GBpages support for x86-64, v2

Index: linux/arch/x86/mm/init_64.c
===================================================================
@@ -415,7 +415,8 @@ void __init paging_init(void)
    from the CPU leading to inconsistent cache lines. address and size
    must be aligned to 2MB boundaries. 
    Does nothing when the mapping doesn't exist. */
-void __init clear_kernel_mapping(unsigned long address, unsigned long size) 
+static void __init
+__clear_kernel_mapping(unsigned long address, unsigned long size)
 {
 	unsigned long end = address + size;
 

@@ -445,6 +446,28 @@ void __init clear_kernel_mapping(unsigne
 	__flush_tlb_all();
 } 
 
+#define overlaps(as, ae, bs, be) ((ae) >= (bs) && (as) <= (be))
+
+void __init clear_kernel_mapping(unsigned long address, unsigned long size)
+{
+	int sh = PMD_SHIFT;
+	unsigned long kernel = __pa(__START_KERNEL_map);
+
+	/*
+	 * Note that we cannot unmap the kernel itself because the unmapped
+	 * holes here are always at least 2MB aligned.
+	 * This just applies to the trailing areas of the 40MB kernel mapping.
+	 */
+	if (overlaps(kernel >> sh, (kernel + KERNEL_TEXT_SIZE) >> sh,
+			__pa(address) >> sh, __pa(address + size) >> sh)) {
+		printk(KERN_WARNING
+			"Kernel mapping at %lx within 2MB of memory hole\n",
+				kernel);
+		__clear_kernel_mapping(__START_KERNEL_map+__pa(address), size);
+	}
+	__clear_kernel_mapping(address, size);
+}
+
 /*
  * Memory hotplug specific functions
  */

Index: linux/include/asm-x86/cpufeature.h
===================================================================
@@ -49,6 +49,7 @@
 #define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
 #define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
 #define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_GBPAGES	(1*32+26) /* GB pages */
 #define X86_FEATURE_RDTSCP	(1*32+27) /* RDTSCP */
 #define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
 #define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */

@@ -173,6 +174,7 @@
 #define cpu_has_bts		boot_cpu_has(X86_FEATURE_BTS)
 #define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
 #define cpu_has_ss		boot_cpu_has(X86_FEATURE_SELFSNOOP)
+#define cpu_has_gbpages 	boot_cpu_has(X86_FEATURE_GBPAGES)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg 	1

Index: linux/include/asm-x86/page_64.h
===================================================================
@@ -23,6 +23,9 @@
 #define MCE_STACK 5
 #define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
 
+#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
+
 #define __PAGE_OFFSET		_AC(0xffff810000000000, UL)
 
 #define __PHYSICAL_START	CONFIG_PHYSICAL_START

Index: linux/arch/x86/kernel/pci-gart_64.c
===================================================================
@@ -501,7 +501,7 @@ static __init unsigned long check_iommu_
 	}
 
 	a = aper + iommu_size;
-	iommu_size -= round_up(a, LARGE_PAGE_SIZE) - a;
+	iommu_size -= round_up(a, PMD_PAGE_SIZE) - a;
 
 	if (iommu_size < 64*1024*1024) {
 		printk(KERN_WARNING

Index: linux/arch/x86/mm/init_64.c
===================================================================
@@ -420,10 +420,10 @@ __clear_kernel_mapping(unsigned long add
 {
 	unsigned long end = address + size;
 
-	BUG_ON(address & ~LARGE_PAGE_MASK);
-	BUG_ON(size & ~LARGE_PAGE_MASK); 
+	BUG_ON(address & ~PMD_PAGE_MASK);
+	BUG_ON(size & ~PMD_PAGE_MASK);
 	
-	for (; address < end; address += LARGE_PAGE_SIZE) { 
+	for (; address < end; address += PMD_PAGE_SIZE) {
 		pgd_t *pgd = pgd_offset_k(address);
 		pud_t *pud;
 		pmd_t *pmd;

