23 files changed, 298 insertions, 397 deletions

diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 3e57a00b8cb..ba3aeb4bc06 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -206,40 +206,43 @@ reenable_mmu:				/* re-enable mmu so we can */
 	andi.	r10,r10,MSR_EE		/* Did EE change? */
 	beq	1f
 
-	/* Save handler and return address into the 2 unused words
-	 * of the STACK_FRAME_OVERHEAD (sneak sneak sneak). Everything
-	 * else can be recovered from the pt_regs except r3 which for
-	 * normal interrupts has been set to pt_regs and for syscalls
-	 * is an argument, so we temporarily use ORIG_GPR3 to save it
-	 */
-	stw	r9,8(r1)
-	stw	r11,12(r1)
-	stw	r3,ORIG_GPR3(r1)
 	/*
 	 * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
 	 * If from user mode there is only one stack frame on the stack, and
 	 * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
 	 * stack frame to make trace_hardirqs_off happy.
+	 *
+	 * This is handy because we also need to save a bunch of GPRs,
+	 * r3 can be different from GPR3(r1) at this point, r9 and r11
+	 * contains the old MSR and handler address respectively,
+	 * r4 & r5 can contain page fault arguments that need to be passed
+	 * along as well. r12, CCR, CTR, XER etc... are left clobbered as
+	 * they aren't useful past this point (aren't syscall arguments),
+	 * the rest is restored from the exception frame.
 	 */
+	stwu	r1,-32(r1)
+	stw	r9,8(r1)
+	stw	r11,12(r1)
+	stw	r3,16(r1)
+	stw	r4,20(r1)
+	stw	r5,24(r1)
 	andi.	r12,r12,MSR_PR
-	beq	11f
-	stwu	r1,-16(r1)
+	b	11f
 	bl	trace_hardirqs_off
-	addi	r1,r1,16
 	b	12f
-
 11:
 	bl	trace_hardirqs_off
 12:
+	lwz	r5,24(r1)
+	lwz	r4,20(r1)
+	lwz	r3,16(r1)
+	lwz	r11,12(r1)
+	lwz	r9,8(r1)
+	addi	r1,r1,32
 	lwz	r0,GPR0(r1)
-	lwz	r3,ORIG_GPR3(r1)
-	lwz	r4,GPR4(r1)
-	lwz	r5,GPR5(r1)
 	lwz	r6,GPR6(r1)
 	lwz	r7,GPR7(r1)
 	lwz	r8,GPR8(r1)
-	lwz	r9,8(r1)
-	lwz	r11,12(r1)
 1:	mtctr	r11
 	mtlr	r9
 	bctr				/* jump to handler */
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index f88698c0f33..4937c969009 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1235,7 +1235,7 @@ void __ppc64_runlatch_on(void)
 	ctrl |= CTRL_RUNLATCH;
 	mtspr(SPRN_CTRLT, ctrl);
 
-	ti->local_flags |= TLF_RUNLATCH;
+	ti->local_flags |= _TLF_RUNLATCH;
 }
 
 /* Called with hard IRQs off */
@@ -1244,7 +1244,7 @@ void __ppc64_runlatch_off(void)
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
 
-	ti->local_flags &= ~TLF_RUNLATCH;
+	ti->local_flags &= ~_TLF_RUNLATCH;
 
 	ctrl = mfspr(SPRN_CTRLF);
 	ctrl &= ~CTRL_RUNLATCH;
diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
index aba6b958b2a..19f56058742 100644
--- a/arch/sparc/kernel/leon_pci.c
+++ b/arch/sparc/kernel/leon_pci.c
@@ -45,7 +45,6 @@ void leon_pci_init(struct platform_device *ofdev, struct leon_pci_info *info)
 
 void __devinit pcibios_fixup_bus(struct pci_bus *pbus)
 {
-	struct leon_pci_info *info = pbus->sysdata;
 	struct pci_dev *dev;
 	int i, has_io, has_mem;
 	u16 cmd;
@@ -111,18 +110,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return pci_enable_resources(dev, mask);
 }
 
