From a5462516aa9942bd68c8769d4bcefa8a7c718300 Mon Sep 17 00:00:00 2001 From: Timur Tabi Date: Mon, 13 Dec 2010 14:08:52 -0600 Subject: driver-core: document restrictions on device_rename() Add text, courtesy of Kay Sievers, that provides some background on device_rename() and why it shouldn't be used. Signed-off-by: Timur Tabi Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index 080e9ca1101..9cd3b5cfcc4 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1551,7 +1551,34 @@ EXPORT_SYMBOL_GPL(device_destroy); * on the same device to ensure that new_name is valid and * won't conflict with other devices. * - * "Never use this function, bad things will happen" - gregkh + * Note: Don't call this function. Currently, the networking layer calls this + * function, but that will change. The following text from Kay Sievers offers + * some insight: + * + * Renaming devices is racy at many levels, symlinks and other stuff are not + * replaced atomically, and you get a "move" uevent, but it's not easy to + * connect the event to the old and new device. Device nodes are not renamed at + * all, there isn't even support for that in the kernel now. + * + * In the meantime, during renaming, your target name might be taken by another + * driver, creating conflicts. Or the old name is taken directly after you + * renamed it -- then you get events for the same DEVPATH, before you even see + * the "move" event. It's just a mess, and nothing new should ever rely on + * kernel device renaming. Besides that, it's not even implemented now for + * other things than (driver-core wise very simple) network devices. + * + * We are currently about to change network renaming in udev to completely + * disallow renaming of devices in the same namespace as the kernel uses, + * because we can't solve the problems properly, that arise with swapping names + * of multiple interfaces without races. Means, renaming of eth[0-9]* will only + * be allowed to some other name than eth[0-9]*, for the aforementioned + * reasons. + * + * Make up a "real" name in the driver before you register anything, or add + * some other attributes for userspace to find the device, or use udev to add + * symlinks -- but never rename kernel devices later, it's a complete mess. We + * don't even want to get into that and try to implement the missing pieces in + * the core. We really have other pieces to fix in the driver core mess. :) */ int device_rename(struct device *dev, const char *new_name) { -- cgit v1.2.3-70-g09d2 From 072fc8f0a8df9bf36392f15b729044cb2ad27332 Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Wed, 26 Jan 2011 18:33:32 +0800 Subject: firmware_classs: change val uevent's type to bool Some place in firmware_class.c using "int uevent" define, but others use "bool uevent". This patch replace all int uevent define to bool. Signed-off-by: Bob Liu Acked-by: Dmitry Torokhov Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_class.c | 7 +++---- include/linux/firmware.h | 4 ++-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c index 40af43ebd92..8c798ef7f13 100644 --- a/drivers/base/firmware_class.c +++ b/drivers/base/firmware_class.c @@ -593,8 +593,7 @@ int request_firmware(const struct firmware **firmware_p, const char *name, struct device *device) { - int uevent = 1; - return _request_firmware(firmware_p, name, device, uevent, false); + return _request_firmware(firmware_p, name, device, true, false); } /** @@ -618,7 +617,7 @@ struct firmware_work { struct device *device; void *context; void (*cont)(const struct firmware *fw, void *context); - int uevent; + bool uevent; }; static int request_firmware_work_func(void *arg) @@ -661,7 +660,7 @@ static int request_firmware_work_func(void *arg) **/ int request_firmware_nowait( - struct module *module, int uevent, + struct module *module, bool uevent, const char *name, struct device *device, gfp_t gfp, void *context, void (*cont)(const struct firmware *fw, void *context)) { diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 53d1e6c4f84..21b3e7588ab 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -39,7 +39,7 @@ struct builtin_fw { int request_firmware(const struct firmware **fw, const char *name, struct device *device); int request_firmware_nowait( - struct module *module, int uevent, + struct module *module, bool uevent, const char *name, struct device *device, gfp_t gfp, void *context, void (*cont)(const struct firmware *fw, void *context)); @@ -52,7 +52,7 @@ static inline int request_firmware(const struct firmware **fw, return -EINVAL; } static inline int request_firmware_nowait( - struct module *module, int uevent, + struct module *module, bool uevent, const char *name, struct device *device, gfp_t gfp, void *context, void (*cont)(const struct firmware *fw, void *context)) { -- cgit v1.2.3-70-g09d2 From 345279bc105e5a331ee81b0e8446b61f2c155784 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 1 Feb 2011 17:19:57 +0100 Subject: sysdev: Fixup warning message Use gcc's __func__ instead of the function name. Signed-off-by: Borislav Petkov Signed-off-by: Greg Kroah-Hartman --- drivers/base/sys.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/sys.c b/drivers/base/sys.c index 1667aaf4fde..b094e0d6139 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -181,8 +181,8 @@ int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv) int err = 0; if (!cls) { - WARN(1, KERN_WARNING "sysdev: invalid class passed to " - "sysdev_driver_register!\n"); + WARN(1, KERN_WARNING "sysdev: invalid class passed to %s!\n", + __func__); return -EINVAL; } -- cgit v1.2.3-70-g09d2 From f4203e3032e5ae74c3e89df85a5a6d96022d0c49 Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Tue, 1 Feb 2011 17:19:56 +0100 Subject: sysdev: Do not register with sysdev when erroring on add When encountering an error while executing the driver's ->add method, we should cancel registration and unwind what we've regged so far. The low level ->add methods do return proper error codes but those aren't looked at in sysdev_driver_register(). Fix that by sharing the unregistering code. Signed-off-by: Borislav Petkov Signed-off-by: Greg Kroah-Hartman --- drivers/base/sys.c | 61 +++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 44 insertions(+), 17 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/sys.c b/drivers/base/sys.c index b094e0d6139..f6fb5474160 100644 --- a/drivers/base/sys.c +++ b/drivers/base/sys.c @@ -166,6 +166,36 @@ EXPORT_SYMBOL_GPL(sysdev_class_unregister); static DEFINE_MUTEX(sysdev_drivers_lock); +/* + * @dev != NULL means that we're unwinding because some drv->add() + * failed for some reason. You need to grab sysdev_drivers_lock before + * calling this. + */ +static void __sysdev_driver_remove(struct sysdev_class *cls, + struct sysdev_driver *drv, + struct sys_device *from_dev) +{ + struct sys_device *dev = from_dev; + + list_del_init(&drv->entry); + if (!cls) + return; + + if (!drv->remove) + goto kset_put; + + if (dev) + list_for_each_entry_continue_reverse(dev, &cls->kset.list, + kobj.entry) + drv->remove(dev); + else + list_for_each_entry(dev, &cls->kset.list, kobj.entry) + drv->remove(dev); + +kset_put: + kset_put(&cls->kset); +} + /** * sysdev_driver_register - Register auxillary driver * @cls: Device class driver belongs to. @@ -175,9 +205,9 @@ static DEFINE_MUTEX(sysdev_drivers_lock); * called on each operation on devices of that class. The refcount * of @cls is incremented. */ - int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv) { + struct sys_device *dev = NULL; int err = 0; if (!cls) { @@ -198,19 +228,27 @@ int sysdev_driver_register(struct sysdev_class *cls, struct sysdev_driver *drv) /* If devices of this class already exist, tell the driver */ if (drv->add) { - struct sys_device *dev; - list_for_each_entry(dev, &cls->kset.list, kobj.entry) - drv->add(dev); + list_for_each_entry(dev, &cls->kset.list, kobj.entry) { + err = drv->add(dev); + if (err) + goto unwind; + } } } else { err = -EINVAL; WARN(1, KERN_ERR "%s: invalid device class\n", __func__); } + + goto unlock; + +unwind: + __sysdev_driver_remove(cls, drv, dev); + +unlock: mutex_unlock(&sysdev_drivers_lock); return err; } - /** * sysdev_driver_unregister - Remove an auxillary driver. * @cls: Class driver belongs to. @@ -220,23 +258,12 @@ void sysdev_driver_unregister(struct sysdev_class *cls, struct sysdev_driver *drv) { mutex_lock(&sysdev_drivers_lock); - list_del_init(&drv->entry); - if (cls) { - if (drv->remove) { - struct sys_device *dev; - list_for_each_entry(dev, &cls->kset.list, kobj.entry) - drv->remove(dev); - } - kset_put(&cls->kset); - } + __sysdev_driver_remove(cls, drv, NULL); mutex_unlock(&sysdev_drivers_lock); } - EXPORT_SYMBOL_GPL(sysdev_driver_register); EXPORT_SYMBOL_GPL(sysdev_driver_unregister); - - /** * sysdev_register - add a system device to the tree * @sysdev: device in question -- cgit v1.2.3-70-g09d2 From 0c2c99b1b8ab5d294f176d631e945ebdefcce4cd Mon Sep 17 00:00:00 2001 From: Nathan Fontenot Date: Thu, 20 Jan 2011 10:43:34 -0600 Subject: memory hotplug: Allow memory blocks to span multiple memory sections Update the memory sysfs code such that each sysfs memory directory is now considered a memory block that can span multiple memory sections per memory block. The default size of each memory block is SECTION_SIZE_BITS to maintain the current behavior of having a single memory section per memory block (i.e. one sysfs directory per memory section). For architectures that want to have memory blocks span multiple memory sections they need only define their own memory_block_size_bytes() routine. Update the memory hotplug documentation to reflect the new behaviors of memory blocks reflected in sysfs. Signed-off-by: Nathan Fontenot Reviewed-by: Robin Holt Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Greg Kroah-Hartman --- Documentation/memory-hotplug.txt | 47 ++++++++---- drivers/base/memory.c | 155 +++++++++++++++++++++++++++------------ 2 files changed, 139 insertions(+), 63 deletions(-) (limited to 'drivers/base') diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt index 57e7e9cc187..8f485d72cf2 100644 --- a/Documentation/memory-hotplug.txt +++ b/Documentation/memory-hotplug.txt @@ -126,36 +126,51 @@ config options. -------------------------------- 4 sysfs files for memory hotplug -------------------------------- -All sections have their device information under /sys/devices/system/memory as +All sections have their device information in sysfs. Each section is part of +a memory block under /sys/devices/system/memory as /sys/devices/system/memory/memoryXXX -(XXX is section id.) +(XXX is the section id.) -Now, XXX is defined as start_address_of_section / section_size. +Now, XXX is defined as (start_address_of_section / section_size) of the first +section contained in the memory block. The files 'phys_index' and +'end_phys_index' under each directory report the beginning and end section id's +for the memory block covered by the sysfs directory. It is expected that all +memory sections in this range are present and no memory holes exist in the +range. Currently there is no way to determine if there is a memory hole, but +the existence of one should not affect the hotplug capabilities of the memory +block. For example, assume 1GiB section size. A device for a memory starting at 0x100000000 is /sys/device/system/memory/memory4 (0x100000000 / 1Gib = 4) This device covers address range [0x100000000 ... 0x140000000) -Under each section, you can see 4 files. +Under each section, you can see 4 or 5 files, the end_phys_index file being +a recent addition and not present on older kernels. -/sys/devices/system/memory/memoryXXX/phys_index +/sys/devices/system/memory/memoryXXX/start_phys_index +/sys/devices/system/memory/memoryXXX/end_phys_index /sys/devices/system/memory/memoryXXX/phys_device /sys/devices/system/memory/memoryXXX/state /sys/devices/system/memory/memoryXXX/removable -'phys_index' : read-only and contains section id, same as XXX. -'state' : read-write - at read: contains online/offline state of memory. - at write: user can specify "online", "offline" command -'phys_device': read-only: designed to show the name of physical memory device. - This is not well implemented now. -'removable' : read-only: contains an integer value indicating - whether the memory section is removable or not - removable. A value of 1 indicates that the memory - section is removable and a value of 0 indicates that - it is not removable. +'phys_index' : read-only and contains section id of the first section + in the memory block, same as XXX. +'end_phys_index' : read-only and contains section id of the last section + in the memory block. +'state' : read-write + at read: contains online/offline state of memory. + at write: user can