Merge branch 'linus' into x86/ptemask

11 files changed, 104 insertions, 60 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 1d035082e78..107e492cb47 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -304,10 +304,14 @@ config ARCH_SPARSEMEM_ENABLE
 	def_bool y
 	select SPARSEMEM_VMEMMAP_ENABLE
 	select SPARSEMEM_VMEMMAP
+	select SPARSEMEM_STATIC if !64BIT
 
 config ARCH_SPARSEMEM_DEFAULT
 	def_bool y
 
+config ARCH_SELECT_MEMORY_MODEL
+       def_bool y
+
 source "mm/Kconfig"
 
 comment "I/O subsystem configuration"
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 655d52543e2..ad40729bec3 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -130,6 +130,7 @@ static void appldata_work_fn(struct work_struct *work)
 
 	P_DEBUG("  -= Work Queue =-\n");
 	i = 0;
+	get_online_cpus();
 	spin_lock(&appldata_ops_lock);
 	list_for_each(lh, &appldata_ops_list) {
 		ops = list_entry(lh, struct appldata_ops, list);
@@ -140,6 +141,7 @@ static void appldata_work_fn(struct work_struct *work)
 		}
 	}
 	spin_unlock(&appldata_ops_lock);
+	put_online_cpus();
 }
 
 /*
@@ -266,12 +268,14 @@ appldata_timer_handler(ctl_table *ctl, int write, struct file *filp,
 	len = *lenp;
 	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
 		return -EFAULT;
+	get_online_cpus();
 	spin_lock(&appldata_timer_lock);
 	if (buf[0] == '1')
 		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
 	else if (buf[0] == '0')
 		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
 	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
 out:
 	*lenp = len;
 	*ppos += len;
@@ -314,10 +318,12 @@ appldata_interval_handler(ctl_table *ctl, int write, struct file *filp,
 		return -EINVAL;
 	}
 
+	get_online_cpus();
 	spin_lock(&appldata_timer_lock);
 	appldata_interval = interval;
 	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
 	spin_unlock(&appldata_timer_lock);
+	put_online_cpus();
 
 	P_INFO("Monitoring CPU interval set to %u milliseconds.\n",
 		 interval);
@@ -556,8 +562,10 @@ static int __init appldata_init(void)
 		return -ENOMEM;
 	}
 
+	get_online_cpus();
 	for_each_online_cpu(i)
 		appldata_online_cpu(i);
+	put_online_cpus();
 
 	/* Register cpu hotplug notifier */
 	register_hotcpu_notifier(&appldata_nb);
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index aa341d0ea1e..c5cdb975d59 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.25
-# Wed Apr 30 11:07:45 2008
+# Linux kernel version: 2.6.26-rc4
+# Fri May 30 09:49:33 2008
 #
 CONFIG_SCHED_MC=y
 CONFIG_MMU=y
@@ -103,6 +103,7 @@ CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
 CONFIG_MODVERSIONS=y
@@ -173,6 +174,7 @@ CONFIG_PREEMPT=y
 # CONFIG_PREEMPT_RCU is not set
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
 CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_SELECT_MEMORY_MODEL=y
 # CONFIG_FLATMEM_MANUAL is not set
 # CONFIG_DISCONTIGMEM_MANUAL is not set
@@ -210,6 +212,7 @@ CONFIG_FORCE_MAX_ZONEORDER=9
 CONFIG_PFAULT=y
 # CONFIG_SHARED_KERNEL is not set
 # CONFIG_CMM is not set
+# CONFIG_PAGE_STATES is not set
 CONFIG_VIRT_TIMER=y
 CONFIG_VIRT_CPU_ACCOUNTING=y
 # CONFIG_APPLDATA_BASE is not set
@@ -620,6 +623,7 @@ CONFIG_S390_VMUR=m
 #
 # CONFIG_MEMSTICK is not set
 # CONFIG_NEW_LEDS is not set
+CONFIG_ACCESSIBILITY=y
 
