2005-04-17 06:20:36 +08:00
|
|
|
#ifdef __KERNEL__
|
2005-10-10 20:54:57 +08:00
|
|
|
#ifndef _ASM_POWERPC_IRQ_H
|
|
|
|
|
#define _ASM_POWERPC_IRQ_H
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-10-10 20:54:57 +08:00
|
|
|
#include <linux/threads.h>
|
2006-07-03 19:36:01 +08:00
|
|
|
#include <linux/list.h>
|
|
|
|
|
#include <linux/radix-tree.h>
|
2005-10-10 20:54:57 +08:00
|
|
|
|
|
|
|
|
#include <asm/types.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <asm/atomic.h>
|
|
|
|
|
|
|
|
|
|
|
2005-09-22 05:52:55 +08:00
|
|
|
/* Define a way to iterate across irqs. */
|
|
|
|
|
#define for_each_irq(i) \
|
|
|
|
|
for ((i) = 0; (i) < NR_IRQS; ++(i))
|
|
|
|
|
|
2006-07-03 19:36:01 +08:00
|
|
|
extern atomic_t ppc_n_lost_interrupts;
|
2005-10-10 20:54:57 +08:00
|
|
|
|
2006-07-03 19:36:01 +08:00
|
|
|
/* 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.
|
2005-10-10 20:54:57 +08:00
|
|
|
*/
|
2006-07-03 19:36:01 +08:00
|
|
|
#define NO_IRQ_IGNORE ((unsigned int)-1)
|
|
|
|
|
|
2009-10-14 03:44:44 +08:00
|
|
|
/* Total number of virq in the platform */
|
|
|
|
|
#define NR_IRQS CONFIG_NR_IRQS
|
2005-10-10 20:54:57 +08:00
|
|
|
|
2006-07-03 19:36:01 +08:00
|
|
|
/* Number of irqs reserved for the legacy controller */
|
|
|
|
|
#define NUM_ISA_INTERRUPTS 16
|
|
|
|
|
|
2009-10-14 03:45:03 +08:00
|
|
|
/* Same thing, used by the generic IRQ code */
|
|
|
|
|
#define NR_IRQS_LEGACY NUM_ISA_INTERRUPTS
|
|
|
|
|
|
2006-07-03 19:36:01 +08:00
|
|
|
/* 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
|
[PATCH] powerpc: fix trigger handling in the new irq code
This patch slightly reworks the new irq code to fix a small design error. I
removed the passing of the trigger to the map() calls entirely, it was not a
good idea to have one call do two different things. It also fixes a couple of
corner cases.
Mapping a linux virtual irq to a physical irq now does only that. Setting the
trigger is a different action which has a different call.
The main changes are:
- I no longer call host->ops->map() for an already mapped irq, I just return
the virtual number that was already mapped. It was called before to give an
opportunity to change the trigger, but that was causing issues as that could
happen while the interrupt was in use by a device, and because of the
trigger change, map would potentially muck around with things in a racy way.
That was causing much burden on a given's controller implementation of
map() to get it right. This is much simpler now. map() is only called on
the initial mapping of an irq, meaning that you know that this irq is _not_
being used. You can initialize the hardware if you want (though you don't
have to).
- Controllers that can handle different type of triggers (level/edge/etc...)
now implement the standard irq_chip->set_type() call as defined by the
generic code. That means that you can use the standard set_irq_type() to
configure an irq line manually if you wish or (though I don't like that
interface), pass explicit trigger flags to request_irq() as defined by the
generic kernel interfaces. Also, using those interfaces guarantees that
your controller set_type callback is called with the descriptor lock held,
thus providing locking against activity on the same interrupt (including
mask/unmask/etc...) automatically. A result is that, for example, MPIC's
own map() implementation calls irq_set_type(NONE) to configure the hardware
to the default triggers.
- To allow the above, the irq_map array entry for the new mapped interrupt
is now set before map() callback is called for the controller.
