From fe97f59a78fefda6c4a8c8ee6a070b1f769fc801 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:54:15 +0100 Subject: PCI/MSI: Check for MSI enabled in __pci_msix_enable() PCI/MSI and PCI/MSI-X are mutually exclusive, but the MSI-X enable code lacks a check for already enabled MSI. Signed-off-by: Thomas Gleixner Reviewed-by: Ashok Raj Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122013.653556720@linutronix.de --- drivers/pci/msi/msi.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index fdd2ec09651e..160af9f01669 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -935,6 +935,11 @@ static int __pci_enable_msix_range(struct pci_dev *dev, if (maxvec < minvec) return -ERANGE; + if (dev->msi_enabled) { + pci_info(dev, "can't enable MSI-X (MSI already enabled)\n"); + return -EINVAL; + } + if (WARN_ON_ONCE(dev->msix_enabled)) return -EINVAL; -- cgit v1.2.3 From 38c0c10ae6a3d386c50e182227f606d8243124b8 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:35 +0100 Subject: PCI/MSI: Use msi_domain_info:: Bus_token Set the bus token in the msi_domain_info structure and let the core code handle the update. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.352437595@linutronix.de --- drivers/pci/msi/irqdomain.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index e9cf318e6670..7766fa6c475c 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -162,8 +162,6 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent) { - struct irq_domain *domain; - if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE)) info->flags &= ~MSI_FLAG_LEVEL_CAPABLE; @@ -178,13 +176,10 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, /* PCI-MSI is oneshot-safe */ info->chip->flags |= IRQCHIP_ONESHOT_SAFE; + /* Let the core update the bus token */ + info->bus_token = DOMAIN_BUS_PCI_MSI; - domain = msi_create_irq_domain(fwnode, info, parent); - if (!domain) - return NULL; - - irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI); - return domain; + return msi_create_irq_domain(fwnode, info, parent); } EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain); -- cgit v1.2.3 From b2bdda205c0c256d6483231d0afe58a6d68fd3ed Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:37 +0100 Subject: PCI/MSI: Let the MSI core free descriptors Let the core do the freeing of descriptors and just keep it around for the legacy case. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.409654736@linutronix.de --- drivers/pci/msi/irqdomain.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 7766fa6c475c..edd0cc204e06 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -24,11 +24,12 @@ void pci_msi_teardown_msi_irqs(struct pci_dev *dev) struct irq_domain *domain; domain = dev_get_msi_domain(&dev->dev); - if (domain && irq_domain_is_hierarchy(domain)) + if (domain && irq_domain_is_hierarchy(domain)) { msi_domain_free_irqs_descs_locked(domain, &dev->dev); - else + } else { pci_msi_legacy_teardown_msi_irqs(dev); - msi_free_msi_descs(&dev->dev); + msi_free_msi_descs(&dev->dev); + } } /** @@ -170,6 +171,9 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); + /* Let the core code free MSI descriptors when freeing interrupts */ + info->flags |= MSI_FLAG_FREE_MSI_DESCS; + info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS; if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) info->flags |= MSI_FLAG_MUST_REACTIVATE; -- cgit v1.2.3 From a474d3fbe287625c6c1cfc56c2a456c5fb7c479e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:54:38 +0100 Subject: PCI/MSI: Get rid of PCI_MSI_IRQ_DOMAIN What a zoo: PCI_MSI select GENERIC_MSI_IRQ PCI_MSI_IRQ_DOMAIN def_bool y depends on PCI_MSI select GENERIC_MSI_IRQ_DOMAIN Ergo PCI_MSI enables PCI_MSI_IRQ_DOMAIN which in turn selects GENERIC_MSI_IRQ_DOMAIN. So all the dependencies on PCI_MSI_IRQ_DOMAIN are just an indirection to PCI_MSI. Match the reality and just admit that PCI_MSI requires GENERIC_MSI_IRQ_DOMAIN. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.467556921@linutronix.de --- arch/um/drivers/Kconfig | 1 - arch/um/include/asm/pci.h | 2 +- arch/x86/Kconfig | 1 - arch/x86/include/asm/pci.h | 4 +-- drivers/pci/Kconfig | 8 ++---- drivers/pci/controller/Kconfig | 30 ++++++++++----------- drivers/pci/controller/dwc/Kconfig | 48 ++++++++++++++++----------------- drivers/pci/controller/mobiveil/Kconfig | 6 ++--- drivers/pci/msi/Makefile | 2 +- drivers/pci/probe.c | 2 -- include/linux/msi.h | 29 ++++++++------------ 11 files changed, 58 insertions(+), 75 deletions(-) (limited to 'drivers/pci') diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig index 5903e2b598aa..a4f0a19fbe14 100644 --- a/arch/um/drivers/Kconfig +++ b/arch/um/drivers/Kconfig @@ -381,7 +381,6 @@ config UML_PCI_OVER_VIRTIO select UML_IOMEM_EMULATION select UML_DMA_EMULATION select PCI_MSI - select PCI_MSI_IRQ_DOMAIN select PCI_LOCKLESS_CONFIG config UML_PCI_OVER_VIRTIO_DEVICE_ID diff --git a/arch/um/include/asm/pci.h b/arch/um/include/asm/pci.h index 34fe4921b5fa..238d2e7faff8 100644 --- a/arch/um/include/asm/pci.h +++ b/arch/um/include/asm/pci.h @@ -7,7 +7,7 @@ /* Generic PCI */ #include -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI /* * This is a bit of an annoying hack, and it assumes we only have * the virt-pci (if anything). Which is true, but still. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 67745ceab0db..64f81a10bfc8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1109,7 +1109,6 @@ config X86_LOCAL_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI select IRQ_DOMAIN_HIERARCHY - select PCI_MSI_IRQ_DOMAIN if PCI_MSI config X86_IO_APIC def_bool y diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 736793d65bcb..c4789de0da09 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -21,7 +21,7 @@ struct pci_sysdata { #ifdef CONFIG_X86_64 void *iommu; /* IOMMU private data */ #endif -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI void *fwnode; /* IRQ domain for MSI assignment */ #endif #if IS_ENABLED(CONFIG_VMD) @@ -52,7 +52,7 @@ static inline int pci_proc_domain(struct pci_bus *bus) } #endif -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) { return to_pci_sysdata(bus)->fwnode; diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 55c028af4bd9..b7f62214668a 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -38,6 +38,7 @@ source "drivers/pci/pcie/Kconfig" config PCI_MSI bool "Message Signaled Interrupts (MSI and MSI-X)" + select GENERIC_MSI_IRQ_DOMAIN select GENERIC_MSI_IRQ help This allows device drivers to enable MSI (Message Signaled @@ -51,11 +52,6 @@ config PCI_MSI If you don't know what to do here, say Y. -config PCI_MSI_IRQ_DOMAIN - def_bool y - depends on PCI_MSI - select GENERIC_MSI_IRQ_DOMAIN - config PCI_MSI_ARCH_FALLBACKS bool @@ -192,7 +188,7 @@ config PCI_LABEL config PCI_HYPERV tristate "Hyper-V PCI Frontend" - depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && SYSFS + depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && SYSFS select PCI_HYPERV_INTERFACE help The PCI device frontend driver allows the kernel to import arbitrary diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index bfd9bac37e24..1569d9a3ada0 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -19,7 +19,7 @@ config PCI_AARDVARK 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 help Add support for Aardvark 64bit PCIe Host Controller. This @@ -29,7 +29,7 @@ config PCI_AARDVARK config PCIE_XILINX_NWL bool "NWL PCIe Core" depends on ARCH_ZYNQMP || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say 'Y' here if you want kernel support for Xilinx NWL PCIe controller. The controller can act as Root Port @@ -53,7 +53,7 @@ config PCI_IXP4XX config PCI_TEGRA bool "NVIDIA Tegra PCIe controller" depends on ARCH_TEGRA || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want support for the PCIe host controller found on NVIDIA Tegra SoCs. @@ -70,7 +70,7 @@ config PCI_RCAR_GEN2 config PCIE_RCAR_HOST bool "Renesas R-Car PCIe host controller" depends on ARCH_RENESAS || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want PCIe controller support on R-Car SoCs in host mode. @@ -99,7 +99,7 @@ config PCI_HOST_GENERIC config PCIE_XILINX bool "Xilinx AXI PCIe host bridge support" depends on OF || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say 'Y' here if you want kernel to support the Xilinx AXI PCIe Host Bridge driver. @@ -124,7 +124,7 @@ config PCI_XGENE config PCI_XGENE_MSI bool "X-Gene v1 PCIe MSI feature" depends on PCI_XGENE - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI default y help Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC. @@ -170,7 +170,7 @@ 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 default ARCH_BCM_IPROC help Say Y here if you want to enable MSI support for Broadcom's iProc @@ -186,7 +186,7 @@ config PCIE_ALTERA config PCIE_ALTERA_MSI tristate "Altera PCIe MSI feature" depends on PCIE_ALTERA - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want PCIe MSI support for the Altera FPGA. This MSI driver supports Altera MSI to GIC controller IP. @@ -215,7 +215,7 @@ config PCIE_ROCKCHIP_HOST tristate "Rockchip PCIe host controller" 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 @@ -239,7 +239,7 @@ config PCIE_MEDIATEK tristate "MediaTek PCIe controller" depends on ARCH_AIROHA || ARCH_MEDIATEK || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Say Y here if you want to enable PCIe controller support on MediaTek SoCs. @@ -247,7 +247,7 @@ config PCIE_MEDIATEK config PCIE_MEDIATEK_GEN3 tristate "MediaTek Gen3 PCIe controller" depends on ARCH_MEDIATEK || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI help Adds support for PCIe Gen3 MAC controller for MediaTek SoCs. This PCIe controller is compatible with Gen3, Gen2 and Gen1 speed, @@ -277,7 +277,7 @@ config PCIE_BRCMSTB depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCMBCA || \ BMIPS_GENERIC || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI default ARCH_BRCMSTB || BMIPS_GENERIC help Say Y here to enable PCIe host controller support for @@ -285,7 +285,7 @@ config PCIE_BRCMSTB config PCI_HYPERV_INTERFACE tristate "Hyper-V PCI Interface" - depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN + depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI help The Hyper-V PCI Interface is a helper driver allows other drivers to have a common interface with the Hyper-V PCI frontend driver. @@ -303,8 +303,6 @@ config PCI_LOONGSON config PCIE_MICROCHIP_HOST bool "Microchip AXI PCIe host bridge support" depends on PCI_MSI && OF - select PCI_MSI_IRQ_DOMAIN - select GENERIC_MSI_IRQ_DOMAIN select PCI_HOST_COMMON help Say Y here if you want kernel to support the Microchip AXI PCIe @@ -326,7 +324,7 @@ config PCIE_APPLE tristate "Apple PCIe controller" depends on ARCH_APPLE || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCI_HOST_COMMON help Say Y here if you want to enable PCIe controller support on Apple diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index 62ce3abf0f19..f3c462130627 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -21,7 +21,7 @@ config PCI_DRA7XX_HOST tristate "TI DRA7xx PCIe controller Host Mode" depends on SOC_DRA7XX || COMPILE_TEST depends on OF && HAS_IOMEM && TI_PIPE3 - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_DRA7XX default y if SOC_DRA7XX @@ -53,7 +53,7 @@ config PCIE_DW_PLAT config PCIE_DW_PLAT_HOST bool "Platform bus based DesignWare PCIe Controller - Host mode" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCIE_DW_PLAT help @@ -67,7 +67,7 @@ config PCIE_DW_PLAT_HOST config PCIE_DW_PLAT_EP bool "Platform bus based DesignWare PCIe Controller - Endpoint mode" - depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI && PCI_MSI depends on PCI_ENDPOINT select PCIE_DW_EP select PCIE_DW_PLAT @@ -83,7 +83,7 @@ config PCIE_DW_PLAT_EP config PCI_EXYNOS tristate "Samsung Exynos PCIe controller" depends on ARCH_EXYNOS || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Enables support for the PCIe controller in the Samsung Exynos SoCs @@ -94,13 +94,13 @@ config PCI_EXYNOS config PCI_IMX6 bool "Freescale i.MX6/7/8 PCIe controller" depends on ARCH_MXC || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST config PCIE_SPEAR13XX bool "STMicroelectronics SPEAr PCIe controller" depends on ARCH_SPEAR13XX || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe support on SPEAr13XX SoCs. @@ -111,7 +111,7 @@ config PCI_KEYSTONE config PCI_KEYSTONE_HOST bool "PCI Keystone Host Mode" depends on ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_KEYSTONE help @@ -135,7 +135,7 @@ config PCI_KEYSTONE_EP config PCI_LAYERSCAPE bool "Freescale Layerscape PCIe controller - Host mode" depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select MFD_SYSCON help @@ -160,7 +160,7 @@ config PCI_LAYERSCAPE_EP config PCI_HISI depends on OF && (ARM64 || COMPILE_TEST) bool "HiSilicon Hip05 and Hip06 SoCs PCIe controllers" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_HOST_COMMON help @@ -170,7 +170,7 @@ config PCI_HISI config PCIE_QCOM bool "Qualcomm PCIe controller" depends on OF && (ARCH_QCOM || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select CRC8 help @@ -191,7 +191,7 @@ config PCIE_QCOM_EP config PCIE_ARMADA_8K bool "Marvell Armada-8K PCIe controller" depends on ARCH_MVEBU || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want to enable PCIe controller support on @@ -205,7 +205,7 @@ config PCIE_ARTPEC6 config PCIE_ARTPEC6_HOST bool "Axis ARTPEC-6 PCIe controller Host Mode" depends on MACH_ARTPEC6 || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCIE_ARTPEC6 help @@ -226,7 +226,7 @@ config PCIE_ROCKCHIP_DW_HOST bool "Rockchip DesignWare PCIe controller" select PCIE_DW select PCIE_DW_HOST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI depends on ARCH_ROCKCHIP || COMPILE_TEST depends on OF help @@ -236,7 +236,7 @@ config PCIE_ROCKCHIP_DW_HOST config PCIE_INTEL_GW bool "Intel Gateway PCIe host controller support" depends on OF && (X86 || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say 'Y' here to enable PCIe Host controller support on Intel @@ -250,7 +250,7 @@ config PCIE_KEEMBAY config PCIE_KEEMBAY_HOST bool "Intel Keem Bay PCIe controller - Host mode" depends on ARCH_KEEMBAY || COMPILE_TEST - depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCIE_KEEMBAY help @@ -262,7 +262,7 @@ config PCIE_KEEMBAY_HOST config PCIE_KEEMBAY_EP bool "Intel Keem Bay PCIe controller - Endpoint mode" depends on ARCH_KEEMBAY || COMPILE_TEST - depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI depends on PCI_ENDPOINT select PCIE_DW_EP select PCIE_KEEMBAY @@ -275,7 +275,7 @@ config PCIE_KEEMBAY_EP config PCIE_KIRIN depends on OF && (ARM64 || COMPILE_TEST) tristate "HiSilicon Kirin series SoCs PCIe controllers" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe controller support @@ -284,7 +284,7 @@ config PCIE_KIRIN config PCIE_HISI_STB bool "HiSilicon STB SoCs PCIe controllers" depends on ARCH_HISI || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe controller support on HiSilicon STB SoCs @@ -292,7 +292,7 @@ config PCIE_HISI_STB config PCI_MESON tristate "MESON PCIe controller" default m if ARCH_MESON - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want to enable PCI controller support on Amlogic @@ -306,7 +306,7 @@ config PCIE_TEGRA194 config PCIE_TEGRA194_HOST tristate "NVIDIA Tegra194 (and later) PCIe controller - Host Mode" depends on ARCH_TEGRA_194_SOC || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PHY_TEGRA194_P2U select PCIE_TEGRA194 @@ -336,7 +336,7 @@ config PCIE_TEGRA194_EP config PCIE_VISCONTI_HOST bool "Toshiba Visconti PCIe controllers" depends on ARCH_VISCONTI || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe controller support on Toshiba Visconti SoC. @@ -346,7 +346,7 @@ config PCIE_UNIPHIER bool "Socionext UniPhier PCIe host controllers" depends on ARCH_UNIPHIER || COMPILE_TEST depends on OF && HAS_IOMEM - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Say Y here if you want PCIe host controller support on UniPhier SoCs. @@ -365,7 +365,7 @@ config PCIE_UNIPHIER_EP config PCIE_AL bool "Amazon Annapurna Labs PCIe controller" depends on OF && (ARM64 || COMPILE_TEST) - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST select PCI_ECAM help @@ -377,7 +377,7 @@ config PCIE_AL config PCIE_FU740 bool "SiFive FU740 PCIe host controller" - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI depends on SOC_SIFIVE || COMPILE_TEST select PCIE_DW_HOST help diff --git a/drivers/pci/controller/mobiveil/Kconfig b/drivers/pci/controller/mobiveil/Kconfig index e4643fb94e78..1d7a07ba9ccd 100644 --- a/drivers/pci/controller/mobiveil/Kconfig +++ b/drivers/pci/controller/mobiveil/Kconfig @@ -8,14 +8,14 @@ config PCIE_MOBIVEIL config PCIE_MOBIVEIL_HOST bool - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_MOBIVEIL config PCIE_MOBIVEIL_PLAT bool "Mobiveil AXI PCIe controller" depends on ARCH_ZYNQMP || COMPILE_TEST depends on OF - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_MOBIVEIL_HOST help Say Y here if you want to enable support for the Mobiveil AXI PCIe @@ -25,7 +25,7 @@ config PCIE_MOBIVEIL_PLAT config PCIE_LAYERSCAPE_GEN4 bool "Freescale Layerscape PCIe Gen4 controller" depends on ARCH_LAYERSCAPE || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_MOBIVEIL_HOST help Say Y here if you want PCIe Gen4 controller support on diff --git a/drivers/pci/msi/Makefile b/drivers/pci/msi/Makefile index 93ef7b9e404d..4e0a7e07965e 100644 --- a/drivers/pci/msi/Makefile +++ b/drivers/pci/msi/Makefile @@ -3,5 +3,5 @@ # Makefile for the PCI/MSI obj-$(CONFIG_PCI) += pcidev_msi.o obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_PCI_MSI_IRQ_DOMAIN) += irqdomain.o +obj-$(CONFIG_PCI_MSI) += irqdomain.o obj-$(CONFIG_PCI_MSI_ARCH_FALLBACKS) += legacy.o diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b66fa42c4b1f..fdd7e56ddf40 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -842,7 +842,6 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus) if (!d) d = pci_host_bridge_acpi_msi_domain(bus); -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN /* * If no IRQ domain was found via the OF tree, try looking it up * directly through the fwnode_handle. @@ -854,7 +853,6 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus) d = irq_find_matching_fwnode(fwnode, DOMAIN_BUS_PCI_MSI); } -#endif return d; } diff --git a/include/linux/msi.h b/include/linux/msi.h index 2dfd7b2bdfbe..9b8414523916 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -238,15 +238,6 @@ static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, } #endif -#ifdef CONFIG_PCI_MSI -struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); -void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); -#else /* CONFIG_PCI_MSI */ -static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) -{ -} -#endif /* CONFIG_PCI_MSI */ - int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc); void msi_free_msi_descs_range(struct device *dev, unsigned int first_index, unsigned int last_index); @@ -259,12 +250,6 @@ static inline void msi_free_msi_descs(struct device *dev) msi_free_msi_descs_range(dev, 0, MSI_MAX_INDEX); } -void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); - -void pci_msi_mask_irq(struct irq_data *data); -void pci_msi_unmask_irq(struct irq_data *data); - /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific @@ -468,18 +453,26 @@ void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int vir void *platform_msi_get_host_data(struct irq_domain *domain); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +/* PCI specific interfaces */ +#ifdef CONFIG_PCI_MSI +struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); +void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); +void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); +void pci_msi_mask_irq(struct irq_data *data); +void pci_msi_unmask_irq(struct irq_data *data); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); bool pci_dev_has_special_msi_domain(struct pci_dev *pdev); -#else +#else /* CONFIG_PCI_MSI */ static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) { return NULL; } -#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */ +static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) { } +#endif /* !CONFIG_PCI_MSI */ #endif /* LINUX_MSI_H */ -- cgit v1.2.3 From 13e7accb81d6c07993385af8342238ff22b41ac8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:54:40 +0100 Subject: genirq: Get rid of GENERIC_MSI_IRQ_DOMAIN Adjust to reality and remove another layer of pointless Kconfig indirection. CONFIG_GENERIC_MSI_IRQ is good enough to serve all purposes. