9 files changed, 136 insertions, 202 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4868e4a951ee..c1c00d0b1692 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1243,10 +1243,7 @@ void __cpuinit cpu_init(void)
         /*
          * Force FPU initialization:
          */
-        if (cpu_has_xsave)
-                current_thread_info()->status = TS_XSAVE;
-        else
-                current_thread_info()->status = 0;
+        current_thread_info()->status = 0;
         clear_used_math();
         mxcsr_feature_mask_init();
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 44a8e0dc6737..cd49141cf153 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -53,6 +53,7 @@
 #include <asm/processor-flags.h>
 #include <asm/ftrace.h>
 #include <asm/irq_vectors.h>
+#include <asm/cpufeature.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -905,7 +906,25 @@ ENTRY(simd_coprocessor_error)
         RING0_INT_FRAME
         pushl $0
         CFI_ADJUST_CFA_OFFSET 4
+#ifdef CONFIG_X86_INVD_BUG
+        /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
+661:    pushl $do_general_protection
+662:
+.section .altinstructions,"a"
+        .balign 4
+        .long 661b
+        .long 663f
+        .byte X86_FEATURE_XMM
+        .byte 662b-661b
+        .byte 664f-663f
+.previous
+.section .altinstr_replacement,"ax"
+663:    pushl $do_simd_coprocessor_error
+664:
+.previous
+#else
         pushl $do_simd_coprocessor_error
+#endif
         CFI_ADJUST_CFA_OFFSET 4
         jmp error_code
         CFI_ENDPROC
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 54c31c285488..86cef6b32253 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -102,65 +102,62 @@ void __cpuinit fpu_init(void)
 
         mxcsr_feature_mask_init();
         /* clean state in init */
-        if (cpu_has_xsave)
-                current_thread_info()->status = TS_XSAVE;
-        else
-                current_thread_info()->status = 0;
+        current_thread_info()->status = 0;
         clear_used_math();
 }
 #endif  /* CONFIG_X86_64 */
 
-/*
- * The _current_ task is using the FPU for the first time
- * so initialize it and set the mxcsr to its default
- * value at reset if we support XMM instructions and then
- * remeber the current task has used the FPU.
- */
-int init_fpu(struct task_struct *tsk)
+static void fpu_finit(struct fpu *fpu)
 {
-        if (tsk_used_math(tsk)) {
-                if (HAVE_HWFP && tsk == current)
-                        unlazy_fpu(tsk);
-                return 0;
-        }
-
-        /*
-         * Memory allocation at the first usage of the FPU and other state.
-         */
-        if (!tsk->thread.xstate) {
-                tsk->thread.xstate = kmem_cache_alloc(task_xstate_cachep,
-                                                      GFP_KERNEL);
-                if (!tsk->thread.xstate)
-                        return -ENOMEM;
-        }
-
 #ifdef CONFIG_X86_32
         if (!HAVE_HWFP) {
-                memset(tsk->thread.xstate, 0, xstate_size);
-                finit_task(tsk);
-                set_stopped_child_used_math(tsk);
-                return 0;
+                finit_soft_fpu(&fpu->state->soft);
+                return;
         }
 #endif
 
         if (cpu_has_fxsr) {
-                struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+                struct i387_fxsave_struct *fx = &fpu->state->fxsave;
 
                 memset(fx, 0, xstate_size);
                 fx->cwd = 0x37f;
                 if (cpu_has_xmm)
                         fx->mxcsr = MXCSR_DEFAULT;
         } else {
-                struct i387_fsave_struct *fp = &tsk->thread.xstate->fsave;
+                struct i387_fsave_struct *fp = &fpu->state->fsave;
                 memset(fp, 0, xstate_size);
                 fp->cwd = 0xffff037fu;
                 fp->swd = 0xffff0000u;
                 fp->twd = 0xffffffffu;
                 fp->fos = 0xffff0000u;
         }
+}
+
+/*
+ * The _current_ task is using the FPU for the first time
+ * so initialize it and set the mxcsr to its default
+ * value at reset if we support XMM instructions and then
+ * remeber the current task has used the FPU.
+ */
+int init_fpu(struct task_struct *tsk)
+{
+        int ret;
+
+        if (tsk_used_math(tsk)) {
+                if (HAVE_HWFP && tsk == current)
+                        unlazy_fpu(tsk);
+                return 0;
+        }
+
         /*
-         * Only the device not available exception or ptrace can call init_fpu.
+         * Memory allocation at the first usage of the FPU and other state.
          */
+        ret = fpu_alloc(&tsk->thread.fpu);
+        if (ret)
+                return ret;
+
+        fpu_finit(&tsk->thread.fpu);
+
         set_stopped_child_used_math(tsk);
         return 0;
 }
@@ -194,7 +191,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
                 return ret;
 
