diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 49c5c41..c298e9d 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1837,6 +1837,12 @@
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
 
+	eagerfpu=	[X86]
+			on	enable eager fpu restore
+			off	disable eager fpu restore
+			auto	selects the default scheme, which automatically
+				enables eagerfpu restore for xsaveopt.
+
 	nohlt		[BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
 			wfi(ARM) instruction doesn't work correctly and not to
 			use it. This is also useful when using JTAG debugger.
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 05e62a3..efc6a95 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -32,6 +32,7 @@
 #include <asm/sigframe.h>
 #include <asm/sighandling.h>
 #include <asm/sys_ia32.h>
+#include <asm/smap.h>
 
 #define FIX_EFLAGS	__FIX_EFLAGS
 
@@ -162,7 +163,8 @@
 	}
 	seg = get_fs();
 	set_fs(KERNEL_DS);
-	ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss, regs->sp);
+	ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL),
+			     (stack_t __force __user *) &uoss, regs->sp);
 	set_fs(seg);
 	if (ret >= 0 && uoss_ptr)  {
 		if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(stack_ia32_t)))
@@ -254,7 +256,7 @@
 		get_user_ex(*pax, &sc->ax);
 	} get_user_catch(err);
 
-	err |= restore_i387_xstate_ia32(buf);
+	err |= restore_xstate_sig(buf, 1);
 
 	return err;
 }
@@ -362,7 +364,7 @@
  */
 static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 				 size_t frame_size,
-				 void **fpstate)
+				 void __user **fpstate)
 {
 	unsigned long sp;
 
@@ -382,9 +384,12 @@
 		sp = (unsigned long) ka->sa.sa_restorer;
 
 	if (used_math()) {
-		sp = sp - sig_xstate_ia32_size;
-		*fpstate = (struct _fpstate_ia32 *) sp;
-		if (save_i387_xstate_ia32(*fpstate) < 0)
+		unsigned long fx_aligned, math_size;
+
+		sp = alloc_mathframe(sp, 1, &fx_aligned, &math_size);
+		*fpstate = (struct _fpstate_ia32 __user *) sp;
+		if (save_xstate_sig(*fpstate, (void __user *)fx_aligned,
+				    math_size) < 0)
 			return (void __user *) -1L;
 	}
 
@@ -449,7 +454,7 @@
 		 * These are actually not used anymore, but left because some
 		 * gdb versions depend on them as a marker.
 		 */
-		put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+		put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
 	} put_user_catch(err);
 
 	if (err)
@@ -526,7 +531,7 @@
 		 * Not actually used anymore, but left because some gdb
 		 * versions need it.
 		 */
-		put_user_ex(*((u64 *)&code), (u64 *)frame->retcode);
+		put_user_ex(*((u64 *)&code), (u64 __user *)frame->retcode);
 	} put_user_catch(err);
 
 	err |= copy_siginfo_to_user32(&frame->info, info);
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 4540bec..c5b938d 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -287,7 +287,7 @@
 	return ret;
 }
 
-asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int *stat_addr,
+asmlinkage long sys32_waitpid(compat_pid_t pid, unsigned int __user *stat_addr,
 			      int options)
 {
 	return compat_sys_wait4(pid, stat_addr, options, NULL);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 633b617..16cae42 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -97,6 +97,7 @@
 #define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
 #define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
 #define X86_FEATURE_APERFMPERF	(3*32+28) /* APERFMPERF */
+#define X86_FEATURE_EAGER_FPU	(3*32+29) /* "eagerfpu" Non lazy FPU restore */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
@@ -300,12 +301,14 @@
 #define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
 #define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_xsaveopt	boot_cpu_has(X86_FEATURE_XSAVEOPT)
 #define cpu_has_osxsave		boot_cpu_has(X86_FEATURE_OSXSAVE)
 #define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 #define cpu_has_pclmulqdq	boot_cpu_has(X86_FEATURE_PCLMULQDQ)
 #define cpu_has_perfctr_core	boot_cpu_has(X86_FEATURE_PERFCTR_CORE)
 #define cpu_has_cx8		boot_cpu_has(X86_FEATURE_CX8)
 #define cpu_has_cx16		boot_cpu_has(X86_FEATURE_CX16)
+#define cpu_has_eager_fpu	boot_cpu_has(X86_FEATURE_EAGER_FPU)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 0fe1358..409b9cc 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -12,6 +12,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/regset.h>
+#include <linux/compat.h>
 #include <linux/slab.h>
 #include <asm/asm.h>
 #include <asm/cpufeature.h>
@@ -20,43 +21,76 @@
 #include <asm/user.h>
 #include <asm/uaccess.h>
 #include <asm/xsave.h>
+#include <asm/smap.h>
 
-extern unsigned int sig_xstate_size;
+#ifdef CONFIG_X86_64
+# include <asm/sigcontext32.h>
+# include <asm/user32.h>
+int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+			compat_sigset_t *set, struct pt_regs *regs);
+int ia32_setup_frame(int sig, struct k_sigaction *ka,
+		     compat_sigset_t *set, struct pt_regs *regs);
+#else
+# define user_i387_ia32_struct	user_i387_struct
+# define user32_fxsr_struct	user_fxsr_struct
+# define ia32_setup_frame	__setup_frame
+# define ia32_setup_rt_frame	__setup_rt_frame
+#endif
+
+extern unsigned int mxcsr_feature_mask;
 extern void fpu_init(void);
+extern void eager_fpu_init(void);
 
 DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
 
+extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
+			      struct task_struct *tsk);
+extern void convert_to_fxsr(struct task_struct *tsk,
+			    const struct user_i387_ia32_struct *env);
+
 extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
 				xstateregs_get;
 extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
 				 xstateregs_set;
 
-
 /*
  * xstateregs_active == fpregs_active. Please refer to the comment
  * at the definition of fpregs_active.
  */
 #define xstateregs_active	fpregs_active
 
-extern struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-extern unsigned int sig_xstate_ia32_size;
-extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
-struct _fpstate_ia32;
-struct _xstate_ia32;
-extern int save_i387_xstate_ia32(void __user *buf);
-extern int restore_i387_xstate_ia32(void __user *buf);
-#endif
-
 #ifdef CONFIG_MATH_EMULATION
+# define HAVE_HWFP		(boot_cpu_data.hard_math)
 extern void finit_soft_fpu(struct i387_soft_struct *soft);
 #else
+# define HAVE_HWFP		1
 static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
 #endif
 
+static inline int is_ia32_compat_frame(void)
+{
+	return config_enabled(CONFIG_IA32_EMULATION) &&
+	       test_thread_flag(TIF_IA32);
+}
+
+static inline int is_ia32_frame(void)
+{
+	return config_enabled(CONFIG_X86_32) || is_ia32_compat_frame();
+}
+
+static inline int is_x32_frame(void)
+{
+	return config_enabled(CONFIG_X86_X32_ABI) && test_thread_flag(TIF_X32);
+}
+
 #define X87_FSW_ES (1 << 7)	/* Exception Summary */
 
+static __always_inline __pure bool use_eager_fpu(void)
+{
+	return static_cpu_has(X86_FEATURE_EAGER_FPU);
+}
+
 static __always_inline __pure bool use_xsaveopt(void)
 {
 	return static_cpu_has(X86_FEATURE_XSAVEOPT);
@@ -72,6 +106,13 @@
         return static_cpu_has(X86_FEATURE_FXSR);
 }
 
+static inline void fx_finit(struct i387_fxsave_struct *fx)
+{
+	memset(fx, 0, xstate_size);
+	fx->cwd = 0x37f;
+	fx->mxcsr = MXCSR_DEFAULT;
+}
+
 extern void __sanitize_i387_state(struct task_struct *);
 
 static inline void sanitize_i387_state(struct task_struct *tsk)
@@ -81,133 +122,104 @@
 	__sanitize_i387_state(tsk);
 }
 
-#ifdef CONFIG_X86_64
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
-	int err;
+#define user_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:" #insn "\n\t"					\
+		     "2: " ASM_CLAC "\n"				\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
 
-	/* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
-	asm volatile("1:  fxrstorq %[fx]\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : [fx] "m" (*fx), "0" (0));
-#else
-	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : [fx] "R" (fx), "m" (*fx), "0" (0));
-#endif
-	return err;
+#define check_insn(insn, output, input...)				\
+({									\
+	int err;							\
+	asm volatile("1:" #insn "\n\t"					\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:  movl $-1,%[err]\n"				\
+		     "    jmp  2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : [err] "=r" (err), output				\
+		     : "0"(0), input);					\
+	err;								\
+})
+
+static inline int fsave_user(struct i387_fsave_struct __user *fx)
+{
+	return user_insn(fnsave %[fx]; fwait,  [fx] "=m" (*fx), "m" (*fx));
 }
 
 static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
-	int err;
+	if (config_enabled(CONFIG_X86_32))
+		return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx));
 
-	/*
-	 * Clear the bytes not touched by the fxsave and reserved
-	 * for the SW usage.
-	 */
-	err = __clear_user(&fx->sw_reserved,
-			   sizeof(struct _fpx_sw_bytes));
-	if (unlikely(err))
-		return -EFAULT;
-
-	/* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
-	asm volatile(ASM_STAC "\n"
-		     "1:  fxsaveq %[fx]\n\t"
-		     "2: " ASM_CLAC "\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), [fx] "=m" (*fx)
-		     : "0" (0));
-#else
-	asm volatile(ASM_STAC "\n"
-		     "1:  rex64/fxsave (%[fx])\n\t"
-		     "2: " ASM_CLAC "\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), "=m" (*fx)
-		     : [fx] "R" (fx), "0" (0));
-#endif
-	if (unlikely(err) &&
-	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
-		err = -EFAULT;
-	/* No need to clear here because the caller clears USED_MATH */
-	return err;
+	/* See comment in fpu_fxsave() below. */
+	return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx));
 }
 
-static inline void fpu_fxsave(struct fpu *fpu)
-{
-	/* Using "rex64; fxsave %0" is broken because, if the memory operand
-	   uses any extended registers for addressing, a second REX prefix
-	   will be generated (to the assembler, rex64 followed by semicolon
-	   is a separate instruction), and hence the 64-bitness is lost. */
-
-#ifdef CONFIG_AS_FXSAVEQ
-	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
-	   starting with gas 2.16. */
-	__asm__ __volatile__("fxsaveq %0"
-			     : "=m" (fpu->state->fxsave));
-#else
-	/* Using, as a workaround, the properly prefixed form below isn't
-	   accepted by any binutils version so far released, complaining that
-	   the same type of prefix is used twice if an extended register is
-	   needed for addressing (fix submitted to mainline 2005-11-21).
-	asm volatile("rex64/fxsave %0"
-		     : "=m" (fpu->state->fxsave));
-	   This, however, we can work around by forcing the compiler to select
-	   an addressing mode that doesn't require extended registers. */
-	asm volatile("rex64/fxsave (%[fx])"
-		     : "=m" (fpu->state->fxsave)
-		     : [fx] "R" (&fpu->state->fxsave));
-#endif
-}
-
-#else  /* CONFIG_X86_32 */
-
-/* perform fxrstor iff the processor has extended states, otherwise frstor */
 static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
-	/*
-	 * The "nop" is needed to make the instructions the same
-	 * length.
-	 */
-	alternative_input(
-		"nop ; frstor %1",
-		"fxrstor %1",
-		X86_FEATURE_FXSR,
-		"m" (*fx));
+	if (config_enabled(CONFIG_X86_32))
+		return check_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		return check_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx));
 
-	return 0;
+	/* See comment in fpu_fxsave() below. */
+	return check_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx),
+			  "m" (*fx));
+}
+
+static inline int frstor_checking(struct i387_fsave_struct *fx)
+{
+	return check_insn(frstor %[fx], "=m" (*fx), [fx] "m" (*fx));
 }
 
 static inline void fpu_fxsave(struct fpu *fpu)
 {
-	asm volatile("fxsave %[fx]"
-		     : [fx] "=m" (fpu->state->fxsave));
+	if (config_enabled(CONFIG_X86_32))
+		asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state->fxsave));
+	else if (config_enabled(CONFIG_AS_FXSAVEQ))
+		asm volatile("fxsaveq %0" : "=m" (fpu->state->fxsave));
+	else {
+		/* Using "rex64; fxsave %0" is broken because, if the memory
+		 * operand uses any extended registers for addressing, a second
+		 * REX prefix will be generated (to the assembler, rex64
+		 * followed by semicolon is a separate instruction), and hence
+		 * the 64-bitness is lost.
+		 *
+		 * Using "fxsaveq %0" would be the ideal choice, but is only
+		 * supported starting with gas 2.16.
+		 *
+		 * Using, as a workaround, the properly prefixed form below
+		 * isn't accepted by any binutils version so far released,
+		 * complaining that the same type of prefix is used twice if
+		 * an extended register is needed for addressing (fix submitted
+		 * to mainline 2005-11-21).
+		 *
+		 *  asm volatile("rex64/fxsave %0" : "=m" (fpu->state->fxsave));
+		 *
+		 * This, however, we can work around by forcing the compiler to
+		 * select an addressing mode that doesn't require extended
+		 * registers.
+		 */
+		asm volatile( "rex64/fxsave (%[fx])"
+			     : "=m" (fpu->state->fxsave)
+			     : [fx] "R" (&fpu->state->fxsave));
+	}
 }
 
-#endif	/* CONFIG_X86_64 */
-
 /*
  * These must be called with preempt disabled. Returns
  * 'true' if the FPU state is still intact.
@@ -250,17 +262,14 @@
 	return fpu_save_init(&tsk->thread.fpu);
 }
 
-static inline int fpu_fxrstor_checking(struct fpu *fpu)
-{
-	return fxrstor_checking(&fpu->state->fxsave);
-}
-
 static inline int fpu_restore_checking(struct fpu *fpu)
 {
 	if (use_xsave())
-		return fpu_xrstor_checking(fpu);
+		return fpu_xrstor_checking(&fpu->state->xsave);
+	else if (use_fxsr())
+		return fxrstor_checking(&fpu->state->fxsave);
 	else
-		return fpu_fxrstor_checking(fpu);
+		return frstor_checking(&fpu->state->fsave);
 }
 
 static inline int restore_fpu_checking(struct task_struct *tsk)
@@ -312,15 +321,52 @@
 static inline void __thread_fpu_end(struct task_struct *tsk)
 {
 	__thread_clear_has_fpu(tsk);
-	stts();
+	if (!use_eager_fpu())
+		stts();
 }
 
 static inline void __thread_fpu_begin(struct task_struct *tsk)
 {
-	clts();
+	if (!use_eager_fpu())
+		clts();
 	__thread_set_has_fpu(tsk);
 }
 
+static inline void __drop_fpu(struct task_struct *tsk)
+{
+	if (__thread_has_fpu(tsk)) {
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		__thread_fpu_end(tsk);
+	}
+}
+
+static inline void drop_fpu(struct task_struct *tsk)
+{
+	/*
+	 * Forget coprocessor state..
+	 */
+	preempt_disable();
+	tsk->fpu_counter = 0;
+	__drop_fpu(tsk);
+	clear_used_math();
+	preempt_enable();
+}
+
+static inline void drop_init_fpu(struct task_struct *tsk)
+{
+	if (!use_eager_fpu())
+		drop_fpu(tsk);
+	else {
+		if (use_xsave())
+			xrstor_state(init_xstate_buf, -1);
+		else
+			fxrstor_checking(&init_xstate_buf->i387);
+	}
+}
+
 /*
  * FPU state switching for scheduling.
  *
@@ -354,7 +400,12 @@
 {
 	fpu_switch_t fpu;
 
-	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+	/*
+	 * If the task has used the math, pre-load the FPU on xsave processors
+	 * or if the past 5 consecutive context-switches used math.
+	 */
+	fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
+					     new->fpu_counter > 5);
 	if (__thread_has_fpu(old)) {
 		if (!__save_init_fpu(old))
 			cpu = ~0;
@@ -366,14 +417,14 @@
 			new->fpu_counter++;
 			__thread_set_has_fpu(new);
 			prefetch(new->thread.fpu.state);
-		} else
+		} else if (!use_eager_fpu())
 			stts();
 	} else {
 		old->fpu_counter = 0;
 		old->thread.fpu.last_cpu = ~0;
 		if (fpu.preload) {
 			new->fpu_counter++;
-			if (fpu_lazy_restore(new, cpu))
+			if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else
 				prefetch(new->thread.fpu.state);
@@ -393,44 +444,40 @@
 {
 	if (fpu.preload) {
 		if (unlikely(restore_fpu_checking(new)))
-			__thread_fpu_end(new);
+			drop_init_fpu(new);
 	}
 }
 
 /*
  * Signal frame handlers...
  */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+extern int save_xstate_sig(void __user *buf, void __user *fx, int size);
+extern int __restore_xstate_sig(void __user *buf, void __user *fx, int size);
 