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20221111122014.524842979@linutronix.de --- drivers/base/Makefile | 2 +- drivers/bus/fsl-mc/Kconfig | 2 +- drivers/dma/Kconfig | 2 +- drivers/dma/qcom/hidma.c | 8 ++++---- drivers/iommu/Kconfig | 2 +- drivers/irqchip/Kconfig | 6 +++--- drivers/mailbox/Kconfig | 2 +- drivers/pci/Kconfig | 1 - drivers/perf/Kconfig | 2 +- drivers/soc/ti/Kconfig | 2 +- include/asm-generic/msi.h | 4 ++-- include/linux/device.h | 8 +++----- include/linux/gpio/driver.h | 2 +- include/linux/msi.h | 8 +++----- kernel/irq/Kconfig | 7 +------ kernel/irq/msi.c | 3 --- 16 files changed, 24 insertions(+), 37 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 83217d243c25..3079bfe53d04 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -22,7 +22,7 @@ obj-$(CONFIG_REGMAP) += regmap/ obj-$(CONFIG_SOC_BUS) += soc.o obj-$(CONFIG_PINCTRL) += pinctrl.o obj-$(CONFIG_DEV_COREDUMP) += devcoredump.o -obj-$(CONFIG_GENERIC_MSI_IRQ_DOMAIN) += platform-msi.o +obj-$(CONFIG_GENERIC_MSI_IRQ) += platform-msi.o obj-$(CONFIG_GENERIC_ARCH_TOPOLOGY) += arch_topology.o obj-$(CONFIG_GENERIC_ARCH_NUMA) += arch_numa.o obj-$(CONFIG_ACPI) += physical_location.o diff --git a/drivers/bus/fsl-mc/Kconfig b/drivers/bus/fsl-mc/Kconfig index b1fd55901c50..9492342e7d13 100644 --- a/drivers/bus/fsl-mc/Kconfig +++ b/drivers/bus/fsl-mc/Kconfig @@ -8,7 +8,7 @@ config FSL_MC_BUS bool "QorIQ DPAA2 fsl-mc bus driver" depends on OF && (ARCH_LAYERSCAPE || (COMPILE_TEST && (ARM || ARM64 || X86_LOCAL_APIC || PPC))) - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Driver to enable the bus infrastructure for the QorIQ DPAA2 architecture. The fsl-mc bus driver handles discovery of diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index 7524b62a8870..25e111ab21f8 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -462,7 +462,7 @@ config MV_XOR_V2 select DMA_ENGINE select DMA_ENGINE_RAID select ASYNC_TX_ENABLE_CHANNEL_SWITCH - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Enable support for the Marvell version 2 XOR engine. diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c index 210f1a9eb441..04d1c33afc12 100644 --- a/drivers/dma/qcom/hidma.c +++ b/drivers/dma/qcom/hidma.c @@ -610,7 +610,7 @@ static irqreturn_t hidma_chirq_handler(int chirq, void *arg) return hidma_ll_inthandler(chirq, lldev); } -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ static irqreturn_t hidma_chirq_handler_msi(int chirq, void *arg) { struct hidma_lldev **lldevp = arg; @@ -671,7 +671,7 @@ static int hidma_sysfs_init(struct hidma_dev *dev) return device_create_file(dev->ddev.dev, dev->chid_attrs); } -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ static void hidma_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) { struct device *dev = msi_desc_to_dev(desc); @@ -687,7 +687,7 @@ static void hidma_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) static void hidma_free_msis(struct hidma_dev *dmadev) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ struct device *dev = dmadev->ddev.dev; int i, virq; @@ -704,7 +704,7 @@ static void hidma_free_msis(struct hidma_dev *dmadev) static int hidma_request_msi(struct hidma_dev *dmadev, struct platform_device *pdev) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ int rc, i, virq; rc = platform_msi_domain_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS, diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index dc5f7a156ff5..8eaf9b72a995 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -389,7 +389,7 @@ config ARM_SMMU_V3 depends on ARM64 select IOMMU_API select IOMMU_IO_PGTABLE_LPAE - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Support for implementations of the ARM System MMU architecture version 3 providing translation support to a PCIe root complex. diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index 7ef9f5e696d3..ffea6a8ccece 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -38,7 +38,7 @@ config ARM_GIC_V3 config ARM_GIC_V3_ITS bool - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ default ARM_GIC_V3 config ARM_GIC_V3_ITS_PCI @@ -375,7 +375,7 @@ config MVEBU_ICU config MVEBU_ODMI bool - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ config MVEBU_PIC bool @@ -488,7 +488,7 @@ config IMX_MU_MSI default m if ARCH_MXC select IRQ_DOMAIN select IRQ_DOMAIN_HIERARCHY - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Provide a driver for the i.MX Messaging Unit block used as a CPU-to-CPU MSI controller. This requires a specially crafted DT diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index 05d6fae800e3..d7af896cbd7b 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -223,7 +223,7 @@ config BCM_FLEXRM_MBOX tristate "Broadcom FlexRM Mailbox" depends on ARM64 depends on ARCH_BCM_IPROC || COMPILE_TEST - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ default m if ARCH_BCM_IPROC help Mailbox implementation of the Broadcom FlexRM ring manager, diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index b7f62214668a..9309f2469b41 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -38,7 +38,6 @@ source "drivers/pci/pcie/Kconfig" config PCI_MSI bool "Message Signaled Interrupts (MSI and MSI-X)" - select GENERIC_MSI_IRQ_DOMAIN select GENERIC_MSI_IRQ help This allows device drivers to enable MSI (Message Signaled diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index 341010f20b77..692ffd56f5cc 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -93,7 +93,7 @@ config ARM_PMU_ACPI config ARM_SMMU_V3_PMU tristate "ARM SMMUv3 Performance Monitors Extension" depends on (ARM64 && ACPI) || (COMPILE_TEST && 64BIT) - depends on GENERIC_MSI_IRQ_DOMAIN + depends on GENERIC_MSI_IRQ help Provides support for the ARM SMMUv3 Performance Monitor Counter Groups (PMCG), which provide monitoring of transactions passing diff --git a/drivers/soc/ti/Kconfig b/drivers/soc/ti/Kconfig index 7e2fb1c16af1..e9a597e4bdc8 100644 --- a/drivers/soc/ti/Kconfig +++ b/drivers/soc/ti/Kconfig @@ -98,6 +98,6 @@ endif # SOC_TI config TI_SCI_INTA_MSI_DOMAIN bool - select GENERIC_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ help Driver to enable Interrupt Aggregator specific MSI Domain. diff --git a/include/asm-generic/msi.h b/include/asm-generic/msi.h index bf910d47e900..124c734ca5d9 100644 --- a/include/asm-generic/msi.h +++ b/include/asm-generic/msi.h @@ -4,7 +4,7 @@ #include -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ #ifndef NUM_MSI_ALLOC_SCRATCHPAD_REGS # define NUM_MSI_ALLOC_SCRATCHPAD_REGS 2 @@ -36,6 +36,6 @@ typedef struct msi_alloc_info { #define GENERIC_MSI_DOMAIN_OPS 1 -#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ +#endif /* CONFIG_GENERIC_MSI_IRQ */ #endif diff --git a/include/linux/device.h b/include/linux/device.h index 424b55df0272..c90a444be1c4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -378,10 +378,8 @@ struct dev_links_info { * @data: Pointer to MSI device data */ struct dev_msi_info { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - struct irq_domain *domain; -#endif #ifdef CONFIG_GENERIC_MSI_IRQ + struct irq_domain *domain; struct msi_device_data *data; #endif }; @@ -742,7 +740,7 @@ static inline void set_dev_node(struct device *dev, int node) static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ return dev->msi.domain; #else return NULL; @@ -751,7 +749,7 @@ static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ dev->msi.domain = d; #endif } diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 6aeea1071b1b..88ae4513abb5 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -27,7 +27,7 @@ struct gpio_chip; union gpio_irq_fwspec { struct irq_fwspec fwspec; -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ msi_alloc_info_t msiinfo; #endif }; diff --git a/include/linux/msi.h b/include/linux/msi.h index 9b8414523916..8b287148e512 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -79,9 +79,7 @@ void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); #ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); #else -static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) -{ -} +static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) { } #endif typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, @@ -278,7 +276,7 @@ static inline void msi_device_destroy_sysfs(struct device *dev) { } */ bool arch_restore_msi_irqs(struct pci_dev *dev); -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +#ifdef CONFIG_GENERIC_MSI_IRQ #include @@ -451,7 +449,7 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nvec); void *platform_msi_get_host_data(struct irq_domain *domain); -#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ +#endif /* CONFIG_GENERIC_MSI_IRQ */ /* PCI specific interfaces */ #ifdef CONFIG_PCI_MSI diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index db3d174c53d4..b64c44ae4c25 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -86,15 +86,10 @@ config GENERIC_IRQ_IPI depends on SMP select IRQ_DOMAIN_HIERARCHY -# Generic MSI interrupt support -config GENERIC_MSI_IRQ - bool - # Generic MSI hierarchical interrupt domain support -config GENERIC_MSI_IRQ_DOMAIN +config GENERIC_MSI_IRQ bool select IRQ_DOMAIN_HIERARCHY - select GENERIC_MSI_IRQ config IRQ_MSI_IOMMU bool diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index b46b74788087..4fde91703c9b 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -461,7 +461,6 @@ static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *d static inline void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { } #endif /* !CONFIG_SYSFS */ -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN static int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); static void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); @@ -1058,5 +1057,3 @@ struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain) { return (struct msi_domain_info *)domain->host_data; } - -#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ -- cgit v1.2.3 From db537dd3bf83169d78e5617b75158f64deabcb0b Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:42 +0100 Subject: PCI/MSI: Get rid of externs in msi.h Follow the style of Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.582175082@linutronix.de --- drivers/pci/msi/msi.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index dbeff066bedd..fc92603b33e1 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -5,12 +5,12 @@ #define msix_table_size(flags) ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) -extern int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -extern void pci_msi_teardown_msi_irqs(struct pci_dev *dev); +int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +void pci_msi_teardown_msi_irqs(struct pci_dev *dev); #ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS -extern int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -extern void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); +int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); #else static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { -- cgit v1.2.3 From c93fd5266cff2afa908659c817c6aff4d5ed6283 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:43 +0100 Subject: PCI/MSI: Move mask and unmask helpers to msi.h The upcoming support for per device MSI interrupt domains needs to share some of the inline helpers with the MSI implementation. Move them to the header file. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.640052354@linutronix.de --- drivers/pci/msi/msi.c | 61 +------------------------------------ drivers/pci/msi/msi.h | 83 ++++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 74 insertions(+), 70 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 160af9f01669..5c310df55d0d 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -16,7 +16,7 @@ static int pci_msi_enable = 1; int pci_msi_ignore_mask; -static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) +void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) { raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock; unsigned long flags; @@ -32,65 +32,6 @@ static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 s raw_spin_unlock_irqrestore(lock, flags); } -static inline void pci_msi_mask(struct msi_desc *desc, u32 mask) -{ - pci_msi_update_mask(desc, 0, mask); -} - -static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask) -{ - pci_msi_update_mask(desc, mask, 0); -} - -static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc) -{ - return desc->pci.mask_base + desc->msi_index * PCI_MSIX_ENTRY_SIZE; -} - -/* - * This internal function does not flush PCI writes to the device. All - * users must ensure that they read from the device before either assuming - * that the device state is up to date, or returning out of this file. - * It does not affect the msi_desc::msix_ctrl cache either. Use with care! - */ -static void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl) -{ - void __iomem *desc_addr = pci_msix_desc_addr(desc); - - if (desc->pci.msi_attrib.can_mask) - writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); -} - -static inline void pci_msix_mask(struct msi_desc *desc) -{ - desc->pci.msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT; - pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); - /* Flush write to device */ - readl(desc->pci.mask_base); -} - -static inline void pci_msix_unmask(struct msi_desc *desc) -{ - desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; - pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); -} - -static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask) -{ - if (desc->pci.msi_attrib.is_msix) - pci_msix_mask(desc); - else - pci_msi_mask(desc, mask); -} - -static void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask) -{ - if (desc->pci.msi_attrib.is_msix) - pci_msix_unmask(desc); - else - pci_msi_unmask(desc, mask); -} - /** * pci_msi_mask_irq - Generic IRQ chip callback to mask PCI/MSI interrupts * @data: pointer to irqdata associated to that interrupt diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index fc92603b33e1..d8f62d911f08 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -8,21 +8,67 @@ int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void pci_msi_teardown_msi_irqs(struct pci_dev *dev); -#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS -int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); -#else -static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +/* Mask/unmask helpers */ +void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set); + +static inline void pci_msi_mask(struct msi_desc *desc, u32 mask) { - WARN_ON_ONCE(1); - return -ENODEV; + pci_msi_update_mask(desc, 0, mask); } -static inline void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) +static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask) { - WARN_ON_ONCE(1); + pci_msi_update_mask(desc, mask, 0); +} + +static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc) +{ + return desc->pci.mask_base + desc->msi_index * PCI_MSIX_ENTRY_SIZE; +} + +/* + * This internal function does not flush PCI writes to the device. All + * users must ensure that they read from the device before either assuming + * that the device state is up to date, or returning out of this file. + * It does not affect the msi_desc::msix_ctrl cache either. Use with care! + */ +static inline void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl) +{ + void __iomem *desc_addr = pci_msix_desc_addr(desc); + + if (desc->pci.msi_attrib.can_mask) + writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); +} + +static inline void pci_msix_mask(struct msi_desc *desc) +{ + desc->pci.msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT; + pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); + /* Flush write to device */ + readl(desc->pci.mask_base); +} + +static inline void pci_msix_unmask(struct msi_desc *desc) +{ + desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; + pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); +} + +static inline void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask) +{ + if (desc->pci.msi_attrib.is_msix) + pci_msix_mask(desc); + else + pci_msi_mask(desc, mask); +} + +static inline void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask) +{ + if (desc->pci.msi_attrib.is_msix) + pci_msix_unmask(desc); + else + pci_msi_unmask(desc, mask); } -#endif /* * PCI 2.3 does not specify mask bits for each MSI interrupt. Attempting to @@ -37,3 +83,20 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) return 0xffffffff; return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; } + +/* Legacy (!IRQDOMAIN) fallbacks */ +#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS +int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); +#else +static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + WARN_ON_ONCE(1); + return -ENODEV; +} + +static inline void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) +{ + WARN_ON_ONCE(1); +} +#endif -- cgit v1.2.3 From b12d0bec385b7a58b9e83751e6cd9f04ec3b23a4 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:45 +0100 Subject: PCI/MSI: Move pci_disable_msi() to api.c msi.c is a maze of randomly sorted functions which makes the code unreadable. As a first step split the driver visible API and the internal implementation which also allows proper API documentation via one file. Create drivers/pci/msi/api.c to group all exported device-driver PCI/MSI APIs in one C file. Begin by moving pci_disable_msi() there and add kernel-doc for the function as appropriate. Suggested-by: Thomas Gleixner Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.696798036@linutronix.de --- drivers/pci/msi/Makefile | 3 +-- drivers/pci/msi/api.c | 37 +++++++++++++++++++++++++++++++++++++ drivers/pci/msi/msi.c | 22 +++++----------------- drivers/pci/msi/msi.h | 4 ++++ 4 files changed, 47 insertions(+), 19 deletions(-) create mode 100644 drivers/pci/msi/api.c (limited to 'drivers/pci') diff --git a/drivers/pci/msi/Makefile b/drivers/pci/msi/Makefile index 4e0a7e07965e..839ff72d72a8 100644 --- a/drivers/pci/msi/Makefile +++ b/drivers/pci/msi/Makefile @@ -2,6 +2,5 @@ # # Makefile for the PCI/MSI obj-$(CONFIG_PCI) += pcidev_msi.o -obj-$(CONFIG_PCI_MSI) += msi.o -obj-$(CONFIG_PCI_MSI) += irqdomain.o +obj-$(CONFIG_PCI_MSI) += api.o msi.o irqdomain.o obj-$(CONFIG_PCI_MSI_ARCH_FALLBACKS) += legacy.o diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c new file mode 100644 index 000000000000..7485942cbe5d --- /dev/null +++ b/drivers/pci/msi/api.