From 4f3549d72d1b5c90ecc7e673402f38f4486d22c2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 2 May 2013 22:15:29 +0200 Subject: Driver core: Add offline/online device operations In some cases, graceful hot-removal of devices is not possible, although in principle the devices in question support hotplug. For example, that may happen for the last CPU in the system or for memory modules holding kernel memory. In those cases it is nice to be able to check if the given device can be gracefully hot-removed before triggering a removal procedure that cannot be aborted or reversed. Unfortunately, however, the kernel currently doesn't provide any support for that. To address that deficiency, introduce support for offline and online operations that can be performed on devices, respectively, before a hot-removal and in case when it is necessary (or convenient) to put a device back online after a successful offline (that has not been followed by removal). The idea is that the offline will fail whenever the given device cannot be gracefully removed from the system and it will not be allowed to use the device after a successful offline (until a subsequent online) in analogy with the existing CPU offline/online mechanism. For now, the offline and online operations are introduced at the bus type level, as that should be sufficient for the most urgent use cases (CPUs and memory modules). In the future, however, the approach may be extended to cover some more complicated device offline/online scenarios involving device drivers etc. The lock_device_hotplug() and unlock_device_hotplug() functions are introduced because subsequent patches need to put larger pieces of code under device_hotplug_lock to prevent race conditions between device offline and removal from happening. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: Toshi Kani --- drivers/base/core.c | 130 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 130 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index 016312437577..60c975686089 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -403,6 +403,36 @@ static ssize_t store_uevent(struct device *dev, struct device_attribute *attr, static struct device_attribute uevent_attr = __ATTR(uevent, S_IRUGO | S_IWUSR, show_uevent, store_uevent); +static ssize_t show_online(struct device *dev, struct device_attribute *attr, + char *buf) +{ + bool val; + + lock_device_hotplug(); + val = !dev->offline; + unlock_device_hotplug(); + return sprintf(buf, "%u\n", val); +} + +static ssize_t store_online(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + bool val; + int ret; + + ret = strtobool(buf, &val); + if (ret < 0) + return ret; + + lock_device_hotplug(); + ret = val ? device_online(dev) : device_offline(dev); + unlock_device_hotplug(); + return ret < 0 ? ret : count; +} + +static struct device_attribute online_attr = + __ATTR(online, S_IRUGO | S_IWUSR, show_online, store_online); + static int device_add_attributes(struct device *dev, struct device_attribute *attrs) { @@ -516,6 +546,12 @@ static int device_add_attrs(struct device *dev) if (error) goto err_remove_type_groups; + if (device_supports_offline(dev) && !dev->offline_disabled) { + error = device_create_file(dev, &online_attr); + if (error) + goto err_remove_type_groups; + } + return 0; err_remove_type_groups: @@ -536,6 +572,7 @@ static void device_remove_attrs(struct device *dev) struct class *class = dev->class; const struct device_type *type = dev->type; + device_remove_file(dev, &online_attr); device_remove_groups(dev, dev->groups); if (type) @@ -1431,6 +1468,99 @@ EXPORT_SYMBOL_GPL(put_device); EXPORT_SYMBOL_GPL(device_create_file); EXPORT_SYMBOL_GPL(device_remove_file); +static DEFINE_MUTEX(device_hotplug_lock); + +void lock_device_hotplug(void) +{ + mutex_lock(&device_hotplug_lock); +} + +void unlock_device_hotplug(void) +{ + mutex_unlock(&device_hotplug_lock); +} + +static int device_check_offline(struct device *dev, void *not_used) +{ + int ret; + + ret = device_for_each_child(dev, NULL, device_check_offline); + if (ret) + return ret; + + return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0; +} + +/** + * device_offline - Prepare the device for hot-removal. + * @dev: Device to be put offline. + * + * Execute the device bus type's .offline() callback, if present, to prepare + * the device for a subsequent hot-removal. If