Index: linux/arch/x86/mm/pageattr_64.c
===================================================================
@@ -70,7 +70,7 @@ static struct page *split_large_page(uns
 	page_private(base) = 0;
 
 	address = __pa(address);
-	addr = address & LARGE_PAGE_MASK; 
+	addr = address & PMD_PAGE_MASK;
 	pbase = (pte_t *)page_address(base);
 	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
 		pbase[i] = pfn_pte(addr >> PAGE_SHIFT, 

@@ -150,7 +150,7 @@ static void revert_page(unsigned long ad
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, address);
 	BUG_ON(pmd_val(*pmd) & _PAGE_PSE);
-	pfn = (__pa(address) & LARGE_PAGE_MASK) >> PAGE_SHIFT;
+	pfn = (__pa(address) & PMD_PAGE_MASK) >> PAGE_SHIFT;
 	large_pte = pfn_pte(pfn, ref_prot);
 	large_pte = pte_mkhuge(large_pte);
 	set_pte((pte_t *)pmd, large_pte);

Index: linux/include/asm-x86/page_32.h
===================================================================
@@ -13,6 +13,10 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
+/* Eventually 32bit should be moved over to the new names too */
+#define LARGE_PAGE_SIZE PMD_PAGE_SIZE
+#define LARGE_PAGE_MASK PMD_PAGE_MASK
+
 #ifdef CONFIG_X86_PAE
 #define __PHYSICAL_MASK_SHIFT	36
 #define __VIRTUAL_MASK_SHIFT	32

Index: linux/include/asm-x86/page.h
===================================================================
@@ -13,8 +13,8 @@
 #define PHYSICAL_PAGE_MASK	(PAGE_MASK & __PHYSICAL_MASK)
 #define PTE_MASK		(_AT(long, PHYSICAL_PAGE_MASK))
 
-#define LARGE_PAGE_SIZE 	(_AC(1,UL) << PMD_SHIFT)
-#define LARGE_PAGE_MASK 	(~(LARGE_PAGE_SIZE-1))
+#define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
+#define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
 
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)

Index: linux/include/asm-x86/pgtable_64.h
===================================================================
@@ -208,6 +208,12 @@ static inline unsigned long pmd_bad(pmd_
 #define pud_offset(pgd, address) ((pud_t *) pgd_page_vaddr(*(pgd)) + pud_index(address))
 #define pud_present(pud) (pud_val(pud) & _PAGE_PRESENT)
 
+static inline int pud_large(pud_t pte)
+{
+	return (pud_val(pte) & (_PAGE_PSE|_PAGE_PRESENT)) ==
+		(_PAGE_PSE|_PAGE_PRESENT);
+}
+
 /* PMD  - Level 2 access */
 #define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
 #define pmd_page(pmd)		(pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))

Index: linux/arch/x86/mm/fault_64.c
===================================================================
@@ -200,7 +200,8 @@ void dump_pagetable(unsigned long addres
 	pud = pud_offset(pgd, address);
 	if (bad_address(pud)) goto bad;
 	printk("PUD %lx ", pud_val(*pud));
-	if (!pud_present(*pud))	goto ret;
+	if (!pud_present(*pud) || pud_large(*pud))
+		goto ret;
 
 	pmd = pmd_offset(pud, address);
 	if (bad_address(pmd)) goto bad;

Index: linux/arch/x86/mm/init_64.c
===================================================================
@@ -57,6 +57,18 @@ static unsigned long dma_reserve __initd
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
+int direct_gbpages;
+
+static int __init parse_direct_gbpages(char *arg)
+{
+	if (!strcmp(arg, "off")) {
+		direct_gbpages = -1;
+		return 0;
+	}
+	return -1;
+}
+early_param("direct_gbpages", parse_direct_gbpages);
+
 /*
  * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
  * physical space so we can cache the place of the first one and move

