Merge branch 'akpm/master'

11 files changed, 141 insertions, 48 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6a9383370311..a4f24f5b1218 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -112,6 +112,7 @@ config X86
 	select GENERIC_STRNLEN_USER
 	select HAVE_CONTEXT_TRACKING if X86_64
 	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_VIRT_TO_BUS
 	select MODULES_USE_ELF_REL if X86_32
 	select MODULES_USE_ELF_RELA if X86_64
 	select CLONE_BACKWARDS if X86_32
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 03abf9b70011..14fb6f9a7363 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -309,8 +309,6 @@ static int load_aout_binary(struct linux_binprm *bprm)
 		(current->mm->start_data = N_DATADDR(ex));
 	current->mm->brk = ex.a_bss +
 		(current->mm->start_brk = N_BSSADDR(ex));
-	current->mm->free_area_cache = TASK_UNMAPPED_BASE;
-	current->mm->cached_hole_size = 0;
 
 	retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
 	if (retval < 0) {
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index cccd07fa5e3a..b8e9224f0b45 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -17,6 +17,8 @@ extern unsigned long pci_mem_start;
 extern int e820_any_mapped(u64 start, u64 end, unsigned type);
 extern int e820_all_mapped(u64 start, u64 end, unsigned type);
 extern void e820_add_region(u64 start, u64 size, int type);
+extern void e820_add_limit_region(u64 start, u64 size, int type);
+extern void e820_adjust_region(u64 *start, u64 *size);
 extern void e820_print_map(char *who);
 extern int
 sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d32abeabbda5..0d5bb689649a 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -47,6 +47,7 @@ unsigned long pci_mem_start = 0xaeedbabe;
 #ifdef CONFIG_PCI
 EXPORT_SYMBOL(pci_mem_start);
 #endif
+static u64 mem_limit = ~0ULL;
 
 /*
  * This function checks if any part of the range <start,end> is mapped
@@ -108,7 +109,7 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type)
  * Add a memory region to the kernel e820 map.
  */
 static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
-					 int type)
+					 int type, bool limited)
 {
 	int x = e820x->nr_map;
 
@@ -119,6 +120,22 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
 		return;
 	}
 
+	if (limited) {
+		if (start >= mem_limit) {
+			printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
+			       (unsigned long long)start,
+			       (unsigned long long)(start + size - 1));
+			return;
+		}
+
+		if (mem_limit - start < size) {
+			printk(KERN_ERR "e820: ignoring [mem %#010llx-%#010llx]\n",
+			       (unsigned long long)mem_limit,
+			       (unsigned long long)(start + size - 1));
+			size = mem_limit - start;
+		}
+	}
+
 	e820x->map[x].addr = start;
 	e820x->map[x].size = size;
 	e820x->map[x].type = type;
@@ -127,7 +144,37 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
 
 void __init e820_add_region(u64 start, u64 size, int type)
 {
-	__e820_add_region(&e820, start, size, type);
+	__e820_add_region(&e820, start, size, type, false);
+}
+
+/*
+ * do_add_efi_memmap() calls this function().
+ *
+ * Note: BOOT_SERVICES_{CODE,DATA} regions on some efi machines are marked
+ * as E820_RAM, and they are needed to be mapped. Please use e820_add_region()
+ * to add BOOT_SERVICES_{CODE,DATA} regions.
+ */
+void __init e820_add_limit_region(u64 start, u64 size, int type)
+{
+	/*
+	 * efi_init() is called after finish_e820_parsing(), so we should
+	 * check whether [start, start + size) contains address above
+	 * mem_limit if the type is E820_RAM.
+	 */
+	__e820_add_region(&e820, start, size, type, type == E820_RAM);
+}
+
+void __init e820_adjust_region(u64 *start, u64 *size)
+{
+	if (*start >= mem_limit) {
+		*size = 0;
+		return;
+	}
+
+	if (mem_limit - *start < *size)
+		*size = mem_limit - *start;
+
+	return;
 }
 
 static void __init e820_print_type(u32 type)
@@ -455,8 +502,9 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
 