that succeeds, the device must + * not be used until either it is removed or its bus type's .online() callback + * is executed. + * + * Call under device_hotplug_lock. + */ +int device_offline(struct device *dev) +{ + int ret; + + if (dev->offline_disabled) + return -EPERM; + + ret = device_for_each_child(dev, NULL, device_check_offline); + if (ret) + return ret; + + device_lock(dev); + if (device_supports_offline(dev)) { + if (dev->offline) { + ret = 1; + } else { + ret = dev->bus->offline(dev); + if (!ret) { + kobject_uevent(&dev->kobj, KOBJ_OFFLINE); + dev->offline = true; + } + } + } + device_unlock(dev); + + return ret; +} + +/** + * device_online - Put the device back online after successful device_offline(). + * @dev: Device to be put back online. + * + * If device_offline() has been successfully executed for @dev, but the device + * has not been removed subsequently, execute its bus type's .online() callback + * to indicate that the device can be used again. + * + * Call under device_hotplug_lock. + */ +int device_online(struct device *dev) +{ + int ret = 0; + + device_lock(dev); + if (device_supports_offline(dev)) { + if (dev->offline) { + ret = dev->bus->online(dev); + if (!ret) { + kobject_uevent(&dev->kobj, KOBJ_ONLINE); + dev->offline = false; + } + } else { + ret = 1; + } + } + device_unlock(dev); + + return ret; +} + struct root_device { struct device dev; struct module *owner; -- cgit v1.2.3 From 0902a9044fa5b7a0456ea4daacec2c2b3189ba8c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 May 2013 00:25:49 +0200 Subject: Driver core: Use generic offline/online for CPU offline/online Rework the CPU hotplug code in drivers/base/cpu.c to use the generic offline/online support introduced previously instead of its own CPU-specific code. For this purpose, modify cpu_subsys to provide offline and online callbacks for CONFIG_HOTPLUG_CPU set and remove the code handling the CPU-specific 'online' sysfs attribute. This modification is not supposed to change the user-observable behavior of the kernel (i.e. the 'online' attribute will be present in exactly the same place in sysfs and should trigger exactly the same actions as before). Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: Toshi Kani --- drivers/base/cpu.c | 89 ++++++++++++++++++++---------------------------------- 1 file changed, 32 insertions(+), 57 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 3d48fc887ef4..25c8768172e9 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -16,12 +16,6 @@ #include "base.h" -struct bus_type cpu_subsys = { - .name = "cpu", - .dev_name = "cpu", -}; -EXPORT_SYMBOL_GPL(cpu_subsys); - static DEFINE_PER_CPU(struct device *, cpu_sys_devices); #ifdef CONFIG_HOTPLUG_CPU @@ -34,69 +28,45 @@ static void change_cpu_under_node(struct cpu *cpu, cpu->node_id = to_nid; } -static ssize_t show_online(struct device *dev, - struct device_attribute *attr, - char *buf) +static int __ref cpu_subsys_online(struct device *dev) { struct cpu *cpu = container_of(dev, struct cpu, dev); + int cpuid = dev->id; + int from_nid, to_nid; + int ret; + + cpu_hotplug_driver_lock(); + + from_nid = cpu_to_node(cpuid); + ret = cpu_up(cpuid); + /* + * When hot adding memory to memoryless node and enabling a cpu + * on the node, node number of the cpu may internally change. + */ + to_nid = cpu_to_node(cpuid); + if (from_nid != to_nid) + change_cpu_under_node(cpu, from_nid, to_nid); - return sprintf(buf, "%u\n", !!cpu_online(cpu->dev.id)); + cpu_hotplug_driver_unlock(); + return ret; } -static ssize_t __ref store_online(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) +static int cpu_subsys_offline(struct device *dev) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - int cpuid = cpu->dev.id; - int from_nid, to_nid; - ssize_t ret; + int ret; cpu_hotplug_driver_lock(); - switch (buf[0]) { - case '0': - ret = cpu_down(cpuid); - if (!ret) - kobject_uevent(&dev->kobj, KOBJ_OFFLINE); - break; - case '1': - from_nid = cpu_to_node(cpuid); - ret = cpu_up(cpuid); - - /* - * When hot adding memory to memoryless node and enabling a cpu - * on the node, node number of the cpu may internally change. - */ - to_nid = cpu_to_node(cpuid); - if (from_nid != to_nid) - change_cpu_under_node(cpu, from_nid, to_nid); - - if (!ret) - kobject_uevent(&dev->kobj, KOBJ_ONLINE); - break; - default: - ret = -EINVAL; - } + ret = cpu_down(dev->id); cpu_hotplug_driver_unlock(); - - if (ret >= 0) - ret = count; return ret; } -static DEVICE_ATTR(online, 0644, show_online, store_online); -static void __cpuinit register_cpu_control(struct cpu *cpu) -{ - device_create_file(&cpu->dev, &dev_attr_online); -} void unregister_cpu(struct cpu *cpu) { int logical_cpu = cpu->dev.id; unregister_cpu_under_node(logical_cpu, cpu_to_node(logical_cpu)); - device_remove_file(&cpu->dev, &dev_attr_online); - device_unregister(&cpu->dev); per_cpu(cpu_sys_devices, logical_cpu) = NULL; return; @@ -123,12 +93,18 @@ static DEVICE_ATTR(probe, S_IWUSR, NULL, cpu_probe_store); static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store); #endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */ -#else /* ... !CONFIG_HOTPLUG_CPU */ -static inline void register_cpu_control(struct cpu *cpu) -{ -} #endif /* CONFIG_HOTPLUG_CPU */ +struct bus_type cpu_subsys = { + .name = "cpu", + .dev_name = "cpu", +#ifdef CONFIG_HOTPLUG_CPU + .online = cpu_subsys_online, + .offline = cpu_subsys_offline, +#endif +}; +EXPORT_SYMBOL_GPL(cpu_subsys); + #ifdef CONFIG_KEXEC #include @@ -277,12 +253,11 @@ int __cpuinit register_cpu(struct cpu *cpu, int num) cpu->dev.id = num; cpu->dev.bus = &cpu_subsys; cpu->dev.release = cpu_device_release; + cpu->dev.offline_disabled = !cpu->hotpluggable; #ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE cpu->dev.bus->uevent = arch_cpu_uevent; #endif error = device_register(&cpu->dev); - if (!error && cpu->hotpluggable) - register_cpu_control(cpu); if (!error) per_cpu(cpu_sys_devices, num) = &cpu->dev; if (!error) -- cgit v1.2.3 From ac212b6980d8d5eda705864fc5a8ecddc6d6eacc Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 May 2013 00:26:22 +0200 Subject: ACPI / processor: Use common hotplug infrastructure Split the ACPI processor driver into two parts, one that is non-modular, resides in the ACPI core and handles the enumeration and hotplug of processors and one that implements the rest of the existing processor driver functionality. The non-modular part uses an ACPI scan handler object to enumerate processors on the basis of information provided by the ACPI namespace and to hook up with the common ACPI hotplug infrastructure. It also populates the ACPI handle of each processor device having a corresponding object in the ACPI namespace, which allows the driver proper to bind to those devices, and makes the driver bind to them if it is readily available (i.e. loaded) when the scan handler's .attach() routine is running. There are a few reasons to make this change. First, switching the ACPI processor driver to using the common ACPI hotplug infrastructure reduces code duplication and size considerably, even though a new file is created along with a header comment etc. Second, since the common hotplug code attempts to offline devices before starting the (non-reversible) removal procedure, it will abort (and possibly roll back) hot-remove operations involving processors if cpu_down() returns an error code for one of them instead of continuing them blindly (if /sys/firmware/acpi/hotplug/force_remove is unset). That is a more desirable behavior than what the current code does. Finally, the separation of the scan/hotplug part from the driver proper makes it possible to simplify the driver's .remove() routine, because it doesn't need to worry about the possible cleanup related to processor removal any more (the scan/hotplug part is responsible for that now) and can handle device removal and driver removal symmetricaly (i.e. as appropriate). Some user-visible changes in sysfs are made (for example, the 'sysdev' link from the ACPI device node to the processor device's directory is gone and a 'physical_node' link is present instead and a corresponding 'firmware_node' is present in the processor device's directory, the processor driver is now visible under /sys/bus/cpu/drivers/ and bound to the processor device), but that shouldn't affect the functionality that users care about (frequency scaling, C-states and thermal management). Tested on my venerable Toshiba Portege R500. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: Toshi Kani --- drivers/base/cpu.