x86, um/x86: switch to generic sys_execve and kernel_execve

32bit wrapper is lost on that; 64bit one is *not*, since
we need to arrange for full pt_regs on stack when we call
sys_execve() and we need to load callee-saved ones from
there afterwards.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

arch/um/kernel/exec.c

@@ -16,7 +16,6 @@
 #include "mem_user.h"
 #include "skas.h"
 #include "os.h"
-#include "internal.h"
 
 void flush_thread(void)
 {
@@ -49,27 +48,7 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp)
 }
 EXPORT_SYMBOL(start_thread);
 
-long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env)
+void __noreturn ret_from_kernel_execve(struct pt_regs *unused)
 {
-	long err;
-
-	err = do_execve(file, argv, env, &current->thread.regs);
-	if (!err)
 	UML_LONGJMP(current->thread.exec_buf, 1);
-	return err;
-}
-
-long sys_execve(const char __user *file, const char __user *const __user *argv,
-		const char __user *const __user *env)
-{
-	long error;
-	char *filename;
-
-	filename = getname(file);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename)) goto out;
-	error = do_execve(filename, argv, env, &current->thread.regs);
-	putname(filename);
- out:
-	return error;
 }

arch/um/kernel/internal.h

-extern long um_execve(const char *file, const char __user *const __user *argv, const char __user *const __user *env);

arch/um/kernel/syscall.c

@@ -13,7 +13,6 @@
 #include "asm/mman.h"
 #include "asm/uaccess.h"
 #include "asm/unistd.h"
-#include "internal.h"
 
 long sys_fork(void)
 {
@@ -50,19 +49,3 @@ long old_mmap(unsigned long addr, unsigned long len,
  out:
 	return err;
 }
-
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	mm_segment_t fs;
-	int ret;
-
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-	ret = um_execve(filename, (const char __user *const __user *)argv,
-			(const char __user *const __user *) envp);
-	set_fs(fs);
-
-	return ret;
-}

arch/x86/ia32/ia32entry.S

@@ -459,7 +459,7 @@ GLOBAL(\label)
 	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi
 	PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi
 	PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx
-	PTREGSCALL stub32_execve, sys32_execve, %rcx
+	PTREGSCALL stub32_execve, compat_sys_execve, %rcx
 	PTREGSCALL stub32_fork, sys_fork, %rdi
 	PTREGSCALL stub32_clone, sys32_clone, %rdx
 	PTREGSCALL stub32_vfork, sys_vfork, %rdi

arch/x86/ia32/sys_ia32.c

@@ -385,21 +385,6 @@ asmlinkage long sys32_sendfile(int out_fd, int in_fd,
 	return ret;
 }
 
-asmlinkage long sys32_execve(const char __user *name, compat_uptr_t __user *argv,
-			     compat_uptr_t __user *envp, struct pt_regs *regs)
-{
-	long error;
-	char *filename;
-
-	filename = getname(name);
-	error = PTR_ERR(filename);
-	if (IS_ERR(filename))
-		return error;
-	error = compat_do_execve(filename, argv, envp, regs);
-	putname(filename);
-	return error;
-}
-
 asmlinkage long sys32_clone(unsigned int clone_flags, unsigned int newsp,
 			    struct pt_regs *regs)
 {

arch/x86/include/asm/sys_ia32.h

@@ -54,8 +54,6 @@ asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32);
 asmlinkage long sys32_personality(unsigned long);
 asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32);
 
-asmlinkage long sys32_execve(const char __user *, compat_uptr_t __user *,
-			     compat_uptr_t __user *, struct pt_regs *);
 asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *);
 
 long sys32_lseek(unsigned int, int, unsigned int);

arch/x86/include/asm/syscalls.h

@@ -25,7 +25,7 @@ int sys_fork(struct pt_regs *);
 int sys_vfork(struct pt_regs *);
 long sys_execve(const char __user *,
 		const char __user *const __user *,
-		const char __user *const __user *, struct pt_regs *);
+		const char __user *const __user *);
 long sys_clone(unsigned long, unsigned long, void __user *,
 	       void __user *, struct pt_regs *);
 

arch/x86/include/asm/unistd.h

@@ -50,6 +50,8 @@
 # define __ARCH_WANT_SYS_TIME
 # define __ARCH_WANT_SYS_UTIME
 # define __ARCH_WANT_SYS_WAITPID
+# define __ARCH_WANT_SYS_EXECVE
+# define __ARCH_WANT_KERNEL_EXECVE
 
 /*
  * "Conditional" syscalls

arch/x86/kernel/Makefile

@@ -23,7 +23,7 @@ obj-y			+= time.o ioport.o ldt.o dumpstack.o nmi.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
-obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
+obj-$(CONFIG_X86_32)	+= i386_ksyms_32.o
 obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o

arch/x86/kernel/asm-offsets.c

@@ -69,4 +69,7 @@ void common(void) {
 	OFFSET(BP_kernel_alignment, boot_params, hdr.kernel_alignment);
 	OFFSET(BP_pref_address, boot_params, hdr.pref_address);
 	OFFSET(BP_code32_start, boot_params, hdr.code32_start);
+
+	BLANK();
+	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
 }

arch/x86/kernel/entry_32.S

@@ -298,6 +298,13 @@ ENTRY(ret_from_fork)
 	CFI_ENDPROC
 END(ret_from_fork)
 
