Merge branch 'x86/cleanups' into perf/uprobes

Merge reason: We want to merge a dependent patch.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

22 files changed, 512 insertions, 196 deletions

diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 834e897b1e2..1b4754f82ba 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,6 +1,12 @@
 #include <asm/ia32.h>
 
 #define __SYSCALL_64(nr, sym, compat) [nr] = 1,
+#define __SYSCALL_COMMON(nr, sym, compat) [nr] = 1,
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) [nr] = 1,
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
 static char syscalls_64[] = {
 #include <asm/syscalls_64.h>
 };
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d43cad74f16..c0f7d68d318 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1044,6 +1044,9 @@ DEFINE_PER_CPU(char *, irq_stack_ptr) =
 
 DEFINE_PER_CPU(unsigned int, irq_count) = -1;
 
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+EXPORT_PER_CPU_SYMBOL(fpu_owner_task);
+
 /*
  * Special IST stacks which the CPU switches to when it calls
  * an IST-marked descriptor entry. Up to 7 stacks (hardware
@@ -1111,6 +1114,8 @@ void debug_stack_reset(void)
 
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
+DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
+EXPORT_PER_CPU_SYMBOL(fpu_owner_task);
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 6b45e5e7a90..73d08ed98a6 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 786e76a8632..e4eeaaf58a4 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/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 79289632cb2..a041e094b8b 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -167,6 +167,7 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 {
         int err = 0;
         mtrr_type type;
+        unsigned long base;
         unsigned long size;
         struct mtrr_sentry sentry;
         struct mtrr_gentry gentry;
@@ -267,14 +268,14 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 #endif
                 if (gentry.regnum >= num_var_ranges)
                         return -EINVAL;
-                mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+                mtrr_if->get(gentry.regnum, &base, &size, &type);
 
                 /* Hide entries that go above 4GB */
-                if (gentry.base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
+                if (base + size - 1 >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT))
                     || size >= (1UL << (8 * sizeof(gentry.size) - PAGE_SHIFT)))
                         gentry.base = gentry.size = gentry.type = 0;
                 else {
-                        gentry.base <<= PAGE_SHIFT;
+                        gentry.base = base << PAGE_SHIFT;
                         gentry.size = size << PAGE_SHIFT;
                         gentry.type = type;
                 }
@@ -321,11 +322,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 #endif
                 if (gentry.regnum >= num_var_ranges)
                         return -EINVAL;
-                mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
+                mtrr_if->get(gentry.regnum, &base, &size, &type);
                 /* Hide entries that would overflow */
                 if (size != (__typeof__(gentry.size))size)
                         gentry.base = gentry.size = gentry.type = 0;
                 else {
+                        gentry.base = base;
                         gentry.size = size;
                         gentry.type = type;
                 }
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3c44b712380..1c52bdbb9b8 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -29,7 +29,6 @@
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
 #include <asm/nmi.h>
-#include <asm/compat.h>
 #include <asm/smp.h>
 #include <asm/alternative.h>
 #include <asm/timer.h>
@@ -988,6 +987,9 @@ static void x86_pmu_start(struct perf_event *event, int flags)
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         int idx = event->hw.idx;
 
+        if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+                return;
+
         if (WARN_ON_ONCE(idx == -1))
                 return;
 
@@ -1674,6 +1676,9 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_COMPAT
+
+#include <asm/compat.h>
+
 static inline int
 perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 513d617b93c..82db83b5c3b 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;
 };
@@ -425,9 +427,11 @@ 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 0397b23be8e..67250a52430 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/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 4025fe4f928..28f98706b08 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -265,7 +265,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
 #endif
         printk("\n");
         if (notify_die(DIE_OOPS, str, regs, err,
-                        current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+                        current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
                 return 1;
 
         show_registers(regs);
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 3fe8239fd8f..2925e14fb1d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -482,7 +482,12 @@ GLOBAL(system_call_after_swapgs)
         testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
         jnz tracesys
 system_call_fastpath:
+#if __SYSCALL_MASK == ~0
         cmpq $__NR_syscall_max,%rax
+#else
+        andl $__SYSCALL_MASK,%eax
+        cmpl $__NR_syscall_max,%eax
+#endif
         ja badsys
         movq %r10,%rcx
         call *sys_call_table(,%rax,8)  # XXX:    rip relative
@@ -596,7 +601,12 @@ tracesys:
          */
         LOAD_ARGS ARGOFFSET, 1
         RESTORE_REST
+#if __SYSCALL_MASK == ~0
         cmpq $__NR_syscall_max,%rax
+#else
+        andl $__SYSCALL_MASK,%eax
+        cmpl $__NR_syscall_max,%eax
+#endif
         ja   int_ret_from_sys_call      /* RAX(%rsp) set to -ENOSYS above */
         movq %r10,%rcx  /* fixup for C */
         call *sys_call_table(,%rax,8)
@@ -736,6 +746,40 @@ ENTRY(stub_rt_sigreturn)
         CFI_ENDPROC
 END(stub_rt_sigreturn)
 
