From: Johannes Berg <johannes@sipsolutions.net>
To: linuxppc-dev@ozlabs.org
Cc: linux-pm@lists.osdl.org, Torrance <torrance123@gmail.com>
Subject: [RFC 07/10] powermac: support G5 CPU hotplug
Date: Mon, 05 Feb 2007 19:30:34 +0100 [thread overview]
Message-ID: <20070205185837.640324000@sipsolutions.net> (raw)
In-Reply-To: 20070205183026.989209000@sipsolutions.net
This patch allows "hotplugging" of CPUs on G5 machines. CPUs that are
disabled are put into an idle loop with interrupts hard-disabled, to wake
them up again we kick them just like when bringing them up.
Maybe there's some way to actually turn off those CPUs even more?
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
--- mb-wireless.orig/arch/powerpc/platforms/powermac/smp.c 2007-02-05 16:07:09.164524763 +0100
+++ mb-wireless/arch/powerpc/platforms/powermac/smp.c 2007-02-05 16:07:50.774524763 +0100
@@ -898,7 +898,7 @@ void smp_core99_cpu_die(unsigned int cpu
cpu_dead[cpu] = 0;
}
-#endif
+#endif /* CONFIG_HOTPLUG_CPU && CONFIG_PP32 */
/* Core99 Macs (dual G4s and G5s) */
struct smp_ops_t core99_smp_ops = {
@@ -908,8 +908,16 @@ struct smp_ops_t core99_smp_ops = {
.setup_cpu = smp_core99_setup_cpu,
.give_timebase = smp_core99_give_timebase,
.take_timebase = smp_core99_take_timebase,
-#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC32)
+#if defined(CONFIG_HOTPLUG_CPU)
+# if defined(CONFIG_PPC32)
.cpu_disable = smp_core99_cpu_disable,
.cpu_die = smp_core99_cpu_die,
+# endif
+# if defined(CONFIG_PPC64)
+ .cpu_disable = generic_cpu_disable,
+ .cpu_die = generic_cpu_die,
+ /* intentionally do *NOT* assign cpu_enable,
+ * the generic code will use kick_cpu then! */
+# endif
#endif
};
--- mb-wireless.orig/arch/powerpc/platforms/powermac/setup.c 2007-02-05 16:07:22.024524763 +0100
+++ mb-wireless/arch/powerpc/platforms/powermac/setup.c 2007-02-05 16:07:50.784524763 +0100
@@ -490,6 +490,9 @@ static int pmac_late_init(void)
#ifdef CONFIG_SOFTWARE_SUSPEND
pm_set_ops(&pmac_pm_ops);
#endif /* CONFIG_SOFTWARE_SUSPEND */
+ /* this is udbg (which is __init) and we can later use it during
+ * cpu hotplug (in smp_core99_kick_cpu) */
+ ppc_md.progress = NULL;
return 0;
}
@@ -716,6 +719,33 @@ static int pmac_pci_probe_mode(struct pc
return PCI_PROBE_NORMAL;
return PCI_PROBE_DEVTREE;
}
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* access per cpu vars from generic smp.c */
+DECLARE_PER_CPU(int, cpu_state);
+
+static void pmac_cpu_die(void)
+{
+ /* turn off as much as possible, we'll be
+ * kicked out as this will only be invoked
+ * on core99 platforms for now ... */
+ hard_irq_disable();
+
+ printk(KERN_DEBUG "CPU#%d offline\n", smp_processor_id());
+ __get_cpu_var(cpu_state) = CPU_DEAD;
+ smp_wmb();
+ while (1) {
+ ppc64_runlatch_off();
+ if (ppc_md.power_save) {
+ ppc_md.power_save();
+ } else {
+ HMT_low();
+ HMT_very_low();
+ }
+ }
+}
+#endif
+
#endif
static void __init pmac_init_irq(void)
@@ -769,6 +799,6 @@ define_machine(powermac) {
