From: Andi Kleen <ak@suse.de>
To: Ingo Molnar <mingo@elte.hu>,
Suresh Siddha <suresh.b.siddha@intel.com>,
Andi Kleen <ak@suse.de>, "Li, Shaohua" <shaohua.li@intel.com>,
"Eric W. Biederman" <ebiederm@xmission.com>,
linux-kernel@vger.kernel.org, patches@x86-64.org
Subject: [PATCH] [4/35] x86_64: optimize & fix APIC mode setup
Date: Sat, 28 Apr 2007 19:52:28 +0200 (CEST) [thread overview]
Message-ID: <20070428175228.1759F151F2@wotan.suse.de> (raw)
In-Reply-To: <20070428752.712152000@suse.de>
From: Ingo Molnar <mingo@elte.hu>
Fix a couple of inconsistencies/problems I found while reviewing the x86_64
genapic code (when I was chasing mysterious eth0 timeouts that would only
trigger if CPU_HOTPLUG is enabled):
- AMD systems defaulted to the slower flat-physical mode instead
of the flat-logical mode. The only restriction on AMD systems
is that they should not use clustered APIC mode.
- removed the CPU hotplug hacks, switching the default for small
systems back from phys-flat to logical-flat. The switching to logical
flat mode on small systems fixed sporadic ethernet driver timeouts i
was getting on a dual-core Athlon64 system:
NETDEV WATCHDOG: eth0: transmit timed out
eth0: Transmit timeout, status 0c 0005 c07f media 80.
eth0: Tx queue start entry 32 dirty entry 28.
eth0: Tx descriptor 0 is 0008a04a. (queue head)
eth0: Tx descriptor 1 is 0008a04a.
eth0: Tx descriptor 2 is 0008a04a.
eth0: Tx descriptor 3 is 0008a04a.
eth0: link up, 100Mbps, full-duplex, lpa 0xC5E1
- The use of '<= 8' was a bug by itself (the valid APIC ids
for logical flat mode go from 0 to 7, not 0 to 8). The new logic
is to use logical flat mode on both AMD and Intel systems, and
to only switch to physical mode when logical mode cannot be used.
If CPU hotplug is racy wrt. APIC shutdown then CPU hotplug needs
fixing, not the whole IRQ system be made inconsistent and slowed
down.
- minor cleanups: simplified some code constructs
build & booted on a couple of AMD and Intel SMP systems.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Andi Kleen <ak@suse.de>
Cc: "Li, Shaohua" <shaohua.li@intel.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---
arch/x86_64/kernel/genapic.c | 39 +++++++++++++++------------------------
1 file changed, 15 insertions(+), 24 deletions(-)
Index: linux/arch/x86_64/kernel/genapic.c
===================================================================
--- linux.orig/arch/x86_64/kernel/genapic.c
+++ linux/arch/x86_64/kernel/genapic.c
@@ -32,21 +32,20 @@ extern struct genapic apic_cluster;
extern struct genapic apic_flat;
extern struct genapic apic_physflat;
-struct genapic *genapic = &apic_flat;
-
+struct genapic __read_mostly *genapic = &apic_flat;
/*
* Check the APIC IDs in bios_cpu_apicid and choose the APIC mode.
*/
void __init clustered_apic_check(void)
{
- long i;
+ int i;
u8 clusters, max_cluster;
u8 id;
u8 cluster_cnt[NUM_APIC_CLUSTERS];
int max_apic = 0;
-#if defined(CONFIG_ACPI)
+#ifdef CONFIG_ACPI
/*
* Some x86_64 machines use physical APIC mode regardless of how many
* procs/clusters are present (x86_64 ES7000 is an example).
@@ -68,20 +67,17 @@ void __init clustered_apic_check(void)
cluster_cnt[APIC_CLUSTERID(id)]++;
}
- /* Don't use clustered mode on AMD platforms. */
+ /*
+ * Don't use clustered mode on AMD platforms, default
+ * to flat logical mode.
+ */
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
- genapic = &apic_physflat;
-#ifndef CONFIG_HOTPLUG_CPU
- /* In the CPU hotplug case we cannot use broadcast mode
- because that opens a race when a CPU is removed.
- Stay at physflat mode in this case.
- It is bad to do this unconditionally though. Once
- we have ACPI platform support for CPU hotplug
- we should detect hotplug capablity from ACPI tables and
- only do this when really needed. -AK */
- if (max_apic <= 8)
- genapic = &apic_flat;
-#endif
+ /*
+ * Switch to physical flat mode if more than 8 APICs
+ * (In the case of 8 CPUs APIC ID goes from 0 to 7):
+ */
+ if (max_apic >= 8)
+ genapic = &apic_physflat;
goto print;
}
@@ -103,14 +99,9 @@ void __init clustered_apic_check(void)
* (We don't use lowest priority delivery + HW APIC IRQ steering, so
* can ignore the clustered logical case and go straight to physical.)
