21 files changed, 265 insertions, 311 deletions

diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
index aba6b958b2a5..19f56058742b 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 7705c6731e28..df3155a17991 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 504c0622f729..1fe0429b6314 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/um/drivers/cow.h b/arch/um/drivers/cow.h
index dc36b222100b..6673508f3426 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 9cbb426c0b91..0ee9cc6cc4c7 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 e672bd6d43e3..43b39d61b538 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 8419f5cf2ac7..fff24352255d 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 492bc4c1b62b..65a1c3d690ea 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 f386d04a84a5..2b73dedb44ca 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 4947b319f53a..0a49ef0c2bf4 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 4be406abeefd..36b62bc52638 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/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
new file mode 100644
index 000000000000..7d01b8c56c00
--- /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 a459fd9b7598..000000000000
--- 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
diff --git a/crypto/Kconfig b/crypto/Kconfig
index 21ff9d015432..8e84225c096b 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -627,7 +627,7 @@ config CRYPTO_BLOWFISH_COMMON
 
 config CRYPTO_BLOWFISH_X86_64
 	tristate "Blowfish cipher algorithm (x86_64)"
-	depends on (X86 || UML_X86) && 64BIT
+	depends on X86 && 64BIT
 	select CRYPTO_ALGAPI
 	select CRYPTO_BLOWFISH_COMMON
 	help
@@ -657,7 +657,7 @@ config CRYPTO_CAMELLIA
 
 config CRYPTO_CAMELLIA_X86_64
 	tristate "Camellia cipher algorithm (x86_64)"
-	depends on (X86 || UML_X86) && 64BIT
+	depends on X86 && 64BIT
 	depends on CRYPTO
 	select CRYPTO_ALGAPI
 	select CRYPTO_LRW
@@ -893,7 +893,7 @@ config CRYPTO_TWOFISH_X86_64
 
 config CRYPTO_TWOFISH_X86_64_3WAY
 	tristate "Twofish cipher algorithm (x86_64, 3-way parallel)"
-	depends on (X86 || UML_X86) && 64BIT
+	depends on X86 && 64BIT
 	select CRYPTO_ALGAPI
 	select CRYPTO_TWOFISH_COMMON
 	select CRYPTO_TWOFISH_X86_64
diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c
index 37f42113af31..00e8f213f56e 100644
--- a/drivers/i2c/busses/i2c-designware-pcidrv.c
+++ b/drivers/i2c/busses/i2c-designware-pcidrv.c
@@ -182,7 +182,6 @@ static int i2c_dw_pci_resume(struct device *dev)
 	pci_restore_state(pdev);
 
 	i2c_dw_init(i2c);
-	i2c_dw_enable(i2c);
 	return 0;
 }
 
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 53969af17558..81fd606e47bc 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -214,7 +214,7 @@ static struct of_device_id __devinitdata of_anatop_regulator_match_tbl[] = {
 	{ /* end */ }
 };
 
-static struct platform_driver anatop_regulator = {
+static struct platform_driver anatop_regulator_driver = {
 	.driver = {
 		.name	= "anatop_regulator",
 		.owner  = THIS_MODULE,
@@ -226,13 +226,13 @@ static struct platform_driver anatop_regulator = {
 
 static int __init anatop_regulator_init(void)
 {
-	return platform_driver_register(&anatop_regulator);
+	return platform_driver_register(&anatop_regulator_driver);
 }
 postcore_initcall(anatop_regulator_init);
 
 static void __exit anatop_regulator_exit(void)
 {
-	platform_driver_unregister(&anatop_regulator);
+	platform_driver_unregister(&anatop_regulator_driver);
 }
 module_exit(anatop_regulator_exit);
 
diff --git a/drivers/sh/clk/cpg.c b/drivers/sh/clk/cpg.c
index 91b6d52f74eb..f0d015dd0fef 100644
--- a/drivers/sh/clk/cpg.c
+++ b/drivers/sh/clk/cpg.c
@@ -2,6 +2,7 @@
  * Helper routines for SuperH Clock Pulse Generator blocks (CPG).
  *
  *  Copyright (C) 2010  Magnus Damm
+ *  Copyright (C) 2010 - 2012  Paul Mundt
  *
  * 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
@@ -13,26 +14,44 @@
 #include <linux/io.h>
 #include <linux/sh_clk.h>
 
