linux/arch/powerpc/platforms/iseries/irq.c

401 lines
10 KiB
C
Raw Normal View History

/*
* This module supports the iSeries PCI bus interrupt handling
* Copyright (C) 20yy <Robert L Holtorf> <IBM Corp>
* Copyright (C) 2004-2005 IBM Corporation
*
* 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.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the:
* Free Software Foundation, Inc.,
* 59 Temple Place, Suite 330,
* Boston, MA 02111-1307 USA
*
* Change Activity:
* Created, December 13, 2000 by Wayne Holm
* End Change Activity
*/
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/threads.h>
#include <linux/smp.h>
#include <linux/param.h>
#include <linux/string.h>
#include <linux/bootmem.h>
#include <linux/irq.h>
#include <linux/spinlock.h>
#include <asm/paca.h>
#include <asm/iseries/hv_types.h>
#include <asm/iseries/hv_lp_event.h>
#include <asm/iseries/hv_call_xm.h>
#include <asm/iseries/it_lp_queue.h>
#include "irq.h"
#include "pci.h"
#include "call_pci.h"
#ifdef CONFIG_PCI
enum pci_event_type {
pe_bus_created = 0, /* PHB has been created */
pe_bus_error = 1, /* PHB has failed */
pe_bus_failed = 2, /* Msg to Secondary, Primary failed bus */
pe_node_failed = 4, /* Multi-adapter bridge has failed */
pe_node_recovered = 5, /* Multi-adapter bridge has recovered */
pe_bus_recovered = 12, /* PHB has been recovered */
pe_unquiese_bus = 18, /* Secondary bus unqiescing */
pe_bridge_error = 21, /* Bridge Error */
pe_slot_interrupt = 22 /* Slot interrupt */
};
struct pci_event {
struct HvLpEvent event;
union {
u64 __align; /* Align on an 8-byte boundary */
struct {
u32 fisr;
HvBusNumber bus_number;
HvSubBusNumber sub_bus_number;
HvAgentId dev_id;
} slot;
struct {
HvBusNumber bus_number;
HvSubBusNumber sub_bus_number;
} bus;
struct {
HvBusNumber bus_number;
HvSubBusNumber sub_bus_number;
HvAgentId dev_id;
} node;
} data;
};
static DEFINE_SPINLOCK(pending_irqs_lock);
static int num_pending_irqs;
static int pending_irqs[NR_IRQS];
static void int_received(struct pci_event *event)
{
int irq;
switch (event->event.xSubtype) {
case pe_slot_interrupt:
irq = event->event.xCorrelationToken;
if (irq < NR_IRQS) {
spin_lock(&pending_irqs_lock);
pending_irqs[irq]++;
num_pending_irqs++;
spin_unlock(&pending_irqs_lock);
} else {
printk(KERN_WARNING "int_received: bad irq number %d\n",
irq);
HvCallPci_eoi(event->data.slot.bus_number,
event->data.slot.sub_bus_number,
event->data.slot.dev_id);
}
break;
/* Ignore error recovery events for now */
case pe_bus_created:
printk(KERN_INFO "int_received: system bus %d created\n",
event->data.bus.bus_number);
break;
case pe_bus_error:
case pe_bus_failed:
printk(KERN_INFO "int_received: system bus %d failed\n",
event->data.bus.bus_number);
break;
case pe_bus_recovered:
case pe_unquiese_bus:
printk(KERN_INFO "int_received: system bus %d recovered\n",
event->data.bus.bus_number);
break;
case pe_node_failed:
case pe_bridge_error:
printk(KERN_INFO
"int_received: multi-adapter bridge %d/%d/%d failed\n",
event->data.node.bus_number,
event->data.node.sub_bus_number,
event->data.node.dev_id);
break;
case pe_node_recovered:
printk(KERN_INFO
"int_received: multi-adapter bridge %d/%d/%d recovered\n",
event->data.node.bus_number,
event->data.node.sub_bus_number,
event->data.node.dev_id);
break;
default:
printk(KERN_ERR
"int_received: unrecognized event subtype 0x%x\n",
event->event.xSubtype);
break;
}
}
static void pci_event_handler(struct HvLpEvent *event)
{
if (event && (event->xType == HvLpEvent_Type_PciIo)) {
if (hvlpevent_is_int(event))
int_received((struct pci_event *)event);
else
printk(KERN_ERR
"pci_event_handler: unexpected ack received\n");
} else if (event)
printk(KERN_ERR
"pci_event_handler: Unrecognized PCI event type 0x%x\n",
(int)event->xType);
else
printk(KERN_ERR "pci_event_handler: NULL event received\n");
}
#define REAL_IRQ_TO_SUBBUS(irq) (((irq) >> 14) & 0xff)
#define REAL_IRQ_TO_BUS(irq) ((((irq) >> 6) & 0xff) + 1)
#define REAL_IRQ_TO_IDSEL(irq) ((((irq) >> 3) & 7) + 1)
#define REAL_IRQ_TO_FUNC(irq) ((irq) & 7)
/*
* This will be called by device drivers (via enable_IRQ)
* to enable INTA in the bridge interrupt status register.