+#ifdef CONFIG_X86_X32_ABI
+        PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx
+
+ENTRY(stub_x32_rt_sigreturn)
+        CFI_STARTPROC
+        addq $8, %rsp
+        PARTIAL_FRAME 0
+        SAVE_REST
+        movq %rsp,%rdi
+        FIXUP_TOP_OF_STACK %r11
+        call sys32_x32_rt_sigreturn
+        movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
+        RESTORE_REST
+        jmp int_ret_from_sys_call
+        CFI_ENDPROC
+END(stub_x32_rt_sigreturn)
+
+ENTRY(stub_x32_execve)
+        CFI_STARTPROC
+        addq $8, %rsp
+        PARTIAL_FRAME 0
+        SAVE_REST
+        FIXUP_TOP_OF_STACK %r11
+        movq %rsp, %rcx
+        call sys32_execve
+        RESTORE_TOP_OF_STACK %r11
+        movq %rax,RAX(%rsp)
+        RESTORE_REST
+        jmp int_ret_from_sys_call
+        CFI_ENDPROC
+END(stub_x32_execve)
+
+#endif
+
 /*
  * Build the entry stubs and pointer table with some assembler magic.
  * We pack 7 stubs into a single 32-byte chunk, which will fit in a
@@ -1532,10 +1576,17 @@ 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/irqinit.c b/arch/x86/kernel/irqinit.c
index 313fb5cddbc..7b77062dea1 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -61,7 +61,7 @@ static irqreturn_t math_error_irq(int cpl, void *dev_id)
         outb(0, 0xF0);
         if (ignore_fpu_irq || !boot_cpu_data.hard_math)
                 return IRQ_NONE;
-        math_error(get_irq_regs(), 0, 16);
+        math_error(get_irq_regs(), 0, X86_TRAP_MF);
         return IRQ_HANDLED;
 }
 
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index ac0417be913..73465aab28f 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/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 485204f58cd..c08d1ff12b7 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -214,6 +214,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
         task_user_gs(p) = get_user_gs(regs);
 
+        p->fpu_counter = 0;
         p->thread.io_bitmap_ptr = NULL;
         tsk = current;
         err = -ENOMEM;
@@ -299,22 +300,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                                  *next = &next_p->thread;
         int cpu = smp_processor_id();
         struct tss_struct *tss = &per_cpu(init_tss, cpu);
-        bool preload_fpu;
+        fpu_switch_t fpu;
 
         /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-        /*
-         * If the task has used fpu the last 5 timeslices, just do a full
-         * restore of the math state immediately to avoid the trap; the
-         * chances of needing FPU soon are obviously high now
-         */
-        preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-        __unlazy_fpu(prev_p);
-
-        /* we're going to use this soon, after a few expensive things */
-        if (preload_fpu)
-                prefetch(next->fpu.state);
+        fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
         /*
          * Reload esp0.
@@ -354,11 +344,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                      task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
                 __switch_to_xtra(prev_p, next_p, tss);
 
-        /* If we're going to preload the fpu context, make sure clts
-           is run while we're batching the cpu state updates. */
-        if (preload_fpu)
-                clts();
-
         /*
          * Leave lazy mode, flushing any hypercalls made here.
          * This must be done before restoring TLS segments so
@@ -368,15 +353,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          */
         arch_end_context_switch(next_p);
 
-        if (preload_fpu)
-                __math_state_restore();
-
         /*
          * Restore %gs if needed (which is common)
          */
         if (prev->gs | next->gs)
                 lazy_load_gs(next->gs);
 
+        switch_fpu_finish(next_p, fpu);
+
         percpu_write(current_task, next_p);
 
         return prev_p;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9b9fe4a85c8..550e77b1b94 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -286,6 +286,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 
         set_tsk_thread_flag(p, TIF_FORK);
 
+        p->fpu_counter = 0;
         p->thread.io_bitmap_ptr = NULL;
 
         savesegment(gs, p->thread.gsindex);
@@ -364,7 +365,9 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
 {
         start_thread_common(regs, new_ip, new_sp,
-                            __USER32_CS, __USER32_DS, __USER32_DS);
+                            test_thread_flag(TIF_X32)
+                            ? __USER_CS : __USER32_CS,
+                            __USER_DS, __USER_DS);
 }
 #endif
 
@@ -386,18 +389,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         int cpu = smp_processor_id();
         struct tss_struct *tss = &per_cpu(init_tss, cpu);
         unsigned fsindex, gsindex;
-        bool preload_fpu;
+        fpu_switch_t fpu;
 
-        /*
-         * If the task has used fpu the last 5 timeslices, just do a full
-         * restore of the math state immediately to avoid the trap; the
-         * chances of needing FPU soon are obviously high now
-         */
-        preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
-
-        /* we're going to use this soon, after a few expensive things */
-        if (preload_fpu)
-                prefetch(next->fpu.state);
+        fpu = switch_fpu_prepare(prev_p, next_p, cpu);
 
         /*
          * Reload esp0, LDT and the page table pointer:
@@ -427,13 +421,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
         load_TLS(next, cpu);
 