-static int sh_clk_mstp32_enable(struct clk *clk)
+static unsigned int sh_clk_read(struct clk *clk)
 {
-	iowrite32(ioread32(clk->mapped_reg) & ~(1 << clk->enable_bit),
-		  clk->mapped_reg);
+	if (clk->flags & CLK_ENABLE_REG_8BIT)
+		return ioread8(clk->mapped_reg);
+	else if (clk->flags & CLK_ENABLE_REG_16BIT)
+		return ioread16(clk->mapped_reg);
+
+	return ioread32(clk->mapped_reg);
+}
+
+static void sh_clk_write(int value, struct clk *clk)
+{
+	if (clk->flags & CLK_ENABLE_REG_8BIT)
+		iowrite8(value, clk->mapped_reg);
+	else if (clk->flags & CLK_ENABLE_REG_16BIT)
+		iowrite16(value, clk->mapped_reg);
+	else
+		iowrite32(value, clk->mapped_reg);
+}
+
+static int sh_clk_mstp_enable(struct clk *clk)
+{
+	sh_clk_write(sh_clk_read(clk) & ~(1 << clk->enable_bit), clk);
 	return 0;
 }
 
-static void sh_clk_mstp32_disable(struct clk *clk)
+static void sh_clk_mstp_disable(struct clk *clk)
 {
-	iowrite32(ioread32(clk->mapped_reg) | (1 << clk->enable_bit),
-		  clk->mapped_reg);
+	sh_clk_write(sh_clk_read(clk) | (1 << clk->enable_bit), clk);
 }
 
-static struct sh_clk_ops sh_clk_mstp32_clk_ops = {
-	.enable		= sh_clk_mstp32_enable,
-	.disable	= sh_clk_mstp32_disable,
+static struct sh_clk_ops sh_clk_mstp_clk_ops = {
+	.enable		= sh_clk_mstp_enable,
+	.disable	= sh_clk_mstp_disable,
 	.recalc		= followparent_recalc,
 };
 
-int __init sh_clk_mstp32_register(struct clk *clks, int nr)
+int __init sh_clk_mstp_register(struct clk *clks, int nr)
 {
 	struct clk *clkp;
 	int ret = 0;
@@ -40,7 +59,7 @@ int __init sh_clk_mstp32_register(struct clk *clks, int nr)
 
 	for (k = 0; !ret && (k < nr); k++) {
 		clkp = clks + k;
-		clkp->ops = &sh_clk_mstp32_clk_ops;
+		clkp->ops = &sh_clk_mstp_clk_ops;
 		ret |= clk_register(clkp);
 	}
 
@@ -72,7 +91,7 @@ static unsigned long sh_clk_div6_recalc(struct clk *clk)
 	clk_rate_table_build(clk, clk->freq_table, table->nr_divisors,
 			     table, NULL);
 
-	idx = ioread32(clk->mapped_reg) & 0x003f;
+	idx = sh_clk_read(clk) & 0x003f;
 
 	return clk->freq_table[idx].frequency;
 }
@@ -98,10 +117,10 @@ static int sh_clk_div6_set_parent(struct clk *clk, struct clk *parent)
 	if (ret < 0)
 		return ret;
 
-	value = ioread32(clk->mapped_reg) &
+	value = sh_clk_read(clk) &
 		~(((1 << clk->src_width) - 1) << clk->src_shift);
 
-	iowrite32(value | (i << clk->src_shift), clk->mapped_reg);
+	sh_clk_write(value | (i << clk->src_shift), clk);
 
 	/* Rebuild the frequency table */
 	clk_rate_table_build(clk, clk->freq_table, table->nr_divisors,
@@ -119,10 +138,10 @@ static int sh_clk_div6_set_rate(struct clk *clk, unsigned long rate)
 	if (idx < 0)
 		return idx;
 