- The irq_create_of_mapping() (also used by irq_of_parse_and_map()) function
for mapping interrupts from the device-tree now also call the separate
set_irq_type(), and only does so if there is a change in the trigger type.
- While I was at it, I changed pci_read_irq_line() (which is the helper I
would expect most archs to use in their pcibios_fixup() to get the PCI
interrupt routing from the device tree) to also handle a fallback when the
DT mapping fails consisting of reading the PCI_INTERRUPT_PIN to know wether
the device has an interrupt at all, and the the PCI_INTERRUPT_LINE to get an
interrupt number from the device. That number is then mapped using the
default controller, and the trigger is set to level low. That default
behaviour works for several platforms that don't have a proper interrupt
tree like Pegasos. If it doesn't work for your platform, then either
provide a proper interrupt tree from the firmware so that fallback isn't
needed, or don't call pci_read_irq_line()
- Add back a bit that got dropped by my main rework patch for properly
clearing pending IPIs on pSeries when using a kexec
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-10 19:44:42 +08:00
|
|
|
* irq number. This is called only once for a given mapping.
|
2006-07-03 19:36:01 +08:00
|
|
|
*/
|
[PATCH] powerpc: fix trigger handling in the new irq code
This patch slightly reworks the new irq code to fix a small design error. I
removed the passing of the trigger to the map() calls entirely, it was not a
good idea to have one call do two different things. It also fixes a couple of
corner cases.
Mapping a linux virtual irq to a physical irq now does only that. Setting the
trigger is a different action which has a different call.
The main changes are:
- I no longer call host->ops->map() for an already mapped irq, I just return
the virtual number that was already mapped. It was called before to give an
opportunity to change the trigger, but that was causing issues as that could
happen while the interrupt was in use by a device, and because of the
trigger change, map would potentially muck around with things in a racy way.
That was causing much burden on a given's controller implementation of
map() to get it right. This is much simpler now. map() is only called on
the initial mapping of an irq, meaning that you know that this irq is _not_
being used. You can initialize the hardware if you want (though you don't
have to).
- Controllers that can handle different type of triggers (level/edge/etc...)
now implement the standard irq_chip->set_type() call as defined by the
generic code. That means that you can use the standard set_irq_type() to
configure an irq line manually if you wish or (though I don't like that
interface), pass explicit trigger flags to request_irq() as defined by the
generic kernel interfaces. Also, using those interfaces guarantees that
your controller set_type callback is called with the descriptor lock held,
thus providing locking against activity on the same interrupt (including
mask/unmask/etc...) automatically. A result is that, for example, MPIC's
own map() implementation calls irq_set_type(NONE) to configure the hardware
to the default triggers.
- To allow the above, the irq_map array entry for the new mapped interrupt
is now set before map() callback is called for the controller.
- The irq_create_of_mapping() (also used by irq_of_parse_and_map()) function
for mapping interrupts from the device-tree now also call the separate
set_irq_type(), and only does so if there is a change in the trigger type.
- While I was at it, I changed pci_read_irq_line() (which is the helper I
would expect most archs to use in their pcibios_fixup() to get the PCI
interrupt routing from the device tree) to also handle a fallback when the
DT mapping fails consisting of reading the PCI_INTERRUPT_PIN to know wether
the device has an interrupt at all, and the the PCI_INTERRUPT_LINE to get an
interrupt number from the device. That number is then mapped using the
default controller, and the trigger is set to level low. That default
behaviour works for several platforms that don't have a proper interrupt
tree like Pegasos. If it doesn't work for your platform, then either
provide a proper interrupt tree from the firmware so that fallback isn't
needed, or don't call pci_read_irq_line()
- Add back a bit that got dropped by my main rework patch for properly
clearing pending IPIs on pSeries when using a kexec
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-10 19:44:42 +08:00
|
|
|
int (*map)(struct irq_host *h, unsigned int virq, irq_hw_number_t hw);
|
2006-07-03 19:36:01 +08:00
|
|
|
|
|
|
|
|
/* Dispose of such a mapping */
|
|
|
|
|
void (*unmap)(struct irq_host *h, unsigned int virq);
|
|
|
|
|
|
2007-01-12 08:58:39 +08:00
|
|
|
/* Update of such a mapping */
|
|
|
|
|
void (*remap)(struct irq_host *h, unsigned int virq, irq_hw_number_t hw);
|
|
|
|
|
|
2006-07-03 19:36:01 +08:00
|
|
|
/* Translate device-tree interrupt specifier from raw format coming
|
|
|
|
|
* from the firmware to a irq_hw_number_t (interrupt line number) and
|
[PATCH] powerpc: fix trigger handling in the new irq code
This patch slightly reworks the new irq code to fix a small design error. I
removed the passing of the trigger to the map() calls entirely, it was not a
good idea to have one call do two different things. It also fixes a couple of
corner cases.