-        /* Must be after DS reload */
-        __unlazy_fpu(prev_p);
-
-        /* Make sure cpu is ready for new context */
-        if (preload_fpu)
-                clts();
-
         /*
          * Leave lazy mode, flushing any hypercalls made here.
          * This must be done before restoring TLS segments so
@@ -474,6 +461,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                 wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
         prev->gsindex = gsindex;
 
+        switch_fpu_finish(next_p, fpu);
+
         /*
          * Switch the PDA and FPU contexts.
          */
@@ -492,13 +481,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                      task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV))
                 __switch_to_xtra(prev_p, next_p, tss);
 
-        /*
-         * Preload the FPU context, now that we've determined that the
-         * task is likely to be using it. 
-         */
-        if (preload_fpu)
-                __math_state_restore();
-
         return prev_p;
 }
 
@@ -508,6 +490,8 @@ void set_personality_64bit(void)
 
         /* Make sure to be in 64bit mode */
         clear_thread_flag(TIF_IA32);
+        clear_thread_flag(TIF_ADDR32);
+        clear_thread_flag(TIF_X32);
 
         /* Ensure the corresponding mm is not marked. */
         if (current->mm)
@@ -520,20 +504,31 @@ void set_personality_64bit(void)
         current->personality &= ~READ_IMPLIES_EXEC;
 }
 
-void set_personality_ia32(void)
+void set_personality_ia32(bool x32)
 {
         /* inherit personality from parent */
 
         /* Make sure to be in 32bit mode */
-        set_thread_flag(TIF_IA32);
-        current->personality |= force_personality32;
+        set_thread_flag(TIF_ADDR32);
 
         /* Mark the associated mm as containing 32-bit tasks. */
         if (current->mm)
                 current->mm->context.ia32_compat = 1;
 
-        /* Prepare the first "return" to user space */
-        current_thread_info()->status |= TS_COMPAT;
+        if (x32) {
+                clear_thread_flag(TIF_IA32);
+                set_thread_flag(TIF_X32);
+                current->personality &= ~READ_IMPLIES_EXEC;
+                /* is_compat_task() uses the presence of the x32
+                   syscall bit flag to determine compat status */
+                current_thread_info()->status &= ~TS_COMPAT;
+        } else {
+                set_thread_flag(TIF_IA32);
+                clear_thread_flag(TIF_X32);
+                current->personality |= force_personality32;
+                /* Prepare the first "return" to user space */
+                current_thread_info()->status |= TS_COMPAT;
+        }
 }
 
 unsigned long get_wchan(struct task_struct *p)
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 50267386b76..6fb330adc7c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -33,6 +33,7 @@
 #include <asm/prctl.h>
 #include <asm/proto.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/traps.h>
 
 #include "tls.h"
 
@@ -1130,6 +1131,100 @@ static int genregs32_set(struct task_struct *target,
         return ret;
 }
 
+#ifdef CONFIG_X86_X32_ABI
+static long x32_arch_ptrace(struct task_struct *child,
+                            compat_long_t request, compat_ulong_t caddr,
+                            compat_ulong_t cdata)
+{
+        unsigned long addr = caddr;
+        unsigned long data = cdata;
+        void __user *datap = compat_ptr(data);
+        int ret;
+
+        switch (request) {
+        /* Read 32bits at location addr in the USER area.  Only allow
+           to return the lower 32bits of segment and debug registers.  */
+        case PTRACE_PEEKUSR: {
+                u32 tmp;
+
+                ret = -EIO;
+                if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+                    addr < offsetof(struct user_regs_struct, cs))
+                        break;
+
+                tmp = 0;  /* Default return condition */
+                if (addr < sizeof(struct user_regs_struct))
+                        tmp = getreg(child, addr);
+                else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+                         addr <= offsetof(struct user, u_debugreg[7])) {
+                        addr -= offsetof(struct user, u_debugreg[0]);
+                        tmp = ptrace_get_debugreg(child, addr / sizeof(data));
+                }
+                ret = put_user(tmp, (__u32 __user *)datap);
+                break;
+        }
+
+        /* Write the word at location addr in the USER area.  Only allow
+           to update segment and debug registers with the upper 32bits
+           zero-extended. */
+        case PTRACE_POKEUSR:
+                ret = -EIO;
+                if ((addr & (sizeof(data) - 1)) || addr >= sizeof(struct user) ||
+                    addr < offsetof(struct user_regs_struct, cs))
+                        break;
+
+                if (addr < sizeof(struct user_regs_struct))
+                        ret = putreg(child, addr, data);
+                else if (addr >= offsetof(struct user, u_debugreg[0]) &&
+                         addr <= offsetof(struct user, u_debugreg[7])) {
+                        addr -= offsetof(struct user, u_debugreg[0]);
+                        ret = ptrace_set_debugreg(child,
+                                                  addr / sizeof(data), data);
+                }
+                break;
+
+        case PTRACE_GETREGS:    /* Get all gp regs from the child. */
+                return copy_regset_to_user(child,
+                                           task_user_regset_view(current),
+                                           REGSET_GENERAL,
+                                           0, sizeof(struct user_regs_struct),
+                                           datap);
+
+        case PTRACE_SETREGS:    /* Set all gp regs in the child. */
+                return copy_regset_from_user(child,
+                                             task_user_regset_view(current),
+                                             REGSET_GENERAL,
+                                             0, sizeof(struct user_regs_struct),
+                                             datap);
+
+        case PTRACE_GETFPREGS:  /* Get the child FPU state. */
+                return copy_regset_to_user(child,
+                                           task_user_regset_view(current),
+                                           REGSET_FP,
+                                           0, sizeof(struct user_i387_struct),
+                                           datap);
+
+        case PTRACE_SETFPREGS:  /* Set the child FPU state. */
+                return copy_regset_from_user(child,
+                                             task_user_regset_view(current),
+                                             REGSET_FP,
+                                             0, sizeof(struct user_i387_struct),
+                                             datap);
+
+                /* normal 64bit interface to access TLS data.
+                   Works just like arch_prctl, except that the arguments
+                   are reversed. */
+        case PTRACE_ARCH_PRCTL:
+                return do_arch_prctl(child, data, addr);
+
+        default:
+                return compat_ptrace_request(child, request, addr, data);
+        }
+
+        return ret;
+}
+#endif
+
 long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
                         compat_ulong_t caddr, compat_ulong_t cdata)
 {
@@ -1139,6 +1234,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
         int ret;
         __u32 val;
 