-	value = ioread32(clk->mapped_reg);
+	value = sh_clk_read(clk);
 	value &= ~0x3f;
 	value |= idx;
-	iowrite32(value, clk->mapped_reg);
+	sh_clk_write(value, clk);
 	return 0;
 }
 
@@ -133,9 +152,9 @@ static int sh_clk_div6_enable(struct clk *clk)
 
 	ret = sh_clk_div6_set_rate(clk, clk->rate);
 	if (ret == 0) {
-		value = ioread32(clk->mapped_reg);
+		value = sh_clk_read(clk);
 		value &= ~0x100; /* clear stop bit to enable clock */
-		iowrite32(value, clk->mapped_reg);
+		sh_clk_write(value, clk);
 	}
 	return ret;
 }
@@ -144,10 +163,10 @@ static void sh_clk_div6_disable(struct clk *clk)
 {
 	unsigned long value;
 
-	value = ioread32(clk->mapped_reg);
+	value = sh_clk_read(clk);
 	value |= 0x100; /* stop clock */
 	value |= 0x3f; /* VDIV bits must be non-zero, overwrite divider */
-	iowrite32(value, clk->mapped_reg);
+	sh_clk_write(value, clk);
 }
 
 static struct sh_clk_ops sh_clk_div6_clk_ops = {
@@ -182,7 +201,7 @@ static int __init sh_clk_init_parent(struct clk *clk)
 		return -EINVAL;
 	}
 
-	val  = (ioread32(clk->mapped_reg) >> clk->src_shift);
+	val  = (sh_clk_read(clk) >> clk->src_shift);
 	val &= (1 << clk->src_width) - 1;
 
 	if (val >= clk->parent_num) {
@@ -252,7 +271,7 @@ static unsigned long sh_clk_div4_recalc(struct clk *clk)
 	clk_rate_table_build(clk, clk->freq_table, table->nr_divisors,
 			     table, &clk->arch_flags);
 
-	idx = (ioread32(clk->mapped_reg) >> clk->enable_bit) & 0x000f;
+	idx = (sh_clk_read(clk) >> clk->enable_bit) & 0x000f;
 
 	return clk->freq_table[idx].frequency;
 }
@@ -270,15 +289,15 @@ static int sh_clk_div4_set_parent(struct clk *clk, struct clk *parent)
 	 */
 
 	if (parent->flags & CLK_ENABLE_ON_INIT)
-		value = ioread32(clk->mapped_reg) & ~(1 << 7);
+		value = sh_clk_read(clk) & ~(1 << 7);
 	else
-		value = ioread32(clk->mapped_reg) | (1 << 7);
+		value = sh_clk_read(clk) | (1 << 7);
 
 	ret = clk_reparent(clk, parent);
 	if (ret < 0)
 		return ret;
 
-	iowrite32(value, clk->mapped_reg);
+	sh_clk_write(value, clk);
 
 	/* Rebiuld the frequency table */
 	clk_rate_table_build(clk, clk->freq_table, table->nr_divisors,
@@ -295,10 +314,10 @@ static int sh_clk_div4_set_rate(struct clk *clk, unsigned long rate)
 	if (idx < 0)
 		return idx;
 
-	value = ioread32(clk->mapped_reg);
+	value = sh_clk_read(clk);
 	value &= ~(0xf << clk->enable_bit);
 	value |= (idx << clk->enable_bit);
-	iowrite32(value, clk->mapped_reg);
+	sh_clk_write(value, clk);
 
 	if (d4t->kick)
 		d4t->kick(clk);
@@ -308,13 +327,13 @@ static int sh_clk_div4_set_rate(struct clk *clk, unsigned long rate)
 
 static int sh_clk_div4_enable(struct clk *clk)
 {
-	iowrite32(ioread32(clk->mapped_reg) & ~(1 << 8), clk->mapped_reg);
+	sh_clk_write(sh_clk_read(clk) & ~(1 << 8), clk);
 	return 0;
 }
 
 static void sh_clk_div4_disable(struct clk *clk)
 {
-	iowrite32(ioread32(clk->mapped_reg) | (1 << 8), clk->mapped_reg);
+	sh_clk_write(sh_clk_read(clk) | (1 << 8), clk);
 }
 
