Split 'flush_old_exec' into two functions

'flush_old_exec()' is the point of no return when doing an execve(), and
it is pretty badly misnamed.  It doesn't just flush the old executable
environment, it also starts up the new one.

Which is very inconvenient for things like setting up the new
personality, because we want the new personality to affect the starting
of the new environment, but at the same time we do _not_ want the new
personality to take effect if flushing the old one fails.

As a result, the x86-64 '32-bit' personality is actually done using this
insane "I'm going to change the ABI, but I haven't done it yet" bit
(TIF_ABI_PENDING), with SET_PERSONALITY() not actually setting the
personality, but just the "pending" bit, so that "flush_thread()" can do
the actual personality magic.

This patch in no way changes any of that insanity, but it does split the
'flush_old_exec()' function up into a preparatory part that can fail
(still called flush_old_exec()), and a new part that will actually set
up the new exec environment (setup_new_exec()).  All callers are changed
to trivially comply with the new world order.

Signed-off-by: H. Peter Anvin <[email protected]>
Cc: [email protected]
Signed-off-by: Linus Torvalds <[email protected]>

arch/sh/kernel/process_64.c

@@ -368,7 +368,7 @@ void exit_thread(void)
 void flush_thread(void)
 {
 
-	/* Called by fs/exec.c (flush_old_exec) to remove traces of a
+	/* Called by fs/exec.c (setup_new_exec) to remove traces of a
 	 * previously running executable. */
 #ifdef CONFIG_SH_FPU
 	if (last_task_used_math == current) {

arch/x86/ia32/ia32_aout.c

@@ -308,15 +308,17 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	if (retval)
 		return retval;
 
-	regs->cs = __USER32_CS;
-	regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
-		regs->r13 = regs->r14 = regs->r15 = 0;
-
 	/* OK, This is the point of no return */
 	set_personality(PER_LINUX);
 	set_thread_flag(TIF_IA32);
 	clear_thread_flag(TIF_ABI_PENDING);
 
+	setup_new_exec(bprm);
+
+	regs->cs = __USER32_CS;
+	regs->r8 = regs->r9 = regs->r10 = regs->r11 = regs->r12 =
+		regs->r13 = regs->r14 = regs->r15 = 0;
+
 	current->mm->end_code = ex.a_text +
 		(current->mm->start_code = N_TXTADDR(ex));
 	current->mm->end_data = ex.a_data +

fs/binfmt_aout.c

@@ -264,6 +264,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 #else
 	set_personality(PER_LINUX);
 #endif
+	setup_new_exec(bprm);
 
 	current->mm->end_code = ex.a_text +
 		(current->mm->start_code = N_TXTADDR(ex));

fs/binfmt_elf.c

@@ -662,27 +662,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0')
 				goto out_free_interp;
 
-			/*
-			 * The early SET_PERSONALITY here is so that the lookup
-			 * for the interpreter happens in the namespace of the 
-			 * to-be-execed image.  SET_PERSONALITY can select an
-			 * alternate root.
-			 *
-			 * However, SET_PERSONALITY is NOT allowed to switch
-			 * this task into the new images's memory mapping
-			 * policy - that is, TASK_SIZE must still evaluate to
-			 * that which is appropriate to the execing application.
-			 * This is because exit_mmap() needs to have TASK_SIZE
-			 * evaluate to the size of the old image.
-			 *
-			 * So if (say) a 64-bit application is execing a 32-bit
-			 * application it is the architecture's responsibility
-			 * to defer changing the value of TASK_SIZE until the
-			 * switch really is going to happen - do this in
-			 * flush_thread().	- akpm
-			 */
-			SET_PERSONALITY(loc->elf_ex);
-
 			interpreter = open_exec(elf_interpreter);
 			retval = PTR_ERR(interpreter);
 			if (IS_ERR(interpreter))
@@ -730,9 +709,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		/* Verify the interpreter has a valid arch */
 		if (!elf_check_arch(&loc->interp_elf_ex))
 			goto out_free_dentry;
-	} else {
-		/* Executables without an interpreter also need a personality  */
-		SET_PERSONALITY(loc->elf_ex);
 	}
 
