phys_addr_t axi_addr, phys_addr_t pci_addr, + size_t size); +void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port); +int plda_pcie_setup_iomems(struct pci_host_bridge *bridge, + struct plda_pcie_rp *port); +int plda_pcie_host_init(struct plda_pcie_rp *port, struct pci_ops *ops, + const struct plda_event *plda_event); +void plda_pcie_host_deinit(struct plda_pcie_rp *pcie); + +static inline void plda_set_default_msi(struct plda_msi *msi) +{ + msi->vector_phy = IMSI_ADDR; + msi->num_vectors = PLDA_MAX_NUM_MSI_IRQS; +} + +static inline void plda_pcie_enable_root_port(struct plda_pcie_rp *plda) +{ + u32 value; + + value = readl_relaxed(plda->bridge_addr + GEN_SETTINGS); + value |= RP_ENABLE; + writel_relaxed(value, plda->bridge_addr + GEN_SETTINGS); +} + +static inline void plda_pcie_set_standard_class(struct plda_pcie_rp *plda) +{ + u32 value; + + /* set class code and reserve revision id */ + value = readl_relaxed(plda->bridge_addr + PCIE_PCI_IDS_DW1); + value &= REVISION_ID_MASK; + value |= (PCI_CLASS_BRIDGE_PCI << IDS_CLASS_CODE_SHIFT); + writel_relaxed(value, plda->bridge_addr + PCIE_PCI_IDS_DW1); +} + +static inline void plda_pcie_set_pref_win_64bit(struct plda_pcie_rp *plda) +{ + u32 value; + + value = readl_relaxed(plda->bridge_addr + PCIE_WINROM); + value |= PREF_MEM_WIN_64_SUPPORT; + writel_relaxed(value, plda->bridge_addr + PCIE_WINROM); +} + +static inline void plda_pcie_disable_ltr(struct plda_pcie_rp *plda) +{ + u32 value; + + value = readl_relaxed(plda->bridge_addr + PMSG_SUPPORT_RX); + value &= ~PMSG_LTR_SUPPORT; + writel_relaxed(value, plda->bridge_addr + PMSG_SUPPORT_RX); +} + +static inline void plda_pcie_disable_func(struct plda_pcie_rp *plda) +{ + u32 value; + + value = readl_relaxed(plda->bridge_addr + PCI_MISC); + value |= PHY_FUNCTION_DIS; + writel_relaxed(value, plda->bridge_addr + PCI_MISC); +} + +static inline void plda_pcie_write_rc_bar(struct plda_pcie_rp *plda, u64 val) +{ + void __iomem *addr = plda->bridge_addr + CONFIG_SPACE_ADDR_OFFSET; + + writel_relaxed(lower_32_bits(val), addr + PCI_BASE_ADDRESS_0); + writel_relaxed(upper_32_bits(val), addr + PCI_BASE_ADDRESS_1); +} +#endif /* _PCIE_PLDA_H */ diff --git a/drivers/pci/controller/plda/pcie-starfive.c b/drivers/pci/controller/plda/pcie-starfive.c new file mode 100644 index 000000000000..3caf53c6c082 --- /dev/null +++ b/drivers/pci/controller/plda/pcie-starfive.c @@ -0,0 +1,492 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for StarFive JH7110 Soc. + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include "../../pci.h" + +#include "pcie-plda.h" + +#define PCIE_FUNC_NUM 4 + +/* system control */ +#define STG_SYSCON_PCIE0_BASE 0x48 +#define STG_SYSCON_PCIE1_BASE 0x1f8 + +#define STG_SYSCON_AR_OFFSET 0x78 +#define STG_SYSCON_AXI4_SLVL_AR_MASK GENMASK(22, 8) +#define STG_SYSCON_AXI4_SLVL_PHY_AR(x) FIELD_PREP(GENMASK(20, 17), x) +#define STG_SYSCON_AW_OFFSET 0x7c +#define STG_SYSCON_AXI4_SLVL_AW_MASK GENMASK(14, 0) +#define STG_SYSCON_AXI4_SLVL_PHY_AW(x) FIELD_PREP(GENMASK(12, 9), x) +#define STG_SYSCON_CLKREQ BIT(22) +#define STG_SYSCON_CKREF_SRC_MASK GENMASK(19, 18) +#define STG_SYSCON_RP_NEP_OFFSET 0xe8 +#define STG_SYSCON_K_RP_NEP BIT(8) +#define STG_SYSCON_LNKSTA_OFFSET 0x170 +#define DATA_LINK_ACTIVE BIT(5) + +/* Parameters for the waiting for link up routine */ +#define LINK_WAIT_MAX_RETRIES 10 +#define LINK_WAIT_USLEEP_MIN 90000 +#define LINK_WAIT_USLEEP_MAX 100000 + +struct starfive_jh7110_pcie { + struct plda_pcie_rp plda; + struct reset_control *resets; + struct clk_bulk_data *clks; + struct regmap *reg_syscon; + struct gpio_desc *power_gpio; + struct gpio_desc *reset_gpio; + struct phy *phy; + + unsigned int stg_pcie_base; + int num_clks; +}; + +/* + * JH7110 PCIe port BAR0/1 can be configured as 64-bit prefetchable memory + * space. PCIe read and write requests targeting BAR0/1 are routed to so called + * 'Bridge Configuration space' in PLDA IP datasheet, which contains the bridge + * internal registers, such as interrupt, DMA and ATU registers... + * JH7110 can access the Bridge Configuration space by local bus, and don`t + * want the bridge internal registers accessed by the DMA from EP devices. + * Thus, they are unimplemented and should be hidden here. + */ +static bool starfive_pcie_hide_rc_bar(struct pci_bus *bus, unsigned int devfn, + int offset) +{ + if (pci_is_root_bus(bus) && !devfn && + (offset == PCI_BASE_ADDRESS_0 || offset == PCI_BASE_ADDRESS_1)) + return true; + + return false; +} + +static int starfive_pcie_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 value) +{ + if (starfive_pcie_hide_rc_bar(bus, devfn, where)) + return PCIBIOS_SUCCESSFUL; + + return pci_generic_config_write(bus, devfn, where, size, value); +} + +static int starfive_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *value) +{ + if (starfive_pcie_hide_rc_bar(bus, devfn, where)) { + *value = 0; + return PCIBIOS_SUCCESSFUL; + } + + return pci_generic_config_read(bus, devfn, where, size, value); +} + +static int starfive_pcie_parse_dt(struct starfive_jh7110_pcie *pcie, + struct device *dev) +{ + int domain_nr; + + pcie->num_clks = devm_clk_bulk_get_all(dev, &pcie->clks); + if (pcie->num_clks < 0) + return dev_err_probe(dev, pcie->num_clks, + "failed to get pcie clocks\n"); + + pcie->resets = devm_reset_control_array_get_exclusive(dev); + if (IS_ERR(pcie->resets)) + return dev_err_probe(dev, PTR_ERR(pcie->resets), + "failed to get pcie resets"); + + pcie->reg_syscon = + syscon_regmap_lookup_by_phandle(dev->of_node, + "starfive,stg-syscon"); + + if (IS_ERR(pcie->reg_syscon)) + return dev_err_probe(dev, PTR_ERR(pcie->reg_syscon), + "failed to parse starfive,stg-syscon\n"); + + pcie->phy = devm_phy_optional_get(dev, NULL); + if (IS_ERR(pcie->phy)) + return dev_err_probe(dev, PTR_ERR(pcie->phy), + "failed to get pcie phy\n"); + + /* + * The PCIe domain numbers are set to be static in JH7110 DTS. + * As the STG system controller defines different bases in PCIe RP0 & + * RP1, we use them to identify which controller is doing the hardware + * initialization. + */ + domain_nr = of_get_pci_domain_nr(dev->of_node); + + if (domain_nr < 0 || domain_nr > 1) + return dev_err_probe(dev, -ENODEV, + "failed to get valid pcie domain\n"); + + if (domain_nr == 0) + pcie->stg_pcie_base = STG_SYSCON_PCIE0_BASE; + else + pcie->stg_pcie_base = STG_SYSCON_PCIE1_BASE; + + pcie->reset_gpio = devm_gpiod_get_optional(dev, "perst", + GPIOD_OUT_HIGH); + if (IS_ERR(pcie->reset_gpio)) + 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"); + + return 0; +} + +static struct pci_ops starfive_pcie_ops = { + .map_bus = plda_pcie_map_bus, + .read = starfive_pcie_config_read, + .write = starfive_pcie_config_write, +}; + +static int starfive_pcie_clk_rst_init(struct starfive_jh7110_pcie *pcie) +{ + struct device *dev = pcie->plda.dev; + int ret; + + ret = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks); + if (ret) + return dev_err_probe(dev, ret, "failed to enable clocks\n"); + + ret = reset_control_deassert(pcie->resets); + if (ret) { + clk_bulk_disable_unprepare(pcie->num_clks, pcie->clks); + dev_err_probe(dev, ret, "failed to deassert resets\n"); + } + + return ret; +} + +static void starfive_pcie_clk_rst_deinit(struct starfive_jh7110_pcie *pcie) +{ + reset_control_assert(pcie->resets); + clk_bulk_disable_unprepare(pcie->num_clks, pcie->clks); +} + +static bool starfive_pcie_link_up(struct plda_pcie_rp *plda) +{ + struct starfive_jh7110_pcie *pcie = + container_of(plda, struct starfive_jh7110_pcie, plda); + int ret; + u32 stg_reg_val; + + ret = regmap_read(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_LNKSTA_OFFSET, + &stg_reg_val); + if (ret) { + dev_err(pcie->plda.dev, "failed to read link status\n"); + return false; + } + + return !!(stg_reg_val & DATA_LINK_ACTIVE); +} + +static int starfive_pcie_host_wait_for_link(struct starfive_jh7110_pcie *pcie) +{ + int retries; + + /* Check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (starfive_pcie_link_up(&pcie->plda)) { + dev_info(pcie->plda.dev, "port link up\n"); + return 0; + } + usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + } + + return -ETIMEDOUT; +} + +static int starfive_pcie_enable_phy(struct device *dev, + struct starfive_jh7110_pcie *pcie) +{ + int ret; + + if (!pcie->phy) + return 0; + + ret = phy_init(pcie->phy); + if (ret) + return dev_err_probe(dev, ret, + "failed to initialize pcie phy\n"); + + ret = phy_set_mode(pcie->phy, PHY_MODE_PCIE); + if (ret) { + dev_err_probe(dev, ret, "failed to set pcie mode\n"); + goto err_phy_on; + } + + ret = phy_power_on(pcie->phy); + if (ret) { + dev_err_probe(dev, ret, "failed to power on pcie phy\n"); + goto err_phy_on; + } + + return 0; + +err_phy_on: + phy_exit(pcie->phy); + return ret; +} + +static void starfive_pcie_disable_phy(struct starfive_jh7110_pcie *pcie) +{ + phy_power_off(pcie->phy); + phy_exit(pcie->phy); +} + +static void starfive_pcie_host_deinit(struct plda_pcie_rp *plda) +{ + struct starfive_jh7110_pcie *pcie = + 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); + starfive_pcie_disable_phy(pcie); +} + +static int starfive_pcie_host_init(struct plda_pcie_rp *plda) +{ + struct starfive_jh7110_pcie *pcie = + container_of(plda, struct starfive_jh7110_pcie, plda); + struct device *dev = plda->dev; + int ret; + int i; + + ret = starfive_pcie_enable_phy(dev, pcie); + if (ret) + return ret; + + regmap_update_bits(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_RP_NEP_OFFSET, + STG_SYSCON_K_RP_NEP, STG_SYSCON_K_RP_NEP); + + regmap_update_bits(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_AW_OFFSET, + STG_SYSCON_CKREF_SRC_MASK, + FIELD_PREP(STG_SYSCON_CKREF_SRC_MASK, 2)); + + regmap_update_bits(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_AW_OFFSET, + STG_SYSCON_CLKREQ, STG_SYSCON_CLKREQ); + + ret = starfive_pcie_clk_rst_init(pcie); + if (ret) + return ret; + + if (pcie->power_gpio) + gpiod_set_value_cansleep(pcie->power_gpio, 1); + + if (pcie->reset_gpio) + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + + /* Disable physical functions except #0 */ + for (i = 1; i < PCIE_FUNC_NUM; i++) { + regmap_update_bits(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_AR_OFFSET, + STG_SYSCON_AXI4_SLVL_AR_MASK, + STG_SYSCON_AXI4_SLVL_PHY_AR(i)); + + regmap_update_bits(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_AW_OFFSET, + STG_SYSCON_AXI4_SLVL_AW_MASK, + STG_SYSCON_AXI4_SLVL_PHY_AW(i)); + + plda_pcie_disable_func(plda); + } + + regmap_update_bits(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_AR_OFFSET, + STG_SYSCON_AXI4_SLVL_AR_MASK, 0); + regmap_update_bits(pcie->reg_syscon, + pcie->stg_pcie_base + STG_SYSCON_AW_OFFSET, + STG_SYSCON_AXI4_SLVL_AW_MASK, 0); + + plda_pcie_enable_root_port(plda); + plda_pcie_write_rc_bar(plda, 0); + + /* PCIe PCI Standard Configuration Identification Settings. */ + plda_pcie_set_standard_class(plda); + + /* + * The LTR message receiving is enabled by the register "PCIe Message + * Reception" as default, but the forward id & addr are uninitialized. + * If we do not disable LTR message forwarding here, or set a legal + * forwarding address, the kernel will get stuck. + * To workaround, disable the LTR message forwarding here before using + * this feature. + */ + plda_pcie_disable_ltr(plda); + + /* + * Enable the prefetchable memory window 64-bit addressing in JH7110. + * The 64-bits prefetchable address translation configurations in ATU + * can be work after enable the register setting below. + */ + plda_pcie_set_pref_win_64bit(plda); + + /* + * Ensure that PERST has been asserted for at least 100 ms, + * the sleep value is T_PVPERL from PCIe CEM spec r2.0 (Table 2-4) + */ + msleep(100); + if (pcie->reset_gpio) + gpiod_set_value_cansleep(pcie->reset_gpio, 0); + + /* + * With a Downstream Port (<=5GT/s), software must wait a minimum + * of 100ms following exit from a conventional reset before + * sending a configuration request to the device. + */ + msleep(PCIE_RESET_CONFIG_WAIT_MS); + + if (starfive_pcie_host_wait_for_link(pcie)) + dev_info(dev, "port link down\n"); + + return 0; +} + +static const struct plda_pcie_host_ops sf_host_ops = { + .host_init = starfive_pcie_host_init, + .host_deinit = starfive_pcie_host_deinit, +}; + +static const struct plda_event stf_pcie_event = { + .intx_event = EVENT_PM_MSI_INT_INTX, + .msi_event = EVENT_PM_MSI_INT_MSI +}; + +static int starfive_pcie_probe(struct platform_device *pdev) +{ + struct starfive_jh7110_pcie *pcie; + struct device *dev = &pdev->dev; + struct plda_pcie_rp *plda; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + plda = &pcie->plda; + plda->dev = dev; + + ret = starfive_pcie_parse_dt(pcie, dev); + if (ret) + return