This patch adds the new irq remapper core. It breaks build of all powerpc platforms as there are some fundamental conflicts with the old code, like the value of NO_IRQ which I'm now setting to 0 (as per discussions with Linus), etc... so the old remapping code is removed at the same time. Subsequent patches will bring back PICs and architectures to building/working state on top of this new core. Signed-off-by: Benjamin Herrenschmidt Index: linux-irq-work/include/asm-powerpc/irq.h =================================================================== --- linux-irq-work.orig/include/asm-powerpc/irq.h 2006-07-01 15:25:26.000000000 +1000 +++ linux-irq-work/include/asm-powerpc/irq.h 2006-07-01 15:25:45.000000000 +1000 @@ -9,26 +9,14 @@ * 2 of the License, or (at your option) any later version. */ +#include #include +#include +#include #include #include -/* this number is used when no interrupt has been assigned */ -#define NO_IRQ (-1) - -/* - * These constants are used for passing information about interrupt - * signal polarity and level/edge sensing to the low-level PIC chip - * drivers. - */ -#define IRQ_SENSE_MASK 0x1 -#define IRQ_SENSE_LEVEL 0x1 /* interrupt on active level */ -#define IRQ_SENSE_EDGE 0x0 /* interrupt triggered by edge */ - -#define IRQ_POLARITY_MASK 0x2 -#define IRQ_POLARITY_POSITIVE 0x2 /* high level or low->high edge */ -#define IRQ_POLARITY_NEGATIVE 0x0 /* low level or high->low edge */ #define get_irq_desc(irq) (&irq_desc[(irq)]) @@ -36,50 +24,324 @@ #define for_each_irq(i) \ for ((i) = 0; (i) < NR_IRQS; ++(i)) -#ifdef CONFIG_PPC64 +extern atomic_t ppc_n_lost_interrupts; -/* - * Maximum number of interrupt sources that we can handle. +#ifdef CONFIG_PPC_MERGE + +/* This number is used when no interrupt has been assigned */ +#define NO_IRQ (0) + +/* This is a special irq number to return from get_irq() to tell that + * no interrupt happened _and_ ignore it (don't count it as bad). Some + * platforms like iSeries rely on that. */ +#define NO_IRQ_IGNORE ((unsigned int)-1) + +/* Total number of virq in the platform (make it a CONFIG_* option ? */ #define NR_IRQS 512 -/* Interrupt numbers are virtual in case they are sparsely - * distributed by the hardware. +/* Number of irqs reserved for the legacy controller */ +#define NUM_ISA_INTERRUPTS 16 + +/* This type is the placeholder for a hardware interrupt number. It has to + * be big enough to enclose whatever representation is used by a given + * platform. + */ +typedef unsigned long irq_hw_number_t; + +/* Interrupt controller "host" data structure. This could be defined as a + * irq domain controller. That is, it handles the mapping between hardware + * and virtual interrupt numbers for a given interrupt domain. The host + * structure is generally created by the PIC code for a given PIC instance + * (though a host can cover more than one PIC if they have a flat number + * model). It's the host callbacks that are responsible for setting the + * irq_chip on a given irq_desc after it's been mapped. + * + * The host code and data structures are fairly agnostic to the fact that + * we use an open firmware device-tree. We do have references to struct + * device_node in two places: in irq_find_host() to find the host matching + * a given interrupt controller node, and of course as an argument to its + * counterpart host->ops->match() callback. However, those are treated as + * generic pointers by the core and the fact that it's actually a device-node + * pointer is purely a convention between callers and implementation. This + * code could thus be used on other architectures by replacing those two + * by some sort of arch-specific void * "token" used to identify interrupt + * controllers. + */ +struct irq_host; +struct radix_tree_root; + +/* Functions below are provided by the host and called whenever a new mapping + * is created or an old mapping is disposed. The host can then proceed to + * whatever internal data structures management is required. It also needs + * to setup the irq_desc when returning from map(). + */ +struct irq_host_ops { + /* Match an interrupt controller device node to a host, returns + * 1 on a match + */ + int (*match)(struct