X-Git-Url: http://pilppa.org/gitweb/?a=blobdiff_plain;f=arch%2Fx86%2Fmm%2Finit_64.c;h=7227a0a3f3a0cb70a52decb2715f681d1c330d3c;hb=b50efd2a55fc1344654875369d458bb6838bd37a;hp=359e3afaaa6b766ca9faeab23f8489e70b2c0296;hpb=1a0db38e5fa50eeb885194b1f4e494d4de55b918;p=linux-2.6-omap-h63xx.git

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 359e3afaaa6..7227a0a3f3a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -48,11 +48,6 @@
 #include <asm/numa.h>
 #include <asm/cacheflush.h>
 
-/*
- * PFN of last memory page.
- */
-unsigned long end_pfn;
-
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
  * The direct mapping extends to max_pfn_mapped, so that we can directly access
@@ -149,22 +144,13 @@ static __init void *spp_getpage(void)
 }
 
 void
-set_pte_vaddr(unsigned long vaddr, pte_t new_pte)
+set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
 {
-	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 
-	pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(new_pte));
-
-	pgd = pgd_offset_k(vaddr);
-	if (pgd_none(*pgd)) {
-		printk(KERN_ERR
-			"PGD FIXMAP MISSING, it should be setup in head.S!\n");
-		return;
-	}
-	pud = pud_offset(pgd, vaddr);
+	pud = pud_page + pud_index(vaddr);
 	if (pud_none(*pud)) {
 		pmd = (pmd_t *) spp_getpage();
 		pud_populate(&init_mm, pud, pmd);
@@ -197,6 +183,64 @@ set_pte_vaddr(unsigned long vaddr, pte_t new_pte)
 	__flush_tlb_one(vaddr);
 }
 
+void
+set_pte_vaddr(unsigned long vaddr, pte_t pteval)
+{
+	pgd_t *pgd;
+	pud_t *pud_page;
+
+	pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));
+
+	pgd = pgd_offset_k(vaddr);
+	if (pgd_none(*pgd)) {
+		printk(KERN_ERR
+			"PGD FIXMAP MISSING, it should be setup in head.S!\n");
+		return;
+	}
+	pud_page = (pud_t*)pgd_page_vaddr(*pgd);
+	set_pte_vaddr_pud(pud_page, vaddr, pteval);
+}
+
+/*
+ * Create large page table mappings for a range of physical addresses.
+ */
+static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
+						pgprot_t prot)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
+	for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
+		pgd = pgd_offset_k((unsigned long)__va(phys));
+		if (pgd_none(*pgd)) {
+			pud = (pud_t *) spp_getpage();
+			set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE |
+						_PAGE_USER));
+		}
+		pud = pud_offset(pgd, (unsigned long)__va(phys));
+		if (pud_none(*pud)) {
+			pmd = (pmd_t *) spp_getpage();
+			set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
+						_PAGE_USER));
+		}
+		pmd = pmd_offset(pud, phys);
+		BUG_ON(!pmd_none(*pmd));
+		set_pmd(pmd, __pmd(phys | pgprot_val(prot)));
+	}
+}
+
+void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
+{
+	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE);
+}
+
+void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
+{
+	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE);
+}
+
 /*
  * The head.S code sets up the kernel high mapping:
  *
@@ -227,6 +271,7 @@ void __init cleanup_highmap(void)
 
 static unsigned long __initdata table_start;
 static unsigned long __meminitdata table_end;
+static unsigned long __meminitdata table_top;
 
 static __meminit void *alloc_low_page(unsigned long *phys)
 {
@@ -240,7 +285,7 @@ static __meminit void *alloc_low_page(unsigned long *phys)
 		return adr;
 	}
 
-	if (pfn >= end_pfn)
+	if (pfn >= table_top)
 		panic("alloc_low_page: ran out of memory");
 
 	adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
@@ -257,15 +302,55 @@ static __meminit void unmap_low_page(void *adr)
 	early_iounmap(adr, PAGE_SIZE);
 }
 