ret; + + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + + plda->host_ops = &sf_host_ops; + plda->num_events = PLDA_MAX_EVENT_NUM; + /* mask doorbell event */ + plda->events_bitmap = GENMASK(PLDA_INT_EVENT_NUM - 1, 0) + & ~BIT(PLDA_AXI_DOORBELL) + & ~BIT(PLDA_PCIE_DOORBELL); + plda->events_bitmap <<= PLDA_NUM_DMA_EVENTS; + ret = plda_pcie_host_init(&pcie->plda, &starfive_pcie_ops, + &stf_pcie_event); + if (ret) { + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); + return ret; + } + + platform_set_drvdata(pdev, pcie); + + return 0; +} + +static void starfive_pcie_remove(struct platform_device *pdev) +{ + struct starfive_jh7110_pcie *pcie = platform_get_drvdata(pdev); + + pm_runtime_put(&pdev->dev); + pm_runtime_disable(&pdev->dev); + plda_pcie_host_deinit(&pcie->plda); + platform_set_drvdata(pdev, NULL); +} + +static int starfive_pcie_suspend_noirq(struct device *dev) +{ + struct starfive_jh7110_pcie *pcie = dev_get_drvdata(dev); + + clk_bulk_disable_unprepare(pcie->num_clks, pcie->clks); + starfive_pcie_disable_phy(pcie); + + return 0; +} + +static int starfive_pcie_resume_noirq(struct device *dev) +{ + struct starfive_jh7110_pcie *pcie = dev_get_drvdata(dev); + int ret; + + ret = starfive_pcie_enable_phy(dev, pcie); + if (ret) + return ret; + + ret = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks); + if (ret) { + dev_err(dev, "failed to enable clocks\n"); + starfive_pcie_disable_phy(pcie); + return ret; + } + + return 0; +} + +static const struct dev_pm_ops starfive_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(starfive_pcie_suspend_noirq, + starfive_pcie_resume_noirq) +}; + +static const struct of_device_id starfive_pcie_of_match[] = { + { .compatible = "starfive,jh7110-pcie", }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, starfive_pcie_of_match); + +static struct platform_driver starfive_pcie_driver = { + .driver = { + .name = "pcie-starfive", + .of_match_table = of_match_ptr(starfive_pcie_of_match), + .pm = pm_sleep_ptr(&starfive_pcie_pm_ops), + }, + .probe = starfive_pcie_probe, + .remove = starfive_pcie_remove, +}; +module_platform_driver(starfive_pcie_driver); + +MODULE_DESCRIPTION("StarFive JH7110 PCIe host driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 3890812cdf87..ec6afc38e898 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -7,18 +7,20 @@ #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> #include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> #include <linux/srcu.h> #include <linux/rculist.h> #include <linux/rcupdate.h> +#include <xen/xen.h> + #include <asm/irqdomain.h> -#include <asm/device.h> -#include <asm/msi.h> -#include <asm/msidef.h> #define VMD_CFGBAR 0 #define VMD_MEMBAR1 2 @@ -28,24 +30,64 @@ #define BUS_RESTRICT_CAP(vmcap) (vmcap & 0x1) #define PCI_REG_VMCONFIG 0x44 #define BUS_RESTRICT_CFG(vmcfg) ((vmcfg >> 8) & 0x3) +#define VMCONFIG_MSI_REMAP 0x2 #define PCI_REG_VMLOCK 0x70 #define MB2_SHADOW_EN(vmlock) (vmlock & 0x2) +#define MB2_SHADOW_OFFSET 0x2000 +#define MB2_SHADOW_SIZE 16 + enum vmd_features { /* * Device may contain registers which hint the physical location of the * membars, in order to allow proper address translation during * resource assignment to enable guest virtualization */ - VMD_FEAT_HAS_MEMBAR_SHADOW = (1 << 0), + VMD_FEAT_HAS_MEMBAR_SHADOW = (1 << 0), /* * Device may provide root port configuration information which limits * bus numbering */ - VMD_FEAT_HAS_BUS_RESTRICTIONS = (1 << 1), + VMD_FEAT_HAS_BUS_RESTRICTIONS = (1 << 1), + + /* + * Device contains physical location shadow registers in + * vendor-specific capability space + */ + VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP = (1 << 2), + + /* + * Device may use MSI-X vector 0 for software triggering and will not + * be used for MSI remapping + */ + VMD_FEAT_OFFSET_FIRST_VECTOR = (1 << 3), + + /* + * Device can bypass remapping MSI-X transactions into its MSI-X table, + * avoiding the requirement of a VMD MSI domain for child device + * interrupt handling. + */ + VMD_FEAT_CAN_BYPASS_MSI_REMAP = (1 << 4), + + /* + * Enable ASPM on the PCIE root ports and set the default LTR of the + * storage devices on platforms where these values are not configured by + * BIOS. This is needed for laptops, which require these settings for + * proper power management of the SoC. + */ + VMD_FEAT_BIOS_PM_QUIRK = (1 << 5), }; +#define VMD_BIOS_PM_QUIRK_LTR 0x1003 /* 3145728 ns */ + +#define VMD_FEATS_CLIENT (VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | \ + VMD_FEAT_HAS_BUS_RESTRICTIONS | \ + VMD_FEAT_OFFSET_FIRST_VECTOR | \ + VMD_FEAT_BIOS_PM_QUIRK) + +static DEFINE_IDA(vmd_instance_ida); + /* * Lock for manipulating VMD IRQ lists. */ @@ -74,18 +116,20 @@ struct vmd_irq { * @srcu: SRCU struct for local synchronization. * @count: number of child IRQs assigned to this vector; used to track * sharing. + * @virq: The underlying VMD Linux interrupt number */ struct vmd_irq_list { struct list_head irq_list; struct srcu_struct srcu; unsigned int count; + unsigned int virq; }; struct vmd_dev { struct pci_dev *dev; - spinlock_t cfg_lock; - char __iomem *cfgbar; + raw_spinlock_t cfg_lock; + void __iomem *cfgbar; int msix_count; struct vmd_irq_list *irqs; @@ -94,11 +138,10 @@ struct vmd_dev { struct resource resources[3]; struct irq_domain *irq_domain; struct pci_bus *bus; - -#ifdef CONFIG_X86_DEV_DMA_OPS - struct dma_map_ops dma_ops; - struct dma_domain dma_domain; -#endif + u8 busn_start; + u8 first_vec; + char *name; + int instance; }; static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) @@ -126,79 +169,73 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) struct vmd_irq_list *irq = vmdirq->irq; struct vmd_dev *vmd = irq_data_get_irq_handler_data(data); - msg->address_hi = MSI_ADDR_BASE_HI; - msg->address_lo = MSI_ADDR_BASE_LO | - MSI_ADDR_DEST_ID(index_from_irqs(vmd, irq)); - msg->data = 0; + memset(msg, 0, sizeof(*msg)); + msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH; + msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW; + msg->arch_addr_lo.destid_0_7 = index_from_irqs(vmd, irq); } -/* - * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops. - */ static void vmd_irq_enable(struct irq_data *data) { struct vmd_irq *vmdirq = data->chip_data; - unsigned long flags; - raw_spin_lock_irqsave(&list_lock, flags); - WARN_ON(vmdirq->enabled); - list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); - vmdirq->enabled = true; - raw_spin_unlock_irqrestore(&list_lock, flags); + 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; - data->chip->irq_mask(data); - - raw_spin_lock_irqsave(&list_lock, flags); - if (vmdirq->enabled) { - list_del_rcu(&vmdirq->node); - vmdirq->enabled = false; + scoped_guard(raw_spinlock_irqsave, &list_lock) { + if (vmdirq->enabled) { + list_del_rcu(&vmdirq->node); + vmdirq->enabled = false; + } } - raw_spin_unlock_irqrestore(&list_lock, flags); } -/* - * XXX: Stubbed until we develop acceptable way to not create conflicts with - * other devices sharing the same vector. - */ -static int vmd_irq_set_affinity(struct irq_data *data, - const struct cpumask *dest, bool force) +static void vmd_pci_msi_disable(struct irq_data *data) +{ + data->chip->irq_mask(data); + vmd_irq_disable(data->parent_data); +} + +static void vmd_pci_msi_shutdown(struct irq_data *data) { - return -EINVAL; + 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, - .irq_set_affinity = vmd_irq_set_affinity, }; -static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, - msi_alloc_info_t *arg) -{ - return 0; -} - /* * XXX: We can be even smarter selecting the best IRQ once we solve the * affinity problem. */ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc) { - int i, best = 1; - unsigned long flags; + int i, best; - if (vmd->msix_count == 1) - return &vmd->irqs[0]; + if (vmd->msix_count == 1 + vmd->first_vec) + return &vmd->irqs[vmd->first_vec]; /* * White list for fast-interrupt handlers. All others will share the @@ -208,252 +245,160 @@ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *d case PCI_CLASS_STORAGE_EXPRESS: break; default: - return &vmd->irqs[0]; + return &vmd->irqs[vmd->first_vec]; } - raw_spin_lock_irqsave(&list_lock, flags); - for (i = 1; 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) -{ - 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); - unsigned int index, vector; - - if (!vmdirq) - return -ENOMEM; - - INIT_LIST_HEAD(&vmdirq->node); - vmdirq->irq = vmd_next_irq(vmd, desc); - vmdirq->virq = virq; - index = index_from_irqs(vmd, vmdirq->irq); - vector = pci_irq_vector(vmd->dev, index); - - irq_domain_set_info(domain, virq, vector, info->chip, vmdirq, - handle_untracked_irq, vmd, NULL); - return 0; -} +static void vmd_msi_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); -static void vmd_msi_free(struct irq_domain *domain, - struct msi_domain_info *info, unsigned int virq) +static int vmd_msi_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) { - 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 msi_desc *desc = ((msi_alloc_info_t *)arg)->desc; + struct vmd_dev *vmd = domain->host_data; + struct vmd_irq *vmdirq; - kfree(vmdirq); -} + for (int i = 0; i < nr_irqs; ++i) { + vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); + if (!vmdirq) { + vmd_msi_free(domain, virq, i); + return -ENOMEM; + } -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); + INIT_LIST_HEAD(&vmdirq->node); + vmdirq->irq = vmd_next_irq(vmd, desc); + vmdirq->virq = virq + i; - if (nvec > vmd->msix_count) - return vmd->msix_count; + irq_domain_set_info(domain, virq + i, vmdirq->irq->virq, + &vmd_msi_controller, vmdirq, + handle_untracked_irq, vmd, NULL); + } - memset(arg, 0, sizeof(*arg)); return 0; } -static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +static void vmd_msi_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { - arg->desc = desc; -} + struct irq_data *irq_data; + struct vmd_irq *vmdirq; -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, -}; + for (int i = 0; i < nr_irqs; ++i) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + vmdirq = irq_data->chip_data; -static struct msi_domain_info vmd_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX, - .ops = &vmd_msi_domain_ops, - .chip = &vmd_msi_controller, -}; + synchronize_srcu(&vmdirq->irq->srcu); -#ifdef CONFIG_X86_DEV_DMA_OPS -/* - * VMD replaces the requester ID with its own. DMA mappings for devices in a - * VMD domain need to be mapped for the VMD, not the device requiring - * the mapping. - */ -static struct device *to_vmd_dev(struct device *dev) -{ - struct pci_dev *pdev = to_pci_dev(dev); - struct vmd_dev *vmd = vmd_from_bus(pdev->bus); + /* XXX: Potential optimization to rebalance */ + scoped_guard(raw_spinlock_irq, &list_lock) + vmdirq->irq->count--; - return &vmd->dev->dev; -} - -static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr, - gfp_t flag, unsigned long attrs) -{ - return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs); -} - -static void vmd_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t addr, unsigned long attrs) -{ - return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs); -} - -static int vmd_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t addr, size_t size, - unsigned long attrs) -{ - return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size, - attrs); + kfree(vmdirq); + } } -static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt, - void *cpu_addr, dma_addr_t addr, size_t size, - unsigned long attrs) -{ - return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size, - attrs); -} +static const struct irq_domain_ops vmd_msi_domain_ops = { + .alloc = vmd_msi_alloc, + .free = vmd_msi_free, +}; -static dma_addr_t vmd_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) +static bool vmd_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, + struct msi_domain_info *info) { - return dma_map_page_attrs(to_vmd_dev(dev), page, offset, size, dir, - attrs); + 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 void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - dma_unmap_page_attrs(to_vmd_dev(dev), addr, size, dir, attrs); -} +#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 int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) -{ - return dma_map_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs); -} +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_unmap_sg(struct device *dev, struct scatterlist *sg, int nents, - enum dma_data_direction dir, unsigned long attrs) +static int vmd_create_irq_domain(struct vmd_dev *vmd) { - dma_unmap_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs); -} + struct irq_domain_info info = { + .size = vmd->msix_count, + .ops = &vmd_msi_domain_ops, + .host_data = vmd, + }; -static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ - dma_sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir); -} + info.fwnode = irq_domain_alloc_named_id_fwnode("VMD-MSI", + vmd->sysdata.domain); + if (!info.fwnode) + return -ENODEV; -static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr, - size_t size, enum dma_data_direction dir) -{ - dma_sync_single_for_device(to_vmd_dev(dev), addr, size, dir); -} + vmd->irq_domain = msi_create_parent_irq_domain(&info, + &vmd_msi_parent_ops); + if (!vmd->irq_domain) { + irq_domain_free_fwnode(info.fwnode); + return -ENODEV; + } -static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) -{ - dma_sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir); + return 0; } -static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg, - int nents, enum dma_data_direction dir) +static void vmd_set_msi_remapping(struct vmd_dev *vmd, bool enable) { - dma_sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir); -} + u16 reg; -static int vmd_dma_supported(struct device *dev, u64 mask) -{ - return dma_supported(to_vmd_dev(dev), mask); + 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 u64 vmd_get_required_mask(struct device *dev) +static void vmd_remove_irq_domain(struct vmd_dev *vmd) { - return dma_get_required_mask(to_vmd_dev(dev)); -} + /* + * Some production BIOS won't enable remapping between soft reboots. + * Ensure remapping is restored before unloading the driver. + */ + if (!vmd->msix_count) + vmd_set_msi_remapping(vmd, true); -static void vmd_teardown_dma_ops(struct vmd_dev *vmd) -{ - struct dma_domain *domain = &vmd->dma_domain; + if (vmd->irq_domain) { + struct fwnode_handle *fn = vmd->irq_domain->fwnode; - if (get_dma_ops(&vmd->dev->dev)) - del_dma_domain(domain); + irq_domain_remove(vmd->irq_domain); + irq_domain_free_fwnode(fn); + } } -#define ASSIGN_VMD_DMA_OPS(source, dest, fn) \ - do { \ - if (source->fn) \ - dest->fn = vmd_##fn; \ - } while (0) - -static void vmd_setup_dma_ops(struct vmd_dev *vmd) -{ - const struct dma_map_ops *source = get_dma_ops(&vmd->dev->dev); - struct dma_map_ops *dest = &vmd->dma_ops; - struct dma_domain *domain = &vmd->dma_domain; - - domain->domain_nr = vmd->sysdata.domain; - domain->dma_ops = dest; - - if (!source) - return; - ASSIGN_VMD_DMA_OPS(source, dest, alloc); - ASSIGN_VMD_DMA_OPS(source, dest, free); - ASSIGN_VMD_DMA_OPS(source, dest, mmap); - ASSIGN_VMD_DMA_OPS(source, dest, get_sgtable); - ASSIGN_VMD_DMA_OPS(source, dest, map_page); - ASSIGN_VMD_DMA_OPS(source, dest, unmap_page); - ASSIGN_VMD_DMA_OPS(source, dest, map_sg); - ASSIGN_VMD_DMA_OPS(source, dest, unmap_sg); - ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_cpu); - ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device); - ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu); - ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device); - ASSIGN_VMD_DMA_OPS(source, dest, dma_supported); - ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask); - add_dma_domain(domain); -} -#undef ASSIGN_VMD_DMA_OPS -#else -static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {} -static void vmd_setup_dma_ops(struct vmd_dev *vmd) {} -#endif - -static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus, +static void __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus, unsigned int devfn, int reg, int len) { - char __iomem *addr = vmd->cfgbar + - (bus->number << 20) + (devfn << 12) + reg; + unsigned int busnr_ecam = bus->number - vmd->busn_start; + u32 offset = PCIE_ECAM_OFFSET(busnr_ecam, devfn, reg); - if ((addr - vmd->cfgbar) + len >= - resource_size(&vmd->dev->resource[VMD_CFGBAR])) + if (offset + len >= resource_size(&vmd->dev->resource[VMD_CFGBAR])) return NULL; - return addr; + return vmd->cfgbar + offset; } /* @@ -464,30 +409,25 @@ static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg, int len, u32 *value) { struct vmd_dev *vmd = vmd_from_bus(bus); - char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); - unsigned long flags; - int ret = 0; + void __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); if (!addr) return -EFAULT; - spin_lock_irqsave(&vmd->cfg_lock, flags); + guard(raw_spinlock_irqsave)(&vmd->cfg_lock); switch (len) { case 1: *value = readb(addr); - break; + return 0; case 2: *value = readw(addr); - break; + return 0; case 4: *value = readl(addr); - break; + return 0; default: - ret = -EINVAL; - break; + return -EINVAL; } - spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; } /* @@ -499,33 +439,28 @@ static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg, int len, u32 value) { struct vmd_dev *vmd = vmd_from_bus(bus); - char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); - unsigned long flags; - int ret = 0; + void __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); if (!addr) return -EFAULT; - spin_lock_irqsave(&vmd->cfg_lock, flags); + guard(raw_spinlock_irqsave)(&vmd->cfg_lock); switch (len) { case 1: writeb(value, addr); readb(addr); - break; + return 0; case 2: writew(value, addr); readw(addr); - break; + return 0; case 4: writel(value, addr); readl(addr); - break; + return 0; default: - ret = -EINVAL; - break; + return -EINVAL; } - spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; } static struct pci_ops vmd_ops = { @@ -533,6 +468,104 @@ static struct pci_ops vmd_ops = { .write = vmd_pci_write, }; +#ifdef CONFIG_ACPI +static struct acpi_device *vmd_acpi_find_companion(struct pci_dev *pci_dev) +{ + struct pci_host_bridge *bridge; + u32 busnr, addr; + + if (pci_dev->bus->ops != &vmd_ops) + return NULL; + + bridge = pci_find_host_bridge(pci_dev->bus); + busnr = pci_dev->bus->number - bridge->bus->number; + /* + * The address computation below is only applicable to relative bus + * numbers below 32. + */ + if (busnr > 31) + return NULL; + + addr = (busnr << 24) | ((u32)pci_dev->devfn << 16) | 0x8000FFFFU; + + dev_dbg(&pci_dev->dev, "Looking for ACPI companion (address 0x%x)\n", + addr); + + return acpi_find_child_device(ACPI_COMPANION(bridge->dev.parent), addr, + false); +} + +static bool hook_installed; + +static void vmd_acpi_begin(void) +{ + if (pci_acpi_set_companion_lookup_hook(vmd_acpi_find_companion)) + return; + + hook_installed = true; +} + +static void vmd_acpi_end(void) +{ + if (!hook_installed) + return; + + pci_acpi_clear_companion_lookup_hook(); + hook_installed = false; +} +#else +static inline void vmd_acpi_begin(void) { } +static inline void vmd_acpi_end(void) { } +#endif /* CONFIG_ACPI */ + +static void vmd_domain_reset(struct vmd_dev *vmd) +{ + u16 bus, max_buses = resource_size(&vmd->resources[0]); + u8 dev, functions, fn, hdr_type; + char __iomem *base; + + for (bus = 0; bus < max_buses; bus++) { + for (dev = 0; dev < 32; dev++) { + base = vmd->cfgbar + PCIE_ECAM_OFFSET(bus, + PCI_DEVFN(dev, 0), 0); + + hdr_type = readb(base + PCI_HEADER_TYPE); + + functions = (hdr_type & PCI_HEADER_TYPE_MFD) ? 