linux/kernel/irq/proc.c

171 lines
3.7 KiB
C
Raw Normal View History

/*
* linux/kernel/irq/proc.c
*
* Copyright (C) 1992, 1998-2004 Linus Torvalds, Ingo Molnar
*
* This file contains the /proc/irq/ handling code.
*/
#include <linux/irq.h>
#include <linux/proc_fs.h>
#include <linux/interrupt.h>
#include "internals.h"
static struct proc_dir_entry *root_irq_dir;
#ifdef CONFIG_SMP
[PATCH] x86/x86_64: deferred handling of writes to /proc/irqxx/smp_affinity When handling writes to /proc/irq, current code is re-programming rte entries directly. This is not recommended and could potentially cause chipset's to lockup, or cause missing interrupts. CONFIG_IRQ_BALANCE does this correctly, where it re-programs only when the interrupt is pending. The same needs to be done for /proc/irq handling as well. Otherwise user space irq balancers are really not doing the right thing. - Changed pending_irq_balance_cpumask to pending_irq_migrate_cpumask for lack of a generic name. - added move_irq out of IRQ_BALANCE, and added this same to X86_64 - Added new proc handler for write, so we can do deferred write at irq handling time. - Display of /proc/irq/XX/smp_affinity used to display CPU_MASKALL, instead it now shows only active cpu masks, or exactly what was set. - Provided a common move_irq implementation, instead of duplicating when using generic irq framework. Tested on i386/x86_64 and ia64 with CONFIG_PCI_MSI turned on and off. Tested UP builds as well. MSI testing: tbd: I have cards, need to look for a x-over cable, although I did test an earlier version of this patch. Will test in a couple days. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Acked-by: Zwane Mwaikambo <zwane@holomorphy.com> Grudgingly-acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Coywolf Qi Hunt <coywolf@lovecn.org> Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-07 06:16:15 +08:00
#ifdef CONFIG_GENERIC_PENDING_IRQ
void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val)
{
set_balance_irq_affinity(irq, mask_val);
[PATCH] x86/x86_64: deferred handling of writes to /proc/irqxx/smp_affinity When handling writes to /proc/irq, current code is re-programming rte entries directly. This is not recommended and could potentially cause chipset's to lockup, or cause missing interrupts. CONFIG_IRQ_BALANCE does this correctly, where it re-programs only when the interrupt is pending. The same needs to be done for /proc/irq handling as well. Otherwise user space irq balancers are really not doing the right thing. - Changed pending_irq_balance_cpumask to pending_irq_migrate_cpumask for lack of a generic name. - added move_irq out of IRQ_BALANCE, and added this same to X86_64 - Added new proc handler for write, so we can do deferred write at irq handling time. - Display of /proc/irq/XX/smp_affinity used to display CPU_MASKALL, instead it now shows only active cpu masks, or exactly what was set. - Provided a common move_irq implementation, instead of duplicating when using generic irq framework. Tested on i386/x86_64 and ia64 with CONFIG_PCI_MSI turned on and off. Tested UP builds as well. MSI testing: tbd: I have cards, need to look for a x-over cable, although I did test an earlier version of this patch. Will test in a couple days. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Acked-by: Zwane Mwaikambo <zwane@holomorphy.com> Grudgingly-acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Coywolf Qi Hunt <coywolf@lovecn.org> Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-07 06:16:15 +08:00
/*
* Save these away for later use. Re-progam when the
* interrupt is pending
*/
set_pending_irq(irq, mask_val);
}
#else
void proc_set_irq_affinity(unsigned int irq, cpumask_t mask_val)
{
set_balance_irq_affinity(irq, mask_val);
irq_desc[irq].affinity = mask_val;
