Merge branch 'devel/debug_ll_init' into zynq/multiplatform

23 files changed, 214 insertions, 201 deletions

diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index 195ac2f9d3d3..2fe141fcc8d6 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -40,6 +40,13 @@ extern void iotable_init(struct map_desc *, int);
 extern void vm_reserve_area_early(unsigned long addr, unsigned long size,
 				  void *caller);
 
+#ifdef CONFIG_DEBUG_LL
+extern void debug_ll_addr(unsigned long *paddr, unsigned long *vaddr);
+extern void debug_ll_io_init(void);
+#else
+static inline void debug_ll_io_init(void) {}
+#endif
+
 struct mem_type;
 extern const struct mem_type *get_mem_type(unsigned int type);
 /*
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index 66f711b2e0e8..6809200c31fb 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -100,6 +100,13 @@ ENTRY(printch)
 		b	1b
 ENDPROC(printch)
 
+ENTRY(debug_ll_addr)
+		addruart r2, r3, ip
+		str	r2, [r0]
+		str	r3, [r1]
+		mov	pc, lr
+ENDPROC(debug_ll_addr)
+
 #else
 
 ENTRY(printascii)
@@ -119,4 +126,11 @@ ENTRY(printch)
 		mov	pc, lr
 ENDPROC(printch)
 
+ENTRY(debug_ll_addr)
+		mov	r2, #0
+		str	r2, [r0]
+		str	r2, [r1]
+		mov	pc, lr
+ENDPROC(debug_ll_addr)
+
 #endif
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 941dfb9e9a78..39719bb93caa 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -876,6 +876,22 @@ static void __init pci_reserve_io(void)
 #define pci_reserve_io() do { } while (0)
 #endif
 
+#ifdef CONFIG_DEBUG_LL
+void __init debug_ll_io_init(void)
+{
+	struct map_desc map;
+
+	debug_ll_addr(&map.pfn, &map.virtual);
+	if (!map.pfn || !map.virtual)
+		return;
+	map.pfn = __phys_to_pfn(map.pfn);
+	map.virtual &= PAGE_MASK;
+	map.length = PAGE_SIZE;
+	map.type = MT_DEVICE;
+	create_mapping(&map);
+}
+#endif
+
 static void * __initdata vmalloc_min =
 	(void *)(VMALLOC_END - (240 << 20) - VMALLOC_OFFSET);
 
diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
index 074f5ed101b9..71f723984cbd 100644
--- a/arch/arm/xen/hypercall.S
+++ b/arch/arm/xen/hypercall.S
@@ -48,20 +48,16 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/opcodes-virt.h>
 #include <xen/interface/xen.h>
 
 
-/* HVC 0xEA1 */
-#ifdef CONFIG_THUMB2_KERNEL
-#define xen_hvc .word 0xf7e08ea1
-#else
-#define xen_hvc .word 0xe140ea71
-#endif
+#define XEN_IMM 0xEA1
 
 #define HYPERCALL_SIMPLE(hypercall)		\
 ENTRY(HYPERVISOR_##hypercall)			\
 	mov r12, #__HYPERVISOR_##hypercall;	\
-	xen_hvc;							\
+	__HVC(XEN_IMM);						\
 	mov pc, lr;							\
 ENDPROC(HYPERVISOR_##hypercall)
 
@@ -76,7 +72,7 @@ ENTRY(HYPERVISOR_##hypercall)			\
 	stmdb sp!, {r4}						\
 	ldr r4, [sp, #4]					\
 	mov r12, #__HYPERVISOR_##hypercall;	\
-	xen_hvc								\
+	__HVC(XEN_IMM);						\
 	ldm sp!, {r4}						\
 	mov pc, lr							\
 ENDPROC(HYPERVISOR_##hypercall)
@@ -100,7 +96,7 @@ ENTRY(privcmd_call)
 	mov r2, r3
 	ldr r3, [sp, #8]
 	ldr r4, [sp, #4]
-	xen_hvc
+	__HVC(XEN_IMM)
 	ldm sp!, {r4}
 	mov pc, lr
 ENDPROC(privcmd_call);
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index b7412504f08a..df2eb4bd9fa2 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -13,6 +13,7 @@ config FRV
 	select GENERIC_CPU_DEVICES
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 
 config ZONE_DMA
 	bool
diff --git a/arch/frv/boot/Makefile b/arch/frv/boot/Makefile
index 6ae3254da019..636d5bbcd53f 100644
--- a/arch/frv/boot/Makefile
+++ b/arch/frv/boot/Makefile
@@ -17,6 +17,8 @@ PARAMS_PHYS	 = 0x0207c000
 INITRD_PHYS	 = 0x02180000
 INITRD_VIRT	 = 0x02180000
 
