From: Bjorn Helgaas <bjorn.helgaas@hp.com>
To: linux-ia64@vger.kernel.org
Subject: Re: [PATCH] New CMC/CPE polling
Date: Fri, 08 Aug 2003 18:39:54 +0000 [thread overview]
Message-ID: <marc-linux-ia64-106036802216384@msgid-missing> (raw)
In-Reply-To: <marc-linux-ia64-105969308328993@msgid-missing>
On Thursday 31 July 2003 5:06 pm, Alex Williamson wrote:
> Here's a redesign of the CMC and CPE polling for both 2.6.0-test2
> and 2.4.21. This is roughly the same design I requested comment on
> a while back (BTW, nobody commented...). Basically, rather than
> flooding all the cpus in parallel, I used some low priority interrupts
> to cascade through the cpus. This should be much more scalable. I
> also added a new feature of enabling interrupts for the CMC and CPE
> handlers. The SAL spec claims these functions are SMP safe and
> re-entrant and even recommends that the corrected error handlers
> should run with interrupts enabled. It works on HP boxes, others
> might want to double check that their firmware adheres to the spec.
> The combination of these things should keep polling from impacting
> system response time. I tried to keep the 2.6 and 2.4 code as similar
> as possible, so I also backported __ffs() to 2.4. Feedback and bug
> reports welcome. Thanks,
I applied this for 2.4. I also applied the following patch to fix
some old comments that were slightly misleading (CMC's and CPE's
have already been "corrected"; they're not "correctable".)
#### AUTHOR bjorn.helgaas@hp.com
#### COMMENT START
### Comments for ChangeSet
ia64: Comment changes to fix "correctable" usage.
### Comments for arch/ia64/kernel/acpi.c
Fix usage ("corrected" machine checks and platform errors, not "correctable").
### Comments for include/asm-ia64/hw_irq.h
Fix usage ("corrected" machine checks and platform errors, not "correctable").
### Comments for include/asm-ia64/processor.h
Fix usage ("corrected" machine checks and platform errors, not "correctable").
#### COMMENT END
# This is a BitKeeper generated patch for the following project:
# Project Name: Linux kernel tree
# This patch format is intended for GNU patch command version 2.5 or higher.
# This patch includes the following deltas:
# ChangeSet 1.1075 -> 1.1076
# include/asm-ia64/processor.h 1.22 -> 1.23
# include/asm-ia64/hw_irq.h 1.5 -> 1.6
# arch/ia64/kernel/acpi.c 1.22 -> 1.23
#
# The following is the BitKeeper ChangeSet Log
# --------------------------------------------
# 03/08/08 bjorn.helgaas@hp.com 1.1076
# ia64: Comment changes to fix "correctable" usage.
# --------------------------------------------
#
diff -Nru a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
--- a/arch/ia64/kernel/acpi.c Fri Aug 8 13:33:51 2003
+++ b/arch/ia64/kernel/acpi.c Fri Aug 8 13:33:51 2003
@@ -217,7 +217,7 @@
int vector = -1;
if (int_type < ACPI_MAX_PLATFORM_INTERRUPTS) {
- /* correctable platform error interrupt */
+ /* corrected platform error interrupt */
vector = platform_intr_list[int_type];
} else
printk(KERN_ERR "acpi_request_vector(): invalid interrupt type\n");
diff -Nru a/include/asm-ia64/hw_irq.h b/include/asm-ia64/hw_irq.h
--- a/include/asm-ia64/hw_irq.h Fri Aug 8 13:33:51 2003
+++ b/include/asm-ia64/hw_irq.h Fri Aug 8 13:33:51 2003
@@ -38,9 +38,9 @@
* Vectors 0x10-0x1f are used for low priority interrupts, e.g. CMCI.
*/
#define IA64_CPEP_VECTOR 0x1c /* corrected platform error polling vector */
-#define IA64_CMCP_VECTOR 0x1d /* correctable machine-check polling vector */
+#define IA64_CMCP_VECTOR 0x1d /* corrected machine-check polling vector */
#define IA64_CPE_VECTOR 0x1e /* corrected platform error interrupt vector */
-#define IA64_CMC_VECTOR 0x1f /* correctable machine-check interrupt vector */
+#define IA64_CMC_VECTOR 0x1f /* corrected machine-check interrupt vector */
/*
* Vectors 0x20-0x2f are reserved for legacy ISA IRQs.
*/
diff -Nru a/include/asm-ia64/processor.h b/include/asm-ia64/processor.h
--- a/include/asm-ia64/processor.h Fri Aug 8 13:33:51 2003
+++ b/include/asm-ia64/processor.h Fri Aug 8 13:33:51 2003
@@ -770,18 +770,12 @@
#define init_task (init_task_union.task)
#define init_stack (init_task_union.stack)
-/*
- * Set the correctable machine check vector register
- */
static inline void
ia64_set_cmcv (__u64 val)
{
asm volatile ("mov cr.cmcv=%0" :: "r"(val) : "memory");
}
-/*
- * Read the correctable machine check vector register
- */
static inline __u64
ia64_get_cmcv (void)
{
prev parent reply other threads:[~2003-08-08 18:39 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-07-31 23:06 [PATCH] New CMC/CPE polling Alex Williamson
2003-08-01 6:34 ` David Mosberger
2003-08-01 14:20 ` Alex Williamson
2003-08-04 18:26 ` Luck, Tony
2003-08-04 18:49 ` Alex Williamson
2003-08-04 20:43 ` Luck, Tony
2003-08-04 21:15 ` Alex Williamson
2003-08-04 21:53 ` Luck, Tony
2003-08-04 23:09 ` David Mosberger
2003-08-08 18:39 ` Bjorn Helgaas [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=marc-linux-ia64-106036802216384@msgid-missing \
--to=bjorn.helgaas@hp.com \
--cc=linux-ia64@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox