Merge branch 'linus' into x86/uv

15 files changed, 81 insertions, 65 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 70b7645ce745..8116a3328a19 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -241,19 +241,17 @@ config PACK_STACK
           Say Y if you are unsure.
 
 config SMALL_STACK
-        bool "Use 4kb/8kb for kernel stack instead of 8kb/16kb"
-        depends on PACK_STACK && !LOCKDEP
+        bool "Use 8kb for kernel stack instead of 16kb"
+        depends on PACK_STACK && 64BIT && !LOCKDEP
         help
           If you say Y here and the compiler supports the -mkernel-backchain
-          option the kernel will use a smaller kernel stack size. For 31 bit
-          the reduced size is 4kb instead of 8kb and for 64 bit it is 8kb
-          instead of 16kb. This allows to run more thread on a system and
-          reduces the pressure on the memory management for higher order
-          page allocations.
+          option the kernel will use a smaller kernel stack size. The reduced
+          size is 8kb instead of 16kb. This allows to run more threads on a
+          system and reduces the pressure on the memory management for higher
+          order page allocations.
 
           Say N if you are unsure.
 
-
 config CHECK_STACK
         bool "Detect kernel stack overflow"
         help
@@ -384,7 +382,7 @@ config IPL
 choice
         prompt "IPL method generated into head.S"
         depends on IPL
-        default IPL_TAPE
+        default IPL_VM
         help
           Select "tape" if you want to IPL the image from a Tape.
 
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index a7f8979fb925..a06a47cdd5e0 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -424,7 +424,7 @@ out:
  */
 int appldata_register_ops(struct appldata_ops *ops)
 {
-        if ((ops->size > APPLDATA_MAX_REC_SIZE) || (ops->size < 0))
+        if (ops->size > APPLDATA_MAX_REC_SIZE)
                 return -EINVAL;
 
         ops->ctl_table = kzalloc(4 * sizeof(struct ctl_table), GFP_KERNEL);
diff --git a/arch/s390/include/asm/kvm_virtio.h b/arch/s390/include/asm/kvm_virtio.h
index 146100224def..c13568b9351c 100644
--- a/arch/s390/include/asm/kvm_virtio.h
+++ b/arch/s390/include/asm/kvm_virtio.h
@@ -52,7 +52,7 @@ struct kvm_vqconfig {
 
 #ifdef __KERNEL__
 /* early virtio console setup */
-#ifdef CONFIG_VIRTIO_CONSOLE
+#ifdef CONFIG_S390_GUEST
 extern void s390_virtio_console_init(void);
 #else
 static inline void s390_virtio_console_init(void)
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index 5dd5e7b3476f..d2b4ff831477 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -7,7 +7,8 @@ typedef struct {
         unsigned long asce_bits;
         unsigned long asce_limit;
         int noexec;
-        int pgstes;
+        int has_pgste;   /* The mmu context has extended page tables */
+        int alloc_pgste; /* cloned contexts will have extended page tables */
 } mm_context_t;
 
 #endif
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 4c2fbf48c9c4..28ec870655af 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -20,12 +20,25 @@ static inline int init_new_context(struct task_struct *tsk,
 #ifdef CONFIG_64BIT
         mm->context.asce_bits |= _ASCE_TYPE_REGION3;
 #endif
-        if (current->mm->context.pgstes) {
+        if (current->mm->context.alloc_pgste) {
+                /*
+                 * alloc_pgste indicates, that any NEW context will be created
+                 * with extended page tables. The old context is unchanged. The
+                 * page table allocation and the page table operations will
+                 * look at has_pgste to distinguish normal and extended page
+                 * tables. The only way to create extended page tables is to
+                 * set alloc_pgste and then create a new context (e.g. dup_mm).
+                 * The page table allocation is called after init_new_context
+                 * and if has_pgste is set, it will create extended page
+                 * tables.
+                 */
                 mm->context.noexec = 0;
-                mm->context.pgstes = 1;
+                mm->context.has_pgste = 1;
+                mm->context.alloc_pgste = 1;
         } else {
                 mm->context.noexec = s390_noexec;
-                mm->context.pgstes = 0;
+                mm->context.has_pgste = 0;
+                mm->context.alloc_pgste = 0;
         }
         mm->context.asce_limit = STACK_TOP_MAX;
         crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 1a928f84afd6..7fc76133b3e4 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -679,7 +679,7 @@ static inline void pmd_clear(pmd_t *pmd)
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-        if (mm->context.pgstes)
+        if (mm->context.has_pgste)
                 ptep_rcp_copy(ptep);
         pte_val(*ptep) = _PAGE_TYPE_EMPTY;
         if (mm->context.noexec)
@@ -763,7 +763,7 @@ static inline int kvm_s390_test_and_clear_page_dirty(struct mm_struct *mm,
         struct page *page;
         unsigned int skey;
 
