Merge commit 'v2.6.28-rc9' into next

9 files changed, 166 insertions, 44 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 59f89b434b4..fea4565ff57 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,7 @@
 obj-y	:=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
 	    pat.o pgtable.o gup.o
 
-obj-$(CONFIG_X86_32)		+= pgtable_32.o
+obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_X86_PTDUMP)	+= dump_pagetables.o
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 4ba373c5b8c..be54176e9eb 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -233,7 +233,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	len = (unsigned long) nr_pages << PAGE_SHIFT;
 	end = start + len;
 	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
-					start, len)))
+					(void __user *)start, len)))
 		goto slow_irqon;
 
 	/*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8396868e82c..c483f424207 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -334,7 +334,6 @@ int devmem_is_allowed(unsigned long pagenr)
 	return 0;
 }
 
-#ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
 pgprot_t kmap_prot;
 
@@ -357,6 +356,7 @@ static void __init kmap_init(void)
 	kmap_prot = PAGE_KERNEL;
 }
 
+#ifdef CONFIG_HIGHMEM
 static void __init permanent_kmaps_init(pgd_t *pgd_base)
 {
 	unsigned long vaddr;
@@ -436,7 +436,6 @@ static void __init set_highmem_pages_init(void)
 #endif /* !CONFIG_NUMA */
 
 #else
-# define kmap_init()				do { } while (0)
 # define permanent_kmaps_init(pgd_base)		do { } while (0)
 # define set_highmem_pages_init()	do { } while (0)
 #endif /* CONFIG_HIGHMEM */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b8e461d4941..9db01db6e3c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -350,8 +350,10 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
 		 * pagetable pages as RO. So assume someone who pre-setup
 		 * these mappings are more intelligent.
 		 */
-		if (pte_val(*pte))
+		if (pte_val(*pte)) {
+			pages++;
 			continue;
+		}
 
 		if (0)
 			printk("   pte=%p addr=%lx pte=%016lx\n",
@@ -418,8 +420,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 			 * not differ with respect to page frame and
 			 * attributes.
 			 */
-			if (page_size_mask & (1 << PG_LEVEL_2M))
+			if (page_size_mask & (1 << PG_LEVEL_2M)) {
+				pages++;
 				continue;
+			}
 			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
 		}
 
@@ -499,8 +503,10 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 			 * not differ with respect to page frame and
 			 * attributes.
 			 */
-			if (page_size_mask & (1 << PG_LEVEL_1G))
+			if (page_size_mask & (1 << PG_LEVEL_1G)) {
+				pages++;
 				continue;
+			}
 			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
 		}
 
@@ -665,12 +671,13 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	unsigned long last_map_addr = 0;
 	unsigned long page_size_mask = 0;
 	unsigned long start_pfn, end_pfn;
+	unsigned long pos;
 
 	struct map_range mr[NR_RANGE_MR];
 	int nr_range, i;
 	int use_pse, use_gbpages;
 
-	printk(KERN_INFO "init_memory_mapping\n");
+	printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
 
 	/*
 	 * Find space for the kernel direct mapping tables.
@@ -704,35 +711,50 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
 	/* head if not big page alignment ?*/
 	start_pfn = start >> PAGE_SHIFT;
-	end_pfn = ((start + (PMD_SIZE - 1)) >> PMD_SHIFT)
+	pos = start_pfn << PAGE_SHIFT;
+	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
 			<< (PMD_SHIFT - PAGE_SHIFT);
-	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+		pos = end_pfn << PAGE_SHIFT;
+	}
 
 	/* big page (2M) range*/
-	start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
+	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
 			 << (PMD_SHIFT - PAGE_SHIFT);
-	end_pfn = ((start + (PUD_SIZE - 1))>>PUD_SHIFT)
+	end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
 			 << (PUD_SHIFT - PAGE_SHIFT);
-	if (end_pfn > ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT)))
-		end_pfn = ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT));
-	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
-			page_size_mask & (1<<PG_LEVEL_2M));
+	if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
+		end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask & (1<<PG_LEVEL_2M));
+		pos = end_pfn << PAGE_SHIFT;
+	}
 