*/
static void iseries_enable_IRQ(struct irq_data *d)
{
u32 bus, dev_id, function, mask;
const u32 sub_bus = 0;
unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
/* The IRQ has already been locked by the caller */
bus = REAL_IRQ_TO_BUS(rirq);
function = REAL_IRQ_TO_FUNC(rirq);
dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
/* Unmask secondary INTA */
mask = 0x80000000;
HvCallPci_unmaskInterrupts(bus, sub_bus, dev_id, mask);
}
/* This is called by iseries_activate_IRQs */
static unsigned int iseries_startup_IRQ(struct irq_data *d)
{
u32 bus, dev_id, function, mask;
const u32 sub_bus = 0;
unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
bus = REAL_IRQ_TO_BUS(rirq);
function = REAL_IRQ_TO_FUNC(rirq);
dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
/* Link the IRQ number to the bridge */
HvCallXm_connectBusUnit(bus, sub_bus, dev_id, d->irq);
/* Unmask bridge interrupts in the FISR */
mask = 0x01010000 << function;
HvCallPci_unmaskFisr(bus, sub_bus, dev_id, mask);
iseries_enable_IRQ(d);
return 0;
}
/*
* This is called out of iSeries_fixup to activate interrupt
* generation for usable slots
*/
void __init iSeries_activate_IRQs()
{
int irq;
unsigned long flags;
for_each_irq (irq) {
struct irq_desc *desc = irq_to_desc(irq);
struct irq_chip *chip;
if (!desc)
continue;
chip = irq_desc_get_chip(desc);
if (chip && chip->irq_startup) {
raw_spin_lock_irqsave(&desc->lock, flags);
chip->irq_startup(&desc->irq_data);
raw_spin_unlock_irqrestore(&desc->lock, flags);
}
}
}
/* this is not called anywhere currently */
static void iseries_shutdown_IRQ(struct irq_data *d)
{
u32 bus, dev_id, function, mask;
const u32 sub_bus = 0;
unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
/* irq should be locked by the caller */
bus = REAL_IRQ_TO_BUS(rirq);
function = REAL_IRQ_TO_FUNC(rirq);
dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
/* Invalidate the IRQ number in the bridge */
HvCallXm_connectBusUnit(bus, sub_bus, dev_id, 0);
/* Mask bridge interrupts in the FISR */
mask = 0x01010000 << function;
HvCallPci_maskFisr(bus, sub_bus, dev_id, mask);
}
/*
* This will be called by device drivers (via disable_IRQ)
* to disable INTA in the bridge interrupt status register.
*/
static void iseries_disable_IRQ(struct irq_data *d)
{
u32 bus, dev_id, function, mask;
const u32 sub_bus = 0;
unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
/* The IRQ has already been locked by the caller */
bus = REAL_IRQ_TO_BUS(rirq);
function = REAL_IRQ_TO_FUNC(rirq);
dev_id = (REAL_IRQ_TO_IDSEL(rirq) << 4) + function;
/* Mask secondary INTA */
mask = 0x80000000;
HvCallPci_maskInterrupts(bus, sub_bus, dev_id, mask);
}
static void iseries_end_IRQ(struct irq_data *d)
{
unsigned int rirq = (unsigned int)irqd_to_hwirq(d);
HvCallPci_eoi(REAL_IRQ_TO_BUS(rirq), REAL_IRQ_TO_SUBBUS(rirq),
(REAL_IRQ_TO_IDSEL(rirq) << 4) + REAL_IRQ_TO_FUNC(rirq));
}
static struct irq_chip iseries_pic = {
.name = "iSeries",
.irq_startup = iseries_startup_IRQ,
.irq_shutdown = iseries_shutdown_IRQ,
.irq_unmask = iseries_enable_IRQ,
.irq_mask = iseries_disable_IRQ,
.irq_eoi = iseries_end_IRQ
};
/*
* This is called out of iSeries_scan_slot to allocate an IRQ for an EADS slot
* It calculates the irq value for the slot.
* Note that sub_bus is always 0 (at the moment at least).
*/
int __init iSeries_allocate_IRQ(HvBusNumber bus,
HvSubBusNumber sub_bus, u32 bsubbus)
{
unsigned int realirq;
u8 idsel = ISERIES_GET_DEVICE_FROM_SUBBUS(bsubbus);
u8 function = ISERIES_GET_FUNCTION_FROM_SUBBUS(bsubbus);
realirq = (((((sub_bus << 8) + (bus - 1)) << 3) + (idsel - 1)) << 3)
+ function;
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
return irq_create_mapping(NULL, realirq);
}
#endif /* CONFIG_PCI */
/*
* Get the next pending IRQ.