irq_host *h, struct device_node *node); + + /* Create or update a mapping between a virtual irq number and a hw + * irq number. This can be called several times for the same mapping + * but with different flags, though unmap shall always be called + * before the virq->hw mapping is changed. + */ + int (*map)(struct irq_host *h, unsigned int virq, + irq_hw_number_t hw, unsigned int flags); + + /* Dispose of such a mapping */ + void (*unmap)(struct irq_host *h, unsigned int virq); + + /* Translate device-tree interrupt specifier from raw format coming + * from the firmware to a irq_hw_number_t (interrupt line number) and + * trigger flags that can be passed to irq_create_mapping(). + * If no translation is provided, raw format is assumed to be one cell + * for interrupt line and default sense. + */ + int (*xlate)(struct irq_host *h, struct device_node *ctrler, + u32 *intspec, unsigned int intsize, + irq_hw_number_t *out_hwirq, unsigned int *out_flags); +}; + +struct irq_host { + struct list_head link; + + /* type of reverse mapping technique */ + unsigned int revmap_type; +#define IRQ_HOST_MAP_LEGACY 0 /* legacy 8259, gets irqs 1..15 */ +#define IRQ_HOST_MAP_NOMAP 1 /* no fast reverse mapping */ +#define IRQ_HOST_MAP_LINEAR 2 /* linear map of interrupts */ +#define IRQ_HOST_MAP_TREE 3 /* radix tree */ + union { + struct { + unsigned int size; + unsigned int *revmap; + } linear; + struct radix_tree_root tree; + } revmap_data; + struct irq_host_ops *ops; + void *host_data; + irq_hw_number_t inval_irq; +}; + +/* The main irq map itself is an array of NR_IRQ entries containing the + * associate host and irq number. An entry with a host of NULL is free. + * An entry can be allocated if it's free, the allocator always then sets + * hwirq first to the host's invalid irq number and then fills ops. + */ +struct irq_map_entry { + irq_hw_number_t hwirq; + struct irq_host *host; +}; + +extern struct irq_map_entry irq_map[NR_IRQS]; + + +/*** + * irq_alloc_host - Allocate a new irq_host data structure + * @node: device-tree node of the interrupt controller + * @revmap_type: type of reverse mapping to use + * @revmap_arg: for IRQ_HOST_MAP_LINEAR linear only: size of the map + * @ops: map/unmap host callbacks + * @inval_irq: provide a hw number in that host space that is always invalid + * + * Allocates and initialize and irq_host structure. Note that in the case of + * IRQ_HOST_MAP_LEGACY, the map() callback will be called before this returns + * for all legacy interrupts except 0 (which is always the invalid irq for + * a legacy controller). For a IRQ_HOST_MAP_LINEAR, the map is allocated by + * this call as well. For a IRQ_HOST_MAP_TREE, the radix tree will be allocated + * later during boot automatically (the reverse mapping will use the slow path + * until that happens). + */ +extern struct irq_host *irq_alloc_host(unsigned int revmap_type, + unsigned int revmap_arg, + struct irq_host_ops *ops, + irq_hw_number_t inval_irq); + + +/*** + * irq_find_host - Locates a host for a given device node + * @node: device-tree node of the interrupt controller + */ +extern struct irq_host *irq_find_host(struct device_node *node); + + +/*** + * irq_set_default_host - Set a "default" host + * @host: default host pointer + * + * For convenience, it's possible to set a "default" host that will be used + * whenever NULL is passed to irq_create_mapping(). It makes life easier for + * platforms that want to manipulate a few hard coded interrupt numbers that + * aren't properly represented in the device-tree. + */ +extern void irq_set_default_host(struct irq_host *host); + + +/*** + * irq_set_virq_count - Set the maximum number of virt irqs + * @count: number of linux virtual irqs, capped with NR_IRQS + * + * This is mainly for use by platforms like iSeries who want to program + * the virtual irq number in the controller to avoid the reverse mapping + */ +extern void irq_set_virq_count(unsigned int count); + + +/*** + * irq_create_mapping - Map a hardware interrupt into linux virq space + * @host: host owning this hardware interrupt or NULL for default host + * @hwirq: hardware irq number in that host space + * @flags: flags passed