[v4,08/12] memory-hotplug: remove memmap of sparse-vmemmap

Message ID	1354010422-19648-9-git-send-email-wency@cn.fujitsu.com (mailing list archive)
State	Superseded
Headers	show Return-Path: <linux-sh-owner@vger.kernel.org> From: Wen Congyang <wency@cn.fujitsu.com> To: x86@kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-acpi@vger.kernel.org, linux-s390@vger.kernel.org, linux-sh@vger.kernel.org, linux-ia64@vger.kernel.org, cmetcalf@tilera.com, sparclinux@vger.kernel.org Cc: David Rientjes <rientjes@google.com>, Jiang Liu <liuj97@gmail.com>, Len Brown <len.brown@intel.com>, benh@kernel.crashing.org, paulus@samba.org, Christoph Lameter <cl@linux.com>, Minchan Kim <minchan.kim@gmail.com>, Andrew Morton <akpm@linux-foundation.org>, KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>, Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>, Jianguo Wu <wujianguo@huawei.com>, Wen Congyang <wency@cn.fujitsu.com> Subject: [Patch v4 08/12] memory-hotplug: remove memmap of sparse-vmemmap Date: Tue, 27 Nov 2012 18:00:18 +0800 Message-Id: <1354010422-19648-9-git-send-email-wency@cn.fujitsu.com> In-Reply-To: <1354010422-19648-1-git-send-email-wency@cn.fujitsu.com> References: <1354010422-19648-1-git-send-email-wency@cn.fujitsu.com> Sender: linux-sh-owner@vger.kernel.org Precedence: bulk