*/
unsigned int iSeries_get_irq(void)
{
2006-07-03 19:36:01 +08:00
int irq = NO_IRQ_IGNORE;
#ifdef CONFIG_SMP
if (get_lppaca()->int_dword.fields.ipi_cnt) {
get_lppaca()->int_dword.fields.ipi_cnt = 0;
powerpc: Consolidate ipi message mux and demux Consolidate the mux and demux of ipi messages into smp.c and call a new smp_ops callback to actually trigger the ipi. The powerpc architecture code is optimised for having 4 distinct ipi triggers, which are mapped to 4 distinct messages (ipi many, ipi single, scheduler ipi, and enter debugger). However, several interrupt controllers only provide a single software triggered interrupt that can be delivered to each cpu. To resolve this limitation, each smp_ops implementation created a per-cpu variable that is manipulated with atomic bitops. Since these lines will be contended they are optimialy marked as shared_aligned and take a full cache line for each cpu. Distro kernels may have 2 or 3 of these in their config, each taking per-cpu space even though at most one will be in use. This consolidation removes smp_message_recv and replaces the single call actions cases with direct calls from the common message recognition loop. The complicated debugger ipi case with its muxed crash handling code is moved to debug_ipi_action which is now called from the demux code (instead of the multi-message action calling smp_message_recv). I put a call to reschedule_action to increase the likelyhood of correctly merging the anticipated scheduler_ipi() hook coming from the scheduler tree; that single required call can be inlined later. The actual message decode is a copy of the old pseries xics code with its memory barriers and cache line spacing, augmented with a per-cpu unsigned long based on the book-e doorbell code. The optional data is set via a callback from the implementation and is passed to the new cause-ipi hook along with the logical cpu number. While currently only the doorbell implemntation uses this data it should be almost zero cost to retrieve and pass it -- it adds a single register load for the argument from the same cache line to which we just completed a store and the register is dead on return from the call. I extended the data element from unsigned int to unsigned long in case some other code wanted to associate a pointer. The doorbell check_self is replaced by a call to smp_muxed_ipi_resend, conditioned on the CPU_DBELL feature. The ifdef guard could be relaxed to CONFIG_SMP but I left it with BOOKE for now. Also, the doorbell interrupt vector for book-e was not calling irq_enter and irq_exit, which throws off cpu accounting and causes code to not realize it is running in interrupt context. Add the missing calls. Signed-off-by: Milton Miller <miltonm@bga.com> Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-05-11 03:29:39 +08:00
smp_ipi_demux();
}
#endif /* CONFIG_SMP */
if (hvlpevent_is_pending())
process_hvlpevents();
#ifdef CONFIG_PCI
if (num_pending_irqs) {
spin_lock(&pending_irqs_lock);
for (irq = 0; irq < NR_IRQS; irq++) {
if (pending_irqs[irq]) {
pending_irqs[irq]--;
num_pending_irqs--;
break;
}
}
spin_unlock(&pending_irqs_lock);
if (irq >= NR_IRQS)
2006-07-03 19:36:01 +08:00
irq = NO_IRQ_IGNORE;
}
#endif
return irq;
}
2006-07-03 19:36:01 +08:00
#ifdef CONFIG_PCI
2006-07-03 19:36:01 +08:00
static int iseries_irq_host_map(struct irq_host *h, unsigned int virq,
[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 hw)
2006-07-03 19:36:01 +08:00
{
irq_set_chip_and_handler(virq, &iseries_pic, handle_fasteoi_irq);
2006-07-03 19:36:01 +08:00
return 0;
}
static int iseries_irq_host_match(struct irq_host *h, struct device_node *np)
{
/* Match all */
return 1;
}
2006-07-03 19:36:01 +08:00
static struct irq_host_ops iseries_irq_host_ops = {
.map = iseries_irq_host_map,
.match = iseries_irq_host_match,
2006-07-03 19:36:01 +08:00
};
/*
* This is called by init_IRQ. set in ppc_md.init_IRQ by iSeries_setup.c
* It must be called before the bus walk.
*/
void __init iSeries_init_IRQ(void)
{
/* Register PCI event handler and open an event path */
struct irq_host *host;
int ret;
/*
* The Hypervisor only allows us up to 256 interrupt
* sources (the irq number is passed in a u8).
*/
irq_set_virq_count(256);
/* Create irq host. No need for a revmap since HV will give us
* back our virtual irq number
*/
host = irq_alloc_host(NULL, IRQ_HOST_MAP_NOMAP, 0,
&iseries_irq_host_ops, 0);
2006-07-03 19:36:01 +08:00
BUG_ON(host == NULL);
irq_set_default_host(host);
ret = HvLpEvent_registerHandler(HvLpEvent_Type_PciIo,
&pci_event_handler);
if (ret == 0) {
ret = HvLpEvent_openPath(HvLpEvent_Type_PciIo, 0);
if (ret != 0)
printk(KERN_ERR "iseries_init_IRQ: open event path "
"failed with rc 0x%x\n", ret);
} else
printk(KERN_ERR "iseries_init_IRQ: register handler "
"failed with rc 0x%x\n", ret);
}
#endif /* CONFIG_PCI */