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 25c8768172e9..7431ba6fc2d4 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -13,11 +13,21 @@ #include #include #include +#include #include "base.h" static DEFINE_PER_CPU(struct device *, cpu_sys_devices); +static int cpu_subsys_match(struct device *dev, struct device_driver *drv) +{ + /* ACPI style match is the only one that may succeed. */ + if (acpi_driver_match_device(dev, drv)) + return 1; + + return 0; +} + #ifdef CONFIG_HOTPLUG_CPU static void change_cpu_under_node(struct cpu *cpu, unsigned int from_nid, unsigned int to_nid) @@ -98,6 +108,7 @@ static DEVICE_ATTR(release, S_IWUSR, NULL, cpu_release_store); struct bus_type cpu_subsys = { .name = "cpu", .dev_name = "cpu", + .match = cpu_subsys_match, #ifdef CONFIG_HOTPLUG_CPU .online = cpu_subsys_online, .offline = cpu_subsys_offline, -- cgit v1.2.3 From 4960e05e22604ee270a023f968e0e4f9bd0c6fef Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 8 May 2013 14:18:37 +0200 Subject: Driver core: Introduce offline/online callbacks for memory blocks Introduce .offline() and .online() callbacks for memory_subsys that will allow the generic device_offline() and device_online() to be used with device objects representing memory blocks. That, in turn, allows the ACPI subsystem to use device_offline() to put removable memory blocks offline, if possible, before removing memory modules holding them. The 'online' sysfs attribute of memory block devices will attempt to put them offline if 0 is written to it and will attempt to apply the previously used online type when onlining them (i.e. when 1 is written to it). Signed-off-by: Rafael J. Wysocki Tested-by: Vasilis Liaskovitis Acked-by: Greg Kroah-Hartman Reviewed-by: Toshi Kani --- drivers/base/memory.c | 112 +++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 87 insertions(+), 25 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 14f8a6954da0..c8f3b63fcacd 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -37,9 +37,14 @@ static inline int base_memory_block_id(int section_nr) return section_nr / sections_per_block; } +static int memory_subsys_online(struct device *dev); +static int memory_subsys_offline(struct device *dev); + static struct bus_type memory_subsys = { .name = MEMORY_CLASS_NAME, .dev_name = MEMORY_CLASS_NAME, + .online = memory_subsys_online, + .offline = memory_subsys_offline, }; static BLOCKING_NOTIFIER_HEAD(memory_chain); @@ -88,6 +93,7 @@ int register_memory(struct memory_block *memory) memory->dev.bus = &memory_subsys; memory->dev.id = memory->start_section_nr / sections_per_block; memory->dev.release = memory_block_release; + memory->dev.offline = memory->state == MEM_OFFLINE; error = device_register(&memory->dev); return error; @@ -278,33 +284,70 @@ static int __memory_block_change_state(struct memory_block *mem, { int ret = 0; - if (mem->state != from_state_req) { - ret = -EINVAL; - goto out; - } + if (mem->state != from_state_req) + return -EINVAL; if (to_state == MEM_OFFLINE) mem->state = MEM_GOING_OFFLINE; ret = memory_block_action(mem->start_section_nr, to_state, online_type); - if (ret) { mem->state = from_state_req; - goto out; + } else { + mem->state = to_state; + if (to_state == MEM_ONLINE) + mem->last_online = online_type; } + return ret; +} - mem->state = to_state; - switch (mem->state) { - case MEM_OFFLINE: - kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE); - break; - case MEM_ONLINE: - kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE); - break; - default: - break; +static int memory_subsys_online(struct device *dev) +{ + struct memory_block *mem = container_of(dev, struct memory_block, dev); + int ret; + + mutex_lock(&mem->state_mutex); + + ret = mem->state == MEM_ONLINE ? 0 : + __memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, + mem->last_online); + + mutex_unlock(&mem->state_mutex); + return ret; +} + +static int memory_subsys_offline(struct device *dev) +{ + struct memory_block *mem = container_of(dev, struct memory_block, dev); + int ret; + + mutex_lock(&mem->state_mutex); + + ret = mem->state == MEM_OFFLINE ? 