From e76623d69408d0bd66a296c6ee5eae1b17a6adfc Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 2 Aug 2012 22:12:06 +0400
Subject: x86: get rid of TIF_IRET hackery

TIF_NOTIFY_RESUME will work in precisely the same way; all that
is achieved by TIF_IRET is appearing that there's some work to be
done, so we end up on the iret exit path.  Just use NOTIFY_RESUME.
And for execve() do that in 32bit start_thread(), not sys_execve()
itself.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/include/asm/thread_info.h | 2 --
 arch/x86/kernel/process.c          | 8 --------
 arch/x86/kernel/process_32.c       | 5 +++++
 arch/x86/kernel/signal.c           | 4 ----
 arch/x86/kernel/vm86_32.c          | 6 +++---
 5 files changed, 8 insertions(+), 17 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 89f794f007ec..c509d07bdbd7 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -79,7 +79,6 @@ struct thread_info {
 #define TIF_SIGPENDING		2	/* signal pending */
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
 #define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
-#define TIF_IRET		5	/* force IRET */
 #define TIF_SYSCALL_EMU		6	/* syscall emulation active */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
@@ -104,7 +103,6 @@ struct thread_info {
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_IRET		(1 << TIF_IRET)
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ef6a8456f719..7162e9c1f598 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -351,14 +351,6 @@ long sys_execve(const char __user *name,
 	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;
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 516fa186121b..75fcad146def 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -194,6 +194,11 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 	 * Free the old FP and other extended state
 	 */
 	free_thread_xstate(current);
+	/*
+	 * force it to the iret return path by making it look as if there was
+	 * some work pending.
+	 */
+	set_thread_flag(TIF_NOTIFY_RESUME);
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index b280908a376e..c648fc529872 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -800,10 +800,6 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 	}
 	if (thread_info_flags & _TIF_USER_RETURN_NOTIFY)
 		fire_user_return_notifiers();
-
-#ifdef CONFIG_X86_32
-	clear_thread_flag(TIF_IRET);
-#endif /* CONFIG_X86_32 */
 }
 
 void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 54abcc0baf23..5c9687b1bde6 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -561,9 +561,9 @@ int handle_vm86_trap(struct kernel_vm86_regs *regs, long error_code, int trapno)
 		if ((trapno == 3) || (trapno == 1)) {
 			KVM86->regs32->ax = VM86_TRAP + (trapno << 8);
 			/* setting this flag forces the code in entry_32.S to
-			   call save_v86_state() and change the stack pointer
-			   to KVM86->regs32 */
-			set_thread_flag(TIF_IRET);
+			   the path where we call save_v86_state() and change
+			   the stack pointer to KVM86->regs32 */
+			set_thread_flag(TIF_NOTIFY_RESUME);
 			return 0;
 		}
 		do_int(regs, trapno, (unsigned char __user *) (regs->pt.ss << 4), SP(regs));
-- 
cgit v1.2.3


From 8e2c85aa6c7a158d967db75931db7f13d20d31f4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 6 Sep 2012 13:39:47 -0400
Subject: um: let signal_delivered() do SIGTRAP on singlestepping into handler

... rather than duplicating that in sigframe setup code (and doing that
inconsistently, at that)

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/um/signal.c | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c
index a508cea13503..ba7363ecf896 100644
--- a/arch/x86/um/signal.c
+++ b/arch/x86/um/signal.c
@@ -416,9 +416,6 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig,
 	PT_REGS_AX(regs) = (unsigned long) sig;
 	PT_REGS_DX(regs) = (unsigned long) 0;
 	PT_REGS_CX(regs) = (unsigned long) 0;
-
-	if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
-		ptrace_notify(SIGTRAP);
 	return 0;
 }
 
@@ -466,9 +463,6 @@ int setup_signal_stack_si(unsigned long stack_top, int sig,
 	PT_REGS_AX(regs) = (unsigned long) sig;
 	PT_REGS_DX(regs) = (unsigned long) &frame->info;
 	PT_REGS_CX(regs) = (unsigned long) &frame->uc;
-
-	if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED))
-		ptrace_notify(SIGTRAP);
 	return 0;
 }
 
-- 
cgit v1.2.3


From a4d94ff8aa864c05b33c2de1f8c5d0176d7a4b63 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 20 Sep 2012 09:28:25 -0400
Subject: um: kill thread->forking

we only use that to tell copy_thread() done by syscall from that
done by kernel_thread().  However, it's easier to do simply by
checking PF_KTHREAD in thread flags.