-static inline void __clear_fpu(struct task_struct *tsk)
+static inline int xstate_sigframe_size(void)
 {
-	if (__thread_has_fpu(tsk)) {
-		/* Ignore delayed exceptions from user space */
-		asm volatile("1: fwait\n"
-			     "2:\n"
-			     _ASM_EXTABLE(1b, 2b));
-		__thread_fpu_end(tsk);
+	return use_xsave() ? xstate_size + FP_XSTATE_MAGIC2_SIZE : xstate_size;
+}
+
+static inline int restore_xstate_sig(void __user *buf, int ia32_frame)
+{
+	void __user *buf_fx = buf;
+	int size = xstate_sigframe_size();
+
+	if (ia32_frame && use_fxsr()) {
+		buf_fx = buf + sizeof(struct i387_fsave_struct);
+		size += sizeof(struct i387_fsave_struct);
 	}
+
+	return __restore_xstate_sig(buf, buf_fx, size);
 }
 
 /*
- * The actual user_fpu_begin/end() functions
- * need to be preemption-safe.
+ * Need to be preemption-safe.
  *
- * NOTE! user_fpu_end() must be used only after you
- * have saved the FP state, and user_fpu_begin() must
- * be used only immediately before restoring it.
- * These functions do not do any save/restore on
- * their own.
+ * NOTE! user_fpu_begin() must be used only immediately before restoring
+ * it. This function does not do any save/restore on their own.
  */
-static inline void user_fpu_end(void)
-{
-	preempt_disable();
-	__thread_fpu_end(current);
-	preempt_enable();
-}
-
 static inline void user_fpu_begin(void)
 {
 	preempt_disable();
@@ -439,25 +486,32 @@
 	preempt_enable();
 }
 
+static inline void __save_fpu(struct task_struct *tsk)
+{
+	if (use_xsave())
+		xsave_state(&tsk->thread.fpu.state->xsave, -1);
+	else
+		fpu_fxsave(&tsk->thread.fpu);
+}
+
 /*
  * These disable preemption on their own and are safe
  */
 static inline void save_init_fpu(struct task_struct *tsk)
 {
 	WARN_ON_ONCE(!__thread_has_fpu(tsk));
+
+	if (use_eager_fpu()) {
+		__save_fpu(tsk);
+		return;
+	}
+
 	preempt_disable();
 	__save_init_fpu(tsk);
 	__thread_fpu_end(tsk);
 	preempt_enable();
 }
 
-static inline void clear_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	__clear_fpu(tsk);
-	preempt_enable();
-}
-
 /*
  * i387 state interaction
  */
@@ -512,11 +566,34 @@
 	}
 }
 
-static inline void fpu_copy(struct fpu *dst, struct fpu *src)
+static inline void fpu_copy(struct task_struct *dst, struct task_struct *src)
 {
-	memcpy(dst->state, src->state, xstate_size);
+	if (use_eager_fpu()) {
+		memset(&dst->thread.fpu.state->xsave, 0, xstate_size);
+		__save_fpu(dst);
+	} else {
+		struct fpu *dfpu = &dst->thread.fpu;
+		struct fpu *sfpu = &src->thread.fpu;
+
+		unlazy_fpu(src);
+		memcpy(dfpu->state, sfpu->state, xstate_size);
+	}
 }
 
-extern void fpu_finit(struct fpu *fpu);
+static inline unsigned long
+alloc_mathframe(unsigned long sp, int ia32_frame, unsigned long *buf_fx,
+		unsigned long *size)
+{
+	unsigned long frame_size = xstate_sigframe_size();
+
+	*buf_fx = sp = round_down(sp - frame_size, 64);
+	if (ia32_frame && use_fxsr()) {
+		frame_size += sizeof(struct i387_fsave_struct);
+		sp -= sizeof(struct i387_fsave_struct);
+	}
+
+	*size = frame_size;
+	return sp;
+}
 
 #endif
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 257d9cc..ed8089d6 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -19,12 +19,37 @@
 struct user_i387_struct;
 
 extern int init_fpu(struct task_struct *child);
+extern void fpu_finit(struct fpu *fpu);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 extern void math_state_restore(void);
 
 extern bool irq_fpu_usable(void);
-extern void kernel_fpu_begin(void);
-extern void kernel_fpu_end(void);
+
+/*
+ * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
+ * and they don't touch the preempt state on their own.
+ * If you enable preemption after __kernel_fpu_begin(), preempt notifier
+ * should call the __kernel_fpu_end() to prevent the kernel/user FPU
+ * state from getting corrupted. KVM for example uses this model.
+ *
+ * All other cases use kernel_fpu_begin/end() which disable preemption
+ * during kernel FPU usage.
+ */
+extern void __kernel_fpu_begin(void);
+extern void __kernel_fpu_end(void);
+
+static inline void kernel_fpu_begin(void)
+{
+	WARN_ON_ONCE(!irq_fpu_usable());
+	preempt_disable();
+	__kernel_fpu_begin();
+}
+
+static inline void kernel_fpu_end(void)
+{
+	__kernel_fpu_end();
+	preempt_enable();
+}
 
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
diff --git a/arch/x86/include/asm/iommu_table.h b/arch/x86/include/asm/iommu_table.h
index f229b13..f42a047 100644
--- a/arch/x86/include/asm/iommu_table.h
+++ b/arch/x86/include/asm/iommu_table.h
@@ -48,7 +48,7 @@
 
 
 #define __IOMMU_INIT(_detect, _depend, _early_init, _late_init, _finish)\
-	static const struct iommu_table_entry const			\
+	static const struct iommu_table_entry				\
 		__iommu_entry_##_detect __used				\
 	__attribute__ ((unused, __section__(".iommu_table"),		\
 			aligned((sizeof(void *)))))	\
@@ -63,10 +63,10 @@
  * to stop detecting the other IOMMUs after yours has been detected.
  */
 #define IOMMU_INIT_POST(_detect)					\
-	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 0)
+	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  NULL, NULL, 0)
 
 #define IOMMU_INIT_POST_FINISH(detect)					\
-	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  0, 0, 1)
+	__IOMMU_INIT(_detect, pci_swiotlb_detect_4gb,  NULL, NULL, 1)
 
 /*
  * A more sophisticated version of IOMMU_INIT. This variant requires:
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 598457c..323973f 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -31,6 +31,10 @@
 	unsigned long sig[_NSIG_WORDS];
 } sigset_t;
 
+#ifndef CONFIG_COMPAT
+typedef sigset_t compat_sigset_t;
+#endif
+
 #else
 /* Here we must cater to libcs that poke about in kernel headers.  */
 
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 3fda9db4..4ca1c61 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -40,7 +40,7 @@
 				struct old_sigaction32 __user *);
 asmlinkage long sys32_alarm(unsigned int);
 
-asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int);
+asmlinkage long sys32_waitpid(compat_pid_t, unsigned int __user *, int);
 asmlinkage long sys32_sysfs(int, u32, u32);
 
 asmlinkage long sys32_sched_rr_get_interval(compat_pid_t,
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index bb05228..fddb53d 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -11,7 +11,8 @@
 #define VDSO32_SYMBOL(base, name)					\
 ({									\
 	extern const char VDSO32_##name[];				\
-	(void *)(VDSO32_##name - VDSO32_PRELINK + (unsigned long)(base)); \
+	(void __user *)(VDSO32_##name - VDSO32_PRELINK +		\
+			(unsigned long)(base));				\
 })
 #endif
 
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
index 4545708..aabd585 100644
--- a/arch/x86/include/asm/xor_32.h
+++ b/arch/x86/include/asm/xor_32.h
@@ -534,38 +534,6 @@
  * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
  */
 
-#define XMMS_SAVE				\
-do {						\
-	preempt_disable();			\
-	cr0 = read_cr0();			\
-	clts();					\
-	asm volatile(				\
-		"movups %%xmm0,(%0)	;\n\t"	\
-		"movups %%xmm1,0x10(%0)	;\n\t"	\
-		"movups %%xmm2,0x20(%0)	;\n\t"	\
-		"movups %%xmm3,0x30(%0)	;\n\t"	\
-		:				\
-		: "r" (xmm_save) 		\
-		: "memory");			\
-} while (0)
-
-#define XMMS_RESTORE				\
-do {						\
-	asm volatile(				\
-		"sfence			;\n\t"	\
-		"movups (%0),%%xmm0	;\n\t"	\
-		"movups 0x10(%0),%%xmm1	;\n\t"	\
-		"movups 0x20(%0),%%xmm2	;\n\t"	\
-		"movups 0x30(%0),%%xmm3	;\n\t"	\
-		:				\
-		: "r" (xmm_save)		\
-		: "memory");			\
-	write_cr0(cr0);				\
-	preempt_enable();			\
-} while (0)
-
-#define ALIGN16 __attribute__((aligned(16)))
-
 #define OFFS(x)		"16*("#x")"
 #define PF_OFFS(x)	"256+16*("#x")"
 #define	PF0(x)		"	prefetchnta "PF_OFFS(x)"(%1)		;\n"
@@ -587,10 +555,8 @@
 xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -633,7 +599,7 @@
 	:
 	: "memory");
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -641,10 +607,8 @@
 	  unsigned long *p3)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -694,7 +658,7 @@
 	:
 	: "memory" );
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -702,10 +666,8 @@
 	  unsigned long *p3, unsigned long *p4)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -762,7 +724,7 @@
 	:
 	: "memory" );
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -770,10 +732,8 @@
 	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
 {
 	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	/* Make sure GCC forgets anything it knows about p4 or p5,
 	   such that it won't pass to the asm volatile below a
@@ -850,7 +810,7 @@
 	   like assuming they have some legal value.  */
 	asm("" : "=r" (p4), "=r" (p5));
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static struct xor_block_template xor_block_pIII_sse = {
diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h
index b9b2323..5fc06d0 100644
--- a/arch/x86/include/asm/xor_64.h
+++ b/arch/x86/include/asm/xor_64.h
@@ -34,41 +34,7 @@
  * no advantages to be gotten from x86-64 here anyways.
  */
 
-typedef struct {
-	unsigned long a, b;
-} __attribute__((aligned(16))) xmm_store_t;
-
-/* Doesn't use gcc to save the XMM registers, because there is no easy way to
-   tell it to do a clts before the register saving. */
-#define XMMS_SAVE				\
-do {						\
-	preempt_disable();			\
-	asm volatile(				\
-		"movq %%cr0,%0		;\n\t"	\
-		"clts			;\n\t"	\
-		"movups %%xmm0,(%1)	;\n\t"	\
-		"movups %%xmm1,0x10(%1)	;\n\t"	\
-		"movups %%xmm2,0x20(%1)	;\n\t"	\
-		"movups %%xmm3,0x30(%1)	;\n\t"	\
-		: "=&r" (cr0)			\
-		: "r" (xmm_save) 		\
-		: "memory");			\
-} while (0)
-
-#define XMMS_RESTORE				\
-do {						\
-	asm volatile(				\
-		"sfence			;\n\t"	\
-		"movups (%1),%%xmm0	;\n\t"	\
-		"movups 0x10(%1),%%xmm1	;\n\t"	\
-		"movups 0x20(%1),%%xmm2	;\n\t"	\
-		"movups 0x30(%1),%%xmm3	;\n\t"	\
-		"movq 	%0,%%cr0	;\n\t"	\
-		:				\
-		: "r" (cr0), "r" (xmm_save)	\
-		: "memory");			\
-	preempt_enable();			\
-} while (0)
+#include <asm/i387.h>
 
 #define OFFS(x)		"16*("#x")"
 #define PF_OFFS(x)	"256+16*("#x")"
@@ -91,10 +57,8 @@
 xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
 {
 	unsigned int lines = bytes >> 8;
-	unsigned long cr0;
-	xmm_store_t xmm_save[4];
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -135,7 +99,7 @@
 	: [inc] "r" (256UL)
 	: "memory");
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -143,11 +107,8 @@
 	  unsigned long *p3)
 {
 	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
 
-	XMMS_SAVE;
-
+	kernel_fpu_begin();
 	asm volatile(
 #undef BLOCK
 #define BLOCK(i) \
@@ -194,7 +155,7 @@
 	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
 	: [inc] "r" (256UL)
 	: "memory");
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -202,10 +163,8 @@
 	  unsigned long *p3, unsigned long *p4)
 {
 	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -261,7 +220,7 @@
 	: [inc] "r" (256UL)
 	: "memory" );
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static void
@@ -269,10 +228,8 @@
 	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
 {
 	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
 
-	XMMS_SAVE;
+	kernel_fpu_begin();
 
 	asm volatile(
 #undef BLOCK
@@ -336,7 +293,7 @@
 	: [inc] "r" (256UL)
 	: "memory");
 
-	XMMS_RESTORE;
+	kernel_fpu_end();
 }
 
 static struct xor_block_template xor_block_sse = {
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 2510d35..7ea79c5 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -20,32 +20,6 @@
 #include <linux/compiler.h>
 #include <asm/i387.h>
 
-#define ALIGN32 __aligned(32)
-
-#define YMM_SAVED_REGS 4
-
-#define YMMS_SAVE \
-do { \
-	preempt_disable(); \
-	cr0 = read_cr0(); \
-	clts(); \
-	asm volatile("vmovaps %%ymm0, %0" : "=m" (ymm_save[0]) : : "memory"); \
-	asm volatile("vmovaps %%ymm1, %0" : "=m" (ymm_save[32]) : : "memory"); \
-	asm volatile("vmovaps %%ymm2, %0" : "=m" (ymm_save[64]) : : "memory"); \
-	asm volatile("vmovaps %%ymm3, %0" : "=m" (ymm_save[96]) : : "memory"); \
-} while (0);
-
-#define YMMS_RESTORE \
-do { \
-	asm volatile("sfence" : : : "memory"); \
-	asm volatile("vmovaps %0, %%ymm3" : : "m" (ymm_save[96])); \
-	asm volatile("vmovaps %0, %%ymm2" : : "m" (ymm_save[64])); \
-	asm volatile("vmovaps %0, %%ymm1" : : "m" (ymm_save[32])); \
-	asm volatile("vmovaps %0, %%ymm0" : : "m" (ymm_save[0])); \
-	write_cr0(cr0); \
-	preempt_enable(); \
-} while (0);
-
 #define BLOCK4(i) \
 		BLOCK(32 * i, 0) \
 		BLOCK(32 * (i + 1), 1) \
@@ -60,10 +34,9 @@
 
 static void xor_avx_2(unsigned long bytes, unsigned long *p0, unsigned long *p1)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -82,16 +55,15 @@
 		p1 = (unsigned long *)((uintptr_t)p1 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static void xor_avx_3(unsigned long bytes, unsigned long *p0, unsigned long *p1,
 	unsigned long *p2)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -113,16 +85,15 @@
 		p2 = (unsigned long *)((uintptr_t)p2 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static void xor_avx_4(unsigned long bytes, unsigned long *p0, unsigned long *p1,
 	unsigned long *p2, unsigned long *p3)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -147,16 +118,15 @@
 		p3 = (unsigned long *)((uintptr_t)p3 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static void xor_avx_5(unsigned long bytes, unsigned long *p0, unsigned long *p1,
 	unsigned long *p2, unsigned long *p3, unsigned long *p4)
 {
-	unsigned long cr0, lines = bytes >> 9;
-	char ymm_save[32 * YMM_SAVED_REGS] ALIGN32;
+	unsigned long lines = bytes >> 9;
 
-	YMMS_SAVE
+	kernel_fpu_begin();
 
 	while (lines--) {
 #undef BLOCK
@@ -184,7 +154,7 @@
 		p4 = (unsigned long *)((uintptr_t)p4 + 512);
 	}
 
-	YMMS_RESTORE
+	kernel_fpu_end();
 }
 
 static struct xor_block_template xor_block_avx = {
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 2a923bd..0415cda 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -34,17 +34,14 @@
 extern unsigned int xstate_size;
 extern u64 pcntxt_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
+extern struct xsave_struct *init_xstate_buf;
 
 extern void xsave_init(void);
 extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 extern int init_fpu(struct task_struct *child);
-extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
-			    void __user *fpstate,
-			    struct _fpx_sw_bytes *sw);
 
-static inline int fpu_xrstor_checking(struct fpu *fpu)
+static inline int fpu_xrstor_checking(struct xsave_struct *fx)
 {
-	struct xsave_struct *fx = &fpu->state->xsave;
 	int err;
 
 	asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
@@ -69,8 +66,7 @@
 	 * Clear the xsave header first, so that reserved fields are
 	 * initialized to zero.
 	 */
-	err = __clear_user(&buf->xsave_hdr,
-			   sizeof(struct xsave_hdr_struct));
+	err = __clear_user(&buf->xsave_hdr, sizeof(buf->xsave_hdr));
 	if (unlikely(err))
 		return -EFAULT;
 
@@ -85,9 +81,6 @@
 			     : [err] "=r" (err)
 			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
 			     : "memory");
-	if (unlikely(err) && __clear_user(buf, xstate_size))
-		err = -EFAULT;
-	/* No need to clear here because the caller clears USED_MATH */
 	return err;
 }
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index c97bb7b..d0e910d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -165,10 +165,15 @@
 	print_cpu_info(&boot_cpu_data);
 #endif
 	check_config();
-	check_fpu();
 	check_hlt();
 	check_popad();
 	init_utsname()->machine[1] =
 		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions();
+
+	/*
+	 * kernel_fpu_begin/end() in check_fpu() relies on the patched
+	 * alternative instructions.
+	 */
+	check_fpu();
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7d35d65..44aec5d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1324,7 +1324,6 @@
 	dbg_restore_debug_regs();
 
 	fpu_init();
-	xsave_init();
 
 	raw_local_save_flags(kernel_eflags);
 
