Merge branch 'suspend' into release

Documentation/kernel-parameters.txt

@@ -150,16 +150,20 @@ and is between 256 and 4096 characters. It is defined in the file
 			default: 0
 
 	acpi_sleep=	[HW,ACPI] Sleep options
-			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering }
-			See Documentation/power/video.txt for s3_bios and s3_mode.
+			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
+				  old_ordering, s4_nonvs }
+			See Documentation/power/video.txt for information on
+			s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
 			as soon as the kernel's real-mode entry point is called.
 			s4_nohwsig prevents ACPI hardware signature from being
 			used during resume from hibernation.
 			old_ordering causes the ACPI 1.0 ordering of the _PTS
-			control method, wrt putting devices into low power
-			states, to be enforced (the ACPI 2.0 ordering of _PTS is
-			used by default).
+			control method, with respect to putting devices into
+			low power states, to be enforced (the ACPI 2.0 ordering
+			of _PTS is used by default).
+			s4_nonvs prevents the kernel from saving/restoring the
+			ACPI NVS memory during hibernation.
 
 	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
 			Format: { level | edge | high | low }
@@ -194,7 +198,7 @@ and is between 256 and 4096 characters. It is defined in the file
 	acpi_skip_timer_override [HW,ACPI]
 			Recognize and ignore IRQ0/pin2 Interrupt Override.
 			For broken nForce2 BIOS resulting in XT-PIC timer.
-	acpi_use_timer_override [HW,ACPI}
+	acpi_use_timer_override [HW,ACPI]
 			Use timer override. For some broken Nvidia NF5 boards
 			that require a timer override, but don't have
 			HPET
@@ -861,17 +865,19 @@ and is between 256 and 4096 characters. It is defined in the file
 			See Documentation/ide/ide.txt.
 
 	idle=		[X86]
-			Format: idle=poll or idle=mwait, idle=halt, idle=nomwait
-			Poll forces a polling idle loop that can slightly improves the performance
-			of waking up a idle CPU, but will use a lot of power and make the system
-			run hot. Not recommended.
-			idle=mwait. On systems which support MONITOR/MWAIT but the kernel chose
-			to not use it because it doesn't save as much power as a normal idle
-			loop use the MONITOR/MWAIT idle loop anyways. Performance should be the same
-			as idle=poll.
-			idle=halt. Halt is forced to be used for CPU idle.
+			Format: idle=poll, idle=mwait, idle=halt, idle=nomwait
+			Poll forces a polling idle loop that can slightly
+			improve the performance of waking up a idle CPU, but
+			will use a lot of power and make the system run hot.
+			Not recommended.
+			idle=mwait: On systems which support MONITOR/MWAIT but
+			the kernel chose to not use it because it doesn't save
+			as much power as a normal idle loop, use the
+			MONITOR/MWAIT idle loop anyways. Performance should be
+			the same as idle=poll.
+			idle=halt: Halt is forced to be used for CPU idle.
 			In such case C2/C3 won't be used again.
-			idle=nomwait. Disable mwait for CPU C-states
+			idle=nomwait: Disable mwait for CPU C-states
 
 	ide-pci-generic.all-generic-ide [HW] (E)IDE subsystem
 			Claim all unknown PCI IDE storage controllers.
@@ -1053,8 +1059,8 @@ and is between 256 and 4096 characters. It is defined in the file
 	lapic		[X86-32,APIC] Enable the local APIC even if BIOS
 			disabled it.
 
-	lapic_timer_c2_ok	[X86-32,x86-64,APIC] trust the local apic timer in
-			C2 power state.
+	lapic_timer_c2_ok	[X86-32,x86-64,APIC] trust the local apic timer
+			in C2 power state.
 
 	libata.dma=	[LIBATA] DMA control
 			libata.dma=0	  Disable all PATA and SATA DMA
@@ -2242,7 +2248,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	thermal.psv=	[HW,ACPI]
 			-1: disable all passive trip points
-			<degrees C>: override all passive trip points to this value
+			<degrees C>: override all passive trip points to this
+			value
 
 	thermal.tzp=	[HW,ACPI]
 			Specify global default ACPI thermal zone polling rate

arch/x86/kernel/acpi/sleep.c

@@ -159,6 +159,8 @@ static int __init acpi_sleep_setup(char *str)
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
+		if (strncmp(str, "s4_nonvs", 8) == 0)
+			acpi_s4_no_nvs();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");

arch/x86/kernel/e820.c

@@ -665,6 +665,27 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 }
 #endif
 