+#ifdef CONFIG_X86_X32_ABI
+        if (!is_ia32_task())
+                return x32_arch_ptrace(child, request, caddr, cdata);
+#endif
+
         switch (request) {
         case PTRACE_PEEKUSR:
                 ret = getreg32(child, addr, &val);
@@ -1326,7 +1426,7 @@ static void fill_sigtrap_info(struct task_struct *tsk,
                                 int error_code, int si_code,
                                 struct siginfo *info)
 {
-        tsk->thread.trap_no = 1;
+        tsk->thread.trap_nr = X86_TRAP_DB;
         tsk->thread.error_code = error_code;
 
         memset(info, 0, sizeof(*info));
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 46a01bdc27e..9c73acc1c86 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -10,10 +10,8 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/kernel.h>
-#include <linux/signal.h>
 #include <linux/errno.h>
 #include <linux/wait.h>
-#include <linux/ptrace.h>
 #include <linux/tracehook.h>
 #include <linux/unistd.h>
 #include <linux/stddef.h>
@@ -26,10 +24,12 @@
 #include <asm/i387.h>
 #include <asm/vdso.h>
 #include <asm/mce.h>
+#include <asm/sighandling.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/proto.h>
 #include <asm/ia32_unistd.h>
+#include <asm/sys_ia32.h>
 #endif /* CONFIG_X86_64 */
 
 #include <asm/syscall.h>
@@ -37,13 +37,6 @@
 
 #include <asm/sigframe.h>
 
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-#define __FIX_EFLAGS    (X86_EFLAGS_AC | X86_EFLAGS_OF | \
-                         X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
-                         X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-                         X86_EFLAGS_CF)
-
 #ifdef CONFIG_X86_32
 # define FIX_EFLAGS     (__FIX_EFLAGS | X86_EFLAGS_RF)
 #else
@@ -68,9 +61,8 @@
         regs->seg = GET_SEG(seg) | 3;                   \
 } while (0)
 
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
-                   unsigned long *pax)
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+                       unsigned long *pax)
 {
         void __user *buf;
         unsigned int tmpflags;
@@ -125,9 +117,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
         return err;
 }
 
-static int
-setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
-                 struct pt_regs *regs, unsigned long mask)
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+                     struct pt_regs *regs, unsigned long mask)
 {
         int err = 0;
 
@@ -159,7 +150,7 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
                 put_user_ex(regs->r15, &sc->r15);
 #endif /* CONFIG_X86_64 */
 
-                put_user_ex(current->thread.trap_no, &sc->trapno);
+                put_user_ex(current->thread.trap_nr, &sc->trapno);
                 put_user_ex(current->thread.error_code, &sc->err);
                 put_user_ex(regs->ip, &sc->ip);
 #ifdef CONFIG_X86_32
@@ -642,6 +633,16 @@ static int signr_convert(int sig)
 #define is_ia32 0
 #endif /* CONFIG_IA32_EMULATION */
 
+#ifdef CONFIG_X86_X32_ABI
+#define is_x32  test_thread_flag(TIF_X32)
+
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+                              siginfo_t *info, compat_sigset_t *set,
+                              struct pt_regs *regs);
+#else /* !CONFIG_X86_X32_ABI */
+#define is_x32  0
+#endif /* CONFIG_X86_X32_ABI */
+
 int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                 sigset_t *set, struct pt_regs *regs);
 int ia32_setup_frame(int sig, struct k_sigaction *ka,
@@ -666,8 +667,14 @@ setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
                         ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
                 else
                         ret = ia32_setup_frame(usig, ka, set, regs);
-        } else
+#ifdef CONFIG_X86_X32_ABI
+        } else if (is_x32) {
+                ret = x32_setup_rt_frame(usig, ka, info,
+                                         (compat_sigset_t *)set, regs);
+#endif
+        } else {
                 ret = __setup_rt_frame(sig, ka, info, set, regs);
+        }
 