         return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-                                   &target->thread.xstate->fxsave, 0, -1);
+                                   &target->thread.fpu.state->fxsave, 0, -1);
 }
 
 int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
@@ -211,19 +208,19 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
                 return ret;
 
         ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-                                 &target->thread.xstate->fxsave, 0, -1);
+                                 &target->thread.fpu.state->fxsave, 0, -1);
 
         /*
          * mxcsr reserved bits must be masked to zero for security reasons.
          */
-        target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask;
+        target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
 
         /*
          * update the header bits in the xsave header, indicating the
          * presence of FP and SSE state.
          */
         if (cpu_has_xsave)
-                target->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
+                target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
 
         return ret;
 }
@@ -246,14 +243,14 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
          * memory layout in the thread struct, so that we can copy the entire
          * xstateregs to the user using one user_regset_copyout().
          */
-        memcpy(&target->thread.xstate->fxsave.sw_reserved,
+        memcpy(&target->thread.fpu.state->fxsave.sw_reserved,
                xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes));
 
         /*
          * Copy the xstate memory layout.
          */
         ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-                                  &target->thread.xstate->xsave, 0, -1);
+                                  &target->thread.fpu.state->xsave, 0, -1);
         return ret;
 }
 
@@ -272,14 +269,14 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
                 return ret;
 
         ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-                                 &target->thread.xstate->xsave, 0, -1);
+                                 &target->thread.fpu.state->xsave, 0, -1);
 
         /*
          * mxcsr reserved bits must be masked to zero for security reasons.
          */
-        target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask;
+        target->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
 
-        xsave_hdr = &target->thread.xstate->xsave.xsave_hdr;
+        xsave_hdr = &target->thread.fpu.state->xsave.xsave_hdr;
 
         xsave_hdr->xstate_bv &= pcntxt_mask;
         /*
@@ -365,7 +362,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave)
 static void
 convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 {
-        struct i387_fxsave_struct *fxsave = &tsk->thread.xstate->fxsave;
+        struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
         struct _fpreg *to = (struct _fpreg *) &env->st_space[0];
         struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0];
         int i;
@@ -405,7 +402,7 @@ static void convert_to_fxsr(struct task_struct *tsk,
                             const struct user_i387_ia32_struct *env)
 
 {
-        struct i387_fxsave_struct *fxsave = &tsk->thread.xstate->fxsave;
+        struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
         struct _fpreg *from = (struct _fpreg *) &env->st_space[0];
         struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0];
         int i;
@@ -445,7 +442,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset,
 
         if (!cpu_has_fxsr) {
                 return user_regset_copyout(&pos, &count, &kbuf, &ubuf,
-                                           &target->thread.xstate->fsave, 0,
+                                           &target->thread.fpu.state->fsave, 0,
                                            -1);
         }
 
@@ -475,7 +472,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 
         if (!cpu_has_fxsr) {
                 return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
-                                          &target->thread.xstate->fsave, 0, -1);
+                                          &target->thread.fpu.state->fsave, 0, -1);
         }
 
         if (pos > 0 || count < sizeof(env))
@@ -490,7 +487,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
          * presence of FP.
          */
         if (cpu_has_xsave)
-                target->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
+                target->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FP;
         return ret;
 }
 
@@ -501,7 +498,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
 static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf)
 {
         struct task_struct *tsk = current;
-        struct i387_fsave_struct *fp = &tsk->thread.xstate->fsave;
+        struct i387_fsave_struct *fp = &tsk->thread.fpu.state->fsave;
 
         fp->status = fp->swd;
         if (__copy_to_user(buf, fp, sizeof(struct i387_fsave_struct)))
@@ -512,7 +509,7 @@ static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf)
 static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
 {
         struct task_struct *tsk = current;
-        struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+        struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
         struct user_i387_ia32_struct env;
         int err = 0;
 