+#ifdef CONFIG_HIBERNATION
+/**
+ * Mark ACPI NVS memory region, so that we can save/restore it during
+ * hibernation and the subsequent resume.
+ */
+static int __init e820_mark_nvs_memory(void)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (ei->type == E820_NVS)
+			hibernate_nvs_register(ei->addr, ei->size);
+	}
+
+	return 0;
+}
+core_initcall(e820_mark_nvs_memory);
+#endif
+
 /*
  * Early reserved memory areas.
  */

drivers/acpi/main.c

@@ -101,6 +101,19 @@ void __init acpi_old_suspend_ordering(void)
  * cases.
  */
 static bool set_sci_en_on_resume;
+/*
+ * The ACPI specification wants us to save NVS memory regions during hibernation
+ * and to restore them during the subsequent resume.  However, it is not certain
+ * if this mechanism is going to work on all machines, so we allow the user to
+ * disable this mechanism using the 'acpi_sleep=s4_nonvs' kernel command line
+ * option.
+ */
+static bool s4_no_nvs;
+
+void __init acpi_s4_no_nvs(void)
+{
+	s4_no_nvs = true;
+}
 
 /**
  *	acpi_pm_disable_gpes - Disable the GPEs.
@@ -394,9 +407,25 @@ void __init acpi_no_s4_hw_signature(void)
 
 static int acpi_hibernation_begin(void)
 {
-	acpi_target_sleep_state = ACPI_STATE_S4;
-	acpi_sleep_tts_switch(acpi_target_sleep_state);
-	return 0;
+	int error;
+
+	error = s4_no_nvs ? 0 : hibernate_nvs_alloc();
+	if (!error) {
+		acpi_target_sleep_state = ACPI_STATE_S4;
+		acpi_sleep_tts_switch(acpi_target_sleep_state);
+	}
+
+	return error;
+}
+
+static int acpi_hibernation_pre_snapshot(void)
+{
+	int error = acpi_pm_prepare();
+
+	if (!error)
+		hibernate_nvs_save();
+
+	return error;
 }
 
 static int acpi_hibernation_enter(void)
@@ -417,6 +446,12 @@ static int acpi_hibernation_enter(void)
 	return ACPI_SUCCESS(status) ? 0 : -EFAULT;
 }
 
+static void acpi_hibernation_finish(void)
+{
+	hibernate_nvs_free();
+	acpi_pm_finish();
+}
+
 static void acpi_hibernation_leave(void)
 {
 	/*
@@ -432,6 +467,8 @@ static void acpi_hibernation_leave(void)
 			"cannot resume!\n");
 		panic("ACPI S4 hardware signature mismatch");
 	}
+	/* Restore the NVS memory area */
+	hibernate_nvs_restore();
 }
 
 static void acpi_pm_enable_gpes(void)
@@ -442,8 +479,8 @@ static void acpi_pm_enable_gpes(void)
 static struct platform_hibernation_ops acpi_hibernation_ops = {
 	.begin = acpi_hibernation_begin,
 	.end = acpi_pm_end,
-	.pre_snapshot = acpi_pm_prepare,
-	.finish = acpi_pm_finish,
+	.pre_snapshot = acpi_hibernation_pre_snapshot,
+	.finish = acpi_hibernation_finish,
 	.prepare = acpi_pm_prepare,
 	.enter = acpi_hibernation_enter,
 	.leave = acpi_hibernation_leave,
@@ -469,8 +506,22 @@ static int acpi_hibernation_begin_old(void)
 
 	error = acpi_sleep_prepare(ACPI_STATE_S4);
 
+	if (!error) {
+		if (!s4_no_nvs)
+			error = hibernate_nvs_alloc();
+		if (!error)
+			acpi_target_sleep_state = ACPI_STATE_S4;
+	}
+	return error;
+}
+
+static int acpi_hibernation_pre_snapshot_old(void)
+{
+	int error = acpi_pm_disable_gpes();
+
 	if (!error)
-		acpi_target_sleep_state = ACPI_STATE_S4;
+		hibernate_nvs_save();
+
 	return error;
 }
 
@@ -481,8 +532,8 @@ static int acpi_hibernation_begin_old(void)
 static struct platform_hibernation_ops acpi_hibernation_ops_old = {
 	.begin = acpi_hibernation_begin_old,
 	.end = acpi_pm_end,
-	.pre_snapshot = acpi_pm_disable_gpes,
-	.finish = acpi_pm_finish,
+	.pre_snapshot = acpi_hibernation_pre_snapshot_old,
+	.finish = acpi_hibernation_finish,
 	.prepare = acpi_pm_disable_gpes,
 	.enter = acpi_hibernation_enter,
 	.leave = acpi_hibernation_leave,

include/linux/acpi.h

@@ -270,6 +270,7 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n,
 #ifdef CONFIG_PM_SLEEP
 void __init acpi_no_s4_hw_signature(void);
 void __init acpi_old_suspend_ordering(void);
+void __init acpi_s4_no_nvs(void);
 #endif /* CONFIG_PM_SLEEP */
 #else	/* CONFIG_ACPI */
 