+ENTRY(ret_from_kernel_execve)
+	movl %eax, %esp
+	movl $0,PT_EAX(%esp)
+	GET_THREAD_INFO(%ebp)
+	jmp syscall_exit
+END(ret_from_kernel_execve)
+
 /*
  * Interrupt exit functions should be protected against kprobes
  */
@@ -322,8 +329,7 @@ ret_from_intr:
 	andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
 #else
 	/*
-	 * We can be coming here from a syscall done in the kernel space,
-	 * e.g. a failed kernel_execve().
+	 * We can be coming here from child spawned by kernel_thread().
 	 */
 	movl PT_CS(%esp), %eax
 	andl $SEGMENT_RPL_MASK, %eax
@@ -727,7 +733,6 @@ ENDPROC(ptregs_##name)
 PTREGSCALL1(iopl)
 PTREGSCALL0(fork)
 PTREGSCALL0(vfork)
-PTREGSCALL3(execve)
 PTREGSCALL2(sigaltstack)
 PTREGSCALL0(sigreturn)
 PTREGSCALL0(rt_sigreturn)

arch/x86/kernel/entry_64.S

@@ -767,7 +767,6 @@ ENTRY(stub_execve)
 	PARTIAL_FRAME 0
 	SAVE_REST
 	FIXUP_TOP_OF_STACK %r11
-	movq %rsp, %rcx
 	call sys_execve
 	RESTORE_TOP_OF_STACK %r11
 	movq %rax,RAX(%rsp)
@@ -817,8 +816,7 @@ ENTRY(stub_x32_execve)
 	PARTIAL_FRAME 0
 	SAVE_REST
 	FIXUP_TOP_OF_STACK %r11
-	movq %rsp, %rcx
-	call sys32_execve
+	call compat_sys_execve
 	RESTORE_TOP_OF_STACK %r11
 	movq %rax,RAX(%rsp)
 	RESTORE_REST
@@ -1216,36 +1214,19 @@ bad_gs:
 	jmp  2b
 	.previous
 
-/*
- * execve(). This function needs to use IRET, not SYSRET, to set up all state properly.
- *
- * C extern interface:
- *	 extern long execve(const char *name, char **argv, char **envp)
- *
- * asm input arguments:
- *	rdi: name, rsi: argv, rdx: envp
- *
- * We want to fallback into:
- *	extern long sys_execve(const char *name, char **argv,char **envp, struct pt_regs *regs)
- *
- * do_sys_execve asm fallback arguments:
- *	rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack
- */
-ENTRY(kernel_execve)
-	CFI_STARTPROC
-	FAKE_STACK_FRAME $0
-	SAVE_ALL
-	movq %rsp,%rcx
-	call sys_execve
-	movq %rax, RAX(%rsp)
-	RESTORE_REST
-	testq %rax,%rax
-	je int_ret_from_sys_call
-	RESTORE_ARGS
-	UNFAKE_STACK_FRAME
-	ret
-	CFI_ENDPROC
-END(kernel_execve)
+ENTRY(ret_from_kernel_execve)
+	movq %rdi, %rsp
+	movl $0, RAX(%rsp)
+	// RESTORE_REST
+	movq 0*8(%rsp), %r15
+	movq 1*8(%rsp), %r14
+	movq 2*8(%rsp), %r13
+	movq 3*8(%rsp), %r12
+	movq 4*8(%rsp), %rbp
+	movq 5*8(%rsp), %rbx
+	addq $(6*8), %rsp
+	jmp int_ret_from_sys_call
+END(ret_from_kernel_execve)
 
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(call_softirq)

arch/x86/kernel/process.c

@@ -298,25 +298,6 @@ sys_clone(unsigned long clone_flags, unsigned long newsp,
 	return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid);
 }
 
-/*
- * sys_execve() executes a new program.
- */
-long sys_execve(const char __user *name,
-		const char __user *const __user *argv,
-		const char __user *const __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;
-}
-
 /*
  * Idle related variables and functions
  */

arch/x86/kernel/process_32.c

@@ -207,6 +207,7 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 	regs->cs		= __USER_CS;
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
+	regs->flags		= X86_EFLAGS_IF;
 	/*
 	 * Free the old FP and other extended state
 	 */

arch/x86/kernel/sys_i386_32.c

-/*
- * This file contains various random system calls that
- * have a non-standard calling sequence on the Linux/i386
- * platform.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/smp.h>
-#include <linux/sem.h>
-#include <linux/msg.h>
-#include <linux/shm.h>
-#include <linux/stat.h>
-#include <linux/syscalls.h>
-#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/utsname.h>
-#include <linux/ipc.h>
-
-#include <linux/uaccess.h>
-#include <linux/unistd.h>
-
-#include <asm/syscalls.h>
-
-/*
- * Do a system call from kernel instead of calling sys_execve so we
- * end up with proper pt_regs.
- */
-int kernel_execve(const char *filename,
-		  const char *const argv[],
-		  const char *const envp[])
-{
-	long __res;
-	asm volatile ("int $0x80"
-	: "=a" (__res)
-	: "0" (__NR_execve), "b" (filename), "c" (argv), "d" (envp) : "memory");
-	return __res;
-}

arch/x86/syscalls/syscall_32.tbl

@@ -17,7 +17,7 @@
 8	i386	creat			sys_creat
 9	i386	link			sys_link
 10	i386	unlink			sys_unlink
-11	i386	execve			ptregs_execve			stub32_execve
+11	i386	execve			sys_execve			stub32_execve
 12	i386	chdir			sys_chdir
 13	i386	time			sys_time			compat_sys_time
 14	i386	mknod			sys_mknod

arch/x86/um/sys_call_table_32.c

@@ -25,7 +25,6 @@
 #define old_mmap sys_old_mmap
 
 #define ptregs_fork sys_fork
-#define ptregs_execve sys_execve
 #define ptregs_iopl sys_iopl
 #define ptregs_vm86old sys_vm86old
 #define ptregs_clone i386_clone