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI MSI/MSI-X — Exported APIs for device drivers + * + * Copyright (C) 2003-2004 Intel + * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com) + * Copyright (C) 2016 Christoph Hellwig. + * Copyright (C) 2022 Linutronix GmbH + */ + +#include + +#include "msi.h" + +/** + * pci_disable_msi() - Disable MSI interrupt mode on device + * @dev: the PCI device to operate on + * + * Legacy device driver API to disable MSI interrupt mode on device, + * free earlier allocated interrupt vectors, and restore INTx emulation. + * The PCI device Linux IRQ (@dev->irq) is restored to its default + * pin-assertion IRQ. This is the cleanup pair of pci_enable_msi(). + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + */ +void pci_disable_msi(struct pci_dev *dev) +{ + if (!pci_msi_enabled() || !dev || !dev->msi_enabled) + return; + + msi_lock_descs(&dev->dev); + pci_msi_shutdown(dev); + pci_free_msi_irqs(dev); + msi_unlock_descs(&dev->dev); +} +EXPORT_SYMBOL(pci_disable_msi); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 5c310df55d0d..4a1300b74518 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -163,7 +163,7 @@ void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) } EXPORT_SYMBOL_GPL(pci_write_msi_msg); -static void free_msi_irqs(struct pci_dev *dev) +void pci_free_msi_irqs(struct pci_dev *dev) { pci_msi_teardown_msi_irqs(dev); @@ -413,7 +413,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, err: pci_msi_unmask(entry, msi_multi_mask(entry)); - free_msi_irqs(dev); + pci_free_msi_irqs(dev); fail: dev->msi_enabled = 0; unlock: @@ -531,7 +531,7 @@ static int msix_setup_interrupts(struct pci_dev *dev, void __iomem *base, goto out_unlock; out_free: - free_msi_irqs(dev); + pci_free_msi_irqs(dev); out_unlock: msi_unlock_descs(&dev->dev); kfree(masks); @@ -680,7 +680,7 @@ int pci_msi_vec_count(struct pci_dev *dev) } EXPORT_SYMBOL(pci_msi_vec_count); -static void pci_msi_shutdown(struct pci_dev *dev) +void pci_msi_shutdown(struct pci_dev *dev) { struct msi_desc *desc; @@ -701,18 +701,6 @@ static void pci_msi_shutdown(struct pci_dev *dev) pcibios_alloc_irq(dev); } -void pci_disable_msi(struct pci_dev *dev) -{ - if (!pci_msi_enable || !dev || !dev->msi_enabled) - return; - - msi_lock_descs(&dev->dev); - pci_msi_shutdown(dev); - free_msi_irqs(dev); - msi_unlock_descs(&dev->dev); -} -EXPORT_SYMBOL(pci_disable_msi); - /** * pci_msix_vec_count - return the number of device's MSI-X table entries * @dev: pointer to the pci_dev data structure of MSI-X device function @@ -797,7 +785,7 @@ void pci_disable_msix(struct pci_dev *dev) msi_lock_descs(&dev->dev); pci_msix_shutdown(dev); - free_msi_irqs(dev); + pci_free_msi_irqs(dev); msi_unlock_descs(&dev->dev); } EXPORT_SYMBOL(pci_disable_msix); diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index d8f62d911f08..634879277349 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -84,6 +84,10 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; } +/* MSI internal functions invoked from the public APIs */ +void pci_msi_shutdown(struct pci_dev *dev); +void pci_free_msi_irqs(struct pci_dev *dev); + /* Legacy (!IRQDOMAIN) fallbacks */ #ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); -- cgit v1.2.3 From bbda3407982211123caadbfdee23594647bd4516 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:46 +0100 Subject: PCI/MSI: Move pci_enable_msi() API to api.c To disentangle the maze in msi.c all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_enable_msi() and make its kernel-doc comprehensive. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.755178149@linutronix.de --- drivers/pci/msi/api.c | 23 +++++++++++++++++++++++ drivers/pci/msi/msi.c | 14 ++------------ drivers/pci/msi/msi.h | 1 + 3 files changed, 26 insertions(+), 12 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 7485942cbe5d..63d7f8f6a284 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -12,6 +12,29 @@ #include "msi.h" +/** + * pci_enable_msi() - Enable MSI interrupt mode on device + * @dev: the PCI device to operate on + * + * Legacy device driver API to enable MSI interrupts mode on device and + * allocate a single interrupt vector. On success, the allocated vector + * Linux IRQ will be saved at @dev->irq. The driver must invoke + * pci_disable_msi() on cleanup. + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + * + * Return: 0 on success, errno otherwise + */ +int pci_enable_msi(struct pci_dev *dev) +{ + int rc = __pci_enable_msi_range(dev, 1, 1, NULL); + if (rc < 0) + return rc; + return 0; +} +EXPORT_SYMBOL(pci_enable_msi); + /** * pci_disable_msi() - Disable MSI interrupt mode on device * @dev: the PCI device to operate on diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 4a1300b74518..98f07ad9af62 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -790,8 +790,8 @@ void pci_disable_msix(struct pci_dev *dev) } EXPORT_SYMBOL(pci_disable_msix); -static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, - struct irq_affinity *affd) +int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, + struct irq_affinity *affd) { int nvec; int rc; @@ -844,16 +844,6 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, } } -/* deprecated, don't use */ -int pci_enable_msi(struct pci_dev *dev) -{ - int rc = __pci_enable_msi_range(dev, 1, 1, NULL); - if (rc < 0) - return rc; - return 0; -} -EXPORT_SYMBOL(pci_enable_msi); - static int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec, struct irq_affinity *affd, diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index 634879277349..00bb98d5bb0e 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -87,6 +87,7 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) /* MSI internal functions invoked from the public APIs */ void pci_msi_shutdown(struct pci_dev *dev); void pci_free_msi_irqs(struct pci_dev *dev); +int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd); /* Legacy (!IRQDOMAIN) fallbacks */ #ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS -- cgit v1.2.3 From be7496c1ef47e1ba8c4b389ee23178fcf066cc4e Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:48 +0100 Subject: PCI/MSI: Move pci_enable_msix_range() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_enable_msix_range() and make its kernel-doc comprehensive. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.813792885@linutronix.de --- drivers/pci/msi/api.c | 32 ++++++++++++++++++++++++++++++++ drivers/pci/msi/msi.c | 30 ++++-------------------------- drivers/pci/msi/msi.h | 3 +++ 3 files changed, 39 insertions(+), 26 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 63d7f8f6a284..d48050555d55 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -58,3 +58,35 @@ void pci_disable_msi(struct pci_dev *dev) msi_unlock_descs(&dev->dev); } EXPORT_SYMBOL(pci_disable_msi); + +/** + * pci_enable_msix_range() - Enable MSI-X interrupt mode on device + * @dev: the PCI device to operate on + * @entries: input/output parameter, array of MSI-X configuration entries + * @minvec: minimum required number of MSI-X vectors + * @maxvec: maximum desired number of MSI-X vectors + * + * Legacy device driver API to enable MSI-X interrupt mode on device and + * configure its MSI-X capability structure as appropriate. The passed + * @entries array must have each of its members "entry" field set to a + * desired (valid) MSI-X vector number, where the range of valid MSI-X + * vector numbers can be queried through pci_msix_vec_count(). If + * successful, the driver must invoke pci_disable_msix() on cleanup. + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + * + * Return: number of MSI-X vectors allocated (which might be smaller + * than @maxvecs), where Linux IRQ numbers for such allocated vectors + * are saved back in the @entries array elements' "vector" field. Return + * -ENOSPC if less than @minvecs interrupt vectors are available. + * Return -EINVAL if one of the passed @entries members "entry" field + * was invalid or a duplicate, or if plain MSI interrupts mode was + * earlier enabled on device. Return other errnos otherwise. + */ +int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, + int minvec, int maxvec) +{ + return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0); +} +EXPORT_SYMBOL(pci_enable_msix_range); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 98f07ad9af62..6700ef1c734e 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -844,10 +844,10 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, } } -static int __pci_enable_msix_range(struct pci_dev *dev, - struct msix_entry *entries, int minvec, - int maxvec, struct irq_affinity *affd, - int flags) +int __pci_enable_msix_range(struct pci_dev *dev, + struct msix_entry *entries, int minvec, + int maxvec, struct irq_affinity *affd, + int flags) { int rc, nvec = maxvec; @@ -886,28 +886,6 @@ static int __pci_enable_msix_range(struct pci_dev *dev, } } -/** - * pci_enable_msix_range - configure device's MSI-X capability structure - * @dev: pointer to the pci_dev data structure of MSI-X device function - * @entries: pointer to an array of MSI-X entries - * @minvec: minimum number of MSI-X IRQs requested - * @maxvec: maximum number of MSI-X IRQs requested - * - * Setup the MSI-X capability structure of device function with a maximum - * possible number of interrupts in the range between @minvec and @maxvec - * upon its software driver call to request for MSI-X mode enabled on its - * hardware device function. It returns a negative errno if an error occurs. - * If it succeeds, it returns the actual number of interrupts allocated and - * indicates the successful configuration of MSI-X capability structure - * with new allocated MSI-X interrupts. - **/ -int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, - int minvec, int maxvec) -{ - return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0); -} -EXPORT_SYMBOL(pci_enable_msix_range); - /** * pci_alloc_irq_vectors_affinity - allocate multiple IRQs for a device * @dev: PCI device to operate on diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index 00bb98d5bb0e..8c4a5289432d 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -88,8 +88,11 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) void pci_msi_shutdown(struct pci_dev *dev); void pci_free_msi_irqs(struct pci_dev *dev); int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd); +int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, + int maxvec, struct irq_affinity *affd, int flags); /* Legacy (!IRQDOMAIN) fallbacks */ + #ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); -- cgit v1.2.3 From 5c0997dc33ac24b7dc0124c2fc1caa37ae39461a Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:50 +0100 Subject: PCI/MSI: Move pci_alloc_irq_vectors() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Make pci_alloc_irq_vectors() a real function instead of wrapper and add proper kernel doc to it. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.870888193@linutronix.de --- drivers/pci/msi/api.c | 33 +++++++++++++++++++++++++++++++++ include/linux/pci.h | 15 +++++++++++---- 2 files changed, 44 insertions(+), 4 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index d48050555d55..1714905943fb 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -90,3 +90,36 @@ int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0); } EXPORT_SYMBOL(pci_enable_msix_range); + +/** + * pci_alloc_irq_vectors() - Allocate multiple device interrupt vectors + * @dev: the PCI device to operate on + * @min_vecs: minimum required number of vectors (must be >= 1) + * @max_vecs: maximum desired number of vectors + * @flags: One or more of: + * %PCI_IRQ_MSIX Allow trying MSI-X vector allocations + * %PCI_IRQ_MSI Allow trying MSI vector allocations + * %PCI_IRQ_LEGACY Allow trying legacy INTx interrupts, if + * and only if @min_vecs == 1 + * %PCI_IRQ_AFFINITY Auto-manage IRQs affinity by spreading + * the vectors around available CPUs + * + * Allocate up to @max_vecs interrupt vectors on device. MSI-X irq + * vector allocation has a higher precedence over plain MSI, which has a + * higher precedence over legacy INTx emulation. + * + * Upon a successful allocation, the caller should use pci_irq_vector() + * to get the Linux IRQ number to be passed to request_threaded_irq(). + * The driver must call pci_free_irq_vectors() on cleanup. + * + * Return: number of allocated vectors (which might be smaller than + * @max_vecs), -ENOSPC if less than @min_vecs interrupt vectors are + * available, other errnos otherwise. + */ +int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags) +{ + return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs, + flags, NULL); +} +EXPORT_SYMBOL(pci_alloc_irq_vectors); diff --git a/include/linux/pci.h b/include/linux/pci.h index 2bda4a4e47e8..243e48f79e82 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1553,6 +1553,8 @@ static inline int pci_enable_msix_exact(struct pci_dev *dev, return rc; return 0; } +int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags); int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags, struct irq_affinity *affd); @@ -1586,6 +1588,13 @@ pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, return 1; return -ENOSPC; } +static inline int +pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags) +{ + return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs, + flags, NULL); +} static inline void pci_free_irq_vectors(struct pci_dev *dev) { @@ -1898,15 +1907,13 @@ pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, { return -ENOSPC; } -#endif /* CONFIG_PCI */ - static inline int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags) { - return pci_alloc_irq_vectors_affinity(dev, min_vecs, max_vecs, flags, - NULL); + return -ENOSPC; } +#endif /* CONFIG_PCI */ /* Include architecture-dependent settings and functions */ -- cgit v1.2.3 From beddb5efb43ee5b1c048e49225f75b03f8d36aac Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:51 +0100 Subject: PCI/MSI: Move pci_alloc_irq_vectors_affinity() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_alloc_irq_vectors_affinity() and let its kernel-doc reference pci_alloc_irq_vectors() documentation added in parent commit. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.927531290@linutronix.de --- drivers/pci/msi/api.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/msi/msi.c | 65 --------------------------------------------------- 2 files changed, 59 insertions(+), 65 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 1714905943fb..8546749afa6e 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -123,3 +123,62 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, flags, NULL); } EXPORT_SYMBOL(pci_alloc_irq_vectors); + +/** + * pci_alloc_irq_vectors_affinity() - Allocate multiple device interrupt + * vectors with affinity requirements + * @dev: the PCI device to operate on + * @min_vecs: minimum required number of vectors (must be >= 1) + * @max_vecs: maximum desired number of vectors + * @flags: allocation flags, as in pci_alloc_irq_vectors() + * @affd: affinity requirements (can be %NULL). + * + * Same as pci_alloc_irq_vectors(), but with the extra @affd parameter. + * Check that function docs, and &struct irq_affinity, for more details. + */ +int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, + unsigned int max_vecs, unsigned int flags, + struct irq_affinity *affd) +{ + struct irq_affinity msi_default_affd = {0}; + int nvecs = -ENOSPC; + + if (flags & PCI_IRQ_AFFINITY) { + if (!affd) + affd = &msi_default_affd; + } else { + if (WARN_ON(affd)) + affd = NULL; + } + + if (flags & PCI_IRQ_MSIX) { + nvecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, + affd, flags); + if (nvecs > 0) + return nvecs; + } + + if (flags & PCI_IRQ_MSI) { + nvecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, affd); + if (nvecs > 0) + return nvecs; + } + + /* use legacy IRQ if allowed */ + if (flags & PCI_IRQ_LEGACY) { + if (min_vecs == 1 && dev->irq) { + /* + * Invoke the affinity spreading logic to ensure that + * the device driver can adjust queue configuration + * for the single interrupt case. + */ + if (affd) + irq_create_affinity_masks(1, affd); + pci_intx(dev, 1); + return 1; + } + } + + return nvecs; +} +EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 6700ef1c734e..a028774f438d 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -886,71 +886,6 @@ int __pci_enable_msix_range(struct pci_dev *dev, } } -/** - * pci_alloc_irq_vectors_affinity - allocate multiple IRQs for a device - * @dev: PCI device to operate on - * @min_vecs: minimum number of vectors required (must be >= 1) - * @max_vecs: maximum (desired) number of vectors - * @flags: flags or quirks for the allocation - * @affd: optional description of the affinity requirements - * - * Allocate up to @max_vecs interrupt vectors for @dev, using MSI-X or MSI - * vectors if available, and fall back to a single legacy vector - * if neither is available. Return the number of vectors allocated, - * (which might be smaller than @max_vecs) if successful, or a negative - * error code on error. If less than @min_vecs interrupt vectors are - * available for @dev the function will fail with -ENOSPC. - * - * To get the Linux IRQ number used for a vector that can be passed to - * request_irq() use the pci_irq_vector() helper. - */ -int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, - unsigned int max_vecs, unsigned int flags, - struct irq_affinity *affd) -{ - struct irq_affinity msi_default_affd = {0}; - int nvecs = -ENOSPC; - - if (flags & PCI_IRQ_AFFINITY) { - if (!affd) - affd = &msi_default_affd; - } else { - if (WARN_ON(affd)) - affd = NULL; - } - - if (flags & PCI_IRQ_MSIX) { - nvecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, - affd, flags); - if (nvecs > 0) - return nvecs; - } - - if (flags & PCI_IRQ_MSI) { - nvecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, affd); - if (nvecs > 0) - return nvecs; - } - - /* use legacy IRQ if allowed */ - if (flags & PCI_IRQ_LEGACY) { - if (min_vecs == 1 && dev->irq) { - /* - * Invoke the affinity spreading logic to ensure that - * the device driver can adjust queue configuration - * for the single interrupt case. - */ - if (affd) - irq_create_affinity_masks(1, affd); - pci_intx(dev, 1); - return 1; - } - } - - return nvecs; -} -EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity); - /** * pci_free_irq_vectors - free previously allocated IRQs for a device * @dev: PCI device to operate on -- cgit v1.2.3 From 017239c8db209307d2acfc0f9a3b104c39f911b3 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:53 +0100 Subject: PCI/MSI: Move pci_irq_vector() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_irq_vector() and let its kernel-doc match the rest of the file. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122014.984490384@linutronix.de --- drivers/pci/msi/api.c | 23 +++++++++++++++++++++++ drivers/pci/msi/msi.c | 24 ------------------------ 2 files changed, 23 insertions(+), 24 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 8546749afa6e..0f1ec87e3f9f 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -182,3 +182,26 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, return nvecs; } EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity); + +/** + * pci_irq_vector() - Get Linux IRQ number of a device interrupt vector + * @dev: the PCI device to operate on + * @nr: device-relative interrupt vector index (0-based); has different + * meanings, depending on interrupt mode + * MSI-X the index in the MSI-X vector table + * MSI the index of the enabled MSI vectors + * INTx must be 0 + * + * Return: the Linux IRQ number, or -EINVAL if @nr is out of range + */ +int pci_irq_vector(struct pci_dev *dev, unsigned int nr) +{ + unsigned int irq; + + if (!dev->msi_enabled && !dev->msix_enabled) + return !nr ? dev->irq : -EINVAL; + + irq = msi_get_virq(&dev->dev, nr); + return irq ? irq : -EINVAL; +} +EXPORT_SYMBOL(pci_irq_vector); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index a028774f438d..38ad2fe4b85c 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -899,30 +899,6 @@ void pci_free_irq_vectors(struct pci_dev *dev) } EXPORT_SYMBOL(pci_free_irq_vectors); -/** - * pci_irq_vector - return Linux IRQ number of a device vector - * @dev: PCI device to operate on - * @nr: Interrupt vector index (0-based) - * - * @nr has the following meanings depending on the interrupt mode: - * MSI-X: The index in the MSI-X vector table - * MSI: The index of the enabled MSI vectors - * INTx: Must be 0 - * - * Return: The Linux interrupt number or -EINVAl if @nr is out of range. - */ -int pci_irq_vector(struct pci_dev *dev, unsigned int nr) -{ - unsigned int irq; - - if (!dev->msi_enabled && !dev->msix_enabled) - return !nr ? dev->irq : -EINVAL; - - irq = msi_get_virq(&dev->dev, nr); - return irq ? irq : -EINVAL; -} -EXPORT_SYMBOL(pci_irq_vector); - /** * pci_irq_get_affinity - return the affinity of a particular MSI vector * @dev: PCI device to operate on -- cgit v1.2.3 From 059f778d66ba88e1acad89a46cfb35eb8703feef Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:54 +0100 Subject: PCI/MSI: Move pci_free_irq_vectors() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_free_irq_vectors() and make its kernel-doc comprehensive. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.042870570@linutronix.de --- drivers/pci/msi/api.c | 15 +++++++++++++++ drivers/pci/msi/msi.c | 13 ------------- 2 files changed, 15 insertions(+), 13 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 0f1ec87e3f9f..2ff2a9ccfc47 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -205,3 +205,18 @@ int pci_irq_vector(struct pci_dev *dev, unsigned int nr) return irq ? irq : -EINVAL; } EXPORT_SYMBOL(pci_irq_vector); + +/** + * pci_free_irq_vectors() - Free previously allocated IRQs for a device + * @dev: the PCI device to operate on + * + * Undo the interrupt vector allocations and possible device MSI/MSI-X + * enablement earlier done through pci_alloc_irq_vectors_affinity() or + * pci_alloc_irq_vectors(). + */ +void pci_free_irq_vectors(struct pci_dev *dev) +{ + pci_disable_msix(dev); + pci_disable_msi(dev); +} +EXPORT_SYMBOL(pci_free_irq_vectors); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 38ad2fe4b85c..ed8caf5ac99f 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -886,19 +886,6 @@ int __pci_enable_msix_range(struct pci_dev *dev, } } -/** - * pci_free_irq_vectors - free previously allocated IRQs for a device - * @dev: PCI device to operate on - * - * Undoes the allocations and enabling in pci_alloc_irq_vectors(). - */ -void pci_free_irq_vectors(struct pci_dev *dev) -{ - pci_disable_msix(dev); - pci_disable_msi(dev); -} -EXPORT_SYMBOL(pci_free_irq_vectors); - /** * pci_irq_get_affinity - return the affinity of a particular MSI vector * @dev: PCI device to operate on -- cgit v1.2.3 From 7b50f62776672e7b328455eddc90ceb01b64ac3e Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:56 +0100 Subject: PCI/MSI: Move pci_msix_vec_count() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_msix_vec_count() and make its kernel-doc comprehensive. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.099461602@linutronix.de --- drivers/pci/msi/api.c | 20 ++++++++++++++++++++ drivers/pci/msi/msi.c | 20 -------------------- 2 files changed, 20 insertions(+), 20 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 2ff2a9ccfc47..83ea38ffa116 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -59,6 +59,26 @@ void pci_disable_msi(struct pci_dev *dev) } EXPORT_SYMBOL(pci_disable_msi); +/** + * pci_msix_vec_count() - Get number of MSI-X interrupt vectors on device + * @dev: the PCI device to operate on + * + * Return: number of MSI-X interrupt vectors available on this device + * (i.e., the device's MSI-X capability structure "table size"), -EINVAL + * if the device is not MSI-X capable, other errnos otherwise. + */ +int pci_msix_vec_count(struct pci_dev *dev) +{ + u16 control; + + if (!dev->msix_cap) + return -EINVAL; + + pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); + return msix_table_size(control); +} +EXPORT_SYMBOL(pci_msix_vec_count); + /** * pci_enable_msix_range() - Enable MSI-X interrupt mode on device * @dev: the PCI device to operate on diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index ed8caf5ac99f..1226d66da992 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -701,26 +701,6 @@ void pci_msi_shutdown(struct pci_dev *dev) pcibios_alloc_irq(dev); } -/** - * pci_msix_vec_count - return the number of device's MSI-X table entries - * @dev: pointer to the pci_dev data structure of MSI-X device function - * This function returns the number of device's MSI-X table entries and - * therefore the number of MSI-X vectors device is capable of sending. - * It returns a negative errno if the device is not capable of sending MSI-X - * interrupts. - **/ -int pci_msix_vec_count(struct pci_dev *dev) -{ - u16 control; - - if (!dev->msix_cap) - return -EINVAL; - - pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); - return msix_table_size(control); -} -EXPORT_SYMBOL(pci_msix_vec_count); - static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd, int flags) { -- cgit v1.2.3 From 18e1926b8c8b7c2249c24057d5f836c578e29f08 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:58 +0100 Subject: PCI/MSI: Move pci_disable_msix() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_disable_msix() and make its kernel-doc comprehensive. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.156785224@linutronix.de --- drivers/pci/msi/api.c | 24 ++++++++++++++++++++++++ drivers/pci/msi/msi.c | 14 +------------- drivers/pci/msi/msi.h | 1 + 3 files changed, 26 insertions(+), 13 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 83ea38ffa116..20a580bea48f 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -111,6 +111,30 @@ int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, } EXPORT_SYMBOL(pci_enable_msix_range); +/** + * pci_disable_msix() - Disable MSI-X interrupt mode on device + * @dev: the PCI device to operate on + * + * Legacy device driver API to disable MSI-X interrupt mode on device, + * free earlier-allocated interrupt vectors, and restore INTx. + * The PCI device Linux IRQ (@dev->irq) is restored to its default pin + * assertion IRQ. This is the cleanup pair of pci_enable_msix_range(). + * + * NOTE: The newer pci_alloc_irq_vectors() / pci_free_irq_vectors() API + * pair should, in general, be used instead. + */ +void pci_disable_msix(struct pci_dev *dev) +{ + if (!pci_msi_enabled() || !dev || !dev->msix_enabled) + return; + + msi_lock_descs(&dev->dev); + pci_msix_shutdown(dev); + pci_free_msi_irqs(dev); + msi_unlock_descs(&dev->dev); +} +EXPORT_SYMBOL(pci_disable_msix); + /** * pci_alloc_irq_vectors() - Allocate multiple device interrupt vectors * @dev: the PCI device to operate on diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 1226d66da992..6fa90d07d2e4 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -736,7 +736,7 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, return msix_capability_init(dev, entries, nvec, affd); } -static void pci_msix_shutdown(struct pci_dev *dev) +void pci_msix_shutdown(struct pci_dev *dev) { struct msi_desc *desc; @@ -758,18 +758,6 @@ static void pci_msix_shutdown(struct pci_dev *dev) pcibios_alloc_irq(dev); } -void pci_disable_msix(struct pci_dev *dev) -{ - if (!pci_msi_enable || !dev || !dev->msix_enabled) - return; - - msi_lock_descs(&dev->dev); - pci_msix_shutdown(dev); - pci_free_msi_irqs(dev); - msi_unlock_descs(&dev->dev); -} -EXPORT_SYMBOL(pci_disable_msix); - int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd) { diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index 8c4a5289432d..77e2587f7e4f 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -86,6 +86,7 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) /* MSI internal functions invoked from the public APIs */ void pci_msi_shutdown(struct pci_dev *dev); +void pci_msix_shutdown(struct pci_dev *dev); void pci_free_msi_irqs(struct pci_dev *dev); int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd); int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, -- cgit v1.2.3 From be37b8428b7b7740bbbc29c17cfa2ee42b9e2d8b Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:54:59 +0100 Subject: PCI/MSI: Move pci_irq_get_affinity() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_irq_get_affinity() and let its kernel-doc match rest of the file. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.214792769@linutronix.de --- drivers/pci/msi/api.c | 43 +++++++++++++++++++++++++++++++++++++++++++ drivers/pci/msi/msi.c | 38 -------------------------------------- 2 files changed, 43 insertions(+), 38 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 20a580bea48f..93ddc5570693 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -9,6 +9,7 @@ */ #include +#include #include "msi.h" @@ -250,6 +251,48 @@ int pci_irq_vector(struct pci_dev *dev, unsigned int nr) } EXPORT_SYMBOL(pci_irq_vector); +/** + * pci_irq_get_affinity() - Get a device interrupt vector affinity + * @dev: the PCI device to operate on + * @nr: device-relative interrupt vector index (0-based); has different + * meanings, depending on interrupt mode + * MSI-X the index in the MSI-X vector table + * MSI the index of the enabled MSI vectors + * INTx must be 0 + * + * Return: MSI/MSI-X vector affinity, NULL if @nr is out of range or if + * the MSI(-X) vector was allocated without explicit affinity + * requirements (e.g., by pci_enable_msi(), pci_enable_msix_range(), or + * pci_alloc_irq_vectors() without the %PCI_IRQ_AFFINITY flag). Return a + * generic set of CPU IDs representing all possible CPUs available + * during system boot if the device is in legacy INTx mode. + */ +const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) +{ + int idx, irq = pci_irq_vector(dev, nr); + struct msi_desc *desc; + + if (WARN_ON_ONCE(irq <= 0)) + return NULL; + + desc = irq_get_msi_desc(irq); + /* Non-MSI does not have the information handy */ + if (!desc) + return cpu_possible_mask; + + /* MSI[X] interrupts can be allocated without affinity descriptor */ + if (!desc->affinity) + return NULL; + + /* + * MSI has a mask array in the descriptor. + * MSI-X has a single mask. + */ + idx = dev->msi_enabled ? nr : 0; + return &desc->affinity[idx].mask; +} +EXPORT_SYMBOL(pci_irq_get_affinity); + /** * pci_free_irq_vectors() - Free previously allocated IRQs for a device * @dev: the PCI device to operate on diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 6fa90d07d2e4..d78646d1c116 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -854,44 +854,6 @@ int __pci_enable_msix_range(struct pci_dev *dev, } } -/** - * pci_irq_get_affinity - return the affinity of a particular MSI vector - * @dev: PCI device to operate on - * @nr: device-relative interrupt vector index (0-based). - * - * @nr has the following meanings depending on the interrupt mode: - * MSI-X: The index in the MSI-X vector table - * MSI: The index of the enabled MSI vectors - * INTx: Must be 0 - * - * Return: A cpumask pointer or NULL if @nr is out of range - */ -const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) -{ - int idx, irq = pci_irq_vector(dev, nr); - struct msi_desc *desc; - - if (WARN_ON_ONCE(irq <= 0)) - return NULL; - - desc = irq_get_msi_desc(irq); - /* Non-MSI does not have the information handy */ - if (!desc) - return cpu_possible_mask; - - /* MSI[X] interrupts can be allocated without affinity descriptor */ - if (!desc->affinity) - return NULL; - - /* - * MSI has a mask array in the descriptor. - * MSI-X has a single mask. - */ - idx = dev->msi_enabled ? nr : 0; - return &desc->affinity[idx].mask; -} -EXPORT_SYMBOL(pci_irq_get_affinity); - struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) { return to_pci_dev(desc->dev); -- cgit v1.2.3 From 897a0b6aa8c7ee0015e8d1f781e8e61069aafe16 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:55:01 +0100 Subject: PCI/MSI: Move pci_msi_enabled() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_msi_enabled() and make its kernel-doc comprehensive. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.271447896@linutronix.de --- drivers/pci/msi/api.c | 12 ++++++++++++ drivers/pci/msi/msi.c | 14 +------------- drivers/pci/msi/msi.h | 3 +++ 3 files changed, 16 insertions(+), 13 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 93ddc5570693..49ae3a3f8282 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -307,3 +307,15 @@ void pci_free_irq_vectors(struct pci_dev *dev) pci_disable_msi(dev); } EXPORT_SYMBOL(pci_free_irq_vectors); + +/** + * pci_msi_enabled() - Are MSI(-X) interrupts enabled system-wide? + * + * Return: true if MSI has not been globally disabled through ACPI FADT, + * PCI bridge quirks, or the "pci=nomsi" kernel command-line option. + */ +int pci_msi_enabled(void) +{ + return pci_msi_enable; +} +EXPORT_SYMBOL(pci_msi_enabled); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index d78646d1c116..59c33bc7fe81 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -13,7 +13,7 @@ #include "../pci.h" #include "msi.h" -static int pci_msi_enable = 1; +int pci_msi_enable = 1; int pci_msi_ignore_mask; void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) @@ -864,15 +864,3 @@ void pci_no_msi(void) { pci_msi_enable = 0; } - -/** - * pci_msi_enabled - is MSI enabled? - * - * Returns true if MSI has not been disabled by the command-line option - * pci=nomsi. - **/ -int pci_msi_enabled(void) -{ - return pci_msi_enable; -} -EXPORT_SYMBOL(pci_msi_enabled); diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index 77e2587f7e4f..f3f4ede53171 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -84,6 +84,9 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; } +/* Subsystem variables */ +extern int pci_msi_enable; + /* MSI internal functions invoked from the public APIs */ void pci_msi_shutdown(struct pci_dev *dev); void pci_msix_shutdown(struct pci_dev *dev); -- cgit v1.2.3 From 57127da98bc87688324cc2d29927b340d7754701 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:55:03 +0100 Subject: PCI/MSI: Move pci_msi_restore_state() to api.c To disentangle the maze in msi.c, all exported device-driver MSI APIs are now to be grouped in one file, api.c. Move pci_msi_enabled() and add kernel-doc for the function. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.331584998@linutronix.de --- drivers/pci/msi/api.c | 15 +++++++++++++++ drivers/pci/msi/msi.c | 11 ++--------- drivers/pci/msi/msi.h | 2 ++ 3 files changed, 19 insertions(+), 9 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 49ae3a3f8282..6c3ad4863850 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -308,6 +308,21 @@ void pci_free_irq_vectors(struct pci_dev *dev) } EXPORT_SYMBOL(pci_free_irq_vectors); +/** + * pci_restore_msi_state() - Restore cached MSI(-X) state on device + * @dev: the PCI device to operate on + * + * Write the Linux-cached MSI(-X) state back on device. This is + * typically useful upon system resume, or after an error-recovery PCI + * adapter reset. + */ +void pci_restore_msi_state(struct pci_dev *dev) +{ + __pci_restore_msi_state(dev); + __pci_restore_msix_state(dev); +} +EXPORT_SYMBOL_GPL(pci_restore_msi_state); + /** * pci_msi_enabled() - Are MSI(-X) interrupts enabled system-wide? * diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 59c33bc7fe81..a5d168c823ff 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -199,7 +199,7 @@ bool __weak arch_restore_msi_irqs(struct pci_dev *dev) return true; } -static void __pci_restore_msi_state(struct pci_dev *dev) +void __pci_restore_msi_state(struct pci_dev *dev) { struct msi_desc *entry; u16 control; @@ -231,7 +231,7 @@ static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set) pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl); } -static void __pci_restore_msix_state(struct pci_dev *dev) +void __pci_restore_msix_state(struct pci_dev *dev) { struct msi_desc *entry; bool write_msg; @@ -257,13 +257,6 @@ static void __pci_restore_msix_state(struct pci_dev *dev) pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } -void pci_restore_msi_state(struct pci_dev *dev) -{ - __pci_restore_msi_state(dev); - __pci_restore_msix_state(dev); -} -EXPORT_SYMBOL_GPL(pci_restore_msi_state); - static void pcim_msi_release(void *pcidev) { struct pci_dev *dev = pcidev; diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index f3f4ede53171..8170ef2c5ad0 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -94,6 +94,8 @@ void pci_free_msi_irqs(struct pci_dev *dev); int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd); int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec, struct irq_affinity *affd, int flags); +void __pci_restore_msi_state(struct pci_dev *dev); +void __pci_restore_msix_state(struct pci_dev *dev); /* Legacy (!IRQDOMAIN) fallbacks */ -- cgit v1.2.3 From 12910ffd189e23d8996e0d19b723518accf57b76 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Fri, 11 Nov 2022 14:55:06 +0100 Subject: PCI/MSI: Reorder functions in msi.c There is no way to navigate msi.c without banging the head against the wall every now and then because MSI and MSI-X specific functions are intermingled and the code flow is completely non-obvious. Reorder everthing so common helpers, MSI and MSI-X specific functions are grouped together. Suggested-by: Thomas Gleixner Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.459089736@linutronix.de --- drivers/pci/msi/msi.c | 639 +++++++++++++++++++++++++------------------------- 1 file changed, 326 insertions(+), 313 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index a5d168c823ff..380e65155b93 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -16,6 +16,97 @@ int pci_msi_enable = 1; int pci_msi_ignore_mask; +/** + * pci_msi_supported - check whether MSI may be enabled on a device + * @dev: pointer to the pci_dev data structure of MSI device function + * @nvec: how many MSIs have been requested? + * + * Look at global flags, the device itself, and its parent buses + * to determine if MSI/-X are supported for the device. If MSI/-X is + * supported return 1, else return 0. + **/ +static int pci_msi_supported(struct pci_dev *dev, int nvec) +{ + struct pci_bus *bus; + + /* MSI must be globally enabled and supported by the device */ + if (!pci_msi_enable) + return 0; + + if (!dev || dev->no_msi) + return 0; + + /* + * You can't ask to have 0 or less MSIs configured. + * a) it's stupid .. + * b) the list manipulation code assumes nvec >= 1. + */ + if (nvec < 1) + return 0; + + /* + * Any bridge which does NOT route MSI transactions from its + * secondary bus to its primary bus must set NO_MSI flag on + * the secondary pci_bus. + * + * The NO_MSI flag can either be set directly by: + * - arch-specific PCI host bus controller drivers (deprecated) + * - quirks for specific PCI bridges + * + * or indirectly by platform-specific PCI host bridge drivers by + * advertising the 'msi_domain' property, which results in + * the NO_MSI flag when no MSI domain is found for this bridge + * at probe time. + */ + for (bus = dev->bus; bus; bus = bus->parent) + if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI) + return 0; + + return 1; +} + +static void pcim_msi_release(void *pcidev) +{ + struct pci_dev *dev = pcidev; + + dev->is_msi_managed = false; + pci_free_irq_vectors(dev); +} + +/* + * Needs to be separate from pcim_release to prevent an ordering problem + * vs. msi_device_data_release() in the MSI core code. + */ +static int pcim_setup_msi_release(struct pci_dev *dev) +{ + int ret; + + if (!pci_is_managed(dev) || dev->is_msi_managed) + return 