0 : + __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1); + + mutex_unlock(&mem->state_mutex); + return ret; +} + +static int __memory_block_change_state_uevent(struct memory_block *mem, + unsigned long to_state, unsigned long from_state_req, + int online_type) +{ + int ret = __memory_block_change_state(mem, to_state, from_state_req, + online_type); + if (!ret) { + switch (mem->state) { + case MEM_OFFLINE: + kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE); + break; + case MEM_ONLINE: + kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE); + break; + default: + break; + } } -out: return ret; } @@ -315,8 +358,8 @@ static int memory_block_change_state(struct memory_block *mem, int ret; mutex_lock(&mem->state_mutex); - ret = __memory_block_change_state(mem, to_state, from_state_req, - online_type); + ret = __memory_block_change_state_uevent(mem, to_state, from_state_req, + online_type); mutex_unlock(&mem->state_mutex); return ret; @@ -326,22 +369,34 @@ store_mem_state(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct memory_block *mem; + bool offline; int ret = -EINVAL; mem = container_of(dev, struct memory_block, dev); - if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) + lock_device_hotplug(); + + if (!strncmp(buf, "online_kernel", min_t(int, count, 13))) { + offline = false; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_KERNEL); - else if (!strncmp(buf, "online_movable", min_t(int, count, 14))) + } else if (!strncmp(buf, "online_movable", min_t(int, count, 14))) { + offline = false; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_MOVABLE); - else if (!strncmp(buf, "online", min_t(int, count, 6))) + } else if (!strncmp(buf, "online", min_t(int, count, 6))) { + offline = false; ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, ONLINE_KEEP); - else if(!strncmp(buf, "offline", min_t(int, count, 7))) + } else if(!strncmp(buf, "offline", min_t(int, count, 7))) { + offline = true; ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1); + } + if (!ret) + dev->offline = offline; + + unlock_device_hotplug(); if (ret) return ret; @@ -563,6 +618,7 @@ static int init_memory_block(struct memory_block **memory, base_memory_block_id(scn_nr) * sections_per_block; mem->end_section_nr = mem->start_section_nr + sections_per_block - 1; mem->state = state; + mem->last_online = ONLINE_KEEP; mem->section_count++; mutex_init(&mem->state_mutex); start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -681,14 +737,20 @@ int unregister_memory_section(struct mem_section *section) /* * offline one memory block. If the memory block has been offlined, do nothing. + * + * Call under device_hotplug_lock. */ int offline_memory_block(struct memory_block *mem) { int ret = 0; mutex_lock(&mem->state_mutex); - if (mem->state != MEM_OFFLINE) - ret = __memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE, -1); + if (mem->state != MEM_OFFLINE) { + ret = __memory_block_change_state_uevent(mem, MEM_OFFLINE, + MEM_ONLINE, -1); + if (!ret) + mem->dev.offline = true; + } mutex_unlock(&mem->state_mutex); return ret; -- cgit v1.2.3 From 1001b4d4a8ee6b2e7a6078a02ccdf68f91b192bd Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Thu, 30 May 2013 00:30:05 +0200 Subject: CPU: Fix sysfs cpu/online of offlined CPUs As reported by Dave Hansen, sysfs cpu/online shows 1 for offlined CPUs at boot. Fix this problem by initializing dev.offline with cpu_online() when registering a CPU. References: https://lkml.org/lkml/2013/5/29/403 Reported-and-tested-by: Dave Hansen Signed-off-by: Toshi Kani Signed-off-by: Rafael J. Wysocki --- drivers/base/cpu.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers/base') diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 7431ba6fc2d4..1d110dc6f0c1 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -265,6 +265,7 @@ int __cpuinit register_cpu(struct cpu *cpu, int num) cpu->dev.bus = &cpu_subsys; cpu->dev.release = cpu_device_release; cpu->dev.offline_disabled = !cpu->hotpluggable; + cpu->dev.offline = !cpu_online(num); #ifdef CONFIG_ARCH_HAS_CPU_AUTOPROBE cpu->dev.bus->uevent = arch_cpu_uevent; #endif -- cgit v1.2.3 From b2c064b25ad07169b2892a733918e6b941bf3366 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 23 May 2013 10:38:55 +0200 Subject: Driver core / memory: Simplify __memory_block_change_state() As noted by Tang Chen, the last_online field in struct memory_block introduced by commit 4960e05 (Driver core: Introduce offline/online callbacks for memory blocks) is not really necessary, because online_pages() restores the previous state if passed ONLINE_KEEP as the last argument. Therefore, remove that field along with the code referring to it. References: http://marc.info/?l=linux-kernel&m=136919777305599&w=2 Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Reviewed-by: Tang Chen --- drivers/base/memory.