 static struct sh_clk_ops sh_clk_div4_clk_ops = {
diff --git a/drivers/staging/android/lowmemorykiller.c b/drivers/staging/android/lowmemorykiller.c
index 052b43e4e505..b91e4bc332a7 100644
--- a/drivers/staging/android/lowmemorykiller.c
+++ b/drivers/staging/android/lowmemorykiller.c
@@ -55,7 +55,6 @@ static int lowmem_minfree[6] = {
 };
 static int lowmem_minfree_size = 4;
 
-static struct task_struct *lowmem_deathpending;
 static unsigned long lowmem_deathpending_timeout;
 
 #define lowmem_print(level, x...)			\
@@ -64,24 +63,6 @@ static unsigned long lowmem_deathpending_timeout;
 			printk(x);			\
 	} while (0)
 
-static int
-task_notify_func(struct notifier_block *self, unsigned long val, void *data);
-
-static struct notifier_block task_nb = {
-	.notifier_call	= task_notify_func,
-};
-
-static int
-task_notify_func(struct notifier_block *self, unsigned long val, void *data)
-{
-	struct task_struct *task = data;
-
-	if (task == lowmem_deathpending)
-		lowmem_deathpending = NULL;
-
-	return NOTIFY_OK;
-}
-
 static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 {
 	struct task_struct *tsk;
@@ -97,19 +78,6 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 	int other_file = global_page_state(NR_FILE_PAGES) -
 						global_page_state(NR_SHMEM);
 
-	/*
-	 * If we already have a death outstanding, then
-	 * bail out right away; indicating to vmscan
-	 * that we have nothing further to offer on
-	 * this pass.
-	 *
-	 * Note: Currently you need CONFIG_PROFILING
-	 * for this to work correctly.
-	 */
-	if (lowmem_deathpending &&
-	    time_before_eq(jiffies, lowmem_deathpending_timeout))
-		return 0;
-
 	if (lowmem_adj_size < array_size)
 		array_size = lowmem_adj_size;
 	if (lowmem_minfree_size < array_size)
@@ -148,6 +116,12 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 		if (!p)
 			continue;
 
+		if (test_tsk_thread_flag(p, TIF_MEMDIE) &&
+		    time_before_eq(jiffies, lowmem_deathpending_timeout)) {
+			task_unlock(p);
+			rcu_read_unlock();
+			return 0;
+		}
 		oom_score_adj = p->signal->oom_score_adj;
 		if (oom_score_adj < min_score_adj) {
 			task_unlock(p);
@@ -174,15 +148,9 @@ static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
 		lowmem_print(1, "send sigkill to %d (%s), adj %d, size %d\n",
 			     selected->pid, selected->comm,
 			     selected_oom_score_adj, selected_tasksize);
-		/*
-		 * If CONFIG_PROFILING is off, then we don't want to stall
-		 * the killer by setting lowmem_deathpending.
-		 */
-#ifdef CONFIG_PROFILING
-		lowmem_deathpending = selected;
 		lowmem_deathpending_timeout = jiffies + HZ;
-#endif
 		send_sig(SIGKILL, selected, 0);
+		set_tsk_thread_flag(selected, TIF_MEMDIE);
 		rem -= selected_tasksize;
 	}
 	lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
@@ -198,7 +166,6 @@ static struct shrinker lowmem_shrinker = {
 
 static int __init lowmem_init(void)
 {
-	task_handoff_register(&task_nb);
 	register_shrinker(&lowmem_shrinker);
 	return 0;
 }
@@ -206,7 +173,6 @@ static int __init lowmem_init(void)
 static void __exit lowmem_exit(void)
 {
 	unregister_shrinker(&lowmem_shrinker);
-	task_handoff_unregister(&task_nb);
 }
 
 module_param_named(cost, lowmem_shrinker.seeks, int, S_IRUGO | S_IWUSR);
diff --git a/include/linux/sh_clk.h b/include/linux/sh_clk.h
index 0a9d8f2ac519..c513b73cd7cb 100644
--- a/include/linux/sh_clk.h
+++ b/include/linux/sh_clk.h
@@ -59,7 +59,15 @@ struct clk {
 	unsigned int		nr_freqs;
 };
 