[PATCH] genirq: rename desc->handler to desc->chip This patch-queue improves the generic IRQ layer to be truly generic, by adding various abstractions and features to it, without impacting existing functionality. While the queue can be best described as "fix and improve everything in the generic IRQ layer that we could think of", and thus it consists of many smaller features and lots of cleanups, the one feature that stands out most is the new 'irq chip' abstraction. The irq-chip abstraction is about describing and coding and IRQ controller driver by mapping its raw hardware capabilities [and quirks, if needed] in a straightforward way, without having to think about "IRQ flow" (level/edge/etc.) type of details. This stands in contrast with the current 'irq-type' model of genirq architectures, which 'mixes' raw hardware capabilities with 'flow' details. The patchset supports both types of irq controller designs at once, and converts i386 and x86_64 to the new irq-chip design. As a bonus side-effect of the irq-chip approach, chained interrupt controllers (master/slave PIC constructs, etc.) are now supported by design as well. The end result of this patchset intends to be simpler architecture-level code and more consolidation between architectures. We reused many bits of code and many concepts from Russell King's ARM IRQ layer, the merging of which was one of the motivations for this patchset. This patch: rename desc->handler to desc->chip. Originally i did not want to do this, because it's a big patch. But having both "desc->handler", "desc->handle_irq" and "action->handler" caused a large degree of confusion and made the code appear alot less clean than it truly is. I have also attempted a dual approach as well by introducing a desc->chip alias - but that just wasnt robust enough and broke frequently. So lets get over with this quickly. The conversion was done automatically via scripts and converts all the code in the kernel. This renaming patch is the first one amongst the patches, so that the remaining patches can stay flexible and can be merged and split up without having some big monolithic patch act as a merge barrier. [akpm@osdl.org: build fix] [akpm@osdl.org: another build fix] Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-29 17:24:36 +08:00
irq_desc[irq].chip->set_affinity(irq, mask_val);
}
[PATCH] x86/x86_64: deferred handling of writes to /proc/irqxx/smp_affinity When handling writes to /proc/irq, current code is re-programming rte entries directly. This is not recommended and could potentially cause chipset's to lockup, or cause missing interrupts. CONFIG_IRQ_BALANCE does this correctly, where it re-programs only when the interrupt is pending. The same needs to be done for /proc/irq handling as well. Otherwise user space irq balancers are really not doing the right thing. - Changed pending_irq_balance_cpumask to pending_irq_migrate_cpumask for lack of a generic name. - added move_irq out of IRQ_BALANCE, and added this same to X86_64 - Added new proc handler for write, so we can do deferred write at irq handling time. - Display of /proc/irq/XX/smp_affinity used to display CPU_MASKALL, instead it now shows only active cpu masks, or exactly what was set. - Provided a common move_irq implementation, instead of duplicating when using generic irq framework. Tested on i386/x86_64 and ia64 with CONFIG_PCI_MSI turned on and off. Tested UP builds as well. MSI testing: tbd: I have cards, need to look for a x-over cable, although I did test an earlier version of this patch. Will test in a couple days. Signed-off-by: Ashok Raj <ashok.raj@intel.com> Acked-by: Zwane Mwaikambo <zwane@holomorphy.com> Grudgingly-acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Coywolf Qi Hunt <coywolf@lovecn.org> Signed-off-by: Ashok Raj <ashok.raj@intel.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-07 06:16:15 +08:00
#endif
static int irq_affinity_read_proc(char *page, char **start, off_t off,
int count, int *eof, void *data)
{
int len = cpumask_scnprintf(page, count, irq_desc[(long)data].affinity);
if (count - len < 2)
return -EINVAL;
len += sprintf(page + len, "\n");
return len;
}
int no_irq_affinity;
static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
unsigned long count, void *data)
{
unsigned int irq = (int)(long)data, full_count = count, err;
cpumask_t new_value, tmp;