8 : 1; + for (fn = 0; fn < functions; fn++) { + base = vmd->cfgbar + PCIE_ECAM_OFFSET(bus, + PCI_DEVFN(dev, fn), 0); + + hdr_type = readb(base + PCI_HEADER_TYPE) & + PCI_HEADER_TYPE_MASK; + + if (hdr_type != PCI_HEADER_TYPE_BRIDGE || + (readw(base + PCI_CLASS_DEVICE) != + PCI_CLASS_BRIDGE_PCI)) + continue; + + /* + * Temporarily disable the I/O range before updating + * PCI_IO_BASE. + */ + writel(0x0000ffff, base + PCI_IO_BASE_UPPER16); + /* Update lower 16 bits of I/O base/limit */ + writew(0x00f0, base + PCI_IO_BASE); + /* Update upper 16 bits of I/O base/limit */ + writel(0, base + PCI_IO_BASE_UPPER16); + + /* MMIO Base/Limit */ + writel(0x0000fff0, base + PCI_MEMORY_BASE); + + /* Prefetchable MMIO Base/Limit */ + writel(0, base + PCI_PREF_LIMIT_UPPER32); + writel(0x0000fff0, base + PCI_PREF_MEMORY_BASE); + writel(0xffffffff, base + PCI_PREF_BASE_UPPER32); + } + } + } +} + static void vmd_attach_resources(struct vmd_dev *vmd) { vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1]; @@ -545,32 +578,211 @@ static void vmd_detach_resources(struct vmd_dev *vmd) vmd->dev->resource[VMD_MEMBAR2].child = NULL; } +static int vmd_get_phys_offsets(struct vmd_dev *vmd, bool native_hint, + resource_size_t *offset1, + resource_size_t *offset2) +{ + struct pci_dev *dev = vmd->dev; + u64 phys1, phys2; + + if (native_hint) { + u32 vmlock; + int ret; + + ret = pci_read_config_dword(dev, PCI_REG_VMLOCK, &vmlock); + if (ret || PCI_POSSIBLE_ERROR(vmlock)) + return -ENODEV; + + if (MB2_SHADOW_EN(vmlock)) { + void __iomem *membar2; + + membar2 = pci_iomap(dev, VMD_MEMBAR2, 0); + if (!membar2) + return -ENOMEM; + phys1 = readq(membar2 + MB2_SHADOW_OFFSET); + phys2 = readq(membar2 + MB2_SHADOW_OFFSET + 8); + pci_iounmap(dev, membar2); + } else + return 0; + } else { + /* Hypervisor-Emulated Vendor-Specific Capability */ + int pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); + u32 reg, regu; + + pci_read_config_dword(dev, pos + 4, ®); + + /* "SHDW" */ + if (pos && reg == 0x53484457) { + pci_read_config_dword(dev, pos + 8, ®); + pci_read_config_dword(dev, pos + 12, ®u); + phys1 = (u64) regu << 32 | reg; + + pci_read_config_dword(dev, pos + 16, ®); + pci_read_config_dword(dev, pos + 20, ®u); + phys2 = (u64) regu << 32 | reg; + } else + return 0; + } + + *offset1 = dev->resource[VMD_MEMBAR1].start - + (phys1 & PCI_BASE_ADDRESS_MEM_MASK); + *offset2 = dev->resource[VMD_MEMBAR2].start - + (phys2 & PCI_BASE_ADDRESS_MEM_MASK); + + return 0; +} + +static int vmd_get_bus_number_start(struct vmd_dev *vmd) +{ + struct pci_dev *dev = vmd->dev; + u16 reg; + + pci_read_config_word(dev, PCI_REG_VMCAP, ®); + if (BUS_RESTRICT_CAP(reg)) { + pci_read_config_word(dev, PCI_REG_VMCONFIG, ®); + + switch (BUS_RESTRICT_CFG(reg)) { + case 0: + vmd->busn_start = 0; + break; + case 1: + vmd->busn_start = 128; + break; + case 2: + vmd->busn_start = 224; + break; + default: + pci_err(dev, "Unknown Bus Offset Setting (%d)\n", + BUS_RESTRICT_CFG(reg)); + return -ENODEV; + } + } + + return 0; +} + +static irqreturn_t vmd_irq(int irq, void *data) +{ + struct vmd_irq_list *irqs = data; + struct vmd_irq *vmdirq; + int idx; + + idx = srcu_read_lock(&irqs->srcu); + list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) + generic_handle_irq(vmdirq->virq); + srcu_read_unlock(&irqs->srcu, idx); + + return IRQ_HANDLED; +} + +static int vmd_alloc_irqs(struct vmd_dev *vmd) +{ + struct pci_dev *dev = vmd->dev; + int i, err; + + vmd->msix_count = pci_msix_vec_count(dev); + if (vmd->msix_count < 0) + return -ENODEV; + + vmd->msix_count = pci_alloc_irq_vectors(dev, vmd->first_vec + 1, + vmd->msix_count, PCI_IRQ_MSIX); + if (vmd->msix_count < 0) + return vmd->msix_count; + + vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs), + GFP_KERNEL); + if (!vmd->irqs) + return -ENOMEM; + + for (i = 0; i < vmd->msix_count; i++) { + err = init_srcu_struct(&vmd->irqs[i].srcu); + if (err) + return err; + + INIT_LIST_HEAD(&vmd->irqs[i].irq_list); + vmd->irqs[i].virq = pci_irq_vector(dev, i); + err = devm_request_irq(&dev->dev, vmd->irqs[i].virq, + vmd_irq, IRQF_NO_THREAD, + vmd->name, &vmd->irqs[i]); + if (err) + return err; + } + + return 0; +} + +/* + * Since VMD is an aperture to regular PCIe root ports, only allow it to + * control features that the OS is allowed to control on the physical PCI bus. + */ +static void vmd_copy_host_bridge_flags(struct pci_host_bridge *root_bridge, + struct pci_host_bridge *vmd_bridge) +{ + vmd_bridge->native_pcie_hotplug = root_bridge->native_pcie_hotplug; + vmd_bridge->native_shpc_hotplug = root_bridge->native_shpc_hotplug; + vmd_bridge->native_aer = root_bridge->native_aer; + vmd_bridge->native_pme = root_bridge->native_pme; + vmd_bridge->native_ltr = root_bridge->native_ltr; + vmd_bridge->native_dpc = root_bridge->native_dpc; +} + /* - * 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. + * Enable ASPM and LTR settings on devices that aren't configured by BIOS. */ -static int vmd_find_free_domain(void) +static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata) { - int domain = 0xffff; - struct pci_bus *bus = NULL; + unsigned long features = *(unsigned long *)userdata; + u16 ltr = VMD_BIOS_PM_QUIRK_LTR; + u32 ltr_reg; + int pos; + + if (!(features & VMD_FEAT_BIOS_PM_QUIRK)) + return 0; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR); + if (!pos) + goto out_state_change; - while ((bus = pci_find_next_bus(bus)) != NULL) - domain = max_t(int, domain, pci_domain_nr(bus)); - return domain + 1; + /* + * Skip if the max snoop LTR is non-zero, indicating BIOS has set it + * so the LTR quirk is not needed. + */ + pci_read_config_dword(pdev, pos + PCI_LTR_MAX_SNOOP_LAT, <r_reg); + if (!!