-struct device_node *pci_device_to_OF_node(struct pci_dev *pdev)
-{
-	/*
-	 * Currently the OpenBoot nodes are not connected with the PCI device,
-	 * this is because the LEON PROM does not create PCI nodes. Eventually
-	 * this will change and the same approach as pcic.c can be used to
-	 * match PROM nodes with pci devices.
-	 */
-	return NULL;
-}
-EXPORT_SYMBOL(pci_device_to_OF_node);
-
 void __devinit pcibios_update_irq(struct pci_dev *dev, int irq)
 {
 #ifdef CONFIG_PCI_DEBUG
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 7705c6731e2..df3155a1799 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -225,6 +225,8 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	unsigned long g2;
 	int from_user = !(regs->psr & PSR_PS);
 	int fault, code;
+	unsigned int flags = (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
+			      (write ? FAULT_FLAG_WRITE : 0));
 
 	if(text_fault)
 		address = regs->pc;
@@ -251,6 +253,7 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
+retry:
 	down_read(&mm->mmap_sem);
 
 	/*
@@ -289,7 +292,11 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -297,13 +304,29 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			current->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+				      1, regs, address);
+		} else {
+			current->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+				      1, regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
 	}
+
 	up_read(&mm->mmap_sem);
 	return;
 
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 504c0622f72..1fe0429b631 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -279,6 +279,7 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 	unsigned int insn = 0;
 	int si_code, fault_code, fault;
 	unsigned long address, mm_rss;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	fault_code = get_thread_fault_code();
 
@@ -333,6 +334,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 			insn = get_fault_insn(regs, insn);
 			goto handle_kernel_fault;
 		}
+
+retry:
 		down_read(&mm->mmap_sem);
 	}
 
@@ -423,7 +426,12 @@ good_area:
 			goto bad_area;
 	}
 
-	fault = handle_mm_fault(mm, vma, address, (fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
+	flags |= ((fault_code & FAULT_CODE_WRITE) ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -431,12 +439,27 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR) {
-		current->maj_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
-	} else {
-		current->min_flt++;
-		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR) {
+			current->maj_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
+				      1, regs, address);
+		} else {
+			current->min_flt++;
+			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
+				      1, regs, address);
+		}
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
 	}
 	up_read(&mm->mmap_sem);
 
diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c
index 7a932704640..446a7f52cc1 100644
--- a/arch/tile/kernel/proc.c
+++ b/arch/tile/kernel/proc.c
@@ -146,7 +146,6 @@ static ctl_table unaligned_table[] = {
 	},
 	{}
 };
-#endif
 
 static struct ctl_path tile_path[] = {
 	{ .procname = "tile" },
@@ -155,10 +154,9 @@ static struct ctl_path tile_path[] = {
 
 static int __init proc_sys_tile_init(void)
 {
-#ifndef __tilegx__  /* FIXME: GX: no support for unaligned access yet */
 	register_sysctl_paths(tile_path, unaligned_table);
-#endif
 	return 0;
 }
 
 arch_initcall(proc_sys_tile_init);
+#endif
diff --git a/arch/tile/kernel/smpboot.c b/arch/tile/kernel/smpboot.c
index b949edcec20..172aef7d315 100644
--- a/arch/tile/kernel/smpboot.c
+++ b/arch/tile/kernel/smpboot.c
@@ -196,6 +196,8 @@ void __cpuinit online_secondary(void)
 	/* This must be done before setting cpu_online_mask */
 	wmb();
 
+	notify_cpu_starting(smp_processor_id());
+
 	/*
 	 * We need to hold call_lock, so there is no inconsistency
 	 * between the time smp_call_function() determines number of
diff --git a/arch/um/drivers/cow.h b/arch/um/drivers/cow.h
index dc36b222100..6673508f342 100644
--- a/arch/um/drivers/cow.h
+++ b/arch/um/drivers/cow.h
@@ -3,41 +3,6 @@
 