 #
 # File systems
@@ -754,11 +758,12 @@ CONFIG_FRAME_WARN=2048
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_UNUSED_SYMBOLS is not set
 CONFIG_DEBUG_FS=y
-CONFIG_HEADERS_CHECK=y
+# CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
 # CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
 # CONFIG_DEBUG_SLAB is not set
 CONFIG_DEBUG_PREEMPT=y
 # CONFIG_DEBUG_RT_MUTEXES is not set
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index c14a336f630..d2f270c995d 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -208,7 +208,7 @@ static const unsigned char formats[][7] = {
 	[INSTR_RRF_F0FF]  = { 0xff, F_16,F_24,F_28,0,0,0 },    /* e.g. madbr */
 	[INSTR_RRF_FUFF]  = { 0xff, F_24,F_16,F_28,U4_20,0,0 },/* e.g. didbr */
 	[INSTR_RRF_RURR]  = { 0xff, R_24,R_28,R_16,U4_20,0,0 },/* e.g. .insn */
-	[INSTR_RRF_R0RR]  = { 0xff, R_24,R_28,R_16,0,0,0 },    /* e.g. idte  */
+	[INSTR_RRF_R0RR]  = { 0xff, R_24,R_16,R_28,0,0,0 },    /* e.g. idte  */
 	[INSTR_RRF_U0FF]  = { 0xff, F_24,U4_16,F_28,0,0,0 },   /* e.g. fixr  */
 	[INSTR_RRF_U0RF]  = { 0xff, R_24,U4_16,F_28,0,0,0 },   /* e.g. cfebr */
 	[INSTR_RRF_M0RR]  = { 0xff, R_24,R_28,M_16,0,0,0 },    /* e.g. sske  */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 1f4228948dc..5d4fa4b1c74 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -711,7 +711,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	memset(sf, 0, sizeof(struct stack_frame));
 	sf->gprs[9] = (unsigned long) sf;
 	cpu_lowcore->save_area[15] = (unsigned long) sf;
-	__ctl_store(cpu_lowcore->cregs_save_area[0], 0, 15);
+	__ctl_store(cpu_lowcore->cregs_save_area, 0, 15);
 	asm volatile(
 		"	stam	0,15,0(%0)"
 		: : "a" (&cpu_lowcore->access_regs_save_area) : "memory");
@@ -1089,7 +1089,7 @@ out:
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-int smp_rescan_cpus(void)
+int __ref smp_rescan_cpus(void)
 {
 	cpumask_t newcpus;
 	int cpu;
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index f639a152869..a0775e1f08d 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -20,7 +20,7 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
 	VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
 	vcpu->stat.diagnose_44++;
 	vcpu_put(vcpu);
-	schedule();
+	yield();
 	vcpu_load(vcpu);
 	return 0;
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index fcd1ed8015c..84a7fed4cd4 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -339,6 +339,11 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 	if (kvm_cpu_has_interrupt(vcpu))
 		return 0;
 
+	__set_cpu_idle(vcpu);
+	spin_lock_bh(&vcpu->arch.local_int.lock);
+	vcpu->arch.local_int.timer_due = 0;
+	spin_unlock_bh(&vcpu->arch.local_int.lock);
+
 	if (psw_interrupts_disabled(vcpu)) {
 		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
 		__unset_cpu_idle(vcpu);
@@ -366,8 +371,6 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
 no_timer:
 	spin_lock_bh(&vcpu->arch.local_int.float_int->lock);
 	spin_lock_bh(&vcpu->arch.local_int.lock);
-	__set_cpu_idle(vcpu);
-	vcpu->arch.local_int.timer_due = 0;
 	add_wait_queue(&vcpu->arch.local_int.wq, &wait);
 	while (list_empty(&vcpu->arch.local_int.list) &&
 		list_empty(&vcpu->arch.local_int.float_int->list) &&
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0ac36a649eb..6558b09ff57 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -423,6 +423,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	return -EINVAL; /* not implemented yet */
 }
 