+OBJCOPYFLAGS	:=-O binary -R .note -R .note.gnu.build-id -R .comment
+
 #
 # If you don't define ZRELADDR above,
 # then it defaults to ZTEXTADDR
@@ -32,18 +34,18 @@ Image: $(obj)/Image
 targets: $(obj)/Image
 
 $(obj)/Image: vmlinux FORCE
-	$(OBJCOPY) -O binary -R .note -R .comment -S vmlinux $@
+	$(OBJCOPY) $(OBJCOPYFLAGS) -S vmlinux $@
 
 #$(obj)/Image:	$(CONFIGURE) $(SYSTEM)
-#	$(OBJCOPY) -O binary -R .note -R .comment -g -S $(SYSTEM) $@
+#	$(OBJCOPY) $(OBJCOPYFLAGS) -g -S $(SYSTEM) $@
 
 bzImage: zImage
 
 zImage:	$(CONFIGURE) compressed/$(LINUX)
-	$(OBJCOPY) -O binary -R .note -R .comment -S compressed/$(LINUX) $@
+	$(OBJCOPY) $(OBJCOPYFLAGS) -S compressed/$(LINUX) $@
 
 bootpImage: bootp/bootp
-	$(OBJCOPY) -O binary -R .note -R .comment -S bootp/bootp $@
+	$(OBJCOPY) $(OBJCOPYFLAGS) -S bootp/bootp $@
 
 compressed/$(LINUX): $(LINUX) dep
 	@$(MAKE) -C compressed $(LINUX)
diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h
index 266a5b25a0c1..2358634cacca 100644
--- a/arch/frv/include/asm/unistd.h
+++ b/arch/frv/include/asm/unistd.h
@@ -30,7 +30,6 @@
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
 #define __ARCH_WANT_SYS_EXECVE
-#define __ARCH_WANT_KERNEL_EXECVE
 
 /*
  * "Conditional" syscalls
diff --git a/arch/frv/kernel/entry.S b/arch/frv/kernel/entry.S
index ee0beb354e4d..dfcd263c0517 100644
--- a/arch/frv/kernel/entry.S
+++ b/arch/frv/kernel/entry.S
@@ -869,11 +869,6 @@ ret_from_kernel_thread:
 	call		schedule_tail
 	calll.p		@(gr21,gr0)
 	or		gr20,gr20,gr8
-	bra		sys_exit
-
-	.globl		ret_from_kernel_execve
-ret_from_kernel_execve:
-	ori		gr28,0,sp
 	bra		__syscall_exit
 
 ###################################################################################################
@@ -1080,27 +1075,10 @@ __entry_return_from_kernel_interrupt:
 	subicc		gr5,#0,gr0,icc0
 	beq		icc0,#0,__entry_return_direct
 
-__entry_preempt_need_resched:
-	ldi		@(gr15,#TI_FLAGS),gr4
-	andicc		gr4,#_TIF_NEED_RESCHED,gr0,icc0
-	beq		icc0,#1,__entry_return_direct
-
-	setlos		#PREEMPT_ACTIVE,gr5
-	sti		gr5,@(gr15,#TI_FLAGS)
-
-	andi		gr23,#~PSR_PIL,gr23
-	movgs		gr23,psr
-
-	call		schedule
-	sti		gr0,@(gr15,#TI_PRE_COUNT)
-
-	movsg		psr,gr23
-	ori		gr23,#PSR_PIL_14,gr23
-	movgs		gr23,psr
-	bra		__entry_preempt_need_resched
-#else
-	bra		__entry_return_direct
+	subcc		gr0,gr0,gr0,icc2		/* set Z and clear C */
+	call		preempt_schedule_irq
 #endif
+	bra		__entry_return_direct
 