0; + + ret = devm_add_action(&dev->dev, pcim_msi_release, dev); + if (!ret) + dev->is_msi_managed = true; + return ret; +} + +/* + * Ordering vs. devres: msi device data has to be installed first so that + * pcim_msi_release() is invoked before it on device release. + */ +static int pci_setup_msi_context(struct pci_dev *dev) +{ + int ret = msi_setup_device_data(&dev->dev); + + if (!ret) + ret = pcim_setup_msi_release(dev); + return ret; +} + +/* + * Helper functions for mask/unmask and MSI message handling + */ + void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) { raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock; @@ -163,15 +254,8 @@ void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) } EXPORT_SYMBOL_GPL(pci_write_msi_msg); -void pci_free_msi_irqs(struct pci_dev *dev) -{ - pci_msi_teardown_msi_irqs(dev); - if (dev->msix_base) { - iounmap(dev->msix_base); - dev->msix_base = NULL; - } -} +/* PCI/MSI specific functionality */ static void pci_intx_for_msi(struct pci_dev *dev, int enable) { @@ -190,111 +274,6 @@ static void pci_msi_set_enable(struct pci_dev *dev, int enable) pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); } -/* - * Architecture override returns true when the PCI MSI message should be - * written by the generic restore function. - */ -bool __weak arch_restore_msi_irqs(struct pci_dev *dev) -{ - return true; -} - -void __pci_restore_msi_state(struct pci_dev *dev) -{ - struct msi_desc *entry; - u16 control; - - if (!dev->msi_enabled) - return; - - entry = irq_get_msi_desc(dev->irq); - - pci_intx_for_msi(dev, 0); - pci_msi_set_enable(dev, 0); - if (arch_restore_msi_irqs(dev)) - __pci_write_msi_msg(entry, &entry->msg); - - pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); - pci_msi_update_mask(entry, 0, 0); - control &= ~PCI_MSI_FLAGS_QSIZE; - control |= (entry->pci.msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; - pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); -} - -static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set) -{ - u16 ctrl; - - pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl); - ctrl &= ~clear; - ctrl |= set; - pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl); -} - -void __pci_restore_msix_state(struct pci_dev *dev) -{ - struct msi_desc *entry; - bool write_msg; - - if (!dev->msix_enabled) - return; - - /* route the table */ - pci_intx_for_msi(dev, 0); - pci_msix_clear_and_set_ctrl(dev, 0, - PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL); - - write_msg = arch_restore_msi_irqs(dev); - - msi_lock_descs(&dev->dev); - msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) { - if (write_msg) - __pci_write_msi_msg(entry, &entry->msg); - pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); - } - msi_unlock_descs(&dev->dev); - - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); -} - -static void pcim_msi_release(void *pcidev) -{ - struct pci_dev *dev = pcidev; - - dev->is_msi_managed = false; - pci_free_irq_vectors(dev); -} - -/* - * Needs to be separate from pcim_release to prevent an ordering problem - * vs. msi_device_data_release() in the MSI core code. - */ -static int pcim_setup_msi_release(struct pci_dev *dev) -{ - int ret; - - if (!pci_is_managed(dev) || dev->is_msi_managed) - return 0; - - ret = devm_add_action(&dev->dev, pcim_msi_release, dev); - if (!ret) - dev->is_msi_managed = true; - return ret; -} - -/* - * Ordering vs. devres: msi device data has to be installed first so that - * pcim_msi_release() is invoked before it on device release. - */ -static int pci_setup_msi_context(struct pci_dev *dev) -{ - int ret = msi_setup_device_data(&dev->dev); - - if (!ret) - ret = pcim_setup_msi_release(dev); - return ret; -} - static int msi_setup_msi_desc(struct pci_dev *dev, int nvec, struct irq_affinity_desc *masks) { @@ -415,45 +394,188 @@ unlock: return ret; } -static void __iomem *msix_map_region(struct pci_dev *dev, - unsigned int nr_entries) +int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, + struct irq_affinity *affd) { - resource_size_t phys_addr; - u32 table_offset; - unsigned long flags; - u8 bir; + int nvec; + int rc; - pci_read_config_dword(dev, dev->msix_cap + PCI_MSIX_TABLE, - &table_offset); - bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR); - flags = pci_resource_flags(dev, bir); - if (!flags || (flags & IORESOURCE_UNSET)) - return NULL; + if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0) + return -EINVAL; - table_offset &= PCI_MSIX_TABLE_OFFSET; - phys_addr = pci_resource_start(dev, bir) + table_offset; + /* Check whether driver already requested MSI-X IRQs */ + if (dev->msix_enabled) { + pci_info(dev, "can't enable MSI (MSI-X already enabled)\n"); + return -EINVAL; + } - return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); -} + if (maxvec < minvec) + return -ERANGE; -static int msix_setup_msi_descs(struct pci_dev *dev, void __iomem *base, - struct msix_entry *entries, int nvec, - struct irq_affinity_desc *masks) -{ - int ret = 0, i, vec_count = pci_msix_vec_count(dev); - struct irq_affinity_desc *curmsk; - struct msi_desc desc; - void __iomem *addr; + if (WARN_ON_ONCE(dev->msi_enabled)) + return -EINVAL; - memset(&desc, 0, sizeof(desc)); + nvec = pci_msi_vec_count(dev); + if (nvec < 0) + return nvec; + if (nvec < minvec) + return -ENOSPC; - desc.nvec_used = 1; - desc.pci.msi_attrib.is_msix = 1; - desc.pci.msi_attrib.is_64 = 1; - desc.pci.msi_attrib.default_irq = dev->irq; - desc.pci.mask_base = base; + if (nvec > maxvec) + nvec = maxvec; - for (i = 0, curmsk = masks; i < nvec; i++, curmsk++) { + rc = pci_setup_msi_context(dev); + if (rc) + return rc; + + for (;;) { + if (affd) { + nvec = irq_calc_affinity_vectors(minvec, nvec, affd); + if (nvec < minvec) + return -ENOSPC; + } + + rc = msi_capability_init(dev, nvec, affd); + if (rc == 0) + return nvec; + + if (rc < 0) + return rc; + if (rc < minvec) + return -ENOSPC; + + nvec = rc; + } +} + +/** + * pci_msi_vec_count - Return the number of MSI vectors a device can send + * @dev: device to report about + * + * This function returns the number of MSI vectors a device requested via + * Multiple Message Capable register. It returns a negative errno if the + * device is not capable sending MSI interrupts. Otherwise, the call succeeds + * and returns a power of two, up to a maximum of 2^5 (32), according to the + * MSI specification. + **/ +int pci_msi_vec_count(struct pci_dev *dev) +{ + int ret; + u16 msgctl; + + if (!dev->msi_cap) + return -EINVAL; + + pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl); + ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); + + return ret; +} +EXPORT_SYMBOL(pci_msi_vec_count); + +/* + * Architecture override returns true when the PCI MSI message should be + * written by the generic restore function. + */ +bool __weak arch_restore_msi_irqs(struct pci_dev *dev) +{ + return true; +} + +void __pci_restore_msi_state(struct pci_dev *dev) +{ + struct msi_desc *entry; + u16 control; + + if (!dev->msi_enabled) + return; + + entry = irq_get_msi_desc(dev->irq); + + pci_intx_for_msi(dev, 0); + pci_msi_set_enable(dev, 0); + if (arch_restore_msi_irqs(dev)) + __pci_write_msi_msg(entry, &entry->msg); + + pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); + pci_msi_update_mask(entry, 0, 0); + control &= ~PCI_MSI_FLAGS_QSIZE; + control |= (entry->pci.msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; + pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); +} + +void pci_msi_shutdown(struct pci_dev *dev) +{ + struct msi_desc *desc; + + if (!pci_msi_enable || !dev || !dev->msi_enabled) + return; + + pci_msi_set_enable(dev, 0); + pci_intx_for_msi(dev, 1); + dev->msi_enabled = 0; + + /* Return the device with MSI unmasked as initial states */ + desc = msi_first_desc(&dev->dev, MSI_DESC_ALL); + if (!WARN_ON_ONCE(!desc)) + pci_msi_unmask(desc, msi_multi_mask(desc)); + + /* Restore dev->irq to its default pin-assertion IRQ */ + dev->irq = desc->pci.msi_attrib.default_irq; + pcibios_alloc_irq(dev); +} + +/* PCI/MSI-X specific functionality */ + +static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set) +{ + u16 ctrl; + + pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl); + ctrl &= ~clear; + ctrl |= set; + pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl); +} + +static void __iomem *msix_map_region(struct pci_dev *dev, + unsigned int nr_entries) +{ + resource_size_t phys_addr; + u32 table_offset; + unsigned long flags; + u8 bir; + + pci_read_config_dword(dev, dev->msix_cap + PCI_MSIX_TABLE, + &table_offset); + bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR); + flags = pci_resource_flags(dev, bir); + if (!flags || (flags & IORESOURCE_UNSET)) + return NULL; + + table_offset &= PCI_MSIX_TABLE_OFFSET; + phys_addr = pci_resource_start(dev, bir) + table_offset; + + return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); +} + +static int msix_setup_msi_descs(struct pci_dev *dev, void __iomem *base, + struct msix_entry *entries, int nvec, + struct irq_affinity_desc *masks) +{ + int ret = 0, i, vec_count = pci_msix_vec_count(dev); + struct irq_affinity_desc *curmsk; + struct msi_desc desc; + void __iomem *addr; + + memset(&desc, 0, sizeof(desc)); + + desc.nvec_used = 1; + desc.pci.msi_attrib.is_msix = 1; + desc.pci.msi_attrib.is_64 = 1; + desc.pci.msi_attrib.default_irq = dev->irq; + desc.pci.mask_base = base; + + for (i = 0, curmsk = masks; i < nvec; i++, curmsk++) { desc.msi_index = entries ? entries[i].entry : i; desc.affinity = masks ? curmsk : NULL; desc.pci.msi_attrib.is_virtual = desc.msi_index >= vec_count; @@ -599,101 +721,6 @@ out_disable: return ret; } -/** - * pci_msi_supported - check whether MSI may be enabled on a device - * @dev: pointer to the pci_dev data structure of MSI device function - * @nvec: how many MSIs have been requested? - * - * Look at global flags, the device itself, and its parent buses - * to determine if MSI/-X are supported for the device. If MSI/-X is - * supported return 1, else return 0. - **/ -static int pci_msi_supported(struct pci_dev *dev, int nvec) -{ - struct pci_bus *bus; - - /* MSI must be globally enabled and supported by the device */ - if (!pci_msi_enable) - return 0; - - if (!dev || dev->no_msi) - return 0; - - /* - * You can't ask to have 0 or less MSIs configured. - * a) it's stupid .. - * b) the list manipulation code assumes nvec >= 1. - */ - if (nvec < 1) - return 0; - - /* - * Any bridge which does NOT route MSI transactions from its - * secondary bus to its primary bus must set NO_MSI flag on - * the secondary pci_bus. - * - * The NO_MSI flag can either be set directly by: - * - arch-specific PCI host bus controller drivers (deprecated) - * - quirks for specific PCI bridges - * - * or indirectly by platform-specific PCI host bridge drivers by - * advertising the 'msi_domain' property, which results in - * the NO_MSI flag when no MSI domain is found for this bridge - * at probe time. - */ - for (bus = dev->bus; bus; bus = bus->parent) - if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI) - return 0; - - return 1; -} - -/** - * pci_msi_vec_count - Return the number of MSI vectors a device can send - * @dev: device to report about - * - * This function returns the number of MSI vectors a device requested via - * Multiple Message Capable register. It returns a negative errno if the - * device is not capable sending MSI interrupts. Otherwise, the call succeeds - * and returns a power of two, up to a maximum of 2^5 (32), according to the - * MSI specification. - **/ -int pci_msi_vec_count(struct pci_dev *dev) -{ - int ret; - u16 msgctl; - - if (!dev->msi_cap) - return -EINVAL; - - pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl); - ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1); - - return ret; -} -EXPORT_SYMBOL(pci_msi_vec_count); - -void pci_msi_shutdown(struct pci_dev *dev) -{ - struct msi_desc *desc; - - if (!pci_msi_enable || !dev || !dev->msi_enabled) - return; - - pci_msi_set_enable(dev, 0); - pci_intx_for_msi(dev, 1); - dev->msi_enabled = 0; - - /* Return the device with MSI unmasked as initial states */ - desc = msi_first_desc(&dev->dev, MSI_DESC_ALL); - if (!WARN_ON_ONCE(!desc)) - pci_msi_unmask(desc, msi_multi_mask(desc)); - - /* Restore dev->irq to its default pin-assertion IRQ */ - dev->irq = desc->pci.msi_attrib.default_irq; - pcibios_alloc_irq(dev); -} - static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd, int flags) { @@ -729,57 +756,23 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, return msix_capability_init(dev, entries, nvec, affd); } -void pci_msix_shutdown(struct pci_dev *dev) -{ - struct msi_desc *desc; - - if (!pci_msi_enable || !dev || !dev->msix_enabled) - return; - - if (pci_dev_is_disconnected(dev)) { - dev->msix_enabled = 0; - return; - } - - /* Return the device with MSI-X masked as initial states */ - msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL) - pci_msix_mask(desc); - - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); - pci_intx_for_msi(dev, 1); - dev->msix_enabled = 0; - pcibios_alloc_irq(dev); -} - -int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, - struct irq_affinity *affd) +int __pci_enable_msix_range(struct pci_dev *dev, + struct msix_entry *entries, int minvec, + int maxvec, struct irq_affinity *affd, + int flags) { - int nvec; - int rc; - - if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0) - return -EINVAL; - - /* Check whether driver already requested MSI-X IRQs */ - if (dev->msix_enabled) { - pci_info(dev, "can't enable MSI (MSI-X already enabled)\n"); - return -EINVAL; - } + int rc, nvec = maxvec; if (maxvec < minvec) return -ERANGE; - if (WARN_ON_ONCE(dev->msi_enabled)) + if (dev->msi_enabled) { + pci_info(dev, "can't enable MSI-X (MSI already enabled)\n"); return -EINVAL; + } - nvec = pci_msi_vec_count(dev); - if (nvec < 0) - return nvec; - if (nvec < minvec) - return -ENOSPC; - - if (nvec > maxvec) - nvec = maxvec; + if (WARN_ON_ONCE(dev->msix_enabled)) + return -EINVAL; rc = pci_setup_msi_context(dev); if (rc) @@ -792,7 +785,7 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, return -ENOSPC; } - rc = msi_capability_init(dev, nvec, affd); + rc = __pci_enable_msix(dev, entries, nvec, affd, flags); if (rc == 0) return nvec; @@ -805,48 +798,68 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, } } -int __pci_enable_msix_range(struct pci_dev *dev, - struct msix_entry *entries, int minvec, - int maxvec, struct irq_affinity *affd, - int flags) +void __pci_restore_msix_state(struct pci_dev *dev) { - int rc, nvec = maxvec; + struct msi_desc *entry; + bool write_msg; - if (maxvec < minvec) - return -ERANGE; + if (!dev->msix_enabled) + return; - if (dev->msi_enabled) { - pci_info(dev, "can't enable MSI-X (MSI already enabled)\n"); - return -EINVAL; + /* route the table */ + pci_intx_for_msi(dev, 0); + pci_msix_clear_and_set_ctrl(dev, 0, + PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL); + + write_msg = arch_restore_msi_irqs(dev); + + msi_lock_descs(&dev->dev); + msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) { + if (write_msg) + __pci_write_msi_msg(entry, &entry->msg); + pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); } + msi_unlock_descs(&dev->dev); - if (WARN_ON_ONCE(dev->msix_enabled)) - return -EINVAL; + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); +} - rc = pci_setup_msi_context(dev); - if (rc) - return rc; +void pci_msix_shutdown(struct pci_dev *dev) +{ + struct msi_desc *desc; - for (;;) { - if (affd) { - nvec = irq_calc_affinity_vectors(minvec, nvec, affd); - if (nvec < minvec) - return -ENOSPC; - } + if (!pci_msi_enable || !dev || !dev->msix_enabled) + return; - rc = __pci_enable_msix(dev, entries, nvec, affd, flags); - if (rc == 0) - return nvec; + if (pci_dev_is_disconnected(dev)) { + dev->msix_enabled = 0; + return; + } - if (rc < 0) - return rc; - if (rc < minvec) - return -ENOSPC; + /* Return the device with MSI-X masked as initial states */ + msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL) + pci_msix_mask(desc); - nvec = rc; + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + pci_intx_for_msi(dev, 1); + dev->msix_enabled = 0; + pcibios_alloc_irq(dev); +} + +/* Common interfaces */ + +void pci_free_msi_irqs(struct pci_dev *dev) +{ + pci_msi_teardown_msi_irqs(dev); + + if (dev->msix_base) { + iounmap(dev->msix_base); + dev->msix_base = NULL; } } +/* Misc. infrastructure */ + struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) { return to_pci_dev(desc->dev); -- cgit v1.2.3 From bab65e48cb064d67b488efb6888c06fd977a8245 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:55:07 +0100 Subject: PCI/MSI: Sanitize MSI-X checks There is no point in doing the same sanity checks over and over in a loop during MSI-X enablement. Put them in front of the loop and return early when they fail. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.516946468@linutronix.de --- drivers/pci/msi/msi.c | 65 ++++++++++++++++++++++++++------------------------- 1 file changed, 33 insertions(+), 32 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 380e65155b93..794ec97c5b70 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -721,47 +721,31 @@ out_disable: return ret; } -static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, - int nvec, struct irq_affinity *affd, int flags) +static bool pci_msix_validate_entries(struct msix_entry *entries, int nvec, int hwsize) { - int nr_entries; int i, j; - if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0) - return -EINVAL; + if (!entries) + return true; - nr_entries = pci_msix_vec_count(dev); - if (nr_entries < 0) - return nr_entries; - if (nvec > nr_entries && !(flags & PCI_IRQ_VIRTUAL)) - return nr_entries; + for (i = 0; i < nvec; i++) { + /* Entry within hardware limit? */ + if (entries[i].entry >= hwsize) + return false; - if (entries) { - /* Check for any invalid entries */ - for (i = 0; i < nvec; i++) { - if (entries[i].entry >= nr_entries) - return -EINVAL; /* invalid entry */ - for (j = i + 1; j < nvec; j++) { - if (entries[i].entry == entries[j].entry) - return -EINVAL; /* duplicate entry */ - } + /* Check for duplicate entries */ + for (j = i + 1; j < nvec; j++) { + if (entries[i].entry == entries[j].entry) + return false; } } - - /* Check whether driver already requested for MSI IRQ */ - if (dev->msi_enabled) { - pci_info(dev, "can't enable MSI-X (MSI IRQ already assigned)\n"); - return -EINVAL; - } - return msix_capability_init(dev, entries, nvec, affd); + return true; } -int __pci_enable_msix_range(struct pci_dev *dev, - struct msix_entry *entries, int minvec, - int maxvec, struct irq_affinity *affd, - int flags) +int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, + int maxvec, struct irq_affinity *affd, int flags) { - int rc, nvec = maxvec; + int hwsize, rc, nvec = maxvec; if (maxvec < minvec) return -ERANGE; @@ -774,6 +758,23 @@ int __pci_enable_msix_range(struct pci_dev *dev, if (WARN_ON_ONCE(dev->msix_enabled)) return -EINVAL; + if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0) + return -EINVAL; + + hwsize = pci_msix_vec_count(dev); + if (hwsize < 0) + return hwsize; + + if (!pci_msix_validate_entries(entries, nvec, hwsize)) + return -EINVAL; + + /* PCI_IRQ_VIRTUAL is a horrible hack! */ + if (nvec > hwsize && !