From 0aad818b2de455f1bfd7ef87c28cdbbaaed9a699 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 29 Apr 2013 15:07:50 -0700 Subject: sparse-vmemmap: specify vmemmap population range in bytes The sparse code, when asking the architecture to populate the vmemmap, specifies the section range as a starting page and a number of pages. This is an awkward interface, because none of the arch-specific code actually thinks of the range in terms of 'struct page' units and always translates it to bytes first. In addition, later patches mix huge page and regular page backing for the vmemmap. For this, they need to call vmemmap_populate_basepages() on sub-section ranges with PAGE_SIZE and PMD_SIZE in mind. But these are not necessarily multiples of the 'struct page' size and so this unit is too coarse. Just translate the section range into bytes once in the generic sparse code, then pass byte ranges down the stack. Signed-off-by: Johannes Weiner Cc: Ben Hutchings Cc: Bernhard Schmidt Cc: Johannes Weiner Cc: Russell King Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Benjamin Herrenschmidt Cc: "Luck, Tony" Cc: Heiko Carstens Acked-by: David S. Miller Tested-by: David S. Miller Cc: Wu Fengguang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'mm/sparse.c') diff --git a/mm/sparse.c b/mm/sparse.c index 7ca6dc84794..a37be5f9050 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -615,11 +615,17 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, } static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) { - vmemmap_free(memmap, nr_pages); + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + + vmemmap_free(start, end); } static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) { - vmemmap_free(memmap, nr_pages); + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + + vmemmap_free(start, end); } #else static struct page *__kmalloc_section_memmap(unsigned long nr_pages) -- cgit v1.2.3-70-g09d2 From 4edd7ceff0662afde195da6f6c43e7cbe1ed2dc4 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 29 Apr 2013 15:08:22 -0700 Subject: mm, hotplug: avoid compiling memory hotremove functions when disabled __remove_pages() is only necessary for CONFIG_MEMORY_HOTREMOVE. PowerPC pseries will return -EOPNOTSUPP if unsupported. Adding an #ifdef causes several other functions it depends on to also become unnecessary, which saves in .text when disabled (it's disabled in most defconfigs besides powerpc, including x86). remove_memory_block() becomes static since it is not referenced outside of drivers/base/memory.c. Build tested on x86 and powerpc with CONFIG_MEMORY_HOTREMOVE both enabled and disabled. Signed-off-by: David Rientjes Acked-by: Toshi Kani Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Greg Kroah-Hartman Cc: Wen Congyang Cc: Tang Chen Cc: Yasuaki Ishimatsu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 12 +++++ drivers/base/memory.c | 44 +++++++-------- include/linux/memory.h | 3 +- include/linux/memory_hotplug.h | 4 +- mm/memory_hotplug.c | 68 +++++++++++------------ mm/sparse.c | 72 +++++++++++++------------ 6 files changed, 113 insertions(+), 90 deletions(-) (limited to 'mm/sparse.c') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2372c609fa2..9a432de363b 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -72,6 +72,7 @@ unsigned long memory_block_size_bytes(void) return get_memblock_size(); } +#ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { unsigned long start, start_pfn; @@ -153,6 +154,17 @@ static int pseries_remove_memory(struct device_node *np) ret = pseries_remove_memblock(base, lmb_size); return ret; } +#else +static inline int pseries_remove_memblock(unsigned long base, + unsigned int memblock_size) +{ + return -EOPNOTSUPP; +} +static inline int pseries_remove_memory(struct device_node *np) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_MEMORY_HOTREMOVE */ static int pseries_add_memory(struct device_node *np) { diff --git a/drivers/base/memory.c b/drivers/base/memory.c index a51007b7903..65d9799cbb6 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -93,16 +93,6 @@ int register_memory(struct memory_block *memory) return error; } -static void -unregister_memory(struct memory_block *memory) -{ - BUG_ON(memory->dev.bus != &memory_subsys); - - /* drop the ref. we got in remove_memory_block() */ - kobject_put(&memory->dev.kobj); - device_unregister(&memory->dev); -} - unsigned long __weak memory_block_size_bytes(void) { return