+static void __meminit
+phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end)
+{
+	unsigned pages = 0;
+	int i;
+	pte_t *pte = pte_page + pte_index(addr);
+
+	for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) {
+
+		if (addr >= end) {
+			if (!after_bootmem) {
+				for(; i < PTRS_PER_PTE; i++, pte++)
+					set_pte(pte, __pte(0));
+			}
+			break;
+		}
+
+		if (pte_val(*pte))
+			continue;
+
+		if (0)
+			printk("   pte=%p addr=%lx pte=%016lx\n",
+			       pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
+		set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL));
+		pages++;
+	}
+	update_page_count(PG_LEVEL_4K, pages);
+}
+
+static void __meminit
+phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end)
+{
+	pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
+
+	phys_pte_init(pte, address, end);
+}
+
 static unsigned long __meminit
-phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
+phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
+			 unsigned long page_size_mask)
 {
 	unsigned long pages = 0;
 
 	int i = pmd_index(address);
 
 	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
+		unsigned long pte_phys;
 		pmd_t *pmd = pmd_page + pmd_index(address);
+		pte_t *pte;
 
 		if (address >= end) {
 			if (!after_bootmem) {
@@ -275,32 +360,46 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
 			break;
 		}
 
-		if (pmd_val(*pmd))
+		if (pmd_val(*pmd)) {
+			if (!pmd_large(*pmd))
+				phys_pte_update(pmd, address, end);
 			continue;
+		}
 
-		pages++;
-		set_pte((pte_t *)pmd,
-			pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+		if (page_size_mask & (1<<PG_LEVEL_2M)) {
+			pages++;
+			set_pte((pte_t *)pmd,
+				pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+			continue;
+		}
+
+		pte = alloc_low_page(&pte_phys);
+		phys_pte_init(pte, address, end);
+		unmap_low_page(pte);
+
+		pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
 	}
 	update_page_count(PG_LEVEL_2M, pages);
 	return address;
 }
 
 static unsigned long __meminit
-phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
+phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
+			 unsigned long page_size_mask)
 {
 	pmd_t *pmd = pmd_offset(pud, 0);
 	unsigned long last_map_addr;
 
 	spin_lock(&init_mm.page_table_lock);
-	last_map_addr = phys_pmd_init(pmd, address, end);
+	last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask);
 	spin_unlock(&init_mm.page_table_lock);
 	__flush_tlb_all();
 	return last_map_addr;
 }
 
 static unsigned long __meminit
-phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
+phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
+			 unsigned long page_size_mask)
 {
 	unsigned long pages = 0;
 	unsigned long last_map_addr = end;
@@ -322,11 +421,12 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 
 		if (pud_val(*pud)) {
 			if (!pud_large(*pud))
-				last_map_addr = phys_pmd_update(pud, addr, end);
+				last_map_addr = phys_pmd_update(pud, addr, end,
+							 page_size_mask);
 			continue;
 		}
 
-		if (direct_gbpages) {
+		if (page_size_mask & (1<<PG_LEVEL_1G)) {
 			pages++;
 			set_pte((pte_t *)pud,
 				pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
@@ -337,11 +437,11 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 		pmd = alloc_low_page(&pmd_phys);
 
 		spin_lock(&init_mm.page_table_lock);
+		last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask);
+		unmap_low_page(pmd);
 		pud_populate(&init_mm, pud, __va(pmd_phys));
-		last_map_addr = phys_pmd_init(pmd, addr, end);
 		spin_unlock(&init_mm.page_table_lock);
 
-		unmap_low_page(pmd);
 	}
 	__flush_tlb_all();
 	update_page_count(PG_LEVEL_1G, pages);
@@ -349,16 +449,31 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
 	return last_map_addr;
 }
 
+static unsigned long __meminit
+phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
+		 unsigned long page_size_mask)
+{
+	pud_t *pud;
+
+	pud = (pud_t *)pgd_page_vaddr(*pgd);
+
+	return phys_pud_init(pud, addr, end, page_size_mask);
+}
+
 static void __init find_early_table_space(unsigned long end)
 {
-	unsigned long puds, pmds, tables, start;
+	unsigned long puds, tables, start;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
 	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
 	if (!direct_gbpages) {
-		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+		unsigned long pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
 		tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
 	}
+	if (!cpu_has_pse) {
+		unsigned long ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		tables += round_up(ptes * sizeof(pte_t), PAGE_SIZE);
+	}
 