-        if (!mm->context.pgstes)
+        if (!mm->context.has_pgste)
                 return -EINVAL;
         rcp_lock(ptep);
         pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
@@ -794,7 +794,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
         int young;
         unsigned long *pgste;
 
-        if (!vma->vm_mm->context.pgstes)
+        if (!vma->vm_mm->context.has_pgste)
                 return 0;
         physpage = pte_val(*ptep) & PAGE_MASK;
         pgste = (unsigned long *) (ptep + PTRS_PER_PTE);
@@ -844,7 +844,7 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 static inline void ptep_invalidate(struct mm_struct *mm,
                                    unsigned long address, pte_t *ptep)
 {
-        if (mm->context.pgstes) {
+        if (mm->context.has_pgste) {
                 rcp_lock(ptep);
                 __ptep_ipte(address, ptep);
                 ptep_rcp_copy(ptep);
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index de3fad60c682..c1eaf9604da7 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -15,13 +15,8 @@
  * Size of kernel stack for each process
  */
 #ifndef __s390x__
-#ifndef __SMALL_STACK
 #define THREAD_ORDER 1
 #define ASYNC_ORDER  1
-#else
-#define THREAD_ORDER 0
-#define ASYNC_ORDER  0
-#endif
 #else /* __s390x__ */
 #ifndef __SMALL_STACK
 #define THREAD_ORDER 2
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index ed500ef799b7..08844fc24a2e 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -61,22 +61,25 @@ STACK_SIZE  = 1 << STACK_SHIFT
 
 #ifdef CONFIG_TRACE_IRQFLAGS
         .macro  TRACE_IRQS_ON
-        l       %r1,BASED(.Ltrace_irq_on)
+        basr    %r2,%r0
+        l       %r1,BASED(.Ltrace_irq_on_caller)
         basr    %r14,%r1
         .endm
 
         .macro  TRACE_IRQS_OFF
-        l       %r1,BASED(.Ltrace_irq_off)
+        basr    %r2,%r0
+        l       %r1,BASED(.Ltrace_irq_off_caller)
         basr    %r14,%r1
         .endm
 
         .macro  TRACE_IRQS_CHECK
+        basr    %r2,%r0
         tm      SP_PSW(%r15),0x03       # irqs enabled?
         jz      0f
-        l       %r1,BASED(.Ltrace_irq_on)
+        l       %r1,BASED(.Ltrace_irq_on_caller)
         basr    %r14,%r1
         j       1f
-0:      l       %r1,BASED(.Ltrace_irq_off)
+0:      l       %r1,BASED(.Ltrace_irq_off_caller)
         basr    %r14,%r1
 1:
         .endm
@@ -1113,9 +1116,12 @@ cleanup_io_leave_insn:
 .Lschedtail:    .long   schedule_tail
 .Lsysc_table:   .long   sys_call_table
 #ifdef CONFIG_TRACE_IRQFLAGS
-.Ltrace_irq_on: .long   trace_hardirqs_on
-.Ltrace_irq_off:
-                .long   trace_hardirqs_off
+.Ltrace_irq_on_caller:
+                .long   trace_hardirqs_on_caller
+.Ltrace_irq_off_caller:
+                .long   trace_hardirqs_off_caller
+#endif
+#ifdef CONFIG_LOCKDEP
 .Llockdep_sys_exit:
                 .long   lockdep_sys_exit
 #endif
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index d7ce150453f2..41aca06682aa 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -61,19 +61,22 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 
 #ifdef CONFIG_TRACE_IRQFLAGS
         .macro  TRACE_IRQS_ON
-         brasl  %r14,trace_hardirqs_on
+         basr   %r2,%r0
+         brasl  %r14,trace_hardirqs_on_caller
         .endm
 
         .macro  TRACE_IRQS_OFF
-         brasl  %r14,trace_hardirqs_off
+         basr   %r2,%r0
+         brasl  %r14,trace_hardirqs_off_caller
         .endm
 