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 33943db..0d23b69 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -823,6 +823,14 @@ int __meminit vmemmap_populate(struct page *start_page, return vmemmap_populate_basepages(start_page, size, node); } +void vmemmap_kfree(struct page *memmap, unsigned long nr_pages) +{ +} + +void vmemmap_free_bootmem(struct page *memmap, unsigned long nr_pages) +{ +} + void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) { diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 6466440..df7d155 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -298,6 +298,14 @@ int __meminit vmemmap_populate(struct page *start_page, return 0; } +void vmemmap_kfree(struct page *memmap, unsigned long nr_pages) +{ +} + +void vmemmap_free_bootmem(struct page *memmap, unsigned long nr_pages) +{ +} + void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) { diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 4f4803a..ab69c34 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -236,6 +236,14 @@ out: return ret; } +void vmemmap_kfree(struct page *memmap, unsigned long nr_pages) +{ +} + +void vmemmap_free_bootmem(struct page *memmap, unsigned long nr_pages) +{ +} + void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 75a984b..546855d 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2232,6 +2232,14 @@ void __meminit vmemmap_populate_print_last(void) } } +void vmemmap_kfree(struct page *memmap, unsigned long nr_pages) +{ +} + +void vmemmap_free_bootmem(struct page *memmap, unsigned long nr_pages) +{ +} + void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 795dae3..e85626d 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -998,6 +998,125 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node) return 0; } +#define PAGE_INUSE 0xFD + +unsigned long find_and_clear_pte_page(unsigned long addr, unsigned long end, + struct page **pp, int *page_size) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte = NULL; + void *page_addr; + unsigned long next; + + *pp = NULL; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + return pgd_addr_end(addr, end); + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) + return pud_addr_end(addr, end); + + if (!cpu_has_pse) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return next; + + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) + return next; + + *page_size = PAGE_SIZE; + *pp = pte_page(*pte); + } else { + next = pmd_addr_end(addr, end); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return next; + + *page_size = PMD_SIZE; + *pp = pmd_page(*pmd); + } + + /* + * Removed page structs are filled with 0xFD. + */ + memset((void *)addr, PAGE_INUSE, next - addr); + + page_addr = page_address(*pp); + + /* + * Check the page is filled with 0xFD or not. + * memchr_inv() returns the address. In this case, we cannot + * clear PTE/PUD entry, since the page is used by other. + * So we cannot also free the page. + * + * memchr_inv() returns NULL. In this case, we can clear + * PTE/PUD entry, since the page is not used by other. + * So we can also free the page. + */ + if (memchr_inv(page_addr, PAGE_INUSE, *page_size)) { + *pp = NULL; + return next; + } + + if (!cpu_has_pse) + pte_clear(&init_mm, addr, pte); + else + pmd_clear(pmd); + + return next; +} + +void vmemmap_kfree(struct page *memmap, unsigned long nr_pages) +{ + unsigned long addr = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + unsigned long next; + struct page *page; + int page_size; + + for (; addr < end; addr = next) { + page = NULL; + page_size = 0; + next = find_and_clear_pte_page(addr, end, &page, &page_size); + if (!page) + continue; + + free_pages((unsigned long)page_address(page), + get_order(page_size)); + __flush_tlb_one(addr); + } +} + +void vmemmap_free_bootmem(struct page *memmap, unsigned long nr_pages) +{ + unsigned long addr = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + unsigned long next; + struct page *page; + int page_size; + unsigned long magic; + + for (; addr < end; addr = next) { + page = NULL; + page_size = 0; + next = find_and_clear_pte_page(addr, end, &page, &page_size); + if (!page) + continue; + + magic = (unsigned long) page->lru.next; + if (magic == SECTION_INFO) + put_page_bootmem(page); + flush_tlb_kernel_range(addr, end); + } +} + void register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 5657670..94d5ccd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1642,6 +1642,8 @@ int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); void register_page_bootmem_memmap(unsigned long section_nr, struct page *map, unsigned long size); +void vmemmap_kfree(struct page *memmpa, unsigned long nr_pages); +void vmemmap_free_bootmem(struct page *memmpa, unsigned long nr_pages); enum mf_flags { MF_COUNT_INCREASED = 1 << 0, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ccc11b6..7797e91 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -301,19 +301,6 @@ static int __meminit __add_section(int nid, struct zone *zone, return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); } -#ifdef CONFIG_SPARSEMEM_VMEMMAP -static int __remove_section(struct zone *zone, struct mem_section *ms) -{ - int ret = -EINVAL; - - if (!valid_section(ms)) - return ret; - - ret = unregister_memory_section(ms); - - return ret; -} -#else static int __remove_section(struct zone *zone, struct mem_section *ms) { unsigned long flags; @@ -330,9 +317,9 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) pgdat_resize_lock(pgdat, &flags); sparse_remove_one_section(zone, ms); pgdat_resize_unlock(pgdat, &flags); - return 0; + + return ret; } -#endif /* * Reasonably generic function for adding memory. It is diff --git a/mm/sparse.c b/mm/sparse.c index fac95f2..c723bc2 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -613,12 +613,13 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, /* This will make the necessary allocations eventually. */ return sparse_mem_map_populate(pnum, nid); } -static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) +static void __kfree_section_memmap(struct page *page, unsigned long nr_pages) { - return; /* XXX: Not implemented yet */ + vmemmap_kfree(page, nr_pages); } -static void free_map_bootmem(struct page *page, unsigned long nr_pages) +static void free_map_bootmem(struct page *page) { + vmemmap_free_bootmem(page, PAGES_PER_SECTION); } #else static struct page *__kmalloc_section_memmap(unsigned long nr_pages) @@ -658,10 +659,14 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) get_order(sizeof(struct page) * nr_pages)); } -static void free_map_bootmem(struct page *page, unsigned long nr_pages) +static void free_map_bootmem(struct page *page) { unsigned long maps_section_nr, removing_section_nr, i; unsigned long magic; + unsigned long nr_pages; + + nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) + >> PAGE_SHIFT; for (i = 0; i < nr_pages; i++, page++) { magic = (unsigned long) page->lru.next; @@ -688,7 +693,6 @@ static void free_map_bootmem(struct page *page, unsigned long nr_pages) static void free_section_usemap(struct page *memmap, unsigned long *usemap) { struct page *usemap_page; - unsigned long nr_pages; if (!usemap) return; @@ -713,10 +717,7 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap) struct page *memmap_page; memmap_page = virt_to_page(memmap); - nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) - >> PAGE_SHIFT; - - free_map_bootmem(memmap_page, nr_pages); + free_map_bootmem(memmap_page); } }

[v4,08/12] memory-hotplug: remove memmap of sparse-vmemmap

Commit Message

Comments

Patch