24 files changed, 94 insertions, 88 deletions

diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 2e49748b27da..234f1d859cea 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -172,13 +172,6 @@ static inline int is_compat_task(void)
         return is_32bit_task();
 }
 
-#else
-
-static inline int is_compat_task(void)
-{
-        return 0;
-}
-
 #endif
 
 static inline void __user *arch_compat_alloc_user_space(long len)
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 4261aa799774..e795933eb2cb 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -29,7 +29,6 @@
 #include <asm/irq.h>
 #include <asm/timer.h>
 #include <asm/nmi.h>
-#include <asm/compat.h>
 #include <asm/smp.h>
 #include "entry.h"
 
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 9d82ed4bcb27..61f95489d70c 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -20,8 +20,8 @@
 #include <linux/regset.h>
 #include <linux/tracehook.h>
 #include <linux/seccomp.h>
+#include <linux/compat.h>
 #include <trace/syscall.h>
-#include <asm/compat.h>
 #include <asm/segment.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 354de0763eff..3b2efc81f34e 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -46,6 +46,7 @@
 #include <linux/kexec.h>
 #include <linux/crash_dump.h>
 #include <linux/memory.h>
+#include <linux/compat.h>
 
 #include <asm/ipl.h>
 #include <asm/uaccess.h>
@@ -59,7 +60,6 @@
 #include <asm/ptrace.h>
 #include <asm/sections.h>
 #include <asm/ebcdic.h>
-#include <asm/compat.h>
 #include <asm/kvm_virtio.h>
 #include <asm/diag.h>
 
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index a8ba840294ff..2d421d90fada 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -30,7 +30,6 @@
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
 #include <asm/lowcore.h>
-#include <asm/compat.h>
 #include "entry.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 354dd39073ef..e8fcd928dc78 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -36,7 +36,6 @@
 #include <asm/pgtable.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
-#include <asm/compat.h>
 #include "../kernel/entry.h"
 
 #ifndef CONFIG_64BIT
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index f09c74881b7e..a0155c02e324 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -29,8 +29,8 @@
 #include <linux/mman.h>
 #include <linux/module.h>
 #include <linux/random.h>
+#include <linux/compat.h>
 #include <asm/pgalloc.h>
-#include <asm/compat.h>
 
 static unsigned long stack_maxrandom_size(void)
 {
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6b45e5e7a901..73d08ed98a64 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -326,8 +326,7 @@ static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb)
         l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
-                                        int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
 {
         int node;
 
@@ -725,14 +724,16 @@ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)   (&((per_cpu(ici_cpuid4_info, x))[y]))
 
 #ifdef CONFIG_SMP
-static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+
+static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index)
 {
-        struct _cpuid4_info     *this_leaf, *sibling_leaf;
-        unsigned long num_threads_sharing;
-        int index_msb, i, sibling;
+        struct _cpuid4_info *this_leaf;
+        int ret, i, sibling;
         struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-        if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
+        ret = 0;
+        if (index == 3) {
+                ret = 1;
                 for_each_cpu(i, cpu_llc_shared_mask(cpu)) {
                         if (!per_cpu(ici_cpuid4_info, i))
                                 continue;
@@ -743,8 +744,35 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
                                 set_bit(sibling, this_leaf->shared_cpu_map);
                         }
                 }
-                return;
+        } else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) {
+                ret = 1;
+                for_each_cpu(i, cpu_sibling_mask(cpu)) {
+                        if (!per_cpu(ici_cpuid4_info, i))
+                                continue;
+                        this_leaf = CPUID4_INFO_IDX(i, index);
+                        for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+                                if (!cpu_online(sibling))
+                                        continue;
+                                set_bit(sibling, this_leaf->shared_cpu_map);
+                        }
+                }
         }
+
+        return ret;
+}
+
+static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
+{
+        struct _cpuid4_info *this_leaf, *sibling_leaf;
+        unsigned long num_threads_sharing;
+        int index_msb, i;
+        struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+        if (c->x86_vendor == X86_VENDOR_AMD) {
+                if (cache_shared_amd_cpu_map_setup(cpu, index))
+                        return;
+        }
+
         this_leaf = CPUID4_INFO_IDX(cpu, index);
         num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 786e76a86322..e4eeaaf58a47 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -528,6 +528,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
         sprintf(name, "threshold_bank%i", bank);
 
+#ifdef CONFIG_SMP
         if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {   /* symlink */
                 i = cpumask_first(cpu_llc_shared_mask(cpu));
 
@@ -553,6 +554,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
                 goto out;
         }
+#endif
 
         b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL);
         if (!b) {
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 3fe8239fd8fb..1333d9851778 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1532,10 +1532,17 @@ ENTRY(nmi)
         pushq_cfi %rdx
 