 #include <asm/types.h>
 
-#if defined(__KERNEL__)
-
-# include <asm/byteorder.h>
-
-# if defined(__BIG_ENDIAN)
-#	define ntohll(x) (x)
-#	define htonll(x) (x)
-# elif defined(__LITTLE_ENDIAN)
-#	define ntohll(x)  be64_to_cpu(x)
-#	define htonll(x)  cpu_to_be64(x)
-# else
-#	error "Could not determine byte order"
-# endif
-
-#else
-/* For the definition of ntohl, htonl and __BYTE_ORDER */
-#include <endian.h>
-#include <netinet/in.h>
-#if defined(__BYTE_ORDER)
-
-#  if __BYTE_ORDER == __BIG_ENDIAN
-#	define ntohll(x) (x)
-#	define htonll(x) (x)
-#  elif __BYTE_ORDER == __LITTLE_ENDIAN
-#	define ntohll(x)  bswap_64(x)
-#	define htonll(x)  bswap_64(x)
-#  else
-#	error "Could not determine byte order: __BYTE_ORDER uncorrectly defined"
-#  endif
-
-#else  /* ! defined(__BYTE_ORDER) */
-#	error "Could not determine byte order: __BYTE_ORDER not defined"
-#endif
-#endif /* ! defined(__KERNEL__) */
-
 extern int init_cow_file(int fd, char *cow_file, char *backing_file,
 			 int sectorsize, int alignment, int *bitmap_offset_out,
 			 unsigned long *bitmap_len_out, int *data_offset_out);
diff --git a/arch/um/drivers/cow_user.c b/arch/um/drivers/cow_user.c
index 9cbb426c0b9..0ee9cc6cc4c 100644
--- a/arch/um/drivers/cow_user.c
+++ b/arch/um/drivers/cow_user.c
@@ -8,11 +8,10 @@
  * that.
  */
 #include <unistd.h>
-#include <byteswap.h>
 #include <errno.h>
 #include <string.h>
 #include <arpa/inet.h>
-#include <asm/types.h>
+#include <endian.h>
 #include "cow.h"
 #include "cow_sys.h"
 
@@ -214,8 +213,8 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
 			   "header\n");
 		goto out;
 	}
-	header->magic = htonl(COW_MAGIC);
-	header->version = htonl(COW_VERSION);
+	header->magic = htobe32(COW_MAGIC);
+	header->version = htobe32(COW_VERSION);
 
 	err = -EINVAL;
 	if (strlen(backing_file) > sizeof(header->backing_file) - 1) {
@@ -246,10 +245,10 @@ int write_cow_header(char *cow_file, int fd, char *backing_file,
 		goto out_free;
 	}
 
-	header->mtime = htonl(modtime);
-	header->size = htonll(*size);
-	header->sectorsize = htonl(sectorsize);
-	header->alignment = htonl(alignment);
+	header->mtime = htobe32(modtime);
+	header->size = htobe64(*size);
+	header->sectorsize = htobe32(sectorsize);
+	header->alignment = htobe32(alignment);
 	header->cow_format = COW_BITMAP;
 
 	err = cow_write_file(fd, header, sizeof(*header));
@@ -301,8 +300,8 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 	magic = header->v1.magic;
 	if (magic == COW_MAGIC)
 		version = header->v1.version;
-	else if (magic == ntohl(COW_MAGIC))
-		version = ntohl(header->v1.version);
+	else if (magic == be32toh(COW_MAGIC))
+		version = be32toh(header->v1.version);
 	/* No error printed because the non-COW case comes through here */
 	else goto out;
 
@@ -327,9 +326,9 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 				   "header\n");
 			goto out;
 		}
-		*mtime_out = ntohl(header->v2.mtime);
-		*size_out = ntohll(header->v2.size);
-		*sectorsize_out = ntohl(header->v2.sectorsize);
+		*mtime_out = be32toh(header->v2.mtime);
+		*size_out = be64toh(header->v2.size);
+		*sectorsize_out = be32toh(header->v2.sectorsize);
 		*bitmap_offset_out = sizeof(header->v2);
 		*align_out = *sectorsize_out;
 		file = header->v2.backing_file;
@@ -341,10 +340,10 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 				   "header\n");
 			goto out;
 		}
-		*mtime_out = ntohl(header->v3.mtime);
-		*size_out = ntohll(header->v3.size);
-		*sectorsize_out = ntohl(header->v3.sectorsize);
-		*align_out = ntohl(header->v3.alignment);
+		*mtime_out = be32toh(header->v3.mtime);
+		*size_out = be64toh(header->v3.size);
+		*sectorsize_out = be32toh(header->v3.sectorsize);
+		*align_out = be32toh(header->v3.alignment);
 		if (*align_out == 0) {
 			cow_printf("read_cow_header - invalid COW header, "
 				   "align == 0\n");
@@ -366,16 +365,16 @@ int read_cow_header(int (*reader)(__u64, char *, int, void *), void *arg,
 		 * this was used until Dec2005 - 64bits are needed to represent
 		 * 2038+. I.e. we can safely do this truncating cast.
 		 *
-		 * Additionally, we must use ntohl() instead of ntohll(), since
+		 * Additionally, we must use be32toh() instead of be64toh(), since
 		 * the program used to use the former (tested - I got mtime
 		 * mismatch "0 vs whatever").
 		 *
 		 * Ever heard about bug-to-bug-compatibility ? ;-) */
-		*mtime_out = (time32_t) ntohl(header->v3_b.mtime);
+		*mtime_out = (time32_t) be32toh(header->v3_b.mtime);
 