to the controller. contains the trigger type among + * others. Use IRQ_TYPE_* defined in include/linux/irq.h + * + * Only one mapping per hardware interrupt is permitted. Returns a linux + * virq number. The flags can be used to provide sense information to the + * controller (typically extracted from the device-tree). If no information + * is passed, the controller defaults will apply (for example, xics can only + * do edge so flags are irrelevant for some pseries specific irqs). + * + * The device-tree generally contains the trigger info in an encoding that is + * specific to a given type of controller. In that case, you can directly use + * host->ops->trigger_xlate() to translate that. + * + * It is recommended that new PICs that don't have existing OF bindings chose + * to use a representation of triggers identical to linux. + */ +extern unsigned int irq_create_mapping(struct irq_host *host, + irq_hw_number_t hwirq, + unsigned int flags); + + +/*** + * irq_dispose_mapping - Unmap an interrupt + * @virq: linux virq number of the interrupt to unmap + */ +extern void irq_dispose_mapping(unsigned int virq); + +/*** + * irq_find_mapping - Find a linux virq from an hw irq number. + * @host: host owning this hardware interrupt + * @hwirq: hardware irq number in that host space + * + * This is a slow path, for use by generic code. It's expected that an + * irq controller implementation directly calls the appropriate low level + * mapping function. + */ +extern unsigned int irq_find_mapping(struct irq_host *host, + irq_hw_number_t hwirq); + + +/*** + * irq_radix_revmap - Find a linux virq from a hw irq number. + * @host: host owning this hardware interrupt + * @hwirq: hardware irq number in that host space + * + * This is a fast path, for use by irq controller code that uses radix tree + * revmaps */ -extern unsigned int virt_irq_to_real_map[NR_IRQS]; +extern unsigned int irq_radix_revmap(struct irq_host *host, + irq_hw_number_t hwirq); -/* The maximum virtual IRQ number that we support. This - * can be set by the platform and will be reduced by the - * value of __irq_offset_value. It defaults to and is - * capped by (NR_IRQS - 1). +/*** + * irq_linear_revmap - Find a linux virq from a hw irq number. + * @host: host owning this hardware interrupt + * @hwirq: hardware irq number in that host space + * + * This is a fast path, for use by irq controller code that uses linear + * revmaps. It does fallback to the slow path if the revmap doesn't exist + * yet and will create the revmap entry with appropriate locking */ -extern unsigned int virt_irq_max; -/* Create a mapping for a real_irq if it doesn't already exist. - * Return the virtual irq as a convenience. +extern unsigned int irq_linear_revmap(struct irq_host *host, + irq_hw_number_t hwirq); + + + +/*** + * irq_alloc_virt - Allocate virtual irq numbers + * @host: host owning these new virtual irqs + * @count: number of consecutive numbers to allocate + * @hint: pass a hint number, the allocator will try to use a 1:1 mapping + * + * This is a low level function that is used internally by irq_create_mapping() + * and that can be used by some irq controllers implementations for things + * like allocating ranges of numbers for MSIs. The revmaps are left untouched. + */ +extern unsigned int irq_alloc_virt(struct irq_host *host, + unsigned int count, + unsigned int hint); + +/*** + * irq_free_virt - Free virtual irq numbers + * @virq: virtual irq number of the first interrupt to free + * @count: number of interrupts to free + * + * This function is the opposite of irq_alloc_virt. It will not clear reverse + * maps, this should be done previously by unmap'ing the interrupt. In fact, + * all interrupts covered by the range being freed should have been unmapped + * prior to calling this. */ -int virt_irq_create_mapping(unsigned int real_irq); -void virt_irq_init(void); +extern void irq_free_virt(unsigned int virq, unsigned int count); + + +/* -- OF helpers -- */ -static inline unsigned int virt_irq_to_real(unsigned int virt_irq) +/* irq_create_of_mapping - Map a hardware interrupt into linux virq space + * @controller: Device node of the interrupt controller + * @inspec: Interrupt specifier from the device-tree + * @intsize: Size of the interrupt specifier from the device-tree + * + * This function is identical to irq_create_mapping except that it takes + * as input informations straight from the device-tree (typically the results + * of the of_irq_map_*() functions + */ +extern unsigned int irq_create_of_mapping(struct device_node *controller, + u32 *intspec, unsigned int intsize); + + +/* irq_of_parse_and_map - Parse nad Map an interrupt into linux virq space + * @device: Device node of the device whose interrupt is to be mapped + * @index: Index of the interrupt to map + * + * This function is a wrapper that chains of_irq_map_one() and + * irq_create_of_mapping() to make things easier to callers + */ +extern unsigned int irq_of_parse_and_map(struct device_node *dev, int index); + +/* -- End OF helpers -- */ + +/*** + * irq_early_init - Init irq remapping subsystem + */ +extern void irq_early_init(void); + +static __inline__ int irq_canonicalize(int irq) { - return virt_irq_to_real_map[virt_irq]; + return irq; } -extern unsigned int real_irq_to_virt_slowpath(unsigned int real_irq); + +#else /* CONFIG_PPC_MERGE */ + +/* This number is used when no interrupt has been assigned */ +#define NO_IRQ (-1) + /* - * List of interrupt controllers. + * These constants are used for passing information about interrupt + * signal polarity and level/edge sensing to the low-level PIC chip + * drivers. */ -#define IC_INVALID 0 -#define IC_OPEN_PIC 1 -#define IC_PPC_XIC 2 -#define IC_CELL_PIC 3 -#define IC_ISERIES 4 +#define IRQ_SENSE_MASK 0x1 +#define IRQ_SENSE_LEVEL 0x1 /* interrupt on active level */ +#define IRQ_SENSE_EDGE 0x0 /* interrupt triggered by edge */ -extern u64 ppc64_interrupt_controller; +#define IRQ_POLARITY_MASK 0x2 +#define IRQ_POLARITY_POSITIVE 0x2 /* high level or low->high edge */ +#define IRQ_POLARITY_NEGATIVE 0x0 /* low level or high->low edge */ -#else /* 32-bit */ #if defined(CONFIG_40x) #include @@ -512,19 +774,11 @@ #endif /* CONFIG_8260 */ -#endif +#endif /* Whatever way too big #ifdef */ -#ifndef CONFIG_PPC_MERGE #define NR_MASK_WORDS ((NR_IRQS + 31) / 32) /* pedantic: these are long because they are used with set_bit --RR */ extern unsigned long ppc_cached_irq_mask[NR_MASK_WORDS]; -#endif - -extern atomic_t ppc_n_lost_interrupts; - -#define virt_irq_create_mapping(x) (x) - -#endif /* * Because many systems have two overlapping names spaces for @@ -563,6 +817,7 @@ irq = 9; return irq; } +#endif /* CONFIG_PPC_MERGE */ extern int distribute_irqs; Index: linux-irq-work/arch/powerpc/kernel/irq.c =================================================================== --- linux-irq-work.orig/arch/powerpc/kernel/irq.c 2006-07-01 15:25:26.000000000 +1000 +++ linux-irq-work/arch/powerpc/kernel/irq.c 2006-07-01 15:25:45.000000000 +1000 @@ -29,6 +29,8 @@ * to reduce code space and undefined function references. */ +#undef DEBUG + #include #include #include @@ -46,7 +48,10 @@ #include #include #include -#include +#include +#include +#include +#include #include #include @@ -57,6 +62,7 @@ #include #include #include +#include #ifdef CONFIG_PPC_ISERIES #include #endif @@ -88,7 +94,6 @@ EXPORT_SYMBOL(irq_desc); int distribute_irqs = 1; -u64 ppc64_interrupt_controller; #endif /* CONFIG_PPC64 */ int show_interrupts(struct seq_file *p, void *v) @@ -181,7 +186,7 @@ void do_IRQ(struct pt_regs *regs) { - int irq; + unsigned int irq; #ifdef CONFIG_IRQSTACKS struct thread_info *curtp, *irqtp; #endif @@ -212,7 +217,7 @@ */ irq = ppc_md.get_irq(regs); - if (irq >= 0) { + if (irq != NO_IRQ && irq != NO_IRQ_IGNORE) { #ifdef CONFIG_IRQSTACKS /* Switch to the irq stack to handle this */ curtp = current_thread_info(); @@ -231,7 +236,7 @@ } else #endif generic_handle_irq(irq, regs); - } else if (irq != -2) + } else if (irq != NO_IRQ_IGNORE) /* That's not SMP safe ... but who cares ? */ ppc_spurious_interrupts++; @@ -248,14 +253,15 @@ void __init init_IRQ(void) { + /* XXX Why that ? Who is calling us early ? Check and remove ! */ #ifdef CONFIG_PPC64 static int once = 0; - if (once) + if (once) { + WARN_ON(1); return; - + } once++; - #endif ppc_md.init_IRQ(); #ifdef CONFIG_PPC64 @@ -263,123 +269,6 @@ #endif } -#ifdef CONFIG_PPC64 -/* - * Virtual IRQ mapping code, used on systems with XICS interrupt controllers. - */ - -#define UNDEFINED_IRQ 0xffffffff -unsigned int virt_irq_to_real_map[NR_IRQS]; - -/* - * Don't use virtual irqs 0, 1, 2 for devices. - * The pcnet32 driver considers interrupt numbers < 2 to be invalid, - * and 2 is the XICS IPI interrupt. - * We limit virtual irqs to __irq_offet_value less than virt_irq_max so - * that when we offset them we don't end up with an interrupt - * number >= virt_irq_max. - */ -#define MIN_VIRT_IRQ 3 - -unsigned int virt_irq_max; -static unsigned int max_virt_irq; -static unsigned int nr_virt_irqs; - -void -virt_irq_init(void) -{ - int i; - - if ((virt_irq_max == 0) || (virt_irq_max > (NR_IRQS - 1))) - virt_irq_max = NR_IRQS - 1; - max_virt_irq = virt_irq_max - __irq_offset_value; - nr_virt_irqs = max_virt_irq - MIN_VIRT_IRQ + 1; - - for (i = 0; i < NR_IRQS; i++) - virt_irq_to_real_map[i] = UNDEFINED_IRQ; -} - -/* Create a mapping for a real_irq if it doesn't already exist. - * Return the virtual irq as a convenience. - */ -int virt_irq_create_mapping(unsigned int real_irq) -{ - unsigned int virq, first_virq; - static int warned; - - if (ppc64_interrupt_controller == IC_OPEN_PIC) - return real_irq; /* no mapping for openpic (for now) */ - - if (ppc64_interrupt_controller == IC_CELL_PIC) - return real_irq; /* no mapping for iic either */ - - /* don't map interrupts < MIN_VIRT_IRQ */ - if (real_irq < MIN_VIRT_IRQ) { - virt_irq_to_real_map[real_irq] = real_irq; - return real_irq; - } - - /* map to a number between MIN_VIRT_IRQ and max_virt_irq */ - virq = real_irq; - if (virq > max_virt_irq) - virq = (virq % nr_virt_irqs) + MIN_VIRT_IRQ; - - /* search for this number or a free slot */ - first_virq = virq; - while (virt_irq_to_real_map[virq] != UNDEFINED_IRQ) { - if (virt_irq_to_real_map[virq] == real_irq) - return virq; - if (++virq > max_virt_irq) - virq = MIN_VIRT_IRQ; - if (virq == first_virq) - goto nospace; /* oops, no free slots */ - } - - virt_irq_to_real_map[virq] = real_irq; - return virq; - - nospace: - if (!warned) { - printk(KERN_CRIT "Interrupt table is full\n"); - printk(KERN_CRIT "Increase virt_irq_max (currently %d) " - "in your kernel sources and rebuild.\n", virt_irq_max); - warned = 1; - } - return NO_IRQ; -} - -/* - * In most cases will get a hit on the very first slot checked in the - * virt_irq_to_real_map. Only when there are a large number of - * IRQs will this be expensive. - */ -unsigned int real_irq_to_virt_slowpath(unsigned int real_irq) -{ - unsigned int virq; - unsigned int first_virq; - - virq = real_irq; - - if (virq > max_virt_irq) - virq = (virq % nr_virt_irqs) + MIN_VIRT_IRQ; - - first_virq = virq; - - do { - if (virt_irq_to_real_map[virq] == real_irq) - return virq; - - virq++; - - if (virq >= max_virt_irq) - virq = 0; - - } while (first_virq != virq); - - return NO_IRQ; - -} -#endif /* CONFIG_PPC64 */ #ifdef CONFIG_IRQSTACKS struct thread_info *softirq_ctx[NR_CPUS] __read_mostly; @@ -439,6 +328,499 @@ } EXPORT_SYMBOL(do_softirq); + +/* + * IRQ controller and virtual interrupts + */ + + +static LIST_HEAD(irq_hosts); +static spinlock_t irq_big_lock = SPIN_LOCK_UNLOCKED; + +struct irq_map_entry irq_map[NR_IRQS]; +static unsigned int irq_virq_count = NR_IRQS; +static struct irq_host *irq_default_host; + +struct irq_host *irq_alloc_host(unsigned int revmap_type, + unsigned int revmap_arg, + struct irq_host_ops *ops, + irq_hw_number_t inval_irq) +{ + struct irq_host *host; + unsigned int size = sizeof(struct irq_host); + unsigned int i; + unsigned int *rmap; + unsigned long flags; + + /* Allocate structure and revmap table if using linear mapping */ + if (revmap_type == IRQ_HOST_MAP_LINEAR) + size += revmap_arg * sizeof(unsigned int); + if (mem_init_done) + host = kzalloc(size, GFP_KERNEL); + else { + host = alloc_bootmem(size); + if (host) + memset(host, 0, size); + } + if (host == NULL) + return NULL; + + /* Fill structure */ + host->revmap_type = revmap_type; + host->inval_irq = inval_irq; + host->ops = ops; + + spin_lock_irqsave(&irq_big_lock, flags); + + /* If it's a legacy controller, check for duplicates and + * mark it as allocated (we use irq 0 host pointer for that + */ + if (revmap_type == IRQ_HOST_MAP_LEGACY) { + if (irq_map[0].host != NULL) { + spin_unlock_irqrestore(&irq_big_lock, flags); + /* If we are early boot, we can't free the structure, + * too bad... + * this will be fixed once slab is made available early + * instead of the current cruft + */ + if (mem_init_done) + kfree(host); + return NULL; + } + irq_map[0].host = host; + } + + list_add(&host->link, &irq_hosts); + spin_unlock_irqrestore(&irq_big_lock, flags); + + /* Additional setups per revmap type */ + switch(revmap_type) { + case IRQ_HOST_MAP_LEGACY: + /* 0 is always the invalid number for legacy */ + host->inval_irq = 0; + /* setup us as the host for all legacy interrupts */ + for (i = 1; i < NUM_ISA_INTERRUPTS; i++) { + irq_map[i].hwirq = 0; + smp_wmb(); + irq_map[i].host = host; + smp_wmb(); + + /* Clear some flags */ + get_irq_desc(i)->status + &= ~(IRQ_NOREQUEST | IRQ_LEVEL); + + /* Legacy flags are left to default at this point, + * one can then use irq_create_mapping() to + * explicitely change them + */ + ops->map(host, i, i, 0); + } + break; + case IRQ_HOST_MAP_LINEAR: + rmap = (unsigned int *)(host + 1); + for (i = 0; i < revmap_arg; i++) + rmap[i] = IRQ_NONE; + host->revmap_data.linear.size = revmap_arg; + smp_wmb(); + host->revmap_data.linear.revmap = rmap; + break; + default: + break; + } + + pr_debug("irq: Allocated host of type %d @0x%p\n", revmap_type, host); + + return host; +} + +struct irq_host *irq_find_host(struct device_node *node) +{ + struct irq_host *h, *found = NULL; + unsigned long flags; + + /* We might want to match the legacy controller last since + * it might potentially be set to match all interrupts in + * the absence of a device node. This isn't a problem so far + * yet though... + */ + spin_lock_irqsave(&irq_big_lock, flags); + list_for_each_entry(h, &irq_hosts, link) + if (h->ops->match == NULL || h->ops->match(h, node)) { + found = h; + break; + } + spin_unlock_irqrestore(&irq_big_lock, flags); + return found; +} +EXPORT_SYMBOL_GPL(irq_find_host); + +void irq_set_default_host(struct irq_host *host) +{ + pr_debug("irq: Default host set to @0x%p\n", host); + + irq_default_host = host; +} + +void irq_set_virq_count(unsigned int count) +{ + pr_debug("irq: Trying to set virq count to %d\n", count); + + BUG_ON(count < NUM_ISA_INTERRUPTS); + if (count < NR_IRQS) + irq_virq_count = count; +} + +unsigned int irq_create_mapping(struct irq_host *host, + irq_hw_number_t hwirq, + unsigned int flags) +{ + unsigned int virq, hint; + + pr_debug("irq: irq_create_mapping(0x%p, 0x%lx, 0x%x)\n", + host, hwirq, flags); + + /* Look for default host if nececssary */ + if (host == NULL) + host = irq_default_host; + if (host == NULL) { + printk(KERN_WARNING "irq_create_mapping called for" + " NULL host, hwirq=%lx\n", hwirq); + WARN_ON(1); + return NO_IRQ; + } + pr_debug("irq: -> using host @%p\n", host); + + /* Check if mapping already exist, if it does, call + * host->ops->map() to update the flags + */ + virq = irq_find_mapping(host, hwirq); + if (virq != IRQ_NONE) { + pr_debug("irq: -> existing mapping on virq %d\n", virq); + host->ops->map(host, virq, hwirq, flags); + return virq; + } + + /* Get a virtual interrupt number */ + if (host->revmap_type == IRQ_HOST_MAP_LEGACY) { + /* Handle legacy */ + virq = (unsigned int)hwirq; + if (virq == 0 || virq >= NUM_ISA_INTERRUPTS) + return NO_IRQ; + return virq; + } else { + /* Allocate a virtual interrupt number */ + hint = hwirq % irq_virq_count; + virq = irq_alloc_virt(host, 1, hint); + if (virq == NO_IRQ) { + pr_debug("irq: -> virq allocation failed\n"); + return NO_IRQ; + } + } + pr_debug("irq: -> obtained virq %d\n", virq); + + /* Clear some flags */ + get_irq_desc(virq)->status &= ~(IRQ_NOREQUEST | IRQ_LEVEL); + + /* map it */ + if (host->ops->map(host, virq, hwirq, flags)) { + pr_debug("irq: -> mapping failed, freeing\n"); + irq_free_virt(virq, 1); + return NO_IRQ; + } + smp_wmb(); + irq_map[virq].hwirq = hwirq; + smp_mb(); + return virq; +} +EXPORT_SYMBOL_GPL(irq_create_mapping); + +extern unsigned int irq_create_of_mapping(struct device_node *controller, + u32 *intspec, unsigned int intsize) +{ + struct irq_host *host; + irq_hw_number_t hwirq; + unsigned int flags = IRQ_TYPE_NONE; + + if (controller == NULL) + host = irq_default_host; + else + host = irq_find_host(controller); + if (host == NULL) + return NO_IRQ; + + /* If host has no translation, then we assume interrupt line */ + if (host->ops->xlate == NULL) + hwirq = intspec[0]; + else { + if (host->ops->xlate(host, controller, intspec, intsize, + &hwirq, &flags)) + return NO_IRQ; + } + + return irq_create_mapping(host, hwirq, flags); +} +EXPORT_SYMBOL_GPL(irq_create_of_mapping); + +unsigned int irq_of_parse_and_map(struct device_node *dev, int index) +{ + struct of_irq oirq; + + if (of_irq_map_one(dev, index, &oirq)) + return NO_IRQ; + + return irq_create_of_mapping(oirq.controller, oirq.specifier, + oirq.size); +} +EXPORT_SYMBOL_GPL(irq_of_parse_and_map); + +void irq_dispose_mapping(unsigned int virq) +{ + struct irq_host *host = irq_map[virq].host; + irq_hw_number_t hwirq; + unsigned long flags; + + WARN_ON (host == NULL); + if (host == NULL) + return; + + /* Never unmap legacy interrupts */ + if (host->revmap_type == IRQ_HOST_MAP_LEGACY) + return; + + /* remove chip and handler */ + set_irq_chip_and_handler(virq, NULL, NULL); + + /* Make sure it's completed */ + synchronize_irq(virq); + + /* Tell the PIC about it */ + if (host->ops->unmap) + host->ops->unmap(host, virq); + smp_mb(); + + /* Clear reverse map */ + hwirq = irq_map[virq].hwirq; + switch(host->revmap_type) { + case IRQ_HOST_MAP_LINEAR: + if (hwirq < host->revmap_data.linear.size) + host->revmap_data.linear.revmap[hwirq] = IRQ_NONE; + break; + case IRQ_HOST_MAP_TREE: + /* Check if radix tree allocated yet */ + if (host->revmap_data.tree.gfp_mask == 0) + break; + /* XXX radix tree not safe ! remove lock whem it becomes safe + * and use some RCU sync to make sure everything is ok before we + * can re-use that map entry + */ + spin_lock_irqsave(&irq_big_lock, flags); + radix_tree_delete(&host->revmap_data.tree, hwirq); + spin_unlock_irqrestore(&irq_big_lock, flags); + break; + } + + /* Destroy map */ + smp_mb(); + irq_map[virq].hwirq = host->inval_irq; + + /* Set some flags */ + get_irq_desc(virq)->status |= IRQ_NOREQUEST; + + /* Free it */ + irq_free_virt(virq, 1); +} +EXPORT_SYMBOL_GPL(irq_dispose_mapping); + +unsigned int irq_find_mapping(struct irq_host *host, + irq_hw_number_t hwirq) +{ + unsigned int i; + unsigned int hint = hwirq % irq_virq_count; + + /* Look for default host if nececssary */ + if (host == NULL) + host = irq_default_host; + if (host == NULL) + return NO_IRQ; + + /* legacy -> bail early */ + if (host->revmap_type == IRQ_HOST_MAP_LEGACY) + return hwirq; + + /* Slow path does a linear search of the map */ + if (hint < NUM_ISA_INTERRUPTS) + hint = NUM_ISA_INTERRUPTS; + i = hint; + do { + if (irq_map[i].host == host && + irq_map[i].hwirq == hwirq) + return i; + i++; + if (i >= irq_virq_count) + i = NUM_ISA_INTERRUPTS; + } while(i != hint); + return NO_IRQ; +} +EXPORT_SYMBOL_GPL(irq_find_mapping); + + +unsigned int irq_radix_revmap(struct irq_host *host, + irq_hw_number_t hwirq) +{ + struct radix_tree_root *tree; + struct irq_map_entry *ptr; + unsigned int virq; + unsigned long flags; + + WARN_ON(host->revmap_type != IRQ_HOST_MAP_TREE); + + /* Check if the radix tree exist yet. We test the value of + * the gfp_mask for that. Sneaky but saves another int in the + * structure. If not, we fallback to slow mode + */ + tree = &host->revmap_data.tree; + if (tree->gfp_mask == 0) + return irq_find_mapping(host, hwirq); + + /* XXX Current radix trees are NOT SMP safe !!! Remove that lock + * when that is fixed (when Nick's patch gets in + */ + spin_lock_irqsave(&irq_big_lock, flags); + + /* Now try to resolve */ + ptr = radix_tree_lookup(tree, hwirq); + /* Found it, return */ + if (ptr) { + virq = ptr - irq_map; + goto bail; + } + + /* If not there, try to insert it */ + virq = irq_find_mapping(host, hwirq); + if (virq != NO_IRQ) + radix_tree_insert(tree, virq, &irq_map[virq]); + bail: + spin_unlock_irqrestore(&irq_big_lock, flags); + return virq; +} + +unsigned int irq_linear_revmap(struct irq_host *host, + irq_hw_number_t hwirq) +{ + unsigned int *revmap; + + WARN_ON(host->revmap_type != IRQ_HOST_MAP_LINEAR); + + /* Check revmap bounds */ + if (unlikely(hwirq >= host->revmap_data.linear.size)) + return irq_find_mapping(host, hwirq); + + /* Check if revmap was allocated */ + revmap = host->revmap_data.linear.revmap; + if (unlikely(revmap == NULL)) + return irq_find_mapping(host, hwirq); + + /* Fill up revmap with slow path if no mapping found */ + if (unlikely(revmap[hwirq] == NO_IRQ)) + revmap[hwirq] = irq_find_mapping(host, hwirq); + + return revmap[hwirq]; +} + +unsigned int irq_alloc_virt(struct irq_host *host, + unsigned int count, + unsigned int hint) +{ + unsigned long flags; + unsigned int i, j, found = NO_IRQ; + unsigned int limit = irq_virq_count - count; + + if (count == 0 || count > (irq_virq_count - NUM_ISA_INTERRUPTS)) + return NO_IRQ; + + spin_lock_irqsave(&irq_big_lock, flags); + + /* Use hint for 1 interrupt if any */ + if (count == 1 && hint >= NUM_ISA_INTERRUPTS && + hint < irq_virq_count && irq_map[hint].host == NULL) { + found = hint; + goto hint_found; + } + + /* Look for count consecutive numbers in the allocatable + * (non-legacy) space + */ + for (i = NUM_ISA_INTERRUPTS; i <= limit; ) { + for (j = i; j < (i + count); j++) + if (irq_map[j].host != NULL) { + i = j + 1; + continue; + } + found = i; + break; + } + if (found == NO_IRQ) { + spin_unlock_irqrestore(&irq_big_lock, flags); + return NO_IRQ; + } + hint_found: + for (i = found; i < (found + count); i++) { + irq_map[i].hwirq = host->inval_irq; + smp_wmb(); + irq_map[i].host = host; + } + spin_unlock_irqrestore(&irq_big_lock, flags); + return found; +} + +void irq_free_virt(unsigned int virq, unsigned int count) +{ + unsigned long flags; + unsigned int i; + + WARN_ON (virq < NUM_ISA_INTERRUPTS); + WARN_ON (count == 0 || (virq + count) > irq_virq_count); + + spin_lock_irqsave(&irq_big_lock, flags); + for (i = virq; i < (virq + count); i++) { + struct irq_host *host; + + if (i < NUM_ISA_INTERRUPTS || + (virq + count) > irq_virq_count) + continue; + + host = irq_map[i].host; + irq_map[i].hwirq = host->inval_irq; + smp_wmb(); + irq_map[i].host = NULL; + } + spin_unlock_irqrestore(&irq_big_lock, flags); +} + +void irq_early_init(void) +{ + unsigned int i; + + for (i = 0; i < NR_IRQS; i++) + get_irq_desc(i)->status |= IRQ_NOREQUEST; +} + +/* We need to create the radix trees late */ +static int irq_late_init(void) +{ + struct irq_host *h; + unsigned long flags; + + spin_lock_irqsave(&irq_big_lock, flags); + list_for_each_entry(h, &irq_hosts, link) { + if (h->revmap_type == IRQ_HOST_MAP_TREE) + INIT_RADIX_TREE(&h->revmap_data.tree, GFP_ATOMIC); + } + spin_unlock_irqrestore(&irq_big_lock, flags); + + return 0; +} +arch_initcall(irq_late_init); #ifdef CONFIG_PCI_MSI int pci_enable_msi(struct pci_dev * pdev) { Index: linux-irq-work/include/asm-powerpc/machdep.h =================================================================== --- linux-irq-work.orig/include/asm-powerpc/machdep.h 2006-07-01 15:25:10.000000000 +1000 +++ linux-irq-work/include/asm-powerpc/machdep.h 2006-07-01 15:25:45.000000000 +1000 @@ -97,7 +97,7 @@ void (*show_percpuinfo)(struct seq_file *m, int i); void (*init_IRQ)(void); - int (*get_irq)(struct pt_regs *); + unsigned int (*get_irq)(struct pt_regs *); #ifdef CONFIG_KEXEC void (*kexec_cpu_down)(int crash_shutdown, int secondary); #endif Index: linux-irq-work/arch/powerpc/kernel/setup_64.c =================================================================== --- linux-irq-work.orig/arch/powerpc/kernel/setup_64.c 2006-07-01 15:25:10.000000000 +1000 +++ linux-irq-work/arch/powerpc/kernel/setup_64.c 2006-07-01 15:25:45.000000000 +1000 @@ -367,6 +367,11 @@ */ initialize_cache_info(); + /* + * Initialize irq remapping subsystem + */ + irq_early_init(); + #ifdef CONFIG_PPC_RTAS /* * Initialize RTAS if available @@ -427,8 +432,6 @@ printk("-----------------------------------------------------\n"); printk("ppc64_pft_size = 0x%lx\n", ppc64_pft_size); - printk("ppc64_interrupt_controller = 0x%ld\n", - ppc64_interrupt_controller); printk("physicalMemorySize = 0x%lx\n", lmb_phys_mem_size()); printk("ppc64_caches.dcache_line_size = 0x%x\n", ppc64_caches.dline_size);