diff options
53 files changed, 1924 insertions, 351 deletions
diff --git a/Documentation/IRQ-domain.txt b/Documentation/IRQ-domain.txt index 8a8b82c9ca53..39cfa72732ff 100644 --- a/Documentation/IRQ-domain.txt +++ b/Documentation/IRQ-domain.txt @@ -151,3 +151,74 @@ used and no descriptor gets allocated it is very important to make sure that the driver using the simple domain call irq_create_mapping() before any irq_find_mapping() since the latter will actually work for the static IRQ assignment case. + +==== Hierarchy IRQ domain ==== +On some architectures, there may be multiple interrupt controllers +involved in delivering an interrupt from the device to the target CPU. +Let's look at a typical interrupt delivering path on x86 platforms: + +Device --> IOAPIC -> Interrupt remapping Controller -> Local APIC -> CPU + +There are three interrupt controllers involved: +1) IOAPIC controller +2) Interrupt remapping controller +3) Local APIC controller + +To support such a hardware topology and make software architecture match +hardware architecture, an irq_domain data structure is built for each +interrupt controller and those irq_domains are organized into hierarchy. +When building irq_domain hierarchy, the irq_domain near to the device is +child and the irq_domain near to CPU is parent. So a hierarchy structure +as below will be built for the example above. + CPU Vector irq_domain (root irq_domain to manage CPU vectors) + ^ + | + Interrupt Remapping irq_domain (manage irq_remapping entries) + ^ + | + IOAPIC irq_domain (manage IOAPIC delivery entries/pins) + +There are four major interfaces to use hierarchy irq_domain: +1) irq_domain_alloc_irqs(): allocate IRQ descriptors and interrupt + controller related resources to deliver these interrupts. +2) irq_domain_free_irqs(): free IRQ descriptors and interrupt controller + related resources associated with these interrupts. +3) irq_domain_activate_irq(): activate interrupt controller hardware to + deliver the interrupt. +3) irq_domain_deactivate_irq(): deactivate interrupt controller hardware + to stop delivering the interrupt. + +Following changes are needed to support hierarchy irq_domain. +1) a new field 'parent' is added to struct irq_domain; it's used to + maintain irq_domain hierarchy information. +2) a new field 'parent_data' is added to struct irq_data; it's used to + build hierarchy irq_data to match hierarchy irq_domains. The irq_data + is used to store irq_domain pointer and hardware irq number. +3) new callbacks are added to struct irq_domain_ops to support hierarchy + irq_domain operations. + +With support of hierarchy irq_domain and hierarchy irq_data ready, an +irq_domain structure is built for each interrupt controller, and an +irq_data structure is allocated for each irq_domain associated with an +IRQ. Now we could go one step further to support stacked(hierarchy) +irq_chip. That is, an irq_chip is associated with each irq_data along +the hierarchy. A child irq_chip may implement a required action by +itself or by cooperating with its parent irq_chip. + +With stacked irq_chip, interrupt controller driver only needs to deal +with the hardware managed by itself and may ask for services from its +parent irq_chip when needed. So we could achieve a much cleaner +software architecture. + +For an interrupt controller driver to support hierarchy irq_domain, it +needs to: +1) Implement irq_domain_ops.alloc and irq_domain_ops.free +2) Optionally implement irq_domain_ops.activate and + irq_domain_ops.deactivate. +3) Optionally implement an irq_chip to manage the interrupt controller + hardware. +4) No need to implement irq_domain_ops.map and irq_domain_ops.unmap, + they are unused with hierarchy irq_domain. + +Hierarchy irq_domain may also be used to support other architectures, +such as ARM, ARM64 etc. diff --git a/arch/arm/include/asm/mach/pci.h b/arch/arm/include/asm/mach/pci.h index 7fc42784becb..8292b5f81e23 100644 --- a/arch/arm/include/asm/mach/pci.h +++ b/arch/arm/include/asm/mach/pci.h @@ -22,6 +22,9 @@ struct hw_pci { #ifdef CONFIG_PCI_DOMAINS int domain; #endif +#ifdef CONFIG_PCI_MSI + struct msi_controller *msi_ctrl; +#endif struct pci_ops *ops; int nr_controllers; void **private_data; @@ -36,8 +39,6 @@ struct hw_pci { resource_size_t start, resource_size_t size, resource_size_t align); - void (*add_bus)(struct pci_bus *bus); - void (*remove_bus)(struct pci_bus *bus); }; /* @@ -47,6 +48,9 @@ struct pci_sys_data { #ifdef CONFIG_PCI_DOMAINS int domain; #endif +#ifdef CONFIG_PCI_MSI + struct msi_controller *msi_ctrl; +#endif struct list_head node; int busnr; /* primary bus number */ u64 mem_offset; /* bus->cpu memory mapping offset */ @@ -65,8 +69,6 @@ struct pci_sys_data { resource_size_t start, resource_size_t size, resource_size_t align); - void (*add_bus)(struct pci_bus *bus); - void (*remove_bus)(struct pci_bus *bus); void *private_data; /* platform controller private data */ }; diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 17a26c17f7f5..daaff73bc776 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -18,6 +18,15 @@ static int debug_pci; +#ifdef CONFIG_PCI_MSI +struct msi_controller *pcibios_msi_controller(struct pci_dev *dev) +{ + struct pci_sys_data *sysdata = dev->bus->sysdata; + + return sysdata->msi_ctrl; +} +#endif + /* * We can't use pci_get_device() here since we are * called from interrupt context. @@ -360,20 +369,6 @@ void pcibios_fixup_bus(struct pci_bus *bus) } EXPORT_SYMBOL(pcibios_fixup_bus); -void pcibios_add_bus(struct pci_bus *bus) -{ - struct pci_sys_data *sys = bus->sysdata; - if (sys->add_bus) - sys->add_bus(bus); -} - -void pcibios_remove_bus(struct pci_bus *bus) -{ - struct pci_sys_data *sys = bus->sysdata; - if (sys->remove_bus) - sys->remove_bus(bus); -} - /* * Swizzle the device pin each time we cross a bridge. If a platform does * not provide a swizzle function, we perform the standard PCI swizzling. @@ -471,12 +466,13 @@ static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, #ifdef CONFIG_PCI_DOMAINS sys->domain = hw->domain; #endif +#ifdef CONFIG_PCI_MSI + sys->msi_ctrl = hw->msi_ctrl; +#endif sys->busnr = busnr; sys->swizzle = hw->swizzle; sys->map_irq = hw->map_irq; sys->align_resource = hw->align_resource; - sys->add_bus = hw->add_bus; - sys->remove_bus = hw->remove_bus; INIT_LIST_HEAD(&sys->resources); if (hw->private_data) diff --git a/arch/arm/mach-iop13xx/msi.c b/arch/arm/mach-iop13xx/msi.c index e7730cf9c15d..9f89e76dfbb9 100644 --- a/arch/arm/mach-iop13xx/msi.c +++ b/arch/arm/mach-iop13xx/msi.c @@ -126,10 +126,10 @@ static void iop13xx_msi_nop(struct irq_data *d) static struct irq_chip iop13xx_msi_chip = { .name = "PCI-MSI", .irq_ack = iop13xx_msi_nop, - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, }; int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) @@ -153,7 +153,7 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) id = iop13xx_cpu_id(); msg.data = (id << IOP13XX_MU_MIMR_CORE_SELECT) | (irq & 0x7f); - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); irq_set_chip_and_handler(irq, &iop13xx_msi_chip, handle_simple_irq); return 0; diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c index 8c3730c3c63d..8ae36ea177d3 100644 --- a/arch/ia64/kernel/msi_ia64.c +++ b/arch/ia64/kernel/msi_ia64.c @@ -35,7 +35,7 @@ static int ia64_set_msi_irq_affinity(struct irq_data *idata, data |= MSI_DATA_VECTOR(irq_to_vector(irq)); msg.data = data; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); cpumask_copy(idata->affinity, cpumask_of(cpu)); return 0; @@ -71,7 +71,7 @@ int ia64_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) MSI_DATA_DELIVERY_FIXED | MSI_DATA_VECTOR(vector); - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); irq_set_chip_and_handler(irq, &ia64_msi_chip, handle_edge_irq); return 0; @@ -102,8 +102,8 @@ static int ia64_msi_retrigger_irq(struct irq_data *data) */ static struct irq_chip ia64_msi_chip = { .name = "PCI-MSI", - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, .irq_ack = ia64_ack_msi_irq, #ifdef CONFIG_SMP .irq_set_affinity = ia64_set_msi_irq_affinity, diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c index 446e7799928c..a0eb27b66d13 100644 --- a/arch/ia64/sn/kernel/msi_sn.c +++ b/arch/ia64/sn/kernel/msi_sn.c @@ -145,7 +145,7 @@ int sn_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *entry) msg.data = 0x100 + irq; irq_set_msi_desc(irq, entry); - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); irq_set_chip_and_handler(irq, &sn_msi_chip, handle_edge_irq); return 0; @@ -205,7 +205,7 @@ static int sn_set_msi_irq_affinity(struct irq_data *data, msg.address_hi = (u32)(bus_addr >> 32); msg.address_lo = (u32)(bus_addr & 0x00000000ffffffff); - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); cpumask_copy(data->affinity, cpu_mask); return 0; @@ -228,8 +228,8 @@ static int sn_msi_retrigger_irq(struct irq_data *data) static struct irq_chip sn_msi_chip = { .name = "PCI-MSI", - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, .irq_ack = sn_ack_msi_irq, #ifdef CONFIG_SMP .irq_set_affinity = sn_set_msi_irq_affinity, diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c index 63bbe07a1ccd..cffaaf4aae3c 100644 --- a/arch/mips/pci/msi-octeon.c +++ b/arch/mips/pci/msi-octeon.c @@ -178,7 +178,7 @@ msi_irq_allocated: pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); irq_set_msi_desc(irq, desc); - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); return 0; } diff --git a/arch/mips/pci/msi-xlp.c b/arch/mips/pci/msi-xlp.c index f7ac3edda1b2..6a40f24c91b4 100644 --- a/arch/mips/pci/msi-xlp.c +++ b/arch/mips/pci/msi-xlp.c @@ -217,7 +217,7 @@ static void xlp_msix_mask_ack(struct irq_data *d) msixvec = nlm_irq_msixvec(d->irq); link = nlm_irq_msixlink(msixvec); - mask_msi_irq(d); + pci_msi_mask_irq(d); md = irq_data_get_irq_handler_data(d); /* Ack MSI on bridge */ @@ -239,10 +239,10 @@ static void xlp_msix_mask_ack(struct irq_data *d) static struct irq_chip xlp_msix_chip = { .name = "XLP-MSIX", - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, .irq_mask_ack = xlp_msix_mask_ack, - .irq_unmask = unmask_msi_irq, + .irq_unmask = pci_msi_unmask_irq, }; void arch_teardown_msi_irq(unsigned int irq) @@ -345,7 +345,7 @@ static int xlp_setup_msi(uint64_t lnkbase, int node, int link, if (ret < 0) return ret; - write_msi_msg(xirq, &msg); + pci_write_msi_msg(xirq, &msg); return 0; } @@ -446,7 +446,7 @@ static int xlp_setup_msix(uint64_t lnkbase, int node, int link, if (ret < 0) return ret; - write_msi_msg(xirq, &msg); + pci_write_msi_msg(xirq, &msg); return 0; } diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c index 0dde80332d3a..26d2dabef281 100644 --- a/arch/mips/pci/pci-xlr.c +++ b/arch/mips/pci/pci-xlr.c @@ -260,7 +260,7 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) if (ret < 0) return ret; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); return 0; } #endif diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 862b32702d29..0883994df384 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -279,7 +279,7 @@ static int axon_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) irq_set_msi_desc(virq, entry); msg.data = virq; - write_msi_msg(virq, &msg); + pci_write_msi_msg(virq, &msg); } return 0; @@ -301,9 +301,9 @@ static void axon_msi_teardown_msi_irqs(struct pci_dev *dev) } static struct irq_chip msic_irq_chip = { - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, - .irq_shutdown = mask_msi_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, + .irq_shutdown = pci_msi_mask_irq, .name = "AXON-MSI", }; diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 4b20f2c6b3b2..540fc6dd56b3 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -90,7 +90,7 @@ static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return rc; } irq_set_msi_desc(virq, entry); - write_msi_msg(virq, &msg); + pci_write_msi_msg(virq, &msg); } return 0; } diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 8b909e94fd9a..691a154c286d 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -476,7 +476,7 @@ again: irq_set_msi_desc(virq, entry); /* Read config space back so we can restore after reset */ - __read_msi_msg(entry, &msg); + __pci_read_msi_msg(entry, &msg); entry->msg = msg; } diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index da08ed088157..7aed8d0876b7 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -82,8 +82,8 @@ static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p) static struct irq_chip fsl_msi_chip = { - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, .irq_ack = fsl_msi_end_irq, .irq_print_chip = fsl_msi_print_chip, }; @@ -242,7 +242,7 @@ static int fsl_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) irq_set_msi_desc(virq, entry); fsl_compose_msi_msg(pdev, hwirq, &msg, msi_data); - write_msi_msg(virq, &msg); + pci_write_msi_msg(virq, &msg); } return 0; diff --git a/arch/powerpc/sysdev/mpic_pasemi_msi.c b/arch/powerpc/sysdev/mpic_pasemi_msi.c index 15dccd35fa11..45c114bc430b 100644 --- a/arch/powerpc/sysdev/mpic_pasemi_msi.c +++ b/arch/powerpc/sysdev/mpic_pasemi_msi.c @@ -42,7 +42,7 @@ static struct mpic *msi_mpic; static void mpic_pasemi_msi_mask_irq(struct irq_data *data) { pr_debug("mpic_pasemi_msi_mask_irq %d\n", data->irq); - mask_msi_irq(data); + pci_msi_mask_irq(data); mpic_mask_irq(data); } @@ -50,7 +50,7 @@ static void mpic_pasemi_msi_unmask_irq(struct irq_data *data) { pr_debug("mpic_pasemi_msi_unmask_irq %d\n", data->irq); mpic_unmask_irq(data); - unmask_msi_irq(data); + pci_msi_unmask_irq(data); } static struct irq_chip mpic_pasemi_msi_chip = { @@ -136,7 +136,7 @@ static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) * register to generate MSI [512...1023] */ msg.data = hwirq-0x200; - write_msi_msg(virq, &msg); + pci_write_msi_msg(virq, &msg); } return 0; diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c index 623d7fba15b4..0dff1cd44481 100644 --- a/arch/powerpc/sysdev/mpic_u3msi.c +++ b/arch/powerpc/sysdev/mpic_u3msi.c @@ -25,14 +25,14 @@ static struct mpic *msi_mpic; static void mpic_u3msi_mask_irq(struct irq_data *data) { - mask_msi_irq(data); + pci_msi_mask_irq(data); mpic_mask_irq(data); } static void mpic_u3msi_unmask_irq(struct irq_data *data) { mpic_unmask_irq(data); - unmask_msi_irq(data); + pci_msi_unmask_irq(data); } static struct irq_chip mpic_u3msi_chip = { @@ -171,7 +171,7 @@ static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) printk("u3msi: allocated virq 0x%x (hw 0x%x) addr 0x%lx\n", virq, hwirq, (unsigned long)addr); msg.data = hwirq; - write_msi_msg(virq, &msg); + pci_write_msi_msg(virq, &msg); hwirq++; } diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c index a6a4dbda9078..908105f835d1 100644 --- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c +++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c @@ -85,7 +85,7 @@ static int hsta_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) msi_bitmap_free_hwirqs(&ppc4xx_hsta_msi.bmp, irq, 1); return -EINVAL; } - write_msi_msg(hwirq, &msg); + pci_write_msi_msg(hwirq, &msg); } return 0; diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c index 22b5200636e7..518eabbe0bdc 100644 --- a/arch/powerpc/sysdev/ppc4xx_msi.c +++ b/arch/powerpc/sysdev/ppc4xx_msi.c @@ -116,7 +116,7 @@ static int ppc4xx_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) irq_set_msi_desc(virq, entry); msg.data = int_no; - write_msi_msg(virq, &msg); + pci_write_msi_msg(virq, &msg); } return 0; } diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index 3c6ee1b64e5d..4ba554ec8eaf 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -73,7 +73,7 @@ static unsigned int ics_opal_startup(struct irq_data *d) * at that level, so we do it here by hand. */ if (d->msi_desc) - unmask_msi_irq(d); + pci_msi_unmask_irq(d); #endif /* unmask it */ diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c index 936575d99c5c..bc81335b2cbc 100644 --- a/arch/powerpc/sysdev/xics/ics-rtas.c +++ b/arch/powerpc/sysdev/xics/ics-rtas.c @@ -76,7 +76,7 @@ static unsigned int ics_rtas_startup(struct irq_data *d) * at that level, so we do it here by hand. */ if (d->msi_desc) - unmask_msi_irq(d); + pci_msi_unmask_irq(d); #endif /* unmask it */ ics_rtas_unmask_irq(d); diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 2fa7b14b9c08..d59c82569750 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -50,8 +50,8 @@ static DEFINE_SPINLOCK(zpci_list_lock); static struct irq_chip zpci_irq_chip = { .name = "zPCI", - .irq_unmask = unmask_msi_irq, - .irq_mask = mask_msi_irq, + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, }; static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); @@ -403,7 +403,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) msg.data = hwirq; msg.address_lo = zdev->msi_addr & 0xffffffff; msg.address_hi = zdev->msi_addr >> 32; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); airq_iv_set_data(zdev->aibv, hwirq, irq); hwirq++; } @@ -448,9 +448,9 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) /* Release MSI interrupts */ list_for_each_entry(msi, &pdev->msi_list, list) { if (msi->msi_attrib.is_msix) - default_msix_mask_irq(msi, 1); + __pci_msix_desc_mask_irq(msi, 1); else - default_msi_mask_irq(msi, 1, 1); + __pci_msi_desc_mask_irq(msi, 1, 1); irq_set_msi_desc(msi->irq, NULL); irq_free_desc(msi->irq); msi->msg.address_lo = 0; diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c index 580651af73f2..84e16d81a6d8 100644 --- a/arch/sparc/kernel/pci_msi.c +++ b/arch/sparc/kernel/pci_msi.c @@ -111,10 +111,10 @@ static void free_msi(struct pci_pbm_info *pbm, int msi_num) static struct irq_chip msi_irq = { .name = "PCI-MSI", - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, /* XXX affinity XXX */ }; @@ -161,7 +161,7 @@ static int sparc64_setup_msi_irq(unsigned int *irq_p, msg.data = msi; irq_set_msi_desc(*irq_p, entry); - write_msi_msg(*irq_p, &msg); + pci_write_msi_msg(*irq_p, &msg); return 0; diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c index e39f9c542807..e717af20dada 100644 --- a/arch/tile/kernel/pci_gx.c +++ b/arch/tile/kernel/pci_gx.c @@ -1453,7 +1453,7 @@ static struct pci_ops tile_cfg_ops = { static unsigned int tilegx_msi_startup(struct irq_data *d) { if (d->msi_desc) - unmask_msi_irq(d); + pci_msi_unmask_irq(d); return 0; } @@ -1465,14 +1465,14 @@ static void tilegx_msi_ack(struct irq_data *d) static void tilegx_msi_mask(struct irq_data *d) { - mask_msi_irq(d); + pci_msi_mask_irq(d); __insn_mtspr(SPR_IPI_MASK_SET_K, 1UL << d->irq); } static void tilegx_msi_unmask(struct irq_data *d) { __insn_mtspr(SPR_IPI_MASK_RESET_K, 1UL << d->irq); - unmask_msi_irq(d); + pci_msi_unmask_irq(d); } static struct irq_chip tilegx_msi_chip = { @@ -1590,7 +1590,7 @@ int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc) msg.address_hi = msi_addr >> 32; msg.address_lo = msi_addr & 0xffffffff; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); irq_set_chip_and_handler(irq, &tilegx_msi_chip, handle_level_irq); irq_set_handler_data(irq, controller); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index e45e4da96bf1..f58a9c7a3c86 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -172,7 +172,6 @@ struct x86_platform_ops { struct pci_dev; struct msi_msg; -struct msi_desc; struct x86_msi_ops { int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type); @@ -183,8 +182,6 @@ struct x86_msi_ops { void (*teardown_msi_irqs)(struct pci_dev *dev); void (*restore_msi_irqs)(struct pci_dev *dev); int (*setup_hpet_msi)(unsigned int irq, unsigned int id); - u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag); - u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag); }; struct IO_APIC_route_entry; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1183d545da1e..7ffe0a2b870f 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -3158,7 +3158,7 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK; msg.address_lo |= MSI_ADDR_DEST_ID(dest); - __write_msi_msg(data->msi_desc, &msg); + __pci_write_msi_msg(data->msi_desc, &msg); return IRQ_SET_MASK_OK_NOCOPY; } @@ -3169,8 +3169,8 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) */ static struct irq_chip msi_chip = { .name = "PCI-MSI", - .irq_unmask = unmask_msi_irq, - .irq_mask = mask_msi_irq, + .irq_unmask = pci_msi_unmask_irq, + .irq_mask = pci_msi_mask_irq, .irq_ack = ack_apic_edge, .irq_set_affinity = msi_set_affinity, .irq_retrigger = ioapic_retrigger_irq, @@ -3196,7 +3196,7 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, * MSI message denotes a contiguous group of IRQs, written for 0th IRQ. */ if (!irq_offset) - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); setup_remapped_irq(irq, irq_cfg(irq), chip); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index e48b674639cc..234b0722de53 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -116,8 +116,6 @@ struct x86_msi_ops x86_msi = { .teardown_msi_irqs = default_teardown_msi_irqs, .restore_msi_irqs = default_restore_msi_irqs, .setup_hpet_msi = default_setup_hpet_msi, - .msi_mask_irq = default_msi_mask_irq, - .msix_mask_irq = default_msix_mask_irq, }; /* MSI arch specific hooks */ @@ -140,14 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev) { x86_msi.restore_msi_irqs(dev); } -u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) -{ - return x86_msi.msi_mask_irq(desc, mask, flag); -} -u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) -{ - return x86_msi.msix_mask_irq(desc, flag); -} #endif struct x86_io_apic_ops x86_io_apic_ops = { diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 093f5f4272d3..1819a91bbb9f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -229,7 +229,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 1; list_for_each_entry(msidesc, &dev->msi_list, list) { - __read_msi_msg(msidesc, &msg); + __pci_read_msi_msg(msidesc, &msg); pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) | ((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff); if (msg.data != XEN_PIRQ_MSI_DATA || @@ -240,7 +240,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) goto error; } xen_msi_compose_msg(dev, pirq, &msg); - __write_msi_msg(msidesc, &msg); + __pci_write_msi_msg(msidesc, &msg); dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq); } else { dev_dbg(&dev->dev, @@ -394,14 +394,7 @@ static void xen_teardown_msi_irq(unsigned int irq) { xen_destroy_irq(irq); } -static u32 xen_nop_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) -{ - return 0; -} -static u32 xen_nop_msix_mask_irq(struct msi_desc *desc, u32 flag) -{ - return 0; -} + #endif int __init pci_xen_init(void) @@ -425,8 +418,7 @@ int __init pci_xen_init(void) x86_msi.setup_msi_irqs = xen_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs; - x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; - x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; + pci_msi_ignore_mask = 1; #endif return 0; } @@ -506,8 +498,7 @@ int __init pci_xen_initial_domain(void) x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs; x86_msi.teardown_msi_irq = xen_teardown_msi_irq; x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; - x86_msi.msi_mask_irq = xen_nop_msi_mask_irq; - x86_msi.msix_mask_irq = xen_nop_msix_mask_irq; + pci_msi_ignore_mask = 1; #endif xen_setup_acpi_sci(); __acpi_register_gsi = acpi_register_gsi_xen; diff --git a/drivers/iommu/irq_remapping.c b/drivers/iommu/irq_remapping.c index 74a1767c89b5..2c3f5ad01098 100644 --- a/drivers/iommu/irq_remapping.c +++ b/drivers/iommu/irq_remapping.c @@ -56,19 +56,13 @@ static int do_setup_msi_irqs(struct pci_dev *dev, int nvec) unsigned int irq; struct msi_desc *msidesc; - WARN_ON(!list_is_singular(&dev->msi_list)); msidesc = list_entry(dev->msi_list.next, struct msi_desc, list); - WARN_ON(msidesc->irq); - WARN_ON(msidesc->msi_attrib.multiple); - WARN_ON(msidesc->nvec_used); irq = irq_alloc_hwirqs(nvec, dev_to_node(&dev->dev)); if (irq == 0) return -ENOSPC; nvec_pow2 = __roundup_pow_of_two(nvec); - msidesc->nvec_used = nvec; - msidesc->msi_attrib.multiple = ilog2(nvec_pow2); for (sub_handle = 0; sub_handle < nvec; sub_handle++) { if (!sub_handle) { index = msi_alloc_remapped_irq(dev, irq, nvec_pow2); @@ -96,8 +90,6 @@ error: * IRQs from tearing down again in default_teardown_msi_irqs() */ msidesc->irq = 0; - msidesc->nvec_used = 0; - msidesc->msi_attrib.multiple = 0; return ret; } diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index a3fd2b37ddb6..463c235acbdc 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -132,7 +132,7 @@ static void armada_370_xp_free_msi(int hwirq) mutex_unlock(&msi_used_lock); } -static int armada_370_xp_setup_msi_irq(struct msi_chip *chip, +static int armada_370_xp_setup_msi_irq(struct msi_controller *chip, struct pci_dev *pdev, struct msi_desc *desc) { @@ -159,11 +159,11 @@ static int armada_370_xp_setup_msi_irq(struct msi_chip *chip, msg.address_hi = 0; msg.data = 0xf00 | (hwirq + 16); - write_msi_msg(virq, &msg); + pci_write_msi_msg(virq, &msg); return 0; } -static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip, +static void armada_370_xp_teardown_msi_irq(struct msi_controller *chip, unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); @@ -175,10 +175,10 @@ static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip, static struct irq_chip armada_370_xp_msi_irq_chip = { .name = "armada_370_xp_msi_irq", - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, }; static int armada_370_xp_msi_map(struct irq_domain *domain, unsigned int virq, @@ -198,7 +198,7 @@ static const struct irq_domain_ops armada_370_xp_msi_irq_ops = { static int armada_370_xp_msi_init(struct device_node *node, phys_addr_t main_int_phys_base) { - struct msi_chip *msi_chip; + struct msi_controller *msi_chip; u32 reg; int ret; diff --git a/drivers/of/of_pci.c b/drivers/of/of_pci.c index 8882b467be95..88471d3d98cd 100644 --- a/drivers/of/of_pci.c +++ b/drivers/of/of_pci.c @@ -236,7 +236,7 @@ EXPORT_SYMBOL_GPL(of_pci_get_host_bridge_resources); static LIST_HEAD(of_pci_msi_chip_list); static DEFINE_MUTEX(of_pci_msi_chip_mutex); -int of_pci_msi_chip_add(struct msi_chip *chip) +int of_pci_msi_chip_add(struct msi_controller *chip) { if (!of_property_read_bool(chip->of_node, "msi-controller")) return -EINVAL; @@ -249,7 +249,7 @@ int of_pci_msi_chip_add(struct msi_chip *chip) } EXPORT_SYMBOL_GPL(of_pci_msi_chip_add); -void of_pci_msi_chip_remove(struct msi_chip *chip) +void of_pci_msi_chip_remove(struct msi_controller *chip) { mutex_lock(&of_pci_msi_chip_mutex); list_del(&chip->list); @@ -257,9 +257,9 @@ void of_pci_msi_chip_remove(struct msi_chip *chip) } EXPORT_SYMBOL_GPL(of_pci_msi_chip_remove); -struct msi_chip *of_pci_find_msi_chip_by_node(struct device_node *of_node) +struct msi_controller *of_pci_find_msi_chip_by_node(struct device_node *of_node) { - struct msi_chip *c; + struct msi_controller *c; mutex_lock(&of_pci_msi_chip_mutex); list_for_each_entry(c, &of_pci_msi_chip_list, list) { diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index 893503fa1782..cced84233ac0 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -4,6 +4,7 @@ config PCI_MSI bool "Message Signaled Interrupts (MSI and MSI-X)" depends on PCI + select GENERIC_MSI_IRQ help This allows device drivers to enable MSI (Message Signaled Interrupts). Message Signaled Interrupts enable a device to @@ -16,6 +17,11 @@ config PCI_MSI If you don't know what to do here, say Y. +config PCI_MSI_IRQ_DOMAIN + bool + depends on PCI_MSI + select GENERIC_MSI_IRQ_DOMAIN + config PCI_DEBUG bool "PCI Debugging" depends