Merge branch 'fixes' of git://github.com/hzhuang1/linux into fixes

* 'fixes' of git://github.com/hzhuang1/linux: (3 commits)
  ARM: pxa: fix invalid mfp pin issue
  ARM: pxa: remove duplicated registeration on pxa-gpio
  ARM: pxa: add dummy clock for pxa25x and pxa27x

Includes an update to v3.3-rc6

32 files changed, 166 insertions, 55 deletions

diff --git a/arch/arm/mach-omap2/mailbox.c b/arch/arm/mach-omap2/mailbox.c
index 415a6f1cf419..2cc1aa004b94 100644
--- a/arch/arm/mach-omap2/mailbox.c
+++ b/arch/arm/mach-omap2/mailbox.c
@@ -420,7 +420,8 @@ static void __exit omap2_mbox_exit(void)
         platform_driver_unregister(&omap2_mbox_driver);
 }
 
-module_init(omap2_mbox_init);
+/* must be ready before omap3isp is probed */
+subsys_initcall(omap2_mbox_init);
 module_exit(omap2_mbox_exit);
 
 MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/mach-pxa/generic.h b/arch/arm/mach-pxa/generic.h
index 0d729e6619df..42d5cca66257 100644
--- a/arch/arm/mach-pxa/generic.h
+++ b/arch/arm/mach-pxa/generic.h
@@ -49,7 +49,6 @@ extern unsigned pxa3xx_get_clk_frequency_khz(int);
 #endif
 
 extern struct syscore_ops pxa_irq_syscore_ops;
-extern struct syscore_ops pxa_gpio_syscore_ops;
 extern struct syscore_ops pxa2xx_mfp_syscore_ops;
 extern struct syscore_ops pxa3xx_mfp_syscore_ops;
 
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index f14775536b83..29b62afc6f7c 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -226,6 +226,12 @@ static void __init pxa25x_mfp_init(void)
 {
         int i;
 
+        /* running before pxa_gpio_probe() */
+#ifdef CONFIG_CPU_PXA26x
+        pxa_last_gpio = 89;
+#else
+        pxa_last_gpio = 84;
+#endif
         for (i = 0; i <= pxa_last_gpio; i++)
                 gpio_desc[i].valid = 1;
 
@@ -295,6 +301,7 @@ static void __init pxa27x_mfp_init(void)
 {
         int i, gpio;
 
+        pxa_last_gpio = 120;    /* running before pxa_gpio_probe() */
         for (i = 0; i <= pxa_last_gpio; i++) {
                 /* skip GPIO2, 5, 6, 7, 8, they are not
                  * valid pins allow configuration
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index 00d6eacab8e4..3352b37b60cf 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -208,6 +208,7 @@ static struct clk_lookup pxa25x_clkregs[] = {
         INIT_CLKREG(&clk_pxa25x_gpio11, NULL, "GPIO11_CLK"),
         INIT_CLKREG(&clk_pxa25x_gpio12, NULL, "GPIO12_CLK"),
         INIT_CLKREG(&clk_pxa25x_mem, "pxa2xx-pcmcia", NULL),
+        INIT_CLKREG(&clk_dummy, "pxa-gpio", NULL),
 };
 
 static struct clk_lookup pxa25x_hwuart_clkreg =
@@ -367,7 +368,6 @@ static int __init pxa25x_init(void)
 
                 register_syscore_ops(&pxa_irq_syscore_ops);
                 register_syscore_ops(&pxa2xx_mfp_syscore_ops);
-                register_syscore_ops(&pxa_gpio_syscore_ops);
                 register_syscore_ops(&pxa2xx_clock_syscore_ops);
 
                 ret = platform_add_devices(pxa25x_devices,
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index c1673b3441d4..6bce78edce7a 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -229,6 +229,7 @@ static struct clk_lookup pxa27x_clkregs[] = {
         INIT_CLKREG(&clk_pxa27x_im, NULL, "IMCLK"),
         INIT_CLKREG(&clk_pxa27x_memc, NULL, "MEMCLK"),
         INIT_CLKREG(&clk_pxa27x_mem, "pxa2xx-pcmcia", NULL),
+        INIT_CLKREG(&clk_dummy, "pxa-gpio", NULL),
 };
 
