2005-11-03 17:50:04 -07:00
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
*
|
|
|
|
* Copyright (c) 2005 Linas Vepstas <linas@linas.org>
|
|
|
|
*/
|
|
|
|
|
2006-04-18 22:05:21 -06:00
|
|
|
#include <linux/delay.h>
|
2005-11-03 17:50:04 -07:00
|
|
|
#include <linux/list.h>
|
2011-05-27 12:25:11 -06:00
|
|
|
#include <linux/sched.h>
|
2013-06-19 23:21:00 -06:00
|
|
|
#include <linux/semaphore.h>
|
2005-11-03 17:50:04 -07:00
|
|
|
#include <linux/pci.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 02:04:11 -06:00
|
|
|
#include <linux/slab.h>
|
2012-10-02 13:32:10 -06:00
|
|
|
#include <linux/kthread.h>
|
2005-11-03 17:50:04 -07:00
|
|
|
#include <asm/eeh_event.h>
|
2005-11-03 17:52:49 -07:00
|
|
|
#include <asm/ppc-pci.h>
|
2005-11-03 17:50:04 -07:00
|
|
|
|
|
|
|
/** Overview:
|
|
|
|
* EEH error states may be detected within exception handlers;
|
|
|
|
* however, the recovery processing needs to occur asynchronously
|
|
|
|
* in a normal kernel context and not an interrupt context.
|
|
|
|
* This pair of routines creates an event and queues it onto a
|
|
|
|
* work-queue, where a worker thread can drive recovery.
|
|
|
|
*/
|
|
|
|
|
2006-06-27 03:53:55 -06:00
|
|
|
static DEFINE_SPINLOCK(eeh_eventlist_lock);
|
2013-06-19 23:21:00 -06:00
|
|
|
static struct semaphore eeh_eventlist_sem;
|
2005-11-03 17:50:04 -07:00
|
|
|
LIST_HEAD(eeh_eventlist);
|
2006-03-29 14:29:18 -07:00
|
|
|
|
2005-11-03 17:50:04 -07:00
|
|
|
/**
|
2012-02-27 13:04:02 -07:00
|
|
|
* eeh_event_handler - Dispatch EEH events.
|
2005-11-03 17:50:04 -07:00
|
|
|
* @dummy - unused
|
2006-03-29 14:29:18 -07:00
|
|
|
*
|
|
|
|
* The detection of a frozen slot can occur inside an interrupt,
|
|
|
|
* where it can be hard to do anything about it. The goal of this
|
|
|
|
* routine is to pull these detection events out of the context
|
|
|
|
* of the interrupt handler, and re-dispatch them for processing
|
|
|
|
* at a later time in a normal context.
|
2005-11-03 17:50:04 -07:00
|
|
|
*/
|
|
|
|
static int eeh_event_handler(void * dummy)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
2012-02-27 13:04:08 -07:00
|
|
|
struct eeh_event *event;
|
2012-09-07 16:44:18 -06:00
|
|
|
struct eeh_pe *pe;
|
2005-11-03 17:50:04 -07:00
|
|
|
|
2013-06-19 23:21:00 -06:00
|
|
|
while (!kthread_should_stop()) {
|
2013-06-25 00:35:28 -06:00
|
|
|
if (down_interruptible(&eeh_eventlist_sem))
|
|
|
|
break;
|
2013-06-19 23:21:00 -06:00
|
|
|
|
|
|
|
/* Fetch EEH event from the queue */
|
|
|
|
spin_lock_irqsave(&eeh_eventlist_lock, flags);
|
|
|
|
event = NULL;
|
|
|
|
if (!list_empty(&eeh_eventlist)) {
|
|
|
|
event = list_entry(eeh_eventlist.next,
|
|
|
|
struct eeh_event, list);
|
|
|
|
list_del(&event->list);
|
|
|
|
}
|
|
|
|
spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
|
|
|
|
if (!event)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
/* We might have event without binding PE */
|
|
|
|
pe = event->pe;
|
|
|
|
if (pe) {
|
|
|
|
eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
|
2013-11-11 23:49:22 -07:00
|
|
|
if (pe->type & EEH_PE_PHB)
|
|
|
|
pr_info("EEH: Detected error on PHB#%d\n",
|
|
|
|
pe->phb->global_number);
|
|
|
|
else
|
|
|
|
pr_info("EEH: Detected PCI bus error on "
|
|
|
|
"PHB#%d-PE#%x\n",
|
|
|
|
pe->phb->global_number, pe->addr);
|
2013-06-19 23:21:00 -06:00
|
|
|
eeh_handle_event(pe);
|
|
|
|
eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
|
|
|
|
} else {
|
|
|
|
eeh_handle_event(NULL);
|
|
|
|
}
|
|
|
|
|
|
|
|
kfree(event);
|
2005-11-03 17:50:04 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2013-06-19 23:21:00 -06:00
|
|
|
* eeh_event_init - Start kernel thread to handle EEH events
|
2012-02-27 13:04:02 -07:00
|
|
|
*
|
|
|
|
* This routine is called to start the kernel thread for processing
|
|
|
|
* EEH event.