specify "online", "offline" command + which will be performed on al sections in the block. +'phys_device' : read-only: designed to show the name of physical memory + device. This is not well implemented now. +'removable' : read-only: contains an integer value indicating + whether the memory block is removable or not + removable. A value of 1 indicates that the memory + block is removable and a value of 0 indicates that + it is not removable. A memory block is removable only if + every section in the block is removable. NOTE: These directories/files appear after physical memory hotplug phase. diff --git a/drivers/base/memory.c b/drivers/base/memory.c index cafeaaf0428..0b704004258 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -30,6 +30,14 @@ static DEFINE_MUTEX(mem_sysfs_mutex); #define MEMORY_CLASS_NAME "memory" +#define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS) + +static int sections_per_block; + +static inline int base_memory_block_id(int section_nr) +{ + return section_nr / sections_per_block; +} static struct sysdev_class memory_sysdev_class = { .name = MEMORY_CLASS_NAME, @@ -84,28 +92,47 @@ EXPORT_SYMBOL(unregister_memory_isolate_notifier); * register_memory - Setup a sysfs device for a memory block */ static -int register_memory(struct memory_block *memory, struct mem_section *section) +int register_memory(struct memory_block *memory) { int error; memory->sysdev.cls = &memory_sysdev_class; - memory->sysdev.id = __section_nr(section); + memory->sysdev.id = memory->phys_index / sections_per_block; error = sysdev_register(&memory->sysdev); return error; } static void -unregister_memory(struct memory_block *memory, struct mem_section *section) +unregister_memory(struct memory_block *memory) { BUG_ON(memory->sysdev.cls != &memory_sysdev_class); - BUG_ON(memory->sysdev.id != __section_nr(section)); /* drop the ref. we got in remove_memory_block() */ kobject_put(&memory->sysdev.kobj); sysdev_unregister(&memory->sysdev); } +unsigned long __weak memory_block_size_bytes(void) +{ + return MIN_MEMORY_BLOCK_SIZE; +} + +static unsigned long get_memory_block_size(void) +{ + unsigned long block_sz; + + block_sz = memory_block_size_bytes(); + + /* Validate blk_sz is a power of 2 and not less than section size */ + if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) { + WARN_ON(1); + block_sz = MIN_MEMORY_BLOCK_SIZE; + } + + return block_sz; +} + /* * use this as the physical section index that this memsection * uses. @@ -116,7 +143,7 @@ static ssize_t show_mem_phys_index(struct sys_device *dev, { struct memory_block *mem = container_of(dev, struct memory_block, sysdev); - return sprintf(buf, "%08lx\n", mem->phys_index); + return sprintf(buf, "%08lx\n", mem->phys_index / sections_per_block); } /* @@ -125,13 +152,16 @@ static ssize_t show_mem_phys_index(struct sys_device *dev, static ssize_t show_mem_removable(struct sys_device *dev, struct sysdev_attribute *attr, char *buf) { - unsigned long start_pfn; - int ret; + unsigned long i, pfn; + int ret = 1; struct memory_block *mem = container_of(dev, struct memory_block, sysdev); - start_pfn = section_nr_to_pfn(mem->phys_index); - ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION); + for (i = 0; i < sections_per_block; i++) { + pfn = section_nr_to_pfn(mem->phys_index + i); + ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION); + } + return sprintf(buf, "%d\n", ret); } @@ -184,17 +214,14 @@ int memory_isolate_notify(unsigned long val, void *v) * OK to have direct references to sparsemem variables in here. */ static int -memory_block_action(struct memory_block *mem, unsigned long action) +memory_section_action(unsigned long phys_index, unsigned long action) { int i; - unsigned long psection; unsigned long start_pfn, start_paddr; struct page *first_page; int ret; - int old_state = mem->state; - psection = mem->phys_index; - first_page = pfn_to_page(psection << PFN_SECTION_SHIFT); + first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT); /* * The probe routines leave the pages reserved, just @@ -207,8 +234,8 @@ memory_block_action(struct memory_block *mem, unsigned long action) continue; printk(KERN_WARNING "section number %ld page number %d " - "not reserved, was it already online? \n", - psection, i); + "not reserved, was it already online?