         /*
+         * If %cs was not the kernel segment, then the NMI triggered in user
+         * space, which means it is definitely not nested.
+         */
+        cmpl $__KERNEL_CS, 16(%rsp)
+        jne first_nmi
+
+        /*
          * Check the special variable on the stack to see if NMIs are
          * executing.
          */
-        cmp $1, -8(%rsp)
+        cmpl $1, -8(%rsp)
         je nested_nmi
 
         /*
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index ac0417be9131..73465aab28f8 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -360,7 +360,6 @@ out:
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
-        pr_info("AMD microcode update via /dev/cpu/microcode not supported\n");
         return UCODE_ERROR;
 }
 
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 70880be26015..2617b1ed4709 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -18,12 +18,12 @@
 #include <linux/hdreg.h>        /* HDIO_GETGEO                      */
 #include <linux/bio.h>
 #include <linux/module.h>
+#include <linux/compat.h>
 #include <linux/init.h>
 
 #include <asm/debug.h>
 #include <asm/idals.h>
 #include <asm/ebcdic.h>
-#include <asm/compat.h>
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/cio.h>
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index f1a2016829fc..792c69e78fe2 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -13,6 +13,7 @@
 #define KMSG_COMPONENT "dasd"
 
 #include <linux/interrupt.h>
+#include <linux/compat.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/blkpg.h>
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index e71298158f9e..911704571b9c 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -11,6 +11,7 @@
 #include <linux/console.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/compat.h>
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/slab.h>
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 75bde6a8b7dc..89c03e6b1c0c 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>
 #include <linux/init.h>
+#include <linux/compat.h>
 #include <linux/kernel.h>
 #include <linux/miscdevice.h>
 #include <linux/slab.h>
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 0c87b0fc7714..8f9a1a384496 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/slab.h>
+#include <linux/compat.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
diff --git a/drivers/s390/scsi/zfcp_cfdc.c b/drivers/s390/scsi/zfcp_cfdc.c
index 303dde09d294..fab2c2592a97 100644
--- a/drivers/s390/scsi/zfcp_cfdc.c
+++ b/drivers/s390/scsi/zfcp_cfdc.c
@@ -11,6 +11,7 @@
 #define KMSG_COMPONENT "zfcp"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
+#include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 6ba596b07a72..e33ed1bfa113 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -370,56 +370,6 @@ TRACE_EVENT(sched_stat_runtime,
                         (unsigned long long)__entry->vruntime)
 );
 
-#ifdef CREATE_TRACE_POINTS
-static inline u64 trace_get_sleeptime(struct task_struct *tsk)
-{
-#ifdef CONFIG_SCHEDSTATS
-        u64 block, sleep;
-
-        block = tsk->se.statistics.block_start;
-        sleep = tsk->se.statistics.sleep_start;
-        tsk->se.statistics.block_start = 0;
-        tsk->se.statistics.sleep_start = 0;
-
-        return block ? block : sleep ? sleep : 0;
-#else
-        return 0;
-#endif
-}
-#endif
-
-/*
- * Tracepoint for accounting sleeptime (time the task is sleeping
- * or waiting for I/O).
- */
-TRACE_EVENT(sched_stat_sleeptime,
-
-        TP_PROTO(struct task_struct *tsk, u64 now),
-
-        TP_ARGS(tsk, now),
-
-        TP_STRUCT__entry(
-                __array( char,  comm,   TASK_COMM_LEN   )
-                __field( pid_t, pid                     )
-                __field( u64,   sleeptime               )
-        ),
-
-        TP_fast_assign(
-                memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
-                __entry->pid            = tsk->pid;
-                __entry->sleeptime = trace_get_sleeptime(tsk);
-                __entry->sleeptime = __entry->sleeptime ?
-                                now - __entry->sleeptime : 0;
-        )
-        TP_perf_assign(
-                __perf_count(__entry->sleeptime);
-        ),
-
-        TP_printk("comm=%s pid=%d sleeptime=%Lu [ns]",
-                        __entry->comm, __entry->pid,
-                        (unsigned long long)__entry->sleeptime)
-);
-
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
  * priority.
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 342d8f44e401..0119b9d467ae 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -53,7 +53,7 @@ unsigned long probe_irq_on(void)
                         if (desc->irq_data.chip->irq_set_type)
                                 desc->irq_data.chip->irq_set_type(&desc->irq_data,
                                                          IRQ_TYPE_PROBE);
-                        irq_startup(desc);
+                        irq_startup(desc, false);
                 }
                 raw_spin_unlock_irq(&desc->lock);
         }
@@ -70,7 +70,7 @@ unsigned long probe_irq_on(void)
                 raw_spin_lock_irq(&desc->lock);
                 if (!desc->action && irq_settings_can_probe(desc)) {
                         desc->istate |= IRQS_AUTODETECT | IRQS_WAITING;
-                        if (irq_startup(desc))
+                        if (irq_startup(desc, false))
                                 desc->istate |= IRQS_PENDING;
                 }
                 raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index f7c543a801d9..fb7db75ee0c8 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -157,19 +157,22 @@ static void irq_state_set_masked(struct irq_desc *desc)
         irqd_set(&desc->irq_data, IRQD_IRQ_MASKED);
 }
 