@@ -547,7 +544,7 @@ static int save_i387_xsave(void __user *buf)
          * header as well as change any contents in the memory layout.
          * xrestore as part of sigreturn will capture all the changes.
          */
-        tsk->thread.xstate->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
+        tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
 
         if (save_i387_fxsave(fx) < 0)
                 return -1;
@@ -599,7 +596,7 @@ static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf)
 {
         struct task_struct *tsk = current;
 
-        return __copy_from_user(&tsk->thread.xstate->fsave, buf,
+        return __copy_from_user(&tsk->thread.fpu.state->fsave, buf,
                                 sizeof(struct i387_fsave_struct));
 }
 
@@ -610,10 +607,10 @@ static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf,
         struct user_i387_ia32_struct env;
         int err;
 
-        err = __copy_from_user(&tsk->thread.xstate->fxsave, &buf->_fxsr_env[0],
+        err = __copy_from_user(&tsk->thread.fpu.state->fxsave, &buf->_fxsr_env[0],
                                size);
         /* mxcsr reserved bits must be masked to zero for security reasons */
-        tsk->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask;
+        tsk->thread.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
         if (err || __copy_from_user(&env, buf, sizeof(env)))
                 return 1;
         convert_to_fxsr(tsk, &env);
@@ -629,7 +626,7 @@ static int restore_i387_xsave(void __user *buf)
         struct i387_fxsave_struct __user *fx =
                 (struct i387_fxsave_struct __user *) &fx_user->_fxsr_env[0];
         struct xsave_hdr_struct *xsave_hdr =
-                                &current->thread.xstate->xsave.xsave_hdr;
+                                &current->thread.fpu.state->xsave.xsave_hdr;
         u64 mask;
         int err;
 
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 0ed2d300cd46..990ae7cfc578 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -60,7 +60,7 @@ 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((void __user *)get_irq_regs()->ip);
+        math_error(get_irq_regs(), 0, 16);
         return IRQ_HANDLED;
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index cc6877535ef4..e7e35219b32f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -31,24 +31,22 @@ struct kmem_cache *task_xstate_cachep;
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
+        int ret;
+
         *dst = *src;
-        if (src->thread.xstate) {
-                dst->thread.xstate = kmem_cache_alloc(task_xstate_cachep,
-                                                      GFP_KERNEL);
-                if (!dst->thread.xstate)
-                        return -ENOMEM;
-                WARN_ON((unsigned long)dst->thread.xstate & 15);
-                memcpy(dst->thread.xstate, src->thread.xstate, xstate_size);
+        if (fpu_allocated(&src->thread.fpu)) {
+                memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
+                ret = fpu_alloc(&dst->thread.fpu);
+                if (ret)
+                        return ret;
+                fpu_copy(&dst->thread.fpu, &src->thread.fpu);
         }
         return 0;
 }
 
 void free_thread_xstate(struct task_struct *tsk)
 {
-        if (tsk->thread.xstate) {
-                kmem_cache_free(task_xstate_cachep, tsk->thread.xstate);
-                tsk->thread.xstate = NULL;
-        }
+        fpu_free(&tsk->thread.fpu);
 }
 
 void free_thread_info(struct thread_info *ti)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 75090c589b7a..8d128783af47 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -309,7 +309,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
         /* we're going to use this soon, after a few expensive things */
         if (preload_fpu)
-                prefetch(next->xstate);
+                prefetch(next->fpu.state);
 
         /*
          * Reload esp0.
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 50cc84ac0a0d..3c2422a99f1f 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -388,7 +388,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
         /* we're going to use this soon, after a few expensive things */
         if (preload_fpu)
-                prefetch(next->xstate);
+                prefetch(next->fpu.state);
 
         /*
          * Reload esp0, LDT and the page table pointer:
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 36f1bd9f8e76..02cfb9b8f5b1 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -108,15 +108,6 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
         dec_preempt_count();
 }
 