(ltr_reg & (PCI_LTR_VALUE_MASK | PCI_LTR_SCALE_MASK))) + goto out_state_change; + + /* + * Set the default values to the maximum required by the platform to + * allow the deepest power management savings. Write as a DWORD where + * the lower word is the max snoop latency and the upper word is the + * max non-snoop latency. + */ + ltr_reg = (ltr << 16) | ltr; + pci_write_config_dword(pdev, pos + PCI_LTR_MAX_SNOOP_LAT, ltr_reg); + pci_info(pdev, "VMD: Default LTR value set by driver\n"); + +out_state_change: + /* + * Ensure devices are in D0 before enabling PCI-PM L1 PM Substates, per + * PCIe r6.0, sec 5.5.4. + */ + pci_set_power_state_locked(pdev, PCI_D0); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); + return 0; } static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) { struct pci_sysdata *sd = &vmd->sysdata; - struct fwnode_handle *fn; struct resource *res; u32 upper_bits; unsigned long flags; LIST_HEAD(resources); resource_size_t offset[2] = {0}; - resource_size_t membar2_offset = 0x2000, busn_start = 0; + resource_size_t membar2_offset = 0x2000; + struct pci_bus *child; + struct pci_dev *dev; + int ret; /* * Shadow registers may exist in certain VMD device ids which allow @@ -579,47 +791,31 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) * or 0, depending on an enable bit in the VMD device. */ if (features & VMD_FEAT_HAS_MEMBAR_SHADOW) { - u32 vmlock; - int ret; - - membar2_offset = 0x2018; - ret = pci_read_config_dword(vmd->dev, PCI_REG_VMLOCK, &vmlock); - if (ret || vmlock == ~0) - return -ENODEV; - - if (MB2_SHADOW_EN(vmlock)) { - void __iomem *membar2; - - membar2 = pci_iomap(vmd->dev, VMD_MEMBAR2, 0); - if (!membar2) - return -ENOMEM; - offset[0] = vmd->dev->resource[VMD_MEMBAR1].start - - readq(membar2 + 0x2008); - offset[1] = vmd->dev->resource[VMD_MEMBAR2].start - - readq(membar2 + 0x2010); - pci_iounmap(vmd->dev, membar2); - } + membar2_offset = MB2_SHADOW_OFFSET + MB2_SHADOW_SIZE; + ret = vmd_get_phys_offsets(vmd, true, &offset[0], &offset[1]); + if (ret) + return ret; + } else if (features & VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP) { + ret = vmd_get_phys_offsets(vmd, false, &offset[0], &offset[1]); + if (ret) + return ret; } /* * Certain VMD devices may have a root port configuration option which - * limits the bus range to between 0-127 or 128-255 + * limits the bus range to between 0-127, 128-255, or 224-255 */ if (features & VMD_FEAT_HAS_BUS_RESTRICTIONS) { - u32 vmcap, vmconfig; - - pci_read_config_dword(vmd->dev, PCI_REG_VMCAP, &vmcap); - pci_read_config_dword(vmd->dev, PCI_REG_VMCONFIG, &vmconfig); - if (BUS_RESTRICT_CAP(vmcap) && - (BUS_RESTRICT_CFG(vmconfig) == 0x1)) - busn_start = 128; + ret = vmd_get_bus_number_start(vmd); + if (ret) + return ret; } res = &vmd->dev->resource[VMD_CFGBAR]; vmd->resources[0] = (struct resource) { .name = "VMD CFGBAR", - .start = busn_start, - .end = busn_start + (resource_size(res) >> 20) - 1, + .start = vmd->busn_start, + .end = vmd->busn_start + (resource_size(res) >> 20) - 1, .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED, }; @@ -633,7 +829,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) * 32-bit resources. __pci_assign_resource() enforces that * artificial restriction to make sure everything will fit. * - * The only way we could use a 64-bit non-prefechable MEMBAR is + * The only way we could use a 64-bit non-prefetchable MEMBAR is * if its address is <4GB so that we can convert it to a 32-bit * resource. To be visible to the host OS, all VMD endpoints must * be initially configured by platform BIOS, which includes setting @@ -666,63 +862,132 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) .parent = res, }; - sd->vmd_domain = true; - sd->domain = vmd_find_free_domain(); - if (sd->domain < 0) - return sd->domain; - - sd->node = pcibus_to_node(vmd->dev->bus); - - fn = irq_domain_alloc_named_id_fwnode("VMD-MSI", vmd->sysdata.domain); - if (!fn) - return -ENODEV; - - vmd->irq_domain = pci_msi_create_irq_domain(fn, &vmd_msi_domain_info, - x86_vector_domain); - irq_domain_free_fwnode(fn); - if (!vmd->irq_domain) - return -ENODEV; + /* + * Currently MSI remapping must be enabled in guest passthrough mode + * due to some missing interrupt remapping plumbing. This is probably + * acceptable because the guest is usually CPU-limited and MSI + * remapping doesn't become a performance bottleneck. + */ + if (!(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) || + offset[0] || offset[1]) { + ret = vmd_alloc_irqs(vmd); + if (ret) + return ret; + + vmd_set_msi_remapping(vmd, true); + + ret = vmd_create_irq_domain(vmd); + if (ret) + return ret; + } else { + vmd_set_msi_remapping(vmd, false); + } pci_add_resource(&resources, &vmd->resources[0]); pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]); pci_add_resource_offset(&resources, &vmd->resources[2], offset[1]); - vmd->bus = pci_create_root_bus(&vmd->dev->dev, busn_start, &vmd_ops, - sd, &resources); + 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); - irq_domain_remove(vmd->irq_domain); + vmd_remove_irq_domain(vmd); return -ENODEV; } + vmd_copy_host_bridge_flags(pci_find_host_bridge(vmd->dev->bus), + to_pci_host_bridge(vmd->bus->bridge)); + vmd_attach_resources(vmd); - vmd_setup_dma_ops(vmd); - dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); - pci_rescan_bus(vmd->bus); + if (vmd->irq_domain) + dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); + else + dev_set_msi_domain(&vmd->bus->dev, + dev_get_msi_domain(&vmd->dev->dev)); WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, "domain"), "Can't create symlink to domain\n"); - return 0; -} -static irqreturn_t vmd_irq(int irq, void *data) -{ - struct vmd_irq_list *irqs = data; - struct vmd_irq *vmdirq; - int idx; + vmd_acpi_begin(); - idx = srcu_read_lock(&irqs->srcu); - list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) - generic_handle_irq(vmdirq->virq); - srcu_read_unlock(&irqs->srcu, idx); + pci_scan_child_bus(vmd->bus); + vmd_domain_reset(vmd); - return IRQ_HANDLED; + /* When Intel VMD is enabled, the OS does not discover the Root Ports + * owned by Intel VMD within the MMCFG space. pci_reset_bus() applies + * a reset to the parent of the PCI device supplied as argument. This + * is why we pass a child device, so the reset can be triggered at + * the Intel bridge level and propagated to all the children in the + * hierarchy. + */ + list_for_each_entry(child, &vmd->bus->children, node) { + if (!list_empty(&child->devices)) { + dev = list_first_entry(&child->devices, + struct pci_dev, bus_list); + ret = pci_reset_bus(dev); + if (ret) + pci_warn(dev, "can't reset device: %d\n", ret); + + break; + } + } + + pci_assign_unassigned_bus_resources(vmd->bus); + + pci_walk_bus(vmd->bus, vmd_pm_enable_quirk, &features); + + /* + * VMD root buses are virtual and don't return true on pci_is_pcie() + * and will fail pcie_bus_configure_settings() early. It can instead be + * run on each of the real root ports. + */ + list_for_each_entry(child, &vmd->bus->children, node) + pcie_bus_configure_settings(child); + + pci_bus_add_devices(vmd->bus); + + vmd_acpi_end(); + return 0; } static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) { + unsigned long features = (unsigned long) id->driver_data; struct vmd_dev *vmd; - int i, err; + int err; + + if (xen_domain()) { + /* + * Xen doesn't have knowledge about devices in the VMD bus + * because the config space of devices behind the VMD bridge is + * not known to Xen, and hence Xen cannot discover or configure + * them in any way. + * + * Bypass of MSI remapping won't work in that case as direct + * write by Linux to the MSI entries won't result in functional + * interrupts, as Xen is the entity that manages the host + * interrupt controller and must configure interrupts. However + * multiplexing of interrupts by the VMD bridge will work under + * Xen, so force the usage of that mode which must always be + * supported by VMD bridges. + */ + features &= ~VMD_FEAT_CAN_BYPASS_MSI_REMAP; + } if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) return -ENOMEM; @@ -732,55 +997,51 @@ 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; + + vmd->name = devm_kasprintf(&dev->dev, GFP_KERNEL, "vmd%d", + vmd->instance); + if (!vmd->name) { + err = -ENOMEM; + goto out_release_instance; + } + err = pcim_enable_device(dev); if (err < 0) - return err; + goto out_release_instance; vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); - if (!vmd->cfgbar) - return -ENOMEM; + if (!vmd->cfgbar) { + err = -ENOMEM; + goto out_release_instance; + } pci_set_master(dev); if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && - dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) - return -ENODEV; - - vmd->msix_count = pci_msix_vec_count(dev); - if (vmd->msix_count < 0) - return -ENODEV; - - vmd->msix_count = pci_alloc_irq_vectors(dev, 1, vmd->msix_count, - PCI_IRQ_MSIX); - if (vmd->msix_count < 0) - return vmd->msix_count; - - vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs), - GFP_KERNEL); - if (!vmd->irqs) - return -ENOMEM; - - for (i = 0; i < vmd->msix_count; i++) { - err = init_srcu_struct(&vmd->irqs[i].srcu); - if (err) - return err; - - INIT_LIST_HEAD(&vmd->irqs[i].irq_list); - err = devm_request_irq(&dev->dev, pci_irq_vector(dev, i), - vmd_irq, IRQF_NO_THREAD, - "vmd", &vmd->irqs[i]); - if (err) - return err; + dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) { + err = -ENODEV; + goto out_release_instance; } - spin_lock_init(&vmd->cfg_lock); + if (features & VMD_FEAT_OFFSET_FIRST_VECTOR) + vmd->first_vec = 1; + + raw_spin_lock_init(&vmd->cfg_lock); pci_set_drvdata(dev, vmd); - err = vmd_enable_domain(vmd, (unsigned long) id->driver_data); + err = vmd_enable_domain(vmd, features); if (err) - return err; + goto out_release_instance; dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", vmd->sysdata.domain); return 0; + + out_release_instance: + ida_free(&vmd_instance_ida, vmd->instance); + return err; } static void vmd_cleanup_srcu(struct vmd_dev *vmd) @@ -795,13 +1056,21 @@ static void vmd_remove(struct pci_dev *dev) { struct vmd_dev *vmd = pci_get_drvdata(dev); - sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); pci_stop_root_bus(vmd->bus); + sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); pci_remove_root_bus(vmd->bus); vmd_cleanup_srcu(vmd); - vmd_teardown_dma_ops(vmd); vmd_detach_resources(vmd); - irq_domain_remove(vmd->irq_domain); + 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) +{ + struct vmd_dev *vmd = pci_get_drvdata(dev); + + vmd_remove_irq_domain(vmd); } #ifdef CONFIG_PM_SLEEP @@ -812,9 +1081,8 @@ static int vmd_suspend(struct device *dev) int i; for (i = 0; i < vmd->msix_count; i++) - devm_free_irq(dev, pci_irq_vector(pdev, i), &vmd->irqs[i]); + devm_free_irq(dev, vmd->irqs[i].virq, &vmd->irqs[i]); - pci_save_state(pdev); return 0; } @@ -824,25 +1092,46 @@ static int vmd_resume(struct device *dev) struct vmd_dev *vmd = pci_get_drvdata(pdev); int err, i; + vmd_set_msi_remapping(vmd, !!vmd->irq_domain); + for (i = 0; i < vmd->msix_count; i++) { - err = devm_request_irq(dev, pci_irq_vector(pdev, i), + err = devm_request_irq(dev, vmd->irqs[i].virq, vmd_irq, IRQF_NO_THREAD, - "vmd", &vmd->irqs[i]); + vmd->name, &vmd->irqs[i]); if (err) return err; } - pci_restore_state(pdev); return 0; } #endif static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume); static const struct pci_device_id vmd_ids[] = { - {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_201D),}, - {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0), + {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_VMD_201D), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP,}, + {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW | - VMD_FEAT_HAS_BUS_RESTRICTIONS,}, + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_CAN_BYPASS_MSI_REMAP,}, + {PCI_VDEVICE(INTEL, 0x467f), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0x4c3d), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xa77f), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0x7d0b), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xad0b), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xb60b), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xb06f), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xb07f), + .driver_data = VMD_FEATS_CLIENT,}, {0,} }; MODULE_DEVICE_TABLE(pci, vmd_ids); @@ -852,6 +1141,7 @@ static struct pci_driver vmd_drv = { .id_table = vmd_ids, .probe = vmd_probe, .remove = vmd_remove, + .shutdown = vmd_shutdown, .driver = { .pm = &vmd_dev_pm_ops, }, @@ -859,5 +1149,6 @@ static struct pci_driver vmd_drv = { module_pci_driver(vmd_drv); MODULE_AUTHOR("Intel Corporation"); +MODULE_DESCRIPTION("Volume Management Device driver"); MODULE_LICENSE("GPL v2"); MODULE_VERSION("0.6"); |