Mapping a linux virtual irq to a physical irq now does only that. Setting the
trigger is a different action which has a different call.
The main changes are:
- I no longer call host->ops->map() for an already mapped irq, I just return
the virtual number that was already mapped. It was called before to give an
opportunity to change the trigger, but that was causing issues as that could
happen while the interrupt was in use by a device, and because of the
trigger change, map would potentially muck around with things in a racy way.
That was causing much burden on a given's controller implementation of
map() to get it right. This is much simpler now. map() is only called on
the initial mapping of an irq, meaning that you know that this irq is _not_
being used. You can initialize the hardware if you want (though you don't
have to).
- Controllers that can handle different type of triggers (level/edge/etc...)
now implement the standard irq_chip->set_type() call as defined by the
generic code. That means that you can use the standard set_irq_type() to
configure an irq line manually if you wish or (though I don't like that
interface), pass explicit trigger flags to request_irq() as defined by the
generic kernel interfaces. Also, using those interfaces guarantees that
your controller set_type callback is called with the descriptor lock held,
thus providing locking against activity on the same interrupt (including
mask/unmask/etc...) automatically. A result is that, for example, MPIC's
own map() implementation calls irq_set_type(NONE) to configure the hardware
to the default triggers.
- To allow the above, the irq_map array entry for the new mapped interrupt
is now set before map() callback is called for the controller.
- The irq_create_of_mapping() (also used by irq_of_parse_and_map()) function
for mapping interrupts from the device-tree now also call the separate
set_irq_type(), and only does so if there is a change in the trigger type.
- While I was at it, I changed pci_read_irq_line() (which is the helper I
would expect most archs to use in their pcibios_fixup() to get the PCI
interrupt routing from the device tree) to also handle a fallback when the
DT mapping fails consisting of reading the PCI_INTERRUPT_PIN to know wether
the device has an interrupt at all, and the the PCI_INTERRUPT_LINE to get an
interrupt number from the device. That number is then mapped using the
default controller, and the trigger is set to level low. That default
behaviour works for several platforms that don't have a proper interrupt
tree like Pegasos. If it doesn't work for your platform, then either
provide a proper interrupt tree from the firmware so that fallback isn't
needed, or don't call pci_read_irq_line()
- Add back a bit that got dropped by my main rework patch for properly
clearing pending IPIs on pSeries when using a kexec
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-10 19:44:42 +08:00
|
|
|
* type (sense) that can be passed to set_irq_type(). In the absence
|
|
|
|
|
* of this callback, irq_create_of_mapping() and irq_of_parse_and_map()
|
|
|
|
|
* will return the hw number in the first cell and IRQ_TYPE_NONE for
|
|
|
|
|
* the type (which amount to keeping whatever default value the
|
|
|
|
|
* interrupt controller has for that line)
|
2006-07-03 19:36:01 +08:00
|
|
|
*/
|
|
|
|
|
int (*xlate)(struct irq_host *h, struct device_node *ctrler,
|
2009-12-08 10:39:50 +08:00
|
|
|
const u32 *intspec, unsigned int intsize,
|
[PATCH] powerpc: fix trigger handling in the new irq code
This patch slightly reworks the new irq code to fix a small design error. I
removed the passing of the trigger to the map() calls entirely, it was not a
good idea to have one call do two different things. It also fixes a couple of
corner cases.