[PATCH] CPEI gets warning at kernel/irq/migration.c:27/move_masked_irq() While running my MCA test (hardware error injection) on 2.6.19, I got some warning like following: > BUG: warning at kernel/irq/migration.c:27/move_masked_irq() > > Call Trace: > [<a000000100013d20>] show_stack+0x40/0xa0 > sp=e00000006b2578d0 bsp=e00000006b2510b0 > [<a000000100013db0>] dump_stack+0x30/0x60 > sp=e00000006b257aa0 bsp=e00000006b251098 > [<a0000001000de430>] move_masked_irq+0xb0/0x240 > sp=e00000006b257aa0 bsp=e00000006b251070 > [<a0000001000de6a0>] move_native_irq+0xe0/0x180 > sp=e00000006b257aa0 bsp=e00000006b251040 > [<a00000010004ff50>] iosapic_end_level_irq+0x30/0xe0 > sp=e00000006b257aa0 bsp=e00000006b251020 > [<a0000001000d94d0>] __do_IRQ+0x170/0x400 > sp=e00000006b257aa0 bsp=e00000006b250fd8 > [<a0000001000116f0>] ia64_handle_irq+0x1b0/0x260 > sp=e00000006b257aa0 bsp=e00000006b250fa8 > [<a00000010000c3a0>] ia64_leave_kernel+0x0/0x280 > sp=e00000006b257aa0 bsp=e00000006b250fa8 > [<a000000100690cf0>] _spin_unlock_irqrestore+0x30/0x60 > sp=e00000006b257c70 bsp=e00000006b250f90 It comes from: [kernel/irq/migration.c] 26 if (CHECK_IRQ_PER_CPU(desc->status)) { 27 WARN_ON(1); 28 return; 29 } By putting some printk in kernel, I found that irqbalance is trying to move CPEI which is handled as PER_CPU irq. That's why. CPEI(Corrected Platform Error Interrupt) is ia64 specific irq, is allowed to pin to particular processor which selected by the platform, and even it is PER_CPU but it has set_affinity handler (=iosapic_set_affinity) as same as other IO-SAPIC-level interrupts. (I don't know why, but I guess that there would be typical situation where the handler for migration is needed, such as hotplug - the processor going to be offline/hot-removed.) To shut up this warning, there are 2 way at least: a) fix CPEI stuff b) prohibit setting affinity to PER_CPU irq I'm not sure what stuff of CPEI need to be fixed, but I think that returning error to attempting move PER_CPU irq is useful for all applications since it will never work. Following small patch takes b) style. It works, the warning disappeared and irqbalance still runs well. Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com> Cc: Arjan van de Ven <arjan@infradead.org> Acked-by: Ingo Molnar <mingo@elte.hu> Acked-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-08 18:35:58 +08:00
if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
CHECK_IRQ_PER_CPU(irq_desc[irq].status))
return -EIO;
err = cpumask_parse_user(buffer, count, new_value);
if (err)
return err;
/*
* Do not allow disabling IRQs completely - it's a too easy
* way to make the system unusable accidentally :-) At least
* one online CPU still has to be targeted.
*/
cpus_and(tmp, new_value, cpu_online_map);
if (cpus_empty(tmp))
/* Special case for empty set - allow the architecture
code to set default SMP affinity. */
return select_smp_affinity(irq) ? -EINVAL : full_count;
proc_set_irq_affinity(irq, new_value);
return full_count;
}
#endif
#define MAX_NAMELEN 128
static int name_unique(unsigned int irq, struct irqaction *new_action)
{
struct irq_desc *desc = irq_desc + irq;
struct irqaction *action;
for (action = desc->action ; action; action = action->next)
if ((action != new_action) && action->name &&
!strcmp(new_action->name, action->name))
return 0;
return 1;
}
void register_handler_proc(unsigned int irq, struct irqaction *action)
{
char name [MAX_NAMELEN];
if (!irq_desc[irq].dir || action->dir || !action->name ||
!name_unique(irq, action))
return;
memset(name, 0, MAX_NAMELEN);
snprintf(name, MAX_NAMELEN, "%s", action->name);
/* create /proc/irq/1234/handler/ */
action->dir = proc_mkdir(name, irq_desc[irq].dir);
}
#undef MAX_NAMELEN
#define MAX_NAMELEN 10
void register_irq_proc(unsigned int irq)
{
char name [MAX_NAMELEN];
if (!root_irq_dir ||
(irq_desc[irq].chip == &no_irq_chip) ||
irq_desc[irq].dir)
return;
memset(name, 0, MAX_NAMELEN);
sprintf(name, "%d", irq);
/* create /proc/irq/1234 */
irq_desc[irq].dir = proc_mkdir(name, root_irq_dir);
#ifdef CONFIG_SMP
{
struct proc_dir_entry *entry;
/* create /proc/irq/<irq>/smp_affinity */
entry = create_proc_entry("smp_affinity", 0600, irq_desc[irq].dir);
if (entry) {
entry->data = (void *)(long)irq;
entry->read_proc = irq_affinity_read_proc;
entry->write_proc = irq_affinity_write_proc;
}
}
#endif
}
#undef MAX_NAMELEN
void unregister_handler_proc(unsigned int irq, struct irqaction *action)
{
if (action->dir)
remove_proc_entry(action->dir->name, irq_desc[irq].dir);
}
void init_irq_proc(void)
{
int i;
/* create /proc/irq */
root_irq_dir = proc_mkdir("irq", NULL);
if (!root_irq_dir)
return;
/*
* Create entries for all existing IRQs.
*/
for (i = 0; i < NR_IRQS; i++)
register_irq_proc(i);
}