MIN_MEMORY_BLOCK_SIZE; @@ -637,8 +627,28 @@ static int add_memory_section(int nid, struct mem_section *section, return ret; } -int remove_memory_block(unsigned long node_id, struct mem_section *section, - int phys_device) +/* + * need an interface for the VM to add new memory regions, + * but without onlining it. + */ +int register_new_memory(int nid, struct mem_section *section) +{ + return add_memory_section(nid, section, NULL, MEM_OFFLINE, HOTPLUG); +} + +#ifdef CONFIG_MEMORY_HOTREMOVE +static void +unregister_memory(struct memory_block *memory) +{ + BUG_ON(memory->dev.bus != &memory_subsys); + + /* drop the ref. we got in remove_memory_block() */ + kobject_put(&memory->dev.kobj); + device_unregister(&memory->dev); +} + +static int remove_memory_block(unsigned long node_id, + struct mem_section *section, int phys_device) { struct memory_block *mem; @@ -661,15 +671,6 @@ int remove_memory_block(unsigned long node_id, struct mem_section *section, return 0; } -/* - * need an interface for the VM to add new memory regions, - * but without onlining it. - */ -int register_new_memory(int nid, struct mem_section *section) -{ - return add_memory_section(nid, section, NULL, MEM_OFFLINE, HOTPLUG); -} - int unregister_memory_section(struct mem_section *section) { if (!present_section(section)) @@ -677,6 +678,7 @@ int unregister_memory_section(struct mem_section *section) return remove_memory_block(0, section, 0); } +#endif /* CONFIG_MEMORY_HOTREMOVE */ /* * offline one memory block. If the memory block has been offlined, do nothing. diff --git a/include/linux/memory.h b/include/linux/memory.h index 0ff6598ee62..73817af8b48 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -115,9 +115,10 @@ extern void unregister_memory_notifier(struct notifier_block *nb); extern int register_memory_isolate_notifier(struct notifier_block *nb); extern void unregister_memory_isolate_notifier(struct notifier_block *nb); extern int register_new_memory(int, struct mem_section *); +#ifdef CONFIG_MEMORY_HOTREMOVE extern int unregister_memory_section(struct mem_section *); +#endif extern int memory_dev_init(void); -extern int remove_memory_block(unsigned long, struct mem_section *, int); extern int memory_notify(unsigned long val, void *v); extern int memory_isolate_notify(unsigned long val, void *v); extern struct memory_block *find_memory_block_hinted(struct mem_section *, diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index b6a3be7d47b..3e622c61092 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -97,13 +97,13 @@ extern void __online_page_free(struct page *page); #ifdef CONFIG_MEMORY_HOTREMOVE extern bool is_pageblock_removable_nolock(struct page *page); extern int arch_remove_memory(u64 start, u64 size); +extern int __remove_pages(struct zone *zone, unsigned long start_pfn, + unsigned long nr_pages); #endif /* CONFIG_MEMORY_HOTREMOVE */ /* reasonably generic interface to expand the physical pages in a zone */ extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn, unsigned long nr_pages); -extern int __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages); #ifdef CONFIG_NUMA extern int memory_add_physaddr_to_nid(u64 start); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c916582591e..60f6daad107 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -436,6 +436,40 @@ static int __meminit __add_section(int nid, struct zone *zone, return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); } +/* + * Reasonably generic function for adding memory. It is + * expected that archs that support memory hotplug will + * call this function after deciding the zone to which to + * add the new pages. + */ +int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, + unsigned long nr_pages) +{ + unsigned long i; + int err = 0; + int start_sec, end_sec; + /* during initialize mem_map, align hot-added range to section */ + start_sec = pfn_to_section_nr(phys_start_pfn); + end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); + + for (i = start_sec; i <= end_sec; i++) { + err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); + + /* + * EEXIST is finally dealt with by ioresource collision + * check. see add_memory() => register_memory_resource() + * Warning will be printed if there is collision. + */ + if (err && (err != -EEXIST)) + break; + err = 0; + } + + return err; +} +EXPORT_SYMBOL_GPL(__add_pages); + +#ifdef CONFIG_MEMORY_HOTREMOVE /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static