 		/* new range is totally covered? */
 		if (ei->addr < start && ei_end > end) {
-			__e820_add_region(e820x, start, size, new_type);
-			__e820_add_region(e820x, end, ei_end - end, ei->type);
+			__e820_add_region(e820x, start, size, new_type, false);
+			__e820_add_region(e820x, end, ei_end - end, ei->type,
+					  false);
 			ei->size = start - ei->addr;
 			real_updated_size += size;
 			continue;
@@ -469,7 +517,7 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
 			continue;
 
 		__e820_add_region(e820x, final_start, final_end - final_start,
-				  new_type);
+				  new_type, false);
 
 		real_updated_size += final_end - final_start;
 
@@ -809,7 +857,7 @@ static int userdef __initdata;
 /* "mem=nopentium" disables the 4MB page tables. */
 static int __init parse_memopt(char *p)
 {
-	u64 mem_size;
+	char *oldp;
 
 	if (!p)
 		return -EINVAL;
@@ -825,11 +873,11 @@ static int __init parse_memopt(char *p)
 	}
 
 	userdef = 1;
-	mem_size = memparse(p, &p);
+	oldp = p;
+	mem_limit = memparse(p, &p);
 	/* don't remove all of memory when handling "mem={invalid}" param */
-	if (mem_size == 0)
+	if (mem_limit == 0 || p == oldp)
 		return -EINVAL;
-	e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1);
 
 	return 0;
 }
@@ -895,6 +943,12 @@ early_param("memmap", parse_memmap_opt);
 
 void __init finish_e820_parsing(void)
 {
+	if (mem_limit != ~0ULL) {
+		userdef = 1;
+		e820_remove_range(mem_limit, ULLONG_MAX - mem_limit,
+				  E820_RAM, 1);
+	}
+
 	if (userdef) {
 		u32 nr = e820.nr_map;
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index e124554598ee..3f06e6149981 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -652,7 +652,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
-	struct hlist_node *node, *tmp;
+	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 	kprobe_opcode_t *correct_ret_addr = NULL;
@@ -682,7 +682,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	 *	 will be the real return address, and all the rest will
 	 *	 point to kretprobe_trampoline.
 	 */
-	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
@@ -701,7 +701,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
 	correct_ret_addr = ri->ret_addr;
-	hlist_for_each_entry_safe(ri, node, tmp, head, hlist) {
+	hlist_for_each_entry_safe(ri, tmp, head, hlist) {
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
@@ -728,7 +728,7 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
-	hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) {
+	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
 	}
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4ed3edbe06bd..956ca358108a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1644,13 +1644,13 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list);
 
-#define for_each_gfn_sp(kvm, sp, gfn, pos)				\
-  hlist_for_each_entry(sp, pos,						\
+#define for_each_gfn_sp(kvm, sp, gfn)					\
+  hlist_for_each_entry(sp,						\
    &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link)	\
 	if ((sp)->gfn != (gfn)) {} else
 
-#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn, pos)		\
-  hlist_for_each_entry(sp, pos,						\
+#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn)			\
+  hlist_for_each_entry(sp,						\
    &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link)	\
 		if ((sp)->gfn != (gfn) || (sp)->role.direct ||		\
 			(sp)->role.invalid) {} else
@@ -1706,11 +1706,10 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 static void kvm_sync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
 {
 	struct kvm_mmu_page *s;
-	struct hlist_node *node;
 	LIST_HEAD(invalid_list);
 	bool flush = false;
 
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
 		if (!s->unsync)
 			continue;
 
@@ -1848,7 +1847,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	union kvm_mmu_page_role role;
 	unsigned quadrant;
 	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
 	bool need_sync = false;
 
 	role = vcpu->arch.mmu.base_role;
@@ -1863,7 +1861,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
 		role.quadrant = quadrant;
 	}
-	for_each_gfn_sp(vcpu->kvm, sp, gfn, node) {
+	for_each_gfn_sp(vcpu->kvm, sp, gfn) {
 		if (!need_sync && sp->unsync)
 			need_sync = true;
 