\n", + phys_index, i); return -EBUSY; } } @@ -219,18 +246,13 @@ memory_block_action(struct memory_block *mem, unsigned long action) ret = online_pages(start_pfn, PAGES_PER_SECTION); break; case MEM_OFFLINE: - mem->state = MEM_GOING_OFFLINE; start_paddr = page_to_pfn(first_page) << PAGE_SHIFT; ret = remove_memory(start_paddr, PAGES_PER_SECTION << PAGE_SHIFT); - if (ret) { - mem->state = old_state; - break; - } break; default: - WARN(1, KERN_WARNING "%s(%p, %ld) unknown action: %ld\n", - __func__, mem, action, action); + WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: " + "%ld\n", __func__, phys_index, action, action); ret = -EINVAL; } @@ -240,7 +262,8 @@ memory_block_action(struct memory_block *mem, unsigned long action) static int memory_block_change_state(struct memory_block *mem, unsigned long to_state, unsigned long from_state_req) { - int ret = 0; + int i, ret = 0; + mutex_lock(&mem->state_mutex); if (mem->state != from_state_req) { @@ -248,8 +271,22 @@ static int memory_block_change_state(struct memory_block *mem, goto out; } - ret = memory_block_action(mem, to_state); - if (!ret) + if (to_state == MEM_OFFLINE) + mem->state = MEM_GOING_OFFLINE; + + for (i = 0; i < sections_per_block; i++) { + ret = memory_section_action(mem->phys_index + i, to_state); + if (ret) + break; + } + + if (ret) { + for (i = 0; i < sections_per_block; i++) + memory_section_action(mem->phys_index + i, + from_state_req); + + mem->state = from_state_req; + } else mem->state = to_state; out: @@ -262,20 +299,15 @@ store_mem_state(struct sys_device *dev, struct sysdev_attribute *attr, const char *buf, size_t count) { struct memory_block *mem; - unsigned int phys_section_nr; int ret = -EINVAL; mem = container_of(dev, struct memory_block, sysdev); - phys_section_nr = mem->phys_index; - - if (!present_section_nr(phys_section_nr)) - goto out; if (!strncmp(buf, "online", min((int)count, 6))) ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); else if(!strncmp(buf, "offline", min((int)count, 7))) ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE); -out: + if (ret) return ret; return count; @@ -315,7 +347,7 @@ static ssize_t print_block_size(struct sysdev_class *class, struct sysdev_class_attribute *attr, char *buf) { - return sprintf(buf, "%lx\n", (unsigned long)PAGES_PER_SECTION * PAGE_SIZE); + return sprintf(buf, "%lx\n", get_memory_block_size()); } static SYSDEV_CLASS_ATTR(block_size_bytes, 0444, print_block_size, NULL); @@ -444,6 +476,7 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section, struct sys_device *sysdev; struct memory_block *mem; char name[sizeof(MEMORY_CLASS_NAME) + 9 + 1]; + int block_id = base_memory_block_id(__section_nr(section)); kobj = hint ? &hint->sysdev.kobj : NULL; @@ -451,7 +484,7 @@ struct memory_block *find_memory_block_hinted(struct mem_section *section, * This only works because we know that section == sysdev->id * slightly redundant with sysdev_register() */ - sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, __section_nr(section)); + sprintf(&name[0], "%s%d", MEMORY_CLASS_NAME, block_id); kobj = kset_find_obj_hinted(&memory_sysdev_class.kset, name, kobj); if (!kobj) @@ -476,26 +509,27 @@ struct memory_block *find_memory_block(struct mem_section *section) return find_memory_block_hinted(section, NULL); } -static int add_memory_block(int nid, struct mem_section *section, - unsigned long state, enum mem_add_context context) +static int init_memory_block(struct memory_block **memory, + struct mem_section *section, unsigned long state) { - struct memory_block *mem = kzalloc(sizeof(*mem), GFP_KERNEL); + struct memory_block *mem; unsigned long start_pfn; + int scn_nr; int ret = 0; + mem = kzalloc(sizeof(*mem), GFP_KERNEL); if (!mem) return -ENOMEM; - mutex_lock(&mem_sysfs_mutex); - - mem->phys_index = __section_nr(section); + scn_nr = __section_nr(section); + mem->phys_index = base_memory_block_id(scn_nr) * sections_per_block; mem->state = state; mem->section_count++; mutex_init(&mem->state_mutex); start_pfn = section_nr_to_pfn(mem->phys_index); mem->phys_device = arch_get_memory_phys_device(start_pfn); - ret = register_memory(mem, section); + ret = register_memory(mem); if (!ret) ret = mem_create_simple_file(mem, phys_index); if (!ret) @@ -504,8 +538,29 @@ static int add_memory_block(int nid, struct mem_section *section, ret = mem_create_simple_file(mem, phys_device); if (!ret) ret = mem_create_simple_file(mem, removable); + + *memory = mem; + return ret; +} + +static int add_memory_section(int nid, struct mem_section *section, + unsigned long state, enum mem_add_context context) +{ + struct memory_block *mem; + int ret = 0; + + mutex_lock(&mem_sysfs_mutex); + + mem = find_memory_block(section); + if (mem) { + mem->section_count++; + kobject_put(&mem->sysdev.kobj); + } else + ret = init_memory_block(&mem, section, state); + if (!ret) { - if (context == HOTPLUG) + if (context == HOTPLUG && + mem->section_count == sections_per_block) ret = register_mem_sect_under_node(mem, nid); } @@ -528,8 +583,10 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, mem_remove_simple_file(mem, state); mem_remove_simple_file(mem, phys_device); mem_remove_simple_file(mem, removable); - unregister_memory(mem, section); - } + unregister_memory(mem); + kfree(mem); + } else + kobject_put(&mem->sysdev.kobj); mutex_unlock(&mem_sysfs_mutex); return 0; @@ -541,7 +598,7 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, */ int register_new_memory(int nid, struct mem_section *section) { - return add_memory_block(nid, section, MEM_OFFLINE, HOTPLUG); + return add_memory_section(nid, section, MEM_OFFLINE, HOTPLUG); } int unregister_memory_section(struct mem_section *section) @@ -560,12 +617,16 @@ int __init memory_dev_init(void) unsigned int i; int ret; int err; + unsigned long block_sz; memory_sysdev_class.kset.uevent_ops = &memory_uevent_ops; ret = sysdev_class_register(&memory_sysdev_class); if (ret) goto out; + block_sz = get_memory_block_size(); + sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE; + /* * Create entries for memory sections that were found * during boot and have been initialized @@ -573,8 +634,8 @@ int __init memory_dev_init(void) for (i = 0; i < NR_MEM_SECTIONS; i++) { if (!present_section_nr(i)) continue; - err = add_memory_block(0, __nr_to_section(i), MEM_ONLINE, - BOOT); + err = add_memory_section(0, __nr_to_section(i), MEM_ONLINE, + BOOT); if (!ret) ret = err; } -- cgit v1.2.3-70-g09d2 From d33601644cd3b09afb2edd9474517edc441c8fad Mon Sep 17 00:00:00 2001 From: Nathan Fontenot Date: Thu, 20 Jan 2011 10:44:29 -0600 Subject: memory hotplug: Update phys_index to [start|end]_section_nr Update the 'phys_index' property of a the memory_block struct to be called start_section_nr, and add a end_section_nr property. The data tracked here is the same but the updated naming is more in line with what is stored here, namely the first and last section number that the memory block spans. The names presented to userspace remain the same, phys_index for start_section_nr and end_phys_index for end_section_nr, to avoid breaking anything in userspace. This also updates the node sysfs code to be aware of the new capability for a memory block to contain multiple memory sections and be aware of the memory block structure name changes (start_section_nr). This requires an additional parameter to unregister_mem_sect_under_nodes so that we know which memory section of the memory block to unregister. Signed-off-by: Nathan Fontenot Reviewed-by: Robin Holt Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Greg Kroah-Hartman --- drivers/base/memory.c | 41 +++++++++++++++++++++++++++++++---------- drivers/base/node.c | 12 ++++++++---- include/linux/memory.h | 3 ++- include/linux/node.h | 6 ++++-- 4 files changed, 45 insertions(+), 17 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 0b704004258..71b4a32b171 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -97,7 +97,7 @@ int register_memory(struct memory_block *memory) int error; memory->sysdev.cls = &memory_sysdev_class; - memory->sysdev.id = memory->phys_index / sections_per_block; + memory->sysdev.id = memory->start_section_nr / sections_per_block; error = sysdev_register(&memory->sysdev); return error; @@ -138,12 +138,26 @@ static unsigned long get_memory_block_size(void) * uses. */ -static ssize_t show_mem_phys_index(struct sys_device *dev, +static ssize_t show_mem_start_phys_index(struct sys_device *dev, struct sysdev_attribute *attr, char *buf) { struct memory_block *mem = container_of(dev, struct memory_block, sysdev); - return sprintf(buf, "%08lx\n", mem->phys_index / sections_per_block); + unsigned long phys_index; + + phys_index = mem->start_section_nr / sections_per_block; + return sprintf(buf, "%08lx\n", phys_index); +} + +static ssize_t show_mem_end_phys_index(struct sys_device *dev, + struct sysdev_attribute *attr, char *buf) +{ + struct memory_block *mem = + container_of(dev, struct memory_block, sysdev); + unsigned long phys_index; + + phys_index = mem->end_section_nr / sections_per_block; + return sprintf(buf, "%08lx\n", phys_index); } /* @@ -158,7 +172,7 @@ static ssize_t show_mem_removable(struct sys_device *dev, container_of(dev, struct memory_block, sysdev); for (i = 0; i < sections_per_block; i++) { - pfn = section_nr_to_pfn(mem->phys_index + i); + pfn = section_nr_to_pfn(mem->start_section_nr + i); ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION); } @@ -275,14 +289,15 @@ static int memory_block_change_state(struct memory_block *mem, mem->state = MEM_GOING_OFFLINE; for (i = 0; i < sections_per_block; i++) { - ret = memory_section_action(mem->phys_index + i, to_state); + ret = memory_section_action(mem->start_section_nr + i, + to_state); if (ret) break; } if (ret) { for (i = 0; i < sections_per_block; i++) - memory_section_action(mem->phys_index + i, + memory_section_action(mem->start_section_nr + i, from_state_req); mem->state = from_state_req; @@ -330,7 +345,8 @@ static ssize_t show_phys_device(struct sys_device *dev, return sprintf(buf, "%d\n", mem->phys_device); } -static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL); +static SYSDEV_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL); +static SYSDEV_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL); static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state); static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL); static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL); @@ -522,16 +538,20 @@ static int init_memory_block(struct memory_block **memory, return -ENOMEM; scn_nr = __section_nr(section); - mem->phys_index = base_memory_block_id(scn_nr) * sections_per_block; + mem->start_section_nr = + 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->section_count++; mutex_init(&mem->state_mutex); - start_pfn = section_nr_to_pfn(mem->phys_index); + start_pfn = section_nr_to_pfn(mem->start_section_nr); mem->phys_device = arch_get_memory_phys_device(start_pfn); ret = register_memory(mem); if (!ret) ret = mem_create_simple_file(mem, phys_index); + if (!ret) + ret = mem_create_simple_file(mem, end_phys_index); if (!ret) ret = mem_create_simple_file(mem, state); if (!ret) @@ -575,11 +595,12 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, mutex_lock(&mem_sysfs_mutex); mem = find_memory_block(section); + unregister_mem_sect_under_nodes(mem, __section_nr(section)); mem->section_count--; if (mem->section_count == 0) { - unregister_mem_sect_under_nodes(mem); mem_remove_simple_file(mem, phys_index); + mem_remove_simple_file(mem, end_phys_index); mem_remove_simple_file(mem, state); mem_remove_simple_file(mem, phys_device); mem_remove_simple_file(mem, removable); diff --git a/drivers/base/node.c b/drivers/base/node.c index 36b43052001..b3b72d64e80 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -375,8 +375,10 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid) return -EFAULT; if (!node_online(nid)) return 0; - sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index); - sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; + + sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); + sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr); + sect_end_pfn += PAGES_PER_SECTION - 1; for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { int page_nid; @@ -400,7 +402,8 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid) } /* unregister memory section under all nodes that it spans */ -int unregister_mem_sect_under_nodes(struct memory_block *mem_blk) +int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, + unsigned long phys_index) { NODEMASK_ALLOC(nodemask_t, unlinked_nodes, GFP_KERNEL); unsigned long pfn, sect_start_pfn, sect_end_pfn; @@ -412,7 +415,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk) if (!unlinked_nodes) return -ENOMEM; nodes_clear(*unlinked_nodes); - sect_start_pfn = section_nr_to_pfn(mem_blk->phys_index); + + sect_start_pfn = section_nr_to_pfn(phys_index); sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1; for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { int nid; diff --git a/include/linux/memory.h b/include/linux/memory.h index 06c1fa0a5c7..e1e3b2b84f8 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -21,7 +21,8 @@ #include struct memory_block { - unsigned long phys_index; + unsigned long start_section_nr; + unsigned long end_section_nr; unsigned long state; int section_count; diff --git a/include/linux/node.h b/include/linux/node.h index 1466945cc9e..92370e22343 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -39,7 +39,8 @@ extern int register_cpu_under_node(unsigned int cpu, unsigned int nid); extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid); extern int register_mem_sect_under_node(struct memory_block *mem_blk, int nid); -extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk); +extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, + unsigned long phys_index); #ifdef CONFIG_HUGETLBFS extern void register_hugetlbfs_with_node(node_registration_func_t doregister, @@ -67,7 +68,8 @@ static inline int register_mem_sect_under_node(struct memory_block *mem_blk, { return 0; } -static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk) +static inline int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, + unsigned long phys_index) { return 0; } -- cgit v1.2.3-70-g09d2 From 6add7cd618b4d4dc525731beb539c5e06e891855 Mon Sep 17 00:00:00 2001 From: Nathan Fontenot Date: Mon, 31 Jan 2011 10:55:23 -0600 Subject: memory hotplug: sysfs probe routine should add all memory sections As a follow-on to the recent patches I submitted that allowed for a sysfs memory block to span multiple memory sections, we should also update the probe routine to online all of the memory sections in a memory block. Without this patch the current code will only add a single memory section. I think the probe routine should add all of the memory sections in the specified memory block so that its behavior is in line with memory hotplug actions through the sysfs interfaces. This patch applies on top of the previous sysfs memory updates to allow a sysfs directory o span multiple memory sections. https://lkml.org/lkml/2011/1/20/245 Signed-off-by: Nathan Fontenot Signed-off-by: Greg Kroah-Hartman --- drivers/base/memory.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'drivers/base') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 71b4a32b171..3da6a43b775 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -387,12 +387,19 @@ memory_probe_store(struct class *class, struct class_attribute *attr, { u64 phys_addr; int nid; - int ret; + int i, ret; phys_addr = simple_strtoull(buf, NULL, 0); - nid = memory_add_physaddr_to_nid(phys_addr); - ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT); + for (i = 0; i < sections_per_block; i++) { + nid = memory_add_physaddr_to_nid(phys_addr); + ret = add_memory(nid, phys_addr, + PAGES_PER_SECTION << PAGE_SHIFT); + if (ret) + break; + + phys_addr += MIN_MEMORY_BLOCK_SIZE; + } if (ret) count = ret; -- cgit v1.2.3-70-g09d2 From 481e20799bdcf98fd5a1d829d187239a90b15395 Mon Sep 17 00:00:00 2001 From: Ferenc Wagner Date: Fri, 7 Jan 2011 15:17:47 +0100 Subject: driver core: Replace the dangerous to_root_device macro with an inline function The original macro worked only when applied to variables named 'dev'. While this could have been fixed by simply renaming the macro argument, a more type-safe replacement by an inline function is preferred. Signed-off-by: Ferenc Wagner Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/base') diff --git a/drivers/base/core.c b/drivers/base/core.c index 9cd3b5cfcc4..81b78ede37c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1320,7 +1320,10 @@ struct root_device struct module *owner; }; -#define to_root_device(dev) container_of(dev, struct root_device, dev) +inline struct root_device *to_root_device(struct device *d) +{ + return container_of(d, struct root_device, dev); +} static void root_device_release(struct device *dev) { -- cgit v1.2.3-70-g09d2