Re: s2disk hang update

From: Rafael J. Wysocki
Date: Tue Feb 16 2010 - 16:16:35 EST


On Tuesday 16 February 2010, Alan Jenkins wrote:
> On 2/16/10, Alan Jenkins <sourcejedi.lkml@xxxxxxxxxxxxxx> wrote:
> > On 2/15/10, Rafael J. Wysocki <rjw@xxxxxxx> wrote:
> >> On Tuesday 09 February 2010, Alan Jenkins wrote:
> >>> Perhaps I spoke too soon. I see the same hang if I run too many
> >>> applications. The first hibernation fails with "not enough swap" as
> >>> expected, but the second or third attempt hangs (with the same backtrace
> >>> as before).
> >>>
> >>> The patch definitely helps though. Without the patch, I see a hang the
> >>> first time I try to hibernate with too many applications running.
> >>
> >> Well, I have an idea.
> >>
> >> Can you try to apply the appended patch in addition and see if that
> >> helps?
> >>
> >> Rafael
> >
> > It doesn't seem to help.
>
> To be clear: It doesn't stop the hang when I hibernate with too many
> applications.
>
> It does stop the same hang in a different case though.
>
> 1. boot with init=/bin/bash
> 2. run s2disk
> 3. cancel the s2disk
> 4. repeat steps 2&3
>
> With the patch, I can run 10s of iterations, with no hang.
> Without the patch, it soon hangs, (in disable_nonboot_cpus(), as always).
>
> That's what happens on 2.6.33-rc7. On 2.6.30, there is no problem.
> On 2.6.31 and 2.6.32 I don't get a hang, but dmesg shows an allocation
> failure after a couple of iterations ("kthreadd: page allocation
> failure. order:1, mode:0xd0"). It looks like it might be the same
> stop_machine thread allocation failure that causes the hang.

Have you tested it alone or on top of the previous one? If you've tested it
alone, please apply the appended one in addition to it and retest.

Rafael

---
From: Rafael J. Wysocki <rjw@xxxxxxx>
Subject: MM / PM: Force GFP_NOIO during suspend/hibernation and resume (rev. 3)

There are quite a few GFP_KERNEL memory allocations made during
suspend/hibernation and resume that may cause the system to hang,
because the I/O operations they depend on cannot be completed due to
the underlying devices being suspended.

Avoid this problem by clearing the __GFP_IO and __GFP_FS bits in
gfp_allowed_mask before suspend/hibernation and restoring the
original values of these bits in gfp_allowed_mask durig the
subsequent resume.

Signed-off-by: Rafael J. Wysocki <rjw@xxxxxxx>
Reported-by: Maxim Levitsky <maximlevitsky@xxxxxxxxx>
---
include/linux/gfp.h | 7 +++----
init/main.c | 2 +-
kernel/power/hibernate.c | 9 +++++++++
kernel/power/suspend.c | 3 +++
mm/page_alloc.c | 26 ++++++++++++++++++++++++++
5 files changed, 42 insertions(+), 5 deletions(-)

Index: linux-2.6/include/linux/gfp.h
===================================================================
--- linux-2.6.orig/include/linux/gfp.h
+++ linux-2.6/include/linux/gfp.h
@@ -83,6 +83,7 @@ struct vm_area_struct;
#define GFP_HIGHUSER_MOVABLE (__GFP_WAIT | __GFP_IO | __GFP_FS | \
__GFP_HARDWALL | __GFP_HIGHMEM | \
__GFP_MOVABLE)
+#define GFP_IOFS (__GFP_IO | __GFP_FS)

#ifdef CONFIG_NUMA
#define GFP_THISNODE (__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
@@ -337,9 +338,7 @@ void drain_local_pages(void *dummy);

extern gfp_t gfp_allowed_mask;

-static inline void set_gfp_allowed_mask(gfp_t mask)
-{
- gfp_allowed_mask = mask;
-}
+extern void set_gfp_allowed_mask(gfp_t mask);
+extern gfp_t clear_gfp_allowed_mask(gfp_t mask);

#endif /* __LINUX_GFP_H */
Index: linux-2.6/init/main.c
===================================================================
--- linux-2.6.orig/init/main.c
+++ linux-2.6/init/main.c
@@ -601,7 +601,7 @@ asmlinkage void __init start_kernel(void
local_irq_enable();