@@ -1379,6 +1378,5 @@
 	dbg_restore_debug_regs();
 
 	fpu_init();
-	xsave_init();
 }
 #endif
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index f250431..675a050 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -19,24 +19,17 @@
 #include <asm/fpu-internal.h>
 #include <asm/user.h>
 
-#ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
-# include <asm/user32.h>
-#else
-# define save_i387_xstate_ia32		save_i387_xstate
-# define restore_i387_xstate_ia32	restore_i387_xstate
-# define _fpstate_ia32		_fpstate
-# define _xstate_ia32		_xstate
-# define sig_xstate_ia32_size   sig_xstate_size
-# define fx_sw_reserved_ia32	fx_sw_reserved
-# define user_i387_ia32_struct	user_i387_struct
-# define user32_fxsr_struct	user_fxsr_struct
-#endif
-
 /*
  * Were we in an interrupt that interrupted kernel mode?
  *
- * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * For now, with eagerfpu we will return interrupted kernel FPU
+ * state as not-idle. TBD: Ideally we can change the return value
+ * to something like __thread_has_fpu(current). But we need to
+ * be careful of doing __thread_clear_has_fpu() before saving
+ * the FPU etc for supporting nested uses etc. For now, take
+ * the simple route!
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
  * pair does nothing at all: the thread must not have fpu (so
  * that we don't try to save the FPU state), and TS must
  * be set (so that the clts/stts pair does nothing that is
@@ -44,6 +37,9 @@
  */
 static inline bool interrupted_kernel_fpu_idle(void)
 {
+	if (use_eager_fpu())
+		return 0;
+
 	return !__thread_has_fpu(current) &&
 		(read_cr0() & X86_CR0_TS);
 }
@@ -77,29 +73,29 @@
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
-void kernel_fpu_begin(void)
+void __kernel_fpu_begin(void)
 {
 	struct task_struct *me = current;
 
-	WARN_ON_ONCE(!irq_fpu_usable());
-	preempt_disable();
 	if (__thread_has_fpu(me)) {
 		__save_init_fpu(me);
 		__thread_clear_has_fpu(me);
-		/* We do 'stts()' in kernel_fpu_end() */
-	} else {
+		/* We do 'stts()' in __kernel_fpu_end() */
+	} else if (!use_eager_fpu()) {
 		this_cpu_write(fpu_owner_task, NULL);
 		clts();
 	}
 }
-EXPORT_SYMBOL(kernel_fpu_begin);
+EXPORT_SYMBOL(__kernel_fpu_begin);
 
-void kernel_fpu_end(void)
+void __kernel_fpu_end(void)
 {
-	stts();
-	preempt_enable();
+	if (use_eager_fpu())
+		math_state_restore();
+	else
+		stts();
 }
-EXPORT_SYMBOL(kernel_fpu_end);
+EXPORT_SYMBOL(__kernel_fpu_end);
 
 void unlazy_fpu(struct task_struct *tsk)
 {
@@ -113,23 +109,15 @@
 }
 EXPORT_SYMBOL(unlazy_fpu);
 
-#ifdef CONFIG_MATH_EMULATION
-# define HAVE_HWFP		(boot_cpu_data.hard_math)
-#else
-# define HAVE_HWFP		1
-#endif
-
-static unsigned int		mxcsr_feature_mask __read_mostly = 0xffffffffu;
+unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
-unsigned int sig_xstate_ia32_size = sizeof(struct _fpstate_ia32);
 static struct i387_fxsave_struct fx_scratch __cpuinitdata;
 
 static void __cpuinit mxcsr_feature_mask_init(void)
 {
 	unsigned long mask = 0;
 
-	clts();
 	if (cpu_has_fxsr) {
 		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
 		asm volatile("fxsave %0" : : "m" (fx_scratch));
@@ -138,7 +126,6 @@
 			mask = 0x0000ffbf;
 	}
 	mxcsr_feature_mask &= mask;
-	stts();
 }
 
 static void __cpuinit init_thread_xstate(void)
@@ -192,9 +179,8 @@
 		init_thread_xstate();
 
 	mxcsr_feature_mask_init();
-	/* clean state in init */
-	current_thread_info()->status = 0;
-	clear_used_math();
+	xsave_init();
+	eager_fpu_init();
 }
 
 void fpu_finit(struct fpu *fpu)
@@ -205,12 +191,7 @@
 	}
 
 	if (cpu_has_fxsr) {
-		struct i387_fxsave_struct *fx = &fpu->state->fxsave;
-
-		memset(fx, 0, xstate_size);
-		fx->cwd = 0x37f;
-		if (cpu_has_xmm)
-			fx->mxcsr = MXCSR_DEFAULT;
+		fx_finit(&fpu->state->fxsave);
 	} else {
 		struct i387_fsave_struct *fp = &fpu->state->fsave;
 		memset(fp, 0, xstate_size);
@@ -454,7 +435,7 @@
  * FXSR floating point environment conversions.
  */
 
-static void
+void
 convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
 {
 	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -491,8 +472,8 @@
 		memcpy(&to[i], &from[i], sizeof(to[0]));
 }
 
-static void convert_to_fxsr(struct task_struct *tsk,
-			    const struct user_i387_ia32_struct *env)
+void convert_to_fxsr(struct task_struct *tsk,
+		     const struct user_i387_ia32_struct *env)
 
 {
 	struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave;
@@ -589,223 +570,6 @@
 }
 
 /*
- * Signal frame handlers.
- */
-
-static inline int save_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
-	struct task_struct *tsk = current;
-	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)))
-		return -1;
-	return 1;
-}
-
-static int save_i387_fxsave(struct _fpstate_ia32 __user *buf)
-{
-	struct task_struct *tsk = current;
-	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
-	struct user_i387_ia32_struct env;
-	int err = 0;
-
-	convert_from_fxsr(&env, tsk);
-	if (__copy_to_user(buf, &env, sizeof(env)))
-		return -1;
-
-	err |= __put_user(fx->swd, &buf->status);
-	err |= __put_user(X86_FXSR_MAGIC, &buf->magic);
-	if (err)
-		return -1;
-
-	if (__copy_to_user(&buf->_fxsr_env[0], fx, xstate_size))
-		return -1;
-	return 1;
-}
-
-static int save_i387_xsave(void __user *buf)
-{
-	struct task_struct *tsk = current;
-	struct _fpstate_ia32 __user *fx = buf;
-	int err = 0;
-
-
-	sanitize_i387_state(tsk);
-
-	/*
-	 * For legacy compatible, we always set FP/SSE bits in the bit
-	 * vector while saving the state to the user context.
-	 * This will enable us capturing any changes(during sigreturn) to
-	 * the FP/SSE bits by the legacy applications which don't touch
-	 * xstate_bv in the xsave header.
-	 *
-	 * xsave aware applications can change the xstate_bv in the xsave
-	 * header as well as change any contents in the memory layout.
-	 * xrestore as part of sigreturn will capture all the changes.
-	 */
-	tsk->thread.fpu.state->xsave.xsave_hdr.xstate_bv |= XSTATE_FPSSE;
-
-	if (save_i387_fxsave(fx) < 0)
-		return -1;
-
-	err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved_ia32,
-			     sizeof(struct _fpx_sw_bytes));
-	err |= __put_user(FP_XSTATE_MAGIC2,
-			  (__u32 __user *) (buf + sig_xstate_ia32_size
-					    - FP_XSTATE_MAGIC2_SIZE));
-	if (err)
-		return -1;
-
-	return 1;
-}
-
-int save_i387_xstate_ia32(void __user *buf)
-{
-	struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
-	struct task_struct *tsk = current;
-
-	if (!used_math())
-		return 0;
-
-	if (!access_ok(VERIFY_WRITE, buf, sig_xstate_ia32_size))
-		return -EACCES;
-	/*
-	 * This will cause a "finit" to be triggered by the next
-	 * attempted FPU operation by the 'current' process.
-	 */
-	clear_used_math();
-
-	if (!HAVE_HWFP) {
-		return fpregs_soft_get(current, NULL,
-				       0, sizeof(struct user_i387_ia32_struct),
-				       NULL, fp) ? -1 : 1;
-	}
-
-	unlazy_fpu(tsk);
-
-	if (cpu_has_xsave)
-		return save_i387_xsave(fp);
-	if (cpu_has_fxsr)
-		return save_i387_fxsave(fp);
-	else
-		return save_i387_fsave(fp);
-}
-
-static inline int restore_i387_fsave(struct _fpstate_ia32 __user *buf)
-{
-	struct task_struct *tsk = current;
-
-	return __copy_from_user(&tsk->thread.fpu.state->fsave, buf,
-				sizeof(struct i387_fsave_struct));
-}
-
-static int restore_i387_fxsave(struct _fpstate_ia32 __user *buf,
-			       unsigned int size)
-{
-	struct task_struct *tsk = current;
-	struct user_i387_ia32_struct env;
-	int err;
-
-	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.fpu.state->fxsave.mxcsr &= mxcsr_feature_mask;
-	if (err || __copy_from_user(&env, buf, sizeof(env)))
-		return 1;
-	convert_to_fxsr(tsk, &env);
-
-	return 0;
-}
-
-static int restore_i387_xsave(void __user *buf)
-{
-	struct _fpx_sw_bytes fx_sw_user;
-	struct _fpstate_ia32 __user *fx_user =
-			((struct _fpstate_ia32 __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.fpu.state->xsave.xsave_hdr;
-	u64 mask;
-	int err;
-
-	if (check_for_xstate(fx, buf, &fx_sw_user))
-		goto fx_only;
-
-	mask = fx_sw_user.xstate_bv;
-
-	err = restore_i387_fxsave(buf, fx_sw_user.xstate_size);
-
-	xsave_hdr->xstate_bv &= pcntxt_mask;
-	/*
-	 * These bits must be zero.
-	 */
-	xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
-
-	/*
-	 * Init the state that is not present in the memory layout
-	 * and enabled by the OS.
-	 */
-	mask = ~(pcntxt_mask & ~mask);
-	xsave_hdr->xstate_bv &= mask;
-
-	return err;
-fx_only:
-	/*
-	 * Couldn't find the extended state information in the memory
-	 * layout. Restore the FP/SSE and init the other extended state
-	 * enabled by the OS.
-	 */
-	xsave_hdr->xstate_bv = XSTATE_FPSSE;
-	return restore_i387_fxsave(buf, sizeof(struct i387_fxsave_struct));
-}
-
-int restore_i387_xstate_ia32(void __user *buf)
-{
-	int err;
-	struct task_struct *tsk = current;
-	struct _fpstate_ia32 __user *fp = (struct _fpstate_ia32 __user *) buf;
-
-	if (HAVE_HWFP)
-		clear_fpu(tsk);
-
-	if (!buf) {
-		if (used_math()) {
-			clear_fpu(tsk);
-			clear_used_math();
-		}
-
-		return 0;
-	} else
-		if (!access_ok(VERIFY_READ, buf, sig_xstate_ia32_size))
-			return -EACCES;
-
-	if (!used_math()) {
-		err = init_fpu(tsk);
-		if (err)
-			return err;
-	}
-
-	if (HAVE_HWFP) {
-		if (cpu_has_xsave)
-			err = restore_i387_xsave(buf);
-		else if (cpu_has_fxsr)
-			err = restore_i387_fxsave(fp, sizeof(struct
-							   i387_fxsave_struct));
-		else
-			err = restore_i387_fsave(fp);
-	} else {
-		err = fpregs_soft_set(current, NULL,
-				      0, sizeof(struct user_i387_ia32_struct),
-				      NULL, fp) != 0;
-	}
-	set_used_math();
-
-	return err;
-}
-
-/*
  * FPU state for core dumps.
  * This is only used for a.out dumps now.
  * It is declared generically using elf_fpregset_t (which is
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
index 0bc72e2..d5f15c3 100644
--- a/arch/x86/kernel/probe_roms.c
+++ b/arch/x86/kernel/probe_roms.c
@@ -150,7 +150,7 @@
 	return oprom;
 }
 
-void *pci_map_biosrom(struct pci_dev *pdev)
+void __iomem *pci_map_biosrom(struct pci_dev *pdev)
 {
 	struct resource *oprom = find_oprom(pdev);
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ef6a845..dc3567e 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -66,15 +66,13 @@
 {
 	int ret;
 
-	unlazy_fpu(src);
-
 	*dst = *src;
 	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);
+		fpu_copy(dst, src);
 	}
 	return 0;
 }
@@ -97,16 +95,6 @@
 				  SLAB_PANIC | SLAB_NOTRACK, NULL);
 }
 
-static inline void drop_fpu(struct task_struct *tsk)
-{
-	/*
-	 * Forget coprocessor state..
-	 */
-	tsk->fpu_counter = 0;
-	clear_fpu(tsk);
-	clear_used_math();
-}
-
 /*
  * Free current thread data structures etc..
  */
@@ -163,7 +151,13 @@
 
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
-	drop_fpu(tsk);
+	drop_init_fpu(tsk);
+	/*
+	 * Free the FPU state for non xsave platforms. They get reallocated
+	 * lazily at the first use.
+	 */
+	if (!use_eager_fpu())
+		free_thread_xstate(tsk);
 }
 
 static void hard_disable_TSC(void)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 516fa18..b9ff83c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -190,10 +190,6 @@
 	regs->cs		= __USER_CS;
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
-	/*
-	 * Free the old FP and other extended state
-	 */
-	free_thread_xstate(current);
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 0a980c9..8a6d20c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -232,10 +232,6 @@
 	regs->cs		= _cs;
 	regs->ss		= _ss;
 	regs->flags		= X86_EFLAGS_IF;
-	/*
-	 * Free the old FP and other extended state
-	 */
-	free_thread_xstate(current);
 }
 
 void
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index c4c6a5c..861a9d1 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1332,9 +1332,6 @@
 #define genregs32_get		genregs_get
 #define genregs32_set		genregs_set
 
-#define user_i387_ia32_struct	user_i387_struct
-#define user32_fxsr_struct	user_fxsr_struct
-
 #endif	/* CONFIG_X86_64 */
 
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 9326128..036bddb 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -118,7 +118,7 @@
 		get_user_ex(*pax, &sc->ax);
 	} get_user_catch(err);
 
-	err |= restore_i387_xstate(buf);
+	err |= restore_xstate_sig(buf, config_enabled(CONFIG_X86_32));
 
 	return err;
 }
@@ -207,35 +207,32 @@
 	     void __user **fpstate)
 {
 	/* Default to using normal stack */
+	unsigned long math_size = 0;
 	unsigned long sp = regs->sp;
+	unsigned long buf_fx = 0;
 	int onsigstack = on_sig_stack(sp);
 
-#ifdef CONFIG_X86_64
 	/* redzone */
-	sp -= 128;
-#endif /* CONFIG_X86_64 */
+	if (config_enabled(CONFIG_X86_64))
+		sp -= 128;
 
 	if (!onsigstack) {
 		/* This is the X/Open sanctioned signal stack switching.  */
 		if (ka->sa.sa_flags & SA_ONSTACK) {
 			if (current->sas_ss_size)
 				sp = current->sas_ss_sp + current->sas_ss_size;
-		} else {
-#ifdef CONFIG_X86_32
-			/* This is the legacy signal stack switching. */
-			if ((regs->ss & 0xffff) != __USER_DS &&
-				!(ka->sa.sa_flags & SA_RESTORER) &&
-					ka->sa.sa_restorer)
+		} else if (config_enabled(CONFIG_X86_32) &&
+			   (regs->ss & 0xffff) != __USER_DS &&
+			   !(ka->sa.sa_flags & SA_RESTORER) &&
+			   ka->sa.sa_restorer) {
+				/* This is the legacy signal stack switching. */
 				sp = (unsigned long) ka->sa.sa_restorer;
-#endif /* CONFIG_X86_32 */
 		}
 	}
 
 	if (used_math()) {
-		sp -= sig_xstate_size;
-#ifdef CONFIG_X86_64
-		sp = round_down(sp, 64);
-#endif /* CONFIG_X86_64 */
+		sp = alloc_mathframe(sp, config_enabled(CONFIG_X86_32),
+				     &buf_fx, &math_size);
 		*fpstate = (void __user *)sp;
 	}
 
@@ -248,8 +245,9 @@
 	if (onsigstack && !likely(on_sig_stack(sp)))
 		return (void __user *)-1L;
 
-	/* save i387 state */
-	if (used_math() && save_i387_xstate(*fpstate) < 0)
+	/* save i387 and extended state */
+	if (used_math() &&
+	    save_xstate_sig(*fpstate, (void __user *)buf_fx, math_size) < 0)
 		return (void __user *)-1L;
 
 	return (void __user *)sp;
@@ -385,7 +383,7 @@
 		 */
 		put_user_ex(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
 	} put_user_catch(err);
-
+	
 	err |= copy_siginfo_to_user(&frame->info, info);
 	err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
 				regs, set->sig[0]);
@@ -477,6 +475,75 @@
 }
 #endif /* CONFIG_X86_32 */
 
+static int x32_setup_rt_frame(int sig, struct k_sigaction *ka,
+			      siginfo_t *info, compat_sigset_t *set,
+			      struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_X32_ABI
+	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);
+
+		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);
+
+	err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
+				regs, set->sig[0]);
+	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+	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;
+#endif	/* CONFIG_X86_X32_ABI */
+
+	return 0;
+}
+
 #ifdef CONFIG_X86_32
 /*
  * Atomically swap in the new signal mask, and wait for a signal.
@@ -615,55 +682,22 @@
 	return sig;
 }
 