 	/* big page (1G) range */
-	start_pfn = end_pfn;
-	end_pfn = (end>>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
-	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+	start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+			 << (PUD_SHIFT - PAGE_SHIFT);
+	end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
 				page_size_mask &
 				 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+		pos = end_pfn << PAGE_SHIFT;
+	}
 
 	/* tail is not big page (1G) alignment */
-	start_pfn = end_pfn;
-	end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
-	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
-			page_size_mask & (1<<PG_LEVEL_2M));
+	start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+			 << (PMD_SHIFT - PAGE_SHIFT);
+	end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+	if (start_pfn < end_pfn) {
+		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+				page_size_mask & (1<<PG_LEVEL_2M));
+		pos = end_pfn << PAGE_SHIFT;
+	}
 
 	/* tail is not big page (2M) alignment */
-	start_pfn = end_pfn;
+	start_pfn = pos>>PAGE_SHIFT;
 	end_pfn = end>>PAGE_SHIFT;
 	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
 
@@ -831,12 +853,12 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;
 
-	last_mapped_pfn = init_memory_mapping(start, start + size-1);
+	last_mapped_pfn = init_memory_mapping(start, start + size);
 	if (last_mapped_pfn > max_pfn_mapped)
 		max_pfn_mapped = last_mapped_pfn;
 
 	ret = __add_pages(zone, start_pfn, nr_pages);
-	WARN_ON(1);
+	WARN_ON_ONCE(ret);
 
 	return ret;
 }
@@ -878,6 +900,7 @@ static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
 void __init mem_init(void)
 {
 	long codesize, reservedpages, datasize, initsize;
+	unsigned long absent_pages;
 
 	start_periodic_check_for_corruption();
 
@@ -893,8 +916,9 @@ void __init mem_init(void)
 #else
 	totalram_pages = free_all_bootmem();
 #endif
-	reservedpages = max_pfn - totalram_pages -
-					absent_pages_in_range(0, max_pfn);
+
+	absent_pages = absent_pages_in_range(0, max_pfn);
+	reservedpages = max_pfn - totalram_pages - absent_pages;
 	after_bootmem = 1;
 
 	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
@@ -911,10 +935,11 @@ void __init mem_init(void)
 				 VSYSCALL_END - VSYSCALL_START);
 
 	printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
-				"%ldk reserved, %ldk data, %ldk init)\n",
+			 "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
 		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
 		max_pfn << (PAGE_SHIFT-10),
 		codesize >> 10,
+		absent_pages << (PAGE_SHIFT-10),
 		reservedpages << (PAGE_SHIFT-10),
 		datasize >> 10,
 		initsize >> 10);
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
new file mode 100644
index 00000000000..d0151d8ce45
--- /dev/null
+++ b/arch/x86/mm/iomap_32.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <asm/iomap.h>
+#include <linux/module.h>
+
+/* Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
+	enum fixed_addresses idx;
+	unsigned long vaddr;
+
+	pagefault_disable();
+
+	idx = type + KM_TYPE_NR*smp_processor_id();
+	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+	set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
+	arch_flush_lazy_mmu_mode();
+
+	return (void*) vaddr;
+}
+EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type)
+{
+	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+	/*
+	 * Force other mappings to Oops if they'll try to access this pte
+	 * without first remap it.  Keeping stale mappings around is a bad idea
+	 * also, in case the page changes cacheability attributes or becomes
+	 * a protected page in a hypervisor.
+	 */
+	if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+		kpte_clear_flush(kmap_pte-idx, vaddr);
+
+	arch_flush_lazy_mmu_mode();
+	pagefault_enable();
+}
+EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index ae71e11eb3e..d4c4307ff3e 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -387,7 +387,7 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
 					unsigned long size)
 {
 	unsigned long flags;
-	void *ret;
+	void __iomem *ret;
 	int err;
 
 	/*
@@ -399,11 +399,11 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
 	if (err < 0)
 		return NULL;
 
-	ret = (void *) __ioremap_caller(phys_addr, size, flags,
-					__builtin_return_address(0));
+	ret = __ioremap_caller(phys_addr, size, flags,
+			       __builtin_return_address(0));
 
 	free_memtype(phys_addr, phys_addr + size);
-	return (void __iomem *)ret;
+	return ret;
 }
 
 void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
@@ -622,7 +622,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
 		__early_set_fixmap(idx, 0, __pgprot(0));
 }
 