/* Interrupts are enabled now so all GFP allocations are safe. */
- set_gfp_allowed_mask(__GFP_BITS_MASK);
+ gfp_allowed_mask = __GFP_BITS_MASK;

kmem_cache_init_late();

Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -76,6 +76,32 @@ unsigned long totalreserve_pages __read_
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;

+#ifdef CONFIG_PM_SLEEP
+/*
+ * The following functions are used by the suspend/hibernate code to temporarily
+ * change gfp_allowed_mask in order to avoid using I/O during memory allocations
+ * while devices are suspended. To avoid races with the suspend/hibernate code,
+ * they should always be called with pm_mutex held (gfp_allowed_mask also should
+ * only be modified with pm_mutex held, unless the suspend/hibernate code is
+ * guaranteed not to run in parallel with that modification).
+ */
+
+void set_gfp_allowed_mask(gfp_t mask)
+{
+ WARN_ON(!mutex_is_locked(&pm_mutex));
+ gfp_allowed_mask = mask;
+}
+
+gfp_t clear_gfp_allowed_mask(gfp_t mask)
+{
+ gfp_t ret = gfp_allowed_mask;
+
+ WARN_ON(!mutex_is_locked(&pm_mutex));
+ gfp_allowed_mask &= ~mask;
+ return ret;
+}
+#endif /* CONFIG_PM_SLEEP */
+
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
int pageblock_order __read_mostly;
#endif
Index: linux-2.6/kernel/power/hibernate.c
===================================================================
--- linux-2.6.orig/kernel/power/hibernate.c
+++ linux-2.6/kernel/power/hibernate.c
@@ -323,6 +323,7 @@ static int create_image(int platform_mod
int hibernation_snapshot(int platform_mode)
{
int error;
+ gfp_t saved_mask;

error = platform_begin(platform_mode);
if (error)
@@ -334,6 +335,7 @@ int hibernation_snapshot(int platform_mo
goto Close;

suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_FREEZE);
if (error)
goto Recover_platform;
@@ -351,6 +353,7 @@ int hibernation_snapshot(int platform_mo

dpm_resume_end(in_suspend ?
(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
+ set_gfp_allowed_mask(saved_mask);
resume_console();
Close:
platform_end(platform_mode);
@@ -445,14 +448,17 @@ static int resume_target_kernel(bool pla
int hibernation_restore(int platform_mode)
{
int error;
+ gfp_t saved_mask;

pm_prepare_console();
suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_QUIESCE);
if (!error) {
error = resume_target_kernel(platform_mode);
dpm_resume_end(PMSG_RECOVER);
}
+ set_gfp_allowed_mask(saved_mask);
resume_console();
pm_restore_console();
return error;
@@ -466,6 +472,7 @@ int hibernation_restore(int platform_mod
int hibernation_platform_enter(void)
{
int error;
+ gfp_t saved_mask;

if (!hibernation_ops)
return -ENOSYS;
@@ -481,6 +488,7 @@ int hibernation_platform_enter(void)

entering_platform_hibernation = true;
suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
error = dpm_suspend_start(PMSG_HIBERNATE);
if (error) {
if (hibernation_ops->recover)
@@ -518,6 +526,7 @@ int hibernation_platform_enter(void)
Resume_devices:
entering_platform_hibernation = false;
dpm_resume_end(PMSG_RESTORE);
+ set_gfp_allowed_mask(saved_mask);
resume_console();

Close:
Index: linux-2.6/kernel/power/suspend.c
===================================================================
--- linux-2.6.orig/kernel/power/suspend.c
+++ linux-2.6/kernel/power/suspend.c
@@ -198,6 +198,7 @@ static int suspend_enter(suspend_state_t
int suspend_devices_and_enter(suspend_state_t state)
{
int error;
+ gfp_t saved_mask;

if (!suspend_ops)
return -ENOSYS;
@@ -208,6 +209,7 @@ int suspend_devices_and_enter(suspend_st
goto Close;
}
suspend_console();
+ saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
suspend_test_start();
error = dpm_suspend_start(PMSG_SUSPEND);
if (error) {
@@ -224,6 +226,7 @@ int suspend_devices_and_enter(suspend_st
suspend_test_start();
dpm_resume_end(PMSG_RESUME);
suspend_test_finish("resume devices");
+ set_gfp_allowed_mask(saved_mask);
resume_console();
Close:
if (suspend_ops->end)
--
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/