[v2,09/12] memory-hotplug: remove page table of x86_64 architecture

Commit Message

Wen Congyang Oct. 23, 2012, 10:30 a.m. UTC

From: Wen Congyang <[e-mail]>

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 <[e-mail]>
CC: Jiang Liu <[e-mail]>
CC: Len Brown <[e-mail]>
CC: Christoph Lameter <[e-mail]>
Cc: Minchan Kim <[e-mail]>
CC: Andrew Morton <[e-mail]>
CC: KOSAKI Motohiro <[e-mail]>
CC: Yasuaki Ishimatsu <[e-mail]>
Signed-off-by: Wen Congyang <[e-mail]>
Signed-off-by: Jianguo Wu <[e-mail]>
Signed-off-by: Jiang Liu <[e-mail]>
---
 arch/x86/include/asm/pgtable_types.h |    1 +
 arch/x86/mm/init_64.c                |  223 ++++++++++++++++++++++++++++++++++
 arch/x86/mm/pageattr.c               |   47 ++++----
 3 files changed, 249 insertions(+), 22 deletions(-)

Patch

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 73b1b6a..4809a9f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -675,6 +675,227 @@  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);
+}
+
+static void 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;
+	}
+
+	/* free a pud table */
+	free_pagetable(pgd_page(*pgd));
+	pgd_clear(pgd);
+}
+
+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;
+
+	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));
+		free_pud_table(pud, pgd);
+		unmap_low_page(pud);
+	}
+
+	flush_tlb_all();
+}
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 int __ref arch_remove_memory(u64 start, u64 size)
 {
@@ -687,6 +908,8 @@  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;
 }