 #ifdef CONFIG_PM
@@ -455,7 +456,6 @@ static int __init pxa27x_init(void)
 
                 register_syscore_ops(&pxa_irq_syscore_ops);
                 register_syscore_ops(&pxa2xx_mfp_syscore_ops);
-                register_syscore_ops(&pxa_gpio_syscore_ops);
                 register_syscore_ops(&pxa2xx_clock_syscore_ops);
 
                 ret = platform_add_devices(devices, ARRAY_SIZE(devices));
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 4f402afa6609..3918a672238e 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -462,7 +462,6 @@ static int __init pxa3xx_init(void)
 
                 register_syscore_ops(&pxa_irq_syscore_ops);
                 register_syscore_ops(&pxa3xx_mfp_syscore_ops);
-                register_syscore_ops(&pxa_gpio_syscore_ops);
                 register_syscore_ops(&pxa3xx_clock_syscore_ops);
 
                 ret = platform_add_devices(devices, ARRAY_SIZE(devices));
diff --git a/arch/arm/mach-pxa/pxa95x.c b/arch/arm/mach-pxa/pxa95x.c
index d082a583df78..5ce434b95e87 100644
--- a/arch/arm/mach-pxa/pxa95x.c
+++ b/arch/arm/mach-pxa/pxa95x.c
@@ -283,7 +283,6 @@ static int __init pxa95x_init(void)
                         return ret;
 
                 register_syscore_ops(&pxa_irq_syscore_ops);
-                register_syscore_ops(&pxa_gpio_syscore_ops);
                 register_syscore_ops(&pxa3xx_clock_syscore_ops);
 
                 ret = platform_add_devices(devices, ARRAY_SIZE(devices));
diff --git a/arch/openrisc/include/asm/ptrace.h b/arch/openrisc/include/asm/ptrace.h
index 054537c5f9c9..e612ce4512c7 100644
--- a/arch/openrisc/include/asm/ptrace.h
+++ b/arch/openrisc/include/asm/ptrace.h
@@ -77,7 +77,6 @@ struct pt_regs {
         long  syscallno;        /* Syscall number (used by strace) */
         long dummy;             /* Cheap alignment fix */
 };
-#endif /* __ASSEMBLY__ */
 
 /* TODO: Rename this to REDZONE because that's what it is */
 #define STACK_FRAME_OVERHEAD  128  /* size of minimum stack frame */
@@ -87,6 +86,13 @@ struct pt_regs {
 #define user_stack_pointer(regs)        ((unsigned long)(regs)->sp)
 #define profile_pc(regs)                instruction_pointer(regs)
 
+static inline long regs_return_value(struct pt_regs *regs)
+{
+        return regs->gpr[11];
+}
+
+#endif /* __ASSEMBLY__ */
+
 /*
  * Offsets used by 'ptrace' system call interface.
  */
diff --git a/arch/openrisc/kernel/init_task.c b/arch/openrisc/kernel/init_task.c
index 45744a384927..ca534082d5f3 100644
--- a/arch/openrisc/kernel/init_task.c
+++ b/arch/openrisc/kernel/init_task.c
@@ -17,6 +17,7 @@
 
 #include <linux/init_task.h>
 #include <linux/mqueue.h>
+#include <linux/export.h>
 
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c
index 59b302338331..4bfead220956 100644
--- a/arch/openrisc/kernel/irq.c
+++ b/arch/openrisc/kernel/irq.c
@@ -23,6 +23,7 @@
 #include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/kernel_stat.h>
+#include <linux/export.h>
 
 #include <linux/irqflags.h>
 
diff --git a/arch/openrisc/kernel/ptrace.c b/arch/openrisc/kernel/ptrace.c
index 656b94beab89..7259047d5f9d 100644
--- a/arch/openrisc/kernel/ptrace.c
+++ b/arch/openrisc/kernel/ptrace.c
@@ -188,11 +188,9 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
                  */
                 ret = -1L;
 
-        /* Are these regs right??? */
-        if (unlikely(current->audit_context))
-                audit_syscall_entry(audit_arch(), regs->syscallno,
-                                    regs->gpr[3], regs->gpr[4],
-                                    regs->gpr[5], regs->gpr[6]);
+        audit_syscall_entry(audit_arch(), regs->syscallno,
+                            regs->gpr[3], regs->gpr[4],
+                            regs->gpr[5], regs->gpr[6]);
 
         return ret ? : regs->syscallno;
 }
@@ -201,9 +199,7 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs)
 {
         int step;
 