@@ -2151,14 +2149,13 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
 	LIST_HEAD(invalid_list);
 	int r;
 
 	pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
 	r = 0;
 	spin_lock(&kvm->mmu_lock);
-	for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
+	for_each_gfn_indirect_valid_sp(kvm, sp, gfn) {
 		pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
 			 sp->role.word);
 		r = 1;
@@ -2288,9 +2285,8 @@ static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 static void kvm_unsync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
 {
 	struct kvm_mmu_page *s;
-	struct hlist_node *node;
 
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
 		if (s->unsync)
 			continue;
 		WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
@@ -2302,10 +2298,9 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 				  bool can_unsync)
 {
 	struct kvm_mmu_page *s;
-	struct hlist_node *node;
 	bool need_unsync = false;
 
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
 		if (!can_unsync)
 			return 1;
 
@@ -3933,7 +3928,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	union kvm_mmu_page_role mask = { .word = 0 };
 	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
@@ -3964,7 +3958,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
 	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (detect_write_misaligned(sp, gpa, bytes) ||
 		      detect_write_flooding(sp)) {
 			zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index fb674fd3fc22..2b97525246d4 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -939,14 +939,8 @@ spurious_fault(unsigned long error_code, unsigned long address)
 	if (pmd_large(*pmd))
 		return spurious_fault_check(error_code, (pte_t *) pmd);
 
-	/*
-	 * Note: don't use pte_present() here, since it returns true
-	 * if the _PAGE_PROTNONE bit is set.  However, this aliases the
-	 * _PAGE_GLOBAL bit, which for kernel pages give false positives
-	 * when CONFIG_DEBUG_PAGEALLOC is used.
-	 */
 	pte = pte_offset_kernel(pmd, address);
-	if (!(pte_flags(*pte) & _PAGE_PRESENT))
+	if (!pte_present(*pte))
 		return 0;
 
 	ret = spurious_fault_check(error_code, pte);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 845df6835f9f..62c29a5bfe26 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -115,10 +115,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mmap_legacy_base();
 		mm->get_unmapped_area = arch_get_unmapped_area;
-		mm->unmap_area = arch_unmap_area;
 	} else {
 		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-		mm->unmap_area = arch_unmap_area_topdown;
 	}
 }
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index dfd30259eb89..ff3633c794c6 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -97,8 +97,7 @@ void numa_set_node(int cpu, int node)
 #endif
 	per_cpu(x86_cpu_to_node_map, cpu) = node;
 
-	if (node != NUMA_NO_NODE)
-		set_cpu_numa_node(cpu, node);
+	set_cpu_numa_node(cpu, node);
 }
 
 void numa_clear_node(int cpu)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index ca1f1c2bb7be..091934e1d0d9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -473,6 +473,19 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
 
 	/*
+	 * Set the PSE and GLOBAL flags only if the PRESENT flag is
+	 * set otherwise pmd_present/pmd_huge will return true even on
+	 * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
+	 * for the ancient hardware that doesn't support it.
+	 */
+	if (pgprot_val(new_prot) & _PAGE_PRESENT)
+		pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
+	else
+		pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
+
+	new_prot = canon_pgprot(new_prot);
+
+	/*
 	 * old_pte points to the large page base address. So we need
 	 * to add the offset of the virtual address:
 	 */
@@ -517,7 +530,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 		 * The address is aligned and the number of pages
 		 * covers the full page.
 		 */
-		new_pte = pfn_pte(pte_pfn(old_pte), canon_pgprot(new_prot));
+		new_pte = pfn_pte(pte_pfn(old_pte), new_prot);
 		__set_pmd_pte(kpte, address, new_pte);
 		cpa->flags |= CPA_FLUSHTLB;
 		do_split = 0;
@@ -561,16 +574,35 @@ int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase)
 #ifdef CONFIG_X86_64
 	if (level == PG_LEVEL_1G) {
 		pfninc = PMD_PAGE_SIZE >> PAGE_SHIFT;
-		pgprot_val(ref_prot) |= _PAGE_PSE;
+		/*
+		 * Set the PSE flags only if the PRESENT flag is set
+		 * otherwise pmd_present/pmd_huge will return true
+		 * even on a non present pmd.
+		 */
+		if (pgprot_val(ref_prot) & _PAGE_PRESENT)
+			pgprot_val(ref_prot) |= _PAGE_PSE;
+		else
+			pgprot_val(ref_prot) &= ~_PAGE_PSE;
 	}
 #endif
 
