11 files changed, 188 insertions, 285 deletions

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/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index b3b733262909..99480e55973d 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -43,7 +43,7 @@ extern void __add_wrong_size(void)
                 switch (sizeof(*(ptr))) {                               \
                 case __X86_CASE_B:                                      \
                         asm volatile (lock #op "b %b0, %1\n"            \
-                                      : "+r" (__ret), "+m" (*(ptr))     \
+                                      : "+q" (__ret), "+m" (*(ptr))     \
                                       : : "memory", "cc");              \
                         break;                                          \
                 case __X86_CASE_W:                                      \
@@ -173,7 +173,7 @@ extern void __add_wrong_size(void)
                 switch (sizeof(*(ptr))) {                               \
                 case __X86_CASE_B:                                      \
                         asm volatile (lock "addb %b1, %0\n"             \
-                                      : "+m" (*(ptr)) : "ri" (inc)      \
+                                      : "+m" (*(ptr)) : "qi" (inc)      \
                                       : "memory", "cc");                \
                         break;                                          \
                 case __X86_CASE_W:                                      \
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8be5f54d9360..e0544597cfe7 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 566e803cc602..8084bc73b18c 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 1c66d30971ad..fcd4b6f3ef02 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/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index f386dc49f988..7515cf0e1805 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -216,9 +216,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
         current_thread_info()->sig_on_uaccess_error = 1;
 
         /*
-         * 0 is a valid user pointer (in the access_ok sense) on 32-bit and
+         * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
          * 64-bit, so we don't need to special-case it here.  For all the
-         * vsyscalls, 0 means "don't write anything" not "write it at
+         * vsyscalls, NULL means "don't write anything" not "write it at
          * address 0".
          */
         ret = -EFAULT;
@@ -247,7 +247,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
                 ret = sys_getcpu((unsigned __user *)regs->di,
                                  (unsigned __user *)regs->si,
-                                 0);
+                                 NULL);
                 break;
         }
 
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 97be9cb54483..d6ae30bbd7bb 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, unsigned 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 res;
+
+        /*
+         * 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 d9b094ca7aaa..ef2a6a5d78e3 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 b7c2849ffb66..0d0326f388c0 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 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