Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756145Ab2F0F5F (ORCPT ); Wed, 27 Jun 2012 01:57:05 -0400 Received: from fgwmail6.fujitsu.co.jp ([192.51.44.36]:58284 "EHLO fgwmail6.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750994Ab2F0F5D (ORCPT ); Wed, 27 Jun 2012 01:57:03 -0400 X-SecurityPolicyCheck: OK by SHieldMailChecker v1.7.4 Message-ID: <4FEAA09F.5000907@jp.fujitsu.com> Date: Wed, 27 Jun 2012 14:56:47 +0900 From: Yasuaki Ishimatsu User-Agent: Mozilla/5.0 (Windows NT 5.1; rv:13.0) Gecko/20120614 Thunderbird/13.0.1 MIME-Version: 1.0 To: , , , CC: , , , , , , , Subject: [RFC PATCH 10/12] memory-hotplug : free memmap of sparse-vmemmap References: <4FEA9C88.1070800@jp.fujitsu.com> In-Reply-To: <4FEA9C88.1070800@jp.fujitsu.com> Content-Type: text/plain; charset="ISO-2022-JP" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5724 Lines: 183 I don't think that all pages of virtual mapping in removed memory can be freed, since page which type is MIX_SECTION_INFO is difficult to free. So, the patch only frees page which type is SECTION_INFO at first. CC: Len Brown CC: Benjamin Herrenschmidt CC: Paul Mackerras CC: Christoph Lameter Cc: Minchan Kim CC: Andrew Morton CC: KOSAKI Motohiro CC: Wen Congyang Signed-off-by: Yasuaki Ishimatsu --- arch/x86/mm/init_64.c | 89 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm.h | 2 + mm/memory_hotplug.c | 5 ++ mm/sparse.c | 5 +- 4 files changed, 99 insertions(+), 2 deletions(-) Index: linux-3.5-rc4/include/linux/mm.h =================================================================== --- linux-3.5-rc4.orig/include/linux/mm.h 2012-06-27 09:11:13.790150442 +0900 +++ linux-3.5-rc4/include/linux/mm.h 2012-06-27 09:11:16.433117400 +0900 @@ -1588,6 +1588,8 @@ int vmemmap_populate(struct page *start_ 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, Index: linux-3.5-rc4/mm/sparse.c =================================================================== --- linux-3.5-rc4.orig/mm/sparse.c 2012-06-27 09:06:35.317631878 +0900 +++ linux-3.5-rc4/mm/sparse.c 2012-06-27 09:11:16.434117388 +0900 @@ -614,12 +614,13 @@ static inline struct page *kmalloc_secti /* 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) { + vmemmap_free_bootmem(page, nr_pages); } #else static struct page *__kmalloc_section_memmap(unsigned long nr_pages) Index: linux-3.5-rc4/arch/x86/mm/init_64.c =================================================================== --- linux-3.5-rc4.orig/arch/x86/mm/init_64.c 2012-06-27 09:11:13.791150430 +0900 +++ linux-3.5-rc4/arch/x86/mm/init_64.c 2012-06-27 09:11:59.254581998 +0900 @@ -978,6 +978,95 @@ vmemmap_populate(struct page *start_page return 0; } +unsigned long find_and_clear_pte_page(unsigned long addr, unsigned long end, + struct page *page) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long next; + + page = NULL; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + return PAGE_SIZE; + + pud = pud_offset(pgd, addr); + if (pud_none(*pud)) + return PAGE_SIZE; + + 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 = pte_page(*pte); + pte_clear(&init_mm, addr, pte); + } else { + next = pmd_addr_end(addr, end); + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return next; + + page = pmd_page(*pmd); + pmd_clear(pmd); + } + + return next; +} + +void __meminit +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; + unsigned int order; + struct page *page; + + for (; addr < end; addr = next) { + next = find_and_clear_pte_page(addr, end, page); + if (!page) + continue; + + if (is_vmalloc_addr(page)) + vfree(page); + else { + order = next - addr; + free_pages((unsigned long)page, + get_order(sizeof(struct page) * order)); + } + } +} + +void __meminit +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; + unsigned long magic; + + for (; addr < end; addr = next) { + next = find_and_clear_pte_page(addr, end, page); + if (!page) + continue; + + magic = (unsigned long) page->lru.next; + if (magic == SECTION_INFO) + put_page_bootmem(page); + } +} + void __meminit register_page_bootmem_memmap(unsigned long section_nr, struct page *start_page, unsigned long size) Index: linux-3.5-rc4/mm/memory_hotplug.c =================================================================== --- linux-3.5-rc4.orig/mm/memory_hotplug.c 2012-06-27 09:11:13.789150454 +0900 +++ linux-3.5-rc4/mm/memory_hotplug.c 2012-06-27 09:11:16.436117363 +0900 @@ -303,6 +303,8 @@ static int __meminit __add_section(int n #ifdef CONFIG_SPARSEMEM_VMEMMAP static int __remove_section(struct zone *zone, struct mem_section *ms) { + unsigned long flags; + struct pglist_data *pgdat = zone->zone_pgdat; int ret; if (!valid_section(ms)) @@ -310,6 +312,9 @@ static int __remove_section(struct zone ret = unregister_memory_section(ms); + pgdat_resize_lock(pgdat, &flags); + sparse_remove_one_section(zone, ms); + pgdat_resize_unlock(pgdat, &flags); return ret; } #else -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/