-        if (unlikely(current->audit_context))
-                audit_syscall_exit(AUDITSC_RESULT(regs->gpr[11]),
-                                   regs->gpr[11]);
+        audit_syscall_exit(regs);
 
         step = test_thread_flag(TIF_SINGLESTEP);
         if (step || test_thread_flag(TIF_SYSCALL_TRACE))
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 55cca1dac431..19ab7b2ea1cd 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -31,7 +31,11 @@ ifdef CONFIG_64BIT
 UTS_MACHINE     := parisc64
 CHECKFLAGS      += -D__LP64__=1 -m64
 WIDTH           := 64
+
+# FIXME: if no default set, should really try to locate dynamically
+ifeq ($(CROSS_COMPILE),)
 CROSS_COMPILE   := hppa64-linux-gnu-
+endif
 else # 32-bit
 WIDTH           :=
 endif
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d1727584230a..6d99a5fcc090 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -227,6 +227,9 @@ config COMPAT
 config SYSVIPC_COMPAT
         def_bool y if COMPAT && SYSVIPC
 
+config KEYS_COMPAT
+        def_bool y if COMPAT && KEYS
+
 config AUDIT_ARCH
         def_bool y
 
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/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 39f8fd4438fc..c383ce440d99 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -11,7 +11,6 @@
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
-#include <linux/crash_dump.h>
 #include <linux/bootmem.h>
 #include <linux/elf.h>
 #include <asm/ipl.h>
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/init.c b/arch/s390/mm/init.c
index 5d633019d8f3..50236610de83 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -223,16 +223,38 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 #ifdef CONFIG_MEMORY_HOTPLUG
 int arch_add_memory(int nid, u64 start, u64 size)
 {
-        struct pglist_data *pgdat;
+        unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
+        unsigned long start_pfn = PFN_DOWN(start);
+        unsigned long size_pages = PFN_DOWN(size);
         struct zone *zone;
         int rc;
 
-        pgdat = NODE_DATA(nid);
-        zone = pgdat->node_zones + ZONE_MOVABLE;
         rc = vmem_add_mapping(start, size);
         if (rc)
                 return rc;
-        rc = __add_pages(nid, zone, PFN_DOWN(start), PFN_DOWN(size));
+        for_each_zone(zone) {
+                if (zone_idx(zone) != ZONE_MOVABLE) {
+                        /* Add range within existing zone limits */
+                        zone_start_pfn = zone->zone_start_pfn;
+                        zone_end_pfn = zone->zone_start_pfn +
+                                       zone->spanned_pages;
+                } else {
+                        /* Add remaining range to ZONE_MOVABLE */
+                        zone_start_pfn = start_pfn;
+                        zone_end_pfn = start_pfn + size_pages;
+                }
+                if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
+                        continue;
+                nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
+                           zone_end_pfn - start_pfn : size_pages;
+                rc = __add_pages(nid, zone, start_pfn, nr_pages);
+                if (rc)
+                        break;
+                start_pfn += nr_pages;
+                size_pages -= nr_pages;
+                if (!size_pages)
+                        break;
+        }
         if (rc)
                 vmem_remove_mapping(start, size);
         return rc;
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/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 096c975e099f..461ce432b1c2 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -242,4 +242,12 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 static inline void perf_events_lapic_init(void) { }
 #endif
 
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
+ extern void amd_pmu_enable_virt(void);
+ extern void amd_pmu_disable_virt(void);
+#else
+ static inline void amd_pmu_enable_virt(void) { }
+ static inline void amd_pmu_disable_virt(void) { }
+#endif
+
 #endif /* _ASM_X86_PERF_EVENT_H */
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/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8944062f46e2..c30c807ddc72 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -147,7 +147,9 @@ struct cpu_hw_events {
         /*
          * AMD specific bits
          */
-        struct amd_nb           *amd_nb;
+        struct amd_nb                   *amd_nb;
+        /* Inverted mask of bits to clear in the perf_ctr ctrl registers */
+        u64                             perf_ctr_virt_mask;
 
         void                            *kfree_on_online;
 };
@@ -417,9 +419,11 @@ void x86_pmu_disable_all(void);
 static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
                                           u64 enable_mask)
 {
+        u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
+
         if (hwc->extra_reg.reg)
                 wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
-        wrmsrl(hwc->config_base, hwc->config | enable_mask);
+        wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
 }
 
 void x86_pmu_enable_all(int added);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 0397b23be8e9..67250a52430b 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -1,4 +1,5 @@
 #include <linux/perf_event.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -357,7 +358,9 @@ static void amd_pmu_cpu_starting(int cpu)
         struct amd_nb *nb;
         int i, nb_id;
 
