Re: [PATCH] apic: use GFP_ATOMIC in lapic_resume
From: Zhang Rui
Date: Tue Dec 28 2010 - 03:48:16 EST
On Tue, 2010-12-28 at 15:56 +0800, Zhang Rui wrote:
> On Tue, 2010-12-28 at 15:39 +0800, David Rientjes wrote:
> > On Tue, 28 Dec 2010, Zhang Rui wrote:
> >
> > > > > Index: linux-2.6/arch/x86/kernel/apic/apic.c
> > > > > ===================================================================
> > > > > --- linux-2.6.orig/arch/x86/kernel/apic/apic.c
> > > > > +++ linux-2.6/arch/x86/kernel/apic/apic.c
> > > > > @@ -1459,7 +1459,7 @@ void __init enable_IR_x2apic(void)
> > > > > if (dmar_table_init_ret && !x2apic_supported())
> > > > > return;
> > > > >
> > > > > - ioapic_entries = alloc_ioapic_entries();
> > > > > + ioapic_entries = alloc_ioapic_entries(GFP_KERNEL);
> > > > > if (!ioapic_entries) {
> > > > > pr_err("Allocate ioapic_entries failed\n");
> > > > > goto out;
> > > > > @@ -2084,7 +2084,7 @@ static int lapic_resume(struct sys_devic
> > > > >
> > > > > local_irq_save(flags);
> > > > > if (intr_remapping_enabled) {
> > > > > - ioapic_entries = alloc_ioapic_entries();
> > > > > + ioapic_entries = alloc_ioapic_entries(GFP_ATOMIC);
> > > > > if (!ioapic_entries) {
> > > > > WARN(1, "Alloc ioapic_entries in lapic resume failed.");
> > > > > ret = -ENOMEM;
> > > >
> > > > You can't do the allocation before disabling irqs when
> > > > intr_remapping_enabled is set?
> > >
> > > yes, we can. The first idea came into my mind is to register a pm
> > > notifier callback to allocate/free the memory. But that one duplicates
> > > the code of alloc_ioapic_entries, which doesn't look nice, neither.
> > > Plus, is there any problem with this one?
> > >
> >
> > We try to avoid GFP_ATOMIC whenever possible and this seems like a
> > particularly trivial case. You can simply move the alloc_ioapic_entries()
> > and NULL check before local_irq_save() and GFP_KERNEL will work fine.
>
> I'm afraid not.
> lapic_resume is invoked in sysdev_resume, which is done with irq
> disabled, please refer to the code in kernel/power/suspend.c.
>
> arch_suspend_disable_irqs();
> BUG_ON(!irqs_disabled());
>
> error = sysdev_suspend(PMSG_SUSPEND);
> if (!error) {
> if (!suspend_test(TEST_CORE) &&
> pm_check_wakeup_events()) {
> error = suspend_ops->enter(state);
> events_check_enabled = false;
> }
> sysdev_resume();
> }
>
> arch_suspend_enable_irqs();
> BUG_ON(irqs_disabled());
>
> To pre-allocate the memory, we need to build a notifier bloack and call
> register_pm_notifier.
what about this one?
Note that it just builds okay, I have not test the patch yet.
pre-allocate the memory used in lapic_resume because lapic_resume, as a
sysdev .resume callback, is always invoked with irq disabled.
Without this patch, I got the following warning messages after resume.