 
 ###############################################################################
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index e1e3aa196aa4..7e33215f1d8f 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -181,6 +181,9 @@ int copy_thread(unsigned long clone_flags,
 	childregs = (struct pt_regs *)
 		(task_stack_page(p) + THREAD_SIZE - FRV_FRAME0_SIZE);
 
+	/* set up the userspace frame (the only place that the USP is stored) */
+	*childregs = *__kernel_frame0_ptr;
+
 	p->set_child_tid = p->clear_child_tid = NULL;
 
 	p->thread.frame	 = childregs;
@@ -191,10 +194,8 @@ int copy_thread(unsigned long clone_flags,
 	p->thread.frame0 = childregs;
 
 	if (unlikely(!regs)) {
-		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gr9 = usp; /* function */
 		childregs->gr8 = arg;
-		childregs->psr = PSR_S;
 		p->thread.pc = (unsigned long) ret_from_kernel_thread;
 		save_user_regs(p->thread.user);
 		return 0;
diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c
index e47857f889b6..b99c2a7cc7a4 100644
--- a/arch/frv/mb93090-mb00/pci-dma-nommu.c
+++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c
@@ -11,6 +11,7 @@
 
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/export.h>
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/pci.h>
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 66d0fff1ee84..125f344f06a9 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -33,7 +33,6 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
 
-/* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1eefebe5d727..224a7e78cb6c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3779,7 +3779,7 @@ static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 {
 	struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
 
-	memcpy(vcpu->run->mmio.data, frag->data, frag->len);
+	memcpy(vcpu->run->mmio.data, frag->data, min(8u, frag->len));
 	return X86EMUL_CONTINUE;
 }
 
@@ -3832,18 +3832,11 @@ mmio:
 	bytes -= handled;
 	val += handled;
 
-	while (bytes) {
-		unsigned now = min(bytes, 8U);
-
-		frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
-		frag->gpa = gpa;
-		frag->data = val;
-		frag->len = now;
-
-		gpa += now;
-		val += now;
-		bytes -= now;
-	}
+	WARN_ON(vcpu->mmio_nr_fragments >= KVM_MAX_MMIO_FRAGMENTS);
+	frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
+	frag->gpa = gpa;
+	frag->data = val;
+	frag->len = bytes;
 	return X86EMUL_CONTINUE;
 }
 
@@ -3890,7 +3883,7 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_cur_fragment = 0;
 
-	vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+	vcpu->run->mmio.len = min(8u, vcpu->mmio_fragments[0].len);
 	vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
 	vcpu->run->exit_reason = KVM_EXIT_MMIO;
 	vcpu->run->mmio.phys_addr = gpa;
@@ -5522,28 +5515,44 @@ static int complete_emulated_pio(struct kvm_vcpu *vcpu)
  *
  * read:
  *   for each fragment
- *     write gpa, len
- *     exit
- *     copy data
+ *     for each mmio piece in the fragment
+ *       write gpa, len
+ *       exit
+ *       copy data
  *   execute insn
  *
  * write:
  *   for each fragment
- *      write gpa, len
- *      copy data
- *      exit
+ *     for each mmio piece in the fragment
+ *       write gpa, len
+ *       copy data
+ *       exit
  */
 static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	struct kvm_mmio_fragment *frag;
+	unsigned len;
 
 	BUG_ON(!vcpu->mmio_needed);
 