-#define CLK_ENABLE_ON_INIT	(1 << 0)
+#define CLK_ENABLE_ON_INIT	BIT(0)
+
+#define CLK_ENABLE_REG_32BIT	BIT(1)	/* default access size */
+#define CLK_ENABLE_REG_16BIT	BIT(2)
+#define CLK_ENABLE_REG_8BIT	BIT(3)
+
+#define CLK_ENABLE_REG_MASK	(CLK_ENABLE_REG_32BIT | \
+				 CLK_ENABLE_REG_16BIT | \
+				 CLK_ENABLE_REG_8BIT)
 
 /* drivers/sh/clk.c */
 unsigned long followparent_recalc(struct clk *);
@@ -102,7 +110,7 @@ long clk_round_parent(struct clk *clk, unsigned long target,
 		      unsigned long *best_freq, unsigned long *parent_freq,
 		      unsigned int div_min, unsigned int div_max);
 
-#define SH_CLK_MSTP32(_parent, _enable_reg, _enable_bit, _flags)	\
+#define SH_CLK_MSTP(_parent, _enable_reg, _enable_bit, _flags)		\
 {									\
 	.parent		= _parent,					\
 	.enable_reg	= (void __iomem *)_enable_reg,			\
@@ -110,7 +118,27 @@ long clk_round_parent(struct clk *clk, unsigned long target,
 	.flags		= _flags,					\
 }
 
-int sh_clk_mstp32_register(struct clk *clks, int nr);
+#define SH_CLK_MSTP32(_p, _r, _b, _f)					\
+	SH_CLK_MSTP(_p, _r, _b, _f | CLK_ENABLE_REG_32BIT)
+
+#define SH_CLK_MSTP16(_p, _r, _b, _f)					\
+	SH_CLK_MSTP(_p, _r, _b, _f | CLK_ENABLE_REG_16BIT)
+
+#define SH_CLK_MSTP8(_p, _r, _b, _f)					\
+	SH_CLK_MSTP(_p, _r, _b, _f | CLK_ENABLE_REG_8BIT)
+
+int sh_clk_mstp_register(struct clk *clks, int nr);
+
+/*
+ * MSTP registration never really cared about access size, despite the
+ * original enable/disable pairs assuming a 32-bit access. Clocks are
+ * responsible for defining their access sizes either directly or via the
+ * clock definition wrappers.
+ */
+static inline int __deprecated sh_clk_mstp32_register(struct clk *clks, int nr)
+{
+	return sh_clk_mstp_register(clks, nr);
+}
 
 #define SH_CLK_DIV4(_parent, _reg, _shift, _div_bitmap, _flags)	\
 {								\
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 3f01fd908730..c4e7d1510f9d 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -132,8 +132,10 @@ static struct module *new_module(char *modname)
 	/* strip trailing .o */
 	s = strrchr(p, '.');
 	if (s != NULL)
-		if (strcmp(s, ".o") == 0)
+		if (strcmp(s, ".o") == 0) {
 			*s = '\0';
+			mod->is_dot_o = 1;
+		}
 
 	/* add to list */
 	mod->name = p;
@@ -587,7 +589,8 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 	unsigned int crc;
 	enum export export;
 
-	if (!is_vmlinux(mod->name) && strncmp(symname, "__ksymtab", 9) == 0)
+	if ((!is_vmlinux(mod->name) || mod->is_dot_o) &&
+	    strncmp(symname, "__ksymtab", 9) == 0)
 		export = export_from_secname(info, get_secindex(info, sym));
 	else
 		export = export_from_sec(info, get_secindex(info, sym));
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 2031119080dc..51207e4d5f8b 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -113,6 +113,7 @@ struct module {
 	int has_cleanup;
 	struct buffer dev_table_buf;
 	char	     srcversion[25];
+	int is_dot_o;
 };
 
 struct elf_info {