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index c8f3b63fcacd..c7092bc3c01e 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -291,13 +291,7 @@ static int __memory_block_change_state(struct memory_block *mem, mem->state = MEM_GOING_OFFLINE; ret = memory_block_action(mem->start_section_nr, to_state, online_type); - if (ret) { - mem->state = from_state_req; - } else { - mem->state = to_state; - if (to_state == MEM_ONLINE) - mem->last_online = online_type; - } + mem->state = ret ? from_state_req : to_state; return ret; } @@ -310,7 +304,7 @@ static int memory_subsys_online(struct device *dev) ret = mem->state == MEM_ONLINE ? 0 : __memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE, - mem->last_online); + ONLINE_KEEP); mutex_unlock(&mem->state_mutex); return ret; @@ -618,7 +612,6 @@ static int init_memory_block(struct memory_block **memory, base_memory_block_id(scn_nr) * sections_per_block; mem->end_section_nr = mem->start_section_nr + sections_per_block - 1; mem->state = state; - mem->last_online = ONLINE_KEEP; mem->section_count++; mutex_init(&mem->state_mutex); start_pfn = section_nr_to_pfn(mem->start_section_nr); -- cgit v1.2.3 From ea50be59345a2b714fd3ed43e1bba89906c177c3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 23 May 2013 10:41:50 +0200 Subject: Driver core / MM: Drop offline_memory_block() Since offline_memory_block(mem) is functionally equivalent to device_offline(&mem->dev), make the only caller of the former use the latter instead and drop offline_memory_block() entirely. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Toshi Kani --- drivers/base/memory.c | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index c7092bc3c01e..4ebf97f99fae 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -728,27 +728,6 @@ int unregister_memory_section(struct mem_section *section) } #endif /* CONFIG_MEMORY_HOTREMOVE */ -/* - * offline one memory block. If the memory block has been offlined, do nothing. - * - * Call under device_hotplug_lock. - */ -int offline_memory_block(struct memory_block *mem) -{ - int ret = 0; - - mutex_lock(&mem->state_mutex); - if (mem->state != MEM_OFFLINE) { - ret = __memory_block_change_state_uevent(mem, MEM_OFFLINE, - MEM_ONLINE, -1); - if (!ret) - mem->dev.offline = true; - } - mutex_unlock(&mem->state_mutex); - - return ret; -} - /* return true if the memory block is offlined, otherwise, return false */ bool is_memblock_offlined(struct memory_block *mem) { -- cgit v1.2.3 From 45f0a85c8258741d11bda25c0a5669c06267204a Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 3 Jun 2013 21:49:52 +0200 Subject: PM / Runtime: Rework the "runtime idle" helper routine The "runtime idle" helper routine, rpm_idle(), currently ignores return values from .runtime_idle() callbacks executed by it. However, it turns out that many subsystems use pm_generic_runtime_idle() which checks the return value of the driver's callback and executes pm_runtime_suspend() for the device unless that value is not 0. If that logic is moved to rpm_idle() instead, pm_generic_runtime_idle() can be dropped and its users will not need any .runtime_idle() callbacks any more. Moreover, the PCI, SCSI, and SATA subsystems' .runtime_idle() routines, pci_pm_runtime_idle(), scsi_runtime_idle(), and ata_port_runtime_idle(), respectively, as well as a few drivers' ones may be simplified if rpm_idle() calls rpm_suspend() after 0 has been returned by the .runtime_idle() callback executed by it. To reduce overall code bloat, make the changes described above. Tested-by: Mika Westerberg Tested-by: Kevin Hilman Signed-off-by: Rafael J. Wysocki Acked-by: Kevin Hilman Reviewed-by: Ulf Hansson Acked-by: Alan Stern --- drivers/base/platform.c | 1 - drivers/base/power/domain.c | 1 - drivers/base/power/generic_ops.c | 23 ----------------------- drivers/base/power/runtime.c | 12 +++++------- 4 files changed, 5 insertions(+), 32 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 9eda84246ffd..96a930387ebc 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -888,7 +888,6 @@ int platform_pm_restore(struct device *dev) static const struct dev_pm_ops platform_dev_pm_ops = { .runtime_suspend = pm_generic_runtime_suspend, .runtime_resume = pm_generic_runtime_resume, - .runtime_idle = pm_generic_runtime_idle, USE_PLATFORM_PM_SLEEP_OPS }; diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 