         if (ret) {
                 force_sigsegv(sig, current);
@@ -850,3 +857,102 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
 
         force_sig(SIGSEGV, me);
 }
+
+#ifdef CONFIG_X86_X32_ABI
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+                              siginfo_t *info, compat_sigset_t *set,
+                              struct pt_regs *regs)
+{
+        struct rt_sigframe_x32 __user *frame;
+        void __user *restorer;
+        int err = 0;
+        void __user *fpstate = NULL;
+
+        frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
+
+        if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+                return -EFAULT;
+
+        if (ka->sa.sa_flags & SA_SIGINFO) {
+                if (copy_siginfo_to_user32(&frame->info, info))
+                        return -EFAULT;
+        }
+
+        put_user_try {
+                /* Create the ucontext.  */
+                if (cpu_has_xsave)
+                        put_user_ex(UC_FP_XSTATE, &frame->uc.uc_flags);
+                else
+                        put_user_ex(0, &frame->uc.uc_flags);
+                put_user_ex(0, &frame->uc.uc_link);
+                put_user_ex(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+                put_user_ex(sas_ss_flags(regs->sp),
+                            &frame->uc.uc_stack.ss_flags);
+                put_user_ex(current->sas_ss_size, &frame->uc.uc_stack.ss_size);
+                put_user_ex(0, &frame->uc.uc__pad0);
+                err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+                                        regs, set->sig[0]);
+                err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+                if (ka->sa.sa_flags & SA_RESTORER) {
+                        restorer = ka->sa.sa_restorer;
+                } else {
+                        /* could use a vstub here */
+                        restorer = NULL;
+                        err |= -EFAULT;
+                }
+                put_user_ex(restorer, &frame->pretcode);
+        } put_user_catch(err);
+
+        if (err)
+                return -EFAULT;
+
+        /* Set up registers for signal handler */
+        regs->sp = (unsigned long) frame;
+        regs->ip = (unsigned long) ka->sa.sa_handler;
+
+        /* We use the x32 calling convention here... */
+        regs->di = sig;
+        regs->si = (unsigned long) &frame->info;
+        regs->dx = (unsigned long) &frame->uc;
+
+        loadsegment(ds, __USER_DS);
+        loadsegment(es, __USER_DS);
+
+        regs->cs = __USER_CS;
+        regs->ss = __USER_DS;
+
+        return 0;
+}
+
+asmlinkage long sys32_x32_rt_sigreturn(struct pt_regs *regs)
+{
+        struct rt_sigframe_x32 __user *frame;
+        sigset_t set;
+        unsigned long ax;
+        struct pt_regs tregs;
+
+        frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
+
+        if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+                goto badframe;
+        if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+                goto badframe;
+
+        sigdelsetmask(&set, ~_BLOCKABLE);
+        set_current_blocked(&set);
+
+        if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+                goto badframe;
+
+        tregs = *regs;
+        if (sys32_sigaltstack(&frame->uc.uc_stack, NULL, &tregs) == -EFAULT)
+                goto badframe;
+
+        return ax;
+
+badframe:
+        signal_fault(regs, frame, "x32 rt_sigreturn");
+        return 0;
+}
+#endif
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 051489082d5..f921df8c209 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -98,7 +98,7 @@ out:
 static void find_start_end(unsigned long flags, unsigned long *begin,
                            unsigned long *end)
 {
-        if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT)) {
+        if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT)) {
                 unsigned long new_begin;
                 /* This is usually used needed to map code in small
                    model, so it needs to be in the first 31bit. Limit
@@ -144,7 +144,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
                     (!vma || addr + len <= vma->vm_start))
                         return addr;
         }
-        if (((flags & MAP_32BIT) || test_thread_flag(TIF_IA32))
+        if (((flags & MAP_32BIT) || test_thread_flag(TIF_ADDR32))
             && len <= mm->cached_hole_size) {
                 mm->cached_hole_size = 0;
                 mm->free_area_cache = begin;
@@ -205,7 +205,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
                 return addr;
 
         /* for MAP_32BIT mappings we force the legact mmap base */
-        if (!test_thread_flag(TIF_IA32) && (flags & MAP_32BIT))
+        if (!test_thread_flag(TIF_ADDR32) && (flags & MAP_32BIT))
                 goto bottomup;
 
         /* requesting a specific address */
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 7ac7943be02..5c7f8c20da7 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -5,6 +5,14 @@
 #include <linux/cache.h>
 #include <asm/asm-offsets.h>
 