Mapping a linux virtual irq to a physical irq now does only that. Setting the
trigger is a different action which has a different call.
The main changes are:
- I no longer call host->ops->map() for an already mapped irq, I just return
the virtual number that was already mapped. It was called before to give an
opportunity to change the trigger, but that was causing issues as that could
happen while the interrupt was in use by a device, and because of the
trigger change, map would potentially muck around with things in a racy way.
That was causing much burden on a given's controller implementation of
map() to get it right. This is much simpler now. map() is only called on
the initial mapping of an irq, meaning that you know that this irq is _not_
being used. You can initialize the hardware if you want (though you don't
have to).
- Controllers that can handle different type of triggers (level/edge/etc...)
now implement the standard irq_chip->set_type() call as defined by the
generic code. That means that you can use the standard set_irq_type() to
configure an irq line manually if you wish or (though I don't like that
interface), pass explicit trigger flags to request_irq() as defined by the
generic kernel interfaces. Also, using those interfaces guarantees that
your controller set_type callback is called with the descriptor lock held,
thus providing locking against activity on the same interrupt (including
mask/unmask/etc...) automatically. A result is that, for example, MPIC's
own map() implementation calls irq_set_type(NONE) to configure the hardware
to the default triggers.
- To allow the above, the irq_map array entry for the new mapped interrupt
is now set before map() callback is called for the controller.
- The irq_create_of_mapping() (also used by irq_of_parse_and_map()) function
for mapping interrupts from the device-tree now also call the separate
set_irq_type(), and only does so if there is a change in the trigger type.
- While I was at it, I changed pci_read_irq_line() (which is the helper I
would expect most archs to use in their pcibios_fixup() to get the PCI
interrupt routing from the device tree) to also handle a fallback when the
DT mapping fails consisting of reading the PCI_INTERRUPT_PIN to know wether
the device has an interrupt at all, and the the PCI_INTERRUPT_LINE to get an
interrupt number from the device. That number is then mapped using the
default controller, and the trigger is set to level low. That default
behaviour works for several platforms that don't have a proper interrupt
tree like Pegasos. If it doesn't work for your platform, then either
provide a proper interrupt tree from the firmware so that fallback isn't
needed, or don't call pci_read_irq_line()
- Add back a bit that got dropped by my main rework patch for properly
clearing pending IPIs on pSeries when using a kexec
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-10 19:44:42 +08:00
|
|
|
irq_hw_number_t *out_hwirq, unsigned int *out_type);
|
2006-07-03 19:36:01 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
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;
|
2007-08-28 16:47:54 +08:00
|
|
|
|
|
|
|
|
/* Optional device node pointer */
|
|
|
|
|
struct device_node *of_node;
|
2006-07-03 19:36:01 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
/* 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];
|
|
|
|
|
|
2007-06-04 12:47:04 +08:00
|
|
|
extern irq_hw_number_t virq_to_hw(unsigned int virq);
|
2006-07-03 19:36:01 +08:00
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* irq_alloc_host - Allocate a new irq_host data structure
|
2007-08-28 16:47:54 +08:00
|
|
|
* @of_node: optional device-tree node of the interrupt controller
|
2006-07-03 19:36:01 +08:00
|
|
|
* @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).
|
|
|
|
|
*/
|
2007-08-28 16:47:54 +08:00
|
|
|
extern struct irq_host *irq_alloc_host(struct device_node *of_node,
|
|
|
|
|
unsigned int revmap_type,
|
2006-07-03 19:36:01 +08:00
|
|
|
unsigned int revmap_arg,
|
|
|
|
|
struct irq_host_ops *ops,
|
|
|
|
|
irq_hw_number_t inval_irq);
|
|
|
|
|
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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);
|
|
|
|
|
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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);
|
|
|
|
|
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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);
|
|
|
|
|
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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
|
|
|
|
|
*
|
|
|
|
|
* Only one mapping per hardware interrupt is permitted. Returns a linux
|
[PATCH] powerpc: fix trigger handling in the new irq code
This patch slightly reworks the new irq code to fix a small design error. I
removed the passing of the trigger to the map() calls entirely, it was not a
good idea to have one call do two different things. It also fixes a couple of
corner cases.