on PCI && DEBUG_KERNEL diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c index 34086ce88e8e..313338db0e43 100644 --- a/drivers/pci/host/pci-keystone-dw.c +++ b/drivers/pci/host/pci-keystone-dw.c @@ -155,7 +155,7 @@ static void ks_dw_pcie_msi_irq_mask(struct irq_data *d) /* Mask the end point if PVM implemented */ if (IS_ENABLED(CONFIG_PCI_MSI)) { if (msi->msi_attrib.maskbit) - mask_msi_irq(d); + pci_msi_mask_irq(d); } ks_dw_pcie_msi_clear_irq(pp, offset); @@ -177,7 +177,7 @@ static void ks_dw_pcie_msi_irq_unmask(struct irq_data *d) /* Mask the end point if PVM implemented */ if (IS_ENABLED(CONFIG_PCI_MSI)) { if (msi->msi_attrib.maskbit) - unmask_msi_irq(d); + pci_msi_unmask_irq(d); } ks_dw_pcie_msi_set_irq(pp, offset); @@ -205,7 +205,7 @@ const struct irq_domain_ops ks_dw_pcie_msi_domain_ops = { .map = ks_dw_pcie_msi_map, }; -int ks_dw_pcie_msi_host_init(struct pcie_port *pp, struct msi_chip *chip) +int ks_dw_pcie_msi_host_init(struct pcie_port *pp, struct msi_controller *chip) { struct keystone_pcie *ks_pcie = to_keystone_pcie(pp); int i; diff --git a/drivers/pci/host/pci-keystone.h b/drivers/pci/host/pci-keystone.h index 1fc1fceede9e..478d932b602d 100644 --- a/drivers/pci/host/pci-keystone.h +++ b/drivers/pci/host/pci-keystone.h @@ -55,4 +55,4 @@ void ks_dw_pcie_msi_set_irq(struct pcie_port *pp, int irq); void ks_dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq); void ks_dw_pcie_v3_65_scan_bus(struct pcie_port *pp); int ks_dw_pcie_msi_host_init(struct pcie_port *pp, - struct msi_chip *chip); + struct msi_controller *chip); diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c index b1315e197ffb..9aa810b733a8 100644 --- a/drivers/pci/host/pci-mvebu.c +++ b/drivers/pci/host/pci-mvebu.c @@ -99,7 +99,7 @@ struct mvebu_pcie_port; struct mvebu_pcie { struct platform_device *pdev; struct mvebu_pcie_port *ports; - struct msi_chip *msi; + struct msi_controller *msi; struct resource io; char io_name[30]; struct resource realio; @@ -774,12 +774,6 @@ static struct pci_bus *mvebu_pcie_scan_bus(int nr, struct pci_sys_data *sys) return bus; } -static void mvebu_pcie_add_bus(struct pci_bus *bus) -{ - struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata); - bus->msi = pcie->msi; -} - static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev, const struct resource *res, resource_size_t start, @@ -816,6 +810,10 @@ static void mvebu_pcie_enable(struct mvebu_pcie *pcie) memset(&hw, 0, sizeof(hw)); +#ifdef CONFIG_PCI_MSI + hw.msi_ctrl = pcie->msi; +#endif + hw.nr_controllers = 1; hw.private_data = (void **)&pcie; hw.setup = mvebu_pcie_setup; @@ -823,7 +821,6 @@ static void mvebu_pcie_enable(struct mvebu_pcie *pcie) hw.map_irq = of_irq_parse_and_map_pci; hw.ops = &mvebu_pcie_ops; hw.align_resource = mvebu_pcie_align_resource; - hw.add_bus = mvebu_pcie_add_bus; pci_common_init(&hw); } diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c index 19bb19c7db4a..feccfa6b6c11 100644 --- a/drivers/pci/host/pci-tegra.c +++ b/drivers/pci/host/pci-tegra.c @@ -238,7 +238,7 @@ ) struct tegra_msi { - struct msi_chip chip; + struct msi_controller chip; DECLARE_BITMAP(used, INT_PCI_MSI_NR); struct irq_domain *domain; unsigned long pages; @@ -259,7 +259,7 @@ struct tegra_pcie_soc_data { bool has_gen2; }; -static inline struct tegra_msi *to_tegra_msi(struct msi_chip *chip) +static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip) { return container_of(chip, struct tegra_msi, chip); } @@ -692,15 +692,6 @@ static int tegra_pcie_map_irq(const struct pci_dev *pdev, u8 slot, u8 pin) return irq; } -static void tegra_pcie_add_bus(struct pci_bus *bus) -{ - if (IS_ENABLED(CONFIG_PCI_MSI)) { - struct tegra_pcie *pcie = sys_to_pcie(bus->sysdata); - - bus->msi = &pcie->msi.chip; - } -} - static struct pci_bus *tegra_pcie_scan_bus(int nr, struct pci_sys_data *sys) { struct tegra_pcie *pcie = sys_to_pcie(sys); @@ -1280,8 +1271,8 @@ static irqreturn_t tegra_pcie_msi_irq(int irq, void *data) return processed > 0 ? IRQ_HANDLED : IRQ_NONE; } -static int tegra_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev, - struct msi_desc *desc) +static int tegra_msi_setup_irq(struct msi_controller *chip, + struct pci_dev *pdev, struct msi_desc *desc) { struct tegra_msi *msi = to_tegra_msi(chip); struct msi_msg msg; @@ -1305,12 +1296,13 @@ static int tegra_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev, msg.address_hi = 0; msg.data = hwirq; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); return 0; } -static void tegra_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) +static void tegra_msi_teardown_irq(struct msi_controller *chip, + unsigned int irq) { struct tegra_msi *msi = to_tegra_msi(chip); struct irq_data *d = irq_get_irq_data(irq); @@ -1322,10 +1314,10 @@ static void tegra_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) static struct irq_chip tegra_msi_irq_chip = { .name = "Tegra PCIe MSI", - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, }; static int tegra_msi_map(struct irq_domain *domain, unsigned int irq, @@ -1893,11 +1885,14 @@ static int tegra_pcie_enable(struct tegra_pcie *pcie) memset(&hw, 0, sizeof(hw)); +#ifdef CONFIG_PCI_MSI + hw.msi_ctrl = &pcie->msi.chip; +#endif + hw.nr_controllers = 1; hw.private_data = (void **)&pcie; hw.setup = tegra_pcie_setup; hw.map_irq = tegra_pcie_map_irq; - hw.add_bus = tegra_pcie_add_bus; hw.scan = tegra_pcie_scan_bus; hw.ops = &tegra_pcie_ops; diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c index dfed00aa3ac0..17b51550f9b5 100644 --- a/drivers/pci/host/pcie-designware.c +++ b/drivers/pci/host/pcie-designware.c @@ -152,10 +152,10 @@ static int dw_pcie_wr_own_conf(struct pcie_port *pp, int where, int size, static struct irq_chip dw_msi_irq_chip = { .name = "PCI-MSI", - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, }; /* MSI int handler */ @@ -276,7 +276,7 @@ no_valid_irq: return -ENOSPC; } -static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev, +static int dw_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev, struct msi_desc *desc) { int irq, pos; @@ -298,12 +298,12 @@ static int dw_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev, else msg.data = pos; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); return 0; } -static void dw_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) +static void dw_msi_teardown_irq(struct msi_controller *chip, unsigned int irq) { struct irq_data *data = irq_get_irq_data(irq); struct msi_desc *msi = irq_data_get_msi(data); @@ -312,7 +312,7 @@ static void dw_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) clear_irq_range(pp, irq, 1, data->hwirq); } -static struct msi_chip dw_pcie_msi_chip = { +static struct msi_controller dw_pcie_msi_chip = { .setup_irq = dw_msi_setup_irq, .teardown_irq = dw_msi_teardown_irq, }; @@ -498,6 +498,11 @@ int __init dw_pcie_host_init(struct pcie_port *pp) val |= PORT_LOGIC_SPEED_CHANGE; dw_pcie_wr_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, val); +#ifdef CONFIG_PCI_MSI + dw_pcie_msi_chip.dev = pp->dev; + dw_pci.msi_ctrl = &dw_pcie_msi_chip; +#endif + dw_pci.nr_controllers = 1; dw_pci.private_data = (void **)&pp; @@ -747,21 +752,10 @@ static int dw_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) return irq; } -static void dw_pcie_add_bus(struct pci_bus *bus) -{ - if (IS_ENABLED(CONFIG_PCI_MSI)) { - struct pcie_port *pp = sys_to_pcie(bus->sysdata); - - dw_pcie_msi_chip.dev = pp->dev; - bus->msi = &dw_pcie_msi_chip; - } -} - static struct hw_pci dw_pci = { .setup = dw_pcie_setup, .scan = dw_pcie_scan_bus, .map_irq = dw_pcie_map_irq, - .add_bus = dw_pcie_add_bus, }; void dw_pcie_setup_rc(struct pcie_port *pp) diff --git a/drivers/pci/host/pcie-designware.h b/drivers/pci/host/pcie-designware.h index c6256751daff..d0bbd276840d 100644 --- a/drivers/pci/host/pcie-designware.h +++ b/drivers/pci/host/pcie-designware.h @@ -73,7 +73,7 @@ struct pcie_host_ops { u32 (*get_msi_addr)(struct pcie_port *pp); u32 (*get_msi_data)(struct pcie_port *pp, int pos); void (*scan_bus)(struct pcie_port *pp); - int (*msi_host_init)(struct pcie_port *pp, struct msi_chip *chip); + int (*msi_host_init)(struct pcie_port *pp, struct msi_controller *chip); }; int dw_pcie_cfg_read(void __iomem *addr, int where, int size, u32 *val); diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c index 61158e03ab5f..d3053e53cf35 100644 --- a/drivers/pci/host/pcie-rcar.c +++ b/drivers/pci/host/pcie-rcar.c @@ -111,14 +111,14 @@ struct rcar_msi { DECLARE_BITMAP(used, INT_PCI_MSI_NR); struct irq_domain *domain; - struct msi_chip chip; + struct msi_controller chip; unsigned long pages; struct mutex lock; int irq1; int irq2; }; -static inline struct rcar_msi *to_rcar_msi(struct msi_chip *chip) +static inline struct rcar_msi *to_rcar_msi(struct msi_controller *chip) { return container_of(chip, struct rcar_msi, chip); } @@ -380,20 +380,10 @@ static int rcar_pcie_setup(int nr, struct pci_sys_data *sys) return 1; } -static void rcar_pcie_add_bus(struct pci_bus *bus) -{ - if (IS_ENABLED(CONFIG_PCI_MSI)) { - struct rcar_pcie *pcie = sys_to_pcie(bus->sysdata); - - bus->msi = &pcie->msi.chip; - } -} - struct hw_pci rcar_pci = { .setup = rcar_pcie_setup, .map_irq = of_irq_parse_and_map_pci, .ops = &rcar_pcie_ops, - .add_bus = rcar_pcie_add_bus, }; static void rcar_pcie_enable(struct rcar_pcie *pcie) @@ -402,6 +392,9 @@ static void rcar_pcie_enable(struct rcar_pcie *pcie) rcar_pci.nr_controllers = 1; rcar_pci.private_data = (void **)&pcie; +#ifdef CONFIG_PCI_MSI + rcar_pci.msi_ctrl = &pcie->msi.chip; +#endif pci_common_init_dev(&pdev->dev, &rcar_pci); #ifdef CONFIG_PCI_DOMAINS @@ -622,7 +615,7 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data) return IRQ_HANDLED; } -static int rcar_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev, +static int rcar_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev, struct msi_desc *desc) { struct rcar_msi *msi = to_rcar_msi(chip); @@ -647,12 +640,12 @@ static int rcar_msi_setup_irq(struct msi_chip *chip, struct pci_dev *pdev, msg.address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR); msg.data = hwirq; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); return 0; } -static void rcar_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) +static void rcar_msi_teardown_irq(struct msi_controller *chip, unsigned int irq) { struct rcar_msi *msi = to_rcar_msi(chip); struct irq_data *d = irq_get_irq_data(irq); @@ -662,10 +655,10 @@ static void rcar_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) static struct irq_chip rcar_msi_irq_chip = { .name = "R-Car PCIe MSI", - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, }; static int rcar_msi_map(struct irq_domain *domain, unsigned int irq, diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c index ccc496b33a97..2f50fa5953fd 100644 --- a/drivers/pci/host/pcie-xilinx.c +++ b/drivers/pci/host/pcie-xilinx.c @@ -335,7 +335,8 @@ static int xilinx_pcie_assign_msi(struct xilinx_pcie_port *port) * @chip: MSI Chip descriptor * @irq: MSI IRQ to destroy */ -static void xilinx_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) +static void xilinx_msi_teardown_irq(struct msi_controller *chip, + unsigned int irq) { xilinx_pcie_destroy_msi(irq); } @@ -348,7 +349,7 @@ static void xilinx_msi_teardown_irq(struct msi_chip *chip, unsigned int irq) * * Return: '0' on success and error value on failure */ -static int xilinx_pcie_msi_setup_irq(struct msi_chip *chip, +static int xilinx_pcie_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev, struct msi_desc *desc) { @@ -374,13 +375,13 @@ static int xilinx_pcie_msi_setup_irq(struct msi_chip *chip, msg.address_lo = msg_addr; msg.data = irq; - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); return 0; } /* MSI Chip Descriptor */ -static struct msi_chip xilinx_pcie_msi_chip = { +static struct msi_controller xilinx_pcie_msi_chip = { .setup_irq = xilinx_pcie_msi_setup_irq, .teardown_irq = xilinx_msi_teardown_irq, }; @@ -388,10 +389,10 @@ static struct msi_chip xilinx_pcie_msi_chip = { /* HW Interrupt Chip Descriptor */ static struct irq_chip xilinx_msi_irq_chip = { .name = "Xilinx PCIe MSI", - .irq_enable = unmask_msi_irq, - .irq_disable = mask_msi_irq, - .irq_mask = mask_msi_irq, - .irq_unmask = unmask_msi_irq, + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, }; /** @@ -431,20 +432,6 @@ static void xilinx_pcie_enable_msi(struct xilinx_pcie_port *port) pcie_write(port, msg_addr, XILINX_PCIE_REG_MSIBASE2); } -/** - * xilinx_pcie_add_bus - Add MSI chip info to PCIe bus - * @bus: PCIe bus - */ -static void xilinx_pcie_add_bus(struct pci_bus *bus) -{ - if (IS_ENABLED(CONFIG_PCI_MSI)) { - struct xilinx_pcie_port *port = sys_to_pcie(bus->sysdata); - - xilinx_pcie_msi_chip.dev = port->dev; - bus->msi = &xilinx_pcie_msi_chip; - } -} - /* INTx Functions */ /** @@ -924,10 +911,14 @@ static int xilinx_pcie_probe(struct platform_device *pdev) .private_data = (void **)&port, .setup = xilinx_pcie_setup, .map_irq = of_irq_parse_and_map_pci, - .add_bus = xilinx_pcie_add_bus, .scan = xilinx_pcie_scan_bus, .ops = &xilinx_pcie_ops, }; + +#ifdef CONFIG_PCI_MSI + xilinx_pcie_msi_chip.dev = port->dev; + hw.msi_ctrl = &xilinx_pcie_msi_chip; +#endif pci_common_init_dev(dev, &hw); return 0; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 084587d7cd13..fd60806d3fd0 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -19,19 +19,82 @@ #include <linux/errno.h> #include <linux/io.h> #include <linux/slab.h> +#include <linux/irqdomain.h> #include "pci.h" static int pci_msi_enable = 1; +int pci_msi_ignore_mask; #define msix_table_size(flags) ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) +#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +static struct irq_domain *pci_msi_default_domain; +static DEFINE_MUTEX(pci_msi_domain_lock); + +struct irq_domain * __weak arch_get_pci_msi_domain(struct pci_dev *dev) +{ + return pci_msi_default_domain; +} + +static struct irq_domain *pci_msi_get_domain(struct pci_dev *dev) +{ + struct irq_domain *domain = NULL; + + if (dev->bus->msi) + domain = dev->bus->msi->domain; + if (!domain) + domain = arch_get_pci_msi_domain(dev); + + return domain; +} + +static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + struct irq_domain *domain; + + domain = pci_msi_get_domain(dev); + if (domain) + return pci_msi_domain_alloc_irqs(domain, dev, nvec, type); + + return arch_setup_msi_irqs(dev, nvec, type); +} + +static void pci_msi_teardown_msi_irqs(struct pci_dev *dev) +{ + struct irq_domain *domain; + + domain = pci_msi_get_domain(dev); + if (domain) + pci_msi_domain_free_irqs(domain, dev); + else + arch_teardown_msi_irqs(dev); +} +#else +#define pci_msi_setup_msi_irqs arch_setup_msi_irqs +#define pci_msi_teardown_msi_irqs arch_teardown_msi_irqs +#endif /* Arch hooks */ +struct msi_controller * __weak pcibios_msi_controller(struct pci_dev *dev) +{ + return NULL; +} + +static struct msi_controller *pci_msi_controller(struct pci_dev *dev) +{ + struct msi_controller *msi_ctrl = dev->bus->msi; + + if (msi_ctrl) + return msi_ctrl; + + return pcibios_msi_controller(dev); +} + int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) { - struct msi_chip *chip = dev->bus->msi; + struct msi_controller *chip = pci_msi_controller(dev); int err; if (!chip || !chip->setup_irq) @@ -48,7 +111,7 @@ int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) void __weak arch_teardown_msi_irq(unsigned int irq) { - struct msi_chip *chip = irq_get_chip_data(irq); + struct msi_controller *chip = irq_get_chip_data(irq); if (!chip || !chip->teardown_irq) return; @@ -85,19 +148,13 @@ int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) */ void default_teardown_msi_irqs(struct pci_dev *dev) { + int i; struct msi_desc *entry; - list_for_each_entry(entry, &dev->msi_list, list) { - int i, nvec; - if (entry->irq == 0) - continue; - if (entry->nvec_used) - nvec = entry->nvec_used; - else - nvec = 1 << entry->msi_attrib.multiple; - for (i = 0; i < nvec; i++) - arch_teardown_msi_irq(entry->irq + i); - } + list_for_each_entry(entry, &dev->msi_list, list) + if (entry->irq) + for (i = 0; i < entry->nvec_used; i++) + arch_teardown_msi_irq(entry->irq + i); } void __weak arch_teardown_msi_irqs(struct pci_dev *dev) @@ -120,7 +177,7 @@ static void default_restore_msi_irq(struct pci_dev *dev, int irq) } if (entry) - __write_msi_msg(entry, &entry->msg); + __pci_write_msi_msg(entry, &entry->msg); } void __weak arch_restore_msi_irqs(struct pci_dev *dev) @@ -163,11 +220,11 @@ static inline __attribute_const__ u32 msi_mask(unsigned x) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { u32 mask_bits = desc->masked; - if (!desc->msi_attrib.maskbit) + if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit) return 0; mask_bits &= ~mask; @@ -177,14 +234,9 @@ u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) return mask_bits; } -__weak u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) -{ - return default_msi_mask_irq(desc, mask, flag); -} - static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - desc->masked = arch_msi_mask_irq(desc, mask, flag); + desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag); } /* @@ -194,11 +246,15 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) * file. This saves a few milliseconds when initialising devices with lots * of MSI-X interrupts. */ -u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag) +u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) { u32 mask_bits = desc->masked; unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL; + + if (pci_msi_ignore_mask) + return 0; + mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; if (flag) mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT; @@ -207,14 +263,9 @@ u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag) return mask_bits; } -__weak u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) -{ - return default_msix_mask_irq(desc, flag); -} - static void msix_mask_irq(struct msi_desc *desc, u32 flag) { - desc->masked = arch_msix_mask_irq(desc, flag); + desc->masked = __pci_msix_desc_mask_irq(desc, flag); } static void msi_set_mask_bit(struct irq_data *data, u32 flag) @@ -230,12 +281,20 @@ static void msi_set_mask_bit(struct irq_data *data, u32 flag) } } -void mask_msi_irq(struct irq_data *data) +/** + * pci_msi_mask_irq - Generic irq chip callback to mask PCI/MSI interrupts + * @data: pointer to irqdata associated to that interrupt + */ +void pci_msi_mask_irq(struct irq_data *data) { msi_set_mask_bit(data, 1); } -void unmask_msi_irq(struct irq_data *data) +/** + * pci_msi_unmask_irq - Generic irq chip callback to unmask PCI/MSI interrupts + * @data: pointer to irqdata associated to that interrupt + */ +void pci_msi_unmask_irq(struct irq_data *data) { msi_set_mask_bit(data, 0); } @@ -244,12 +303,11 @@ void default_restore_msi_irqs(struct pci_dev *dev) { struct msi_desc *entry; - list_for_each_entry(entry, &dev->msi_list, list) { + list_for_each_entry(entry, &dev->msi_list, list) default_restore_msi_irq(dev, entry->irq); - } } -void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) +void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { BUG_ON(entry->dev->current_state != PCI_D0); @@ -279,32 +337,7 @@ void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) } } -void read_msi_msg(unsigned int irq, struct msi_msg *msg) -{ - struct msi_desc *entry = irq_get_msi_desc(irq); - - __read_msi_msg(entry, msg); -} - -void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) -{ - /* Assert that the cache is valid, assuming that - * valid messages are not all-zeroes. */ - BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo | - entry->msg.data)); - - *msg = entry->msg; -} - -void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) -{ - struct msi_desc *entry = irq_get_msi_desc(irq); - - __get_cached_msi_msg(entry, msg); -} -EXPORT_SYMBOL_GPL(get_cached_msi_msg); - -void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) +void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { if (entry->dev->current_state != PCI_D0) { /* Don't touch the hardware now */ @@ -341,34 +374,27 @@ void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) entry->msg = *msg; } -void write_msi_msg(unsigned int irq, struct msi_msg *msg) +void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) { struct msi_desc *entry = irq_get_msi_desc(irq); - __write_msi_msg(entry, msg); + __pci_write_msi_msg(entry, msg); } -EXPORT_SYMBOL_GPL(write_msi_msg); +EXPORT_SYMBOL_GPL(pci_write_msi_msg); static void free_msi_irqs(struct pci_dev *dev) { struct msi_desc *entry, *tmp; struct attribute **msi_attrs; struct device_attribute *dev_attr; - int count = 0; + int i, count = 0; - list_for_each_entry(entry, &dev->msi_list, list) { - int i, nvec; - if (!entry->irq) - continue; - if (entry->nvec_used) - nvec = entry->nvec_used; - else - nvec = 1 << entry->msi_attrib.multiple; - for (i = 0; i < nvec; i++) - BUG_ON(irq_has_action(entry->irq + i)); - } + list_for_each_entry(entry, &dev->msi_list, list) + if (entry->irq) + for (i = 0; i < entry->nvec_used; i++) + BUG_ON(irq_has_action(entry->irq + i)); - arch_teardown_msi_irqs(dev); + pci_msi_teardown_msi_irqs(dev); list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) { if (entry->msi_attrib.is_msix) { @@ -451,9 +477,8 @@ static void __pci_restore_msix_state(struct pci_dev *dev) PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL); arch_restore_msi_irqs(dev); - list_for_each_entry(entry, &dev->msi_list, list) { + list_for_each_entry(entry, &dev->msi_list, list) msix_mask_irq(entry, entry->masked); - } msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } @@ -497,9 +522,8 @@ static int populate_msi_sysfs(struct pci_dev *pdev) int count = 0; /* Determine how many msi entries we have */ - list_for_each_entry(entry, &pdev->msi_list, list) { + list_for_each_entry(entry, &pdev->msi_list, list) ++num_msi; - } if (!num_msi) return 0; @@ -559,7 +583,7 @@ error_attrs: return ret; } -static struct msi_desc *msi_setup_entry(struct pci_dev *dev) +static struct msi_desc *msi_setup_entry(struct pci_dev *dev, int nvec) { u16 control; struct msi_desc *entry; @@ -577,6 +601,8 @@ static struct msi_desc *msi_setup_entry(struct pci_dev *dev) entry->msi_attrib.maskbit = !!(control & PCI_MSI_FLAGS_MASKBIT); entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ entry->msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1; + entry->msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec)); + entry->nvec_used = nvec; if (control & PCI_MSI_FLAGS_64BIT) entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64; @@ -623,7 +649,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) msi_set_enable(dev, 0); /* Disable MSI during set up */ - entry = msi_setup_entry(dev); + entry = msi_setup_entry(dev, nvec); if (!entry) return -ENOMEM; @@ -634,7 +660,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec) list_add_tail(&entry->list, &dev->msi_list); /* Configure MSI capability structure */ - ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); + ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { msi_mask_irq(entry, mask, ~mask); free_msi_irqs(dev); @@ -701,6 +727,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.entry_nr = entries[i].entry; entry->msi_attrib.default_irq = dev->irq; entry->mask_base = base; + entry->nvec_used = 1; list_add_tail(&entry->list, &dev->msi_list); } @@ -719,7 +746,6 @@ static void msix_program_entries(struct pci_dev *dev, PCI_MSIX_ENTRY_VECTOR_CTRL; entries[i].vector = entry->irq; - irq_set_msi_desc(entry->irq, entry); entry->masked = readl(entry->mask_base + offset); msix_mask_irq(entry, 1); i++; @@ -756,7 +782,7 @@ static int msix_capability_init(struct pci_dev *dev, if (ret) return ret; - ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); + ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); if (ret) goto out_avail; @@ -895,7 +921,7 @@ void pci_msi_shutdown(struct pci_dev *dev) /* Return the device with MSI unmasked as initial states */ mask = msi_mask(desc->msi_attrib.multi_cap); /* Keep cached state to be restored */ - arch_msi_mask_irq(desc, mask, ~mask); + __pci_msi_desc_mask_irq(desc, mask, ~mask); /* Restore dev->irq to its default pin-assertion irq */ dev->irq = desc->msi_attrib.default_irq; @@ -993,7 +1019,7 @@ void pci_msix_shutdown(struct pci_dev *dev) /* Return the device with MSI-X masked as initial states */ list_for_each_entry(entry, &dev->msi_list, list) { /* Keep cached states to be restored */ - arch_msix_mask_irq(entry, 1); + __pci_msix_desc_mask_irq(entry, 1); } msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); @@ -1138,3 +1164,197 @@ int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, return nvec; } EXPORT_SYMBOL(pci_enable_msix_range); + +#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +/** + * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space + * @irq_data: Pointer to interrupt data of the MSI interrupt + * @msg: Pointer to the message + */ +void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg) +{ + struct msi_desc *desc = irq_data->msi_desc; + + /* + * For MSI-X desc->irq is always equal to irq_data->irq. For + * MSI only the first interrupt of MULTI MSI passes the test. + */ + if (desc->irq == irq_data->irq) + __pci_write_msi_msg(desc, msg); +} + +/** + * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source + * @dev: Pointer to the PCI device + * @desc: Pointer to the msi descriptor + * + * The ID number is only used within the irqdomain. + */ +irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev, + struct msi_desc *desc) +{ + return (irq_hw_number_t)desc->msi_attrib.entry_nr | + PCI_DEVID(dev->bus->number, dev->devfn) << 11 | + (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; +} + +static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) +{ + return !desc->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 + */ +int pci_msi_domain_check_cap(struct irq_domain *domain, + struct msi_domain_info *info, struct device *dev) +{ + struct msi_desc *desc = first_pci_msi_entry(to_pci_dev(dev)); + + /* 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; + else if (desc->msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX)) + return -ENOTSUPP; + + return 0; +} + +static int pci_msi_domain_handle_error(struct irq_domain *domain, + struct msi_desc *desc, int error) +{ + /* Special handling to support pci_enable_msi_range() */ + if (pci_msi_desc_is_multi_msi(desc) && error == -ENOSPC) + return 1; + + return error; +} + +#ifdef GENERIC_MSI_DOMAIN_OPS +static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, + struct msi_desc *desc) +{ + arg->desc = desc; + arg->hwirq = pci_msi_domain_calc_hwirq(msi_desc_to_pci_dev(desc), + desc); +} +#else +#define pci_msi_domain_set_desc NULL +#endif + +static struct msi_domain_ops pci_msi_domain_ops_default = { + .set_desc = pci_msi_domain_set_desc, + .msi_check = pci_msi_domain_check_cap, + .handle_error = pci_msi_domain_handle_error, +}; + +static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) +{ + struct msi_domain_ops *ops = info->ops; + + if (ops == NULL) { + info->ops = &pci_msi_domain_ops_default; + } else { + if (ops->set_desc == NULL) + ops->set_desc = pci_msi_domain_set_desc; + if (ops->msi_check == NULL) + ops->msi_check = pci_msi_domain_check_cap; + if (ops->handle_error == NULL) + ops->handle_error = pci_msi_domain_handle_error; + } +} + +static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info) +{ + struct irq_chip *chip = info->chip; + + BUG_ON(!chip); + if (!chip->irq_write_msi_msg) + chip->irq_write_msi_msg = pci_msi_domain_write_msg; +} + +/** + * pci_msi_create_irq_domain - Creat a MSI interrupt domain + * @node: Optional device-tree node of the interrupt controller + * @info: MSI domain info + * @parent: Parent irq domain + * + * Updates the domain and chip ops and creates a MSI interrupt domain. + * + * Returns: + * A domain pointer or NULL in case of failure. + */ +struct irq_domain *pci_msi_create_irq_domain(struct device_node *node, + struct msi_domain_info *info, + struct irq_domain *parent) +{ + if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS) + pci_msi_domain_update_dom_ops(info); + if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) + pci_msi_domain_update_chip_ops(info); + + return msi_create_irq_domain(node, info, parent); +} + +/** + * pci_msi_domain_alloc_irqs - Allocate interrupts for @dev in @domain + * @domain: The interrupt domain to allocate from + * @dev: The device for which to allocate + * @nvec: The number of interrupts to allocate + * @type: Unused to allow simpler migration from the arch_XXX interfaces + * + * Returns: + * A virtual interrupt number or an error code in case of failure + */ +int pci_msi_domain_alloc_irqs(struct irq_domain *domain, struct pci_dev *dev, + int nvec, int type) +{ + return msi_domain_alloc_irqs(domain, &dev->dev, nvec); +} + +/** + * pci_msi_domain_free_irqs - Free interrupts for @dev in @domain + * @domain: The interrupt domain + * @dev: The device for which to free interrupts + */ +void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev) +{ + msi_domain_free_irqs(domain, &dev->dev); +} + +/** + * pci_msi_create_default_irq_domain - Create a default MSI interrupt domain + * @node: Optional device-tree node of the interrupt controller + * @info: MSI domain info + * @parent: Parent irq domain + * + * Returns: A domain pointer or NULL in case of failure. If successful + * the default PCI/MSI irqdomain pointer is updated. + */ +struct irq_domain *pci_msi_create_default_irq_domain(struct device_node *node, + struct msi_domain_info *info, struct irq_domain *parent) +{ + struct irq_domain *domain; + + mutex_lock(&pci_msi_domain_lock); + if (pci_msi_default_domain) { + pr_err("PCI: default irq domain for PCI MSI has already been created.\n"); + domain = NULL; + } else { + domain = pci_msi_create_irq_domain(node, info, parent); + pci_msi_default_domain = domain; + } + mutex_unlock(&pci_msi_domain_lock); + + return domain; +} +#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */ diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 553212f037c3..e8d695b3f54e 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -560,7 +560,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, struct msi_msg msg; get_cached_msi_msg(irq, &msg); - write_msi_msg(irq, &msg); + pci_write_msi_msg(irq, &msg); } ret = request_irq(irq, vfio_msihandler, 0, diff --git a/include/asm-generic/msi.h b/include/asm-generic/msi.h new file mode 100644 index 000000000000..61c58d8878ce --- /dev/null +++ b/include/asm-generic/msi.h @@ -0,0 +1,32 @@ +#ifndef __ASM_GENERIC_MSI_H +#define __ASM_GENERIC_MSI_H + +#include <linux/types.h> + +#ifndef NUM_MSI_ALLOC_SCRATCHPAD_REGS +# define NUM_MSI_ALLOC_SCRATCHPAD_REGS 2 +#endif + +struct msi_desc; + +/** + * struct msi_alloc_info - Default structure for MSI interrupt allocation. + * @desc: Pointer to msi descriptor + * @hwirq: Associated hw interrupt number in the domain + * @scratchpad: Storage for implementation specific scratch data + * + * Architectures can provide their own implementation by not including + * asm-generic/msi.h into their arch specific header file. + */ +typedef struct msi_alloc_info { + struct msi_desc *desc; + irq_hw_number_t hwirq; + union { + unsigned long ul; + void *ptr; + } scratchpad[NUM_MSI_ALLOC_SCRATCHPAD_REGS]; +} msi_alloc_info_t; + +#define GENERIC_MSI_DOMAIN_OPS 1 + +#endif diff --git a/include/linux/irq.h b/include/linux/irq.h index 8588e5efe577..d09ec7a1243e 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -15,6 +15,7 @@ #include <linux/spinlock.h> #include <linux/cpumask.h> #include <linux/gfp.h> +#include <linux/irqhandler.h> #include <linux/irqreturn.h> #include <linux/irqnr.h> #include <linux/errno.h> @@ -28,11 +29,7 @@ struct seq_file; struct module; -struct irq_desc; -struct irq_data; -typedef void (*irq_flow_handler_t)(unsigned int irq, - struct irq_desc *desc); -typedef void (*irq_preflow_handler_t)(struct irq_data *data); +struct msi_msg; /* * IRQ line status. @@ -114,10 +111,14 @@ enum { * * IRQ_SET_MASK_OK - OK, core updates irq_data.affinity * IRQ_SET_MASK_NOCPY - OK, chip did update irq_data.affinity + * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to + * support stacked irqchips, which indicates skipping + * all descendent irqchips. */ enum { IRQ_SET_MASK_OK = 0, IRQ_SET_MASK_OK_NOCOPY, + IRQ_SET_MASK_OK_DONE, }; struct msi_desc; @@ -134,6 +135,8 @@ struct irq_domain; * @chip: low level interrupt hardware access * @domain: Interrupt translation domain; responsible for mapping * between hwirq number and linux irq number. + * @parent_data: pointer to parent struct irq_data to support hierarchy + * irq_domain * @handler_data: per-IRQ data for the irq_chip methods * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations @@ -152,6 +155,9 @@ struct irq_data { unsigned int state_use_accessors; struct irq_chip *chip; struct irq_domain *domain; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + struct irq_data *parent_data; +#endif void *handler_data; void *chip_data; struct msi_desc *msi_desc; @@ -316,6 +322,8 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) * any other callback related to this irq * @irq_release_resources: optional to release resources acquired with * irq_request_resources + * @irq_compose_msi_msg: optional to compose message content for MSI + * @irq_write_msi_msg: optional to write message content for MSI * @flags: chip specific flags */ struct irq_chip { @@ -352,6 +360,9 @@ struct irq_chip { int (*irq_request_resources)(struct irq_data *data); void (*irq_release_resources)(struct irq_data *data); + void (*irq_compose_msi_msg)(struct irq_data *data, struct msi_msg *msg); + void (*irq_write_msi_msg)(struct irq_data *data, struct msi_msg *msg); + unsigned long flags; }; @@ -439,6 +450,18 @@ extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc); extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); +extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +extern void irq_chip_ack_parent(struct irq_data *data); +extern int irq_chip_retrigger_hierarchy(struct irq_data *data); +extern void irq_chip_mask_parent(struct irq_data *data); +extern void irq_chip_unmask_parent(struct irq_data *data); +extern void irq_chip_eoi_parent(struct irq_data *data); +extern int irq_chip_set_affinity_parent(struct irq_data *data, + const struct cpumask *dest, + bool force); +#endif + /* Handling of unhandled and spurious interrupts: */ extern void note_interrupt(unsigned int irq, struct irq_desc *desc, irqreturn_t action_ret); diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index b0f9d16e48f6..676d7306a360 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -33,11 +33,14 @@ #define _LINUX_IRQDOMAIN_H #include <linux/types.h> +#include <linux/irqhandler.h> #include <linux/radix-tree.h> struct device_node; struct irq_domain; struct of_device_id; +struct irq_chip; +struct irq_data; /* Number of irqs reserved for a legacy isa controller */ #define NUM_ISA_INTERRUPTS 16 @@ -64,6 +67,16 @@ struct irq_domain_ops { int (*xlate)(struct irq_domain *d, struct device_node *node, const u32 *intspec, unsigned int intsize, unsigned long *out_hwirq, unsigned int *out_type); + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + /* extended V2 interfaces to support hierarchy irq_domains */ + int (*alloc)(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs, void *arg); + void (*free)(struct irq_domain *d, unsigned int virq, + unsigned int nr_irqs); + void (*activate)(struct irq_domain *d, struct irq_data *irq_data); + void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data); +#endif }; extern struct irq_domain_ops irq_generic_chip_ops; @@ -77,6 +90,7 @@ struct irq_domain_chip_generic; * @ops: pointer to irq_domain methods * @host_data: private data pointer for use by owner. Not touched by irq_domain * core code. + * @flags: host per irq_domain flags * * Optional elements * @of_node: Pointer to device tree nodes associated with the irq_domain. Used @@ -84,6 +98,7 @@ struct irq_domain_chip_generic; * @gc: Pointer to a list of generic chips. There is a helper function for * setting up one or more generic chips for interrupt controllers * drivers using the generic chip library which uses this pointer. + * @parent: Pointer to parent irq_domain to support hierarchy irq_domains * * Revmap data, used internally by irq_domain * @revmap_direct_max_irq: The largest hwirq that can be set for controllers that @@ -97,10 +112,14 @@ struct irq_domain { const char *name; const struct irq_domain_ops *ops; void *host_data; + unsigned int flags; /* Optional data */ struct device_node *of_node; struct irq_domain_chip_generic *gc; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + struct irq_domain *parent; +#endif /* reverse map data. The linear map gets appended to the irq_domain */ irq_hw_number_t hwirq_max; @@ -110,6 +129,22 @@ struct irq_domain { unsigned int linear_revmap[]; }; +/* Irq domain flags */ +enum { + /* Irq domain is hierarchical */ + IRQ_DOMAIN_FLAG_HIERARCHY = (1 << 0), + + /* Core calls alloc/free recursive through the domain hierarchy. */ + IRQ_DOMAIN_FLAG_AUTO_RECURSIVE = (1 << 1), + + /* + * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved + * for implementation specific purposes and ignored by the + * core code. + */ + IRQ_DOMAIN_FLAG_NONCORE = (1 << 16), +}; + #ifdef CONFIG_IRQ_DOMAIN struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, irq_hw_number_t hwirq_max, int direct_max, @@ -220,8 +255,74 @@ int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr, const u32 *intspec, unsigned int intsize, irq_hw_number_t *out_hwirq, unsigned int *out_type); +/* V2 interfaces to support hierarchy IRQ domains. */ +extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, + unsigned int virq); +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +extern struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, + unsigned int flags, unsigned int size, + struct device_node *node, + const struct irq_domain_ops *ops, void *host_data); +extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc); +extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs); +extern void irq_domain_activate_irq(struct irq_data *irq_data); +extern void irq_domain_deactivate_irq(struct irq_data *irq_data); + +static inline int irq_domain_alloc_irqs(struct irq_domain *domain, + unsigned int nr_irqs, int node, void *arg) +{ + return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false); +} + +extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, + unsigned int virq, + irq_hw_number_t hwirq, + struct irq_chip *chip, + void *chip_data); +extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, struct irq_chip *chip, + void *chip_data, irq_flow_handler_t handler, + void *handler_data, const char *handler_name); +extern void irq_domain_reset_irq_data(struct irq_data *irq_data); +extern void irq_domain_free_irqs_common(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs); +extern void irq_domain_free_irqs_top(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs); + +extern int irq_domain_alloc_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs, void *arg); + +extern void irq_domain_free_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs); + +static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY; +} +#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +static inline void irq_domain_activate_irq(struct irq_data *data) { } +static inline void irq_domain_deactivate_irq(struct irq_data *data) { } +static inline int irq_domain_alloc_irqs(struct irq_domain *domain, + unsigned int nr_irqs, int node, void *arg) +{ + return -1; +} + +static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) +{ + return false; +} +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ + #else /* CONFIG_IRQ_DOMAIN */ static inline void irq_dispose_mapping(unsigned int virq) { } +static inline void irq_domain_activate_irq(struct irq_data *data) { } +static inline void irq_domain_deactivate_irq(struct irq_data *data) { } #endif /* !CONFIG_IRQ_DOMAIN */ #endif /* _LINUX_IRQDOMAIN_H */ diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h new file mode 100644 index 000000000000..62d543004197 --- /dev/null +++ b/include/linux/irqhandler.h @@ -0,0 +1,14 @@ +#ifndef _LINUX_IRQHANDLER_H +#define _LINUX_IRQHANDLER_H + +/* + * Interrupt flow handler typedefs are defined here to avoid circular + * include dependencies. + */ + +struct irq_desc; +struct irq_data; +typedef void (*irq_flow_handler_t)(unsigned int irq, struct irq_desc *desc); +typedef void (*irq_preflow_handler_t)(struct irq_data *data); + +#endif diff --git a/include/linux/msi.h b/include/linux/msi.h index 44f4746d033b..8ac4a68ffae2 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -10,17 +10,12 @@ struct msi_msg { u32 data; /* 16 bits of msi message data */ }; +extern int pci_msi_ignore_mask; /* Helper functions */ struct irq_data; struct msi_desc; -void mask_msi_irq(struct irq_data *data); -void unmask_msi_irq(struct irq_data *data); -void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); -void read_msi_msg(unsigned int irq, struct msi_msg *msg); void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); -void write_msi_msg(unsigned int irq, struct msi_msg *msg); struct msi_desc { struct { @@ -48,6 +43,52 @@ struct msi_desc { struct msi_msg msg; }; +/* Helpers to hide struct msi_desc implementation details */ +#define msi_desc_to_dev(desc) (&(desc)->dev.dev) +#define dev_to_msi_list(dev) (&to_pci_dev((dev))->msi_list) +#define first_msi_entry(dev) \ + list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list) +#define for_each_msi_entry(desc, dev) \ + list_for_each_entry((desc), dev_to_msi_list((dev)), list) + +#ifdef CONFIG_PCI_MSI +#define first_pci_msi_entry(pdev) first_msi_entry(&(pdev)->dev) +#define for_each_pci_msi_entry(desc, pdev) \ + for_each_msi_entry((desc), &(pdev)->dev) + +static inline struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) +{ + return desc->dev; +} +#endif /* CONFIG_PCI_MSI */ + +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_write_msi_msg(unsigned int irq, struct msi_msg *msg); + +u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); +u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); +void pci_msi_mask_irq(struct irq_data *data); +void pci_msi_unmask_irq(struct irq_data *data); + +/* Conversion helpers. Should be removed after merging */ +static inline void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) +{ + __pci_write_msi_msg(entry, msg); +} +static inline void write_msi_msg(int irq, struct msi_msg *msg) +{ + pci_write_msi_msg(irq, msg); +} +static inline void mask_msi_irq(struct irq_data *data) +{ + pci_msi_mask_irq(data); +} +static inline void unmask_msi_irq(struct irq_data *data) +{ + pci_msi_unmask_irq(data); +} + /* * The arch hooks to setup up msi irqs. Those functions are * implemented as weak symbols so that they /can/ be overriden by @@ -61,18 +102,142 @@ void arch_restore_msi_irqs(struct pci_dev *dev); void default_teardown_msi_irqs(struct pci_dev *dev); void default_restore_msi_irqs(struct pci_dev *dev); -u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); -u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag); -struct msi_chip { +struct msi_controller { struct module *owner; struct device *dev; struct device_node *of_node; struct list_head list; +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + struct irq_domain *domain; +#endif - int (*setup_irq)(struct msi_chip *chip, struct pci_dev *dev, + int (*setup_irq)(struct msi_controller *chip, struct pci_dev *dev, struct msi_desc *desc); - void (*teardown_irq)(struct msi_chip *chip, unsigned int irq); + void (*teardown_irq)(struct msi_controller *chip, unsigned int irq); +}; + +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + +#include <linux/irqhandler.h> +#include <asm/msi.h> + +struct irq_domain; +struct irq_chip; +struct device_node; +struct msi_domain_info; + +/** + * struct msi_domain_ops - MSI interrupt domain callbacks + * @get_hwirq: Retrieve the resulting hw irq number + * @msi_init: Domain specific init function for MSI interrupts + * @msi_free: Domain specific function to free a MSI interrupts + * @msi_check: Callback for verification of the domain/info/dev data + * @msi_prepare: Prepare the allocation of the interrupts in the domain + * @msi_finish: Optional callbacl to finalize the allocation + * @set_desc: Set the msi descriptor for an interrupt + * @handle_error: Optional error handler if the allocation fails + * + * @get_hwirq, @msi_init and @msi_free are callbacks used by + * msi_create_irq_domain() and related interfaces + * + * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error + * are callbacks used by msi_irq_domain_alloc_irqs() and related + * interfaces which are based on msi_desc. + */ +struct msi_domain_ops { + irq_hw_number_t (*get_hwirq)(struct msi_domain_info *info, + msi_alloc_info_t *arg); + int (*msi_init)(struct irq_domain *domain, + struct msi_domain_info *info, + unsigned int virq, irq_hw_number_t hwirq, + msi_alloc_info_t *arg); + void (*msi_free)(struct irq_domain *domain, + struct msi_domain_info *info, + unsigned int virq); + int (*msi_check)(struct irq_domain *domain, + struct msi_domain_info *info, + struct device *dev); + int (*msi_prepare)(struct irq_domain *domain, + struct device *dev, int nvec, + msi_alloc_info_t *arg); + void (*msi_finish)(msi_alloc_info_t *arg, int retval); + void (*set_desc)(msi_alloc_info_t *arg, + struct msi_desc *desc); + int (*handle_error)(struct irq_domain *domain, + struct msi_desc *desc, int error); +}; + +/** + * struct msi_domain_info - MSI interrupt domain data + * @flags: Flags to decribe features and capabilities + * @ops: The callback data structure + * @chip: Optional: associated interrupt chip + * @chip_data: Optional: associated interrupt chip data + * @handler: Optional: associated interrupt flow handler + * @handler_data: Optional: associated interrupt flow handler data + * @handler_name: Optional: associated interrupt flow handler name + * @data: Optional: domain specific data + */ +struct msi_domain_info { + u32 flags; + struct msi_domain_ops *ops; + struct irq_chip *chip; + void *chip_data; + irq_flow_handler_t handler; + void *handler_data; + const char *handler_name; + void *data; +}; + +/* Flags for msi_domain_info */ +enum { + /* + * Init non implemented ops callbacks with default MSI domain + * callbacks. + */ + MSI_FLAG_USE_DEF_DOM_OPS = (1 << 0), + /* + * Init non implemented chip callbacks with default MSI chip + * callbacks. + */ + MSI_FLAG_USE_DEF_CHIP_OPS = (1 << 1), + /* Build identity map between hwirq and irq */ + MSI_FLAG_IDENTITY_MAP = (1 << 2), + /* Support multiple PCI MSI interrupts */ + MSI_FLAG_MULTI_PCI_MSI = (1 << 3), + /* Support PCI MSIX interrupts */ + MSI_FLAG_PCI_MSIX = (1 << 4), }; +int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, + bool force); + +struct irq_domain *msi_create_irq_domain(struct device_node *of_node, + struct msi_domain_info *info, + struct irq_domain *parent); +int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, + int nvec); +void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); +struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); + +#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ + +#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); +struct irq_domain *pci_msi_create_irq_domain(struct device_node *node, + struct msi_domain_info *info, + struct irq_domain *parent); +int pci_msi_domain_alloc_irqs(struct irq_domain *domain, struct pci_dev *dev, + int nvec, int type); +void pci_msi_domain_free_irqs(struct irq_domain *domain, struct pci_dev *dev); +struct irq_domain *pci_msi_create_default_irq_domain(struct device_node *node, + struct msi_domain_info *info, struct irq_domain *parent); + +irq_hw_number_t pci_msi_domain_calc_hwirq(struct pci_dev *dev, + struct msi_desc *desc); +int pci_msi_domain_check_cap(struct irq_domain *domain, + struct msi_domain_info *info, struct device *dev); +#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */ + #endif /* LINUX_MSI_H */ diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h index 1fd207e7a847..ce0e5abeb454 100644 --- a/include/linux/of_pci.h +++ b/include/linux/of_pci.h @@ -59,13 +59,13 @@ int of_pci_get_host_bridge_resources(struct device_node *dev, #endif #if defined(CONFIG_OF) && defined(CONFIG_PCI_MSI) -int of_pci_msi_chip_add(struct msi_chip *chip); -void of_pci_msi_chip_remove(struct msi_chip *chip); -struct msi_chip *of_pci_find_msi_chip_by_node(struct device_node *of_node); +int of_pci_msi_chip_add(struct msi_controller *chip); +void of_pci_msi_chip_remove(struct msi_controller *chip); +struct msi_controller *of_pci_find_msi_chip_by_node(struct device_node *of_node); #else -static inline int of_pci_msi_chip_add(struct msi_chip *chip) { return -EINVAL; } -static inline void of_pci_msi_chip_remove(struct msi_chip *chip) { } -static inline struct msi_chip * +static inline int of_pci_msi_chip_add(struct msi_controller *chip) { return -EINVAL; } +static inline void of_pci_msi_chip_remove(struct msi_controller *chip) { } +static inline struct msi_controller * of_pci_find_msi_chip_by_node(struct device_node *of_node) { return NULL; } #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 4c8ac5fcc224..a523cee3abb5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -450,7 +450,7 @@ struct pci_bus { struct resource busn_res; /* bus numbers routed to this bus */ struct pci_ops *ops; /* configuration access functions */ - struct msi_chip *msi; /* MSI controller */ + struct msi_controller *msi; /* MSI controller */ void *sysdata; /* hook for sys-specific extension */ struct proc_dir_entry *procdir; /* directory entry in /proc/bus/pci */ diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 225086b2652e..9a76e3beda54 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -55,6 +55,21 @@ config GENERIC_IRQ_CHIP config IRQ_DOMAIN bool +# Support for hierarchical irq domains +config IRQ_DOMAIN_HIERARCHY + bool + select IRQ_DOMAIN + +# Generic MSI interrupt support +config GENERIC_MSI_IRQ + bool + +# Generic MSI hierarchical interrupt domain support +config GENERIC_MSI_IRQ_DOMAIN + bool + select IRQ_DOMAIN_HIERARCHY + select GENERIC_MSI_IRQ + config HANDLE_DOMAIN_IRQ bool diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile index fff17381f0af..d12123526e2b 100644 --- a/kernel/irq/Makefile +++ b/kernel/irq/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_IRQ_DOMAIN) += irqdomain.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o obj-$(CONFIG_PM_SLEEP) += pm.o +obj-$(CONFIG_GENERIC_MSI_IRQ) += msi.o diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index e5202f00cabc..6f1c7a566b95 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <linux/irqdomain.h> #include <trace/events/irq.h> @@ -178,6 +179,7 @@ int irq_startup(struct irq_desc *desc, bool resend) irq_state_clr_disabled(desc); desc->depth = 0; + irq_domain_activate_irq(&desc->irq_data); if (desc->irq_data.chip->irq_startup) { ret = desc->irq_data.chip->irq_startup(&desc->irq_data); irq_state_clr_masked(desc); @@ -199,6 +201,7 @@ void irq_shutdown(struct irq_desc *desc) desc->irq_data.chip->irq_disable(&desc->irq_data); else desc->irq_data.chip->irq_mask(&desc->irq_data); + irq_domain_deactivate_irq(&desc->irq_data); irq_state_set_masked(desc); } @@ -728,7 +731,30 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, if (!handle) { handle = handle_bad_irq; } else { - if (WARN_ON(desc->irq_data.chip == &no_irq_chip)) + struct irq_data *irq_data = &desc->irq_data; +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + /* + * With hierarchical domains we might run into a + * situation where the outermost chip is not yet set + * up, but the inner chips are there. Instead of + * bailing we install the handler, but obviously we + * cannot enable/startup the interrupt at this point. + */ + while (irq_data) { + if (irq_data->chip != &no_irq_chip) + break; + /* + * Bail out if the outer chip is not set up + * and the interrrupt supposed to be started + * right away. + */ + if (WARN_ON(is_chained)) + goto out; + /* Try the parent */ + irq_data = irq_data->parent_data; + } +#endif + if (WARN_ON(!irq_data || irq_data->chip == &no_irq_chip)) goto out; } @@ -847,3 +873,105 @@ void irq_cpu_offline(void) raw_spin_unlock_irqrestore(&desc->lock, flags); } } + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +/** + * irq_chip_ack_parent - Acknowledge the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_ack_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_ack(data); +} + +/** + * irq_chip_mask_parent - Mask the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_mask_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_mask(data); +} + +/** + * irq_chip_unmask_parent - Unmask the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_unmask_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_unmask(data); +} + +/** + * irq_chip_eoi_parent - Invoke EOI on the parent interrupt + * @data: Pointer to interrupt specific data + */ +void irq_chip_eoi_parent(struct irq_data *data) +{ + data = data->parent_data; + data->chip->irq_eoi(data); +} + +/** + * irq_chip_set_affinity_parent - Set affinity on the parent interrupt + * @data: Pointer to interrupt specific data + * @dest: The affinity mask to set + * @force: Flag to enforce setting (disable online checks) + * + * Conditinal, as the underlying parent chip might not implement it. + */ +int irq_chip_set_affinity_parent(struct irq_data *data, + const struct cpumask *dest, bool force) +{ + data = data->parent_data; + if (data->chip->irq_set_affinity) + return data->chip->irq_set_affinity(data, dest, force); + + return -ENOSYS; +} + +/** + * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware + * @data: Pointer to interrupt specific data + * + * Iterate through the domain hierarchy of the interrupt and check + * whether a hw retrigger function exists. If yes, invoke it. + */ +int irq_chip_retrigger_hierarchy(struct irq_data *data) +{ + for (data = data->parent_data; data; data = data->parent_data) + if (data->chip && data->chip->irq_retrigger) + return data->chip->irq_retrigger(data); + + return -ENOSYS; +} +#endif + +/** + * irq_chip_compose_msi_msg - Componse msi message for a irq chip + * @data: Pointer to interrupt specific data + * @msg: Pointer to the MSI message + * + * For hierarchical domains we find the first chip in the hierarchy + * which implements the irq_compose_msi_msg callback. For non + * hierarchical we use the top level chip. + */ +int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct irq_data *pos = NULL; + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY + for (; data; data = data->parent_data) +#endif + if (data->chip && data->chip->irq_compose_msi_msg) + pos = data; + if (!pos) + return -ENOSYS; + + pos->chip->irq_compose_msi_msg(pos, msg); + + return 0; +} diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 6534ff6ce02e..7fac311057b8 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -23,6 +23,10 @@ static DEFINE_MUTEX(irq_domain_mutex); static DEFINE_MUTEX(revmap_trees_mutex); static struct irq_domain *irq_default_domain; +static int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, + irq_hw_number_t hwirq, int node); +static void irq_domain_check_hierarchy(struct irq_domain *domain); + /** * __irq_domain_add() - Allocate a new irq_domain data structure * @of_node: optional device-tree node of the interrupt controller @@ -30,7 +34,7 @@ static struct irq_domain *irq_default_domain; * @hwirq_max: Maximum number of interrupts supported by controller * @direct_max: Maximum value of direct maps; Use ~0 for no limit; 0 for no * direct mapping - * @ops: map/unmap domain callbacks + * @ops: domain callbacks * @host_data: Controller private data pointer * * Allocates and initialize and irq_domain structure. @@ -56,6 +60,7 @@ struct irq_domain *__irq_domain_add(struct device_node *of_node, int size, domain->hwirq_max = hwirq_max; domain->revmap_size = size; domain->revmap_direct_max_irq = direct_max; + irq_domain_check_hierarchy(domain); mutex_lock(&irq_domain_mutex); list_add(&domain->link, &irq_domain_list); @@ -109,7 +114,7 @@ EXPORT_SYMBOL_GPL(irq_domain_remove); * @first_irq: first number of irq block assigned to the domain, * pass zero to assign irqs on-the-fly. If first_irq is non-zero, then * pre-map all of the irqs in the domain to virqs starting at first_irq. - * @ops: map/unmap domain callbacks + * @ops: domain callbacks * @host_data: Controller private data pointer * * Allocates an irq_domain, and optionally if first_irq is positive then also @@ -174,10 +179,8 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node, domain = __irq_domain_add(of_node, first_hwirq + size, first_hwirq + size, 0, ops, host_data); - if (!domain) - return NULL; - - irq_domain_associate_many(domain, first_irq, first_hwirq, size); + if (domain) + irq_domain_associate_many(domain, first_irq, first_hwirq, size); return domain; } @@ -388,7 +391,6 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping); unsigned int irq_create_mapping(struct irq_domain *domain, irq_hw_number_t hwirq) { - unsigned int hint; int virq; pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq); @@ -410,12 +412,8 @@ unsigned int irq_create_mapping(struct irq_domain *domain, } /* Allocate a virtual interrupt number */ - hint = hwirq % nr_irqs; - if (hint == 0) - hint++; - virq = irq_alloc_desc_from(hint, of_node_to_nid(domain->of_node)); - if (virq <= 0) - virq = irq_alloc_desc_from(1, of_node_to_nid(domain->of_node)); + virq = irq_domain_alloc_descs(-1, 1, hwirq, + of_node_to_nid(domain->of_node)); if (virq <= 0) { pr_debug("-> virq allocation failed\n"); return 0; @@ -471,7 +469,7 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) struct irq_domain *domain; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; - unsigned int virq; + int virq; domain = irq_data->np ? irq_find_host(irq_data->np) : irq_default_domain; if (!domain) { @@ -489,10 +487,24 @@ unsigned int irq_create_of_mapping(struct of_phandle_args *irq_data) return 0; } - /* Create mapping */ - virq = irq_create_mapping(domain, hwirq); - if (!virq) - return virq; + if (irq_domain_is_hierarchy(domain)) { + /* + * If we've already configured this interrupt, + * don't do it again, or hell will break loose. + */ + virq = irq_find_mapping(domain, hwirq); + if (virq) + return virq; + + virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, irq_data); + if (virq <= 0) + return 0; + } else { + /* Create mapping */ + virq = irq_create_mapping(domain, hwirq); + if (!virq) + return virq; + } /* Set type if specified and different than the current one */ if (type != IRQ_TYPE_NONE && @@ -540,8 +552,8 @@ unsigned int irq_find_mapping(struct irq_domain *domain, return 0; if (hwirq < domain->revmap_direct_max_irq) { - data = irq_get_irq_data(hwirq); - if (data && (data->domain == domain) && (data->hwirq == hwirq)) + data = irq_domain_get_irq_data(domain, hwirq); + if (data && data->hwirq == hwirq) return hwirq; } @@ -709,3 +721,518 @@ const struct irq_domain_ops irq_domain_simple_ops = { .xlate = irq_domain_xlate_onetwocell, }; EXPORT_SYMBOL_GPL(irq_domain_simple_ops); + +static int irq_domain_alloc_descs(int virq, unsigned int cnt, + irq_hw_number_t hwirq, int node) +{ + unsigned int hint; + + if (virq >= 0) { + virq = irq_alloc_descs(virq, virq, cnt, node); + } else { + hint = hwirq % nr_irqs; + if (hint == 0) + hint++; + virq = irq_alloc_descs_from(hint, cnt, node); + if (virq <= 0 && hint > 1) + virq = irq_alloc_descs_from(1, cnt, node); + } + + return virq; +} + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +/** + * irq_domain_add_hierarchy - Add a irqdomain into the hierarchy + * @parent: Parent irq domain to associate with the new domain + * @flags: Irq domain flags associated to the domain + * @size: Size of the domain. See below + * @node: Optional device-tree node of the interrupt controller + * @ops: Pointer to the interrupt domain callbacks + * @host_data: Controller private data pointer + * + * If @size is 0 a tree domain is created, otherwise a linear domain. + * + * If successful the parent is associated to the new domain and the + * domain flags are set. + * Returns pointer to IRQ domain, or NULL on failure. + */ +struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent, + unsigned int flags, + unsigned int size, + struct device_node *node, + const struct irq_domain_ops *ops, + void *host_data) +{ + struct irq_domain *domain; + + if (size) + domain = irq_domain_add_linear(node, size, ops, host_data); + else + domain = irq_domain_add_tree(node, ops, host_data); + if (domain) { + domain->parent = parent; + domain->flags |= flags; + } + + return domain; +} + +static void irq_domain_insert_irq(int virq) +{ + struct irq_data *data; + + for (data = irq_get_irq_data(virq); data; data = data->parent_data) { + struct irq_domain *domain = data->domain; + irq_hw_number_t hwirq = data->hwirq; + + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = virq; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_insert(&domain->revmap_tree, hwirq, data); + mutex_unlock(&revmap_trees_mutex); + } + + /* If not already assigned, give the domain the chip's name */ + if (!domain->name && data->chip) + domain->name = data->chip->name; + } + + irq_clear_status_flags(virq, IRQ_NOREQUEST); +} + +static void irq_domain_remove_irq(int virq) +{ + struct irq_data *data; + + irq_set_status_flags(virq, IRQ_NOREQUEST); + irq_set_chip_and_handler(virq, NULL, NULL); + synchronize_irq(virq); + smp_mb(); + + for (data = irq_get_irq_data(virq); data; data = data->parent_data) { + struct irq_domain *domain = data->domain; + irq_hw_number_t hwirq = data->hwirq; + + if (hwirq < domain->revmap_size) { + domain->linear_revmap[hwirq] = 0; + } else { + mutex_lock(&revmap_trees_mutex); + radix_tree_delete(&domain->revmap_tree, hwirq); + mutex_unlock(&revmap_trees_mutex); + } + } +} + +static struct irq_data *irq_domain_insert_irq_data(struct irq_domain *domain, + struct irq_data *child) +{ + struct irq_data *irq_data; + + irq_data = kzalloc_node(sizeof(*irq_data), GFP_KERNEL, child->node); + if (irq_data) { + child->parent_data = irq_data; + irq_data->irq = child->irq; + irq_data->node = child->node; + irq_data->domain = domain; + } + + return irq_data; +} + +static void irq_domain_free_irq_data(unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irq_data, *tmp; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_get_irq_data(virq + i); + tmp = irq_data->parent_data; + irq_data->parent_data = NULL; + irq_data->domain = NULL; + + while (tmp) { + irq_data = tmp; + tmp = tmp->parent_data; + kfree(irq_data); + } + } +} + +static int irq_domain_alloc_irq_data(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *irq_data; + struct irq_domain *parent; + int i; + + /* The outermost irq_data is embedded in struct irq_desc */ + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_get_irq_data(virq + i); + irq_data->domain = domain; + + for (parent = domain->parent; parent; parent = parent->parent) { + irq_data = irq_domain_insert_irq_data(parent, irq_data); + if (!irq_data) { + irq_domain_free_irq_data(virq, i + 1); + return -ENOMEM; + } + } + } + + return 0; +} + +/** + * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain + * @domain: domain to match + * @virq: IRQ number to get irq_data + */ +struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, + unsigned int virq) +{ + struct irq_data *irq_data; + + for (irq_data = irq_get_irq_data(virq); irq_data; + irq_data = irq_data->parent_data) + if (irq_data->domain == domain) + return irq_data; + + return NULL; +} + +/** + * irq_domain_set_hwirq_and_chip - Set hwirq and irqchip of @virq at @domain + * @domain: Interrupt domain to match + * @virq: IRQ number + * @hwirq: The hwirq number + * @chip: The associated interrupt chip + * @chip_data: The associated chip data + */ +int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, struct irq_chip *chip, + void *chip_data) +{ + struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq); + + if (!irq_data) + return -ENOENT; + + irq_data->hwirq = hwirq; + irq_data->chip = chip ? chip : &no_irq_chip; + irq_data->chip_data = chip_data; + + return 0; +} + +/** + * irq_domain_set_info - Set the complete data for a @virq in @domain + * @domain: Interrupt domain to match + * @virq: IRQ number + * @hwirq: The hardware interrupt number + * @chip: The associated interrupt chip + * @chip_data: The associated interrupt chip data + * @handler: The interrupt flow handler + * @handler_data: The interrupt flow handler data + * @handler_name: The interrupt handler name + */ +void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, + irq_hw_number_t hwirq, struct irq_chip *chip, + void *chip_data, irq_flow_handler_t handler, + void *handler_data, const char *handler_name) +{ + irq_domain_set_hwirq_and_chip(domain, virq, hwirq, chip, chip_data); + __irq_set_handler(virq, handler, 0, handler_name); + irq_set_handler_data(virq, handler_data); +} + +/** + * irq_domain_reset_irq_data - Clear hwirq, chip and chip_data in @irq_data + * @irq_data: The pointer to irq_data + */ +void irq_domain_reset_irq_data(struct irq_data *irq_data) +{ + irq_data->hwirq = 0; + irq_data->chip = &no_irq_chip; + irq_data->chip_data = NULL; +} + +/** + * irq_domain_free_irqs_common - Clear irq_data and free the parent + * @domain: Interrupt domain to match + * @virq: IRQ number to start with + * @nr_irqs: The number of irqs to free + */ +void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *irq_data; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + if (irq_data) + irq_domain_reset_irq_data(irq_data); + } + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +} + +/** + * irq_domain_free_irqs_top - Clear handler and handler data, clear irqdata and free parent + * @domain: Interrupt domain to match + * @virq: IRQ number to start with + * @nr_irqs: The number of irqs to free + */ +void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_set_handler_data(virq + i, NULL); + irq_set_handler(virq + i, NULL); + } + irq_domain_free_irqs_common(domain, virq, nr_irqs); +} + +static bool irq_domain_is_auto_recursive(struct irq_domain *domain) +{ + return domain->flags & IRQ_DOMAIN_FLAG_AUTO_RECURSIVE; +} + +static void irq_domain_free_irqs_recursive(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs) +{ + domain->ops->free(domain, irq_base, nr_irqs); + if (irq_domain_is_auto_recursive(domain)) { + BUG_ON(!domain->parent); + irq_domain_free_irqs_recursive(domain->parent, irq_base, + nr_irqs); + } +} + +static int irq_domain_alloc_irqs_recursive(struct irq_domain *domain, + unsigned int irq_base, + unsigned int nr_irqs, void *arg) +{ + int ret = 0; + struct irq_domain *parent = domain->parent; + bool recursive = irq_domain_is_auto_recursive(domain); + + BUG_ON(recursive && !parent); + if (recursive) + ret = irq_domain_alloc_irqs_recursive(parent, irq_base, + nr_irqs, arg); + if (ret >= 0) + ret = domain->ops->alloc(domain, irq_base, nr_irqs, arg); + if (ret < 0 && recursive) + irq_domain_free_irqs_recursive(parent, irq_base, nr_irqs); + + return ret; +} + +/** + * __irq_domain_alloc_irqs - Allocate IRQs from domain + * @domain: domain to allocate from + * @irq_base: allocate specified IRQ nubmer if irq_base >= 0 + * @nr_irqs: number of IRQs to allocate + * @node: NUMA node id for memory allocation + * @arg: domain specific argument + * @realloc: IRQ descriptors have already been allocated if true + * + * Allocate IRQ numbers and initialized all data structures to support + * hierarchy IRQ domains. + * Parameter @realloc is mainly to support legacy IRQs. + * Returns error code or allocated IRQ number + * + * The whole process to setup an IRQ has been split into two steps. + * The first step, __irq_domain_alloc_irqs(), is to allocate IRQ + * descriptor and required hardware resources. The second step, + * irq_domain_activate_irq(), is to program hardwares with preallocated + * resources. In this way, it's easier to rollback when failing to + * allocate resources. + */ +int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, + unsigned int nr_irqs, int node, void *arg, + bool realloc) +{ + int i, ret, virq; + + if (domain == NULL) { + domain = irq_default_domain; + if (WARN(!domain, "domain is NULL; cannot allocate IRQ\n")) + return -EINVAL; + } + + if (!domain->ops->alloc) { + pr_debug("domain->ops->alloc() is NULL\n"); + return -ENOSYS; + } + + if (realloc && irq_base >= 