[ 109.780371] BUG: sleeping function called from invalid context at
mm/slub.c:793
[ 109.780782] in_atomic(): 0, irqs_disabled(): 1, pid: 1391, name: bash
[ 109.781024] Pid: 1391, comm: bash Not tainted 2.6.37-rc5+ #182
[ 109.781264] Call Trace:
[ 109.781501] [<ffffffff8104156a>] __might_sleep+0xeb/0xf0
[ 109.781743] [<ffffffff8110d5e2>] slab_pre_alloc_hook.clone.33
+0x28/0x31
[ 109.781987] [<ffffffff8110dcef>] __kmalloc+0x88/0x115
[ 109.782224] [<ffffffff81025e4a>] ? kzalloc.clone.19+0x13/0x15
[ 109.782465] [<ffffffff81025e4a>] kzalloc.clone.19+0x13/0x15
[ 109.782704] [<ffffffff81025ff0>] alloc_ioapic_entries+0x20/0x82
[ 109.782948] [<ffffffff81024201>] lapic_resume+0x3a/0x245
[ 109.783189] [<ffffffff813a8329>] ? cpufreq_resume+0x30/0xb0
[ 109.783431] [<ffffffff812ec4ee>] __sysdev_resume+0x25/0xc5
[ 109.783673] [<ffffffff812ec644>] sysdev_resume+0xb6/0xfb
[ 109.783914] [<ffffffff81083256>] suspend_devices_and_enter
+0x13c/0x1c1
[ 109.784159] [<ffffffff810833b8>] enter_state+0xdd/0x12e
[ 109.784398] [<ffffffff81082a61>] state_store+0xae/0xcb
[ 109.784640] [<ffffffff81225737>] kobj_attr_store+0x17/0x19
[ 109.784882] [<ffffffff81173311>] sysfs_write_file+0x114/0x150
[ 109.785124] [<ffffffff8111aebb>] vfs_write+0xac/0xff
[ 109.785365] [<ffffffff8111b0c2>] sys_write+0x4a/0x6e
[ 109.785604] [<ffffffff8100ac82>] system_call_fastpath+0x16/0x1b
Signed-off-by: Zhang Rui <rui.zhang@xxxxxxxxx>
---
arch/x86/kernel/apic/apic.c | 38 +++++++++++++++++++++++++++++++++-----
1 file changed, 33 insertions(+), 5 deletions(-)
Index: linux-2.6/arch/x86/kernel/apic/apic.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/apic/apic.c
+++ linux-2.6/arch/x86/kernel/apic/apic.c
@@ -34,6 +34,7 @@
#include <linux/nmi.h>
#include <linux/smp.h>
#include <linux/mm.h>
+#include <linux/suspend.h>
#include <asm/perf_event.h>
#include <asm/x86_init.h>
@@ -2033,6 +2034,34 @@ static struct {
unsigned int apic_thmr;
} apic_pm_state;
+static struct IO_APIC_route_entry **ioapic_entries;
+
+static int lapic_notifier_cb(struct notifier_block *nb,
+ unsigned long val, void *unused)
+{
+ switch(val) {
+ case PM_HIBERNATION_PREPARE:
+ case PM_SUSPEND_PREPARE:
+ case PM_RESTORE_PREPARE:
+ ioapic_entries = alloc_ioapic_entries();
+ if (!ioapic_entries)
+ return NOTIFY_BAD;
+ return NOTIFY_OK;
+ case PM_POST_HIBERNATION:
+ case PM_POST_SUSPEND:
+ case PM_POST_RESTORE:
+ free_ioapic_entries(ioapic_entries);
+ ioapic_entries = NULL;
+ return NOTIFY_OK;
+ }
+ return NOTIFY_BAD;
+}
+
+static struct notifier_block lapic_pm_nb = {
+ .notifier_call = lapic_notifier_cb,
+ .priority = 0,
+};
+
static int lapic_suspend(struct sys_device *dev, pm_message_t state)
{
unsigned long flags;
@@ -2077,14 +2106,12 @@ static int lapic_resume(struct sys_devic
unsigned long flags;
int maxlvt;
int ret = 0;
- struct IO_APIC_route_entry **ioapic_entries = NULL;
if (!apic_pm_state.active)
return 0;
local_irq_save(flags);
if (intr_remapping_enabled) {
- ioapic_entries = alloc_ioapic_entries();
if (!ioapic_entries) {
WARN(1, "Alloc ioapic_entries in lapic resume failed.");
ret = -ENOMEM;
@@ -2094,7 +2121,6 @@ static int lapic_resume(struct sys_devic
ret = save_IO_APIC_setup(ioapic_entries);
if (ret) {
WARN(1, "Saving IO-APIC state failed: %d\n", ret);
- free_ioapic_entries(ioapic_entries);
goto restore;
}
@@ -2145,7 +2171,6 @@ static int lapic_resume(struct sys_devic
reenable_intr_remapping(x2apic_mode);
legacy_pic->restore_mask();
restore_IO_APIC_setup(ioapic_entries);
- free_ioapic_entries(ioapic_entries);
}
restore:
local_irq_restore(flags);
@@ -2183,8 +2208,11 @@ static int __init init_lapic_sysfs(void)
/* XXX: remove suspend/resume procs if !apic_pm_state.active? */
error = sysdev_class_register(&lapic_sysclass);
- if (!error)
+ if (!error) {
error = sysdev_register(&device_lapic);
+ if (!error)
+ error = register_pm_notifier(&lapic_pm_nb);
+ }
return error;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/