-#ifdef CONFIG_X86_32
-
-#define is_ia32	1
-#define ia32_setup_frame	__setup_frame
-#define ia32_setup_rt_frame	__setup_rt_frame
-
-#else /* !CONFIG_X86_32 */
-
-#ifdef CONFIG_IA32_EMULATION
-#define is_ia32	test_thread_flag(TIF_IA32)
-#else /* !CONFIG_IA32_EMULATION */
-#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,
-		sigset_t *set, struct pt_regs *regs);
-
-#endif /* CONFIG_X86_32 */
-
 static int
 setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		struct pt_regs *regs)
 {
 	int usig = signr_convert(sig);
 	sigset_t *set = sigmask_to_save();
+	compat_sigset_t *cset = (compat_sigset_t *) set;
 
 	/* Set up the stack frame */
-	if (is_ia32) {
+	if (is_ia32_frame()) {
 		if (ka->sa.sa_flags & SA_SIGINFO)
-			return ia32_setup_rt_frame(usig, ka, info, set, regs);
+			return ia32_setup_rt_frame(usig, ka, info, cset, regs);
 		else
-			return ia32_setup_frame(usig, ka, set, regs);
-#ifdef CONFIG_X86_X32_ABI
-	} else if (is_x32) {
-		return x32_setup_rt_frame(usig, ka, info,
-					 (compat_sigset_t *)set, regs);
-#endif
+			return ia32_setup_frame(usig, ka, cset, regs);
+	} else if (is_x32_frame()) {
+		return x32_setup_rt_frame(usig, ka, info, cset, regs);
 	} else {
 		return __setup_rt_frame(sig, ka, info, set, regs);
 	}
@@ -827,73 +861,6 @@
 }
 
 #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);
-
-		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);
-
-	err |= setup_sigcontext(&frame->uc.uc_mcontext, fpstate,
-				regs, set->sig[0]);
-	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
-	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;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b481341..4f4aba0 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -613,11 +613,12 @@
 	}
 
 	__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);
+		drop_init_fpu(tsk);
 		force_sig(SIGSEGV, tsk);
 		return;
 	}
@@ -629,6 +630,8 @@
 dotraplinkage void __kprobes
 do_device_not_available(struct pt_regs *regs, long error_code)
 {
+	BUG_ON(use_eager_fpu());
+
 #ifdef CONFIG_MATH_EMULATION
 	if (read_cr0() & X86_CR0_EM) {
 		struct math_emu_info info = { };
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 3d3e207..4e89b3d 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -10,9 +10,7 @@
 #include <linux/compat.h>
 #include <asm/i387.h>
 #include <asm/fpu-internal.h>
-#ifdef CONFIG_IA32_EMULATION
-#include <asm/sigcontext32.h>
-#endif
+#include <asm/sigframe.h>
 #include <asm/xcr.h>
 
 /*
@@ -23,13 +21,9 @@
 /*
  * Represents init state for the supported extended state.
  */
-static struct xsave_struct *init_xstate_buf;
+struct xsave_struct *init_xstate_buf;
 
-struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-struct _fpx_sw_bytes fx_sw_reserved_ia32;
-#endif
-
+static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
 static unsigned int *xstate_offsets, *xstate_sizes, xstate_features;
 
 /*
@@ -44,9 +38,9 @@
  */
 void __sanitize_i387_state(struct task_struct *tsk)
 {
-	u64 xstate_bv;
-	int feature_bit = 0x2;
 	struct i387_fxsave_struct *fx = &tsk->thread.fpu.state->fxsave;
+	int feature_bit = 0x2;
+	u64 xstate_bv;
 
 	if (!fx)
 		return;
@@ -104,213 +98,326 @@
  * Check for the presence of extended state information in the
  * user fpstate pointer in the sigcontext.
  */
-int check_for_xstate(struct i387_fxsave_struct __user *buf,
-		     void __user *fpstate,
-		     struct _fpx_sw_bytes *fx_sw_user)
+static inline int check_for_xstate(struct i387_fxsave_struct __user *buf,
+				   void __user *fpstate,
+				   struct _fpx_sw_bytes *fx_sw)
 {
 	int min_xstate_size = sizeof(struct i387_fxsave_struct) +
 			      sizeof(struct xsave_hdr_struct);
 	unsigned int magic2;
-	int err;
 
-	err = __copy_from_user(fx_sw_user, &buf->sw_reserved[0],
-			       sizeof(struct _fpx_sw_bytes));
-	if (err)
-		return -EFAULT;
+	if (__copy_from_user(fx_sw, &buf->sw_reserved[0], sizeof(*fx_sw)))
+		return -1;
 
-	/*
-	 * First Magic check failed.
-	 */
-	if (fx_sw_user->magic1 != FP_XSTATE_MAGIC1)
-		return -EINVAL;
+	/* Check for the first magic field and other error scenarios. */
+	if (fx_sw->magic1 != FP_XSTATE_MAGIC1 ||
+	    fx_sw->xstate_size < min_xstate_size ||
+	    fx_sw->xstate_size > xstate_size ||
+	    fx_sw->xstate_size > fx_sw->extended_size)
+		return -1;
 
 	/*
-	 * Check for error scenarios.
-	 */
-	if (fx_sw_user->xstate_size < min_xstate_size ||
-	    fx_sw_user->xstate_size > xstate_size ||
-	    fx_sw_user->xstate_size > fx_sw_user->extended_size)
-		return -EINVAL;
-
-	err = __get_user(magic2, (__u32 *) (((void *)fpstate) +
-					    fx_sw_user->extended_size -
-					    FP_XSTATE_MAGIC2_SIZE));
-	if (err)
-		return err;
-	/*
 	 * Check for the presence of second magic word at the end of memory
 	 * layout. This detects the case where the user just copied the legacy
 	 * fpstate layout with out copying the extended state information
 	 * in the memory layout.
 	 */
-	if (magic2 != FP_XSTATE_MAGIC2)
-		return -EFAULT;
+	if (__get_user(magic2, (__u32 __user *)(fpstate + fx_sw->xstate_size))
+	    || magic2 != FP_XSTATE_MAGIC2)
+		return -1;
 
 	return 0;
 }
 
-#ifdef CONFIG_X86_64
 /*
  * Signal frame handlers.
  */
-
-int save_i387_xstate(void __user *buf)
+static inline int save_fsave_header(struct task_struct *tsk, void __user *buf)
 {
-	struct task_struct *tsk = current;
-	int err = 0;
+	if (use_fxsr()) {
+		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct user_i387_ia32_struct env;
+		struct _fpstate_ia32 __user *fp = buf;
 
-	if (!access_ok(VERIFY_WRITE, buf, sig_xstate_size))
-		return -EACCES;
+		convert_from_fxsr(&env, tsk);
 
-	BUG_ON(sig_xstate_size < xstate_size);
-
-	if ((unsigned long)buf % 64)
-		pr_err("%s: bad fpstate %p\n", __func__, buf);
-
-	if (!used_math())
-		return 0;
-
-	if (user_has_fpu()) {
-		if (use_xsave())
-			err = xsave_user(buf);
-		else
-			err = fxsave_user(buf);
-
-		if (err)
-			return err;
-		user_fpu_end();
+		if (__copy_to_user(buf, &env, sizeof(env)) ||
+		    __put_user(xsave->i387.swd, &fp->status) ||
+		    __put_user(X86_FXSR_MAGIC, &fp->magic))
+			return -1;
 	} else {
-		sanitize_i387_state(tsk);
-		if (__copy_to_user(buf, &tsk->thread.fpu.state->fxsave,
-				   xstate_size))
+		struct i387_fsave_struct __user *fp = buf;
+		u32 swd;
+		if (__get_user(swd, &fp->swd) || __put_user(swd, &fp->status))
 			return -1;
 	}
 
-	clear_used_math(); /* trigger finit */
-
-	if (use_xsave()) {
-		struct _fpstate __user *fx = buf;
-		struct _xstate __user *x = buf;
-		u64 xstate_bv;
-
-		err = __copy_to_user(&fx->sw_reserved, &fx_sw_reserved,
-				     sizeof(struct _fpx_sw_bytes));
-
-		err |= __put_user(FP_XSTATE_MAGIC2,
-				  (__u32 __user *) (buf + sig_xstate_size
-						    - FP_XSTATE_MAGIC2_SIZE));
-
-		/*
-		 * Read the xstate_bv which we copied (directly from the cpu or
-		 * from the state in task struct) to the user buffers and
-		 * set the FP/SSE bits.
-		 */
-		err |= __get_user(xstate_bv, &x->xstate_hdr.xstate_bv);
-
-		/*
-		 * For legacy compatible, we always set FP/SSE bits in the bit
-		 * vector while saving the state to the user context. This will
-		 * enable us capturing any changes(during sigreturn) to
-		 * the FP/SSE bits by the legacy applications which don't touch
-		 * xstate_bv in the xsave header.
-		 *
-		 * xsave aware apps can change the xstate_bv in the xsave
-		 * header as well as change any contents in the memory layout.
-		 * xrestore as part of sigreturn will capture all the changes.
-		 */
-		xstate_bv |= XSTATE_FPSSE;
-
-		err |= __put_user(xstate_bv, &x->xstate_hdr.xstate_bv);
-
-		if (err)
-			return err;
-	}
-
-	return 1;
+	return 0;
 }
 
-/*
- * Restore the extended state if present. Otherwise, restore the FP/SSE
- * state.
- */
-static int restore_user_xstate(void __user *buf)
+static inline int save_xstate_epilog(void __user *buf, int ia32_frame)
 {
-	struct _fpx_sw_bytes fx_sw_user;
-	u64 mask;
+	struct xsave_struct __user *x = buf;
+	struct _fpx_sw_bytes *sw_bytes;
+	u32 xstate_bv;
 	int err;
 
-	if (((unsigned long)buf % 64) ||
-	     check_for_xstate(buf, buf, &fx_sw_user))
-		goto fx_only;
+	/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
+	sw_bytes = ia32_frame ? &fx_sw_reserved_ia32 : &fx_sw_reserved;
+	err = __copy_to_user(&x->i387.sw_reserved, sw_bytes, sizeof(*sw_bytes));
 
-	mask = fx_sw_user.xstate_bv;
-
-	/*
-	 * restore the state passed by the user.
-	 */
-	err = xrestore_user(buf, mask);
-	if (err)
+	if (!use_xsave())
 		return err;
 
-	/*
-	 * init the state skipped by the user.
-	 */
-	mask = pcntxt_mask & ~mask;
-	if (unlikely(mask))
-		xrstor_state(init_xstate_buf, mask);
+	err |= __put_user(FP_XSTATE_MAGIC2, (__u32 *)(buf + xstate_size));
 
-	return 0;
-
-fx_only:
 	/*
-	 * couldn't find the extended state information in the
-	 * memory layout. Restore just the FP/SSE and init all
-	 * the other extended state.
+	 * Read the xstate_bv which we copied (directly from the cpu or
+	 * from the state in task struct) to the user buffers.
 	 */
-	xrstor_state(init_xstate_buf, pcntxt_mask & ~XSTATE_FPSSE);
-	return fxrstor_checking((__force struct i387_fxsave_struct *)buf);
+	err |= __get_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
+
+	/*
+	 * For legacy compatible, we always set FP/SSE bits in the bit
+	 * vector while saving the state to the user context. This will
+	 * enable us capturing any changes(during sigreturn) to
+	 * the FP/SSE bits by the legacy applications which don't touch
+	 * xstate_bv in the xsave header.
+	 *
+	 * xsave aware apps can change the xstate_bv in the xsave
+	 * header as well as change any contents in the memory layout.
+	 * xrestore as part of sigreturn will capture all the changes.
+	 */
+	xstate_bv |= XSTATE_FPSSE;
+
+	err |= __put_user(xstate_bv, (__u32 *)&x->xsave_hdr.xstate_bv);
+
+	return err;
+}
+
+static inline int save_user_xstate(struct xsave_struct __user *buf)
+{
+	int err;
+
+	if (use_xsave())
+		err = xsave_user(buf);
+	else if (use_fxsr())
+		err = fxsave_user((struct i387_fxsave_struct __user *) buf);
+	else
+		err = fsave_user((struct i387_fsave_struct __user *) buf);
+
+	if (unlikely(err) && __clear_user(buf, xstate_size))
+		err = -EFAULT;
+	return err;
 }
 
 /*
- * This restores directly out of user space. Exceptions are handled.
+ * Save the fpu, extended register state to the user signal frame.
+ *
+ * 'buf_fx' is the 64-byte aligned pointer at which the [f|fx|x]save
+ *  state is copied.
+ *  'buf' points to the 'buf_fx' or to the fsave header followed by 'buf_fx'.
+ *
+ *	buf == buf_fx for 64-bit frames and 32-bit fsave frame.
+ *	buf != buf_fx for 32-bit frames with fxstate.
+ *
+ * If the fpu, extended register state is live, save the state directly
+ * to the user frame pointed by the aligned pointer 'buf_fx'. Otherwise,
+ * copy the thread's fpu state to the user frame starting at 'buf_fx'.
+ *
+ * If this is a 32-bit frame with fxstate, put a fsave header before
+ * the aligned state at 'buf_fx'.
+ *
+ * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
+ * indicating the absence/presence of the extended state to the user.
  */
-int restore_i387_xstate(void __user *buf)
+int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 {
+	struct xsave_struct *xsave = &current->thread.fpu.state->xsave;
 	struct task_struct *tsk = current;
-	int err = 0;
+	int ia32_fxstate = (buf != buf_fx);
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
+
+	if (!access_ok(VERIFY_WRITE, buf, size))
+		return -EACCES;
+
+	if (!HAVE_HWFP)
+		return fpregs_soft_get(current, NULL, 0,
+			sizeof(struct user_i387_ia32_struct), NULL,
+			(struct _fpstate_ia32 __user *) buf) ? -1 : 1;
+
+	if (user_has_fpu()) {
+		/* Save the live register state to the user directly. */
+		if (save_user_xstate(buf_fx))
+			return -1;
+		/* Update the thread's fxstate to save the fsave header. */
+		if (ia32_fxstate)
+			fpu_fxsave(&tsk->thread.fpu);
+	} else {
+		sanitize_i387_state(tsk);
+		if (__copy_to_user(buf_fx, xsave, xstate_size))
+			return -1;
+	}
+
+	/* Save the fsave header for the 32-bit frames. */
+	if ((ia32_fxstate || !use_fxsr()) && save_fsave_header(tsk, buf))
+		return -1;
+
+	if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
+		return -1;
+
+	drop_init_fpu(tsk);	/* trigger finit */
+
+	return 0;
+}
+
+static inline void
+sanitize_restored_xstate(struct task_struct *tsk,
+			 struct user_i387_ia32_struct *ia32_env,
+			 u64 xstate_bv, int fx_only)
+{
+	struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+	struct xsave_hdr_struct *xsave_hdr = &xsave->xsave_hdr;
+
+	if (use_xsave()) {
+		/* These bits must be zero. */
+		xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0;
+
+		/*
+		 * Init the state that is not present in the memory
+		 * layout and not enabled by the OS.
+		 */
+		if (fx_only)
+			xsave_hdr->xstate_bv = XSTATE_FPSSE;
+		else
+			xsave_hdr->xstate_bv &= (pcntxt_mask & xstate_bv);
+	}
+
+	if (use_fxsr()) {
+		/*
+		 * mscsr reserved bits must be masked to zero for security
+		 * reasons.
+		 */
+		xsave->i387.mxcsr &= mxcsr_feature_mask;
+
+		convert_to_fxsr(tsk, ia32_env);
+	}
+}
+
+/*
+ * Restore the extended state if present. Otherwise, restore the FP/SSE state.
+ */
+static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
+{
+	if (use_xsave()) {
+		if ((unsigned long)buf % 64 || fx_only) {
+			u64 init_bv = pcntxt_mask & ~XSTATE_FPSSE;
+			xrstor_state(init_xstate_buf, init_bv);
+			return fxrstor_checking((__force void *) buf);
+		} else {
+			u64 init_bv = pcntxt_mask & ~xbv;
+			if (unlikely(init_bv))
+				xrstor_state(init_xstate_buf, init_bv);
+			return xrestore_user(buf, xbv);
+		}
+	} else if (use_fxsr()) {
+		return fxrstor_checking((__force void *) buf);
+	} else
+		return frstor_checking((__force void *) buf);
+}
+
+int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
+{
+	int ia32_fxstate = (buf != buf_fx);
+	struct task_struct *tsk = current;
+	int state_size = xstate_size;
+	u64 xstate_bv = 0;
+	int fx_only = 0;
+
+	ia32_fxstate &= (config_enabled(CONFIG_X86_32) ||
+			 config_enabled(CONFIG_IA32_EMULATION));
 
 	if (!buf) {
-		if (used_math())
-			goto clear;
+		drop_init_fpu(tsk);
 		return 0;
-	} else
-		if (!access_ok(VERIFY_READ, buf, sig_xstate_size))
-			return -EACCES;
-
-	if (!used_math()) {
-		err = init_fpu(tsk);
-		if (err)
-			return err;
 	}
 