7072404c8b6d..bfb8955c406c 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -2143,7 +2143,6 @@ void pm_genpd_init(struct generic_pm_domain *genpd, genpd->max_off_time_changed = true; genpd->domain.ops.runtime_suspend = pm_genpd_runtime_suspend; genpd->domain.ops.runtime_resume = pm_genpd_runtime_resume; - genpd->domain.ops.runtime_idle = pm_generic_runtime_idle; genpd->domain.ops.prepare = pm_genpd_prepare; genpd->domain.ops.suspend = pm_genpd_suspend; genpd->domain.ops.suspend_late = pm_genpd_suspend_late; diff --git a/drivers/base/power/generic_ops.c b/drivers/base/power/generic_ops.c index bfd898b8988e..5ee030a864f9 100644 --- a/drivers/base/power/generic_ops.c +++ b/drivers/base/power/generic_ops.c @@ -11,29 +11,6 @@ #include #ifdef CONFIG_PM_RUNTIME -/** - * pm_generic_runtime_idle - Generic runtime idle callback for subsystems. - * @dev: Device to handle. - * - * If PM operations are defined for the @dev's driver and they include - * ->runtime_idle(), execute it and return its error code, if nonzero. - * Otherwise, execute pm_runtime_suspend() for the device and return 0. - */ -int pm_generic_runtime_idle(struct device *dev) -{ - const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; - - if (pm && pm->runtime_idle) { - int ret = pm->runtime_idle(dev); - if (ret) - return ret; - } - - pm_runtime_suspend(dev); - return 0; -} -EXPORT_SYMBOL_GPL(pm_generic_runtime_idle); - /** * pm_generic_runtime_suspend - Generic runtime suspend callback for subsystems. * @dev: Device to suspend. diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index ef13ad08afb2..268a35097578 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -293,11 +293,8 @@ static int rpm_idle(struct device *dev, int rpmflags) /* Pending requests need to be canceled. */ dev->power.request = RPM_REQ_NONE; - if (dev->power.no_callbacks) { - /* Assume ->runtime_idle() callback would have suspended. */ - retval = rpm_suspend(dev, rpmflags); + if (dev->power.no_callbacks) goto out; - } /* Carry out an asynchronous or a synchronous idle notification. */ if (rpmflags & RPM_ASYNC) { @@ -306,7 +303,8 @@ static int rpm_idle(struct device *dev, int rpmflags) dev->power.request_pending = true; queue_work(pm_wq, &dev->power.work); } - goto out; + trace_rpm_return_int(dev, _THIS_IP_, 0); + return 0; } dev->power.idle_notification = true; @@ -326,14 +324,14 @@ static int rpm_idle(struct device *dev, int rpmflags) callback = dev->driver->pm->runtime_idle; if (callback) - __rpm_callback(callback, dev); + retval = __rpm_callback(callback, dev); dev->power.idle_notification = false; wake_up_all(&dev->power.wait_queue); out: trace_rpm_return_int(dev, _THIS_IP_, retval); - return retval; + return retval ? retval : rpm_suspend(dev, rpmflags); } /** -- cgit v1.2.3 From 5070158804b5339c71809f5e673cea1cfacd804d Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Sat, 30 Mar 2013 16:25:15 +0530 Subject: cpufreq: rename index as driver_data in cpufreq_frequency_table The "index" field of struct cpufreq_frequency_table was never an index and isn't used at all by the cpufreq core. It only is useful for cpufreq drivers for their internal purposes. Many people nowadays blindly set it in ascending order with the assumption that the core will use it, which is a mistake. Rename it to "driver_data" as that's what its purpose is. All of its users are updated accordingly. [rjw: Changelog] Signed-off-by: Viresh Kumar Acked-by: Simon Horman Signed-off-by: Rafael J. Wysocki --- drivers/base/power/opp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index f0077cb8e249..c8ec186303db 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -648,14 +648,14 @@ int opp_init_cpufreq_table(struct device *dev, list_for_each_entry(opp, &dev_opp->opp_list, node) { if (opp->available) { - freq_table[i].index = i; + freq_table[i].driver_data = i; freq_table[i].frequency = opp->rate / 1000; i++; } } mutex_unlock(&dev_opp_list_lock); - freq_table[i].index = i; + freq_table[i].driver_data = i; freq_table[i].frequency = CPUFREQ_TABLE_END; *table = &freq_table[0]; -- cgit v1.2.3 From 9350de06be45a5a8b927ac6577c9d35de61c90ca Mon Sep 17 00:00:00 2001 From: Bernie Thompson Date: Sat, 1 Jun 2013 00:47:43 +0000 Subject: PM / wakeup: Adjust messaging for wake events during suspend This adds in a new message to the wakeup code which adds an indication to the log that suspend