Merge branch 'x86/asm' into x86/urgent

Merge reason: it's stable so lets push it upstream.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

9 files changed, 138 insertions, 211 deletions

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 50b9c220e12..44a8e0dc673 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -725,22 +725,61 @@ END(syscall_badsys)
 /*
  * System calls that need a pt_regs pointer.
  */
-#define PTREGSCALL(name) \
+#define PTREGSCALL0(name) \
         ALIGN; \
 ptregs_##name: \
         leal 4(%esp),%eax; \
         jmp sys_##name;
 
-PTREGSCALL(iopl)
-PTREGSCALL(fork)
-PTREGSCALL(clone)
-PTREGSCALL(vfork)
-PTREGSCALL(execve)
-PTREGSCALL(sigaltstack)
-PTREGSCALL(sigreturn)
-PTREGSCALL(rt_sigreturn)
-PTREGSCALL(vm86)
-PTREGSCALL(vm86old)
+#define PTREGSCALL1(name) \
+        ALIGN; \
+ptregs_##name: \
+        leal 4(%esp),%edx; \
+        movl (PT_EBX+4)(%esp),%eax; \
+        jmp sys_##name;
+
+#define PTREGSCALL2(name) \
+        ALIGN; \
+ptregs_##name: \
+        leal 4(%esp),%ecx; \
+        movl (PT_ECX+4)(%esp),%edx; \
+        movl (PT_EBX+4)(%esp),%eax; \
+        jmp sys_##name;
+
+#define PTREGSCALL3(name) \
+        ALIGN; \
+ptregs_##name: \
+        leal 4(%esp),%eax; \
+        pushl %eax; \
+        movl PT_EDX(%eax),%ecx; \
+        movl PT_ECX(%eax),%edx; \
+        movl PT_EBX(%eax),%eax; \
+        call sys_##name; \
+        addl $4,%esp; \
+        ret
+
+PTREGSCALL1(iopl)
+PTREGSCALL0(fork)
+PTREGSCALL0(vfork)
+PTREGSCALL3(execve)
+PTREGSCALL2(sigaltstack)
+PTREGSCALL0(sigreturn)
+PTREGSCALL0(rt_sigreturn)
+PTREGSCALL2(vm86)
+PTREGSCALL1(vm86old)
+
+/* Clone is an oddball.  The 4th arg is in %edi */
+        ALIGN;
+ptregs_clone:
+        leal 4(%esp),%eax
+        pushl %eax
+        pushl PT_EDI(%eax)
+        movl PT_EDX(%eax),%ecx
+        movl PT_ECX(%eax),%edx
+        movl PT_EBX(%eax),%eax
+        call sys_clone
+        addl $8,%esp
+        ret
 
 .macro FIXUP_ESPFIX_STACK
 /*
@@ -1008,12 +1047,8 @@ END(spurious_interrupt_bug)
 ENTRY(kernel_thread_helper)
         pushl $0                # fake return address for unwinder
         CFI_STARTPROC
-        movl %edx,%eax
-        push %edx
-        CFI_ADJUST_CFA_OFFSET 4
-        call *%ebx
-        push %eax
-        CFI_ADJUST_CFA_OFFSET 4
+        movl %edi,%eax
+        call *%esi
         call do_exit
         ud2                     # padding for call trace
         CFI_ENDPROC
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 63bca794c8f..73d9b2c0e21 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1166,63 +1166,20 @@ bad_gs:
         jmp  2b
         .previous
 