-		*size_out = ntohll(header->v3_b.size);
-		*sectorsize_out = ntohl(header->v3_b.sectorsize);
-		*align_out = ntohl(header->v3_b.alignment);
+		*size_out = be64toh(header->v3_b.size);
+		*sectorsize_out = be32toh(header->v3_b.sectorsize);
+		*align_out = be32toh(header->v3_b.alignment);
 		if (*align_out == 0) {
 			cow_printf("read_cow_header - invalid COW header, "
 				   "align == 0\n");
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index e672bd6d43e..43b39d61b53 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -22,6 +22,7 @@
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
 #include <asm/uaccess.h>
+#include <asm/switch_to.h>
 
 #include "init.h"
 #include "irq_kern.h"
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 8419f5cf2ac..fff24352255 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,3 +1,4 @@
 generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
 generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
-generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h
+generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
+generic-y += switch_to.h
diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile
index 492bc4c1b62..65a1c3d690e 100644
--- a/arch/um/kernel/Makefile
+++ b/arch/um/kernel/Makefile
@@ -3,9 +3,10 @@
 # Licensed under the GPL
 #
 
-CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START) \
-                        -DELF_ARCH=$(LDS_ELF_ARCH)        \
-                        -DELF_FORMAT=$(LDS_ELF_FORMAT)
+CPPFLAGS_vmlinux.lds := -DSTART=$(LDS_START)		\
+                        -DELF_ARCH=$(LDS_ELF_ARCH)	\
+                        -DELF_FORMAT=$(LDS_ELF_FORMAT)	\
+			$(LDS_EXTRA)
 extra-y := vmlinux.lds
 clean-files :=
 
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index f386d04a84a..2b73dedb44c 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -88,11 +88,8 @@ static inline void set_current(struct task_struct *task)
 
 extern void arch_switch_to(struct task_struct *to);
 
-void *_switch_to(void *prev, void *next, void *last)
+void *__switch_to(struct task_struct *from, struct task_struct *to)
 {
-	struct task_struct *from = prev;
-	struct task_struct *to = next;
-
 	to->thread.prev_sched = from;
 	set_current(to);
 
@@ -111,7 +108,6 @@ void *_switch_to(void *prev, void *next, void *last)
 	} while (current->thread.saved_task);
 
 	return current->thread.prev_sched;
-
 }
 
 void interrupt_end(void)
diff --git a/arch/um/kernel/skas/mmu.c b/arch/um/kernel/skas/mmu.c
index 4947b319f53..0a49ef0c2bf 100644
--- a/arch/um/kernel/skas/mmu.c
+++ b/arch/um/kernel/skas/mmu.c
@@ -103,7 +103,6 @@ int init_new_context(struct task_struct *task, struct mm_struct *mm)
 
 void uml_setup_stubs(struct mm_struct *mm)
 {
-	struct page **pages;
 	int err, ret;
 
 	if (!skas_needs_stub)
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 4be406abeef..36b62bc5263 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -14,6 +14,9 @@ LINK-y			+= $(call cc-option,-m32)
 
 export LDFLAGS
 
+LDS_EXTRA		:= -Ui386
+export LDS_EXTRA
+
 # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y.
 include $(srctree)/arch/x86/Makefile_32.cpu
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8be5f54d936..e0544597cfe 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -557,6 +557,8 @@ struct __large_struct { unsigned long buf[100]; };
 
 extern unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
+extern __must_check long
+strncpy_from_user(char *dst, const char __user *src, long count);
 
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 566e803cc60..8084bc73b18 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,11 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to,
 	return n;
 }
 
-long __must_check strncpy_from_user(char *dst, const char __user *src,
-				    long count);
-long __must_check __strncpy_from_user(char *dst,
-				      const char __user *src, long count);
-
 /**
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 1c66d30971a..fcd4b6f3ef0 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,10 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 }
 
-__must_check long
-strncpy_from_user(char *dst, const char __user *src, long count);
-__must_check long
-__strncpy_from_user(char *dst, const char __user *src, long count);
 __must_check long strnlen_user(const char __user *str, long n);
 __must_check long __strnlen_user(const char __user *str, long n);
 __must_check long strlen_user(const char __user *str);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 97be9cb5448..57252c928f5 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -7,6 +7,8 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
 
