Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759762Ab2KAJjU (ORCPT ); Thu, 1 Nov 2012 05:39:20 -0400 Received: from cn.fujitsu.com ([222.73.24.84]:5829 "EHLO song.cn.fujitsu.com" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1759225Ab2KAJjM (ORCPT ); Thu, 1 Nov 2012 05:39:12 -0400 X-IronPort-AV: E=Sophos;i="4.80,693,1344182400"; d="scan'208";a="6116044" From: Wen Congyang 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 , Jiang Liu , Len Brown , benh@kernel.crashing.org, paulus@samba.org, Christoph Lameter , Minchan Kim , Andrew Morton , KOSAKI Motohiro , Yasuaki Ishimatsu , Jianguo Wu , Wen Congyang , Jiang Liu Subject: [PATCH v3 09/12] memory-hotplug: remove page table of x86_64 architecture Date: Thu, 1 Nov 2012 17:44:40 +0800 Message-Id: <1351763083-7905-10-git-send-email-wency@cn.fujitsu.com> X-Mailer: git-send-email 1.8.0 In-Reply-To: <1351763083-7905-1-git-send-email-wency@cn.fujitsu.com> References: <1351763083-7905-1-git-send-email-wency@cn.fujitsu.com> X-MIMETrack: Itemize by SMTP Server on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2012/11/01 17:38:11, Serialize by Router on mailserver/fnst(Release 8.5.3|September 15, 2011) at 2012/11/01 17:38:13, Serialize complete at 2012/11/01 17:38:13 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9099 Lines: 370 For hot removing memory, we sholud remove page table about the memory. So the patch searches a page table about the removed memory, and clear page table. CC: David Rientjes CC: Jiang Liu CC: Len Brown CC: Christoph Lameter Cc: Minchan Kim CC: Andrew Morton CC: KOSAKI Motohiro CC: Yasuaki Ishimatsu Signed-off-by: Wen Congyang Signed-off-by: Jianguo Wu Signed-off-by: Jiang Liu --- arch/x86/include/asm/pgtable_types.h | 1 + arch/x86/mm/init_64.c | 231 +++++++++++++++++++++++++++++++++++ arch/x86/mm/pageattr.c | 47 +++---- 3 files changed, 257 insertions(+), 22 deletions(-) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index ec8a1fc..fb0c24d 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -332,6 +332,7 @@ static inline void update_page_count(int level, unsigned long pages) { } * as a pte too. */ extern pte_t *lookup_address(unsigned long address, unsigned int *level); +extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase); #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index e85626d..23d932a 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -680,6 +680,235 @@ int arch_add_memory(int nid, u64 start, u64 size) } EXPORT_SYMBOL_GPL(arch_add_memory); +static inline void free_pagetable(struct page *page) +{ + struct zone *zone; + bool bootmem = false; + + /* bootmem page has reserved flag */ + if (PageReserved(page)) { + __ClearPageReserved(page); + bootmem = true; + } + + __free_page(page); + + if (bootmem) { + zone = page_zone(page); + zone_span_writelock(zone); + zone->present_pages++; + zone_span_writeunlock(zone); + totalram_pages++; + } +} + +static void free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (pte_val(*pte)) + return; + } + + /* free a pte talbe */ + free_pagetable(pmd_page(*pmd)); + pmd_clear(pmd); +} + +static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) +{ + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (pmd_val(*pmd)) + return; + } + + /* free a pmd talbe */ + free_pagetable(pud_page(*pud)); + pud_clear(pud); +} + +/* return true if pgd is changed, otherwise return false */ +static bool free_pud_table(pud_t *pud_start, pgd_t *pgd) +{ + pud_t *pud; + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (pud_val(*pud)) + return false; + } + + /* free a pud table */ + free_pagetable(pgd_page(*pgd)); + pgd_clear(pgd); + + return true; +} + +static void __meminit +phys_pte_remove(pte_t *pte_page, unsigned long addr, unsigned long end) +{ + unsigned pages = 0; + int i = pte_index(addr); + + pte_t *pte = pte_page + pte_index(addr); + + for (; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) { + + if (addr >= end) + break; + + if (!pte_present(*pte)) + continue; + + pages++; + set_pte(pte, __pte(0)); + } + + update_page_count(PG_LEVEL_4K, -pages); +} + +static void __meminit +phys_pmd_remove(pmd_t *pmd_page, unsigned long addr, unsigned long end) +{ + unsigned long pages = 0, next; + int i = pmd_index(addr); + + for (; i < PTRS_PER_PMD && addr < end; i++, addr = next) { + unsigned long pte_phys; + pmd_t *pmd = pmd_page + pmd_index(addr); + pte_t *pte; + + next = pmd_addr_end(addr, end); + + if (!pmd_present(*pmd)) + continue; + + if (pmd_large(*pmd)) { + if (IS_ALIGNED(addr, PMD_SIZE) && + IS_ALIGNED(next, PMD_SIZE)) { + set_pmd(pmd, __pmd(0)); + pages++; + continue; + } + + /* + * We use 2M page, but we need to remove part of them, + * so split 