         .macro TRACE_IRQS_CHECK
+        basr    %r2,%r0
         tm      SP_PSW(%r15),0x03       # irqs enabled?
         jz      0f
-        brasl   %r14,trace_hardirqs_on
+        brasl   %r14,trace_hardirqs_on_caller
         j       1f
-0:      brasl   %r14,trace_hardirqs_off
+0:      brasl   %r14,trace_hardirqs_off_caller
 1:
         .endm
 #else
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 3e2c05cb6a87..04f8c67a6101 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -136,9 +136,12 @@ static void default_idle(void)
                 return;
         }
         trace_hardirqs_on();
+        /* Don't trace preempt off for idle. */
+        stop_critical_timings();
         /* Wait for external, I/O or machine check interrupt. */
         __load_psw_mask(psw_kernel_bits | PSW_MASK_WAIT |
                         PSW_MASK_IO | PSW_MASK_EXT);
+        start_critical_timings();
 }
 
 void cpu_idle(void)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 62122bad1e33..400b040df7fa 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -604,13 +604,13 @@ setup_memory(void)
                 if (memory_chunk[i].type != CHUNK_READ_WRITE)
                         continue;
                 start_chunk = PFN_DOWN(memory_chunk[i].addr);
-                end_chunk = start_chunk + PFN_DOWN(memory_chunk[i].size) - 1;
+                end_chunk = start_chunk + PFN_DOWN(memory_chunk[i].size);
                 end_chunk = min(end_chunk, end_pfn);
                 if (start_chunk >= end_chunk)
                         continue;
                 add_active_range(0, start_chunk, end_chunk);
                 pfn = max(start_chunk, start_pfn);
-                for (; pfn <= end_chunk; pfn++)
+                for (; pfn < end_chunk; pfn++)
                         page_set_storage_key(PFN_PHYS(pfn), PAGE_DEFAULT_KEY);
         }
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 9e8b1f9b8f4d..b5595688a477 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -1119,9 +1119,7 @@ out:
         return rc;
 }
 
-static ssize_t __ref rescan_store(struct sys_device *dev,
-                                  struct sysdev_attribute *attr,
-                                  const char *buf,
+static ssize_t __ref rescan_store(struct sysdev_class *class, const char *buf,
                                   size_t count)
 {
         int rc;
@@ -1129,12 +1127,10 @@ static ssize_t __ref rescan_store(struct sys_device *dev,
         rc = smp_rescan_cpus();
         return rc ? rc : count;
 }
-static SYSDEV_ATTR(rescan, 0200, NULL, rescan_store);
+static SYSDEV_CLASS_ATTR(rescan, 0200, NULL, rescan_store);
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static ssize_t dispatching_show(struct sys_device *dev,
-                                struct sysdev_attribute *attr,
-                                char *buf)
+static ssize_t dispatching_show(struct sysdev_class *class, char *buf)
 {
         ssize_t count;
 
@@ -1144,9 +1140,8 @@ static ssize_t dispatching_show(struct sys_device *dev,
         return count;
 }
 
-static ssize_t dispatching_store(struct sys_device *dev,
-                                 struct sysdev_attribute *attr,
-                                 const char *buf, size_t count)
+static ssize_t dispatching_store(struct sysdev_class *dev, const char *buf,
+                                 size_t count)
 {
         int val, rc;
         char delim;
@@ -1168,7 +1163,8 @@ out:
         put_online_cpus();
         return rc ? rc : count;
 }
-static SYSDEV_ATTR(dispatching, 0644, dispatching_show, dispatching_store);
+static SYSDEV_CLASS_ATTR(dispatching, 0644, dispatching_show,
+                         dispatching_store);
 
 static int __init topology_init(void)
 {
@@ -1178,13 +1174,11 @@ static int __init topology_init(void)
         register_cpu_notifier(&smp_cpu_nb);
 
 #ifdef CONFIG_HOTPLUG_CPU
-        rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
-                               &attr_rescan.attr);
+        rc = sysdev_class_create_file(&cpu_sysdev_class, &attr_rescan);
         if (rc)
                 return rc;
 #endif
-        rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
-                               &attr_dispatching.attr);
+        rc = sysdev_class_create_file(&cpu_sysdev_class, &attr_dispatching);
         if (rc)
                 return rc;
         for_each_present_cpu(cpu) {
diff --git a/arch/s390/kernel/sys_s390.c b/arch/s390/kernel/sys_s390.c
index 5fdb799062b7..4fe952e557ac 100644
--- a/arch/s390/kernel/sys_s390.c
+++ b/arch/s390/kernel/sys_s390.c
@@ -198,7 +198,7 @@ asmlinkage long s390x_newuname(struct new_utsname __user *name)
 {
         int ret = sys_newuname(name);
 