+#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+
+#ifdef CONFIG_X86_X32_ABI
+# define __SYSCALL_X32(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
+#else
+# define __SYSCALL_X32(nr, sym, compat) /* nothing */
+#endif
+
 #define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 482ec3af206..c6d17ad59b8 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -119,7 +119,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
                  * traps 0, 1, 3, 4, and 5 should be forwarded to vm86.
                  * On nmi (interrupt 2), do_trap should not be called.
                  */
-                if (trapnr < 6)
+                if (trapnr < X86_TRAP_UD)
                         goto vm86_trap;
                 goto trap_signal;
         }
@@ -132,7 +132,7 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 trap_signal:
 #endif
         /*
-         * We want error_code and trap_no set for userspace faults and
+         * We want error_code and trap_nr set for userspace faults and
          * kernelspace faults which result in die(), but not
          * kernelspace faults which are fixed up.  die() gives the
          * process no chance to handle the signal and notice the
@@ -141,7 +141,7 @@ trap_signal:
          * delivered, faults.  See also do_general_protection below.
          */
         tsk->thread.error_code = error_code;
-        tsk->thread.trap_no = trapnr;
+        tsk->thread.trap_nr = trapnr;
 
 #ifdef CONFIG_X86_64
         if (show_unhandled_signals && unhandled_signal(tsk, signr) &&
@@ -164,7 +164,7 @@ trap_signal:
 kernel_trap:
         if (!fixup_exception(regs)) {
                 tsk->thread.error_code = error_code;
-                tsk->thread.trap_no = trapnr;
+                tsk->thread.trap_nr = trapnr;
                 die(str, regs, error_code);
         }
         return;
@@ -203,27 +203,31 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code)	\
         do_trap(trapnr, signr, str, regs, error_code, &info);           \
 }
 
-DO_ERROR_INFO(0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip)
-DO_ERROR(4, SIGSEGV, "overflow", overflow)
-DO_ERROR(5, SIGSEGV, "bounds", bounds)
-DO_ERROR_INFO(6, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip)
-DO_ERROR(9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun)
-DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS)
-DO_ERROR(11, SIGBUS, "segment not present", segment_not_present)
+DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV,
+                regs->ip)
+DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
+DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
+DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN,
+                regs->ip)
+DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
+                coprocessor_segment_overrun)
+DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
+DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
 #ifdef CONFIG_X86_32
-DO_ERROR(12, SIGBUS, "stack segment", stack_segment)
+DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
 #endif
-DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0)
+DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
+                BUS_ADRALN, 0)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
 {
         if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-                        12, SIGBUS) == NOTIFY_STOP)
+                        X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
                 return;
         preempt_conditional_sti(regs);
-        do_trap(12, SIGBUS, "stack segment", regs, error_code, NULL);
+        do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
         preempt_conditional_cli(regs);
 }
 
@@ -233,10 +237,10 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
         struct task_struct *tsk = current;
 
         /* Return not checked because double check cannot be ignored */
-        notify_die(DIE_TRAP, str, regs, error_code, 8, SIGSEGV);
+        notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
         tsk->thread.error_code = error_code;
-        tsk->thread.trap_no = 8;
+        tsk->thread.trap_nr = X86_TRAP_DF;
 
         /*
          * This is always a kernel trap and never fixable (and thus must
@@ -264,7 +268,7 @@ do_general_protection(struct pt_regs *regs, long error_code)
                 goto gp_in_kernel;
 
         tsk->thread.error_code = error_code;
-        tsk->thread.trap_no = 13;
+        tsk->thread.trap_nr = X86_TRAP_GP;
 
         if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
                         printk_ratelimit()) {
@@ -291,9 +295,9 @@ gp_in_kernel:
                 return;
 
         tsk->thread.error_code = error_code;
-        tsk->thread.trap_no = 13;
-        if (notify_die(DIE_GPF, "general protection fault", regs,
-                                error_code, 13, SIGSEGV) == NOTIFY_STOP)
+        tsk->thread.trap_nr = X86_TRAP_GP;
+        if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
+                        X86_TRAP_GP, SIGSEGV) == NOTIFY_STOP)
                 return;
         die("general protection fault", regs, error_code);
 }
@@ -302,13 +306,13 @@ gp_in_kernel:
 dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
-        if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
-                        == NOTIFY_STOP)
+        if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+                                SIGTRAP) == NOTIFY_STOP)
                 return;
 #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */
 
-        if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP)
-                        == NOTIFY_STOP)
+        if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
+                        SIGTRAP) == NOTIFY_STOP)
                 return;
 
         /*
@@ -317,7 +321,7 @@ dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
          */
         debug_stack_usage_inc();
         preempt_conditional_sti(regs);
-        do_trap(3, SIGTRAP, "int3", regs, error_code, NULL);
+        do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
         preempt_conditional_cli(regs);
         debug_stack_usage_dec();
 }
@@ -422,8 +426,8 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
         preempt_conditional_sti(regs);
 
         if (regs->flags & X86_VM_MASK) {
-                handle_vm86_trap((struct kernel_vm86_regs *) regs,
-                                error_code, 1);
+                handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
+                                        X86_TRAP_DB);
                 preempt_conditional_cli(regs);
                 debug_stack_usage_dec();
                 return;
@@ -460,7 +464,8 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
         struct task_struct *task = current;
         siginfo_t info;
         unsigned short err;
-        char *str = (trapnr == 16) ? "fpu exception" : "simd exception";
+        char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
+                                                "simd exception";
 