-	user_fpu_begin();
-	if (use_xsave())
-		err = restore_user_xstate(buf);
-	else
-		err = fxrstor_checking((__force struct i387_fxsave_struct *)
-				       buf);
-	if (unlikely(err)) {
+	if (!access_ok(VERIFY_READ, buf, size))
+		return -EACCES;
+
+	if (!used_math() && init_fpu(tsk))
+		return -1;
+
+	if (!HAVE_HWFP) {
+		return fpregs_soft_set(current, NULL,
+				       0, sizeof(struct user_i387_ia32_struct),
+				       NULL, buf) != 0;
+	}
+
+	if (use_xsave()) {
+		struct _fpx_sw_bytes fx_sw_user;
+		if (unlikely(check_for_xstate(buf_fx, buf_fx, &fx_sw_user))) {
+			/*
+			 * Couldn't find the extended state information in the
+			 * memory layout. Restore just the FP/SSE and init all
+			 * the other extended state.
+			 */
+			state_size = sizeof(struct i387_fxsave_struct);
+			fx_only = 1;
+		} else {
+			state_size = fx_sw_user.xstate_size;
+			xstate_bv = fx_sw_user.xstate_bv;
+		}
+	}
+
+	if (ia32_fxstate) {
 		/*
-		 * Encountered an error while doing the restore from the
-		 * user buffer, clear the fpu state.
+		 * For 32-bit frames with fxstate, copy the user state to the
+		 * thread's fpu state, reconstruct fxstate from the fsave
+		 * header. Sanitize the copied state etc.
 		 */
-clear:
-		clear_fpu(tsk);
-		clear_used_math();
+		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct user_i387_ia32_struct env;
+		int err = 0;
+
+		/*
+		 * Drop the current fpu which clears used_math(). This ensures
+		 * that any context-switch during the copy of the new state,
+		 * avoids the intermediate state from getting restored/saved.
+		 * Thus avoiding the new restored state from getting corrupted.
+		 * We will be ready to restore/save the state only after
+		 * set_used_math() is again set.
+		 */
+		drop_fpu(tsk);
+
+		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		    __copy_from_user(&env, buf, sizeof(env))) {
+			err = -1;
+		} else {
+			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
+			set_used_math();
+		}
+
+		if (use_eager_fpu())
+			math_state_restore();
+
+		return err;
+	} else {
+		/*
+		 * For 64-bit frames and 32-bit fsave frames, restore the user
+		 * state to the registers directly (with exceptions handled).
+		 */
+		user_fpu_begin();
+		if (restore_user_xstate(buf_fx, xstate_bv, fx_only)) {
+			drop_init_fpu(tsk);
+			return -1;
+		}
 	}
-	return err;
+
+	return 0;
 }
-#endif
 
 /*
  * Prepare the SW reserved portion of the fxsave memory layout, indicating
@@ -321,31 +428,22 @@
  */
 static void prepare_fx_sw_frame(void)
 {
-	int size_extended = (xstate_size - sizeof(struct i387_fxsave_struct)) +
-			     FP_XSTATE_MAGIC2_SIZE;
+	int fsave_header_size = sizeof(struct i387_fsave_struct);
+	int size = xstate_size + FP_XSTATE_MAGIC2_SIZE;
 
-	sig_xstate_size = sizeof(struct _fpstate) + size_extended;
-
-#ifdef CONFIG_IA32_EMULATION
-	sig_xstate_ia32_size = sizeof(struct _fpstate_ia32) + size_extended;
-#endif
-
-	memset(&fx_sw_reserved, 0, sizeof(fx_sw_reserved));
+	if (config_enabled(CONFIG_X86_32))
+		size += fsave_header_size;
 
 	fx_sw_reserved.magic1 = FP_XSTATE_MAGIC1;
-	fx_sw_reserved.extended_size = sig_xstate_size;
+	fx_sw_reserved.extended_size = size;
 	fx_sw_reserved.xstate_bv = pcntxt_mask;
 	fx_sw_reserved.xstate_size = xstate_size;
-#ifdef CONFIG_IA32_EMULATION
-	memcpy(&fx_sw_reserved_ia32, &fx_sw_reserved,
-	       sizeof(struct _fpx_sw_bytes));
-	fx_sw_reserved_ia32.extended_size = sig_xstate_ia32_size;
-#endif
-}
 
-#ifdef CONFIG_X86_64
-unsigned int sig_xstate_size = sizeof(struct _fpstate);
-#endif
+	if (config_enabled(CONFIG_IA32_EMULATION)) {
+		fx_sw_reserved_ia32 = fx_sw_reserved;
+		fx_sw_reserved_ia32.extended_size += fsave_header_size;
+	}
+}
 
 /*
  * Enable the extended processor state save/restore feature
@@ -384,19 +482,21 @@
 /*
  * setup the xstate image representing the init state
  */
-static void __init setup_xstate_init(void)
+static void __init setup_init_fpu_buf(void)
 {
-	setup_xstate_features();
-
 	/*
 	 * Setup init_xstate_buf to represent the init state of
 	 * all the features managed by the xsave
 	 */
 	init_xstate_buf = alloc_bootmem_align(xstate_size,
 					      __alignof__(struct xsave_struct));
-	init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
+	fx_finit(&init_xstate_buf->i387);
 
-	clts();
+	if (!cpu_has_xsave)
+		return;
+
+	setup_xstate_features();
+
 	/*
 	 * Init all the features state with header_bv being 0x0
 	 */
@@ -406,9 +506,21 @@
 	 * of any feature which is not represented by all zero's.
 	 */
 	xsave_state(init_xstate_buf, -1);
-	stts();
 }
 
+static enum { AUTO, ENABLE, DISABLE } eagerfpu = AUTO;
+static int __init eager_fpu_setup(char *s)
+{
+	if (!strcmp(s, "on"))
+		eagerfpu = ENABLE;
+	else if (!strcmp(s, "off"))
+		eagerfpu = DISABLE;
+	else if (!strcmp(s, "auto"))
+		eagerfpu = AUTO;
+	return 1;
+}
+__setup("eagerfpu=", eager_fpu_setup);
+
 /*
  * Enable and initialize the xsave feature.
  */
@@ -445,8 +557,11 @@
 
 	update_regset_xstate_info(xstate_size, pcntxt_mask);
 	prepare_fx_sw_frame();
+	setup_init_fpu_buf();
 
-	setup_xstate_init();
+	/* Auto enable eagerfpu for xsaveopt */
+	if (cpu_has_xsaveopt && eagerfpu != DISABLE)
+		eagerfpu = ENABLE;
 
 	pr_info("enabled xstate_bv 0x%llx, cntxt size 0x%x\n",
 		pcntxt_mask, xstate_size);
@@ -471,3 +586,43 @@
 	next_func = xstate_enable;
 	this_func();
 }
+
+static inline void __init eager_fpu_init_bp(void)
+{
+	current->thread.fpu.state =
+	    alloc_bootmem_align(xstate_size, __alignof__(struct xsave_struct));
+	if (!init_xstate_buf)
+		setup_init_fpu_buf();
+}
+
+void __cpuinit eager_fpu_init(void)
+{
+	static __refdata void (*boot_func)(void) = eager_fpu_init_bp;
+
+	clear_used_math();
+	current_thread_info()->status = 0;
+
+	if (eagerfpu == ENABLE)
+		setup_force_cpu_cap(X86_FEATURE_EAGER_FPU);
+
+	if (!cpu_has_eager_fpu) {
+		stts();
+		return;
+	}
+
+	if (boot_func) {
+		boot_func();
+		boot_func = NULL;
+	}
+
+	/*
+	 * This is same as math_state_restore(). But use_xsave() is
+	 * not yet patched to use math_state_restore().
+	 */
+	init_fpu(current);
+	__thread_fpu_begin(current);
+	if (cpu_has_xsave)
+		xrstor_state(init_xstate_buf, -1);
+	else
+		fxrstor_checking(&init_xstate_buf->i387);
+}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c00f03d..70dfcec 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1493,8 +1493,12 @@
 #ifdef CONFIG_X86_64
 	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
-	if (user_has_fpu())
-		clts();
+	/*
+	 * If the FPU is not active (through the host task or
+	 * the guest vcpu), then restore the cr0.TS bit.
+	 */
+	if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
+		stts();
 	load_gdt(&__get_cpu_var(host_gdt));
 }
 
@@ -3730,7 +3734,7 @@
 	unsigned long tmpl;
 	struct desc_ptr dt;
 
-	vmcs_writel(HOST_CR0, read_cr0() | X86_CR0_TS);  /* 22.2.3 */
+	vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS);  /* 22.2.3 */
 	vmcs_writel(HOST_CR4, read_cr4());  /* 22.2.3, 22.2.5 */
 	vmcs_writel(HOST_CR3, read_cr3());  /* 22.2.3  FIXME: shadow tables */
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 148ed66..02b2cd5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5972,7 +5972,7 @@
 	 */
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
-	unlazy_fpu(current);
+	__kernel_fpu_begin();
 	fpu_restore_checking(&vcpu->arch.guest_fpu);
 	trace_kvm_fpu(1);
 }
@@ -5986,6 +5986,7 @@
 
 	vcpu->guest_fpu_loaded = 0;
 	fpu_save_init(&vcpu->arch.guest_fpu);
+	__kernel_fpu_end();
 	++vcpu->stat.fpu_reload;
 	kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
 	trace_kvm_fpu(0);
diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c
index 39809035..4af12e1 100644
--- a/drivers/lguest/x86/core.c
+++ b/drivers/lguest/x86/core.c
@@ -203,8 +203,8 @@
 	 * we set it now, so we can trap and pass that trap to the Guest if it
 	 * uses the FPU.
 	 */
-	if (cpu->ts)
-		unlazy_fpu(current);
+	if (cpu->ts && user_has_fpu())
+		stts();
 
 	/*
 	 * SYSENTER is an optimized way of doing system calls.  We can't allow
@@ -234,6 +234,10 @@
 	 if (boot_cpu_has(X86_FEATURE_SEP))
 		wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
 
+	/* Clear the host TS bit if it was set above. */
+	if (cpu->ts && user_has_fpu())
+		clts();
+
 	/*
 	 * If the Guest page faulted, then the cr2 register will tell us the
 	 * bad virtual address.  We have to grab this now, because once we
@@ -249,7 +253,7 @@
 	 * a different CPU. So all the critical stuff should be done
 	 * before this.
 	 */
-	else if (cpu->regs->trapnum == 7)
+	else if (cpu->regs->trapnum == 7 && !user_has_fpu())
 		math_state_restore();
 }
 
diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c
index 4f50145..662c5f7 100644
--- a/drivers/net/can/sja1000/sja1000_platform.c
+++ b/drivers/net/can/sja1000/sja1000_platform.c
@@ -109,7 +109,9 @@
 	priv = netdev_priv(dev);
 
 	dev->irq = res_irq->start;
-	priv->irq_flags = res_irq->flags & (IRQF_TRIGGER_MASK | IRQF_SHARED);
+	priv->irq_flags = res_irq->flags & IRQF_TRIGGER_MASK;
+	if (res_irq->flags & IORESOURCE_IRQ_SHAREABLE)
+		priv->irq_flags |= IRQF_SHARED;
 	priv->reg_base = addr;
 	/* The CAN clock frequency is half the oscillator clock frequency */
 	priv->can.clock.freq = pdata->osc_freq / 2;
diff --git a/drivers/net/can/softing/softing_fw.c b/drivers/net/can/softing/softing_fw.c
index 3105961..b595d34 100644
--- a/drivers/net/can/softing/softing_fw.c
+++ b/drivers/net/can/softing/softing_fw.c
@@ -150,7 +150,7 @@
 	const uint8_t *mem, *end, *dat;
 	uint16_t type, len;
 	uint32_t addr;
-	uint8_t *buf = NULL;
+	uint8_t *buf = NULL, *new_buf;
 	int buflen = 0;
 	int8_t type_end = 0;
 
@@ -199,11 +199,12 @@
 		if (len > buflen) {
 			/* align buflen */
 			buflen = (len + (1024-1)) & ~(1024-1);
-			buf = krealloc(buf, buflen, GFP_KERNEL);
-			if (!buf) {
+			new_buf = krealloc(buf, buflen, GFP_KERNEL);
+			if (!new_buf) {
 				ret = -ENOMEM;
 				goto failed;
 			}
+			buf = new_buf;
 		}
 		/* verify record data */
 		memcpy_fromio(buf, &dpram[addr + offset], len);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 463b9ec..6d1a24a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1708,9 +1708,6 @@
 			continue;		\
 		else
 
-#define for_each_napi_rx_queue(bp, var) \
-	for ((var) = 0; (var) < bp->num_napi_queues; (var)++)
-
 /* Skip OOO FP */
 #define for_each_tx_queue(bp, var) \
 	for ((var) = 0; (var) < BNX2X_NUM_QUEUES(bp); (var)++) \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index e879e19..af20c6e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2046,6 +2046,8 @@
 	 */
 	bnx2x_setup_tc(bp->dev, bp->max_cos);
 
+	/* Add all NAPI objects */
+	bnx2x_add_all_napi(bp);
 	bnx2x_napi_enable(bp);
 
 	/* set pf load just before approaching the MCP */
@@ -2408,6 +2410,8 @@
 
 		/* Disable HW interrupts, NAPI */
 		bnx2x_netif_stop(bp, 1);
+		/* Delete all NAPI objects */
+		bnx2x_del_all_napi(bp);
 
 		/* Release IRQs */
 		bnx2x_free_irq(bp);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index dfa757e..21b5532 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -792,7 +792,7 @@
 	bp->num_napi_queues = bp->num_queues;
 
 	/* Add NAPI objects */
-	for_each_napi_rx_queue(bp, i)
+	for_each_rx_queue(bp, i)
 		netif_napi_add(bp->dev, &bnx2x_fp(bp, i, napi),
 			       bnx2x_poll, BNX2X_NAPI_WEIGHT);
 }
@@ -801,7 +801,7 @@
 {
 	int i;
 
-	for_each_napi_rx_queue(bp, i)
+	for_each_rx_queue(bp, i)
 		netif_napi_del(&bnx2x_fp(bp, i, napi));
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index fc4e0e3..c37a68d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -2888,11 +2888,9 @@
  */
 static void bnx2x_change_num_queues(struct bnx2x *bp, int num_rss)
 {
-	bnx2x_del_all_napi(bp);
 	bnx2x_disable_msi(bp);
 	BNX2X_NUM_QUEUES(bp) = num_rss + NON_ETH_CONTEXT_USE;
 	bnx2x_set_int_mode(bp);
-	bnx2x_add_all_napi(bp);
 }
 
 /**
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 02b5a34..2105498 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8427,6 +8427,8 @@
 
 	/* Disable HW interrupts, NAPI */
 	bnx2x_netif_stop(bp, 1);
+	/* Delete all NAPI objects */
+	bnx2x_del_all_napi(bp);
 
 	/* Release IRQs */
 	bnx2x_free_irq(bp);
@@ -11229,10 +11231,12 @@
 static void poll_bnx2x(struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
+	int i;
 
-	disable_irq(bp->pdev->irq);
-	bnx2x_interrupt(bp->pdev->irq, dev);
-	enable_irq(bp->pdev->irq);
+	for_each_eth_queue(bp, i) {
+		struct bnx2x_fastpath *fp = &bp->fp[i];
+		napi_schedule(&bnx2x_fp(bp, fp->index, napi));
+	}
 }
 #endif
 
@@ -11899,9 +11903,6 @@
 	 */
 	bnx2x_set_int_mode(bp);
 
-	/* Add all NAPI objects */
-	bnx2x_add_all_napi(bp);
-
 	rc = register_netdev(dev);
 	if (rc) {
 		dev_err(&pdev->dev, "Cannot register net device\n");
@@ -11976,9 +11977,6 @@
 
 	unregister_netdev(dev);
 
-	/* Delete all NAPI objects */
-	bnx2x_del_all_napi(bp);
-
 	/* Power on: we can't let PCI layer write to us while we are in D3 */
 	bnx2x_set_power_state(bp, PCI_D0);
 
@@ -12025,6 +12023,8 @@
 	bnx2x_tx_disable(bp);
 
 	bnx2x_netif_stop(bp, 0);
+	/* Delete all NAPI objects */
+	bnx2x_del_all_napi(bp);
 
 	del_timer_sync(&bp->timer);
 
diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c
index 845b202..1384469 100644
--- a/drivers/net/ethernet/cirrus/cs89x0.c
+++ b/drivers/net/ethernet/cirrus/cs89x0.c
@@ -1243,6 +1243,7 @@
 {
 	struct net_local *lp = netdev_priv(dev);
 	unsigned long flags;
+	u16 cfg;
 
 	spin_lock_irqsave(&lp->lock, flags);
 	if (dev->flags & IFF_PROMISC)
@@ -1260,11 +1261,10 @@
 	/* in promiscuous mode, we accept errored packets,
 	 * so we have to enable interrupts on them also
 	 */
-	writereg(dev, PP_RxCFG,
-		 (lp->curr_rx_cfg |
-		  (lp->rx_mode == RX_ALL_ACCEPT)
-		  ? (RX_CRC_ERROR_ENBL | RX_RUNT_ENBL | RX_EXTRA_DATA_ENBL)
-		  : 0));
+	cfg = lp->curr_rx_cfg;
+	if (lp->rx_mode == RX_ALL_ACCEPT)
+		cfg |= RX_CRC_ERROR_ENBL | RX_RUNT_ENBL | RX_EXTRA_DATA_ENBL;
+	writereg(dev, PP_RxCFG, cfg);
 	spin_unlock_irqrestore(&lp->lock, flags);
 }
 