 	/*
 	 * RED-PEN putting page tables only on node 0 could
@@ -372,10 +487,10 @@ static void __init find_early_table_space(unsigned long end)
 
 	table_start >>= PAGE_SHIFT;
 	table_end = table_start;
+	table_top = table_start + (tables >> PAGE_SHIFT);
 
-	early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, table_start << PAGE_SHIFT,
-		(table_start << PAGE_SHIFT) + tables);
+	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
+		end, table_start << PAGE_SHIFT, table_top << PAGE_SHIFT);
 }
 
 static void __init init_gbpages(void)
@@ -498,15 +613,55 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 }
 #endif
 
+static unsigned long __init kernel_physical_mapping_init(unsigned long start,
+						unsigned long end,
+						unsigned long page_size_mask)
+{
+
+	unsigned long next, last_map_addr = end;
+
+	start = (unsigned long)__va(start);
+	end = (unsigned long)__va(end);
+
+	for (; start < end; start = next) {
+		pgd_t *pgd = pgd_offset_k(start);
+		unsigned long pud_phys;
+		pud_t *pud;
+
+		next = start + PGDIR_SIZE;
+		if (next > end)
+			next = end;
+
+		if (pgd_val(*pgd)) {
+			last_map_addr = phys_pud_update(pgd, __pa(start),
+						 __pa(end), page_size_mask);
+			continue;
+		}
+
+		if (after_bootmem)
+			pud = pud_offset(pgd, start & PGDIR_MASK);
+		else
+			pud = alloc_low_page(&pud_phys);
+
+		last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
+						 page_size_mask);
+		unmap_low_page(pud);
+		pgd_populate(&init_mm, pgd_offset_k(start),
+			     __va(pud_phys));
+	}
+
+	return last_map_addr;
+}
 /*
  * Setup the direct mapping of the physical memory at PAGE_OFFSET.
  * This runs before bootmem is initialized and gets pages directly from
  * the physical memory. To access them they are temporarily mapped.
  */
-unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long end)
+unsigned long __init_refok init_memory_mapping(unsigned long start,
+					       unsigned long end)
 {
-	unsigned long next, last_map_addr = end;
-	unsigned long start_phys = start, end_phys = end;
+	unsigned long last_map_addr;
+	unsigned long page_size_mask = 0;
 
 	printk(KERN_INFO "init_memory_mapping\n");
 
@@ -522,39 +677,27 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned lon
 		find_early_table_space(end);
 	}
 
-	start = (unsigned long)__va(start);
-	end = (unsigned long)__va(end);
+	if (direct_gbpages)
+		page_size_mask |= 1 << PG_LEVEL_1G;
+	if (cpu_has_pse)
+		page_size_mask |= 1 << PG_LEVEL_2M;
 
-	for (; start < end; start = next) {
-		pgd_t *pgd = pgd_offset_k(start);
-		unsigned long pud_phys;
-		pud_t *pud;
-
-		if (after_bootmem)
-			pud = pud_offset(pgd, start & PGDIR_MASK);
-		else
-			pud = alloc_low_page(&pud_phys);
-
-		next = start + PGDIR_SIZE;
-		if (next > end)
-			next = end;
-		last_map_addr = phys_pud_init(pud, __pa(start), __pa(next));
-		if (!after_bootmem)
-			pgd_populate(&init_mm, pgd_offset_k(start),
-				     __va(pud_phys));
-		unmap_low_page(pud);
-	}
+	last_map_addr = kernel_physical_mapping_init(start, end,
+							 page_size_mask);
 
 	if (!after_bootmem)
 		mmu_cr4_features = read_cr4();
 	__flush_tlb_all();
 
-	if (!after_bootmem)
+	if (!after_bootmem && table_end > table_start)
 		reserve_early(table_start << PAGE_SHIFT,
 				 table_end << PAGE_SHIFT, "PGTABLE");
 