2M page to 4K page. + */ + pte = alloc_low_page(&pte_phys); + BUG_ON(!pte); + __split_large_page((pte_t *)pmd, + (unsigned long)__va(addr), pte); + + spin_lock(&init_mm.page_table_lock); + pmd_populate_kernel(&init_mm, pmd, __va(pte_phys)); + spin_unlock(&init_mm.page_table_lock); + + /* Do a global flush tlb after splitting a large page */ + flush_tlb_all(); + } + + spin_lock(&init_mm.page_table_lock); + pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd)); + phys_pte_remove(pte, addr, next); + free_pte_table(pte, pmd); + unmap_low_page(pte); + spin_unlock(&init_mm.page_table_lock); + } + update_page_count(PG_LEVEL_2M, -pages); +} + +static void __meminit +phys_pud_remove(pud_t *pud_page, unsigned long addr, unsigned long end) +{ + unsigned long pages = 0, next; + int i = pud_index(addr); + + for (; i < PTRS_PER_PUD && addr < end; i++, addr = next) { + unsigned long pmd_phys; + pud_t *pud = pud_page + pud_index(addr); + pmd_t *pmd; + + next = pud_addr_end(addr, end); + + if (!pud_present(*pud)) + continue; + + if (pud_large(*pud)) { + if (IS_ALIGNED(addr, PUD_SIZE) && + IS_ALIGNED(next, PUD_SIZE)) { + set_pud(pud, __pud(0)); + pages++; + continue; + } + + /* + * We use 1G page, but we need to remove part of them, + * so split 1G page to 2M page. + */ + pmd = alloc_low_page(&pmd_phys); + BUG_ON(!pmd); + __split_large_page((pte_t *)pud, + (unsigned long)__va(addr), + (pte_t *)pmd); + + spin_lock(&init_mm.page_table_lock); + pud_populate(&init_mm, pud, __va(pmd_phys)); + spin_unlock(&init_mm.page_table_lock); + + /* Do a global flush tlb after splitting a large page */ + flush_tlb_all(); + } + + pmd = map_low_page((pmd_t *)pud_page_vaddr(*pud)); + phys_pmd_remove(pmd, addr, next); + free_pmd_table(pmd, pud); + unmap_low_page(pmd); + } + + update_page_count(PG_LEVEL_1G, -pages); +} + +void __meminit +kernel_physical_mapping_remove(unsigned long start, unsigned long end) +{ + unsigned long next; + bool pgd_changed = false; + + start = (unsigned long)__va(start); + end = (unsigned long)__va(end); + + for (; start < end; start = next) { + pgd_t *pgd = pgd_offset_k(start); + pud_t *pud; + + next = pgd_addr_end(start, end); + + if (!pgd_present(*pgd)) + continue; + + pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd)); + phys_pud_remove(pud, __pa(start), __pa(next)); + if (free_pud_table(pud, pgd)) + pgd_changed = true; + unmap_low_page(pud); + } + + if (pgd_changed) + sync_global_pgds(start, end - 1); + + flush_tlb_all(); +} + #ifdef CONFIG_MEMORY_HOTREMOVE int __ref arch_remove_memory(u64 start, u64 size) { @@ -692,6 +921,8 @@ int __ref arch_remove_memory(u64 start, u64 size) ret = __remove_pages(zone, start_pfn, nr_pages); WARN_ON_ONCE(ret); + kernel_physical_mapping_remove(start, start + size); + return ret; } #endif diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a718e0d..7dcb6f9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -501,21 +501,13 @@ out_unlock: return do_split; } -static int split_large_page(pte_t *kpte, unsigned long address) +int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase) { unsigned long pfn, pfninc = 1; unsigned int i, level; - pte_t *pbase, *tmp; + pte_t *tmp; pgprot_t ref_prot; - struct page *base; - - if (!debug_pagealloc) - spin_unlock(&cpa_lock); - base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); - if (!debug_pagealloc) - spin_lock(&cpa_lock); - if (!base) - return -ENOMEM; + struct page *base = virt_to_page(pbase); spin_lock(&pgd_lock); /* @@ -523,10 +515,11 @@ static int split_large_page(pte_t *kpte, unsigned long address) * up for us already: */ tmp = lookup_address(address, &level); - if (tmp != kpte) - goto out_unlock; + if (tmp != kpte) { + spin_unlock(&pgd_lock); + return 1; + } - pbase = (pte_t *)page_address(base); paravirt_alloc_pte(&init_mm, page_to_pfn(base)); ref_prot = pte_pgprot(pte_clrhuge(*kpte)); /* @@ -579,17 +572,27 @@ static int split_large_page(pte_t *kpte, unsigned long address) * going on. */ __flush_tlb_all(); + spin_unlock(&pgd_lock); - base = NULL; + return 0; +} -out_unlock: - /* - * If we dropped out via the lookup_address check under - * pgd_lock then stick the page back into the pool: - */ - if (base) +static int split_large_page(pte_t *kpte, unsigned long address) +{ + pte_t *pbase; + struct page *base; + + if (!debug_pagealloc) + spin_unlock(&cpa_lock); + base = alloc_pages(GFP_KERNEL | __GFP_NOTRACK, 0); + if (!debug_pagealloc) + spin_lock(&cpa_lock); + if (!base) + return -ENOMEM; + + pbase = (pte_t *)page_address(base); + if (__split_large_page(kpte, address, pbase)) __free_page(base); - spin_unlock(&pgd_lock); return 0; } -- 1.8.0 -- 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/