At 11/28/2012 05:40 PM, Jianguo Wu Wrote:

Hmm, vmemmap doesn't use vmalloc() to allocate memory.

+		else
+			free_pages((unsigned long)page_address(page), order);
+	}
+}
+
+static void free_pte_table(pmd_t *pmd)
+{
+	pte_t *pte, *pte_start;
+	int i;
+
+	pte_start = (pte_t *)pmd_page_vaddr(*pmd);
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte = pte_start + i;
+		if (pte_val(*pte))
+			return;
+	}
+
+	/* free a pte talbe */
+	vmemmap_free_pages(pmd_page(*pmd), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pmd_clear(pmd);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static void free_pmd_table(pud_t *pud)
+{
+	pmd_t *pmd, *pmd_start;
+	int i;
+
+	pmd_start = (pmd_t *)pud_page_vaddr(*pud);
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd = pmd_start + i;
+		if (pmd_val(*pmd))
+			return;
+	}
+
+	/* free a pmd talbe */
+	vmemmap_free_pages(pud_page(*pud), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pud_clear(pud);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static void free_pud_table(pgd_t *pgd)
+{
+	pud_t *pud, *pud_start;
+	int i;
+
+	pud_start = (pud_t *)pgd_page_vaddr(*pgd);
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		pud = pud_start + i;
+		if (pud_val(*pud))
+			return;
+	}
+
+	/* free a pud table */
+	vmemmap_free_pages(pgd_page(*pgd), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pgd_clear(pgd);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static int split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
+{
+	struct page *page = pmd_page(*(pmd_t *)kpte);
+	int i = 0;
+	unsigned long magic;
+	unsigned long section_nr;
+
+	__split_large_page(kpte, address, pbase);
+	__flush_tlb_all();
+
+	magic = (unsigned long) page->lru.next;
+	if (magic == SECTION_INFO) {
+		section_nr = pfn_to_section_nr(page_to_pfn(page));
+		while (i < PTRS_PER_PMD) {
+			page++;
+			i++;
+			get_page_bootmem(section_nr, page, SECTION_INFO);
+		}
+	}
+
+	return 0;
+}
+
+static void vmemmap_pte_remove(pmd_t *pmd, unsigned long addr, unsigned long end)
+{
+	pte_t *pte;
+	unsigned long next;
+
+	pte = pte_offset_kernel(pmd, addr);
+	for (; addr < end; pte++, addr += PAGE_SIZE) {
+		next = (addr + PAGE_SIZE) & PAGE_MASK;
+		if (next > end)
+			next = end;
+
+		if (pte_none(*pte))
+			continue;
+		if (IS_ALIGNED(addr, PAGE_SIZE) &&
+		    IS_ALIGNED(end, PAGE_SIZE)) {
+			vmemmap_free_pages(pte_page(*pte), 0);
+			spin_lock(&init_mm.page_table_lock);
+			pte_clear(&init_mm, addr, pte);
+			spin_unlock(&init_mm.page_table_lock);

If addr or end is not alianed with PAGE_SIZE, you may leak some
memory.

+		}
+	}
+
+	free_pte_table(pmd);
+	__flush_tlb_all();
+}
+
+static void vmemmap_pmd_remove(pud_t *pud, unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	pmd_t *pmd;
+
+	pmd = pmd_offset(pud, addr);
+	for (; addr < end; addr = next, pmd++) {
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(*pmd))
+			continue;
+
+		if (cpu_has_pse) {
+			unsigned long pte_base;
+
+			if (IS_ALIGNED(addr, PMD_SIZE) &&
+			    IS_ALIGNED(next, PMD_SIZE)) {
+				vmemmap_free_pages(pmd_page(*pmd),
+						   get_order(PMD_SIZE));
+				spin_lock(&init_mm.page_table_lock);
+				pmd_clear(pmd);
+				spin_unlock(&init_mm.page_table_lock);
+				continue;
+			}
+
+			/*
+			 * We use 2M page, but we need to remove part of them,
+			 * so split 2M page to 4K page.
+			 */
+			pte_base = get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);

get_zeored_page() may fail. You should handle this error.

+			split_large_page((pte_t *)pmd, addr, (pte_t *)pte_base);
+			__flush_tlb_all();
+
+			spin_lock(&init_mm.page_table_lock);
+			pmd_populate_kernel(&init_mm, pmd, (pte_t *)pte_base);
+			spin_unlock(&init_mm.page_table_lock);
+		}
+
+		vmemmap_pte_remove(pmd, addr, next);
+	}
+
+	free_pmd_table(pud);
+	__flush_tlb_all();
+}
+
+static void vmemmap_pud_remove(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+	unsigned long next;
+	pud_t *pud;
+
+	pud = pud_offset(pgd, addr);
+	for (; addr < end; addr = next, pud++) {
+		next = pud_addr_end(addr, end);
+		if (pud_none(*pud))
+			continue;
+
+		vmemmap_pmd_remove(pud, addr, next);
+	}
+
+	free_pud_table(pgd);
+	__flush_tlb_all();
+}
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+	unsigned long addr = (unsigned long)memmap;
+	unsigned long end = (unsigned long)(memmap + nr_pages);
+	unsigned long next;
+
+	for (; addr < end; addr = next) {
+		pgd_t *pgd = pgd_offset_k(addr);
+
+		next = pgd_addr_end(addr, end);
+		if (!pgd_present(*pgd))
+			continue;
+
+		vmemmap_pud_remove(pgd, addr, next);
+		sync_global_pgds(addr, next);

The parameter for sync_global_pgds() is [start, end], not
[start, end)

Why do you change this line?

 {
-	return; /* XXX: Not implemented yet */
+	vmemmap_free(page, nr_pages);
 }
 static void free_map_bootmem(struct page *page, unsigned long nr_pages)
 {
+	vmemmap_free(page, nr_pages);
 }
 #else
 static struct page *__kmalloc_section_memmap(unsigned long nr_pages)