[POWERPC] Add new interrupt mapping core and change platforms to use it

This adds the new irq remapper core and removes the old one.  Because
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..., this commit also changes the relevant platform and driver code
over to use the new remapper (so as not to cause difficulties later
in bisecting).

This patch removes the old pre-parsing of the open firmware interrupt
tree along with all the bogus assumptions it made to try to renumber
interrupts according to the platform. This is all to be handled by the
new code now.

For the pSeries XICS interrupt controller, a single remapper host is
created for the whole machine regardless of how many interrupt
presentation and source controllers are found, and it's set to match
any device node that isn't a 8259.  That works fine on pSeries and
avoids having to deal with some of the complexities of split source
controllers vs. presentation controllers in the pSeries device trees.

The powerpc i8259 PIC driver now always requests the legacy interrupt
range. It also has the feature of being able to match any device node
(including NULL) if passed no device node as an input. That will help
porting over platforms with broken device-trees like Pegasos who don't
have a proper interrupt tree.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>

6 files changed, 340 insertions, 73 deletions

diff --git a/include/asm-powerpc/i8259.h b/include/asm-powerpc/i8259.h
index ff31cb9..c80e113 100644
--- a/include/asm-powerpc/i8259.h
+++ b/include/asm-powerpc/i8259.h
@@ -4,8 +4,13 @@
 
 #include <linux/irq.h>
 
+#ifdef CONFIG_PPC_MERGE
+extern void i8259_init(struct device_node *node, unsigned long intack_addr);
+extern unsigned int i8259_irq(struct pt_regs *regs);
+#else
 extern void i8259_init(unsigned long intack_addr, int offset);
 extern int i8259_irq(struct pt_regs *regs);
+#endif
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_I8259_H */
diff --git a/include/asm-powerpc/irq.h b/include/asm-powerpc/irq.h
index 13fa2ef..e057547 100644
--- a/include/asm-powerpc/irq.h
+++ b/include/asm-powerpc/irq.h
@@ -9,26 +9,14 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#include <linux/config.h>
 #include <linux/threads.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
 
 #include <asm/types.h>
 #include <asm/atomic.h>
 
-/* 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 +24,325 @@
 #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 unsigned int virt_irq_to_real_map[NR_IRQS];
+extern void irq_dispose_mapping(unsigned int virq);
 
-/* 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_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 virt_irq_max;
+extern unsigned int irq_find_mapping(struct irq_host *host,
+				     irq_hw_number_t hwirq);
 
-/* Create a mapping for a real_irq if it doesn't already exist.
- * Return the virtual irq as a convenience.
+
+/***
+ * 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 irq_radix_revmap(struct irq_host *host,
+				     irq_hw_number_t hwirq);
+
+/***
+ * 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 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.
  */
-int virt_irq_create_mapping(unsigned int real_irq);
-void virt_irq_init(void);
+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.
+ */
+extern void irq_free_virt(unsigned int virq, unsigned int count);
+
+
+/* -- OF helpers -- */
+
+/* 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 -- */
 
-static inline unsigned int virt_irq_to_real(unsigned int virt_irq)
+/***
+ * 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)
+#define NO_IRQ_IGNORE		(-2)
+
 
 /*
- * 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 <asm/ibm4xx.h>
@@ -512,19 +775,11 @@ extern u64 ppc64_interrupt_controller;
 
 #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 +818,7 @@ static __inline__ int irq_canonicalize(int irq)
 		irq = 9;
 	return irq;
 }
+#endif /* CONFIG_PPC_MERGE */
 
 extern int distribute_irqs;
 
diff --git a/include/asm-powerpc/machdep.h b/include/asm-powerpc/machdep.h
index eba133d..c17c137 100644
--- a/include/asm-powerpc/machdep.h
+++ b/include/asm-powerpc/machdep.h
@@ -97,7 +97,7 @@ struct machdep_calls {
 	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
diff --git a/include/asm-powerpc/mpic.h b/include/asm-powerpc/mpic.h
index a2277cb..eb241c9 100644
--- a/include/asm-powerpc/mpic.h
+++ b/include/asm-powerpc/mpic.h
@@ -129,6 +129,12 @@ struct mpic_irq_fixup
 /* The instance data of a given MPIC */
 struct mpic
 {
+	/* The device node of the interrupt controller */
+	struct device_node	*of_node;
+
+	/* The remapper for this MPIC */
+	struct irq_host		*irqhost;
+
 	/* The "linux" controller struct */
 	struct irq_chip		hc_irq;
 #ifdef CONFIG_MPIC_BROKEN_U3
@@ -144,16 +150,12 @@ struct mpic
 	unsigned int		isu_size;
 	unsigned int		isu_shift;
 	unsigned int		isu_mask;
-	/* Offset of irq vector numbers */
-	unsigned int		irq_offset;	
 	unsigned int		irq_count;
-	/* Offset of ipi vector numbers */
-	unsigned int		ipi_offset;
 	/* Number of sources */
 	unsigned int		num_sources;
 	/* Number of CPUs */
 	unsigned int		num_cpus;
-	/* senses array */
+	/* default senses array */
 	unsigned char		*senses;
 	unsigned int		senses_count;
 