was cancelled due to a wake event occouring during the suspend sequence. It also adjusts the message printed in suspend.c to reflect the potential that a suspend was aborted, as opposed to a device failing to suspend. Without these message adjustments one can end up with a kernel log that says that a device failed to suspend with no actual device suspend failures, which can be confusing to the log examiner. Signed-off-by: Bernie Thompson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/wakeup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 79715e7fa43e..407a2efa10bb 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -707,8 +707,10 @@ bool pm_wakeup_pending(void) } spin_unlock_irqrestore(&events_lock, flags); - if (ret) + if (ret) { + pr_info("PM: Wakeup pending, aborting suspend\n"); print_active_wakeup_sources(); + } return ret; } -- cgit v1.2.3 From bb177fedd348c92c2bea6adc9a2163ebff15272e Mon Sep 17 00:00:00 2001 From: Julius Werner Date: Wed, 12 Jun 2013 12:55:22 -0700 Subject: PM / Sleep: Print last wakeup source on failed wakeup_count write Commit a938da06 introduced a useful little log message to tell users/debuggers which wakeup source aborted a suspend. However, this message is only printed if the abort happens during the in-kernel suspend path (after writing /sys/power/state). The full specification of the /sys/power/wakeup_count facility allows user-space power managers to double-check if wakeups have already happened before it actually tries to suspend (e.g. while it was running user-space pre-suspend hooks), by writing the last known wakeup_count value to /sys/power/wakeup_count. This patch changes the sysfs handler for that node to also print said log message if that write fails, so that we can figure out the offending wakeup source for both kinds of suspend aborts. Signed-off-by: Julius Werner Signed-off-by: Rafael J. Wysocki --- drivers/base/power/wakeup.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 407a2efa10bb..2d56f4113ae7 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -659,7 +659,7 @@ void pm_wakeup_event(struct device *dev, unsigned int msec) } EXPORT_SYMBOL_GPL(pm_wakeup_event); -static void print_active_wakeup_sources(void) +void pm_print_active_wakeup_sources(void) { struct wakeup_source *ws; int active = 0; @@ -683,6 +683,7 @@ static void print_active_wakeup_sources(void) last_activity_ws->name); rcu_read_unlock(); } +EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources); /** * pm_wakeup_pending - Check if power transition in progress should be aborted. @@ -709,7 +710,7 @@ bool pm_wakeup_pending(void) if (ret) { pr_info("PM: Wakeup pending, aborting suspend\n"); - print_active_wakeup_sources(); + pm_print_active_wakeup_sources(); } return ret; -- cgit v1.2.3 From 96d9d0b5dc17e80cefbd7c5be15a5072d33513f8 Mon Sep 17 00:00:00 2001 From: Sahara Date: Fri, 21 Jun 2013 11:12:30 +0900 Subject: PM / QoS: Add dev_pm_qos_request tracepoints Adds tracepoints to dev_pm_qos_add_request, dev_pm_qos_update_request, and dev_pm_qos_remove_request. It's useful for checking device name, dev_pm_qos_request_type, and value. Signed-off-by: Sahara Signed-off-by: Rafael J. Wysocki --- drivers/base/power/qos.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'drivers/base') diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c index 71671c42ef45..5c1361a9e5dd 100644 --- a/drivers/base/power/qos.c +++ b/drivers/base/power/qos.c @@ -42,6 +42,7 @@ #include #include #include +#include #include "power.h" @@ -305,6 +306,7 @@ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req, else if (!dev->power.qos) ret = dev_pm_qos_constraints_allocate(dev); + trace_dev_pm_qos_add_request(dev_name(dev), type, value); if (!ret) { req->dev = dev; req->type = type; @@ -349,6 +351,8 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req, return -EINVAL; } + trace_dev_pm_qos_update_request(dev_name(req->dev), req->type, + new_value); if (curr_value != new_value) ret = apply_constraint(req, PM_QOS_UPDATE_REQ, new_value); @@ -398,6 +402,8 @@ static int __dev_pm_qos_remove_request(struct dev_pm_qos_request *req) if (IS_ERR_OR_NULL(req->dev->power.qos)) return -ENODEV; + trace_dev_pm_qos_remove_request(dev_name(req->dev), req->type, + PM_QOS_DEFAULT_VALUE); ret = apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE); memset(req, 0, sizeof(*req)); return ret; -- cgit v1.2.3