Mapping a linux virtual irq to a physical irq now does only that. Setting the
trigger is a different action which has a different call.
The main changes are:
- I no longer call host->ops->map() for an already mapped irq, I just return
the virtual number that was already mapped. It was called before to give an
opportunity to change the trigger, but that was causing issues as that could
happen while the interrupt was in use by a device, and because of the
trigger change, map would potentially muck around with things in a racy way.
That was causing much burden on a given's controller implementation of
map() to get it right. This is much simpler now. map() is only called on
the initial mapping of an irq, meaning that you know that this irq is _not_
being used. You can initialize the hardware if you want (though you don't
have to).
- Controllers that can handle different type of triggers (level/edge/etc...)
now implement the standard irq_chip->set_type() call as defined by the
generic code. That means that you can use the standard set_irq_type() to
configure an irq line manually if you wish or (though I don't like that
interface), pass explicit trigger flags to request_irq() as defined by the
generic kernel interfaces. Also, using those interfaces guarantees that
your controller set_type callback is called with the descriptor lock held,
thus providing locking against activity on the same interrupt (including
mask/unmask/etc...) automatically. A result is that, for example, MPIC's
own map() implementation calls irq_set_type(NONE) to configure the hardware
to the default triggers.
- To allow the above, the irq_map array entry for the new mapped interrupt
is now set before map() callback is called for the controller.
- The irq_create_of_mapping() (also used by irq_of_parse_and_map()) function
for mapping interrupts from the device-tree now also call the separate
set_irq_type(), and only does so if there is a change in the trigger type.
- While I was at it, I changed pci_read_irq_line() (which is the helper I
would expect most archs to use in their pcibios_fixup() to get the PCI
interrupt routing from the device tree) to also handle a fallback when the
DT mapping fails consisting of reading the PCI_INTERRUPT_PIN to know wether
the device has an interrupt at all, and the the PCI_INTERRUPT_LINE to get an
interrupt number from the device. That number is then mapped using the
default controller, and the trigger is set to level low. That default
behaviour works for several platforms that don't have a proper interrupt
tree like Pegasos. If it doesn't work for your platform, then either
provide a proper interrupt tree from the firmware so that fallback isn't
needed, or don't call pci_read_irq_line()
- Add back a bit that got dropped by my main rework patch for properly
clearing pending IPIs on pSeries when using a kexec
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-10 19:44:42 +08:00
|
|
|
* virq number.
|
|
|
|
|
* If the sense/trigger is to be specified, set_irq_type() should be called
|
|
|
|
|
* on the number returned from that call.
|
2006-07-03 19:36:01 +08:00
|
|
|
*/
|
|
|
|
|
extern unsigned int irq_create_mapping(struct irq_host *host,
|
[PATCH] powerpc: fix trigger handling in the new irq code
This patch slightly reworks the new irq code to fix a small design error. I
removed the passing of the trigger to the map() calls entirely, it was not a
good idea to have one call do two different things. It also fixes a couple of
corner cases.
Mapping a linux virtual irq to a physical irq now does only that. Setting the
trigger is a different action which has a different call.
The main changes are:
- I no longer call host->ops->map() for an already mapped irq, I just return
the virtual number that was already mapped. It was called before to give an
opportunity to change the trigger, but that was causing issues as that could
happen while the interrupt was in use by a device, and because of the
trigger change, map would potentially muck around with things in a racy way.
