[PATCH 8/10] memory-hotplug : remove page table of x86_64 architecture

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Wen Congyang <wency@xxxxxxxxxxxxxx>

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 <rientjes@xxxxxxxxxx>
CC: Jiang Liu <liuj97@xxxxxxxxx>
CC: Len Brown <len.brown@xxxxxxxxx>
CC: Christoph Lameter <cl@xxxxxxxxx>
Cc: Minchan Kim <minchan.kim@xxxxxxxxx>
CC: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
CC: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
CC: Yasuaki Ishimatsu <isimatu.yasuaki@xxxxxxxxxxxxxx>
Signed-off-by: Wen Congyang <wency@xxxxxxxxxxxxxx>
---
 arch/x86/include/asm/pgtable_types.h |    1 
 arch/x86/mm/init_64.c                |  147 +++++++++++++++++++++++++++++++++++
 arch/x86/mm/pageattr.c               |   47 +++++------
 3 files changed, 173 insertions(+), 22 deletions(-)

Index: linux-3.6/arch/x86/mm/init_64.c
===================================================================
--- linux-3.6.orig/arch/x86/mm/init_64.c	2012-10-04 18:30:21.171698416 +0900
+++ linux-3.6/arch/x86/mm/init_64.c	2012-10-04 18:30:27.317704652 +0900
@@ -675,6 +675,151 @@ int arch_add_memory(int nid, u64 start, 
 }
 EXPORT_SYMBOL_GPL(arch_add_memory);
 
+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; i++, addr = next) {
+		unsigned long pte_phys;
+		pmd_t *pmd = pmd_page + pmd_index(addr);
+		pte_t *pte;
+
+		if (addr >= end)
+			break;
+
+		next = (addr & PMD_MASK) + PMD_SIZE;
+
+		if (!pmd_present(*pmd))
+			continue;
+
+		if (pmd_large(*pmd)) {
+			if ((addr & ~PMD_MASK) == 0 && next <= end) {
+				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);
+			__split_large_page((pte_t *)pmd, 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);
+		}
+
+		spin_lock(&init_mm.page_table_lock);
+		pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd));
+		phys_pte_remove(pte, addr, end);
+		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; i++, addr = next) {
+		unsigned long pmd_phys;
+		pud_t *pud = pud_page + pud_index(addr);
+		pmd_t *pmd;
+
+		if (addr >= end)
+			break;
+
+		next = (addr & PUD_MASK) + PUD_SIZE;
+
+		if (!pud_present(*pud))
+			continue;
+
+		if (pud_large(*pud)) {
+			if ((addr & ~PUD_MASK) == 0 && next <= end) {
+				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);
+			__split_large_page((pte_t *)pud, 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);
+		}
+
+		pmd = map_low_page(pmd_offset(pud, 0));
+		phys_pmd_remove(pmd, addr, end);
+		unmap_low_page(pmd);
+		__flush_tlb_all();
+	}
+	__flush_tlb_all();
+
+	update_page_count(PG_LEVEL_1G, -pages);
+}
+
+void __meminit
+kernel_physical_mapping_remove(unsigned long start, unsigned long end)
+{
+	unsigned long next;
+
+	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 = (start + PGDIR_SIZE) & PGDIR_MASK;
+		if (next > end)
+			next = end;
+
+		if (!pgd_present(*pgd))
+			continue;
+
+		pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd));
+		phys_pud_remove(pud, __pa(start), __pa(end));
+		unmap_low_page(pud);
+	}
+
+	__flush_tlb_all();
+}
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 int __ref arch_remove_memory(u64 start, u64 size)
 {
@@ -687,6 +832,8 @@ int __ref arch_remove_memory(u64 start, 
 	ret = __remove_pages(zone, start_pfn, nr_pages);
 	WARN_ON_ONCE(ret);
 
+	kernel_physical_mapping_remove(start, start + size);
+
 	return ret;
 }
 #endif
Index: linux-3.6/arch/x86/include/asm/pgtable_types.h
===================================================================
--- linux-3.6.orig/arch/x86/include/asm/pgtable_types.h	2012-10-04 18:26:51.925486954 +0900
+++ linux-3.6/arch/x86/include/asm/pgtable_types.h	2012-10-04 18:30:27.322704656 +0900
@@ -334,6 +334,7 @@ static inline void update_page_count(int
  * 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__ */
 
Index: linux-3.6/arch/x86/mm/pageattr.c
===================================================================
--- linux-3.6.orig/arch/x86/mm/pageattr.c	2012-10-04 18:26:51.923486952 +0900
+++ linux-3.6/arch/x86/mm/pageattr.c	2012-10-04 18:30:27.328704662 +0900
@@ -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,
 	 * 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,
 	 * 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;
 }

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>


[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]