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 7fac97b..8c63d06 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -259,7 +259,7 @@
 	int num = 0, status = 0;
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
-	spin_lock_bh(&adapter->mcc_cq_lock);
+	spin_lock(&adapter->mcc_cq_lock);
 	while ((compl = be_mcc_compl_get(adapter))) {
 		if (compl->flags & CQE_FLAGS_ASYNC_MASK) {
 			/* Interpret flags as an async trailer */
@@ -280,7 +280,7 @@
 	if (num)
 		be_cq_notify(adapter, mcc_obj->cq.id, mcc_obj->rearm_cq, num);
 
-	spin_unlock_bh(&adapter->mcc_cq_lock);
+	spin_unlock(&adapter->mcc_cq_lock);
 	return status;
 }
 
@@ -295,7 +295,9 @@
 		if (be_error(adapter))
 			return -EIO;
 
+		local_bh_disable();
 		status = be_process_mcc(adapter);
+		local_bh_enable();
 
 		if (atomic_read(&mcc_obj->q.used) == 0)
 			break;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 90a903d8..78b8aa8 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3763,7 +3763,9 @@
 	/* when interrupts are not yet enabled, just reap any pending
 	* mcc completions */
 	if (!netif_running(adapter->netdev)) {
+		local_bh_disable();
 		be_process_mcc(adapter);
+		local_bh_enable();
 		goto reschedule;
 	}
 
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 4605f72..d3233f5 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1041,7 +1041,7 @@
 
 	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) {
 		dev->hw_features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
-		dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
+		dev->features |= NETIF_F_HW_VLAN_RX;
 	}
 
 	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_EXTENDED_HASH) {
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index cd15332..cb3356c 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -310,6 +310,7 @@
 	 */
 	struct e1000_ring *tx_ring /* One per active queue */
 						____cacheline_aligned_in_smp;
+	u32 tx_fifo_limit;
 
 	struct napi_struct napi;
 
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 46c3b1f..d01a099 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3517,6 +3517,15 @@
 	}
 
 	/*
+	 * Alignment of Tx data is on an arbitrary byte boundary with the
+	 * maximum size per Tx descriptor limited only to the transmit
+	 * allocation of the packet buffer minus 96 bytes with an upper
+	 * limit of 24KB due to receive synchronization limitations.
+	 */
+	adapter->tx_fifo_limit = min_t(u32, ((er32(PBA) >> 16) << 10) - 96,
+				       24 << 10);
+
+	/*
 	 * Disable Adaptive Interrupt Moderation if 2 full packets cannot
 	 * fit in receive buffer.
 	 */
@@ -4785,12 +4794,9 @@
 	return 1;
 }
 
-#define E1000_MAX_PER_TXD	8192
-#define E1000_MAX_TXD_PWR	12
-
 static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb,
 			unsigned int first, unsigned int max_per_txd,
-			unsigned int nr_frags, unsigned int mss)
+			unsigned int nr_frags)
 {
 	struct e1000_adapter *adapter = tx_ring->adapter;
 	struct pci_dev *pdev = adapter->pdev;
@@ -5023,20 +5029,19 @@
 
 static int e1000_maybe_stop_tx(struct e1000_ring *tx_ring, int size)
 {
+	BUG_ON(size > tx_ring->count);
+
 	if (e1000_desc_unused(tx_ring) >= size)
 		return 0;
 	return __e1000_maybe_stop_tx(tx_ring, size);
 }
 
-#define TXD_USE_COUNT(S, X) (((S) >> (X)) + 1)
 static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 				    struct net_device *netdev)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_ring *tx_ring = adapter->tx_ring;
 	unsigned int first;
-	unsigned int max_per_txd = E1000_MAX_PER_TXD;
-	unsigned int max_txd_pwr = E1000_MAX_TXD_PWR;
 	unsigned int tx_flags = 0;
 	unsigned int len = skb_headlen(skb);
 	unsigned int nr_frags;
@@ -5056,18 +5061,8 @@
 	}
 
 	mss = skb_shinfo(skb)->gso_size;
-	/*
-	 * The controller does a simple calculation to
-	 * make sure there is enough room in the FIFO before
-	 * initiating the DMA for each buffer.  The calc is:
-	 * 4 = ceil(buffer len/mss).  To make sure we don't
-	 * overrun the FIFO, adjust the max buffer len if mss
-	 * drops.
-	 */
 	if (mss) {
 		u8 hdr_len;
-		max_per_txd = min(mss << 2, max_per_txd);
-		max_txd_pwr = fls(max_per_txd) - 1;
 
 		/*
 		 * TSO Workaround for 82571/2/3 Controllers -- if skb->data
@@ -5097,12 +5092,12 @@
 		count++;
 	count++;
 
-	count += TXD_USE_COUNT(len, max_txd_pwr);
+	count += DIV_ROUND_UP(len, adapter->tx_fifo_limit);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++)
-		count += TXD_USE_COUNT(skb_frag_size(&skb_shinfo(skb)->frags[f]),
-				       max_txd_pwr);
+		count += DIV_ROUND_UP(skb_frag_size(&skb_shinfo(skb)->frags[f]),
+				      adapter->tx_fifo_limit);
 
 	if (adapter->hw.mac.tx_pkt_filtering)
 		e1000_transfer_dhcp_info(adapter, skb);
@@ -5144,15 +5139,18 @@
 		tx_flags |= E1000_TX_FLAGS_NO_FCS;
 
 	/* if count is 0 then mapping error has occurred */
-	count = e1000_tx_map(tx_ring, skb, first, max_per_txd, nr_frags, mss);
+	count = e1000_tx_map(tx_ring, skb, first, adapter->tx_fifo_limit,
+			     nr_frags);
 	if (count) {
 		skb_tx_timestamp(skb);
 
 		netdev_sent_queue(netdev, skb->len);
 		e1000_tx_queue(tx_ring, tx_flags, count);
 		/* Make sure there is space in the ring for the next send. */
-		e1000_maybe_stop_tx(tx_ring, MAX_SKB_FRAGS + 2);
-
+		e1000_maybe_stop_tx(tx_ring,
+				    (MAX_SKB_FRAGS *
+				     DIV_ROUND_UP(PAGE_SIZE,
+						  adapter->tx_fifo_limit) + 2));
 	} else {
 		dev_kfree_skb_any(skb);
 		tx_ring->buffer_info[first].time_stamp = 0;
@@ -6327,8 +6325,8 @@
 	adapter->hw.phy.autoneg_advertised = 0x2f;
 
 	/* ring size defaults */
-	adapter->rx_ring->count = 256;
-	adapter->tx_ring->count = 256;
+	adapter->rx_ring->count = E1000_DEFAULT_RXD;
+	adapter->tx_ring->count = E1000_DEFAULT_TXD;
 
 	/*
 	 * Initial Wake on LAN setting - If APM wake is enabled in
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 8cba2df..5faedd8 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -863,8 +863,8 @@
 				       &ip_entry->ip4dst, &ip_entry->pdst);
 	if (rc != 0) {
 		rc = efx_filter_get_ipv4_full(
-			&spec, &proto, &ip_entry->ip4src, &ip_entry->psrc,
-			&ip_entry->ip4dst, &ip_entry->pdst);
+			&spec, &proto, &ip_entry->ip4dst, &ip_entry->pdst,
+			&ip_entry->ip4src, &ip_entry->psrc);
 		EFX_WARN_ON_PARANOID(rc);
 		ip_mask->ip4src = ~0;
 		ip_mask->psrc = ~0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index e2d0832..719be39 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -22,6 +22,9 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
+#ifndef __COMMON_H__
+#define __COMMON_H__
+
 #include <linux/etherdevice.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
@@ -366,3 +369,5 @@
 
 extern void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
 extern const struct stmmac_ring_mode_ops ring_mode_ops;
+
+#endif /* __COMMON_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs.h b/drivers/net/ethernet/stmicro/stmmac/descs.h
index 9820ec8..223adf9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs.h
@@ -20,6 +20,10 @@
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
+
+#ifndef __DESCS_H__
+#define __DESCS_H__
+
 struct dma_desc {
 	/* Receive descriptor */
 	union {
@@ -166,3 +170,5 @@
 					 * is not calculated */
 	cic_full = 3,		/* IP header and pseudoheader */
 };
+
+#endif /* __DESCS_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
index dd8d6e1..7ee9499 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
@@ -27,6 +27,9 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
+#ifndef __DESC_COM_H__
+#define __DESC_COM_H__
+
 #if defined(CONFIG_STMMAC_RING)
 static inline void ehn_desc_rx_set_on_ring_chain(struct dma_desc *p, int end)
 {
@@ -124,3 +127,5 @@
 	p->des01.tx.buffer1_size = len;
 }
 #endif
+
+#endif /* __DESC_COM_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100.h b/drivers/net/ethernet/stmicro/stmmac/dwmac100.h
index 7c6d857..2ec6aea 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100.h
@@ -22,6 +22,9 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
+#ifndef __DWMAC100_H__
+#define __DWMAC100_H__
+
 #include <linux/phy.h>
 #include "common.h"
 
@@ -119,3 +122,5 @@
 #define DMA_MISSED_FRAME_M_CNTR	0x0000ffff	/* Missed Frame Couinter */
 
 extern const struct stmmac_dma_ops dwmac100_dma_ops;
+
+#endif /* __DWMAC100_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index f90fcb5..0e4cace 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -19,6 +19,8 @@
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
+#ifndef __DWMAC1000_H__
+#define __DWMAC1000_H__
 
 #include <linux/phy.h>
 #include "common.h"
@@ -229,6 +231,7 @@
 #define GMAC_MMC_RX_CSUM_OFFLOAD   0x208
 
 /* Synopsys Core versions */
-#define	DWMAC_CORE_3_40	34
+#define	DWMAC_CORE_3_40	0x34
 
 extern const struct stmmac_dma_ops dwmac1000_dma_ops;
+#endif /* __DWMAC1000_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index e678ce3..e49c9a0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -22,6 +22,9 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
+#ifndef __DWMAC_DMA_H__
+#define __DWMAC_DMA_H__
+
 /* DMA CRS Control and Status Register Mapping */
 #define DMA_BUS_MODE		0x00001000	/* Bus Mode */
 #define DMA_XMT_POLL_DEMAND	0x00001004	/* Transmit Poll Demand */
@@ -109,3 +112,5 @@
 extern void dwmac_dma_stop_rx(void __iomem *ioaddr);
 extern int dwmac_dma_interrupt(void __iomem *ioaddr,
 				struct stmmac_extra_stats *x);
+
+#endif /* __DWMAC_DMA_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h
index a3835202..67995ef 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc.h
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h
@@ -22,6 +22,9 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
+#ifndef __MMC_H__
+#define __MMC_H__
+
 /* MMC control register */
 /* When set, all counter are reset */
 #define MMC_CNTRL_COUNTER_RESET		0x1
@@ -129,3 +132,5 @@
 extern void dwmac_mmc_ctrl(void __iomem *ioaddr, unsigned int mode);
 extern void dwmac_mmc_intr_all_mask(void __iomem *ioaddr);
 extern void dwmac_mmc_read(void __iomem *ioaddr, struct stmmac_counters *mmc);
+
+#endif /* __MMC_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index c07cfe9..0c74a70 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -33,7 +33,7 @@
 #define MMC_TX_INTR		0x00000108	/* MMC TX Interrupt */
 #define MMC_RX_INTR_MASK	0x0000010c	/* MMC Interrupt Mask */
 #define MMC_TX_INTR_MASK	0x00000110	/* MMC Interrupt Mask */
-#define MMC_DEFAUL_MASK		0xffffffff
+#define MMC_DEFAULT_MASK		0xffffffff
 
 /* MMC TX counter registers */
 
@@ -147,8 +147,8 @@
 /* To mask all all interrupts.*/
 void dwmac_mmc_intr_all_mask(void __iomem *ioaddr)
 {
-	writel(MMC_DEFAUL_MASK, ioaddr + MMC_RX_INTR_MASK);
-	writel(MMC_DEFAUL_MASK, ioaddr + MMC_TX_INTR_MASK);
+	writel(MMC_DEFAULT_MASK, ioaddr + MMC_RX_INTR_MASK);
+	writel(MMC_DEFAULT_MASK, ioaddr + MMC_TX_INTR_MASK);
 }
 
 /* This reads the MAC core counters (if actaully supported).
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index f2d3665..e872e1d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -20,6 +20,9 @@
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
 
+#ifndef __STMMAC_H__
+#define __STMMAC_H__
+
 #define STMMAC_RESOURCE_NAME   "stmmaceth"
 #define DRV_MODULE_VERSION	"March_2012"
 
@@ -166,3 +169,5 @@
 {
 }
 #endif /* CONFIG_STMMAC_PCI */
+
+#endif /* __STMMAC_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.h
index 6863590..aea9b14 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_timer.h
@@ -21,6 +21,8 @@
 
   Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
 *******************************************************************************/
+#ifndef __STMMAC_TIMER_H__
+#define __STMMAC_TIMER_H__
 
 struct stmmac_timer {
 	void (*timer_start) (unsigned int new_freq);
@@ -40,3 +42,5 @@
 extern int tmu2_register_user(void *fnt, void *data);
 extern void tmu2_unregister_user(void);
 #endif
+
+#endif /* __STMMAC_TIMER_H__ */
diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c
index cd7ee20..a9ca4a0 100644
--- a/drivers/net/ethernet/ti/davinci_mdio.c
+++ b/drivers/net/ethernet/ti/davinci_mdio.c
@@ -394,8 +394,10 @@
 	struct device *dev = &pdev->dev;
 	struct davinci_mdio_data *data = dev_get_drvdata(dev);
 
-	if (data->bus)
+	if (data->bus) {
+		mdiobus_unregister(data->bus);
 		mdiobus_free(data->bus);
+	}
 
 	if (data->clk)
 		clk_put(data->clk);
diff --git a/drivers/net/fddi/skfp/pmf.c b/drivers/net/fddi/skfp/pmf.c
index 24d8566..441b4dc 100644
--- a/drivers/net/fddi/skfp/pmf.c
+++ b/drivers/net/fddi/skfp/pmf.c
@@ -673,7 +673,7 @@
 			sm_pm_get_ls(smc,port_to_mib(smc,port))) ;
 		break ;
 	case SMT_P_REASON :
-		* (u_long *) to = 0 ;
+		*(u32 *)to = 0 ;
 		sp_len = 4 ;
 		goto sp_done ;
 	case SMT_P1033 :			/* time stamp */
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 328397c..adfab3f 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -413,7 +413,9 @@
 
 	/* 5. Gobi 2000 and 3000 devices */
 	{QMI_GOBI_DEVICE(0x413c, 0x8186)},	/* Dell Gobi 2000 Modem device (N0218, VU936) */
+	{QMI_GOBI_DEVICE(0x413c, 0x8194)},	/* Dell Gobi 3000 Composite */
 	{QMI_GOBI_DEVICE(0x05c6, 0x920b)},	/* Generic Gobi 2000 Modem device */
+	{QMI_GOBI_DEVICE(0x05c6, 0x920d)},	/* Gobi 3000 Composite */
 	{QMI_GOBI_DEVICE(0x05c6, 0x9225)},	/* Sony Gobi 2000 Modem device (N0279, VU730) */
 	{QMI_GOBI_DEVICE(0x05c6, 0x9245)},	/* Samsung Gobi 2000 Modem device (VL176) */
 	{QMI_GOBI_DEVICE(0x03f0, 0x251d)},	/* HP Gobi 2000 Modem device (VP412) */
@@ -441,6 +443,8 @@
 	{QMI_GOBI_DEVICE(0x1199, 0x9015)},	/* Sierra Wireless Gobi 3000 Modem device */
 	{QMI_GOBI_DEVICE(0x1199, 0x9019)},	/* Sierra Wireless Gobi 3000 Modem device */
 	{QMI_GOBI_DEVICE(0x1199, 0x901b)},	/* Sierra Wireless MC7770 */
+	{QMI_GOBI_DEVICE(0x12d1, 0x14f1)},	/* Sony Gobi 3000 Composite */
+	{QMI_GOBI_DEVICE(0x1410, 0xa021)},	/* Foxconn Gobi 3000 Modem device (Novatel E396) */
 