-#ifdef CONFIG_X86_32
-static inline void
-die_if_kernel(const char *str, struct pt_regs *regs, long err)
-{
-        if (!user_mode_vm(regs))
-                die(str, regs, err);
-}
-#endif
-
 static void __kprobes
 do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
         long error_code, siginfo_t *info)
@@ -585,55 +576,67 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
         return;
 }
 
-#ifdef CONFIG_X86_64
-static int kernel_math_error(struct pt_regs *regs, const char *str, int trapnr)
-{
-        if (fixup_exception(regs))
-                return 1;
-
-        notify_die(DIE_GPF, str, regs, 0, trapnr, SIGFPE);
-        /* Illegal floating point operation in the kernel */
-        current->thread.trap_no = trapnr;
-        die(str, regs, 0);
-        return 0;
-}
-#endif
-
 /*
  * Note that we play around with the 'TS' bit in an attempt to get
  * the correct behaviour even in the presence of the asynchronous
  * IRQ13 behaviour
  */
-void math_error(void __user *ip)
+void math_error(struct pt_regs *regs, int error_code, int trapnr)
 {
-        struct task_struct *task;
+        struct task_struct *task = current;
         siginfo_t info;
-        unsigned short cwd, swd, err;
+        unsigned short err;
+        char *str = (trapnr == 16) ? "fpu exception" : "simd exception";
+
+        if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) == NOTIFY_STOP)
+                return;
+        conditional_sti(regs);
+
+        if (!user_mode_vm(regs))
+        {
+                if (!fixup_exception(regs)) {
+                        task->thread.error_code = error_code;
+                        task->thread.trap_no = trapnr;
+                        die(str, regs, error_code);
+                }
+                return;
+        }
 
         /*
          * Save the info for the exception handler and clear the error.
          */
-        task = current;
         save_init_fpu(task);
-        task->thread.trap_no = 16;
-        task->thread.error_code = 0;
+        task->thread.trap_no = trapnr;
+        task->thread.error_code = error_code;
         info.si_signo = SIGFPE;
         info.si_errno = 0;
-        info.si_addr = ip;
-        /*
-         * (~cwd & swd) will mask out exceptions that are not set to unmasked
-         * status.  0x3f is the exception bits in these regs, 0x200 is the
-         * C1 reg you need in case of a stack fault, 0x040 is the stack
-         * fault bit.  We should only be taking one exception at a time,
-         * so if this combination doesn't produce any single exception,
-         * then we have a bad program that isn't synchronizing its FPU usage
-         * and it will suffer the consequences since we won't be able to
-         * fully reproduce the context of the exception
-         */
-        cwd = get_fpu_cwd(task);
-        swd = get_fpu_swd(task);
+        info.si_addr = (void __user *)regs->ip;
+        if (trapnr == 16) {
+                unsigned short cwd, swd;
+                /*
+                 * (~cwd & swd) will mask out exceptions that are not set to unmasked
+                 * status.  0x3f is the exception bits in these regs, 0x200 is the
+                 * C1 reg you need in case of a stack fault, 0x040 is the stack
+                 * fault bit.  We should only be taking one exception at a time,
+                 * so if this combination doesn't produce any single exception,
+                 * then we have a bad program that isn't synchronizing its FPU usage
+                 * and it will suffer the consequences since we won't be able to
+                 * fully reproduce the context of the exception
+                 */
+                cwd = get_fpu_cwd(task);
+                swd = get_fpu_swd(task);
 
-        err = swd & ~cwd;
+                err = swd & ~cwd;
+        } else {
+                /*
+                 * The SIMD FPU exceptions are handled a little differently, as there
+                 * is only a single status/control register.  Thus, to determine which
+                 * unmasked exception was caught we must mask the exception mask bits
+                 * at 0x1f80, and then use these to mask the exception bits at 0x3f.
+                 */
+                unsigned short mxcsr = get_fpu_mxcsr(task);
+                err = ~(mxcsr >> 7) & mxcsr;
+        }
 
         if (err & 0x001) {      /* Invalid op */
                 /*
@@ -662,97 +665,17 @@ void math_error(void __user *ip)
 
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-        conditional_sti(regs);
-
 #ifdef CONFIG_X86_32
         ignore_fpu_irq = 1;
-#else
-        if (!user_mode(regs) &&
-            kernel_math_error(regs, "kernel x87 math error", 16))
-                return;
 #endif
 