@@ -209,14 +211,11 @@ struct mpic
  * The values in the array start at the first source of the MPIC,
  * that is senses[0] correspond to linux irq "irq_offset".
  */
-extern struct mpic *mpic_alloc(unsigned long phys_addr,
+extern struct mpic *mpic_alloc(struct device_node *node,
+			       unsigned long phys_addr,
 			       unsigned int flags,
 			       unsigned int isu_size,
-			       unsigned int irq_offset,
 			       unsigned int irq_count,
-			       unsigned int ipi_offset,
-			       unsigned char *senses,
-			       unsigned int senses_num,
 			       const char *name);
 
 /* Assign ISUs, to call before mpic_init()
@@ -228,6 +227,22 @@ extern struct mpic *mpic_alloc(unsigned long phys_addr,
 extern void mpic_assign_isu(struct mpic *mpic, unsigned int isu_num,
 			    unsigned long phys_addr);
 
+/* Set default sense codes
+ *
+ * @mpic:	controller
+ * @senses:	array of sense codes
+ * @count:	size of above array
+ *
+ * Optionally provide an array (indexed on hardware interrupt numbers
+ * for this MPIC) of default sense codes for the chip. Those are linux
+ * sense codes IRQ_TYPE_*
+ *
+ * The driver gets ownership of the pointer, don't dispose of it or
+ * anything like that. __init only.
+ */
+extern void mpic_set_default_senses(struct mpic *mpic, u8 *senses, int count);
+
+
 /* Initialize the controller. After this has been called, none of the above
  * should be called again for this mpic
  */
@@ -269,9 +284,9 @@ extern void mpic_send_ipi(unsigned int ipi_no, unsigned int cpu_mask);
 void smp_mpic_message_pass(int target, int msg);
 
 /* Fetch interrupt from a given mpic */
-extern int mpic_get_one_irq(struct mpic *mpic, struct pt_regs *regs);
+extern unsigned int mpic_get_one_irq(struct mpic *mpic, struct pt_regs *regs);
 /* This one gets to the primary mpic */
-extern int mpic_get_irq(struct pt_regs *regs);
+extern unsigned int mpic_get_irq(struct pt_regs *regs);
 
 /* Set the EPIC clock ratio */
 void mpic_set_clk_ratio(struct mpic *mpic, u32 clock_ratio);
@@ -279,8 +294,5 @@ void mpic_set_clk_ratio(struct mpic *mpic, u32 clock_ratio);
 /* Enable/Disable EPIC serial interrupt mode */
 void mpic_set_serial_int(struct mpic *mpic, int enable);
 
-/* global mpic for pSeries */
-extern struct mpic *pSeries_mpic;
-
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_MPIC_H */
diff --git a/include/asm-powerpc/prom.h b/include/asm-powerpc/prom.h
index 48bef40..b095a28 100644
--- a/include/asm-powerpc/prom.h
+++ b/include/asm-powerpc/prom.h
@@ -64,11 +64,6 @@ struct boot_param_header
 typedef u32 phandle;
 typedef u32 ihandle;
 
-struct interrupt_info {
-	int	line;
-	int	sense;		/* +ve/-ve logic, edge or level, etc. */
-};
-
 struct property {
 	char	*name;
 	int	length;
@@ -81,8 +76,6 @@ struct device_node {
 	char	*type;
 	phandle	node;
 	phandle linux_phandle;
-	int	n_intrs;
-	struct	interrupt_info *intrs;
 	char	*full_name;
 
 	struct	property *properties;
diff --git a/include/asm-powerpc/spu.h b/include/asm-powerpc/spu.h
index 9609d3e..c02d105 100644
--- a/include/asm-powerpc/spu.h
+++ b/include/asm-powerpc/spu.h
@@ -117,6 +117,7 @@ struct spu {
 	struct list_head sched_list;
 	int number;
 	int nid;
+	unsigned int irqs[3];
 	u32 isrc;
 	u32 node;
 	u64 flags;