-int irq_startup(struct irq_desc *desc)
+int irq_startup(struct irq_desc *desc, bool resend)
 {
+        int ret = 0;
+
         irq_state_clr_disabled(desc);
         desc->depth = 0;
 
         if (desc->irq_data.chip->irq_startup) {
-                int ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
+                ret = desc->irq_data.chip->irq_startup(&desc->irq_data);
                 irq_state_clr_masked(desc);
-                return ret;
+        } else {
+                irq_enable(desc);
         }
-
-        irq_enable(desc);
-        return 0;
+        if (resend)
+                check_irq_resend(desc, desc->irq_data.irq);
+        return ret;
 }
 
 void irq_shutdown(struct irq_desc *desc)
@@ -330,6 +333,24 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(handle_simple_irq);
 
+/*
+ * Called unconditionally from handle_level_irq() and only for oneshot
+ * interrupts from handle_fasteoi_irq()
+ */
+static void cond_unmask_irq(struct irq_desc *desc)
+{
+        /*
+         * We need to unmask in the following cases:
+         * - Standard level irq (IRQF_ONESHOT is not set)
+         * - Oneshot irq which did not wake the thread (caused by a
+         *   spurious interrupt or a primary handler handling it
+         *   completely).
+         */
+        if (!irqd_irq_disabled(&desc->irq_data) &&
+            irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot)
+                unmask_irq(desc);
+}
+
 /**
  *      handle_level_irq - Level type irq handler
  *      @irq:   the interrupt number
@@ -362,8 +383,8 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 
         handle_irq_event(desc);
 
-        if (!irqd_irq_disabled(&desc->irq_data) && !(desc->istate & IRQS_ONESHOT))
-                unmask_irq(desc);
+        cond_unmask_irq(desc);
+
 out_unlock:
         raw_spin_unlock(&desc->lock);
 }
@@ -417,6 +438,9 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
         preflow_handler(desc);
         handle_irq_event(desc);
 
+        if (desc->istate & IRQS_ONESHOT)
+                cond_unmask_irq(desc);
+
 out_eoi:
         desc->irq_data.chip->irq_eoi(&desc->irq_data);
 out_unlock:
@@ -625,7 +649,7 @@ __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
                 irq_settings_set_noprobe(desc);
                 irq_settings_set_norequest(desc);
                 irq_settings_set_nothread(desc);
-                irq_startup(desc);
+                irq_startup(desc, true);
         }
 out:
         irq_put_desc_busunlock(desc, flags);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index b7952316016a..40378ff877e7 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -67,7 +67,7 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
-extern int irq_startup(struct irq_desc *desc);
+extern int irq_startup(struct irq_desc *desc, bool resend);
 extern void irq_shutdown(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index a9a9dbe49fea..32313c084442 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1027,7 +1027,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
                         desc->istate |= IRQS_ONESHOT;
 
                 if (irq_settings_can_autoenable(desc))
-                        irq_startup(desc);
+                        irq_startup(desc, true);
                 else
                         /* Undo nested disables: */
                         desc->depth = 1;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5255c9d2e053..b342f57879e6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1932,7 +1932,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
         local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
         finish_lock_switch(rq, prev);
-        trace_sched_stat_sleeptime(current, rq->clock);
 
         fire_sched_in_preempt_notifiers(current);
         if (mm)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7c6414fc669d..aca16b843b7e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1003,6 +1003,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
                 if (unlikely(delta > se->statistics.sleep_max))
                         se->statistics.sleep_max = delta;
 
+                se->statistics.sleep_start = 0;
                 se->statistics.sum_sleep_runtime += delta;
 
                 if (tsk) {
@@ -1019,6 +1020,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
                 if (unlikely(delta > se->statistics.block_max))
                         se->statistics.block_max = delta;
 
+                se->statistics.block_start = 0;
                 se->statistics.sum_sleep_runtime += delta;
 
                 if (tsk) {