int find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, @@ -658,39 +692,6 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) return 0; } -/* - * Reasonably generic function for adding memory. It is - * expected that archs that support memory hotplug will - * call this function after deciding the zone to which to - * add the new pages. - */ -int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, - unsigned long nr_pages) -{ - unsigned long i; - int err = 0; - int start_sec, end_sec; - /* during initialize mem_map, align hot-added range to section */ - start_sec = pfn_to_section_nr(phys_start_pfn); - end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); - - for (i = start_sec; i <= end_sec; i++) { - err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); - - /* - * EEXIST is finally dealt with by ioresource collision - * check. see add_memory() => register_memory_resource() - * Warning will be printed if there is collision. - */ - if (err && (err != -EEXIST)) - break; - err = 0; - } - - return err; -} -EXPORT_SYMBOL_GPL(__add_pages); - /** * __remove_pages() - remove sections of pages from a zone * @zone: zone from which pages need to be removed @@ -733,6 +734,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, return ret; } EXPORT_SYMBOL_GPL(__remove_pages); +#endif /* CONFIG_MEMORY_HOTREMOVE */ int set_online_page_callback(online_page_callback_t callback) { diff --git a/mm/sparse.c b/mm/sparse.c index a37be5f9050..1c91f0d3f6a 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -620,6 +620,7 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) vmemmap_free(start, end); } +#ifdef CONFIG_MEMORY_HOTREMOVE static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) { unsigned long start = (unsigned long)memmap; @@ -627,6 +628,7 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) vmemmap_free(start, end); } +#endif /* CONFIG_MEMORY_HOTREMOVE */ #else static struct page *__kmalloc_section_memmap(unsigned long nr_pages) { @@ -664,6 +666,7 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) get_order(sizeof(struct page) * nr_pages)); } +#ifdef CONFIG_MEMORY_HOTREMOVE static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) { unsigned long maps_section_nr, removing_section_nr, i; @@ -690,40 +693,9 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) put_page_bootmem(page); } } +#endif /* CONFIG_MEMORY_HOTREMOVE */ #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -static void free_section_usemap(struct page *memmap, unsigned long *usemap) -{ - struct page *usemap_page; - unsigned long nr_pages; - - if (!usemap) - return; - - usemap_page = virt_to_page(usemap); - /* - * Check to see if allocation came from hot-plug-add - */ - if (PageSlab(usemap_page) || PageCompound(usemap_page)) { - kfree(usemap); - if (memmap) - __kfree_section_memmap(memmap, PAGES_PER_SECTION); - return; - } - - /* - * The usemap came from bootmem. This is packed with other usemaps - * on the section which has pgdat at boot time. Just keep it as is now. - */ - - if (memmap) { - nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) - >> PAGE_SHIFT; - - free_map_bootmem(memmap, nr_pages); - } -} - /* * returns the number of sections whose mem_maps were properly * set. If this is <=0, then that means that the passed-in @@ -800,6 +772,39 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) } #endif +#ifdef CONFIG_MEMORY_HOTREMOVE +static void free_section_usemap(struct page *memmap, unsigned long *usemap) +{ + struct page *usemap_page; + unsigned long nr_pages; + + if (!usemap) + return; + + usemap_page = virt_to_page(usemap); + /* + * Check to see if allocation came from hot-plug-add + */ + if (PageSlab(usemap_page) || PageCompound(usemap_page)) { + kfree(usemap); + if (memmap) + __kfree_section_memmap(memmap, PAGES_PER_SECTION); + return; + } + + /* + * The usemap came from bootmem. This is packed with other usemaps + * on the section which has pgdat at boot time. Just keep it as is now. + */ + + if (memmap) { + nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) + >> PAGE_SHIFT; + + free_map_bootmem(memmap, nr_pages); + } +} + void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) { struct page *memmap = NULL; @@ -819,4 +824,5 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION); free_section_usemap(memmap, usemap); } -#endif +#endif /* CONFIG_MEMORY_HOTREMOVE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ -- cgit v1.2.3-70-g09d2