+#include <asm/word-at-a-time.h>
+
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
  */
@@ -41,3 +43,104 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);
+
+static inline unsigned long count_bytes(unsigned long mask)
+{
+	mask = (mask - 1) & ~mask;
+	mask >>= 7;
+	return count_masked_bytes(mask);
+}
+
+/*
+ * Do a strncpy, return length of string without final '\0'.
+ * 'count' is the user-supplied count (return 'count' if we
+ * hit it), 'max' is the address space maximum (and we return
+ * -EFAULT if we hit it).
+ */
+static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, long max)
+{
+	long res = 0;
+
+	/*
+	 * Truncate 'max' to the user-specified limit, so that
+	 * we only have one limit we need to check in the loop
+	 */
+	if (max > count)
+		max = count;
+
+	while (max >= sizeof(unsigned long)) {
+		unsigned long c;
+
+		/* Fall back to byte-at-a-time if we get a page fault */
+		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+			break;
+		/* This can write a few bytes past the NUL character, but that's ok */
+		*(unsigned long *)(dst+res) = c;
+		c = has_zero(c);
+		if (c)
+			return res + count_bytes(c);
+		res += sizeof(unsigned long);
+		max -= sizeof(unsigned long);
+	}
+
+	while (max) {
+		char c;
+
+		if (unlikely(__get_user(c,src+res)))
+			return -EFAULT;
+		dst[res] = c;
+		if (!c)
+			return res;
+		res++;
+		max--;
+	}
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, that's ok - we got as much as the user asked for.
+	 */
+	if (res >= count)
+		return count;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's an EFAULT.
+	 */
+	return -EFAULT;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	max_addr = current_thread_info()->addr_limit.seg;
+	src_addr = (unsigned long)src;
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		return do_strncpy_from_user(dst, src, count, max);
+	}
+	return -EFAULT;
+}
+EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index d9b094ca7aa..ef2a6a5d78e 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -33,93 +33,6 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon
 	__movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n))
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst, src, count, res)			   \
-do {									   \
-	int __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testl %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decl %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subl %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movl %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&d"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-/**
- * __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- * Caller must check the specified block with access_ok() before calling
- * this function.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b7c2849ffb6..0d0326f388c 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -9,55 +9,6 @@
 #include <asm/uaccess.h>
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst,src,count,res)			   \
-do {									   \
-	long __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testq %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decq %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subq %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movq %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&r"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		return __strncpy_from_user(dst, src, count);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
new file mode 100644
index 00000000000..7d01b8c56c0
--- /dev/null
+++ b/arch/x86/um/asm/barrier.h
@@ -0,0 +1,75 @@
+#ifndef _ASM_UM_BARRIER_H_
+#define _ASM_UM_BARRIER_H_
+
+#include <asm/asm.h>
+#include <asm/segment.h>
+#include <asm/cpufeature.h>
+#include <asm/cmpxchg.h>
+#include <asm/nops.h>
+
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+#ifdef CONFIG_X86_32
+
+#define mb()	alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb()	alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb()	alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+
+#else /* CONFIG_X86_32 */
+
+#define mb()	asm volatile("mfence" : : : "memory")
+#define rmb()	asm volatile("lfence" : : : "memory")
+#define wmb()	asm volatile("sfence" : : : "memory")
+
+#endif /* CONFIG_X86_32 */
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+
+#define smp_mb()	mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+#define smp_rmb()	rmb()
+#else /* CONFIG_X86_PPRO_FENCE */
+#define smp_rmb()	barrier()
+#endif /* CONFIG_X86_PPRO_FENCE */
+
+#ifdef CONFIG_X86_OOSTORE
+#define smp_wmb()	wmb()
+#else /* CONFIG_X86_OOSTORE */
+#define smp_wmb()	barrier()
+#endif /* CONFIG_X86_OOSTORE */
+
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+
+#else /* CONFIG_SMP */
+
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif
diff --git a/arch/x86/um/asm/system.h b/arch/x86/um/asm/system.h
deleted file mode 100644
index a459fd9b759..00000000000
--- a/arch/x86/um/asm/system.h
+++ /dev/null
@@ -1,135 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
-# define AT_VECTOR_SIZE_ARCH 2
-#else
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-void default_idle(void);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
-#define wmb()	asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
-#else
-# define smp_rmb()	barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-extern void *_switch_to(void *prev, void *next, void *last);
-#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
-
-#endif