 	/* Complete previous fragment */
-	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
+	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment];
+	len = min(8u, frag->len);
 	if (!vcpu->mmio_is_write)
-		memcpy(frag->data, run->mmio.data, frag->len);
+		memcpy(frag->data, run->mmio.data, len);
+
+	if (frag->len <= 8) {
+		/* Switch to the next fragment. */
+		frag++;
+		vcpu->mmio_cur_fragment++;
+	} else {
+		/* Go forward to the next mmio piece. */
+		frag->data += len;
+		frag->gpa += len;
+		frag->len -= len;
+	}
+
 	if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
 		vcpu->mmio_needed = 0;
 		if (vcpu->mmio_is_write)
@@ -5551,13 +5560,12 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
 		vcpu->mmio_read_completed = 1;
 		return complete_emulated_io(vcpu);
 	}
-	/* Initiate next fragment */
-	++frag;
+
 	run->exit_reason = KVM_EXIT_MMIO;
 	run->mmio.phys_addr = frag->gpa;
 	if (vcpu->mmio_is_write)
-		memcpy(run->mmio.data, frag->data, frag->len);
-	run->mmio.len = frag->len;
+		memcpy(run->mmio.data, frag->data, min(8u, frag->len));
+	run->mmio.len = min(8u, frag->len);
 	run->mmio.is_write = vcpu->mmio_is_write;
 	vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	return 0;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 6226c99729b9..dcf5f2dd91ec 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1288,6 +1288,25 @@ unsigned long xen_read_cr2_direct(void)
 	return this_cpu_read(xen_vcpu_info.arch.cr2);
 }
 
+void xen_flush_tlb_all(void)
+{
+	struct mmuext_op *op;
+	struct multicall_space mcs;
+
+	trace_xen_mmu_flush_tlb_all(0);
+
+	preempt_disable();
+
+	mcs = xen_mc_entry(sizeof(*op));
+
+	op = mcs.args;
+	op->cmd = MMUEXT_TLB_FLUSH_ALL;
+	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+
+	xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+	preempt_enable();
+}
 static void xen_flush_tlb(void)
 {
 	struct mmuext_op *op;
@@ -2518,7 +2537,7 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 	err = 0;
 out:
 
-	flush_tlb_all();
+	xen_flush_tlb_all();
 
 	return err;
 }
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index cdcb48adee4c..0d1f36a22c98 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -13,6 +13,8 @@ config XTENSA
 	select GENERIC_CPU_DEVICES
 	select MODULES_USE_ELF_RELA
 	select GENERIC_PCI_IOMAP
+	select GENERIC_KERNEL_THREAD
+	select GENERIC_KERNEL_EXECVE
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index e6be5b9091c2..700c2e6f2d25 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -62,6 +62,10 @@ static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
 static inline void iounmap(volatile void __iomem *addr)
 {
 }
+
+#define virt_to_bus     virt_to_phys
+#define bus_to_virt     phys_to_virt
+
 #endif /* CONFIG_MMU */
 
 /*
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 5c371d8d4528..2d630e7399ca 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -152,6 +152,7 @@ struct thread_struct {
 
 /* Clearing a0 terminates the backtrace. */
 #define start_thread(regs, new_pc, new_sp) \
+	memset(regs, 0, sizeof(*regs)); \
 	regs->pc = new_pc; \
 	regs->ps = USER_PS_VALUE; \
 	regs->areg[1] = new_sp; \
@@ -168,9 +169,6 @@ struct mm_struct;
 /* Free all resources held by a thread. */
 #define release_thread(thread) do { } while(0)
 
-/* Create a kernel thread without removing it from tasklists */
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
 /* Copy and release all segment info associated with a VM */
 #define copy_segments(p, mm)	do { } while(0)
 #define release_segments(mm)	do { } while(0)
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index c1dacca312f3..124aeee0d381 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -10,7 +10,7 @@
 
 struct pt_regs;
 struct sigaction;
-asmlinkage long xtensa_execve(char*, char**, char**, struct pt_regs*);
+asmlinkage long sys_execve(char*, char**, char**, struct pt_regs*);
 asmlinkage long xtensa_clone(unsigned long, unsigned long, struct pt_regs*);
 asmlinkage long xtensa_ptrace(long, long, long, long);
 asmlinkage long xtensa_sigreturn(struct pt_regs*);
diff --git a/arch/xtensa/include/asm/unistd.h b/arch/xtensa/include/asm/unistd.h
index 9ef1c31d2c83..f4e6eaa40d1c 100644
--- a/arch/xtensa/include/asm/unistd.h
+++ b/arch/xtensa/include/asm/unistd.h
@@ -1,16 +1,9 @@
-/*
- * include/asm-xtensa/unistd.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
- */
+#ifndef _XTENSA_UNISTD_H
+#define _XTENSA_UNISTD_H
 
