mm/pm: force GFP_NOIO during suspend/hibernation and resume

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.

[akpm@linux-foundation.org: fix CONFIG_PM=n linkage]
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Reported-by: Maxim Levitsky <maximlevitsky@gmail.com>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 41 insertions, 5 deletions

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index e5567e6762f..2e1b32c0484 100644
--- a/include/linux/gfp.h
+++ b/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 */
diff --git a/init/main.c b/init/main.c
index 40aaa020cd6..41d0f10dbbc 100644
--- a/init/main.c
+++ b/init/main.c
@@ -618,7 +618,7 @@ 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();
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index bbfe472d752..da5288ec239 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -323,6 +323,7 @@ static int create_image(int platform_mode)
 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_mode)
 		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_mode)
 
 	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 platform_mode)
 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_mode)
 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:
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 6f10dfc2d3e..44cce10b582 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -189,6 +189,7 @@ static int suspend_enter(suspend_state_t state)
 int suspend_devices_and_enter(suspend_state_t state)
 {
 	int error;
+	gfp_t saved_mask;
 
 	if (!suspend_ops)
 		return -ENOSYS;
@@ -199,6 +200,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
+	saved_mask = clear_gfp_allowed_mask(GFP_IOFS);
 	suspend_test_start();
 	error = dpm_suspend_start(PMSG_SUSPEND);
 	if (error) {
@@ -215,6 +217,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	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)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0734bedabd9..298f307c63a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -76,6 +76,31 @@ unsigned long totalreserve_pages __read_mostly;
 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