That was causing much burden on a given's controller implementation of
map() to get it right. This is much simpler now. map() is only called on
the initial mapping of an irq, meaning that you know that this irq is _not_
being used. You can initialize the hardware if you want (though you don't
have to).
- Controllers that can handle different type of triggers (level/edge/etc...)
now implement the standard irq_chip->set_type() call as defined by the
generic code. That means that you can use the standard set_irq_type() to
configure an irq line manually if you wish or (though I don't like that
interface), pass explicit trigger flags to request_irq() as defined by the
generic kernel interfaces. Also, using those interfaces guarantees that
your controller set_type callback is called with the descriptor lock held,
thus providing locking against activity on the same interrupt (including
mask/unmask/etc...) automatically. A result is that, for example, MPIC's
own map() implementation calls irq_set_type(NONE) to configure the hardware
to the default triggers.
- To allow the above, the irq_map array entry for the new mapped interrupt
is now set before map() callback is called for the controller.
- The irq_create_of_mapping() (also used by irq_of_parse_and_map()) function
for mapping interrupts from the device-tree now also call the separate
set_irq_type(), and only does so if there is a change in the trigger type.
- While I was at it, I changed pci_read_irq_line() (which is the helper I
would expect most archs to use in their pcibios_fixup() to get the PCI
interrupt routing from the device tree) to also handle a fallback when the
DT mapping fails consisting of reading the PCI_INTERRUPT_PIN to know wether
the device has an interrupt at all, and the the PCI_INTERRUPT_LINE to get an
interrupt number from the device. That number is then mapped using the
default controller, and the trigger is set to level low. That default
behaviour works for several platforms that don't have a proper interrupt
tree like Pegasos. If it doesn't work for your platform, then either
provide a proper interrupt tree from the firmware so that fallback isn't
needed, or don't call pci_read_irq_line()
- Add back a bit that got dropped by my main rework patch for properly
clearing pending IPIs on pSeries when using a kexec
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-07-10 19:44:42 +08:00
|
|
|
irq_hw_number_t hwirq);
|
2006-07-03 19:36:01 +08:00
|
|
|
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* irq_dispose_mapping - Unmap an interrupt
|
|
|
|
|
* @virq: linux virq number of the interrupt to unmap
|
2005-10-10 20:54:57 +08:00
|
|
|
*/
|
2006-07-03 19:36:01 +08:00
|
|
|
extern void irq_dispose_mapping(unsigned int virq);
|
2005-10-10 20:54:57 +08:00
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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.
|
2006-04-04 12:49:48 +08:00
|
|
|
*/
|
2006-07-03 19:36:01 +08:00
|
|
|
extern unsigned int irq_find_mapping(struct irq_host *host,
|
|
|
|
|
irq_hw_number_t hwirq);
|
2006-04-04 12:49:48 +08:00
|
|
|
|
2007-06-04 21:00:00 +08:00
|
|
|
/**
|
|
|
|
|
* irq_create_direct_mapping - Allocate a virq for direct mapping
|
|
|
|
|
* @host: host to allocate the virq for or NULL for default host
|
|
|
|
|
*
|
|
|
|
|
* This routine is used for irq controllers which can choose the hardware
|
|
|
|
|
* interrupt numbers they generate. In such a case it's simplest to use
|
|
|
|
|
* the linux virq as the hardware interrupt number.
|
|
|
|
|
*/
|
|
|
|
|
extern unsigned int irq_create_direct_mapping(struct irq_host *host);
|
2006-07-03 19:36:01 +08:00
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2008-09-04 20:37:07 +08:00
|
|
|
* irq_radix_revmap_insert - Insert a hw irq to linux virq number mapping.
|
|
|
|
|
* @host: host owning this hardware interrupt
|
|
|
|
|
* @virq: linux irq number
|
|
|
|
|
* @hwirq: hardware irq number in that host space
|
|
|
|
|
*
|
|
|
|
|
* This is for use by irq controllers that use a radix tree reverse
|
|
|
|
|
* mapping for fast lookup.