 	{ }					/* END */
 };
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 8531c1c..fd4b26d 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1573,7 +1573,7 @@
 				netif_device_present(dev->net) &&
 				!timer_pending(&dev->delay) &&
 				!test_bit(EVENT_RX_HALT, &dev->flags))
-					rx_alloc_submit(dev, GFP_KERNEL);
+					rx_alloc_submit(dev, GFP_NOIO);
 
 			if (!(dev->txq.qlen >= TX_QLEN(dev)))
 				netif_tx_wake_all_queues(dev->net);
diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c
index 4026c90..b7e0258 100644
--- a/drivers/net/wireless/ath/ath5k/eeprom.c
+++ b/drivers/net/wireless/ath/ath5k/eeprom.c
@@ -1482,7 +1482,7 @@
 	case AR5K_EEPROM_MODE_11A:
 		offset += AR5K_EEPROM_TARGET_PWR_OFF_11A(ee->ee_version);
 		rate_pcal_info = ee->ee_rate_tpwr_a;
-		ee->ee_rate_target_pwr_num[mode] = AR5K_EEPROM_N_5GHZ_CHAN;
+		ee->ee_rate_target_pwr_num[mode] = AR5K_EEPROM_N_5GHZ_RATE_CHAN;
 		break;
 	case AR5K_EEPROM_MODE_11B:
 		offset += AR5K_EEPROM_TARGET_PWR_OFF_11B(ee->ee_version);
diff --git a/drivers/net/wireless/ath/ath5k/eeprom.h b/drivers/net/wireless/ath/ath5k/eeprom.h
index dc2bcfe..94a9bbe 100644
--- a/drivers/net/wireless/ath/ath5k/eeprom.h
+++ b/drivers/net/wireless/ath/ath5k/eeprom.h
@@ -182,6 +182,7 @@
 #define AR5K_EEPROM_EEP_DELTA		10
 #define AR5K_EEPROM_N_MODES		3
 #define AR5K_EEPROM_N_5GHZ_CHAN		10
+#define AR5K_EEPROM_N_5GHZ_RATE_CHAN	8
 #define AR5K_EEPROM_N_2GHZ_CHAN		3
 #define AR5K_EEPROM_N_2GHZ_CHAN_2413	4
 #define	AR5K_EEPROM_N_2GHZ_CHAN_MAX	4
diff --git a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
index 192ad5c..a5edebe 100644
--- a/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
+++ b/drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c
@@ -1233,6 +1233,9 @@
 	/* dpc will not be rescheduled */
 	wl->resched = false;
 
+	/* inform publicly that interface is down */
+	wl->pub->up = false;
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c
index 95aa8e1..83324b3 100644
--- a/drivers/net/wireless/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/ipw2x00/ipw2100.c
@@ -2042,7 +2042,8 @@
 		return;
 	}
 	len = ETH_ALEN;
-	ipw2100_get_ordinal(priv, IPW_ORD_STAT_ASSN_AP_BSSID, &bssid, &len);
+	ret = ipw2100_get_ordinal(priv, IPW_ORD_STAT_ASSN_AP_BSSID, bssid,
+				  &len);
 	if (ret) {
 		IPW_DEBUG_INFO("failed querying ordinals at line %d\n",
 			       __LINE__);
diff --git a/drivers/net/wireless/iwlwifi/dvm/debugfs.c b/drivers/net/wireless/iwlwifi/dvm/debugfs.c
index 46782f1..a47b306 100644
--- a/drivers/net/wireless/iwlwifi/dvm/debugfs.c
+++ b/drivers/net/wireless/iwlwifi/dvm/debugfs.c
@@ -124,6 +124,9 @@
 	const struct fw_img *img;
 	size_t bufsz;
 
+	if (!iwl_is_ready_rf(priv))
+		return -EAGAIN;
+
 	/* default is to dump the entire data segment */
 	if (!priv->dbgfs_sram_offset && !priv->dbgfs_sram_len) {
 		priv->dbgfs_sram_offset = 0x800000;
diff --git a/drivers/net/wireless/iwlwifi/pcie/internal.h b/drivers/net/wireless/iwlwifi/pcie/internal.h
index d9694c5..4ffc18d 100644
--- a/drivers/net/wireless/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/iwlwifi/pcie/internal.h
@@ -350,7 +350,7 @@
 /*****************************************************
 * Error handling
 ******************************************************/
-int iwl_dump_fh(struct iwl_trans *trans, char **buf, bool display);
+int iwl_dump_fh(struct iwl_trans *trans, char **buf);
 void iwl_dump_csr(struct iwl_trans *trans);
 
 /*****************************************************
diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c
index 39a6ca1..d1a61ba 100644
--- a/drivers/net/wireless/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/rx.c
@@ -555,7 +555,7 @@
 	}
 
 	iwl_dump_csr(trans);
-	iwl_dump_fh(trans, NULL, false);
+	iwl_dump_fh(trans, NULL);
 
 	iwl_op_mode_nic_error(trans->op_mode);
 }
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 939c2f7..1e86ea2 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -1649,13 +1649,9 @@
 #undef IWL_CMD
 }
 
-int iwl_dump_fh(struct iwl_trans *trans, char **buf, bool display)
+int iwl_dump_fh(struct iwl_trans *trans, char **buf)
 {
 	int i;
-#ifdef CONFIG_IWLWIFI_DEBUG
-	int pos = 0;
-	size_t bufsz = 0;
-#endif
 	static const u32 fh_tbl[] = {
 		FH_RSCSR_CHNL0_STTS_WPTR_REG,
 		FH_RSCSR_CHNL0_RBDCB_BASE_REG,
@@ -1667,29 +1663,35 @@
 		FH_TSSR_TX_STATUS_REG,
 		FH_TSSR_TX_ERROR_REG
 	};
-#ifdef CONFIG_IWLWIFI_DEBUG
-	if (display) {
-		bufsz = ARRAY_SIZE(fh_tbl) * 48 + 40;
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	if (buf) {
+		int pos = 0;
+		size_t bufsz = ARRAY_SIZE(fh_tbl) * 48 + 40;
+
 		*buf = kmalloc(bufsz, GFP_KERNEL);
 		if (!*buf)
 			return -ENOMEM;
+
 		pos += scnprintf(*buf + pos, bufsz - pos,
 				"FH register values:\n");
-		for (i = 0; i < ARRAY_SIZE(fh_tbl); i++) {
+
+		for (i = 0; i < ARRAY_SIZE(fh_tbl); i++)
 			pos += scnprintf(*buf + pos, bufsz - pos,
 				"  %34s: 0X%08x\n",
 				get_fh_string(fh_tbl[i]),
 				iwl_read_direct32(trans, fh_tbl[i]));
-		}
+
 		return pos;
 	}
 #endif
+
 	IWL_ERR(trans, "FH register values:\n");
-	for (i = 0; i <  ARRAY_SIZE(fh_tbl); i++) {
+	for (i = 0; i <  ARRAY_SIZE(fh_tbl); i++)
 		IWL_ERR(trans, "  %34s: 0X%08x\n",
 			get_fh_string(fh_tbl[i]),
 			iwl_read_direct32(trans, fh_tbl[i]));
-	}
+
 	return 0;
 }
 
@@ -1982,11 +1984,11 @@
 				     size_t count, loff_t *ppos)
 {
 	struct iwl_trans *trans = file->private_data;
-	char *buf;
+	char *buf = NULL;
 	int pos = 0;
 	ssize_t ret = -EFAULT;
 
-	ret = pos = iwl_dump_fh(trans, &buf, true);
+	ret = pos = iwl_dump_fh(trans, &buf);
 	if (buf) {
 		ret = simple_read_from_buffer(user_buf,
 					      count, ppos, buf, pos);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 3089990..650f79a 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -57,8 +57,7 @@
 static const struct ethtool_ops xennet_ethtool_ops;
 
 struct netfront_cb {
-	struct page *page;
-	unsigned offset;
+	int pull_to;
 };
 
 #define NETFRONT_SKB_CB(skb)	((struct netfront_cb *)((skb)->cb))
@@ -867,15 +866,9 @@
 	struct sk_buff *skb;
 
 	while ((skb = __skb_dequeue(rxq)) != NULL) {
-		struct page *page = NETFRONT_SKB_CB(skb)->page;
-		void *vaddr = page_address(page);
-		unsigned offset = NETFRONT_SKB_CB(skb)->offset;
+		int pull_to = NETFRONT_SKB_CB(skb)->pull_to;
 
-		memcpy(skb->data, vaddr + offset,
-		       skb_headlen(skb));
-
-		if (page != skb_frag_page(&skb_shinfo(skb)->frags[0]))
-			__free_page(page);
+		__pskb_pull_tail(skb, pull_to - skb_headlen(skb));
 
 		/* Ethernet work: Delayed to here as it peeks the header. */
 		skb->protocol = eth_type_trans(skb, dev);
@@ -913,7 +906,6 @@
 	struct sk_buff_head errq;
 	struct sk_buff_head tmpq;
 	unsigned long flags;
-	unsigned int len;
 	int err;
 
 	spin_lock(&np->rx_lock);
@@ -955,24 +947,13 @@
 			}
 		}
 
-		NETFRONT_SKB_CB(skb)->page =
-			skb_frag_page(&skb_shinfo(skb)->frags[0]);
-		NETFRONT_SKB_CB(skb)->offset = rx->offset;
+		NETFRONT_SKB_CB(skb)->pull_to = rx->status;
+		if (NETFRONT_SKB_CB(skb)->pull_to > RX_COPY_THRESHOLD)
+			NETFRONT_SKB_CB(skb)->pull_to = RX_COPY_THRESHOLD;
 
-		len = rx->status;
-		if (len > RX_COPY_THRESHOLD)
-			len = RX_COPY_THRESHOLD;
-		skb_put(skb, len);
-
-		if (rx->status > len) {
-			skb_shinfo(skb)->frags[0].page_offset =
-				rx->offset + len;
-			skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status - len);
-			skb->data_len = rx->status - len;
-		} else {
-			__skb_fill_page_desc(skb, 0, NULL, 0, 0);
-			skb_shinfo(skb)->nr_frags = 0;
-		}
+		skb_shinfo(skb)->frags[0].page_offset = rx->offset;
+		skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx->status);
+		skb->data_len = rx->status;
 
 		i = xennet_fill_frags(np, skb, &tmpq);
 
@@ -999,7 +980,7 @@
 		 * receive throughout using the standard receive
 		 * buffer size was cut by 25%(!!!).
 		 */
-		skb->truesize += skb->data_len - (RX_COPY_THRESHOLD - len);
+		skb->truesize += skb->data_len - RX_COPY_THRESHOLD;
 		skb->len += skb->data_len;
 
 		if (rx->flags & XEN_NETRXF_csum_blank)
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 074923c..f0cf934 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1576,9 +1576,14 @@
 		/* result already set, check signature */
 		if (server->sec_mode &
 		    (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) {
-			if (cifs_verify_signature(rdata->iov, rdata->nr_iov,
-					  server, mid->sequence_number + 1))
-				cERROR(1, "Unexpected SMB signature");
+			int rc = 0;
+
+			rc = cifs_verify_signature(rdata->iov, rdata->nr_iov,
+						   server,
+						   mid->sequence_number + 1);
+			if (rc)
+				cERROR(1, "SMB signature verification returned "
+				       "error = %d", rc);
 		}
 		/* FIXME: should this be counted toward the initiating task? */
 		task_io_account_read(rdata->bytes);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index cbe709a..781025b 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -356,19 +356,12 @@
 cifs_create_set_dentry:
 	if (rc != 0) {
 		cFYI(1, "Create worked, get_inode_info failed rc = %d", rc);
+		CIFSSMBClose(xid, tcon, *fileHandle);
 		goto out;
 	}
 	d_drop(direntry);
 	d_add(direntry, newinode);
 
-	/* ENOENT for create?  How weird... */
-	rc = -ENOENT;
-	if (!newinode) {
-		CIFSSMBClose(xid, tcon, *fileHandle);
-		goto out;
-	}
-	rc = 0;
-
 out:
 	kfree(buf);
 	kfree(full_path);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7354877..cb79c7e 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -124,10 +124,10 @@
 {
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
-	unsigned long oldtime = cifs_i->time;
 
 	cifs_revalidate_cache(inode, fattr);
 
+	spin_lock(&inode->i_lock);
 	inode->i_atime = fattr->cf_atime;
 	inode->i_mtime = fattr->cf_mtime;
 	inode->i_ctime = fattr->cf_ctime;
@@ -148,9 +148,6 @@
 	else
 		cifs_i->time = jiffies;
 
-	cFYI(1, "inode 0x%p old_time=%ld new_time=%ld", inode,
-		 oldtime, cifs_i->time);
-
 	cifs_i->delete_pending = fattr->cf_flags & CIFS_FATTR_DELETE_PENDING;
 
 	cifs_i->server_eof = fattr->cf_eof;
@@ -158,7 +155,6 @@
 	 * Can't safely change the file size here if the client is writing to
 	 * it due to potential races.
 	 */
-	spin_lock(&inode->i_lock);
 	if (is_size_safe_to_change(cifs_i, fattr->cf_eof)) {
 		i_size_write(inode, fattr->cf_eof);
 
@@ -859,12 +855,14 @@
 
 	if (rc && tcon->ipc) {
 		cFYI(1, "ipc connection - fake read inode");
+		spin_lock(&inode->i_lock);
 		inode->i_mode |= S_IFDIR;
 		set_nlink(inode, 2);
 		inode->i_op = &cifs_ipc_inode_ops;
 		inode->i_fop = &simple_dir_operations;
 		inode->i_uid = cifs_sb->mnt_uid;
 		inode->i_gid = cifs_sb->mnt_gid;
+		spin_unlock(&inode->i_lock);
 	} else if (rc) {
 		iget_failed(inode);
 		inode = ERR_PTR(rc);
@@ -1110,6 +1108,15 @@
 	goto out_close;
 }
 
+/* copied from fs/nfs/dir.c with small changes */
+static void
+cifs_drop_nlink(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	if (inode->i_nlink > 0)
+		drop_nlink(inode);
+	spin_unlock(&inode->i_lock);
+}
 
 /*
  * If dentry->d_inode is null (usually meaning the cached dentry
@@ -1166,13 +1173,13 @@
 psx_del_no_retry:
 	if (!rc) {
 		if (inode)
-			drop_nlink(inode);
+			cifs_drop_nlink(inode);
 	} else if (rc == -ENOENT) {
 		d_drop(dentry);
 	} else if (rc == -ETXTBSY) {
 		rc = cifs_rename_pending_delete(full_path, dentry, xid);
 		if (rc == 0)
-			drop_nlink(inode);
+			cifs_drop_nlink(inode);
 	} else if ((rc == -EACCES) && (dosattr == 0) && inode) {
 		attrs = kzalloc(sizeof(*attrs), GFP_KERNEL);
 		if (attrs == NULL) {
@@ -1241,9 +1248,10 @@
 	 * setting nlink not necessary except in cases where we failed to get it
 	 * from the server or was set bogus
 	 */
+	spin_lock(&dentry->d_inode->i_lock);
 	if ((dentry->d_inode) && (dentry->d_inode->i_nlink < 2))
 		set_nlink(dentry->d_inode, 2);
-
+	spin_unlock(&dentry->d_inode->i_lock);
 	mode &= ~current_umask();
 	/* must turn on setgid bit if parent dir has it */
 	if (inode->i_mode & S_ISGID)
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 09e4b3a..e6ce3b1 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -433,7 +433,9 @@
 	if (old_file->d_inode) {
 		cifsInode = CIFS_I(old_file->d_inode);
 		if (rc == 0) {
+			spin_lock(&old_file->d_inode->i_lock);
 			inc_nlink(old_file->d_inode);
+			spin_unlock(&old_file->d_inode->i_lock);
 /* BB should we make this contingent on superblock flag NOATIME? */
 /*			old_file->d_inode->i_ctime = CURRENT_TIME;*/
 			/* parent dir timestamps will update from srv
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index a4ff5d5..e4d3b99 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -52,7 +52,8 @@
 			cERROR(1, "Bad protocol string signature header %x",
 				  *(unsigned int *) hdr->ProtocolId);
 		if (mid != hdr->MessageId)
-			cERROR(1, "Mids do not match");
+			cERROR(1, "Mids do not match: %llu and %llu", mid,
+				  hdr->MessageId);
 	}
 	cERROR(1, "Bad SMB detected. The Mid=%llu", hdr->MessageId);
 	return 1;
@@ -107,7 +108,7 @@
 	 * ie Validate the wct via smb2_struct_sizes table above
 	 */
 
-	if (length < 2 + sizeof(struct smb2_hdr)) {
+	if (length < sizeof(struct smb2_pdu)) {
 		if ((length >= sizeof(struct smb2_hdr)) && (hdr->Status != 0)) {
 			pdu->StructureSize2 = 0;
 			/*
@@ -121,15 +122,15 @@
 		return 1;
 	}
 	if (len > CIFSMaxBufSize + MAX_SMB2_HDR_SIZE - 4) {
-		cERROR(1, "SMB length greater than maximum, mid=%lld", mid);
+		cERROR(1, "SMB length greater than maximum, mid=%llu", mid);
 		return 1;
 	}
 
 	if (check_smb2_hdr(hdr, mid))
 		return 1;
 
-	if (hdr->StructureSize != SMB2_HEADER_SIZE) {
-		cERROR(1, "Illegal structure size %d",
+	if (hdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
+		cERROR(1, "Illegal structure size %u",
 			  le16_to_cpu(hdr->StructureSize));
 		return 1;
 	}
@@ -161,8 +162,9 @@
 	if (4 + len != clc_len) {
 		cFYI(1, "Calculated size %u length %u mismatch mid %llu",
 			clc_len, 4 + len, mid);
-		if (clc_len == 4 + len + 1) /* BB FIXME (fix samba) */
-			return 0; /* BB workaround Samba 3 bug SessSetup rsp */
+		/* server can return one byte more */
+		if (clc_len == 4 + len + 1)
+			return 0;
 		return 1;
 	}
 	return 0;
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index f37a1b4..c5fbfac 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -87,10 +87,6 @@
 