+	printk(KERN_INFO "last_map_addr: %lx end: %lx\n",
+			 last_map_addr, end);
+
 	if (!after_bootmem)
-		early_memtest(start_phys, end_phys);
+		early_memtest(start, end);
 
 	return last_map_addr >> PAGE_SHIFT;
 }
@@ -585,9 +728,9 @@ void __init paging_init(void)
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
 	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
 	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
-	max_zone_pfns[ZONE_NORMAL] = end_pfn;
+	max_zone_pfns[ZONE_NORMAL] = max_pfn;
 
-	memory_present(0, 0, end_pfn);
+	memory_present(0, 0, max_pfn);
 	sparse_init();
 	free_area_init_nodes(max_zone_pfns);
 }
@@ -669,8 +812,8 @@ void __init mem_init(void)
 #else
 	totalram_pages = free_all_bootmem();
 #endif
-	reservedpages = end_pfn - totalram_pages -
-					absent_pages_in_range(0, end_pfn);
+	reservedpages = max_pfn - totalram_pages -
+					absent_pages_in_range(0, max_pfn);
 	after_bootmem = 1;
 
 	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
@@ -689,7 +832,7 @@ void __init mem_init(void)
 	printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
 				"%ldk reserved, %ldk data, %ldk init)\n",
 		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
-		end_pfn << (PAGE_SHIFT-10),
+		max_pfn << (PAGE_SHIFT-10),
 		codesize >> 10,
 		reservedpages << (PAGE_SHIFT-10),
 		datasize >> 10,
@@ -783,7 +926,7 @@ int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
 #endif
 	unsigned long pfn = phys >> PAGE_SHIFT;
 
-	if (pfn >= end_pfn) {
+	if (pfn >= max_pfn) {
 		/*
 		 * This can happen with kdump kernels when accessing
 		 * firmware tables:
@@ -922,7 +1065,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 	pmd_t *pmd;
 
 	for (; addr < end; addr = next) {
-		next = pmd_addr_end(addr, end);
+		void *p = NULL;
 
 		pgd = vmemmap_pgd_populate(addr, node);
 		if (!pgd)
@@ -932,33 +1075,51 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
 		if (!pud)
 			return -ENOMEM;
 
-		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd)) {
-			pte_t entry;
-			void *p;
+		if (!cpu_has_pse) {
+			next = (addr + PAGE_SIZE) & PAGE_MASK;
+			pmd = vmemmap_pmd_populate(pud, addr, node);
+
+			if (!pmd)
+				return -ENOMEM;
+
+			p = vmemmap_pte_populate(pmd, addr, node);
 
-			p = vmemmap_alloc_block(PMD_SIZE, node);
 			if (!p)
 				return -ENOMEM;
 
-			entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
-							PAGE_KERNEL_LARGE);
-			set_pmd(pmd, __pmd(pte_val(entry)));
-
-			/* check to see if we have contiguous blocks */
-			if (p_end != p || node_start != node) {
-				if (p_start)
-					printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
-						addr_start, addr_end-1, p_start, p_end-1, node_start);
-				addr_start = addr;
-				node_start = node;
-				p_start = p;
-			}
-			addr_end = addr + PMD_SIZE;
-			p_end = p + PMD_SIZE;
+			addr_end = addr + PAGE_SIZE;
+			p_end = p + PAGE_SIZE;
 		} else {
-			vmemmap_verify((pte_t *)pmd, node, addr, next);
+			next = pmd_addr_end(addr, end);
+
+			pmd = pmd_offset(pud, addr);
+			if (pmd_none(*pmd)) {
+				pte_t entry;
+
+				p = vmemmap_alloc_block(PMD_SIZE, node);
+				if (!p)
+					return -ENOMEM;
+
+				entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
+						PAGE_KERNEL_LARGE);
+				set_pmd(pmd, __pmd(pte_val(entry)));
+
+				addr_end = addr + PMD_SIZE;
+				p_end = p + PMD_SIZE;
+
+				/* check to see if we have contiguous blocks */
+				if (p_end != p || node_start != node) {
+					if (p_start)
+						printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
+						       addr_start, addr_end-1, p_start, p_end-1, node_start);
+					addr_start = addr;
+					node_start = node;
+					p_start = p;
+				}
+			} else
+				vmemmap_verify((pte_t *)pmd, node, addr, next);
 		}
+
 	}
 	return 0;
 }