-        math_error((void __user *)regs->ip);
-}
-
-static void simd_math_error(void __user *ip)
-{
-        struct task_struct *task;
-        siginfo_t info;
-        unsigned short mxcsr;
-
-        /*
-         * Save the info for the exception handler and clear the error.
-         */
-        task = current;
-        save_init_fpu(task);
-        task->thread.trap_no = 19;
-        task->thread.error_code = 0;
-        info.si_signo = SIGFPE;
-        info.si_errno = 0;
-        info.si_code = __SI_FAULT;
-        info.si_addr = ip;
-        /*
-         * The SIMD FPU exceptions are handled a little differently, as there
-         * is only a single status/control register.  Thus, to determine which
-         * unmasked exception was caught we must mask the exception mask bits
-         * at 0x1f80, and then use these to mask the exception bits at 0x3f.
-         */
-        mxcsr = get_fpu_mxcsr(task);
-        switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) {
-        case 0x000:
-        default:
-                break;
-        case 0x001: /* Invalid Op */
-                info.si_code = FPE_FLTINV;
-                break;
-        case 0x002: /* Denormalize */
-        case 0x010: /* Underflow */
-                info.si_code = FPE_FLTUND;
-                break;
-        case 0x004: /* Zero Divide */
-                info.si_code = FPE_FLTDIV;
-                break;
-        case 0x008: /* Overflow */
-                info.si_code = FPE_FLTOVF;
-                break;
-        case 0x020: /* Precision */
-                info.si_code = FPE_FLTRES;
-                break;
-        }
-        force_sig_info(SIGFPE, &info, task);
+        math_error(regs, error_code, 16);
 }
 
 dotraplinkage void
 do_simd_coprocessor_error(struct pt_regs *regs, long error_code)
 {
-        conditional_sti(regs);
-
-#ifdef CONFIG_X86_32
-        if (cpu_has_xmm) {
-                /* Handle SIMD FPU exceptions on PIII+ processors. */
-                ignore_fpu_irq = 1;
-                simd_math_error((void __user *)regs->ip);
-                return;
-        }
-        /*
-         * Handle strange cache flush from user space exception
-         * in all other cases.  This is undocumented behaviour.
-         */
-        if (regs->flags & X86_VM_MASK) {
-                handle_vm86_fault((struct kernel_vm86_regs *)regs, error_code);
-                return;
-        }
-        current->thread.trap_no = 19;
-        current->thread.error_code = error_code;
-        die_if_kernel("cache flush denied", regs, error_code);
-        force_sig(SIGSEGV, current);
-#else
-        if (!user_mode(regs) &&
-                        kernel_math_error(regs, "kernel simd math error", 19))
-                return;
-        simd_math_error((void __user *)regs->ip);
-#endif
+        math_error(regs, error_code, 19);
 }
 
 dotraplinkage void
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 782c3a362ec6..37e68fc5e24a 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -99,7 +99,7 @@ int save_i387_xstate(void __user *buf)
                 if (err)
                         return err;
 
-                if (task_thread_info(tsk)->status & TS_XSAVE)
+                if (use_xsave())
                         err = xsave_user(buf);
                 else
                         err = fxsave_user(buf);
@@ -109,14 +109,14 @@ int save_i387_xstate(void __user *buf)
                 task_thread_info(tsk)->status &= ~TS_USEDFPU;
                 stts();
         } else {
-                if (__copy_to_user(buf, &tsk->thread.xstate->fxsave,
+                if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
                                    xstate_size))
                         return -1;
         }
 
         clear_used_math(); /* trigger finit */
 
-        if (task_thread_info(tsk)->status & TS_XSAVE) {
+        if (use_xsave()) {
                 struct _fpstate __user *fx = buf;
                 struct _xstate __user *x = buf;
                 u64 xstate_bv;
@@ -225,7 +225,7 @@ int restore_i387_xstate(void __user *buf)
                 clts();
                 task_thread_info(current)->status |= TS_USEDFPU;
         }
-        if (task_thread_info(tsk)->status & TS_XSAVE)
+        if (use_xsave())
                 err = restore_user_xstate(buf);
         else
                 err = fxrstor_checking((__force struct i387_fxsave_struct *)