Merge branch 'irq-irqdomain-for-linus' of git://git.kernel.org/pub/sc…

…m/linux/kernel/git/tip/tip

Pull irq domain updates from Thomas Gleixner:
 "The real interesting irq updates:

   - Support for hierarchical irq domains:

     For complex interrupt routing scenarios where more than one
     interrupt related chip is involved we had no proper representation
     in the generic interrupt infrastructure so far.  That made people
     implement rather ugly constructs in their nested irq chip
     implementations.  The main offenders are x86 and arm/gic.

     To distangle that mess we have now hierarchical irqdomains which
     seperate the various interrupt chips and connect them via the
     hierarchical domains.  That keeps the domain specific details
     internal to the particular hierarchy level and removes the
     criss/cross referencing of chip internals.  The resulting hierarchy
     for a complex x86 system will look like this:

        vector          mapped: 74
          msi-0         mapped: 2
          dmar-ir-1     mapped: 69
            ioapic-1    mapped: 4
            ioapic-0    mapped: 20
            pci-msi-2   mapped: 45
          dmar-ir-0     mapped: 3
            ioapic-2    mapped: 1
            pci-msi-1   mapped: 2
          htirq         mapped: 0

     Neither ioapic nor pci-msi know about the dmar interrupt remapping
     between themself and the vector domain.  If interrupt remapping is
     disabled ioapic and pci-msi become direct childs of the vector
     domain.

     In hindsight we should have done that years ago, but in hindsight
     we always know better :)

   - Support for generic MSI interrupt domain handling

     We have more and more non PCI related MSI interrupts, so providing
     a generic infrastructure for this is better than having all
     affected architectures implementing their own private hacks.

   - Support for PCI-MSI interrupt domain handling, based on the generic
     MSI support.

     This part carries the pci/msi branch from Bjorn Helgaas pci tree to
     avoid a massive conflict.  The PCI/MSI parts are acked by Bjorn.

  I have two more branches on top of this.  The full conversion of x86
  to hierarchical domains and a partial conversion of arm/gic"

* 'irq-irqdomain-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  genirq: Move irq_chip_write_msi_msg() helper to core
  PCI/MSI: Allow an msi_controller to be associated to an irq domain
  PCI/MSI: Provide mechanism to alloc/free MSI/MSIX interrupt from irqdomain
  PCI/MSI: Enhance core to support hierarchy irqdomain
  PCI/MSI: Move cached entry functions to irq core
  genirq: Provide default callbacks for msi_domain_ops
  genirq: Introduce msi_domain_alloc/free_irqs()
  asm-generic: Add msi.h
  genirq: Add generic msi irq domain support
  genirq: Introduce callback irq_chip.irq_write_msi_msg
  genirq: Work around __irq_set_handler vs stacked domains ordering issues
  irqdomain: Introduce helper function irq_domain_add_hierarchy()
  irqdomain: Implement a method to automatically call parent domains alloc/free
  genirq: Introduce helper irq_domain_set_info() to reduce duplicated code
  genirq: Split out flow handler typedefs into seperate header file
  genirq: Add IRQ_SET_MASK_OK_DONE to support stacked irqchip
  genirq: Introduce irq_chip.irq_compose_msi_msg() to support stacked irqchip
  genirq: Add more helper functions to support stacked irq_chip
  genirq: Introduce helper functions to support stacked irq_chip
  irqdomain: Do irq_find_mapping and set_type for hierarchy irqdomain in case OF
  ...

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.

arch/arm/include/asm/mach/pci.h

@@ -21,6 +21,9 @@ struct device;
 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;
@@ -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);
 };
 
 /*
@@ -46,6 +47,9 @@ struct hw_pci {
 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			*/
@@ -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	*/
 };
 

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.
@@ -470,13 +465,14 @@ 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)

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;

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,

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,

arch/mips/pci/msi-octeon.c

@@ -178,7 +178,7 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 	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;
 }
 

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;
 }
 

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

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",
 };
 

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;
 }

arch/powerpc/platforms/pseries/msi.c

@@ -476,7 +476,7 @@ static int rtas_setup_msi_irqs(struct pci_dev *pdev, int nvec_in, int type)
 		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;
 	}
 

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;
 

arch/powerpc/sysdev/mpic_pasemi_msi.c

@@ -42,15 +42,15 @@ 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);
 }
 
 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;