+extern void s390_handle_mcck(void);
+
 static void __vcpu_run(struct kvm_vcpu *vcpu)
 {
 	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
@@ -430,13 +432,21 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	if (need_resched())
 		schedule();
 
+	if (test_thread_flag(TIF_MCCK_PENDING))
+		s390_handle_mcck();
+
+	kvm_s390_deliver_pending_interrupts(vcpu);
+
 	vcpu->arch.sie_block->icptcode = 0;
 	local_irq_disable();
 	kvm_guest_enter();
 	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
-	sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs);
+	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
+		VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
 	local_irq_disable();
@@ -475,7 +485,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	might_sleep();
 
 	do {
-		kvm_s390_deliver_pending_interrupts(vcpu);
 		__vcpu_run(vcpu);
 		rc = kvm_handle_sie_intercept(vcpu);
 	} while (!signal_pending(current) && !rc);
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 29f3a63806b..05598649b32 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -44,37 +44,34 @@ char  empty_zero_page[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
 
 void show_mem(void)
 {
-	int i, total = 0, reserved = 0;
-	int shared = 0, cached = 0;
+	unsigned long i, total = 0, reserved = 0;
+	unsigned long shared = 0, cached = 0;
+	unsigned long flags;
 	struct page *page;
+	pg_data_t *pgdat;
 
 	printk("Mem-info:\n");
 	show_free_areas();
-	i = max_mapnr;
-	while (i-- > 0) {
-		if (!pfn_valid(i))
-			continue;
-		page = pfn_to_page(i);
-		total++;
-		if (PageReserved(page))
-			reserved++;
-		else if (PageSwapCache(page))
-			cached++;
-		else if (page_count(page))
-			shared += page_count(page) - 1;
+	for_each_online_pgdat(pgdat) {
+		pgdat_resize_lock(pgdat, &flags);
+		for (i = 0; i < pgdat->node_spanned_pages; i++) {
+			if (!pfn_valid(pgdat->node_start_pfn + i))
+				continue;
+			page = pfn_to_page(pgdat->node_start_pfn + i);
+			total++;
+			if (PageReserved(page))
+				reserved++;
+			else if (PageSwapCache(page))
+				cached++;
+			else if (page_count(page))
+				shared += page_count(page) - 1;
+		}
+		pgdat_resize_unlock(pgdat, &flags);
 	}
-	printk("%d pages of RAM\n", total);
-	printk("%d reserved pages\n", reserved);
-	printk("%d pages shared\n", shared);
-	printk("%d pages swap cached\n", cached);
-
-	printk("%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
-	printk("%lu pages writeback\n", global_page_state(NR_WRITEBACK));
-	printk("%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
-	printk("%lu pages slab\n",
-	       global_page_state(NR_SLAB_RECLAIMABLE) +
-	       global_page_state(NR_SLAB_UNRECLAIMABLE));
-	printk("%lu pages pagetables\n", global_page_state(NR_PAGETABLE));
+	printk("%ld pages of RAM\n", total);
+	printk("%ld reserved pages\n", reserved);
+	printk("%ld pages shared\n", shared);
+	printk("%ld pages swap cached\n", cached);
 }
 
 /*
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 5c1aea97cd1..3d98ba82ea6 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -254,36 +254,46 @@ void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
 int s390_enable_sie(void)
 {
 	struct task_struct *tsk = current;
-	struct mm_struct *mm;
-	int rc;
+	struct mm_struct *mm, *old_mm;
 
-	task_lock(tsk);
-
-	rc = 0;
+	/* Do we have pgstes? if yes, we are done */
 	if (tsk->mm->context.pgstes)
-		goto unlock;
+		return 0;
 
-	rc = -EINVAL;
+	/* lets check if we are allowed to replace the mm */
+	task_lock(tsk);
 	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
-	    tsk->mm != tsk->active_mm || tsk->mm->ioctx_list)
-		goto unlock;
+	    tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) {
+		task_unlock(tsk);
+		return -EINVAL;
+	}
+	task_unlock(tsk);
 
