From: tip-bot for Daniel J Blueman <daniel@numascale-asia.com>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@redhat.com,
sp@numascale.com, jbarnes@virtuousgeek.org, tglx@linutronix.de,
daniel@numascale-asia.com, mingo@elte.hu
Subject: [tip:x86/apic] x86: Add x86_init platform override to fix up NUMA core numbering
Date: Mon, 5 Dec 2011 09:58:39 -0800 [thread overview]
Message-ID: <tip-64be4c1c2428e148de6081af235e2418e6a66dda@git.kernel.org> (raw)
In-Reply-To: <1323073238-32686-2-git-send-email-daniel@numascale-asia.com>
Commit-ID: 64be4c1c2428e148de6081af235e2418e6a66dda
Gitweb: http://git.kernel.org/tip/64be4c1c2428e148de6081af235e2418e6a66dda
Author: Daniel J Blueman <daniel@numascale-asia.com>
AuthorDate: Mon, 5 Dec 2011 16:20:37 +0800
Committer: Ingo Molnar <mingo@elte.hu>
CommitDate: Mon, 5 Dec 2011 17:17:21 +0100
x86: Add x86_init platform override to fix up NUMA core numbering
Add an x86_init vector for handling inconsistent core numbering.
This is useful for multi-fabric platforms, such as Numascale
NumaConnect.
v2:
- use struct x86_cpuinit_ops
- provide default fall-back function to warn
Signed-off-by: Daniel J Blueman <daniel@numascale-asia.com>
Cc: Steffen Persvold <sp@numascale.com>
Cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Link: http://lkml.kernel.org/r/1323073238-32686-2-git-send-email-daniel@numascale-asia.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
arch/x86/include/asm/x86_init.h | 3 +++
arch/x86/kernel/cpu/amd.c | 7 +++++++
arch/x86/kernel/cpu/common.c | 9 +++++++++
arch/x86/kernel/x86_init.c | 1 +
4 files changed, 20 insertions(+), 0 deletions(-)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 1971e65..1ac860a 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -7,6 +7,7 @@
struct mpc_bus;
struct mpc_cpu;
struct mpc_table;
+struct cpuinfo_x86;
/**
* struct x86_init_mpparse - platform specific mpparse ops
@@ -147,6 +148,7 @@ struct x86_init_ops {
*/
struct x86_cpuinit_ops {
void (*setup_percpu_clockev)(void);
+ void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
};
/**
@@ -186,5 +188,6 @@ extern struct x86_msi_ops x86_msi;
extern void x86_init_noop(void);
extern void x86_init_uint_noop(unsigned int unused);
+extern void x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node);
#endif
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 0bab2b1..ef21bdc 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -353,6 +353,13 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
if (node == NUMA_NO_NODE)
node = per_cpu(cpu_llc_id, cpu);
+ /*
+ * If core numbers are inconsistent, it's likely a multi-fabric platform,
+ * so invoke platform-specific handler
+ */
+ if (c->phys_proc_id != node)
+ x86_cpuinit.fixup_cpu_id(c, node);
+
if (!node_online(node)) {
/*
* Two possibilities here:
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index aa003b1..ad4da45 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1141,6 +1141,15 @@ static void dbg_restore_debug_regs(void)
#endif /* ! CONFIG_KGDB */
/*
+ * Prints an error where the NUMA and configured core-number mismatch and the
+ * platform didn't override this to fix it up
+ */
+void __cpuinit x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node)
+{
+ pr_err("NUMA core number %d differs from configured core number %d\n", node, c->phys_proc_id);
+}
+
+/*
* cpu_init() initializes state that is per-CPU. Some data is already
* initialized (naturally) in the bootstrap process, such as the GDT
* and IDT. We reload them nevertheless, this function acts as a
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index c1d6cd5..91f83e2 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -92,6 +92,7 @@ struct x86_init_ops x86_init __initdata = {
struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
.setup_percpu_clockev = setup_secondary_APIC_clock,
+ .fixup_cpu_id = x86_default_fixup_cpu_id,
};
static void default_nmi_init(void) { };
next prev parent reply other threads:[~2011-12-05 17:59 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-10-26 6:07 [PATCH 1/3] Add Numachip APIC support Daniel J Blueman
2011-10-26 6:07 ` [PATCH 2/3] Add multi-node boot support Daniel J Blueman
2011-10-27 7:30 ` Ingo Molnar
2011-10-27 10:46 ` Steffen Persvold
2011-10-27 11:38 ` Ingo Molnar
2011-10-27 11:42 ` Steffen Persvold
2011-12-02 18:31 ` Daniel J Blueman
2011-12-05 8:20 ` [PATCH 1/3] Make flat_init_apic_ldr available Daniel J Blueman
2011-12-05 8:20 ` [PATCH 2/3] v2: Add x86_init platform override to fix up core numbering Daniel J Blueman
2011-12-05 17:58 ` tip-bot for Daniel J Blueman [this message]
2011-12-06 6:30 ` [tip:x86/apic] x86: Fix the !CONFIG_NUMA build of the new CPU ID fixup code support tip-bot for Steffen Persvold
2011-12-05 8:20 ` [PATCH 3/3] v4: Add support for Numascale's NumaChip Daniel J Blueman
2011-12-05 9:10 ` Ingo Molnar
2011-12-05 9:49 ` Steffen Persvold
2011-12-05 16:07 ` [PATCH 3/3] v5: Add NumaChip support Daniel J Blueman
2011-12-05 17:59 ` [tip:x86/apic] x86: " tip-bot for Steffen Persvold
2011-12-05 20:31 ` Ingo Molnar
2011-12-06 0:10 ` Steffen Persvold
2011-12-06 5:50 ` Ingo Molnar
2011-12-06 6:09 ` Steffen Persvold
2011-12-08 22:35 ` Kevin Winchester
2011-12-09 1:24 ` Steffen Persvold
2011-12-09 7:22 ` Ingo Molnar
2011-12-10 1:52 ` Kevin Winchester
2011-12-10 2:28 ` Kevin Winchester
2011-12-18 9:44 ` Ingo Molnar
2011-12-19 0:12 ` [PATCH] x86: Simplify code by allowing more of struct cpuinfo_x86 for the !SMP case Kevin Winchester
2011-12-19 14:07 ` [tip:x86/apic] " tip-bot for Kevin Winchester
2011-12-19 18:47 ` Ingo Molnar
2011-12-21 0:52 ` [PATCH] " Kevin Winchester
2011-12-21 8:48 ` [tip:x86/apic] x86: Simplify code by removing a !SMP #ifdefs from 'struct cpuinfo_x86' tip-bot for Kevin Winchester
2011-12-05 17:57 ` [tip:x86/apic] x86: Make flat_init_apic_ldr() available tip-bot for Daniel J Blueman
2011-10-26 6:07 ` [PATCH 3/3] Add NumaChip quirk Daniel J Blueman
2011-10-27 7:26 ` [PATCH 1/3] Add Numachip APIC support Ingo Molnar
2011-10-27 7:35 ` Ingo Molnar
2011-10-27 7:44 ` Ingo Molnar
2011-10-27 10:31 ` Steffen Persvold
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=tip-64be4c1c2428e148de6081af235e2418e6a66dda@git.kernel.org \
--to=daniel@numascale-asia.com \
--cc=hpa@zytor.com \
--cc=jbarnes@virtuousgeek.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mingo@redhat.com \
--cc=sp@numascale.com \
--cc=tglx@linutronix.de \
/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