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 --- include/linux/device.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index c0a126125325..eeb33315514c 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -71,6 +71,10 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *); * the specific driver's probe to initial the matched device. * @remove: Called when a device removed from this bus. * @shutdown: Called at shut-down time to quiesce the device. + * + * @online: Called to put the device back online (after offlining it). + * @offline: Called to put the device offline for hot-removal. May fail. + * * @suspend: Called when a device on this bus wants to go to sleep mode. * @resume: Called to bring a device on this bus out of sleep mode. * @pm: Power management operations of this bus, callback the specific @@ -104,6 +108,9 @@ struct bus_type { int (*remove)(struct device *dev); void (*shutdown)(struct device *dev); + int (*online)(struct device *dev); + int (*offline)(struct device *dev); + int (*suspend)(struct device *dev, pm_message_t state); int (*resume)(struct device *dev); @@ -648,6 +655,8 @@ struct acpi_dev_node { * @release: Callback to free the device after all references have * gone away. This should be set by the allocator of the * device (i.e. the bus driver that discovered the device). + * @offline_disabled: If set, the device is permanently online. + * @offline: Set after successful invocation of bus type's .offline(). * * At the lowest level, every device in a Linux system is represented by an * instance of struct device. The device structure contains the information @@ -720,6 +729,9 @@ struct device { void (*release)(struct device *dev); struct iommu_group *iommu_group; + + bool offline_disabled:1; + bool offline:1; }; static inline struct device *kobj_to_dev(struct kobject *kobj) @@ -856,6 +868,15 @@ extern const char *device_get_devnode(struct device *dev, extern void *dev_get_drvdata(const struct device *dev); extern int dev_set_drvdata(struct device *dev, void *data); +static inline bool device_supports_offline(struct device *dev) +{ + return dev->bus && dev->bus->offline && dev->bus->online; +} + +extern void lock_device_hotplug(void); +extern void unlock_device_hotplug(void); +extern int device_offline(struct device *dev); +extern int device_online(struct device *dev); /* * Root device objects for grouping under /sys/devices */ -- cgit v1.2.3 From e2ff39400d81233374e780b133496a2296643d7d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 8 May 2013 00:29:49 +0200 Subject: ACPI / memhotplug: Bind removable memory blocks to ACPI device nodes During ACPI memory hotplug configuration bind memory blocks residing in modules removable through the standard ACPI mechanism to struct acpi_device objects associated with ACPI namespace objects representing those modules. Accordingly, unbind those memory blocks from the struct acpi_device objects when the memory modules in question are being removed. When "offline" operation for devices representing memory blocks is introduced, this will allow the ACPI core's device hot-remove code to use it to carry out remove_memory() for those memory blocks and check the results of that before it actually removes the modules holding them from the system. Since walk_memory_range() is used for accessing all memory blocks corresponding to a given ACPI namespace object, it is exported from memory_hotplug.c so that the code in acpi_memhotplug.c can use it. Signed-off-by: Rafael J. Wysocki Tested-by: Vasilis Liaskovitis Reviewed-by: Toshi Kani --- include/linux/memory_hotplug.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 3e622c610925..2975b7b2a9d8 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -245,6 +245,8 @@ static inline int is_mem_section_removable(unsigned long pfn, static inline void try_offline_node(int nid) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ +extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, + void *arg, int (*func)(struct memory_block *, void *)); extern int mem_online_node(int nid); extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); -- 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 --- include/linux/memory.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 85c31a8e2904..3d5346583022 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -26,6 +26,7 @@ struct memory_block { unsigned long start_section_nr; unsigned long end_section_nr; unsigned long state; + int last_online; int section_count; /* -- 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 --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 3d5346583022..85c31a8e2904 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -26,7 +26,6 @@ struct memory_block { unsigned long start_section_nr; unsigned long end_section_nr; unsigned long state; - int last_online; int section_count; /* -- 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 --- include/linux/memory_hotplug.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2975b7b2a9d8..ae5480a00963 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -251,7 +251,6 @@ extern int mem_online_node(int nid); extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); -extern int offline_memory_block(struct memory_block *mem); extern bool is_memblock_offlined(struct memory_block *mem); extern int remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, -- cgit v1.2.3 From 242831eb15a06fa4414eaa705fdc6dd432ab98d1 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Mon, 27 May 2013 12:58:46 +0200 Subject: Memory hotplug / ACPI: Simplify memory removal Now that the memory offlining should be taken care of by the companion device offlining code in acpi_scan_hot_remove(), the ACPI memory hotplug driver doesn't need to offline it in remove_memory() any more. Moreover, since the return value of remove_memory() is not used, it's better to make it be a void function and trigger a BUG() if the memory scheduled for removal is not offline. Change the code in accordance with the above observations. Signed-off-by: Rafael J. Wysocki Reviewed-by: Toshi Kani --- include/linux/memory_hotplug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ae5480a00963..00569fb4ed6a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -252,7 +252,7 @@ extern int add_memory(int nid, u64 start, u64 size); extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); -extern int remove_memory(int nid, u64 start, u64 size); +extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, int nr_pages); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms); -- cgit v1.2.3 From aba6efc47133af4941cda16e690f71b7ad894da2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 1 Jun 2013 22:24:07 +0200 Subject: Memory hotplug: Move alternative function definitions to header Move the definitions of offline_pages() and remove_memory() for CONFIG_MEMORY_HOTREMOVE to memory_hotplug.h, where they belong, and make them static inline. Signed-off-by: Rafael J. Wysocki --- include/linux/memory_hotplug.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 00569fb4ed6a..dd38e62b84d2 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -234,6 +234,8 @@ static inline void unlock_memory_hotplug(void) {} extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); extern void try_offline_node(int nid); +extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); +extern void remove_memory(int nid, u64 start, u64 size); #else static inline int is_mem_section_removable(unsigned long pfn, @@ -243,6 +245,13 @@ static inline int is_mem_section_removable(unsigned long pfn, } static inline void try_offline_node(int nid) {} + +static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) +{ + return -EINVAL; +} + +static inline void remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, -- cgit v1.2.3 From 08f502c1c343031f0d126bd00e87dede38269d12 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Tue, 18 Jun 2013 15:06:45 -0600 Subject: ACPI: Do not use CONFIG_ACPI_HOTPLUG_MEMORY_MODULE CONFIG_ACPI_HOTPLUG_MEMORY has been changed to bool (y/n), and its module option is no longer valid. So, stop using CONFIG_ACPI_HOTPLUG_MEMORY_MODULE. Signed-off-by: Toshi Kani Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 17b5b5967641..353ba256f368 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -352,8 +352,7 @@ extern acpi_status acpi_pci_osc_control_set(acpi_handle handle, /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ - (defined(CONFIG_ACPI_HOTPLUG_MEMORY) || \ - defined(CONFIG_ACPI_HOTPLUG_MEMORY_MODULE)) && \ + defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ defined(CONFIG_ACPI_CONTAINER) #define ACPI_HOTPLUG_OST #endif -- cgit v1.2.3