-/*
- * Create a kernel thread.
- *
- * C extern interface:
- *      extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
- *
- * asm input arguments:
- *      rdi: fn, rsi: arg, rdx: flags
- */
-ENTRY(kernel_thread)
-        CFI_STARTPROC
-        FAKE_STACK_FRAME $child_rip
-        SAVE_ALL
-
-        # rdi: flags, rsi: usp, rdx: will be &pt_regs
-        movq %rdx,%rdi
-        orq  kernel_thread_flags(%rip),%rdi
-        movq $-1, %rsi
-        movq %rsp, %rdx
-
-        xorl %r8d,%r8d
-        xorl %r9d,%r9d
-
-        # clone now
-        call do_fork
-        movq %rax,RAX(%rsp)
-        xorl %edi,%edi
-
-        /*
-         * It isn't worth to check for reschedule here,
-         * so internally to the x86_64 port you can rely on kernel_thread()
-         * not to reschedule the child before returning, this avoids the need
-         * of hacks for example to fork off the per-CPU idle tasks.
-         * [Hopefully no generic code relies on the reschedule -AK]
-         */
-        RESTORE_ALL
-        UNFAKE_STACK_FRAME
-        ret
-        CFI_ENDPROC
-END(kernel_thread)
-
-ENTRY(child_rip)
+ENTRY(kernel_thread_helper)
         pushq $0                # fake return address
         CFI_STARTPROC
         /*
          * Here we are in the child and the registers are set as they were
          * at kernel_thread() invocation in the parent.
          */
-        movq %rdi, %rax
-        movq %rsi, %rdi
-        call *%rax
+        call *%rsi
         # exit
         mov %eax, %edi
         call do_exit
         ud2                     # padding for call trace
         CFI_ENDPROC
-END(child_rip)
+END(kernel_thread_helper)
 
 /*
  * execve(). This function needs to use IRET, not SYSRET, to set up all state properly.
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 99c4d308f16..8eec0ec59af 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -103,9 +103,10 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
  * on system-call entry - see also fork() and the signal handling
  * code.
  */
-static int do_iopl(unsigned int level, struct pt_regs *regs)
+long sys_iopl(unsigned int level, struct pt_regs *regs)
 {
         unsigned int old = (regs->flags >> 12) & 3;
+        struct thread_struct *t = &current->thread;
 
         if (level > 3)
                 return -EINVAL;
@@ -115,29 +116,8 @@ static int do_iopl(unsigned int level, struct pt_regs *regs)
                         return -EPERM;
         }
         regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12);
-
-        return 0;
-}
-
-#ifdef CONFIG_X86_32
-long sys_iopl(struct pt_regs *regs)
-{
-        unsigned int level = regs->bx;
-        struct thread_struct *t = &current->thread;
-        int rc;
-
-        rc = do_iopl(level, regs);
-        if (rc < 0)
-                goto out;
-
         t->iopl = level << 12;
         set_iopl_mask(t->iopl);
-out:
-        return rc;
-}
-#else
-asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs)
-{
-        return do_iopl(level, regs);
+
+        return 0;
 }
-#endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 7a7bd4e3ec4..98c2cdeb599 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -255,6 +255,76 @@ int sys_vfork(struct pt_regs *regs)
                        NULL, NULL);
 }
 
+long
+sys_clone(unsigned long clone_flags, unsigned long newsp,
+          void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
+{
+        if (!newsp)
+                newsp = regs->sp;
+        return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
+}
+
+/*
+ * This gets run with %si containing the
+ * function to call, and %di containing
+ * the "args".
+ */
+extern void kernel_thread_helper(void);
+
+/*
+ * Create a kernel thread
+ */
+int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
+{
+        struct pt_regs regs;
+
+        memset(&regs, 0, sizeof(regs));
+
+        regs.si = (unsigned long) fn;
+        regs.di = (unsigned long) arg;
+
+#ifdef CONFIG_X86_32
+        regs.ds = __USER_DS;
+        regs.es = __USER_DS;
+        regs.fs = __KERNEL_PERCPU;
+        regs.gs = __KERNEL_STACK_CANARY;
+#endif
+
+        regs.orig_ax = -1;
+        regs.ip = (unsigned long) kernel_thread_helper;
+        regs.cs = __KERNEL_CS | get_kernel_rpl();
+        regs.flags = X86_EFLAGS_IF | 0x2;
+
+        /* Ok, create the new process.. */
+        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
+}
+EXPORT_SYMBOL(kernel_thread);
+
+/*
+ * sys_execve() executes a new program.
+ */
+long sys_execve(char __user *name, char __user * __user *argv,
+                char __user * __user *envp, struct pt_regs *regs)
+{
+        long error;
+        char *filename;
+
+        filename = getname(name);
+        error = PTR_ERR(filename);
+        if (IS_ERR(filename))
+                return error;
+        error = do_execve(filename, argv, envp, regs);
+
+#ifdef CONFIG_X86_32
+        if (error == 0) {
+                /* Make sure we don't return using sysenter.. */
+                set_thread_flag(TIF_IRET);
+        }
+#endif
+
+        putname(filename);
+        return error;
+}
 