-static void *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
 static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
 static int __init check_early_ioremap_leak(void)
 {
@@ -645,7 +645,7 @@ static int __init check_early_ioremap_leak(void)
 }
 late_initcall(check_early_ioremap_leak);
 
-static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
+static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
 {
 	unsigned long offset, last_addr;
 	unsigned int nrpages;
@@ -713,23 +713,23 @@ static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size,
 	if (early_ioremap_debug)
 		printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0));
 
-	prev_map[slot] = (void *) (offset + fix_to_virt(idx0));
+	prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0));
 	return prev_map[slot];
 }
 
 /* Remap an IO device */
-void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size)
 {
 	return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO);
 }
 
 /* Remap memory */
-void __init *early_memremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size)
 {
 	return __early_ioremap(phys_addr, size, PAGE_KERNEL);
 }
 
-void __init early_iounmap(void *addr, unsigned long size)
+void __init early_iounmap(void __iomem *addr, unsigned long size)
 {
 	unsigned long virt_addr;
 	unsigned long offset;
@@ -779,7 +779,7 @@ void __init early_iounmap(void *addr, unsigned long size)
 		--idx;
 		--nrpages;
 	}
-	prev_map[slot] = 0;
+	prev_map[slot] = NULL;
 }
 
 void __this_fixmap_does_not_exist(void)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 847c164725f..8518c678d83 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -222,6 +222,41 @@ static void __init remap_numa_kva(void)
 	}
 }
 
+#ifdef CONFIG_HIBERNATION
+/**
+ * resume_map_numa_kva - add KVA mapping to the temporary page tables created
+ *                       during resume from hibernation
+ * @pgd_base - temporary resume page directory
+ */
+void resume_map_numa_kva(pgd_t *pgd_base)
+{
+	int node;
+
+	for_each_online_node(node) {
+		unsigned long start_va, start_pfn, size, pfn;
+
+		start_va = (unsigned long)node_remap_start_vaddr[node];
+		start_pfn = node_remap_start_pfn[node];
+		size = node_remap_size[node];
+
+		printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+
+		for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
+			pgd_t *pgd = pgd_base + pgd_index(vaddr);
+			pud_t *pud = pud_offset(pgd, vaddr);
+			pmd_t *pmd = pmd_offset(pud, vaddr);
+
+			set_pmd(pmd, pfn_pmd(start_pfn + pfn,
+						PAGE_KERNEL_LARGE_EXEC));
+
+			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
+				__FUNCTION__, vaddr, start_pfn + pfn);
+		}
+	}
+}
+#endif
+
 static unsigned long calculate_numa_remap_pages(void)
 {
 	int nid;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f1dc1b75d16..e89d24815f2 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -67,18 +67,18 @@ static void split_page_count(int level)
 
 void arch_report_meminfo(struct seq_file *m)
 {
-	seq_printf(m, "DirectMap4k:  %8lu kB\n",
+	seq_printf(m, "DirectMap4k:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_4K] << 2);
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-	seq_printf(m, "DirectMap2M:  %8lu kB\n",
+	seq_printf(m, "DirectMap2M:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_2M] << 11);
 #else
-	seq_printf(m, "DirectMap4M:  %8lu kB\n",
+	seq_printf(m, "DirectMap4M:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_2M] << 12);
 #endif
 #ifdef CONFIG_X86_64
 	if (direct_gbpages)
-		seq_printf(m, "DirectMap1G:  %8lu kB\n",
+		seq_printf(m, "DirectMap1G:    %8lu kB\n",
 			direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
 }
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 738fd0f2495..eb1bf000d12 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -481,12 +481,16 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 	return 1;
 }
 #else
+/* This check is needed to avoid cache aliasing when PAT is enabled */
 static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 {
 	u64 from = ((u64)pfn) << PAGE_SHIFT;
 	u64 to = from + size;
 	u64 cursor = from;
 
+	if (!pat_enabled)
+		return 1;
+
 	while (cursor < to) {
 		if (!devmem_is_allowed(pfn)) {
 			printk(KERN_INFO