11 files changed, 110 insertions, 205 deletions

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