 /*
  * Idle related variables and functions
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 120b88797a7..9c517b5858f 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -180,39 +180,6 @@ void show_regs(struct pt_regs *regs)
         show_trace(NULL, regs, &regs->sp, regs->bp);
 }
 
-/*
- * This gets run with %bx containing the
- * function to call, and %dx containing
- * the "args".
- */
-extern void kernel_thread_helper(void);
-
-/*
- * Create a kernel thread
- */
-int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
-{
-        struct pt_regs regs;
-
-        memset(&regs, 0, sizeof(regs));
-
-        regs.bx = (unsigned long) fn;
-        regs.dx = (unsigned long) arg;
-
-        regs.ds = __USER_DS;
-        regs.es = __USER_DS;
-        regs.fs = __KERNEL_PERCPU;
-        regs.gs = __KERNEL_STACK_CANARY;
-        regs.orig_ax = -1;
-        regs.ip = (unsigned long) kernel_thread_helper;
-        regs.cs = __KERNEL_CS | get_kernel_rpl();
-        regs.flags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
-
-        /* Ok, create the new process.. */
-        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-}
-EXPORT_SYMBOL(kernel_thread);
-
 void release_thread(struct task_struct *dead_task)
 {
         BUG_ON(dead_task->mm);
@@ -424,46 +391,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         return prev_p;
 }
 
-int sys_clone(struct pt_regs *regs)
-{
-        unsigned long clone_flags;
-        unsigned long newsp;
-        int __user *parent_tidptr, *child_tidptr;
-
-        clone_flags = regs->bx;
-        newsp = regs->cx;
-        parent_tidptr = (int __user *)regs->dx;
-        child_tidptr = (int __user *)regs->di;
-        if (!newsp)
-                newsp = regs->sp;
-        return do_fork(clone_flags, newsp, regs, 0, parent_tidptr, child_tidptr);
-}
-
-/*
- * sys_execve() executes a new program.
- */
-int sys_execve(struct pt_regs *regs)
-{
-        int error;
-        char *filename;
-
-        filename = getname((char __user *) regs->bx);
-        error = PTR_ERR(filename);
-        if (IS_ERR(filename))
-                goto out;
-        error = do_execve(filename,
-                        (char __user * __user *) regs->cx,
-                        (char __user * __user *) regs->dx,
-                        regs);
-        if (error == 0) {
-                /* Make sure we don't return using sysenter.. */
-                set_thread_flag(TIF_IRET);
-        }
-        putname(filename);
-out:
-        return error;
-}
-
 #define top_esp                (THREAD_SIZE - sizeof(unsigned long))
 #define top_ebp                (THREAD_SIZE - 2*sizeof(unsigned long))
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e5ab0cd0ef3..52fbd0c6019 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -57,8 +57,6 @@ asmlinkage extern void ret_from_fork(void);
 DEFINE_PER_CPU(unsigned long, old_rsp);
 static DEFINE_PER_CPU(unsigned char, is_idle);
 
-unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
-
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
 
 void idle_notifier_register(struct notifier_block *n)
@@ -273,8 +271,9 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
         *childregs = *regs;
 
         childregs->ax = 0;
-        childregs->sp = sp;
-        if (sp == ~0UL)
+        if (user_mode(regs))
+                childregs->sp = sp;
+        else
                 childregs->sp = (unsigned long)childregs;
 
         p->thread.sp = (unsigned long) childregs;
@@ -508,25 +507,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         return prev_p;
 }
 