|
|
|
|
|
*/
|
|
|
|
|
extern void irq_radix_revmap_insert(struct irq_host *host, unsigned int virq,
|
|
|
|
|
irq_hw_number_t hwirq);
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
|
* irq_radix_revmap_lookup - Find a linux virq from a hw irq number.
|
2006-07-03 19:36:01 +08:00
|
|
|
* @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
|
|
|
|
|
*/
|
2008-09-04 20:37:07 +08:00
|
|
|
extern unsigned int irq_radix_revmap_lookup(struct irq_host *host,
|
|
|
|
|
irq_hw_number_t hwirq);
|
2006-07-03 19:36:01 +08:00
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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);
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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.
|
2005-10-10 20:54:57 +08:00
|
|
|
*/
|
2006-07-03 19:36:01 +08:00
|
|
|
extern unsigned int irq_alloc_virt(struct irq_host *host,
|
|
|
|
|
unsigned int count,
|
|
|
|
|
unsigned int hint);
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* 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);
|
|
|
|
|
|
2006-08-02 09:13:50 +08:00
|
|
|
/**
|
2006-07-03 19:36:01 +08:00
|
|
|
* irq_early_init - Init irq remapping subsystem
|
|
|
|
|
*/
|
|
|
|
|
extern void irq_early_init(void);
|
|
|
|
|
|
|
|
|
|
static __inline__ int irq_canonicalize(int irq)
|
2005-10-10 20:54:57 +08:00
|
|
|
{
|
2006-07-03 19:36:01 +08:00
|
|
|
return irq;
|
2005-10-10 20:54:57 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
extern int distribute_irqs;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-10-10 20:54:57 +08:00
|
|
|
struct irqaction;
|
|
|
|
|
struct pt_regs;
|
|
|
|
|
|
powerpc: Implement accurate task and CPU time accounting
This implements accurate task and cpu time accounting for 64-bit
powerpc kernels. Instead of accounting a whole jiffy of time to a
task on a timer interrupt because that task happened to be running at
the time, we now account time in units of timebase ticks according to
the actual time spent by the task in user mode and kernel mode. We
also count the time spent processing hardware and software interrupts
accurately. This is conditional on CONFIG_VIRT_CPU_ACCOUNTING. If
that is not set, we do tick-based approximate accounting as before.
To get this accurate information, we read either the PURR (processor
utilization of resources register) on POWER5 machines, or the timebase
on other machines on
* each entry to the kernel from usermode
* each exit to usermode
* transitions between process context, hard irq context and soft irq
context in kernel mode
* context switches.
On POWER5 systems with shared-processor logical partitioning we also
read both the PURR and the timebase at each timer interrupt and
context switch in order to determine how much time has been taken by
the hypervisor to run other partitions ("steal" time). Unfortunately,
since we need values of the PURR on both threads at the same time to
accurately calculate the steal time, and since we can only calculate
steal time on a per-core basis, the apportioning of the steal time
between idle time (time which we ceded to the hypervisor in the idle
loop) and actual stolen time is somewhat approximate at the moment.
This is all based quite heavily on what s390 does, and it uses the
generic interfaces that were added by the s390 developers,
i.e. account_system_time(), account_user_time(), etc.
This patch doesn't add any new interfaces between the kernel and
userspace, and doesn't change the units in which time is reported to
userspace by things such as /proc/stat, /proc/<pid>/stat, getrusage(),
times(), etc. Internally the various task and cpu times are stored in
timebase units, but they are converted to USER_HZ units (1/100th of a
second) when reported to userspace. Some precision is therefore lost
but there should not be any accumulating error, since the internal
accumulation is at full precision.