         if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
                 return;
@@ -470,7 +475,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
         {
                 if (!fixup_exception(regs)) {
                         task->thread.error_code = error_code;
-                        task->thread.trap_no = trapnr;
+                        task->thread.trap_nr = trapnr;
                         die(str, regs, error_code);
                 }
                 return;
@@ -480,12 +485,12 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
          * Save the info for the exception handler and clear the error.
          */
         save_init_fpu(task);
-        task->thread.trap_no = trapnr;
+        task->thread.trap_nr = trapnr;
         task->thread.error_code = error_code;
         info.si_signo = SIGFPE;
         info.si_errno = 0;
         info.si_addr = (void __user *)regs->ip;
-        if (trapnr == 16) {
+        if (trapnr == X86_TRAP_MF) {
                 unsigned short cwd, swd;
                 /*
                  * (~cwd & swd) will mask out exceptions that are not set to unmasked
@@ -529,10 +534,11 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr)
                 info.si_code = FPE_FLTRES;
         } else {
                 /*
-                 * If we're using IRQ 13, or supposedly even some trap 16
-                 * implementations, it's possible we get a spurious trap...
+                 * If we're using IRQ 13, or supposedly even some trap
+                 * X86_TRAP_MF implementations, it's possible
+                 * we get a spurious trap, which is not an error.
                  */
-                return;         /* Spurious trap, no error */
+                return;
         }
         force_sig_info(SIGFPE, &info, task);
 }
@@ -543,13 +549,13 @@ dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
         ignore_fpu_irq = 1;
 #endif
 
-        math_error(regs, error_code, 16);
+        math_error(regs, error_code, X86_TRAP_MF);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-        math_error(regs, error_code, 19);
+        math_error(regs, error_code, X86_TRAP_XF);
 }
 
 dotraplinkage void
@@ -571,41 +577,18 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
 }
 
 /*
- * __math_state_restore assumes that cr0.TS is already clear and the
- * fpu state is all ready for use.  Used during context switch.
- */
-void __math_state_restore(void)
-{
-        struct thread_info *thread = current_thread_info();
-        struct task_struct *tsk = thread->task;
-
-        /*
-         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
-         */
-        if (unlikely(restore_fpu_checking(tsk))) {
-                stts();
-                force_sig(SIGSEGV, tsk);
-                return;
-        }
-
-        thread->status |= TS_USEDFPU;   /* So we fnsave on switch_to() */
-        tsk->fpu_counter++;
-}
-
-/*
  * 'math_state_restore()' saves the current math information in the
  * old math state array, and gets the new ones from the current task
  *
  * Careful.. There are problems with IBM-designed IRQ13 behaviour.
  * Don't touch unless you *really* know how it works.
  *
- * Must be called with kernel preemption disabled (in this case,
- * local interrupts are disabled at the call-site in entry.S).
+ * Must be called with kernel preemption disabled (eg with local
+ * local interrupts as in the case of do_device_not_available).
  */
-asmlinkage void math_state_restore(void)
+void math_state_restore(void)
 {
-        struct thread_info *thread = current_thread_info();
-        struct task_struct *tsk = thread->task;
+        struct task_struct *tsk = current;
 
         if (!tsk_used_math(tsk)) {
                 local_irq_enable();
@@ -622,9 +605,17 @@ asmlinkage void math_state_restore(void)
                 local_irq_disable();
         }
 
-        clts();                         /* Allow maths ops (or we recurse) */
+        __thread_fpu_begin(tsk);
+        /*
+         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
+         */
+        if (unlikely(restore_fpu_checking(tsk))) {
+                __thread_fpu_end(tsk);
+                force_sig(SIGSEGV, tsk);
+                return;
+        }
 
-        __math_state_restore();
+        tsk->fpu_counter++;
 }
 EXPORT_SYMBOL_GPL(math_state_restore);
 
@@ -658,20 +649,21 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code)
         info.si_errno = 0;
         info.si_code = ILL_BADSTK;
         info.si_addr = NULL;
-        if (notify_die(DIE_TRAP, "iret exception",
-                        regs, error_code, 32, SIGILL) == NOTIFY_STOP)
+        if (notify_die(DIE_TRAP, "iret exception", regs, error_code,
+                        X86_TRAP_IRET, SIGILL) == NOTIFY_STOP)
                 return;
-        do_trap(32, SIGILL, "iret exception", regs, error_code, &info);
+        do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code,
+                &info);
 }
 #endif
 
 /* Set of traps needed for early debugging. */
 void __init early_trap_init(void)
 {
-        set_intr_gate_ist(1, &debug, DEBUG_STACK);
+        set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
         /* int3 can be called from all */
-        set_system_intr_gate_ist(3, &int3, DEBUG_STACK);
-        set_intr_gate(14, &page_fault);
+        set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
+        set_intr_gate(X86_TRAP_PF, &page_fault);
         load_idt(&idt_descr);
 }
 
@@ -687,30 +679,30 @@ void __init trap_init(void)
         early_iounmap(p, 4);
 #endif
 