|
2005-11-03 17:50:04 -07:00
|
|
|
*/
|
2013-06-19 23:21:00 -06:00
|
|
|
int eeh_event_init(void)
|
2005-11-03 17:50:04 -07:00
|
|
|
{
|
2013-06-19 23:21:00 -06:00
|
|
|
struct task_struct *t;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
/* Initialize semaphore */
|
|
|
|
sema_init(&eeh_eventlist_sem, 0);
|
|
|
|
|
|
|
|
t = kthread_run(eeh_event_handler, NULL, "eehd");
|
|
|
|
if (IS_ERR(t)) {
|
|
|
|
ret = PTR_ERR(t);
|
|
|
|
pr_err("%s: Failed to start EEH daemon (%d)\n",
|
|
|
|
__func__, ret);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
2005-11-03 17:50:04 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
2012-02-27 13:04:02 -07:00
|
|
|
* eeh_send_failure_event - Generate a PCI error event
|
2012-09-07 16:44:11 -06:00
|
|
|
* @pe: EEH PE
|
2005-11-03 17:50:04 -07:00
|
|
|
*
|
|
|
|
* This routine can be called within an interrupt context;
|
|
|
|
* the actual event will be delivered in a normal context
|
|
|
|
* (from a workqueue).
|
|
|
|
*/
|
2012-09-07 16:44:11 -06:00
|
|
|
int eeh_send_failure_event(struct eeh_pe *pe)
|
2005-11-03 17:50:04 -07:00
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
struct eeh_event *event;
|
|
|
|
|
2012-09-07 16:44:11 -06:00
|
|
|
event = kzalloc(sizeof(*event), GFP_ATOMIC);
|
|
|
|
if (!event) {
|
|
|
|
pr_err("EEH: out of memory, event not handled\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
event->pe = pe;
|
2005-11-03 17:50:04 -07:00
|
|
|
|
|
|
|
/* We may or may not be called in an interrupt context */
|
|
|
|
spin_lock_irqsave(&eeh_eventlist_lock, flags);
|
|
|
|
list_add(&event->list, &eeh_eventlist);
|
|
|
|
spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
|
|
|
|
|
2013-06-19 23:21:00 -06:00
|
|
|
/* For EEH deamon to knick in */
|
|
|
|
up(&eeh_eventlist_sem);
|
2005-11-03 17:50:04 -07:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2013-06-19 23:21:02 -06:00
|
|
|
|
|
|
|
/**
|
|
|
|
* eeh_remove_event - Remove EEH event from the queue
|
|
|
|
* @pe: Event binding to the PE
|
2014-06-04 01:31:52 -06:00
|
|
|
* @force: Event will be removed unconditionally
|
2013-06-19 23:21:02 -06:00
|
|
|
*
|
|
|
|
* On PowerNV platform, we might have subsequent coming events
|
|
|
|
* is part of the former one. For that case, those subsequent
|
|
|
|
* coming events are totally duplicated and unnecessary, thus
|
|
|
|
* they should be removed.
|
|
|
|
*/
|
2014-06-04 01:31:52 -06:00
|
|
|
void eeh_remove_event(struct eeh_pe *pe, bool force)
|
2013-06-19 23:21:02 -06:00
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
struct eeh_event *event, *tmp;
|
|
|
|
|
2014-06-04 01:31:52 -06:00
|
|
|
/*
|
|
|
|
* If we have NULL PE passed in, we have dead IOC
|
|
|
|
* or we're sure we can report all existing errors
|
|
|
|
* by the caller.
|
|
|
|
*
|
|
|
|
* With "force", the event with associated PE that
|
|
|
|
* have been isolated, the event won't be removed
|
|
|
|
* to avoid event lost.
|
|
|
|
*/
|
2013-06-19 23:21:02 -06:00
|
|
|
spin_lock_irqsave(&eeh_eventlist_lock, flags);
|
|
|
|
list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) {
|
2014-06-04 01:31:52 -06:00
|
|
|
if (!force && event->pe &&
|
|
|
|
(event->pe->state & EEH_PE_ISOLATED))
|
|
|
|
continue;
|
|
|
|
|
2013-06-19 23:21:02 -06:00
|
|
|
if (!pe) {
|
|
|
|
list_del(&event->list);
|
|
|
|
kfree(event);
|
|
|
|
} else if (pe->type & EEH_PE_PHB) {
|
|
|
|
if (event->pe && event->pe->phb == pe->phb) {
|
|
|
|
list_del(&event->list);
|
|
|
|
kfree(event);
|
|
|
|
}
|
|
|
|
} else if (event->pe == pe) {
|
|
|
|
list_del(&event->list);
|
|
|
|
kfree(event);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
|
|
|
|
}
|