-/*
- * sys_execve() executes a new program.
- */
-asmlinkage
-long sys_execve(char __user *name, char __user * __user *argv,
-                char __user * __user *envp, struct pt_regs *regs)
-{
-        long error;
-        char *filename;
-
-        filename = getname(name);
-        error = PTR_ERR(filename);
-        if (IS_ERR(filename))
-                return error;
-        error = do_execve(filename, argv, envp, regs);
-        putname(filename);
-        return error;
-}
-
 void set_personality_64bit(void)
 {
         /* inherit personality from parent */
@@ -541,15 +521,6 @@ void set_personality_64bit(void)
         current->personality &= ~READ_IMPLIES_EXEC;
 }
 
-asmlinkage long
-sys_clone(unsigned long clone_flags, unsigned long newsp,
-          void __user *parent_tid, void __user *child_tid, struct pt_regs *regs)
-{
-        if (!newsp)
-                newsp = regs->sp;
-        return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
-}
-
 unsigned long get_wchan(struct task_struct *p)
 {
         unsigned long stack;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 74fe6d86dc5..4fd173cd8e5 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -545,22 +545,12 @@ sys_sigaction(int sig, const struct old_sigaction __user *act,
 }
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_X86_32
-int sys_sigaltstack(struct pt_regs *regs)
-{
-        const stack_t __user *uss = (const stack_t __user *)regs->bx;
-        stack_t __user *uoss = (stack_t __user *)regs->cx;
-
-        return do_sigaltstack(uss, uoss, regs->sp);
-}
-#else /* !CONFIG_X86_32 */
-asmlinkage long
+long
 sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
                 struct pt_regs *regs)
 {
         return do_sigaltstack(uss, uoss, regs->sp);
 }
-#endif /* CONFIG_X86_32 */
 
 /*
  * Do a signal return; undo the signal stack.
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 9c4e6253905..5ffb5622f79 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -197,9 +197,8 @@ out:
 static int do_vm86_irq_handling(int subfunction, int irqnumber);
 static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk);
 
-int sys_vm86old(struct pt_regs *regs)
+int sys_vm86old(struct vm86_struct __user *v86, struct pt_regs *regs)
 {
-        struct vm86_struct __user *v86 = (struct vm86_struct __user *)regs->bx;
         struct kernel_vm86_struct info; /* declare this _on top_,
                                          * this avoids wasting of stack space.
                                          * This remains on the stack until we
@@ -227,7 +226,7 @@ out:
 }
 
 
-int sys_vm86(struct pt_regs *regs)
+int sys_vm86(unsigned long cmd, unsigned long arg, struct pt_regs *regs)
 {
         struct kernel_vm86_struct info; /* declare this _on top_,
                                          * this avoids wasting of stack space.
@@ -239,12 +238,12 @@ int sys_vm86(struct pt_regs *regs)
         struct vm86plus_struct __user *v86;
 
         tsk = current;
-        switch (regs->bx) {
+        switch (cmd) {
         case VM86_REQUEST_IRQ:
         case VM86_FREE_IRQ:
         case VM86_GET_IRQ_BITS:
         case VM86_GET_AND_RESET_IRQ:
-                ret = do_vm86_irq_handling(regs->bx, (int)regs->cx);
+                ret = do_vm86_irq_handling(cmd, (int)arg);
                 goto out;
         case VM86_PLUS_INSTALL_CHECK:
                 /*
@@ -261,7 +260,7 @@ int sys_vm86(struct pt_regs *regs)
         ret = -EPERM;
         if (tsk->thread.saved_sp0)
                 goto out;
-        v86 = (struct vm86plus_struct __user *)regs->cx;
+        v86 = (struct vm86plus_struct __user *)arg;
         tmp = copy_vm86_regs_from_user(&info.regs, &v86->regs,
                                        offsetof(struct kernel_vm86_struct, regs32) -
                                        sizeof(info.regs));
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index a1029769b6f..9fafaf83b3b 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -17,8 +17,6 @@
 EXPORT_SYMBOL(mcount);
 #endif
 
-EXPORT_SYMBOL(kernel_thread);
-
 EXPORT_SYMBOL(__get_user_1);
 EXPORT_SYMBOL(__get_user_2);
 EXPORT_SYMBOL(__get_user_4);