Index: linux/include/asm-x86/pgtable_64.h
===================================================================
@@ -248,6 +248,8 @@ static inline int pud_large(pud_t pte)
 
 #define update_mmu_cache(vma,address,pte) do { } while (0)
 
+extern int direct_gbpages;
+
 /* Encode and de-code a swap entry */
 #define __swp_type(x)			(((x).val >> 1) & 0x3f)
 #define __swp_offset(x)			((x).val >> 8)

Index: linux/arch/x86/mm/pageattr_64.c
===================================================================
@@ -40,6 +40,9 @@ pte_t *lookup_address(unsigned long addr
 	pud = pud_offset(pgd, address);
 	if (!pud_present(*pud))
 		return NULL; 
+	*level = 2;
+	if (pud_large(*pud))
+		return (pte_t *)pud;
 	pmd = pmd_offset(pud, address);
 	if (!pmd_present(*pmd))
 		return NULL; 

@@ -53,30 +56,85 @@ pte_t *lookup_address(unsigned long addr
 	return pte;
 } 
 
-static struct page *split_large_page(unsigned long address, pgprot_t prot,
-				     pgprot_t ref_prot)
-{ 
-	int i; 
+static pte_t *alloc_split_page(struct page **base)
+{
+	struct page *p = alloc_page(GFP_KERNEL);
+	if (!p)
+		return NULL;
+	SetPagePrivate(p);
+	page_private(p) = 0;
+	*base = p;
+	return page_address(p);
+}
+
+static struct page *free_split_page(struct page *base)
+{
+	BUG_ON(!PagePrivate(base));
+	BUG_ON(page_private(base) != 0);
+	ClearPagePrivate(base);
+	__free_page(base);
+	return NULL;
+}
+
+static struct page *
+split_pmd(unsigned long paddr, pgprot_t prot, pgprot_t ref_prot)
+{
+	int i;
 	unsigned long addr;
-	struct page *base = alloc_pages(GFP_KERNEL, 0);
-	pte_t *pbase;
-	if (!base) 
+	struct page *base;
+	pte_t *pbase = alloc_split_page(&base);
+	if (!pbase)
 		return NULL;
-	/*
-	 * page_private is used to track the number of entries in
-	 * the page table page have non standard attributes.
-	 */
-	SetPagePrivate(base);
-	page_private(base) = 0;
 
-	address = __pa(address);
-	addr = address & PMD_PAGE_MASK;
-	pbase = (pte_t *)page_address(base);
-	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
-		pbase[i] = pfn_pte(addr >> PAGE_SHIFT, 
-				   addr == address ? prot : ref_prot);
+	addr = paddr & PMD_PAGE_MASK;
+	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE)
+		pbase[i] = pfn_pte(addr >> PAGE_SHIFT,
+			   addr == paddr ? prot : ref_prot);
+
+	return base;
+}
+
+static struct page *
+split_gb(unsigned long paddr, pgprot_t prot, pgprot_t ref_prot)
+{
+	unsigned long addr;
+	int i;
+	struct page *base;
+	pte_t *pbase = alloc_split_page(&base);
+
+	if (!pbase)
+		return NULL;
+	addr = paddr & PUD_PAGE_MASK;
+	for (i = 0; i < PTRS_PER_PMD; i++, addr += PMD_PAGE_SIZE) {
+		if (paddr >= addr && paddr < addr + PMD_PAGE_SIZE) {
+			struct page *l3;
+			l3 = split_pmd(paddr, prot, ref_prot);
+			if (!l3)
+				return free_split_page(base);
+			page_private(l3)++;
+			pbase[i] = mk_pte(l3, ref_prot);
+		} else {
+			pbase[i] = pfn_pte(addr>>PAGE_SHIFT, ref_prot);
+			pbase[i] = pte_mkhuge(pbase[i]);
+		}
 	}
 	return base;
+}
+
+static struct page *split_large_page(unsigned long address, pgprot_t prot,
+				     pgprot_t ref_prot, int level)
+{
+	unsigned long paddr = __pa(address);
+	if (level == 2)
+		return split_gb(paddr, prot, ref_prot);
+	else if (level == 3)
+		return split_pmd(paddr, prot, ref_prot);
+	else {
+		printk("address %lx\n", address);
+		dump_pagetable(address);
+		BUG();
+	}
+	return NULL;
 } 
 
 struct flush_arg {

@@ -132,17 +190,40 @@ static inline void save_page(struct page
 		list_add(&fpage->lru, &deferred_pages);
 }
 