-        if (current->personality == PER_LINUX32 && !ret) {
+        if (personality(current->personality) == PER_LINUX32 && !ret) {
                 ret = copy_to_user(name->machine, "s390\0\0\0\0", 8);
                 if (ret) ret = -EFAULT;
         }
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 632b13e10053..a947899dcba1 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -65,18 +65,21 @@ static int machine_has_topology_irq;
 static struct timer_list topology_timer;
 static void set_topology_timer(void);
 static DECLARE_WORK(topology_work, topology_work_fn);
+/* topology_lock protects the core linked list */
+static DEFINE_SPINLOCK(topology_lock);
 
 cpumask_t cpu_core_map[NR_CPUS];
 
 cpumask_t cpu_coregroup_map(unsigned int cpu)
 {
         struct core_info *core = &core_info;
+        unsigned long flags;
         cpumask_t mask;
 
         cpus_clear(mask);
         if (!machine_has_topology)
                 return cpu_present_map;
-        mutex_lock(&smp_cpu_state_mutex);
+        spin_lock_irqsave(&topology_lock, flags);
         while (core) {
                 if (cpu_isset(cpu, core->mask)) {
                         mask = core->mask;
@@ -84,7 +87,7 @@ cpumask_t cpu_coregroup_map(unsigned int cpu)
                 }
                 core = core->next;
         }
-        mutex_unlock(&smp_cpu_state_mutex);
+        spin_unlock_irqrestore(&topology_lock, flags);
         if (cpus_empty(mask))
                 mask = cpumask_of_cpu(cpu);
         return mask;
@@ -133,7 +136,7 @@ static void tl_to_cores(struct tl_info *info)
         union tl_entry *tle, *end;
         struct core_info *core = &core_info;
 
-        mutex_lock(&smp_cpu_state_mutex);
+        spin_lock_irq(&topology_lock);
         clear_cores();
         tle = info->tle;
         end = (union tl_entry *)((unsigned long)info + info->length);
@@ -157,7 +160,7 @@ static void tl_to_cores(struct tl_info *info)
                 }
                 tle = next_tle(tle);
         }
-        mutex_unlock(&smp_cpu_state_mutex);
+        spin_unlock_irq(&topology_lock);
 }
 
 static void topology_update_polarization_simple(void)
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 3d98ba82ea67..ef3635b52fc0 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -169,7 +169,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
         unsigned long *table;
         unsigned long bits;
 
-        bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL;
+        bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
         spin_lock(&mm->page_table_lock);
         page = NULL;
         if (!list_empty(&mm->context.pgtable_list)) {
@@ -186,7 +186,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
                 pgtable_page_ctor(page);
                 page->flags &= ~FRAG_MASK;
                 table = (unsigned long *) page_to_phys(page);
-                if (mm->context.pgstes)
+                if (mm->context.has_pgste)
                         clear_table_pgstes(table);
                 else
                         clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
@@ -210,7 +210,7 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
         struct page *page;
         unsigned long bits;
 
-        bits = (mm->context.noexec || mm->context.pgstes) ? 3UL : 1UL;
+        bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
         bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
         page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
         spin_lock(&mm->page_table_lock);
@@ -257,7 +257,7 @@ int s390_enable_sie(void)
         struct mm_struct *mm, *old_mm;
 
         /* Do we have pgstes? if yes, we are done */
-        if (tsk->mm->context.pgstes)
+        if (tsk->mm->context.has_pgste)
                 return 0;
 
         /* lets check if we are allowed to replace the mm */
@@ -269,14 +269,14 @@ int s390_enable_sie(void)
         }
         task_unlock(tsk);
 
-        /* we copy the mm with pgstes enabled */
-        tsk->mm->context.pgstes = 1;
+        /* we copy the mm and let dup_mm create the page tables with_pgstes */
+        tsk->mm->context.alloc_pgste = 1;
         mm = dup_mm(tsk);
-        tsk->mm->context.pgstes = 0;
+        tsk->mm->context.alloc_pgste = 0;
         if (!mm)
                 return -ENOMEM;
 
-        /* Now lets check again if somebody attached ptrace etc */
+        /* Now lets check again if something happened */
         task_lock(tsk);
         if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
             tsk->mm != tsk->active_mm || tsk->mm->ioctx_list) {