[RFC PATCH 8/8] memory-hotplug: implement arch_remove_memory()

[Wen Congyang]

Set the entry for the removed memory to 0. If the entry related meory
is not whole removed, split it to smaller page, and clear it.

CC: David Rientjes <rientjes@xxxxxxxxxx>
CC: Jiang Liu <liuj97@xxxxxxxxx>
CC: Len Brown <len.brown@xxxxxxxxx>
CC: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
CC: Paul Mackerras <paulus@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/mm/init_64.c |  159 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 156 insertions(+), 3 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 78b94bc..d78f352 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -675,11 +675,164 @@ int arch_add_memory(int nid, u64 start, u64 size)
 }
 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 arch_remove_memory(unsigned long start, unsigned long size)
+int __ref arch_remove_memory(unsigned long start, unsigned long size)
 {
-	/* TODO */
-	return -EBUSY;
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	int ret;
+
+	ret = __remove_pages(start_pfn, nr_pages);
+	WARN_ON_ONCE(ret);
+
+	kernel_physical_mapping_remove(start, start + size);
+
+	return ret;
 }
 #endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/