Signed-off-by: Paul Mackerras <paulus@samba.org>
2006-02-24 07:06:59 +08:00
|
|
|
#define __ARCH_HAS_DO_SOFTIRQ
|
|
|
|
|
|
2008-04-30 16:49:55 +08:00
|
|
|
#if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
|
|
|
|
|
/*
|
|
|
|
|
* Per-cpu stacks for handling critical, debug and machine check
|
|
|
|
|
* level interrupts.
|
|
|
|
|
*/
|
|
|
|
|
extern struct thread_info *critirq_ctx[NR_CPUS];
|
|
|
|
|
extern struct thread_info *dbgirq_ctx[NR_CPUS];
|
|
|
|
|
extern struct thread_info *mcheckirq_ctx[NR_CPUS];
|
|
|
|
|
extern void exc_lvl_ctx_init(void);
|
|
|
|
|
#else
|
|
|
|
|
#define exc_lvl_ctx_init()
|
|
|
|
|
#endif
|
|
|
|
|
|
2005-10-10 20:54:57 +08:00
|
|
|
/*
|
|
|
|
|
* Per-cpu stacks for handling hard and soft interrupts.
|
|
|
|
|
*/
|
|
|
|
|
extern struct thread_info *hardirq_ctx[NR_CPUS];
|
|
|
|
|
extern struct thread_info *softirq_ctx[NR_CPUS];
|
|
|
|
|
|
|
|
|
|
extern void irq_ctx_init(void);
|
|
|
|
|
extern void call_do_softirq(struct thread_info *tp);
|
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers
Maintain a per-CPU global "struct pt_regs *" variable which can be used instead
of passing regs around manually through all ~1800 interrupt handlers in the
Linux kernel.
The regs pointer is used in few places, but it potentially costs both stack
space and code to pass it around. On the FRV arch, removing the regs parameter
from all the genirq function results in a 20% speed up of the IRQ exit path
(ie: from leaving timer_interrupt() to leaving do_IRQ()).
Where appropriate, an arch may override the generic storage facility and do
something different with the variable. On FRV, for instance, the address is
maintained in GR28 at all times inside the kernel as part of general exception
handling.
Having looked over the code, it appears that the parameter may be handed down
through up to twenty or so layers of functions. Consider a USB character
device attached to a USB hub, attached to a USB controller that posts its
interrupts through a cascaded auxiliary interrupt controller. A character
device driver may want to pass regs to the sysrq handler through the input
layer which adds another few layers of parameter passing.
I've build this code with allyesconfig for x86_64 and i386. I've runtested the
main part of the code on FRV and i386, though I can't test most of the drivers.
I've also done partial conversion for powerpc and MIPS - these at least compile
with minimal configurations.
This will affect all archs. Mostly the changes should be relatively easy.
Take do_IRQ(), store the regs pointer at the beginning, saving the old one:
struct pt_regs *old_regs = set_irq_regs(regs);
And put the old one back at the end:
set_irq_regs(old_regs);
Don't pass regs through to generic_handle_irq() or __do_IRQ().
In timer_interrupt(), this sort of change will be necessary:
- update_process_times(user_mode(regs));
- profile_tick(CPU_PROFILING, regs);
+ update_process_times(user_mode(get_irq_regs()));
+ profile_tick(CPU_PROFILING);
I'd like to move update_process_times()'s use of get_irq_regs() into itself,
except that i386, alone of the archs, uses something other than user_mode().
Some notes on the interrupt handling in the drivers:
(*) input_dev() is now gone entirely. The regs pointer is no longer stored in
the input_dev struct.
(*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does
something different depending on whether it's been supplied with a regs
pointer or not.
(*) Various IRQ handler function pointers have been moved to type
irq_handler_t.
Signed-Off-By: David Howells <dhowells@redhat.com>
(cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
|
|
|
extern int call_handle_irq(int irq, void *p1,
|
2006-07-03 17:32:51 +08:00
|
|
|
struct thread_info *tp, void *func);
|
2005-10-20 07:23:26 +08:00
|
|
|
extern void do_IRQ(struct pt_regs *regs);
|
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif /* _ASM_IRQ_H */
|
|
|
|
|
#endif /* __KERNEL__ */
|