-	tsk->mm->context.pgstes = 1;	/* dirty little tricks .. */
+	/* we copy the mm with pgstes enabled */
+	tsk->mm->context.pgstes = 1;
 	mm = dup_mm(tsk);
 	tsk->mm->context.pgstes = 0;
-
-	rc = -ENOMEM;
 	if (!mm)
-		goto unlock;
-	mmput(tsk->mm);
+		return -ENOMEM;
+
+	/* Now lets check again if somebody attached ptrace etc */
+	task_lock(tsk);
+	if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
+	    tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) {
+		mmput(mm);
+		task_unlock(tsk);
+		return -EINVAL;
+	}
+
+	/* ok, we are alone. No ptrace, no threads, etc. */
+	old_mm = tsk->mm;
 	tsk->mm = tsk->active_mm = mm;
 	preempt_disable();
 	update_mm(mm, tsk);
 	cpu_set(smp_processor_id(), mm->cpu_vm_mask);
 	preempt_enable();
-	rc = 0;
-unlock:
 	task_unlock(tsk);
-	return rc;
+	mmput(old_mm);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(s390_enable_sie);
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index ea2804808f3..e4868bfc672 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -27,12 +27,19 @@ struct memory_segment {
 
 static LIST_HEAD(mem_segs);
 
-static pud_t *vmem_pud_alloc(void)
+static void __ref *vmem_alloc_pages(unsigned int order)
+{
+	if (slab_is_available())
+		return (void *)__get_free_pages(GFP_KERNEL, order);
+	return alloc_bootmem_pages((1 << order) * PAGE_SIZE);
+}
+
+static inline pud_t *vmem_pud_alloc(void)
 {
 	pud_t *pud = NULL;
 
 #ifdef CONFIG_64BIT
-	pud = vmemmap_alloc_block(PAGE_SIZE * 4, 0);
+	pud = vmem_alloc_pages(2);
 	if (!pud)
 		return NULL;
 	clear_table((unsigned long *) pud, _REGION3_ENTRY_EMPTY, PAGE_SIZE * 4);
@@ -40,12 +47,12 @@ static pud_t *vmem_pud_alloc(void)
 	return pud;
 }
 
-static pmd_t *vmem_pmd_alloc(void)
+static inline pmd_t *vmem_pmd_alloc(void)
 {
 	pmd_t *pmd = NULL;
 
 #ifdef CONFIG_64BIT
-	pmd = vmemmap_alloc_block(PAGE_SIZE * 4, 0);
+	pmd = vmem_alloc_pages(2);
 	if (!pmd)
 		return NULL;
 	clear_table((unsigned long *) pmd, _SEGMENT_ENTRY_EMPTY, PAGE_SIZE * 4);
@@ -207,13 +214,14 @@ int __meminit vmemmap_populate(struct page *start, unsigned long nr, int node)
 		if (pte_none(*pt_dir)) {
 			unsigned long new_page;
 
-			new_page =__pa(vmemmap_alloc_block(PAGE_SIZE, 0));
+			new_page =__pa(vmem_alloc_pages(0));
 			if (!new_page)
 				goto out;
 			pte = pfn_pte(new_page >> PAGE_SHIFT, PAGE_KERNEL);
 			*pt_dir = pte;
 		}
 	}
+	memset(start, 0, nr * sizeof(struct page));
 	ret = 0;
 out:
 	flush_tlb_kernel_range(start_addr, end_addr);
@@ -228,7 +236,7 @@ static int insert_memory_segment(struct memory_segment *seg)
 {
 	struct memory_segment *tmp;
 
-	if (seg->start + seg->size >= VMEM_MAX_PHYS ||
+	if (seg->start + seg->size > VMEM_MAX_PHYS ||
 	    seg->start + seg->size < seg->start)
 		return -ERANGE;