0) { + virq = irq_base; + } else { + virq = irq_domain_alloc_descs(irq_base, nr_irqs, 0, node); + if (virq < 0) { + pr_debug("cannot allocate IRQ(base %d, count %d)\n", + irq_base, nr_irqs); + return virq; + } + } + + if (irq_domain_alloc_irq_data(domain, virq, nr_irqs)) { + pr_debug("cannot allocate memory for IRQ%d\n", virq); + ret = -ENOMEM; + goto out_free_desc; + } + + mutex_lock(&irq_domain_mutex); + ret = irq_domain_alloc_irqs_recursive(domain, virq, nr_irqs, arg); + if (ret < 0) { + mutex_unlock(&irq_domain_mutex); + goto out_free_irq_data; + } + for (i = 0; i < nr_irqs; i++) + irq_domain_insert_irq(virq + i); + mutex_unlock(&irq_domain_mutex); + + return virq; + +out_free_irq_data: + irq_domain_free_irq_data(virq, nr_irqs); +out_free_desc: + irq_free_descs(virq, nr_irqs); + return ret; +} + +/** + * irq_domain_free_irqs - Free IRQ number and associated data structures + * @virq: base IRQ number + * @nr_irqs: number of IRQs to free + */ +void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *data = irq_get_irq_data(virq); + int i; + + if (WARN(!data || !data->domain || !data->domain->ops->free, + "NULL pointer, cannot free irq\n")) + return; + + mutex_lock(&irq_domain_mutex); + for (i = 0; i < nr_irqs; i++) + irq_domain_remove_irq(virq + i); + irq_domain_free_irqs_recursive(data->domain, virq, nr_irqs); + mutex_unlock(&irq_domain_mutex); + + irq_domain_free_irq_data(virq, nr_irqs); + irq_free_descs(virq, nr_irqs); +} + +/** + * irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain + * @irq_base: Base IRQ number + * @nr_irqs: Number of IRQs to allocate + * @arg: Allocation data (arch/domain specific) + * + * Check whether the domain has been setup recursive. If not allocate + * through the parent domain. + */ +int irq_domain_alloc_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, unsigned int nr_irqs, + void *arg) +{ + /* irq_domain_alloc_irqs_recursive() has called parent's alloc() */ + if (irq_domain_is_auto_recursive(domain)) + return 0; + + domain = domain->parent; + if (domain) + return irq_domain_alloc_irqs_recursive(domain, irq_base, + nr_irqs, arg); + return -ENOSYS; +} + +/** + * irq_domain_free_irqs_parent - Free interrupts from parent domain + * @irq_base: Base IRQ number + * @nr_irqs: Number of IRQs to free + * + * Check whether the domain has been setup recursive. If not free + * through the parent domain. + */ +void irq_domain_free_irqs_parent(struct irq_domain *domain, + unsigned int irq_base, unsigned int nr_irqs) +{ + /* irq_domain_free_irqs_recursive() will call parent's free */ + if (!irq_domain_is_auto_recursive(domain) && domain->parent) + irq_domain_free_irqs_recursive(domain->parent, irq_base, + nr_irqs); +} + +/** + * irq_domain_activate_irq - Call domain_ops->activate recursively to activate + * interrupt + * @irq_data: outermost irq_data associated with interrupt + * + * This is the second step to call domain_ops->activate to program interrupt + * controllers, so the interrupt could actually get delivered. + */ +void irq_domain_activate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (irq_data->parent_data) + irq_domain_activate_irq(irq_data->parent_data); + if (domain->ops->activate) + domain->ops->activate(domain, irq_data); + } +} + +/** + * irq_domain_deactivate_irq - Call domain_ops->deactivate recursively to + * deactivate interrupt + * @irq_data: outermost irq_data associated with interrupt + * + * It calls domain_ops->deactivate to program interrupt controllers to disable + * interrupt delivery. + */ +void irq_domain_deactivate_irq(struct irq_data *irq_data) +{ + if (irq_data && irq_data->domain) { + struct irq_domain *domain = irq_data->domain; + + if (domain->ops->deactivate) + domain->ops->deactivate(domain, irq_data); + if (irq_data->parent_data) + irq_domain_deactivate_irq(irq_data->parent_data); + } +} + +static void irq_domain_check_hierarchy(struct irq_domain *domain) +{ + /* Hierarchy irq_domains must implement callback alloc() */ + if (domain->ops->alloc) + domain->flags |= IRQ_DOMAIN_FLAG_HIERARCHY; +} +#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ +/** + * irq_domain_get_irq_data - Get irq_data associated with @virq and @domain + * @domain: domain to match + * @virq: IRQ number to get irq_data + */ +struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, + unsigned int virq) +{ + struct irq_data *irq_data = irq_get_irq_data(virq); + + return (irq_data && irq_data->domain == domain) ? irq_data : NULL; +} + +static void irq_domain_check_hierarchy(struct irq_domain *domain) +{ +} +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0a9104b4608b..80692373abd6 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -183,6 +183,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, ret = chip->irq_set_affinity(data, mask, force); switch (ret) { case IRQ_SET_MASK_OK: + case IRQ_SET_MASK_OK_DONE: cpumask_copy(data->affinity, mask); case IRQ_SET_MASK_OK_NOCOPY: irq_set_thread_affinity(desc); @@ -600,6 +601,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, switch (ret) { case IRQ_SET_MASK_OK: + case IRQ_SET_MASK_OK_DONE: irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK); irqd_set(&desc->irq_data, flags); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c new file mode 100644 index 000000000000..3e18163f336f --- /dev/null +++ b/kernel/irq/msi.c @@ -0,0 +1,330 @@ +/* + * linux/kernel/irq/msi.c + * + * Copyright (C) 2014 Intel Corp. + * Author: Jiang Liu <jiang.liu@linux.intel.com> + * + * This file is licensed under GPLv2. + * + * This file contains common code to support Message Signalled Interrupt for + * PCI compatible and non PCI compatible devices. + */ +#include <linux/types.h> +#include <linux/device.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/msi.h> + +/* Temparory solution for building, will be removed later */ +#include <linux/pci.h> + +void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) +{ + *msg = entry->msg; +} + +void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) +{ + struct msi_desc *entry = irq_get_msi_desc(irq); + + __get_cached_msi_msg(entry, msg); +} +EXPORT_SYMBOL_GPL(get_cached_msi_msg); + +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN +static inline void irq_chip_write_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + data->chip->irq_write_msi_msg(data, msg); +} + +/** + * msi_domain_set_affinity - Generic affinity setter function for MSI domains + * @irq_data: The irq data associated to the interrupt + * @mask: The affinity mask to set + * @force: Flag to enforce setting (disable online checks) + * + * Intended to be used by MSI interrupt controllers which are + * implemented with hierarchical domains. + */ +int msi_domain_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + struct irq_data *parent = irq_data->parent_data; + struct msi_msg msg; + int ret; + + ret = parent->chip->irq_set_affinity(parent, mask, force); + if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) { + BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg)); + irq_chip_write_msi_msg(irq_data, &msg); + } + + return ret; +} + +static void msi_domain_activate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct msi_msg msg; + + BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg)); + irq_chip_write_msi_msg(irq_data, &msg); +} + +static void msi_domain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data) +{ + struct msi_msg msg; + + memset(&msg, 0, sizeof(msg)); + irq_chip_write_msi_msg(irq_data, &msg); +} + +static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg) +{ + struct msi_domain_info *info = domain->host_data; + struct msi_domain_ops *ops = info->ops; + irq_hw_number_t hwirq = ops->get_hwirq(info, arg); + int i, ret; + + if (irq_find_mapping(domain, hwirq) > 0) + return -EEXIST; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg); + if (ret < 0) + return ret; + + for (i = 0; i < nr_irqs; i++) { + ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg); + if (ret < 0) { + if (ops->msi_free) { + for (i--; i > 0; i--) + ops->msi_free(domain, info, virq + i); + } + irq_domain_free_irqs_top(domain, virq, nr_irqs); + return ret; + } + } + + return 0; +} + +static void msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct msi_domain_info *info = domain->host_data; + int i; + + if (info->ops->msi_free) { + for (i = 0; i < nr_irqs; i++) + info->ops->msi_free(domain, info, virq + i); + } + irq_domain_free_irqs_top(domain, virq, nr_irqs); +} + +static struct irq_domain_ops msi_domain_ops = { + .alloc = msi_domain_alloc, + .free = msi_domain_free, + .activate = msi_domain_activate, + .deactivate = msi_domain_deactivate, +}; + +#ifdef GENERIC_MSI_DOMAIN_OPS +static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return arg->hwirq; +} + +static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) +{ + memset(arg, 0, sizeof(*arg)); + return 0; +} + +static void msi_domain_ops_set_desc(msi_alloc_info_t *arg, + struct msi_desc *desc) +{ + arg->desc = desc; +} +#else +#define msi_domain_ops_get_hwirq NULL +#define msi_domain_ops_prepare NULL +#define msi_domain_ops_set_desc NULL +#endif /* !GENERIC_MSI_DOMAIN_OPS */ + +static int msi_domain_ops_init(struct irq_domain *domain, + struct msi_domain_info *info, + unsigned int virq, irq_hw_number_t hwirq, + msi_alloc_info_t *arg) +{ + irq_domain_set_hwirq_and_chip(domain, virq, hwirq, info->chip, + info->chip_data); + if (info->handler && info->handler_name) { + __irq_set_handler(virq, info->handler, 0, info->handler_name); + if (info->handler_data) + irq_set_handler_data(virq, info->handler_data); + } + return 0; +} + +static int msi_domain_ops_check(struct irq_domain *domain, + struct msi_domain_info *info, + struct device *dev) +{ + return 0; +} + +static struct msi_domain_ops msi_domain_ops_default = { + .get_hwirq = msi_domain_ops_get_hwirq, + .msi_init = msi_domain_ops_init, + .msi_check = msi_domain_ops_check, + .msi_prepare = msi_domain_ops_prepare, + .set_desc = msi_domain_ops_set_desc, +}; + +static void msi_domain_update_dom_ops(struct msi_domain_info *info) +{ + struct msi_domain_ops *ops = info->ops; + + if (ops == NULL) { + info->ops = &msi_domain_ops_default; + return; + } + + if (ops->get_hwirq == NULL) + ops->get_hwirq = msi_domain_ops_default.get_hwirq; + if (ops->msi_init == NULL) + ops->msi_init = msi_domain_ops_default.msi_init; + if (ops->msi_check == NULL) + ops->msi_check = msi_domain_ops_default.msi_check; + if (ops->msi_prepare == NULL) + ops->msi_prepare = msi_domain_ops_default.msi_prepare; + if (ops->set_desc == NULL) + ops->set_desc = msi_domain_ops_default.set_desc; +} + +static void msi_domain_update_chip_ops(struct msi_domain_info *info) +{ + struct irq_chip *chip = info->chip; + + BUG_ON(!chip); + if (!chip->irq_mask) + chip->irq_mask = pci_msi_mask_irq; + if (!chip->irq_unmask) + chip->irq_unmask = pci_msi_unmask_irq; + if (!chip->irq_set_affinity) + chip->irq_set_affinity = msi_domain_set_affinity; +} + +/** + * msi_create_irq_domain - Create a MSI interrupt domain + * @of_node: Optional device-tree node of the interrupt controller + * @info: MSI domain info + * @parent: Parent irq domain + */ +struct irq_domain *msi_create_irq_domain(struct device_node *node, + struct msi_domain_info *info, + struct irq_domain *parent) +{ + if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS) + msi_domain_update_dom_ops(info); + if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) + msi_domain_update_chip_ops(info); + + return irq_domain_add_hierarchy(parent, 0, 0, node, &msi_domain_ops, + info); +} + +/** + * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain + * @domain: The domain to allocate from + * @dev: Pointer to device struct of the device for which the interrupts + * are allocated + * @nvec: The number of interrupts to allocate + * + * Returns 0 on success or an error code. + */ +int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, + int nvec) +{ + struct msi_domain_info *info = domain->host_data; + struct msi_domain_ops *ops = info->ops; + msi_alloc_info_t arg; + struct msi_desc *desc; + int i, ret, virq = -1; + + ret = ops->msi_check(domain, info, dev); + if (ret == 0) + ret = ops->msi_prepare(domain, dev, nvec, &arg); + if (ret) + return ret; + + for_each_msi_entry(desc, dev) { + ops->set_desc(&arg, desc); + if (info->flags & MSI_FLAG_IDENTITY_MAP) + virq = (int)ops->get_hwirq(info, &arg); + else + virq = -1; + + virq = __irq_domain_alloc_irqs(domain, virq, desc->nvec_used, + dev_to_node(dev), &arg, false); + if (virq < 0) { + ret = -ENOSPC; + if (ops->handle_error) + ret = ops->handle_error(domain, desc, ret); + if (ops->msi_finish) + ops->msi_finish(&arg, ret); + return ret; + } + + for (i = 0; i < desc->nvec_used; i++) + irq_set_msi_desc_off(virq, i, desc); + } + + if (ops->msi_finish) + ops->msi_finish(&arg, 0); + + for_each_msi_entry(desc, dev) { + if (desc->nvec_used == 1) + dev_dbg(dev, "irq %d for MSI\n", virq); + else + dev_dbg(dev, "irq [%d-%d] for MSI\n", + virq, virq + desc->nvec_used - 1); + } + + return 0; +} + +/** + * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated tp @dev + * @domain: The domain to managing the interrupts + * @dev: Pointer to device struct of the device for which the interrupts + * are free + */ +void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +{ + struct msi_desc *desc; + + for_each_msi_entry(desc, dev) { + irq_domain_free_irqs(desc->irq, desc->nvec_used); + desc->irq = 0; + } +} + +/** + * msi_get_domain_info - Get the MSI interrupt domain info for @domain + * @domain: The interrupt domain to retrieve data from + * + * Returns the pointer to the msi_domain_info stored in + * @domain->host_data. + */ +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 */ |