+#define __ARCH_WANT_SYS_EXECVE
 #include <uapi/asm/unistd.h>
 
-
 /*
  * "Conditional" syscalls
  *
@@ -37,3 +30,5 @@
 #define __IGNORE_mmap				/* use mmap2 */
 #define __IGNORE_vfork				/* use clone */
 #define __IGNORE_fadvise64			/* use fadvise64_64 */
+
+#endif /* _XTENSA_UNISTD_H */
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 479abaea5aae..9f36d0e3e0ac 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -1,14 +1,4 @@
-/*
- * include/asm-xtensa/unistd.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2012 Tensilica Inc.
- */
-
-#ifndef _UAPI_XTENSA_UNISTD_H
+#if !defined(_UAPI_XTENSA_UNISTD_H) || defined(__SYSCALL)
 #define _UAPI_XTENSA_UNISTD_H
 
 #ifndef __SYSCALL
@@ -272,7 +262,7 @@ __SYSCALL(115, sys_sendmmsg, 4)
 #define __NR_clone 				116
 __SYSCALL(116, xtensa_clone, 5)
 #define __NR_execve 				117
-__SYSCALL(117, xtensa_execve, 3)
+__SYSCALL(117, sys_execve, 3)
 #define __NR_exit 				118
 __SYSCALL(118, sys_exit, 1)
 #define __NR_exit_group 			119
@@ -759,4 +749,6 @@ __SYSCALL(331, sys_kcmp, 5)
 
 #define SYS_XTENSA_COUNT                  5     /* count */
 
+#undef __SYSCALL
+
 #endif /* _UAPI_XTENSA_UNISTD_H */
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 18453067c258..90bfc1dbc13d 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1833,50 +1833,6 @@ ENTRY(system_call)
 
 
 /*
- * Create a kernel thread
- *
- * int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
- * a2                    a2                 a3             a4
- */
-
-ENTRY(kernel_thread)
-	entry	a1, 16
-
-	mov	a5, a2			# preserve fn over syscall
-	mov	a7, a3			# preserve args over syscall
-
-	movi	a3, _CLONE_VM | _CLONE_UNTRACED
-	movi	a2, __NR_clone
-	or	a6, a4, a3		# arg0: flags
-	mov	a3, a1			# arg1: sp
-	syscall
-
-	beq	a3, a1, 1f		# branch if parent
-	mov	a6, a7			# args
-	callx4	a5			# fn(args)
-
-	movi	a2, __NR_exit
-	syscall				# return value of fn(args) still in a6
-
-1:	retw
-
-/*
- * Do a system call from kernel instead of calling sys_execve, so we end up
- * with proper pt_regs.
- *
- * int kernel_execve(const char *fname, char *const argv[], charg *const envp[])
- * a2                        a2               a3                  a4
- */
-
-ENTRY(kernel_execve)
-	entry	a1, 16
-	mov	a6, a2			# arg0 is in a6
-	movi	a2, __NR_execve
-	syscall
-
-	retw
-
-/*
  * Task switch.
  *
  * struct task*  _switch_to (struct task* prev, struct task* next)
@@ -1958,3 +1914,16 @@ ENTRY(ret_from_fork)
 
 	j	common_exception_return
 
+/*
+ * Kernel thread creation helper
+ * On entry, set up by copy_thread: a2 = thread_fn, a3 = thread_fn arg
+ *           left from _switch_to: a6 = prev
+ */
+ENTRY(ret_from_kernel_thread)
+
+	call4	schedule_tail
+	mov	a6, a3
+	callx4	a2
+	j	common_exception_return
+
+ENDPROC(ret_from_kernel_thread)
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 1908f6642d31..09ae7bfab9a7 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -45,6 +45,7 @@
 #include <asm/regs.h>
 
 extern void ret_from_fork(void);
+extern void ret_from_kernel_thread(void);
 
 struct task_struct *current_set[NR_CPUS] = {&init_task, };
 