+static void reset_large_pte(pte_t *pte, unsigned long addr, pgprot_t prot)
+{
+	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
+	set_pte(pte, pte_mkhuge(pfn_pte(pfn, prot)));
+}
+
+static void
+revert_gb(unsigned long address, pud_t *pud, pmd_t *pmd, pgprot_t ref_prot)
+{
+	struct page *p = virt_to_page(pmd);
+
+	/* Reserved pages have been already set up at boot. Don't touch those. */
+	if (PageReserved(p))
+		return;
+
+	--page_private(p);
+	BUG_ON(page_private(p) < 0);
+	if (page_private(p) == 0) {
+		save_page(p);
+		reset_large_pte((pte_t *)pud, address & PUD_PAGE_MASK,
+					ref_prot);
+	}
+}
+
 /* 
  * No more special protections in this 2MB area - revert to a
- * large page again. 
+ * large or GB page again.
  */
+
 static void revert_page(unsigned long address, pgprot_t ref_prot)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t large_pte;
-	unsigned long pfn;
 
 	pgd = pgd_offset_k(address);
 	BUG_ON(pgd_none(*pgd));

@@ -150,10 +231,9 @@ static void revert_page(unsigned long ad
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, address);
 	BUG_ON(pmd_val(*pmd) & _PAGE_PSE);
-	pfn = (__pa(address) & PMD_PAGE_MASK) >> PAGE_SHIFT;
-	large_pte = pfn_pte(pfn, ref_prot);
-	large_pte = pte_mkhuge(large_pte);
-	set_pte((pte_t *)pmd, large_pte);
+	reset_large_pte((pte_t *)pmd, address & PMD_PAGE_MASK, ref_prot);
+
+	revert_gb(address, pud, pmd, ref_prot);
 }      
 
 /*

@@ -189,6 +269,7 @@ static void set_tlb_flush(unsigned long 
 static const unsigned short pat_bit[5] = {
 	[4] = _PAGE_PAT,
 	[3] = _PAGE_PAT_LARGE,
+	[2] = _PAGE_PAT_LARGE,
 };
 
 static int cache_attr_changed(pte_t pte, pgprot_t prot, int level)

@@ -228,15 +309,14 @@ __change_page_attr(unsigned long address
 				page_private(kpte_page)++;
 			set_pte(kpte, pfn_pte(pfn, prot));
 		} else {
-			/*
-			 * split_large_page will take the reference for this
-			 * change_page_attr on the split page.
-			 */
 			struct page *split;
 			ref_prot2 = pte_pgprot(pte_clrhuge(*kpte));
-			split = split_large_page(address, prot, ref_prot2);
+			split = split_large_page(address, prot, ref_prot2,
+						level);
 			if (!split)
 				return -ENOMEM;
+			if (level == 3 && !PageReserved(kpte_page))
+				page_private(kpte_page)++;
 			pgprot_val(ref_prot2) &= ~_PAGE_NX;
 			set_pte(kpte, mk_pte(split, ref_prot2));
 			kpte_page = split;

Index: linux/arch/x86/mm/init_64.c
===================================================================
@@ -268,13 +268,20 @@ void early_iounmap(void *addr, unsigned 
 	__flush_tlb();
 }
 
+static unsigned long direct_entry(unsigned long paddr)
+{
+	unsigned long entry;
+	entry = __PAGE_KERNEL_LARGE|paddr;
+	entry &= __supported_pte_mask;
+	return entry;
+}
+
 static void __meminit
 phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
 {
 	int i = pmd_index(address);
 