-        set_intr_gate(0, &divide_error);
-        set_intr_gate_ist(2, &nmi, NMI_STACK);
+        set_intr_gate(X86_TRAP_DE, &divide_error);
+        set_intr_gate_ist(X86_TRAP_NMI, &nmi, NMI_STACK);
         /* int4 can be called from all */
-        set_system_intr_gate(4, &overflow);
-        set_intr_gate(5, &bounds);
-        set_intr_gate(6, &invalid_op);
-        set_intr_gate(7, &device_not_available);
+        set_system_intr_gate(X86_TRAP_OF, &overflow);
+        set_intr_gate(X86_TRAP_BR, &bounds);
+        set_intr_gate(X86_TRAP_UD, &invalid_op);
+        set_intr_gate(X86_TRAP_NM, &device_not_available);
 #ifdef CONFIG_X86_32
-        set_task_gate(8, GDT_ENTRY_DOUBLEFAULT_TSS);
+        set_task_gate(X86_TRAP_DF, GDT_ENTRY_DOUBLEFAULT_TSS);
 #else
-        set_intr_gate_ist(8, &double_fault, DOUBLEFAULT_STACK);
+        set_intr_gate_ist(X86_TRAP_DF, &double_fault, DOUBLEFAULT_STACK);
 #endif
-        set_intr_gate(9, &coprocessor_segment_overrun);
-        set_intr_gate(10, &invalid_TSS);
-        set_intr_gate(11, &segment_not_present);
-        set_intr_gate_ist(12, &stack_segment, STACKFAULT_STACK);
-        set_intr_gate(13, &general_protection);
-        set_intr_gate(15, &spurious_interrupt_bug);
-        set_intr_gate(16, &coprocessor_error);
-        set_intr_gate(17, &alignment_check);
+        set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
+        set_intr_gate(X86_TRAP_TS, &invalid_TSS);
+        set_intr_gate(X86_TRAP_NP, &segment_not_present);
+        set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+        set_intr_gate(X86_TRAP_GP, &general_protection);
+        set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
+        set_intr_gate(X86_TRAP_MF, &coprocessor_error);
+        set_intr_gate(X86_TRAP_AC, &alignment_check);
 #ifdef CONFIG_X86_MCE
-        set_intr_gate_ist(18, &machine_check, MCE_STACK);
+        set_intr_gate_ist(X86_TRAP_MC, &machine_check, MCE_STACK);
 #endif
-        set_intr_gate(19, &simd_coprocessor_error);
+        set_intr_gate(X86_TRAP_XF, &simd_coprocessor_error);
 
         /* Reserve all the builtin and the syscall vector: */
         for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
@@ -735,7 +727,7 @@ void __init trap_init(void)
 
 #ifdef CONFIG_X86_64
         memcpy(&nmi_idt_table, &idt_table, IDT_ENTRIES * 16);
-        set_nmi_gate(1, &debug);
-        set_nmi_gate(3, &int3);
+        set_nmi_gate(X86_TRAP_DB, &debug);
+        set_nmi_gate(X86_TRAP_BP, &int3);
 #endif
 }
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index b466cab5ba1..a1315ab2d6b 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -567,7 +567,7 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
         }
         if (trapno != 1)
                 return 1; /* we let this handle by the calling routine */
-        current->thread.trap_no = trapno;
+        current->thread.trap_nr = trapno;
         current->thread.error_code = error_code;
         force_sig(SIGTRAP, current);
         return 0;
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index b07ba939356..327509b95e0 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -153,7 +153,7 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
 
                 thread->error_code      = 6;  /* user fault, no page, write */
                 thread->cr2             = ptr;
-                thread->trap_no         = 14;
+                thread->trap_nr         = X86_TRAP_PF;
 
                 memset(&info, 0, sizeof(info));
                 info.si_signo           = SIGSEGV;
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index a3911343976..71109111411 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -47,7 +47,7 @@ void __sanitize_i387_state(struct task_struct *tsk)
         if (!fx)
                 return;
 
-        BUG_ON(task_thread_info(tsk)->status & TS_USEDFPU);
+        BUG_ON(__thread_has_fpu(tsk));
 
         xstate_bv = tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv;
 
@@ -168,7 +168,7 @@ int save_i387_xstate(void __user *buf)
         if (!used_math())
                 return 0;
 
-        if (task_thread_info(tsk)->status & TS_USEDFPU) {
+        if (user_has_fpu()) {
                 if (use_xsave())
                         err = xsave_user(buf);
                 else
@@ -176,8 +176,7 @@ int save_i387_xstate(void __user *buf)
 
                 if (err)
                         return err;
-                task_thread_info(tsk)->status &= ~TS_USEDFPU;
-                stts();
+                user_fpu_end();
         } else {
                 sanitize_i387_state(tsk);
                 if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
@@ -292,10 +291,7 @@ int restore_i387_xstate(void __user *buf)
                         return err;
         }
 
-        if (!(task_thread_info(current)->status & TS_USEDFPU)) {
-                clts();
-                task_thread_info(current)->status |= TS_USEDFPU;
-        }
+        user_fpu_begin();
         if (use_xsave())
                 err = restore_user_xstate(buf);
         else