 #define SMB2_PROTO_NUMBER __constant_cpu_to_le32(0x424d53fe)
 
-#define SMB2_HEADER_SIZE __constant_le16_to_cpu(64)
-
-#define SMB2_ERROR_STRUCTURE_SIZE2 __constant_le16_to_cpu(9)
-
 /*
  * SMB2 Header Definition
  *
@@ -99,6 +95,9 @@
  * "PDU" :  "Protocol Data Unit" (ie a network "frame")
  *
  */
+
+#define SMB2_HEADER_STRUCTURE_SIZE __constant_le16_to_cpu(64)
+
 struct smb2_hdr {
 	__be32 smb2_buf_length;	/* big endian on wire */
 				/* length is only two or three bytes - with
@@ -140,6 +139,9 @@
  *  command code name for the struct. Note that structures must be packed.
  *
  */
+
+#define SMB2_ERROR_STRUCTURE_SIZE2 __constant_le16_to_cpu(9)
+
 struct smb2_err_rsp {
 	struct smb2_hdr hdr;
 	__le16 StructureSize;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 83867ef..d9b639b 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -503,13 +503,16 @@
 	/* convert the length into a more usable form */
 	if (server->sec_mode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED)) {
 		struct kvec iov;
+		int rc = 0;
 
 		iov.iov_base = mid->resp_buf;
 		iov.iov_len = len;
 		/* FIXME: add code to kill session */
-		if (cifs_verify_signature(&iov, 1, server,
-					  mid->sequence_number + 1) != 0)
-			cERROR(1, "Unexpected SMB signature");
+		rc = cifs_verify_signature(&iov, 1, server,
+					   mid->sequence_number + 1);
+		if (rc)
+			cERROR(1, "SMB signature verification returned error = "
+			       "%d", rc);
 	}
 
 	/* BB special case reconnect tid and uid here? */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index fc35260..6b4565c 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2149,7 +2149,7 @@
 #define PCI_DEVICE_ID_TIGON3_5704S	0x16a8
 #define PCI_DEVICE_ID_NX2_57800_VF	0x16a9
 #define PCI_DEVICE_ID_NX2_5706S		0x16aa
-#define PCI_DEVICE_ID_NX2_57840_MF	0x16ab
+#define PCI_DEVICE_ID_NX2_57840_MF	0x16a4
 #define PCI_DEVICE_ID_NX2_5708S		0x16ac
 #define PCI_DEVICE_ID_NX2_57840_VF	0x16ad
 #define PCI_DEVICE_ID_NX2_57810_MF	0x16ae
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index e1ce104..4a045cd 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -18,6 +18,7 @@
 	u16 ctmask;		/* bitmask of ct events to be delivered */
 	u16 expmask;		/* bitmask of expect events to be delivered */
 	u32 pid;		/* netlink pid of destroyer */
+	struct timer_list timeout;
 };
 
 static inline struct nf_conntrack_ecache *
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 346b1eb..e4ba3e7 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -168,24 +168,16 @@
 	struct napi_struct *napi;
 	int budget = 16;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
 	list_for_each_entry(napi, &dev->napi_list, dev_list) {
-		local_irq_enable();
 		if (napi->poll_owner != smp_processor_id() &&
 		    spin_trylock(&napi->poll_lock)) {
-			rcu_read_lock_bh();
 			budget = poll_one_napi(rcu_dereference_bh(dev->npinfo),
 					       napi, budget);
-			rcu_read_unlock_bh();
 			spin_unlock(&napi->poll_lock);
 
-			if (!budget) {
-				local_irq_disable();
+			if (!budget)
 				break;
-			}
 		}
-		local_irq_disable();
 	}
 }
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 8eec8f4..ebdf06f 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -124,6 +124,8 @@
 static struct kmem_cache *mrt_cachep __read_mostly;
 
 static struct mr_table *ipmr_new_table(struct net *net, u32 id);
+static void ipmr_free_table(struct mr_table *mrt);
+
 static int ip_mr_forward(struct net *net, struct mr_table *mrt,
 			 struct sk_buff *skb, struct mfc_cache *cache,
 			 int local);
@@ -131,6 +133,7 @@
 			     struct sk_buff *pkt, vifi_t vifi, int assert);
 static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 			      struct mfc_cache *c, struct rtmsg *rtm);
+static void mroute_clean_tables(struct mr_table *mrt);
 static void ipmr_expire_process(unsigned long arg);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -271,7 +274,7 @@
 
 	list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) {
 		list_del(&mrt->list);
-		kfree(mrt);
+		ipmr_free_table(mrt);
 	}
 	fib_rules_unregister(net->ipv4.mr_rules_ops);
 }
@@ -299,7 +302,7 @@
 
 static void __net_exit ipmr_rules_exit(struct net *net)
 {
-	kfree(net->ipv4.mrt);
+	ipmr_free_table(net->ipv4.mrt);
 }
 #endif
 
@@ -336,6 +339,13 @@
 	return mrt;
 }
 
+static void ipmr_free_table(struct mr_table *mrt)
+{
+	del_timer_sync(&mrt->ipmr_expire_timer);
+	mroute_clean_tables(mrt);
+	kfree(mrt);
+}
+
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
 
 static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v)
diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c
index 4ad9cf1..9c87cde 100644
--- a/net/ipv4/netfilter/nf_nat_sip.c
+++ b/net/ipv4/netfilter/nf_nat_sip.c
@@ -502,7 +502,10 @@
 		ret = nf_ct_expect_related(rtcp_exp);
 		if (ret == 0)
 			break;
-		else if (ret != -EBUSY) {
+		else if (ret == -EBUSY) {
+			nf_ct_unexpect_related(rtp_exp);
+			continue;
+		} else if (ret < 0) {
 			nf_ct_unexpect_related(rtp_exp);
 			port = 0;
 			break;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fd9ecb5..82cf2a7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -934,12 +934,14 @@
 	if (mtu < ip_rt_min_pmtu)
 		mtu = ip_rt_min_pmtu;
 
+	rcu_read_lock();
 	if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
 		struct fib_nh *nh = &FIB_RES_NH(res);
 
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
 				      jiffies + ip_rt_mtu_expires);
 	}
+	rcu_read_unlock();
 	return mtu;
 }
 
@@ -956,7 +958,7 @@
 		dst->obsolete = DST_OBSOLETE_KILL;
 	} else {
 		rt->rt_pmtu = mtu;
-		dst_set_expires(&rt->dst, ip_rt_mtu_expires);
+		rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires);
 	}
 }
 
@@ -1263,7 +1265,7 @@
 {
 	struct rtable *rt = (struct rtable *) dst;
 
-	if (dst->flags & DST_NOCACHE) {
+	if (!list_empty(&rt->rt_uncached)) {
 		spin_lock_bh(&rt_uncached_lock);
 		list_del(&rt->rt_uncached);
 		spin_unlock_bh(&rt_uncached_lock);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 85308b9..6e38c6c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2926,13 +2926,14 @@
  * tcp_xmit_retransmit_queue().
  */
 static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
-				  int newly_acked_sacked, bool is_dupack,
+				  int prior_sacked, bool is_dupack,
 				  int flag)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
 				    (tcp_fackets_out(tp) > tp->reordering));
+	int newly_acked_sacked = 0;
 	int fast_rexmit = 0;
 
 	if (WARN_ON(!tp->packets_out && tp->sacked_out))
@@ -2992,6 +2993,7 @@
 				tcp_add_reno_sack(sk);
 		} else
 			do_lost = tcp_try_undo_partial(sk, pkts_acked);
+		newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked;
 		break;
 	case TCP_CA_Loss:
 		if (flag & FLAG_DATA_ACKED)
@@ -3013,6 +3015,7 @@
 			if (is_dupack)
 				tcp_add_reno_sack(sk);
 		}
+		newly_acked_sacked = pkts_acked + tp->sacked_out - prior_sacked;
 
 		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
 			tcp_try_undo_dsack(sk);
@@ -3590,7 +3593,6 @@
 	int prior_packets;
 	int prior_sacked = tp->sacked_out;
 	int pkts_acked = 0;
-	int newly_acked_sacked = 0;
 	bool frto_cwnd = false;
 
 	/* If the ack is older than previous acks
@@ -3666,8 +3668,6 @@
 	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
 
 	pkts_acked = prior_packets - tp->packets_out;
-	newly_acked_sacked = (prior_packets - prior_sacked) -
-			     (tp->packets_out - tp->sacked_out);
 
 	if (tp->frto_counter)
 		frto_cwnd = tcp_process_frto(sk, flag);
@@ -3681,7 +3681,7 @@
 		    tcp_may_raise_cwnd(sk, flag))
 			tcp_cong_avoid(sk, ack, prior_in_flight);
 		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
-		tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+		tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
 				      is_dupack, flag);
 	} else {
 		if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
@@ -3698,7 +3698,7 @@
 no_queue:
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
 	if (flag & FLAG_DSACKING_ACK)
-		tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+		tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
 				      is_dupack, flag);
 	/* If this ack opens up a zero window, clear backoff.  It was
 	 * being used to time the probes, and is probably far higher than
@@ -3718,8 +3718,7 @@
 	 */
 	if (TCP_SKB_CB(skb)->sacked) {
 		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
-		newly_acked_sacked = tp->sacked_out - prior_sacked;
-		tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+		tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
 				      is_dupack, flag);
 	}
 
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 6dc7fd3..282f372 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -167,8 +167,6 @@
 	struct esp_data *esp = x->data;
 
 	/* skb is pure payload to encrypt */
-	err = -ENOMEM;
-
 	aead = esp->aead;
 	alen = crypto_aead_authsize(aead);
 
@@ -203,8 +201,10 @@
 	}
 
 	tmp = esp_alloc_tmp(aead, nfrags + sglists, seqhilen);
-	if (!tmp)
+	if (!tmp) {
+		err = -ENOMEM;
 		goto error;
+	}
 
 	seqhi = esp_tmp_seqhi(tmp);
 	iv = esp_tmp_iv(aead, tmp, seqhilen);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 393355d..513cab0 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1347,11 +1347,10 @@
 	/* Remove from tunnel list */
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
 	list_del_rcu(&tunnel->list);
+	kfree_rcu(tunnel, rcu);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
-	synchronize_rcu();
 
 	atomic_dec(&l2tp_tunnel_count);
-	kfree(tunnel);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a38ec6c..56d583e 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -163,6 +163,7 @@
 
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
+	struct rcu_head rcu;
 	rwlock_t		hlist_lock;	/* protect session_hlist */
 	struct hlist_head	session_hlist[L2TP_HASH_SIZE];
 						/* hashed list of sessions,
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index acf712f..c5e8c9c 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1811,37 +1811,31 @@
 			meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr,
 					sdata, NULL, NULL);
 		} else {
-			int is_mesh_mcast = 1;
-			const u8 *mesh_da;
+			/* DS -> MBSS (802.11-2012 13.11.3.3).
+			 * For unicast with unknown forwarding information,
+			 * destination might be in the MBSS or if that fails
+			 * forwarded to another mesh gate. In either case
+			 * resolution will be handled in ieee80211_xmit(), so
+			 * leave the original DA. This also works for mcast */
+			const u8 *mesh_da = skb->data;
 
-			if (is_multicast_ether_addr(skb->data))
-				/* DA TA mSA AE:SA */
-				mesh_da = skb->data;
-			else {
-				static const u8 bcast[ETH_ALEN] =
-					{ 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
-				if (mppath) {
-					/* RA TA mDA mSA AE:DA SA */
-					mesh_da = mppath->mpp;
-					is_mesh_mcast = 0;
-				} else if (mpath) {
-					mesh_da = mpath->dst;
-					is_mesh_mcast = 0;
-				} else {
-					/* DA TA mSA AE:SA */
-					mesh_da = bcast;
-				}
-			}
+			if (mppath)
+				mesh_da = mppath->mpp;
+			else if (mpath)
+				mesh_da = mpath->dst;
+			rcu_read_unlock();
+
 			hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc,
 					mesh_da, sdata->vif.addr);
-			rcu_read_unlock();
-			if (is_mesh_mcast)
+			if (is_multicast_ether_addr(mesh_da))
+				/* DA TA mSA AE:SA */
 				meshhdrlen =
 					ieee80211_new_mesh_header(&mesh_hdr,
 							sdata,
 							skb->data + ETH_ALEN,
 							NULL);
 			else
+				/* RA TA mDA mSA AE:DA SA */
 				meshhdrlen =
 					ieee80211_new_mesh_header(&mesh_hdr,
 							sdata,
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 72bf32a..f51013c 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1171,8 +1171,10 @@
 		goto out_err;
 	}
 	svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
-	if (!svc->stats.cpustats)
+	if (!svc->stats.cpustats) {
+		ret = -ENOMEM;
 		goto out_err;
+	}
 
 	/* I'm the first user of the service */
 	atomic_set(&svc->usecnt, 0);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index cf48755..2ceec64 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -249,12 +249,15 @@
 {
 	struct nf_conn *ct = (void *)ul_conntrack;
 	struct net *net = nf_ct_net(ct);
+	struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
+
+	BUG_ON(ecache == NULL);
 
 	if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) {
 		/* bad luck, let's retry again */
-		ct->timeout.expires = jiffies +
+		ecache->timeout.expires = jiffies +
 			(random32() % net->ct.sysctl_events_retry_timeout);
-		add_timer(&ct->timeout);
+		add_timer(&ecache->timeout);
 		return;
 	}
 	/* we've got the event delivered, now it's dying */
@@ -268,6 +271,9 @@
 void nf_ct_insert_dying_list(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
+	struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
+
+	BUG_ON(ecache == NULL);
 
 	/* add this conntrack to the dying list */
 	spin_lock_bh(&nf_conntrack_lock);
@@ -275,10 +281,10 @@
 			     &net->ct.dying);
 	spin_unlock_bh(&nf_conntrack_lock);
 	/* set a new timer to retry event delivery */
-	setup_timer(&ct->timeout, death_by_event, (unsigned long)ct);
-	ct->timeout.expires = jiffies +
+	setup_timer(&ecache->timeout, death_by_event, (unsigned long)ct);
+	ecache->timeout.expires = jiffies +
 		(random32() % net->ct.sysctl_events_retry_timeout);
-	add_timer(&ct->timeout);
+	add_timer(&ecache->timeout);
 }
 EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index da4fc37..9807f32 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2790,7 +2790,8 @@
 		goto err_unreg_subsys;
 	}
 
-	if (register_pernet_subsys(&ctnetlink_net_ops)) {
+	ret = register_pernet_subsys(&ctnetlink_net_ops);
+	if (ret < 0) {
 		pr_err("ctnetlink_init: cannot register pernet operations\n");
 		goto err_unreg_exp_subsys;
 	}
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 169ab59..14e2f39 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -480,7 +480,7 @@
 	}
 
 	if (indev && skb_mac_header_was_set(skb)) {
-		if (nla_put_be32(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) ||
+		if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) ||
 		    nla_put_be16(inst->skb, NFULA_HWLEN,
 				 htons(skb->dev->hard_header_len)) ||
 		    nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len,
@@ -996,8 +996,10 @@
 
 #ifdef CONFIG_PROC_FS
 	if (!proc_create("nfnetlink_log", 0440,
-			 proc_net_netfilter, &nful_file_ops))
+			 proc_net_netfilter, &nful_file_ops)) {
+		status = -ENOMEM;
 		goto cleanup_logger;
+	}
 #endif
 	return status;
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 1445d73..5270238 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1373,7 +1373,8 @@
 		dst_pid = addr->nl_pid;
 		dst_group = ffs(addr->nl_groups);
 		err =  -EPERM;
-		if (dst_group && !netlink_capable(sock, NL_NONROOT_SEND))
+		if ((dst_group || dst_pid) &&
+		    !netlink_capable(sock, NL_NONROOT_SEND))
 			goto out;
 	} else {
 		dst_pid = nlk->dst_pid;
@@ -2147,6 +2148,7 @@
 	rcu_assign_pointer(nl_table[NETLINK_USERSOCK].listeners, listeners);
 	nl_table[NETLINK_USERSOCK].module = THIS_MODULE;
 	nl_table[NETLINK_USERSOCK].registered = 1;
+	nl_table[NETLINK_USERSOCK].nl_nonroot = NL_NONROOT_SEND;
 
 	netlink_table_ungrab();
 }
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index aee7196..c5c9e2a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1273,7 +1273,7 @@
 	spin_unlock(&f->lock);
 }
 
-bool match_fanout_group(struct packet_type *ptype, struct sock * sk)
+static bool match_fanout_group(struct packet_type *ptype, struct sock * sk)
 {
 	if (ptype->af_packet_priv == (void*)((struct packet_sock *)sk)->fanout)
 		return true;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 87cd0e4..210be48 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1994,8 +1994,10 @@
 		goto error;
 
 	x->outer_mode = xfrm_get_mode(x->props.mode, family);
-	if (x->outer_mode == NULL)
+	if (x->outer_mode == NULL) {
+		err = -EPROTONOSUPPORT;
 		goto error;
+	}
 
 	if (init_replay) {
 		err = xfrm_init_replay(x);