-        if (boot_cpu_data.x86_max_cores < 2)
+        cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+        if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15)
                 return;
 
         nb_id = amd_get_nb_id(cpu);
@@ -587,9 +590,9 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
         .put_event_constraints  = amd_put_event_constraints,
 
         .cpu_prepare            = amd_pmu_cpu_prepare,
-        .cpu_starting           = amd_pmu_cpu_starting,
         .cpu_dead               = amd_pmu_cpu_dead,
 #endif
+        .cpu_starting           = amd_pmu_cpu_starting,
 };
 
 __init int amd_pmu_init(void)
@@ -621,3 +624,33 @@ __init int amd_pmu_init(void)
 
         return 0;
 }
+
+void amd_pmu_enable_virt(void)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+        cpuc->perf_ctr_virt_mask = 0;
+
+        /* Reload all events */
+        x86_pmu_disable_all();
+        x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
+
+void amd_pmu_disable_virt(void)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+        /*
+         * We only mask out the Host-only bit so that host-only counting works
+         * when SVM is disabled. If someone sets up a guest-only counter when
+         * SVM is disabled the Guest-only bits still gets set and the counter
+         * will not count anything.
+         */
+        cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+        /* Reload all events */
+        x86_pmu_disable_all();
+        x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
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/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 5fa553babe56..e385214711cb 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -29,6 +29,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/slab.h>
 
+#include <asm/perf_event.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
 #include <asm/kvm_para.h>
@@ -575,6 +576,8 @@ static void svm_hardware_disable(void *garbage)
                 wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
 
         cpu_svm_disable();
+
+        amd_pmu_disable_virt();
 }
 
 static int svm_hardware_enable(void *garbage)
@@ -622,6 +625,8 @@ static int svm_hardware_enable(void *garbage)
 
         svm_init_erratum_383();
 
+        amd_pmu_enable_virt();
+
         return 0;
 }
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 12eb07bfb267..4172af8ceeb3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1141,7 +1141,9 @@ asmlinkage void __init xen_start_kernel(void)
 
         /* Prevent unwanted bits from being set in PTEs. */
         __supported_pte_mask &= ~_PAGE_GLOBAL;
+#if 0
         if (!xen_initial_domain())
+#endif
                 __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
         __supported_pte_mask |= _PAGE_IOMAP;
@@ -1204,10 +1206,6 @@ asmlinkage void __init xen_start_kernel(void)
 
         pgd = (pgd_t *)xen_start_info->pt_base;
 
-        if (!xen_initial_domain())
-                __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
-
-        __supported_pte_mask |= _PAGE_IOMAP;
         /* Don't do the full vcpu_info placement stuff until we have a
            possible map and a non-dummy shared_info. */
         per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 58a0e46c404d..95c1cf60c669 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -415,13 +415,13 @@ static pteval_t iomap_pte(pteval_t val)
 static pteval_t xen_pte_val(pte_t pte)
 {
         pteval_t pteval = pte.pte;
-
+#if 0
         /* If this is a WC pte, convert back from Xen WC to Linux WC */
         if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
                 WARN_ON(!pat_enabled);
                 pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
         }
-
+#endif
         if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
                 return pteval;
 
@@ -463,7 +463,7 @@ void xen_set_pat(u64 pat)
 static pte_t xen_make_pte(pteval_t pte)
 {
         phys_addr_t addr = (pte & PTE_PFN_MASK);
-
+#if 0
         /* If Linux is trying to set a WC pte, then map to the Xen WC.
          * If _PAGE_PAT is set, then it probably means it is really
          * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
@@ -476,7 +476,7 @@ static pte_t xen_make_pte(pteval_t pte)
                 if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
                         pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
         }
-
+#endif
         /*
          * Unprivileged domains are allowed to do IOMAPpings for
          * PCI passthrough, but not map ISA space.  The ISA