 	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
-		unsigned long entry;
 		pmd_t *pmd = pmd_page + pmd_index(address);
 
 		if (address >= end) {

@@ -287,9 +294,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned 
 		if (pmd_val(*pmd))
 			continue;
 
-		entry = __PAGE_KERNEL_LARGE|_PAGE_GLOBAL|address;
-		entry &= __supported_pte_mask;
-		set_pmd(pmd, __pmd(entry));
+		set_pmd(pmd, __pmd(direct_entry(address)));
 	}
 }
 

@@ -317,7 +322,13 @@ static void __meminit phys_pud_init(pud_
 			break;
 
 		if (pud_val(*pud)) {
-			phys_pmd_update(pud, addr, end);
+			if (!pud_large(*pud))
+				phys_pmd_update(pud, addr, end);
+			continue;
+		}
+
+		if (direct_gbpages > 0) {
+			set_pud(pud, __pud(direct_entry(addr)));
 			continue;
 		}
 

@@ -336,9 +347,11 @@ static void __init find_early_table_spac
 	unsigned long puds, pmds, tables, start;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE) +
-		 round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
+	if (!direct_gbpages) {
+		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+		tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+	}
 
  	/* RED-PEN putting page tables only on node 0 could
  	   cause a hotspot and fill up ZONE_DMA. The page tables

@@ -373,8 +386,15 @@ void __init_refok init_memory_mapping(un
 	 * mapped.  Unfortunately this is done currently before the nodes are 
 	 * discovered.
 	 */
-	if (!after_bootmem)
+	if (!after_bootmem) {
+		if (direct_gbpages >= 0 && cpu_has_gbpages) {
+			printk(KERN_INFO "Using GB pages for direct mapping\n");
+			direct_gbpages = 1;
+		} else
+			direct_gbpages = 0;
+
 		find_early_table_space(end);
+	}
 
 	start = (unsigned long)__va(start);
 	end = (unsigned long)__va(end);

@@ -423,6 +443,27 @@ void __init paging_init(void)
 }
 #endif
 
+static void split_gb_page(pud_t *pud, unsigned long paddr)
+{
+	int i;
+	pmd_t *pmd;
+	struct page *p = alloc_page(GFP_KERNEL);
+	if (!p)
+		return;
+
+	Dprintk("split_gb_page %lx\n", paddr);
+
+	SetPagePrivate(p);
+	/* Set reference to 1 so that c_p_a() does not undo it */
+	page_private(p) = 1;
+
+	paddr &= PUD_PAGE_MASK;
+	pmd = page_address(p);
+	for (i = 0; i < PTRS_PER_PTE; i++, paddr += PMD_PAGE_SIZE)
+		pmd[i] = __pmd(direct_entry(paddr));
+	pud_populate(NULL, pud, pmd);
+}
+
 /* Unmap a kernel mapping if it exists. This is useful to avoid prefetches
    from the CPU leading to inconsistent cache lines. address and size
    must be aligned to 2MB boundaries. 

@@ -434,6 +475,8 @@ __clear_kernel_mapping(unsigned long add
 
 	BUG_ON(address & ~PMD_PAGE_MASK);
 	BUG_ON(size & ~PMD_PAGE_MASK);
+
+	Dprintk("clear_kernel_mapping %lx-%lx\n", address, address+size);
 	
 	for (; address < end; address += PMD_PAGE_SIZE) {
 		pgd_t *pgd = pgd_offset_k(address);

@@ -442,6 +485,8 @@ __clear_kernel_mapping(unsigned long add
 		if (pgd_none(*pgd))
 			continue;
 		pud = pud_offset(pgd, address);
+		if (pud_large(*pud))
+			split_gb_page(pud, __pa(address));
 		if (pud_none(*pud))
 			continue; 
 		pmd = pmd_offset(pud, address);