@@ -158,18 +159,30 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 /*
  * Copy thread.
  *
+ * There are two modes in which this function is called:
+ * 1) Userspace thread creation,
+ *    regs != NULL, usp_thread_fn is userspace stack pointer.
+ *    It is expected to copy parent regs (in case CLONE_VM is not set
+ *    in the clone_flags) and set up passed usp in the childregs.
+ * 2) Kernel thread creation,
+ *    regs == NULL, usp_thread_fn is the function to run in the new thread
+ *    and thread_fn_arg is its parameter.
+ *    childregs are not used for the kernel threads.
+ *
  * The stack layout for the new thread looks like this:
  *
- *	+------------------------+ <- sp in childregs (= tos)
+ *	+------------------------+
  *	|       childregs        |
  *	+------------------------+ <- thread.sp = sp in dummy-frame
  *	|      dummy-frame       |    (saved in dummy-frame spill-area)
  *	+------------------------+
  *
- * We create a dummy frame to return to ret_from_fork:
- *   a0 points to ret_from_fork (simulating a call4)
+ * We create a dummy frame to return to either ret_from_fork or
+ *   ret_from_kernel_thread:
+ *   a0 points to ret_from_fork/ret_from_kernel_thread (simulating a call4)
  *   sp points to itself (thread.sp)
- *   a2, a3 are unused.
+ *   a2, a3 are unused for userspace threads,
+ *   a2 points to thread_fn, a3 holds thread_fn arg for kernel threads.
  *
  * Note: This is a pristine frame, so we don't need any spill region on top of
  *       childregs.
@@ -185,43 +198,63 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
  * involved.  Much simpler to just not copy those live frames across.
  */
 
-int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long unused,
-                struct task_struct * p, struct pt_regs * regs)
+int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn,
+		unsigned long thread_fn_arg,
+		struct task_struct *p, struct pt_regs *unused)
 {
-	struct pt_regs *childregs;
-	unsigned long tos;
-	int user_mode = user_mode(regs);
+	struct pt_regs *childregs = task_pt_regs(p);
 
 #if (XTENSA_HAVE_COPROCESSORS || XTENSA_HAVE_IO_PORTS)
 	struct thread_info *ti;
 #endif
 
-	/* Set up new TSS. */
-	tos = (unsigned long)task_stack_page(p) + THREAD_SIZE;
-	if (user_mode)
-		childregs = (struct pt_regs*)(tos - PT_USER_SIZE);
-	else
-		childregs = (struct pt_regs*)tos - 1;
-
-	/* This does not copy all the regs.  In a bout of brilliance or madness,
-	   ARs beyond a0-a15 exist past the end of the struct. */
-	*childregs = *regs;
-
 	/* Create a call4 dummy-frame: a0 = 0, a1 = childregs. */
 	*((int*)childregs - 3) = (unsigned long)childregs;
 	*((int*)childregs - 4) = 0;
 
-	childregs->areg[2] = 0;
-	p->set_child_tid = p->clear_child_tid = NULL;
-	p->thread.ra = MAKE_RA_FOR_CALL((unsigned long)ret_from_fork, 0x1);
 	p->thread.sp = (unsigned long)childregs;
 
-	if (user_mode(regs)) {
+	if (!(p->flags & PF_KTHREAD)) {
+		struct pt_regs *regs = current_pt_regs();
+		unsigned long usp = usp_thread_fn ?
+			usp_thread_fn : regs->areg[1];
 