(flags & PCI_IRQ_VIRTUAL)) + nvec = hwsize; + + if (nvec < minvec) + return -ENOSPC; + rc = pci_setup_msi_context(dev); if (rc) return rc; @@ -785,7 +786,7 @@ int __pci_enable_msix_range(struct pci_dev *dev, return -ENOSPC; } - rc = __pci_enable_msix(dev, entries, nvec, affd, flags); + rc = msix_capability_init(dev, entries, nvec, affd); if (rc == 0) return nvec; -- cgit v1.2.3 From d2a463b297415ca6dd4d60bb1c867dd7c931587b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:55:09 +0100 Subject: PCI/MSI: Reject multi-MSI early When hierarchical MSI interrupt domains are enabled then there is no point to do tons of work and detect the missing support for multi-MSI late in the allocation path. Just query the domain feature flags right away. The query function is going to be used for other purposes later and has a mode argument which influences the result: ALLOW_LEGACY returns true when: - there is no irq domain attached (legacy support) - there is a irq domain attached which has the feature flag set DENY_LEGACY returns only true when: - there is a irq domain attached which has the feature flag set This allows to use the function universally without ifdeffery in the calling code. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.574339988@linutronix.de --- drivers/pci/msi/irqdomain.c | 22 ++++++++++++++++++++++ drivers/pci/msi/msi.c | 4 ++++ drivers/pci/msi/msi.h | 9 +++++++++ 3 files changed, 35 insertions(+) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index edd0cc204e06..666ed21f2924 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -187,6 +187,28 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, } EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain); +/** + * pci_msi_domain_supports - Check for support of a particular feature flag + * @pdev: The PCI device to operate on + * @feature_mask: The feature mask to check for (full match) + * @mode: If ALLOW_LEGACY this grants the feature when there is no irq domain + * associated to the device. If DENY_LEGACY the lack of an irq domain + * makes the feature unsupported + */ +bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask, + enum support_mode mode) +{ + struct msi_domain_info *info; + struct irq_domain *domain; + + domain = dev_get_msi_domain(&pdev->dev); + + if (!domain || !irq_domain_is_hierarchy(domain)) + return mode == ALLOW_LEGACY; + info = domain->host_data; + return (info->flags & feature_mask) == feature_mask; +} + /* * Users of the generic MSI infrastructure expect a device to have a single ID, * so with DMA aliases we have to pick the least-worst compromise. Devices with diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 794ec97c5b70..bc84647c6dbd 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -347,6 +347,10 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, struct msi_desc *entry; int ret; + /* Reject multi-MSI early on irq domain enabled architectures */ + if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY)) + return 1; + /* * Disable MSI during setup in the hardware, but mark it enabled * so that setup code can evaluate it. diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index 8170ef2c5ad0..9d75b6fb3e0c 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -97,6 +97,15 @@ int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int void __pci_restore_msi_state(struct pci_dev *dev); void __pci_restore_msix_state(struct pci_dev *dev); +/* irq_domain related functionality */ + +enum support_mode { + ALLOW_LEGACY, + DENY_LEGACY, +}; + +bool pci_msi_domain_supports(struct pci_dev *dev, unsigned int feature_mask, enum support_mode mode); + /* Legacy (!IRQDOMAIN) fallbacks */ #ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS -- cgit v1.2.3 From 99f3d279765725920aa5924fa445537a20129a6f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:55:11 +0100 Subject: PCI/MSI: Reject MSI-X early Similar to PCI multi-MSI reject MSI-X enablement when a irq domain is attached to the device which does not support MSI-X. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.631728309@linutronix.de --- drivers/pci/msi/msi.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index bc84647c6dbd..0740acd10bde 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -762,6 +762,10 @@ int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int if (WARN_ON_ONCE(dev->msix_enabled)) return -EINVAL; + /* Check MSI-X early on irq domain enabled architectures */ + if (!pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX, ALLOW_LEGACY)) + return -ENOTSUPP; + if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0) return -EINVAL; -- cgit v1.2.3 From 4644d22eb673f173252610a93aaaba4c2bff7b41 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:55:12 +0100 Subject: PCI/MSI: Validate MSI-X contiguous restriction early With interrupt domains the sanity check for MSI-X vector validation can be done _before_ any allocation happens. The sanity check only applies to the allocation functions which have an 'entries' array argument. The entries array is filled by the caller with the requested MSI-X indices. Some drivers have gaps in the index space which is not supported on all architectures. The PCI/MSI irq domain has a 'feature' bit to enforce this validation late during the allocation phase. Just do it right away before doing any other work along with the other sanity checks on that array. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.691357406@linutronix.de --- drivers/pci/msi/msi.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 0740acd10bde..b94f6da3f32f 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -725,13 +725,17 @@ out_disable: return ret; } -static bool pci_msix_validate_entries(struct msix_entry *entries, int nvec, int hwsize) +static bool pci_msix_validate_entries(struct pci_dev *dev, struct msix_entry *entries, + int nvec, int hwsize) { + bool nogap; int i, j; if (!entries) return true; + nogap = pci_msi_domain_supports(dev, MSI_FLAG_MSIX_CONTIGUOUS, DENY_LEGACY); + for (i = 0; i < nvec; i++) { /* Entry within hardware limit? */ if (entries[i].entry >= hwsize) @@ -742,6 +746,9 @@ static bool pci_msix_validate_entries(struct msix_entry *entries, int nvec, int if (entries[i].entry == entries[j].entry) return false; } + /* Check for unsupported gaps */ + if (nogap && entries[i].entry != i) + return false; } return true; } @@ -773,7 +780,7 @@ int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int if (hwsize < 0) return hwsize; - if (!pci_msix_validate_entries(entries, nvec, hwsize)) + if (!pci_msix_validate_entries(dev, entries, nvec, hwsize)) return -EINVAL; /* PCI_IRQ_VIRTUAL is a horrible hack! */ -- cgit v1.2.3 From 9c03b2589da2b2b259a960f2a325731f6b38d115 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:55:14 +0100 Subject: PCI/MSI: Remove redundant msi_check() callback All these sanity checks are now done _before_ any allocation work happens. No point in doing it twice. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20221111122015.749446904@linutronix.de --- drivers/pci/msi/irqdomain.c | 48 --------------------------------------------- 1 file changed, 48 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 666ed21f2924..dea2e8c4dfa4 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -64,51 +64,6 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; } -static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) -{ - return !desc->pci.msi_attrib.is_msix && desc->nvec_used > 1; -} - -/** - * pci_msi_domain_check_cap - Verify that @domain supports the capabilities - * for @dev - * @domain: The interrupt domain to check - * @info: The domain info for verification - * @dev: The device to check - * - * Returns: - * 0 if the functionality is supported - * 1 if Multi MSI is requested, but the domain does not support it - * -ENOTSUPP otherwise - */ -static int pci_msi_domain_check_cap(struct irq_domain *domain, - struct msi_domain_info *info, - struct device *dev) -{ - struct msi_desc *desc = msi_first_desc(dev, MSI_DESC_ALL); - - /* Special handling to support __pci_enable_msi_range() */ - if (pci_msi_desc_is_multi_msi(desc) && - !(info->flags & MSI_FLAG_MULTI_PCI_MSI)) - return 1; - - if (desc->pci.msi_attrib.is_msix) { - if (!(info->flags & MSI_FLAG_PCI_MSIX)) - return -ENOTSUPP; - - if (info->flags & MSI_FLAG_MSIX_CONTIGUOUS) { - unsigned int idx = 0; - - /* Check for gaps in the entry indices */ - msi_for_each_desc(desc, dev, MSI_DESC_ALL) { - if (desc->msi_index != idx++) - return -ENOTSUPP; - } - } - } - return 0; -} - static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { @@ -118,7 +73,6 @@ static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, static struct msi_domain_ops pci_msi_domain_ops_default = { .set_desc = pci_msi_domain_set_desc, - .msi_check = pci_msi_domain_check_cap, }; static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) @@ -130,8 +84,6 @@ static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) } else { if (ops->set_desc == NULL) ops->set_desc = pci_msi_domain_set_desc; - if (ops->msi_check == NULL) - ops->msi_check = pci_msi_domain_check_cap; } } -- cgit v1.2.3 From d474d92d70250d43e7ce0c7cb8623f31ee7c40f6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 11 Nov 2022 14:55:17 +0100 Subject: x86/apic: Remove X86_IRQ_ALLOC_CONTIGUOUS_VECTORS Now that the PCI/MSI core code does early checking for multi-MSI support X86_IRQ_ALLOC_CONTIGUOUS_VECTORS is not required anymore. Remove the flag and rely on MSI_FLAG_MULTI_PCI_MSI. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20221111122015.865042356@linutronix.de --- arch/x86/include/asm/irqdomain.h | 4 +--- arch/x86/kernel/apic/msi.c | 6 ++---- arch/x86/kernel/apic/vector.c | 4 ---- drivers/iommu/amd/iommu.c | 7 ------- drivers/iommu/intel/irq_remapping.c | 7 ------- drivers/pci/controller/pci-hyperv.c | 15 +-------------- 6 files changed, 4 insertions(+), 39 deletions(-) (limited to 'drivers/pci') diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index 125c23b7bad3..30c325c235c0 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -7,9 +7,7 @@ #ifdef CONFIG_X86_LOCAL_APIC enum { - /* Allocate contiguous CPU vectors */ - X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1, - X86_IRQ_ALLOC_LEGACY = 0x2, + X86_IRQ_ALLOC_LEGACY = 0x1, }; extern int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec); diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 7517eb05bdc1..248a6a5c0ad8 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -161,12 +161,10 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg) { init_irq_alloc_info(arg, NULL); - if (to_pci_dev(dev)->msix_enabled) { + if (to_pci_dev(dev)->msix_enabled) arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; - } else { + else arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; - arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - } return 0; } diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3e6f6b448f6a..c1efebd27e6c 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -539,10 +539,6 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, if (disable_apic) return -ENXIO; - /* Currently vector allocator can't guarantee contiguous allocations */ - if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1) - return -ENOSYS; - /* * Catch any attempt to touch the cascade interrupt on a PIC * equipped system. diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 8ece86484b27..72dfe57f5802 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -3297,13 +3297,6 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI) return -EINVAL; - /* - * With IRQ remapping enabled, don't need contiguous CPU vectors - * to support multiple MSI interrupts. - */ - if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) - info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - sbdf = get_devid(info); if (sbdf < 0) return -EINVAL; diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c index 0b80a272e9a7..a914eba787ac 100644 --- a/drivers/iommu/intel/irq_remapping.c +++ b/drivers/iommu/intel/irq_remapping.c @@ -1337,13 +1337,6 @@ static int intel_irq_remapping_alloc(struct irq_domain *domain, if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI) return -EINVAL; - /* - * With IRQ remapping enabled, don't need contiguous CPU vectors - * to support multiple MSI interrupts. - */ - if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) - info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); if (ret < 0) return ret; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ba64284eaf9f..1dee55d16a4d 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -611,20 +611,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) return cfg->vector; } -static int hv_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *info) -{ - int ret = pci_msi_prepare(domain, dev, nvec, info); - - /* - * By using the interrupt remapper in the hypervisor IOMMU, contiguous - * CPU vectors is not needed for multi-MSI - */ - if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) - info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; - - return ret; -} +#define hv_msi_prepare pci_msi_prepare /** * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current -- cgit v1.2.3 From 6842694c5088925d216529d4a2358ab5ee8bb862 Mon Sep 17 00:00:00 2001 From: Bagas Sanjaya Date: Sat, 3 Dec 2022 17:05:11 +0700 Subject: PCI/MSI: Use bullet lists in kernel-doc comments of api.c Use bullet-list RST syntax for kernel-doc parameters' flags and interrupt mode descriptions. Otherwise Sphinx produces "Unexpected identation" errors and warnings. Fixes: 5c0997dc33ac24 ("PCI/MSI: Move pci_alloc_irq_vectors() to api.c") Fixes: 017239c8db2093 ("PCI/MSI: Move pci_irq_vector() to api.c") Fixes: be37b8428b7b77 ("PCI/MSI: Move pci_irq_get_affinity() to api.c") Reported-by: Stephen Rothwell Suggested-by: Ahmed S. Darwish Signed-off-by: Bagas Sanjaya Signed-off-by: Thomas Gleixner Acked-by: Ahmed S. Darwish Link: https://lore.kernel.org/r/20221203100511.222136-1-bagasdotme@gmail.com --- drivers/pci/msi/api.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 6c3ad4863850..2d46a0cfd541 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -142,12 +142,15 @@ EXPORT_SYMBOL(pci_disable_msix); * @min_vecs: minimum required number of vectors (must be >= 1) * @max_vecs: maximum desired number of vectors * @flags: One or more of: - * %PCI_IRQ_MSIX Allow trying MSI-X vector allocations - * %PCI_IRQ_MSI Allow trying MSI vector allocations - * %PCI_IRQ_LEGACY Allow trying legacy INTx interrupts, if - * and only if @min_vecs == 1 - * %PCI_IRQ_AFFINITY Auto-manage IRQs affinity by spreading - * the vectors around available CPUs + * + * * %PCI_IRQ_MSIX Allow trying MSI-X vector allocations + * * %PCI_IRQ_MSI Allow trying MSI vector allocations + * + * * %PCI_IRQ_LEGACY Allow trying legacy INTx interrupts, if + * and only if @min_vecs == 1 + * + * * %PCI_IRQ_AFFINITY Auto-manage IRQs affinity by spreading + * the vectors around available CPUs * * Allocate up to @max_vecs interrupt vectors on device. MSI-X irq * vector allocation has a higher precedence over plain MSI, which has a @@ -232,10 +235,11 @@ EXPORT_SYMBOL(pci_alloc_irq_vectors_affinity); * pci_irq_vector() - Get Linux IRQ number of a device interrupt vector * @dev: the PCI device to operate on * @nr: device-relative interrupt vector index (0-based); has different - * meanings, depending on interrupt mode - * MSI-X the index in the MSI-X vector table - * MSI the index of the enabled MSI vectors - * INTx must be 0 + * meanings, depending on interrupt mode: + * + * * MSI-X the index in the MSI-X vector table + * * MSI the index of the enabled MSI vectors + * * INTx must be 0 * * Return: the Linux IRQ number, or -EINVAL if @nr is out of range */ @@ -255,10 +259,11 @@ EXPORT_SYMBOL(pci_irq_vector); * pci_irq_get_affinity() - Get a device interrupt vector affinity * @dev: the PCI device to operate on * @nr: device-relative interrupt vector index (0-based); has different - * meanings, depending on interrupt mode - * MSI-X the index in the MSI-X vector table - * MSI the index of the enabled MSI vectors - * INTx must be 0 + * meanings, depending on interrupt mode: + * + * * MSI-X the index in the MSI-X vector table + * * MSI the index of the enabled MSI vectors + * * INTx must be 0 * * Return: MSI/MSI-X vector affinity, NULL if @nr is out of range or if * the MSI(-X) vector was allocated without explicit affinity -- cgit v1.2.3 From 1c89396300292da4e4a87db63bef45975461fa25 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:24:27 +0100 Subject: genirq/msi: Rename msi_add_msi_desc() to msi_insert_msi_desc() This reflects the functionality better. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124230314.103554618@linutronix.de --- drivers/pci/msi/msi.c | 4 ++-- drivers/soc/ti/ti_sci_inta_msi.c | 4 ++-- include/linux/msi.h | 2 +- kernel/irq/msi.c | 6 ++++-- 4 files changed, 9 insertions(+), 7 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index b94f6da3f32f..d107bde58bd6 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -308,7 +308,7 @@ static int msi_setup_msi_desc(struct pci_dev *dev, int nvec, if (desc.pci.msi_attrib.can_mask) pci_read_config_dword(dev, desc.pci.mask_pos, &desc.pci.msi_mask); - return msi_add_msi_desc(&dev->dev, &desc); + return msi_insert_msi_desc(&dev->dev, &desc); } static int msi_verify_entries(struct pci_dev *dev) @@ -591,7 +591,7 @@ static int msix_setup_msi_descs(struct pci_dev *dev, void __iomem *base, desc.pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } - ret = msi_add_msi_desc(&dev->dev, &desc); + ret = msi_insert_msi_desc(&dev->dev, &desc); if (ret) break; } diff --git a/drivers/soc/ti/ti_sci_inta_msi.c b/drivers/soc/ti/ti_sci_inta_msi.c index 991c78b34745..255849cb81ed 100644 --- a/drivers/soc/ti/ti_sci_inta_msi.c +++ b/drivers/soc/ti/ti_sci_inta_msi.c @@ -73,13 +73,13 @@ static int ti_sci_inta_msi_alloc_descs(struct device *dev, for (set = 0; set < res->sets; set++) { for (i = 0; i < res->desc[set].num; i++, count++) { msi_desc.msi_index = res->desc[set].start + i; - if (msi_add_msi_desc(dev, &msi_desc)) + if (msi_insert_msi_desc(dev, &msi_desc)) goto fail; } for (i = 0; i < res->desc[set].num_sec; i++, count++) { msi_desc.msi_index = res->desc[set].start_sec + i; - if (msi_add_msi_desc(dev, &msi_desc)) + if (msi_insert_msi_desc(dev, &msi_desc)) goto fail; } } diff --git a/include/linux/msi.h b/include/linux/msi.h index 764a4e8828fb..f8ba85af3542 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -286,7 +286,7 @@ static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, } #endif -int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc); +int msi_insert_msi_desc(struct device *dev, struct msi_desc *init_desc); void msi_free_msi_descs_range(struct device *dev, unsigned int first_index, unsigned int last_index); /** diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index e1593c16518b..33b8a6cca3f8 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -77,13 +77,15 @@ static int msi_insert_desc(struct msi_device_data *md, struct msi_desc *desc, un } /** - * msi_add_msi_desc - Allocate and initialize a MSI descriptor + * msi_insert_msi_desc - Allocate and initialize a MSI descriptor and + * insert it at @init_desc->msi_index + * * @dev: Pointer to the device for which the descriptor is allocated * @init_desc: Pointer to an MSI descriptor to initialize the new descriptor * * Return: 0 on success or an appropriate failure code. */ -int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) +int msi_insert_msi_desc(struct device *dev, struct msi_desc *init_desc) { struct msi_desc *desc; -- cgit v1.2.3 From d3a11dee9f946daa6e66aca1bf8db93e9d4e02ec Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:24:36 +0100 Subject: PCI/MSI: Use msi_domain_alloc/free_irqs_all_locked() Switch to the new domain id aware interfaces to phase out the previous ones. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124230314.455168748@linutronix.de --- drivers/pci/msi/irqdomain.