include/linux/suspend.h

@@ -232,6 +232,11 @@ extern unsigned long get_safe_page(gfp_t gfp_mask);
 
 extern void hibernation_set_ops(struct platform_hibernation_ops *ops);
 extern int hibernate(void);
+extern int hibernate_nvs_register(unsigned long start, unsigned long size);
+extern int hibernate_nvs_alloc(void);
+extern void hibernate_nvs_free(void);
+extern void hibernate_nvs_save(void);
+extern void hibernate_nvs_restore(void);
 #else /* CONFIG_HIBERNATION */
 static inline int swsusp_page_is_forbidden(struct page *p) { return 0; }
 static inline void swsusp_set_page_free(struct page *p) {}
@@ -239,6 +244,14 @@ static inline void swsusp_unset_page_free(struct page *p) {}
 
 static inline void hibernation_set_ops(struct platform_hibernation_ops *ops) {}
 static inline int hibernate(void) { return -ENOSYS; }
+static inline int hibernate_nvs_register(unsigned long a, unsigned long b)
+{
+	return 0;
+}
+static inline int hibernate_nvs_alloc(void) { return 0; }
+static inline void hibernate_nvs_free(void) {}
+static inline void hibernate_nvs_save(void) {}
+static inline void hibernate_nvs_restore(void) {}
 #endif /* CONFIG_HIBERNATION */
 
 #ifdef CONFIG_PM_SLEEP

kernel/power/disk.c

@@ -259,12 +259,12 @@ int hibernation_snapshot(int platform_mode)
 {
 	int error, ftrace_save;
 
-	/* Free memory before shutting down devices. */
-	error = swsusp_shrink_memory();
+	error = platform_begin(platform_mode);
 	if (error)
 		return error;
 
-	error = platform_begin(platform_mode);
+	/* Free memory before shutting down devices. */
+	error = swsusp_shrink_memory();
 	if (error)
 		goto Close;
 

kernel/power/swsusp.c

@@ -262,3 +262,125 @@ int swsusp_shrink_memory(void)
 
 	return 0;
 }
+
+/*
+ * Platforms, like ACPI, may want us to save some memory used by them during
+ * hibernation and to restore the contents of this memory during the subsequent
+ * resume.  The code below implements a mechanism allowing us to do that.
+ */
+
+struct nvs_page {
+	unsigned long phys_start;
+	unsigned int size;
+	void *kaddr;
+	void *data;
+	struct list_head node;
+};
+
+static LIST_HEAD(nvs_list);
+
+/**
+ *	hibernate_nvs_register - register platform NVS memory region to save
+ *	@start - physical address of the region
+ *	@size - size of the region
+ *
+ *	The NVS region need not be page-aligned (both ends) and we arrange
+ *	things so that the data from page-aligned addresses in this region will
+ *	be copied into separate RAM pages.
+ */
+int hibernate_nvs_register(unsigned long start, unsigned long size)
+{
+	struct nvs_page *entry, *next;
+
+	while (size > 0) {
+		unsigned int nr_bytes;
+
+		entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
+		if (!entry)
+			goto Error;
+
+		list_add_tail(&entry->node, &nvs_list);
+		entry->phys_start = start;
+		nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
+		entry->size = (size < nr_bytes) ? size : nr_bytes;
+
+		start += entry->size;
+		size -= entry->size;
+	}
+	return 0;
+
+ Error:
+	list_for_each_entry_safe(entry, next, &nvs_list, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	return -ENOMEM;
+}
+
+/**
+ *	hibernate_nvs_free - free data pages allocated for saving NVS regions
+ */
+void hibernate_nvs_free(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			free_page((unsigned long)entry->data);
+			entry->data = NULL;
+			if (entry->kaddr) {
+				iounmap(entry->kaddr);
+				entry->kaddr = NULL;
+			}
+		}
+}
+
+/**
+ *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ */
+int hibernate_nvs_alloc(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node) {
+		entry->data = (void *)__get_free_page(GFP_KERNEL);
+		if (!entry->data) {
+			hibernate_nvs_free();
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ *	hibernate_nvs_save - save NVS memory regions
+ */
+void hibernate_nvs_save(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Saving platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			entry->kaddr = ioremap(entry->phys_start, entry->size);
+			memcpy(entry->data, entry->kaddr, entry->size);
+		}
+}
+
+/**
+ *	hibernate_nvs_restore - restore NVS memory regions
+ *
+ *	This function is going to be called with interrupts disabled, so it
+ *	cannot iounmap the virtual addresses used to access the NVS region.
+ */
+void hibernate_nvs_restore(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Restoring platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data)
+			memcpy(entry->kaddr, entry->data, entry->size);
+}