 	/*
+	 * Set the GLOBAL flags only if the PRESENT flag is set
+	 * otherwise pmd/pte_present will return true even on a non
+	 * present pmd/pte. The canon_pgprot will clear _PAGE_GLOBAL
+	 * for the ancient hardware that doesn't support it.
+	 */
+	if (pgprot_val(ref_prot) & _PAGE_PRESENT)
+		pgprot_val(ref_prot) |= _PAGE_GLOBAL;
+	else
+		pgprot_val(ref_prot) &= ~_PAGE_GLOBAL;
+
+	/*
 	 * Get the target pfn from the original entry:
 	 */
 	pfn = pte_pfn(*kpte);
 	for (i = 0; i < PTRS_PER_PTE; i++, pfn += pfninc)
-		set_pte(&pbase[i], pfn_pte(pfn, ref_prot));
+		set_pte(&pbase[i], pfn_pte(pfn, canon_pgprot(ref_prot)));
 
 	if (pfn_range_is_mapped(PFN_DOWN(__pa(address)),
 				PFN_DOWN(__pa(address)) + 1))
@@ -685,6 +717,18 @@ repeat:
 		new_prot = static_protections(new_prot, address, pfn);
 
 		/*
+		 * Set the GLOBAL flags only if the PRESENT flag is
+		 * set otherwise pte_present will return true even on
+		 * a non present pte. The canon_pgprot will clear
+		 * _PAGE_GLOBAL for the ancient hardware that doesn't
+		 * support it.
+		 */
+		if (pgprot_val(new_prot) & _PAGE_PRESENT)
+			pgprot_val(new_prot) |= _PAGE_GLOBAL;
+		else
+			pgprot_val(new_prot) &= ~_PAGE_GLOBAL;
+
+		/*
 		 * We need to keep the pfn from the existing PTE,
 		 * after all we're only going to change it's attributes
 		 * not the memory it points to
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 70b2a3a305d6..34464b6c0077 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -320,10 +320,17 @@ static void __init do_add_efi_memmap(void)
 		int e820_type;
 
 		switch (md->type) {
-		case EFI_LOADER_CODE:
-		case EFI_LOADER_DATA:
 		case EFI_BOOT_SERVICES_CODE:
 		case EFI_BOOT_SERVICES_DATA:
+			/* EFI_BOOT_SERVICES_{CODE,DATA} needs to be mapped */
+			if (md->attribute & EFI_MEMORY_WB)
+				e820_type = E820_RAM;
+			else
+				e820_type = E820_RESERVED;
+			e820_add_region(start, size, e820_type);
+			continue;
+		case EFI_LOADER_CODE:
+		case EFI_LOADER_DATA:
 		case EFI_CONVENTIONAL_MEMORY:
 			if (md->attribute & EFI_MEMORY_WB)
 				e820_type = E820_RAM;
@@ -348,7 +355,7 @@ static void __init do_add_efi_memmap(void)
 			e820_type = E820_RESERVED;
 			break;
 		}
-		e820_add_region(start, size, e820_type);
+		e820_add_limit_region(start, size, e820_type);
 	}
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
 }
@@ -455,6 +462,8 @@ void __init efi_free_boot_services(void)
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
+		e820_adjust_region(&start, &size);
+
 		/* Could not reserve boot area */
 		if (!size)
 			continue;