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index dea2e8c4dfa4..f4338fb42c2d 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -14,7 +14,7 @@ int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) domain = dev_get_msi_domain(&dev->dev); if (domain && irq_domain_is_hierarchy(domain)) - return msi_domain_alloc_irqs_descs_locked(domain, &dev->dev, nvec); + return msi_domain_alloc_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN, nvec); return pci_msi_legacy_setup_msi_irqs(dev, nvec, type); } @@ -25,7 +25,7 @@ void pci_msi_teardown_msi_irqs(struct pci_dev *dev) domain = dev_get_msi_domain(&dev->dev); if (domain && irq_domain_is_hierarchy(domain)) { - msi_domain_free_irqs_descs_locked(domain, &dev->dev); + msi_domain_free_irqs_all_locked(&dev->dev, MSI_DEFAULT_DOMAIN); } else { pci_msi_legacy_teardown_msi_irqs(dev); msi_free_msi_descs(&dev->dev); -- cgit v1.2.3 From 877d6c4e93f5091bfa52549bde8fb9ce71d6f7e5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:00 +0100 Subject: PCI/MSI: Split __pci_write_msi_msg() The upcoming per device MSI domains will create different domains for MSI and MSI-X. Split the write message function into MSI and MSI-X helpers so they can be used by those new domain functions seperately. Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124232325.857982142@linutronix.de --- drivers/pci/msi/msi.c | 104 ++++++++++++++++++++++++++------------------------ 1 file changed, 54 insertions(+), 50 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index d107bde58bd6..76a3d447e947 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -180,6 +180,58 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) } } +static inline void pci_write_msg_msi(struct pci_dev *dev, struct msi_desc *desc, + struct msi_msg *msg) +{ + int pos = dev->msi_cap; + u16 msgctl; + + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); + msgctl &= ~PCI_MSI_FLAGS_QSIZE; + msgctl |= desc->pci.msi_attrib.multiple << 4; + pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl); + + pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, msg->address_lo); + if (desc->pci.msi_attrib.is_64) { + pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, msg->address_hi); + pci_write_config_word(dev, pos + PCI_MSI_DATA_64, msg->data); + } else { + pci_write_config_word(dev, pos + PCI_MSI_DATA_32, msg->data); + } + /* Ensure that the writes are visible in the device */ + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); +} + +static inline void pci_write_msg_msix(struct msi_desc *desc, struct msi_msg *msg) +{ + void __iomem *base = pci_msix_desc_addr(desc); + u32 ctrl = desc->pci.msix_ctrl; + bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT); + + if (desc->pci.msi_attrib.is_virtual) + return; + /* + * The specification mandates that the entry is masked + * when the message is modified: + * + * "If software changes the Address or Data value of an + * entry while the entry is unmasked, the result is + * undefined." + */ + if (unmasked) + pci_msix_write_vector_ctrl(desc, ctrl | PCI_MSIX_ENTRY_CTRL_MASKBIT); + + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); + writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); + writel(msg->data, base + PCI_MSIX_ENTRY_DATA); + + if (unmasked) + pci_msix_write_vector_ctrl(desc, ctrl); + + /* Ensure that the writes are visible in the device */ + readl(base + PCI_MSIX_ENTRY_DATA); +} + void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { struct pci_dev *dev = msi_desc_to_pci_dev(entry); @@ -187,63 +239,15 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) if (dev->current_state != PCI_D0 || pci_dev_is_disconnected(dev)) { /* Don't touch the hardware now */ } else if (entry->pci.msi_attrib.is_msix) { - void __iomem *base = pci_msix_desc_addr(entry); - u32 ctrl = entry->pci.msix_ctrl; - bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT); - - if (entry->pci.msi_attrib.is_virtual) - goto skip; - - /* - * The specification mandates that the entry is masked - * when the message is modified: - * - * "If software changes the Address or Data value of an - * entry while the entry is unmasked, the result is - * undefined." - */ - if (unmasked) - pci_msix_write_vector_ctrl(entry, ctrl | PCI_MSIX_ENTRY_CTRL_MASKBIT); - - writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); - writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); - writel(msg->data, base + PCI_MSIX_ENTRY_DATA); - - if (unmasked) - pci_msix_write_vector_ctrl(entry, ctrl); - - /* Ensure that the writes are visible in the device */ - readl(base + PCI_MSIX_ENTRY_DATA); + pci_write_msg_msix(entry, msg); } else { - int pos = dev->msi_cap; - u16 msgctl; - - pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); - msgctl &= ~PCI_MSI_FLAGS_QSIZE; - msgctl |= entry->pci.msi_attrib.multiple << 4; - pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl); - - pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, - msg->address_lo); - if (entry->pci.msi_attrib.is_64) { - pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, - msg->address_hi); - pci_write_config_word(dev, pos + PCI_MSI_DATA_64, - msg->data); - } else { - pci_write_config_word(dev, pos + PCI_MSI_DATA_32, - msg->data); - } - /* Ensure that the writes are visible in the device */ - pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); + pci_write_msg_msi(dev, entry, msg); } -skip: entry->msg = *msg; if (entry->write_msi_msg) entry->write_msi_msg(entry, entry->write_msi_msg_data); - } void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) -- cgit v1.2.3 From 15c72f824b32761696b1854500bb3dedccbbb45a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:04 +0100 Subject: PCI/MSI: Add support for per device MSI[X] domains Provide a template and the necessary callbacks to create PCI/MSI and PCI/MSI-X domains. The domains are created when MSI or MSI-X is enabled. The domain's lifetime is either the device lifetime or in case that e.g. MSI-X was tried first and failed, then the MSI-X domain is removed and a MSI domain is created as both are mutually exclusive and reside in the default domain ID slot of the per device domain pointer array. Also expand pci_msi_domain_supports() to handle feature checks correctly even in the case that the per device domain was not yet created by checking the features supported by the MSI parent. Add the necessary setup calls into the MSI and MSI-X enable code path. These setup calls are backwards compatible. They return success when there is no parent domain found, which means the existing global domains or the legacy allocation path keep just working. Co-developed-by: Ahmed S. Darwish Signed-off-by: Ahmed S. Darwish Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124232325.975388241@linutronix.de --- drivers/pci/msi/irqdomain.c | 188 +++++++++++++++++++++++++++++++++++++++++++- drivers/pci/msi/msi.c | 16 +++- drivers/pci/msi/msi.h | 2 + 3 files changed, 201 insertions(+), 5 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index f4338fb42c2d..be3d50ffc093 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -139,6 +139,170 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, } EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain); +/* + * Per device MSI[-X] domain functionality + */ +static void pci_device_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->desc = desc; + arg->hwirq = desc->msi_index; +} + +static void pci_irq_mask_msi(struct irq_data *data) +{ + struct msi_desc *desc = irq_data_get_msi_desc(data); + + pci_msi_mask(desc, BIT(data->irq - desc->irq)); +} + +static void pci_irq_unmask_msi(struct irq_data *data) +{ + struct msi_desc *desc = irq_data_get_msi_desc(data); + + pci_msi_unmask(desc, BIT(data->irq - desc->irq)); +} + +#ifdef CONFIG_GENERIC_IRQ_RESERVATION_MODE +# define MSI_REACTIVATE MSI_FLAG_MUST_REACTIVATE +#else +# define MSI_REACTIVATE 0 +#endif + +#define MSI_COMMON_FLAGS (MSI_FLAG_FREE_MSI_DESCS | \ + MSI_FLAG_ACTIVATE_EARLY | \ + MSI_FLAG_DEV_SYSFS | \ + MSI_REACTIVATE) + +static const struct msi_domain_template pci_msi_template = { + .chip = { + .name = "PCI-MSI", + .irq_mask = pci_irq_mask_msi, + .irq_unmask = pci_irq_unmask_msi, + .irq_write_msi_msg = pci_msi_domain_write_msg, + .flags = IRQCHIP_ONESHOT_SAFE, + }, + + .ops = { + .set_desc = pci_device_domain_set_desc, + }, + + .info = { + .flags = MSI_COMMON_FLAGS | MSI_FLAG_MULTI_PCI_MSI, + .bus_token = DOMAIN_BUS_PCI_DEVICE_MSI, + }, +}; + +static void pci_irq_mask_msix(struct irq_data *data) +{ + pci_msix_mask(irq_data_get_msi_desc(data)); +} + +static void pci_irq_unmask_msix(struct irq_data *data) +{ + pci_msix_unmask(irq_data_get_msi_desc(data)); +} + +static const struct msi_domain_template pci_msix_template = { + .chip = { + .name = "PCI-MSIX", + .irq_mask = pci_irq_mask_msix, + .irq_unmask = pci_irq_unmask_msix, + .irq_write_msi_msg = pci_msi_domain_write_msg, + .flags = IRQCHIP_ONESHOT_SAFE, + }, + + .ops = { + .set_desc = pci_device_domain_set_desc, + }, + + .info = { + .flags = MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX, + .bus_token = DOMAIN_BUS_PCI_DEVICE_MSIX, + }, +}; + +static bool pci_match_device_domain(struct pci_dev *pdev, enum irq_domain_bus_token bus_token) +{ + return msi_match_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, bus_token); +} + +static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_domain_template *tmpl, + unsigned int hwsize) +{ + struct irq_domain *domain = dev_get_msi_domain(&pdev->dev); + + if (!domain || !irq_domain_is_msi_parent(domain)) + return true; + + return msi_create_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN, tmpl, + hwsize, NULL, NULL); +} + +/** + * pci_setup_msi_device_domain - Setup a device MSI interrupt domain + * @pdev: The PCI device to create the domain on + * + * Return: + * True when: + * - The device does not have a MSI parent irq domain associated, + * which keeps the legacy architecture specific and the global + * PCI/MSI domain models working + * - The MSI domain exists already + * - The MSI domain was successfully allocated + * False when: + * - MSI-X is enabled + * - The domain creation fails. + * + * The created MSI domain is preserved until: + * - The device is removed + * - MSI is disabled and a MSI-X domain is created + */ +bool pci_setup_msi_device_domain(struct pci_dev *pdev) +{ + if (WARN_ON_ONCE(pdev->msix_enabled)) + return false; + + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI)) + return true; + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX)) + msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN); + + return pci_create_device_domain(pdev, &pci_msi_template, 1); +} + +/** + * pci_setup_msix_device_domain - Setup a device MSI-X interrupt domain + * @pdev: The PCI device to create the domain on + * @hwsize: The size of the MSI-X vector table + * + * Return: + * True when: + * - The device does not have a MSI parent irq domain associated, + * which keeps the legacy architecture specific and the global + * PCI/MSI domain models working + * - The MSI-X domain exists already + * - The MSI-X domain was successfully allocated + * False when: + * - MSI is enabled + * - The domain creation fails. + * + * The created MSI-X domain is preserved until: + * - The device is removed + * - MSI-X is disabled and a MSI domain is created + */ +bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize) +{ + if (WARN_ON_ONCE(pdev->msi_enabled)) + return false; + + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX)) + return true; + if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSI)) + msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN); + + return pci_create_device_domain(pdev, &pci_msix_template, hwsize); +} + /** * pci_msi_domain_supports - Check for support of a particular feature flag * @pdev: The PCI device to operate on @@ -152,13 +316,33 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask, { struct msi_domain_info *info; struct irq_domain *domain; + unsigned int supported; domain = dev_get_msi_domain(&pdev->dev); if (!domain || !irq_domain_is_hierarchy(domain)) return mode == ALLOW_LEGACY; - info = domain->host_data; - return (info->flags & feature_mask) == feature_mask; + + if (!irq_domain_is_msi_parent(domain)) { + /* + * For "global" PCI/MSI interrupt domains the associated + * msi_domain_info::flags is the authoritive source of + * information. + */ + info = domain->host_data; + supported = info->flags; + } else { + /* + * For MSI parent domains the supported feature set + * is avaliable in the parent ops. This makes checks + * possible before actually instantiating the + * per device domain because the parent is never + * expanding the PCI/MSI functionality. + */ + supported = domain->msi_parent_ops->supported_flags; + } + + return (supported & feature_mask) == feature_mask; } /* diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 76a3d447e947..b8d74df3817e 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -436,6 +436,9 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, if (rc) return rc; + if (!pci_setup_msi_device_domain(dev)) + return -ENODEV; + for (;;) { if (affd) { nvec = irq_calc_affinity_vectors(minvec, nvec, affd); @@ -787,9 +790,13 @@ int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int if (!pci_msix_validate_entries(dev, entries, nvec, hwsize)) return -EINVAL; - /* PCI_IRQ_VIRTUAL is a horrible hack! */ - if (nvec > hwsize && !(flags & PCI_IRQ_VIRTUAL)) - nvec = hwsize; + if (hwsize < nvec) { + /* Keep the IRQ virtual hackery working */ + if (flags & PCI_IRQ_VIRTUAL) + hwsize = nvec; + else + nvec = hwsize; + } if (nvec < minvec) return -ENOSPC; @@ -798,6 +805,9 @@ int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int if (rc) return rc; + if (!pci_setup_msix_device_domain(dev, hwsize)) + return -ENODEV; + for (;;) { if (affd) { nvec = irq_calc_affinity_vectors(minvec, nvec, affd); diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index 9d75b6fb3e0c..74408cc689c6 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -105,6 +105,8 @@ enum support_mode { }; bool pci_msi_domain_supports(struct pci_dev *dev, unsigned int feature_mask, enum support_mode mode); +bool pci_setup_msi_device_domain(struct pci_dev *pdev); +bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize); /* Legacy (!IRQDOMAIN) fallbacks */ -- cgit v1.2.3 From 45c0402457c1ed2f07ee32dc129ae710e0dc288c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:07 +0100 Subject: PCI/MSI: Remove unused pci_dev_has_special_msi_domain() The check for special MSI domains like VMD which prevents the interrupt remapping code to overwrite device::msi::domain is not longer required and has been replaced by an x86 specific version which is aware of MSI parent domains. Remove it. Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124232326.093093200@linutronix.de --- drivers/pci/msi/irqdomain.c | 21 --------------------- include/linux/msi.h | 1 - 2 files changed, 22 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index be3d50ffc093..473640381f92 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -414,24 +414,3 @@ struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) DOMAIN_BUS_PCI_MSI); return dom; } - -/** - * pci_dev_has_special_msi_domain - Check whether the device is handled by - * a non-standard PCI-MSI domain - * @pdev: The PCI device to check. - * - * Returns: True if the device irqdomain or the bus irqdomain is - * non-standard PCI/MSI. - */ -bool pci_dev_has_special_msi_domain(struct pci_dev *pdev) -{ - struct irq_domain *dom = dev_get_msi_domain(&pdev->dev); - - if (!dom) - dom = dev_get_msi_domain(&pdev->bus->dev); - - if (!dom) - return true; - - return dom->bus_token != DOMAIN_BUS_PCI_MSI; -} diff --git a/include/linux/msi.h b/include/linux/msi.h index b4ab00562a29..b5dda4bf4156 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -617,7 +617,6 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct irq_domain *parent); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); -bool pci_dev_has_special_msi_domain(struct pci_dev *pdev); #else /* CONFIG_PCI_MSI */ static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) { -- cgit v1.2.3 From 612ad43330d98f800f3784d68e7d8ab66d17a512 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:21 +0100 Subject: PCI/MSI: Split MSI-X descriptor setup The upcoming mechanism to allocate MSI-X vectors after enabling MSI-X needs to share some of the MSI-X descriptor setup. The regular descriptor setup on enable has the following code flow: 1) Allocate descriptor 2) Setup descriptor with PCI specific data 3) Insert descriptor 4) Allocate interrupts which in turn scans the inserted descriptors This cannot be easily changed because the PCI/MSI code needs to handle the legacy architecture specific allocation model and the irq domain model where quite some domains have the assumption that the above flow is how it works. Ideally the code flow should look like this: 1) Invoke allocation at the MSI core 2) MSI core allocates descriptor 3) MSI core calls back into the irq domain which fills in the domain specific parts This could be done for underlying parent MSI domains which support post-enable allocation/free but that would create significantly different code pathes for MSI/MSI-X enable. Though for dynamic allocation which wants to share the allocation code with the upcoming PCI/IMS support it's the right thing to do. Split the MSI-X descriptor setup into the preallocation part which just sets the index and fills in the horrible hack of virtual IRQs and the real PCI specific MSI-X setup part which solely depends on the index in the descriptor. This allows to provide a common dynamic allocation interface at the MSI core level for both PCI/MSI-X and PCI/IMS. Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124232326.616292598@linutronix.de --- drivers/pci/msi/msi.c | 72 ++++++++++++++++++++++++++++++++------------------- drivers/pci/msi/msi.h | 2 ++ 2 files changed, 47 insertions(+), 27 deletions(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index b8d74df3817e..1f716624ca56 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -569,34 +569,56 @@ static void __iomem *msix_map_region(struct pci_dev *dev, return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE); } -static int msix_setup_msi_descs(struct pci_dev *dev, void __iomem *base, - struct msix_entry *entries, int nvec, - struct irq_affinity_desc *masks) +/** + * msix_prepare_msi_desc - Prepare a half initialized MSI descriptor for operation + * @dev: The PCI device for which the descriptor is prepared + * @desc: The MSI descriptor for preparation + * + * This is separate from msix_setup_msi_descs() below to handle dynamic + * allocations for MSI-X after initial enablement. + * + * Ideally the whole MSI-X setup would work that way, but there is no way to + * support this for the legacy arch_setup_msi_irqs() mechanism and for the + * fake irq domains like the x86 XEN one. Sigh... + * + * The descriptor is zeroed and only @desc::msi_index and @desc::affinity + * are set. When called from msix_setup_msi_descs() then the is_virtual + * attribute is initialized as well. + * + * Fill in the rest. + */ +void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc) +{ + desc->nvec_used = 1; + desc->pci.msi_attrib.is_msix = 1; + desc->pci.msi_attrib.is_64 = 1; + desc->pci.msi_attrib.default_irq = dev->irq; + desc->pci.mask_base = dev->msix_base; + desc->pci.msi_attrib.can_mask = !pci_msi_ignore_mask && + !desc->pci.msi_attrib.is_virtual; + + if (desc->pci.msi_attrib.can_mask) { + void __iomem *addr = pci_msix_desc_addr(desc); + + desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + } +} + +static int msix_setup_msi_descs(struct pci_dev *dev, struct msix_entry *entries, + int nvec, struct irq_affinity_desc *masks) { int ret = 0, i, vec_count = pci_msix_vec_count(dev); struct irq_affinity_desc *curmsk; struct msi_desc desc; - void __iomem *addr; memset(&desc, 0, sizeof(desc)); - desc.nvec_used = 1; - desc.pci.msi_attrib.is_msix = 1; - desc.pci.msi_attrib.is_64 = 1; - desc.pci.msi_attrib.default_irq = dev->irq; - desc.pci.mask_base = base; - for (i = 0, curmsk = masks; i < nvec; i++, curmsk++) { desc.msi_index = entries ? entries[i].entry : i; desc.affinity = masks ? curmsk : NULL; desc.pci.msi_attrib.is_virtual = desc.msi_index >= vec_count; - desc.pci.msi_attrib.can_mask = !pci_msi_ignore_mask && - !desc.pci.msi_attrib.is_virtual; - if (desc.pci.msi_attrib.can_mask) { - addr = pci_msix_desc_addr(&desc); - desc.pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); - } + msix_prepare_msi_desc(dev, &desc); ret = msi_insert_msi_desc(&dev->dev, &desc); if (ret) @@ -629,9 +651,8 @@ static void msix_mask_all(void __iomem *base, int tsize) writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); } -static int msix_setup_interrupts(struct pci_dev *dev, void __iomem *base, - struct msix_entry *entries, int nvec, - struct irq_affinity *affd) +static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries, + int nvec, struct irq_affinity *affd) { struct irq_affinity_desc *masks = NULL; int ret; @@ -640,7 +661,7 @@ static int msix_setup_interrupts(struct pci_dev *dev, void __iomem *base, masks = irq_create_affinity_masks(nvec, affd); msi_lock_descs(&dev->dev); - ret = msix_setup_msi_descs(dev, base, entries, nvec, masks); + ret = msix_setup_msi_descs(dev, entries, nvec, masks); if (ret) goto out_free; @@ -678,7 +699,6 @@ out_unlock: static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd) { - void __iomem *base; int ret, tsize; u16 control; @@ -696,15 +716,13 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); /* Request & Map MSI-X table region */ tsize = msix_table_size(control); - base = msix_map_region(dev, tsize); - if (!base) { + dev->msix_base = msix_map_region(dev, tsize); + if (!dev->msix_base) { ret = -ENOMEM; goto out_disable; } - dev->msix_base = base; - - ret = msix_setup_interrupts(dev, base, entries, nvec, affd); + ret = msix_setup_interrupts(dev, entries, nvec, affd); if (ret) goto out_disable; @@ -719,7 +737,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, * which takes the MSI-X mask bits into account even * when MSI-X is disabled, which prevents MSI delivery. */ - msix_mask_all(base, tsize); + msix_mask_all(dev->msix_base, tsize); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); pcibios_free_irq(dev); diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index 74408cc689c6..ee53cf079f4e 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -84,6 +84,8 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; } +void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc); + /* Subsystem variables */ extern int pci_msi_enable; -- cgit v1.2.3 From 73bd063ca03493f44e0700cc08824093da9741bc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:23 +0100 Subject: PCI/MSI: Provide prepare_desc() MSI domain op The setup of MSI descriptors for PCI/MSI-X interrupts depends partially on the MSI index for which the descriptor is initialized. Dynamic MSI-X vector allocation post MSI-X enablement allows to allocate vectors at a given index or at any free index in the available table range. The latter requires that the descriptor is initialized after the MSI core has chosen an index. Implement the prepare_desc() op in the PCI/MSI-X specific msi_domain_ops which is invoked before the core interrupt descriptor and the associated Linux interrupt number is allocated. That callback is also provided for the upcoming PCI/IMS implementations so the implementation specific interrupt domain can do their domain specific initialization of the MSI descriptors. Signed-off-by: Thomas Gleixner Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124232326.673658806@linutronix.de --- drivers/pci/msi/irqdomain.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 473640381f92..8afaef10b939 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -202,6 +202,14 @@ static void pci_irq_unmask_msix(struct irq_data *data) pci_msix_unmask(irq_data_get_msi_desc(data)); } +static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg, + struct msi_desc *desc) +{ + /* Don't fiddle with preallocated MSI descriptors */ + if (!desc->pci.mask_base) + msix_prepare_msi_desc(to_pci_dev(desc->dev), desc); +} + static const struct msi_domain_template pci_msix_template = { .chip = { .name = "PCI-MSIX", @@ -212,6 +220,7 @@ static const struct msi_domain_template pci_msix_template = { }, .ops = { + .prepare_desc = pci_msix_prepare_desc, .set_desc = pci_device_domain_set_desc, }, -- cgit v1.2.3 From 34026364df8eca05ee32e706a2c014511a19af02 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:24 +0100 Subject: PCI/MSI: Provide post-enable dynamic allocation interfaces for MSI-X MSI-X vectors can be allocated after the initial MSI-X enablement, but this needs explicit support of the underlying interrupt domains. Provide a function to query the ability and functions to allocate/free individual vectors post-enable. The allocation can either request a specific index in the MSI-X table or with the index argument MSI_ANY_INDEX it allocates the next free vector. The return value is a struct msi_map which on success contains both index and the Linux interrupt number. In case of failure index is negative and the Linux interrupt number is 0. The allocation function is for a single MSI-X index at a time as that's sufficient for the most urgent use case VFIO to get rid of the 'disable MSI-X, reallocate, enable-MSI-X' cycle which is prone to lost interrupts and redirections to the legacy and obviously unhandled INTx. As single index allocation is also sufficient for the use cases Jason Gunthorpe pointed out: Allocation of a MSI-X or IMS vector for a network queue. See Link below. Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/all/20211126232735.547996838@linutronix.de Link: https://lore.kernel.org/r/20221124232326.731233614@linutronix.de --- drivers/pci/msi/api.c | 67 +++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/msi/irqdomain.c | 3 +- include/linux/pci.h | 6 ++++ 3 files changed, 75 insertions(+), 1 deletion(-) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 2d46a0cfd541..c8816db91e9c 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -112,6 +112,73 @@ int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, } EXPORT_SYMBOL(pci_enable_msix_range); +/** + * pci_msix_can_alloc_dyn - Query whether dynamic allocation after enabling + * MSI-X is supported + * + * @dev: PCI device to operate on + * + * Return: True if supported, false otherwise + */ +bool pci_msix_can_alloc_dyn(struct pci_dev *dev) +{ + if (!dev->msix_cap) + return false; + + return pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX_ALLOC_DYN, DENY_LEGACY); +} +EXPORT_SYMBOL_GPL(pci_msix_can_alloc_dyn); + +/** + * pci_msix_alloc_irq_at - Allocate an MSI-X interrupt after enabling MSI-X + * at a given MSI-X vector index or any free vector index + * + * @dev: PCI device to operate on + * @index: Index to allocate. If @index == MSI_ANY_INDEX this allocates + * the next free index in the MSI-X table + * @affdesc: Optional pointer to an affinity descriptor structure. NULL otherwise + * + * Return: A struct msi_map + * + * On success msi_map::index contains the allocated index (>= 0) and + * msi_map::virq contains the allocated Linux interrupt number (> 0). + * + * On fail msi_map::index contains the error code and msi_map::virq + * is set to 0. + */ +struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, + const struct irq_affinity_desc *affdesc) +{ + struct msi_map map = { .index = -ENOTSUPP }; + + if (!dev->msix_enabled) + return map; + + if (!pci_msix_can_alloc_dyn(dev)) + return map; + + return msi_domain_alloc_irq_at(&dev->dev, MSI_DEFAULT_DOMAIN, index, affdesc, NULL); +} +EXPORT_SYMBOL_GPL(pci_msix_alloc_irq_at); + +/** + * pci_msix_free_irq - Free an interrupt on a PCI/MSIX interrupt domain + * which was allocated via pci_msix_alloc_irq_at() + * + * @dev: The PCI device to operate on + * @map: A struct msi_map describing the interrupt to free + * as returned from the allocation function. + */ +void pci_msix_free_irq(struct pci_dev *dev, struct msi_map map) +{ + if (WARN_ON_ONCE(map.index < 0 || map.virq <= 0)) + return; + if (WARN_ON_ONCE(!pci_msix_can_alloc_dyn(dev))) + return; + msi_domain_free_irqs_range(&dev->dev, MSI_DEFAULT_DOMAIN, map.index, map.index); +} +EXPORT_SYMBOL_GPL(pci_msix_free_irq); + /** * pci_disable_msix() - Disable MSI-X interrupt mode on device * @dev: the PCI device to operate on diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 8afaef10b939..deb1930b4e66 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -225,7 +225,8 @@ static const struct msi_domain_template pci_msix_template = { }, .info = { - .flags = MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX, + .flags = MSI_COMMON_FLAGS | MSI_FLAG_PCI_MSIX | + MSI_FLAG_PCI_MSIX_ALLOC_DYN, .bus_token = DOMAIN_BUS_PCI_DEVICE_MSIX, }, }; diff --git a/include/linux/pci.h b/include/linux/pci.h index 243e48f79e82..68b14ba93df2 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -38,6 +38,7 @@ #include #include #include +#include #include #include @@ -1559,6 +1560,11 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, unsigned int max_vecs, unsigned int flags, struct irq_affinity *affd); +bool pci_msix_can_alloc_dyn(struct pci_dev *dev); +struct msi_map pci_msix_alloc_irq_at(struct pci_dev *dev, unsigned int index, + const struct irq_affinity_desc *affdesc); +void pci_msix_free_irq(struct pci_dev *pdev, struct msi_map map); + void pci_free_irq_vectors(struct pci_dev *dev); int pci_irq_vector(struct pci_dev *dev, unsigned int nr); const struct cpumask *pci_irq_get_affinity(struct pci_dev *pdev, int vec); -- cgit v1.2.3 From 0194425af0c87acaad457989a2c6d90dba58e776 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:29 +0100 Subject: PCI/MSI: Provide IMS (Interrupt Message Store) support IMS (Interrupt Message Store) is a new specification which allows implementation specific storage of MSI messages contrary to the strict standard specified MSI and MSI-X message stores. This requires new device specific interrupt domains to handle the implementation defined storage which can be an array in device memory or host/guest memory which is shared with hardware queues. Add a function to create IMS domains for PCI devices. IMS domains are using the new per device domain mechanism and are configured by the device driver via a template. IMS domains are created as secondary device domains so they work side on side with MSI[-X] on the same device. The IMS domains have a few constraints: - The index space is managed by the core code. Device memory based IMS provides a storage array with a fixed size which obviously requires an index. But there is no association between index and functionality so the core can randomly allocate an index in the array. System memory based IMS does not have the concept of an index as the storage is somewhere in memory. In that case the index is purely software based to keep track of the allocations. - There is no requirement for consecutive index ranges This is currently a limitation of the MSI core and can be implemented if there is a justified use case by changing the internal storage from xarray to maple_tree. For now it's single vector allocation. - The interrupt chip must provide the following callbacks: - irq_mask() - irq_unmask() - irq_write_msi_msg() - The interrupt chip must provide the following optional callbacks when the irq_mask(), irq_unmask() and irq_write_msi_msg() callbacks cannot operate directly on hardware, e.g. in the case that the interrupt message store is in queue memory: - irq_bus_lock() - irq_bus_unlock() These callbacks are invoked from preemptible task context and are allowed to sleep. In this case the mandatory callbacks above just store the information. The irq_bus_unlock() callback is supposed to make the change effective before returning. - Interrupt affinity setting is handled by the underlying parent interrupt domain and communicated to the IMS domain via irq_write_msi_msg(). IMS domains cannot have a irq_set_affinity() callback. That's a reasonable restriction similar to the PCI/MSI device domain implementations. The domain is automatically destroyed when the PCI device is removed. Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124232326.904316841@linutronix.de --- drivers/pci/msi/irqdomain.c | 59 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 5 ++++ 2 files changed, 64 insertions(+) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index deb1930b4e66..e33bcc872699 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -355,6 +355,65 @@ bool pci_msi_domain_supports(struct pci_dev *pdev, unsigned int feature_mask, return (supported & feature_mask) == feature_mask; } +/** + * pci_create_ims_domain - Create a secondary IMS domain for a PCI device + * @pdev: The PCI device to operate on + * @template: The MSI info template which describes the domain + * @hwsize: The size of the hardware entry table or 0 if the domain + * is purely software managed + * @data: Optional pointer to domain specific data to be stored + * in msi_domain_info::data + * + * Return: True on success, false otherwise + * + * An IMS domain is expected to have the following constraints: + * - The index space is managed by the core code + * + * - There is no requirement for consecutive index ranges + * + * - The interrupt chip must provide the following callbacks: + * - irq_mask() + * - irq_unmask() + * - irq_write_msi_msg() + * + * - The interrupt chip must provide the following optional callbacks + * when the irq_mask(), irq_unmask() and irq_write_msi_msg() callbacks + * cannot operate directly on hardware, e.g. in the case that the + * interrupt message store is in queue memory: + * - irq_bus_lock() + * - irq_bus_unlock() + * + * These callbacks are invoked from preemptible task context and are + * allowed to sleep. In this case the mandatory callbacks above just + * store the information. The irq_bus_unlock() callback is supposed + * to make the change effective before returning. + * + * - Interrupt affinity setting is handled by the underlying parent + * interrupt domain and communicated to the IMS domain via + * irq_write_msi_msg(). + * + * The domain is automatically destroyed when the PCI device is removed. + */ +bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, + unsigned int hwsize, void *data) +{ + struct irq_domain *domain = dev_get_msi_domain(&pdev->dev); + + if (!domain || !irq_domain_is_msi_parent(domain)) + return false; + + if (template->info.bus_token != DOMAIN_BUS_PCI_DEVICE_IMS || + !(template->info.flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS) || + !(template->info.flags & MSI_FLAG_FREE_MSI_DESCS) || + !template->chip.irq_mask || !template->chip.irq_unmask || + !template->chip.irq_write_msi_msg || template->chip.irq_set_affinity) + return false; + + return msi_create_device_irq_domain(&pdev->dev, MSI_SECONDARY_DOMAIN, template, + hwsize, data, NULL); +} +EXPORT_SYMBOL_GPL(pci_create_ims_domain); + /* * Users of the generic MSI infrastructure expect a device to have a single ID, * so with DMA aliases we have to pick the least-worst compromise. Devices with diff --git a/include/linux/pci.h b/include/linux/pci.h index 68b14ba93df2..1592b630d919 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2487,6 +2487,11 @@ static inline bool pci_is_thunderbolt_attached(struct pci_dev *pdev) void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type); #endif +struct msi_domain_template; + +bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, + unsigned int hwsize, void *data); + #include #define pci_printk(level, pdev, fmt, arg...) \ -- cgit v1.2.3 From c9e5bea273834a63b5e9ba90ad94b305ba50704e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 25 Nov 2022 00:26:31 +0100 Subject: PCI/MSI: Provide pci_ims_alloc/free_irq() Single vector allocation which allocates the next free index in the IMS space. The free function releases. All allocated vectors are released also via pci_free_vectors() which is also releasing MSI/MSI-X vectors. Signed-off-by: Thomas Gleixner Reviewed-by: Kevin Tian Acked-by: Bjorn Helgaas Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20221124232326.961711347@linutronix.de --- drivers/pci/msi/api.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pci.h | 3 +++ 2 files changed, 53 insertions(+) (limited to 'drivers/pci') diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index c8816db91e9c..b8009aa11f3c 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -365,6 +365,56 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) } EXPORT_SYMBOL(pci_irq_get_affinity); +/** + * pci_ims_alloc_irq - Allocate an interrupt on a PCI/IMS interrupt domain + * @dev: The PCI device to operate on + * @icookie: Pointer to an IMS implementation specific cookie for this + * IMS instance (PASID, queue ID, pointer...). + * The cookie content is copied into the MSI descriptor for the + * interrupt chip callbacks or domain specific setup functions. + * @affdesc: Optional pointer to an interrupt affinity descriptor + * + * There is no index for IMS allocations as IMS is an implementation + * specific storage and does not have any direct associations between + * index, which might be a pure software construct, and device + * functionality. This association is established by the driver either via + * the index - if there is a hardware table - or in case of purely software + * managed IMS implementation the association happens via the + * irq_write_msi_msg() callback of the implementation specific interrupt + * chip, which utilizes the provided @icookie to store the MSI message in + * the appropriate place. + * + * Return: A struct msi_map + * + * On success msi_map::index contains the allocated index (>= 0) and + * msi_map::virq the allocated Linux interrupt number (> 0). + * + * On fail msi_map::index contains the error code and msi_map::virq + * is set to 0. + */ +struct msi_map pci_ims_alloc_irq(struct pci_dev *dev, union msi_instance_cookie *icookie, + const struct irq_affinity_desc *affdesc) +{ + return msi_domain_alloc_irq_at(&dev->dev, MSI_SECONDARY_DOMAIN, MSI_ANY_INDEX, + affdesc, icookie); +} +EXPORT_SYMBOL_GPL(pci_ims_alloc_irq); + +/** + * pci_ims_free_irq - Allocate an interrupt on a PCI/IMS interrupt domain + * which was allocated via pci_ims_alloc_irq() + * @dev: The PCI device to operate on + * @map: A struct msi_map describing the interrupt to free as + * returned from pci_ims_alloc_irq() + */ +void pci_ims_free_irq(struct pci_dev *dev, struct msi_map map) +{ + if (WARN_ON_ONCE(map.index < 0 || map.virq <= 0)) + return; + msi_domain_free_irqs_range(&dev->dev, MSI_SECONDARY_DOMAIN, map.index, map.index); +} +EXPORT_SYMBOL_GPL(pci_ims_free_irq); + /** * pci_free_irq_vectors() - Free previously allocated IRQs for a device * @dev: the PCI device to operate on diff --git a/include/linux/pci.h b/include/linux/pci.h index 1592b630d919..aa514b54c681 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2491,6 +2491,9 @@ struct msi_domain_template; bool pci_create_ims_domain(struct pci_dev *pdev, const struct msi_domain_template *template, unsigned int hwsize, void *data); +struct msi_map pci_ims_alloc_irq(struct pci_dev *pdev, union msi_instance_cookie *icookie, + const struct irq_affinity_desc *affdesc); +void pci_ims_free_irq(struct pci_dev *pdev, struct msi_map map); #include -- cgit v1.2.3