.phys_mem_access_prot = pci_phys_mem_access_prot,
#endif
#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PPC64)
- .cpu_die = generic_mach_cpu_die,
+ .cpu_die = pmac_cpu_die,
#endif
};
--- mb-wireless.orig/arch/powerpc/kernel/smp.c 2007-02-05 16:07:09.274524763 +0100
+++ mb-wireless/arch/powerpc/kernel/smp.c 2007-02-05 18:15:51.114524763 +0100
@@ -558,6 +558,11 @@ int __devinit start_secondary(void *unus
local_irq_enable();
+ /* it seems to be possible that we died from within
+ * an interrupt ... reset the in-irq counts */
+ task_thread_info(paca[cpu].__current)->preempt_count &=
+ ~(SOFTIRQ_MASK|HARDIRQ_MASK);
+
cpu_idle();
return 0;
}
--
next prev parent reply other threads:[~2007-02-05 19:09 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-02-05 18:30 [PATCH/RFC 00/10] suspend to disk for powermac G5 Johannes Berg
2007-02-05 18:30 ` [PATCH 01/10] dont copy pages that arent RAM Johannes Berg
2007-02-05 18:30 ` [PATCH 02/10] windfarm: dont die on suspend thread signal Johannes Berg
2007-02-05 22:43 ` Christoph Hellwig
2007-02-05 22:54 ` [PATCH revision 2] " Johannes Berg
2007-02-05 23:04 ` Benjamin Herrenschmidt
2007-02-05 23:04 ` Benjamin Herrenschmidt
2007-02-05 22:54 ` [PATCH 02/10] " Andrew Morton
2007-02-05 22:55 ` Johannes Berg
2007-02-05 22:58 ` Benjamin Herrenschmidt
2007-02-05 18:30 ` [PATCH 03/10] powerpc: fix comment in kernel/irq.c Johannes Berg
2007-02-05 22:59 ` Benjamin Herrenschmidt
2007-02-05 23:18 ` Andrew Morton
2007-02-05 23:53 ` Benjamin Herrenschmidt
2007-02-05 18:30 ` [PATCH 04/10] powermac: clean up PIC initialisation code Johannes Berg
2007-02-08 4:41 ` Paul Mackerras
2007-02-08 13:03 ` Johannes Berg
2007-02-05 18:30 ` [PATCH 05/10] powermac: generic time suspend/resume code Johannes Berg
2007-02-19 10:00 ` [linux-pm] " Guennadi Liakhovetski
2007-02-19 23:19 ` Guennadi Liakhovetski
2007-02-05 18:30 ` [RFC 06/10] powerpc: MPIC sys_device & suspend/resume Johannes Berg
2007-02-07 12:24 ` Johannes Berg
2007-02-05 18:30 ` Johannes Berg [this message]
2007-02-06 12:42 ` [linux-pm] [RFC 07/10] powermac: support G5 CPU hotplug Pavel Machek
2007-02-07 11:40 ` Johannes Berg
2007-02-07 12:23 ` Johannes Berg
2007-02-05 18:30 ` [RFC 08/10] powerpc: dart iommu suspend Johannes Berg
2007-02-06 1:19 ` Olof Johansson
2007-02-06 1:26 ` Johannes Berg
2007-02-06 1:52 ` Johannes Berg
2007-02-07 12:22 ` Johannes Berg
2007-02-06 12:40 ` [linux-pm] " Pavel Machek
2007-02-07 11:42 ` Johannes Berg
2007-02-05 18:30 ` [RFC 09/10] powermac: suspend to disk on G5 Johannes Berg
2007-02-05 18:30 ` [RFC 10/10] powermac: fix G5-cpufreq for cpu on/offline Johannes Berg
2007-02-07 12:21 ` Johannes Berg
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=20070205185837.640324000@sipsolutions.net \
--to=johannes@sipsolutions.net \
--cc=linux-pm@lists.osdl.org \
--cc=linuxppc-dev@ozlabs.org \
--cc=torrance123@gmail.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;
as well as URLs for NNTP newsgroup(s).