+		p->thread.ra = MAKE_RA_FOR_CALL(
+				(unsigned long)ret_from_fork, 0x1);
+
+		/* This does not copy all the regs.
+		 * In a bout of brilliance or madness,
+		 * ARs beyond a0-a15 exist past the end of the struct.
+		 */
+		*childregs = *regs;
 		childregs->areg[1] = usp;
+		childregs->areg[2] = 0;
+
+		/* When sharing memory with the parent thread, the child
+		   usually starts on a pristine stack, so we have to reset
+		   windowbase, windowstart and wmask.
+		   (Note that such a new thread is required to always create
+		   an initial call4 frame)
+		   The exception is vfork, where the new thread continues to
+		   run on the parent's stack until it calls execve. This could
+		   be a call8 or call12, which requires a legal stack frame
+		   of the previous caller for the overflow handlers to work.
+		   (Note that it's always legal to overflow live registers).
+		   In this case, ensure to spill at least the stack pointer
+		   of that frame. */
+
 		if (clone_flags & CLONE_VM) {
-			childregs->wmask = 1;	/* can't share live windows */
+			/* check that caller window is live and same stack */
+			int len = childregs->wmask & ~0xf;
+			if (regs->areg[1] == usp && len != 0) {
+				int callinc = (regs->areg[0] >> 30) & 3;
+				int caller_ars = XCHAL_NUM_AREGS - callinc * 4;
+				put_user(regs->areg[caller_ars+1],
+					 (unsigned __user*)(usp - 12));
+			}
+			childregs->wmask = 1;
+			childregs->windowstart = 1;
+			childregs->windowbase = 0;
 		} else {
 			int len = childregs->wmask & ~0xf;
 			memcpy(&childregs->areg[XCHAL_NUM_AREGS - len/4],
@@ -230,11 +263,19 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 // FIXME: we need to set THREADPTR in thread_info...
 		if (clone_flags & CLONE_SETTLS)
 			childregs->areg[2] = childregs->areg[6];
-
 	} else {
-		/* In kernel space, we start a new thread with a new stack. */
-		childregs->wmask = 1;
-		childregs->areg[1] = tos;
+		p->thread.ra = MAKE_RA_FOR_CALL(
+				(unsigned long)ret_from_kernel_thread, 1);
+
+		/* pass parameters to ret_from_kernel_thread:
+		 * a2 = thread_fn, a3 = thread_fn arg
+		 */
+		*((int *)childregs - 1) = thread_fn_arg;
+		*((int *)childregs - 2) = usp_thread_fn;
+
+		/* Childregs are only used when we're going to userspace
+		 * in which case start_thread will set them up.
+		 */
 	}
 
 #if (XTENSA_HAVE_COPROCESSORS || XTENSA_HAVE_IO_PORTS)
@@ -330,32 +371,5 @@ long xtensa_clone(unsigned long clone_flags, unsigned long newsp,
                   void __user *child_tid, long a5,
                   struct pt_regs *regs)
 {
-        if (!newsp)
-                newsp = regs->areg[1];
         return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
 }
-
-/*
- * xtensa_execve() executes a new program.
- */
-
-asmlinkage
-long xtensa_execve(const char __user *name,
-		   const char __user *const __user *argv,
-                   const char __user *const __user *envp,
-                   long a3, long a4, long a5,
-                   struct pt_regs *regs)
-{
-	long error;
-	struct filename *filename;
-
-	filename = getname(name);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		goto out;
-	error = do_execve(filename->name, argv, envp, regs);
-	putname(filename);
-out:
-	return error;
-}
-
diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index a5c01e74d5d5..5702065f472a 100644
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -32,10 +32,8 @@ typedef void (*syscall_t)(void);
 syscall_t sys_call_table[__NR_syscall_count] /* FIXME __cacheline_aligned */= {
 	[0 ... __NR_syscall_count - 1] = (syscall_t)&sys_ni_syscall,
 
-#undef __SYSCALL
 #define __SYSCALL(nr,symbol,nargs) [ nr ] = (syscall_t)symbol,
-#undef  __KERNEL_SYSCALLS__
-#include <asm/unistd.h>
+#include <uapi/asm/unistd.h>
 };
 
 asmlinkage long xtensa_shmat(int shmid, char __user *shmaddr, int shmflg)
@@ -49,7 +47,8 @@ asmlinkage long xtensa_shmat(int shmid, char __user *shmaddr, int shmflg)
 	return (long)ret;
 }
 
-asmlinkage long xtensa_fadvise64_64(int fd, int advice, unsigned long long offset, unsigned long long len)
+asmlinkage long xtensa_fadvise64_64(int fd, int advice,
+		unsigned long long offset, unsigned long long len)
 {
 	return sys_fadvise64_64(fd, offset, len, advice);
 }
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index a8b9f1fd1e17..afe058b24e6e 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -43,7 +43,6 @@ EXPORT_SYMBOL(__strncpy_user);
 EXPORT_SYMBOL(clear_page);
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(kernel_thread);
 EXPORT_SYMBOL(empty_zero_page);
 
 /*