*/
- if (clusters <= 1 && max_cluster <= 8 && cluster_cnt[0] == max_cluster) {
-#ifdef CONFIG_HOTPLUG_CPU
- /* Don't use APIC shortcuts in CPU hotplug to avoid races */
- genapic = &apic_physflat;
-#else
+ if (clusters <= 1 && max_cluster <= 8 && cluster_cnt[0] == max_cluster)
genapic = &apic_flat;
-#endif
- } else
+ else
genapic = &apic_cluster;
print:
next prev parent reply other threads:[~2007-04-28 18:15 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-28 17:52 [PATCH] [0/35] Some x86 2.6.22 candidate patches for review Andi Kleen
2007-04-28 17:52 ` [PATCH] [1/35] i386: revert i386-fix-the-verify_quirk_intel_irqbalance Andi Kleen
2007-04-28 17:52 ` [PATCH] [2/35] x86_64: revert x86_64-mm-add-genapic_force Andi Kleen
2007-04-28 17:52 ` [PATCH] [3/35] x86: revert x86_64-mm-fix-the-irqbalance-quirk-for-e7320-e7520-e7525 Andi Kleen
2007-04-28 17:52 ` Andi Kleen [this message]
2007-04-28 17:52 ` [PATCH] [5/35] x86_64: always use physical delivery mode on > 8 CPUs Andi Kleen
2007-04-28 17:52 ` [PATCH] [6/35] x86_64: remove clustered APIC mode Andi Kleen
2007-04-28 17:52 ` [PATCH] [7/35] x86: default to physical mode on hotplug CPU kernels Andi Kleen
2007-04-28 17:52 ` [PATCH] [8/35] x86_64: a memcpy that tries to reduce cache pressure Andi Kleen
2007-04-30 7:26 ` [patches] [PATCH] [8/35] x86_64: a memcpy that tries to reducecache pressure Jan Beulich
2007-04-30 9:04 ` Andi Kleen
2007-04-30 16:14 ` Bryan O'Sullivan
2007-04-30 16:25 ` Andi Kleen
2007-04-28 17:52 ` [PATCH] [9/35] i386: adjustments to page table dump during oops (v4) Andi Kleen
2007-04-28 17:52 ` [PATCH] [10/35] x86: adjust inclusion of asm/fixmap.h Andi Kleen
2007-04-28 17:52 ` [PATCH] [11/35] x86_64: adjust inclusion of asm/vsyscall32.h Andi Kleen
2007-04-28 17:52 ` [PATCH] [12/35] x86: consolidate smp_send_stop() Andi Kleen
2007-04-28 17:52 ` [PATCH] [13/35] i386: No need to use -traditional for processing asm in i386/kernel/ Andi Kleen
2007-04-28 17:52 ` [PATCH] [14/35] i386: mtrr range check correction Andi Kleen
2007-04-28 17:52 ` [PATCH] [15/35] i386: pit_latch_buggy has no effect Andi Kleen
2007-04-28 17:52 ` [PATCH] [16/35] i386: Add an option for the VIA C7 which sets appropriate L1 cache Andi Kleen
2007-04-28 18:08 ` Jeff Garzik
2007-04-28 18:28 ` Dave Jones
2007-04-28 17:52 ` [PATCH] [17/35] i386: probe_roms() cleanup Andi Kleen
2007-04-28 17:52 ` [PATCH] [18/35] x86_64: a few missing entry.S annotations Andi Kleen
2007-04-28 17:52 ` [PATCH] [19/35] i386: Add dwarf2 annotations to *_user and checksum functions Andi Kleen
2007-04-28 17:52 ` [PATCH] [20/35] x86: Fix i386 and x86_64 fault information pollution Andi Kleen
2007-04-28 17:52 ` [PATCH] [21/35] x86_64: Some cleanup in time.c Andi Kleen
2007-04-28 17:52 ` [PATCH] [22/35] i386: i386 make NMI use PERFCTR1 for architectural perfmon (take 2) Andi Kleen
2007-04-28 17:52 ` [PATCH] [23/35] x86_64: x86_64 " Andi Kleen
2007-04-28 17:52 ` [PATCH] [24/35] i386: Add __init to probe_bigsmp Andi Kleen
2007-04-28 17:52 ` [PATCH] [25/35] i386: Change sysenter_setup to __cpuinit & improve __INIT, __INITDATA Andi Kleen
2007-04-28 17:52 ` [PATCH] [26/35] x86_64: Correct max number of CPUs in Kconfig Andi Kleen
2007-04-28 17:52 ` [PATCH] [27/35] i386: Support Oprofile for AMD Family 10 CPUs Andi Kleen
2007-04-28 17:52 ` [PATCH] [28/35] x86: Drop cc-options call for all options supported in gcc 3.2+ Andi Kleen
2007-04-28 17:52 ` [PATCH] [29/35] i386: Update __copy_to_user_inatomic linuxdoc description Andi Kleen
2007-04-28 17:52 ` [PATCH] [30/35] i386: clean up mach_reboot_fixups Andi Kleen
2007-04-28 17:52 ` [PATCH] [31/35] i386: Fix usage of -mtune when X86_GENERIC=y or CONFIG_MCORE2=y Andi Kleen
2007-04-28 17:52 ` [PATCH] [32/35] x86_64: Remove unused set_seg_base Andi Kleen
2007-04-28 17:52 ` [PATCH] [33/35] x86_64: Remove duplicated code for reading control registers Andi Kleen
2007-04-28 17:53 ` [PATCH] [34/35] x86_64: fix cpu MHz reporting on constant_tsc cpus Andi Kleen
2007-04-28 17:53 ` [PATCH] [35/35] i386: Simplify smp_call_function*() by using common implementation Andi Kleen
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=20070428175228.1759F151F2@wotan.suse.de \
--to=ak@suse.de \
--cc=ebiederm@xmission.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=patches@x86-64.org \
--cc=shaohua.li@intel.com \
--cc=suresh.b.siddha@intel.com \
/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
Powered by JetHome