 	/* Flush all traces of the currently running executable */
@@ -752,7 +728,8 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 
 	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
 		current->flags |= PF_RANDOMIZE;
-	arch_pick_mmap_layout(current->mm);
+
+	setup_new_exec(bprm);
 
 	/* Do this so that we can load the interpreter, if need be.  We will
 	   change some of these later */

fs/binfmt_elf_fdpic.c

@@ -321,6 +321,9 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm,
 	set_personality(PER_LINUX_FDPIC);
 	if (elf_read_implies_exec(&exec_params.hdr, executable_stack))
 		current->personality |= READ_IMPLIES_EXEC;
+
+	setup_new_exec(bprm);
+
 	set_binfmt(&elf_fdpic_format);
 
 	current->mm->start_code = 0;

fs/binfmt_flat.c

@@ -519,6 +519,7 @@ static int load_flat_file(struct linux_binprm * bprm,
 
 		/* OK, This is the point of no return */
 		set_personality(PER_LINUX_32BIT);
+		setup_new_exec(bprm);
 	}
 
 	/*

fs/binfmt_som.c

@@ -227,6 +227,7 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 	/* OK, This is the point of no return */
 	current->flags &= ~PF_FORKNOEXEC;
 	current->personality = PER_HPUX;
+	setup_new_exec(bprm);
 
 	/* Set the task size for HP-UX processes such that
 	 * the gateway page is outside the address space.

fs/exec.c

@@ -941,9 +941,7 @@ void set_task_comm(struct task_struct *tsk, char *buf)
 
 int flush_old_exec(struct linux_binprm * bprm)
 {
-	char * name;
-	int i, ch, retval;
-	char tcomm[sizeof(current->comm)];
+	int retval;
 
 	/*
 	 * Make sure we have a private signal table and that
@@ -963,6 +961,20 @@ int flush_old_exec(struct linux_binprm * bprm)
 		goto out;
 
 	bprm->mm = NULL;		/* We're using it now */
+	return 0;
+
+out:
+	return retval;
+}
+EXPORT_SYMBOL(flush_old_exec);
+
+void setup_new_exec(struct linux_binprm * bprm)
+{
+	int i, ch;
+	char * name;
+	char tcomm[sizeof(current->comm)];
+
+	arch_pick_mmap_layout(current->mm);
 
 	/* This is the point of no return */
 	current->sas_ss_sp = current->sas_ss_size = 0;
@@ -1019,14 +1031,8 @@ int flush_old_exec(struct linux_binprm * bprm)
 
 	flush_signal_handlers(current, 0);
 	flush_old_files(current->files);
-
-	return 0;
-
-out:
-	return retval;
 }
-
-EXPORT_SYMBOL(flush_old_exec);
+EXPORT_SYMBOL(setup_new_exec);
 
 /*
  * Prepare credentials and lock ->cred_guard_mutex.

include/linux/binfmts.h

@@ -109,6 +109,7 @@ extern int prepare_binprm(struct linux_binprm *);
 extern int __must_check remove_arg_zero(struct linux_binprm *);
 extern int search_binary_handler(struct linux_binprm *,struct pt_regs *);
 extern int flush_old_exec(struct linux_binprm * bprm);
+extern void setup_new_exec(struct linux_binprm * bprm);
 
 extern int suid_dumpable;
 #define SUID_DUMP_DISABLE	0	/* No setuid dumping */

include/linux/sched.h

@@ -1369,7 +1369,7 @@ struct task_struct {
 	char comm[TASK_COMM_LEN]; /* executable name excluding path
 				     - access with [gs]et_task_comm (which lock
 				       it with task_lock())
-				     - initialized normally by flush_old_exec */
+				     - initialized normally by setup_new_exec */
 /* file system info */
 	int link_count, total_link_count;
 #ifdef CONFIG_SYSVIPC