Merge sys_clone() guts for 32bit and 64bit, while we are at it...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/um/shared/sysdep/syscalls.h |  2 ++
 arch/x86/um/sys_call_table_32.c      |  2 +-
 arch/x86/um/syscalls_32.c            | 27 +++++++--------------------
 arch/x86/um/syscalls_64.c            | 23 +++--------------------
 4 files changed, 13 insertions(+), 41 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
index bd9a89b67e41..ca255a805ed9 100644
--- a/arch/x86/um/shared/sysdep/syscalls.h
+++ b/arch/x86/um/shared/sysdep/syscalls.h
@@ -1,3 +1,5 @@
+extern long sys_clone(unsigned long clone_flags, unsigned long newsp,
+	       void __user *parent_tid, void __user *child_tid);
 #ifdef __i386__
 #include "syscalls_32.h"
 #else
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 68d1dc91b37b..b5408cecac6c 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -28,7 +28,7 @@
 #define ptregs_execve sys_execve
 #define ptregs_iopl sys_iopl
 #define ptregs_vm86old sys_vm86old
-#define ptregs_clone sys_clone
+#define ptregs_clone i386_clone
 #define ptregs_vm86 sys_vm86
 #define ptregs_sigaltstack sys_sigaltstack
 #define ptregs_vfork sys_vfork
diff --git a/arch/x86/um/syscalls_32.c b/arch/x86/um/syscalls_32.c
index b853e8600b9d..db444c7218fe 100644
--- a/arch/x86/um/syscalls_32.c
+++ b/arch/x86/um/syscalls_32.c
@@ -3,37 +3,24 @@
  * Licensed under the GPL
  */
 
-#include "linux/sched.h"
-#include "linux/shm.h"
-#include "linux/ipc.h"
-#include "linux/syscalls.h"
-#include "asm/mman.h"
-#include "asm/uaccess.h"
-#include "asm/unistd.h"
+#include <linux/syscalls.h>
+#include <sysdep/syscalls.h>
 
 /*
  * The prototype on i386 is:
  *
- *     int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls, int * child_tidptr)
+ *     int clone(int flags, void * child_stack, int * parent_tidptr, struct user_desc * newtls
  *
  * and the "newtls" arg. on i386 is read by copy_thread directly from the
  * register saved on the stack.
  */
-long sys_clone(unsigned long clone_flags, unsigned long newsp,
-	       int __user *parent_tid, void *newtls, int __user *child_tid)
+long i386_clone(unsigned long clone_flags, unsigned long newsp,
+		int __user *parent_tid, void *newtls, int __user *child_tid)
 {
-	long ret;
-
-	if (!newsp)
-		newsp = UPT_SP(&current->thread.regs.regs);
-
-	current->thread.forking = 1;
-	ret = do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
-		      child_tid);
-	current->thread.forking = 0;
-	return ret;
+	return sys_clone(clone_flags, newsp, parent_tid, child_tid);
 }
 
+
 long sys_sigaction(int sig, const struct old_sigaction __user *act,
 			 struct old_sigaction __user *oact)
 {
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index f3d82bb6e15a..adb08eb5c22a 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -5,12 +5,9 @@
  * Licensed under the GPL
  */
 
-#include "linux/linkage.h"
-#include "linux/personality.h"
-#include "linux/utsname.h"
-#include "asm/prctl.h" /* XXX This should get the constants from libc */
-#include "asm/uaccess.h"
-#include "os.h"
+#include <linux/sched.h>
+#include <asm/prctl.h> /* XXX This should get the constants from libc */
+#include <os.h>
 
 long arch_prctl(struct task_struct *task, int code, unsigned long __user *addr)
 {
@@ -79,20 +76,6 @@ long sys_arch_prctl(int code, unsigned long addr)
 	return arch_prctl(current, code, (unsigned long __user *) addr);
 }
 
-long sys_clone(unsigned long clone_flags, unsigned long newsp,
-	       void __user *parent_tid, void __user *child_tid)
-{
-	long ret;
-
-	if (!newsp)
-		newsp = UPT_SP(&current->thread.regs.regs);
-	current->thread.forking = 1;
-	ret = do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
-		      child_tid);
-	current->thread.forking = 0;
-	return ret;
-}
-
 void arch_switch_to(struct task_struct *to)
 {
 	if ((to->thread.arch.fs == 0) || (to->mm == NULL))
-- 
cgit v1.2.3


From 7076aada1040de4ed79a5977dbabdb5e5ea5e249 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 10 Sep 2012 16:44:54 -0400
Subject: x86: split ret_from_fork

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/Kconfig                 |  1 +
 arch/x86/include/asm/processor.h |  5 -----
 arch/x86/kernel/entry_32.S       | 15 ++++++++++-----
 arch/x86/kernel/entry_64.S       | 27 +++++++++++----------------
 arch/x86/kernel/process.c        | 38 --------------------------------------
 arch/x86/kernel/process_32.c     | 31 ++++++++++++++++++++++++-------
 arch/x86/kernel/process_64.c     | 35 +++++++++++++++++++++--------------
 7 files changed, 67 insertions(+), 85 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ec3a1aa4abd..d93eb9d1bb97 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -97,6 +97,7 @@ config X86
 	select KTIME_SCALAR if X86_32
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select GENERIC_KERNEL_THREAD
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS || UPROBES)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d048cad9bcad..078f3fdedf95 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -589,11 +589,6 @@ typedef struct {
 } mm_segment_t;
 
 
-/*
- * create a kernel thread without removing it from tasklists
- */
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 623f28837476..ac1107346fc9 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -994,15 +994,20 @@ END(spurious_interrupt_bug)
  */
 	.popsection
 
-ENTRY(kernel_thread_helper)
-	pushl $0		# fake return address for unwinder
+ENTRY(ret_from_kernel_thread)
 	CFI_STARTPROC
-	movl %edi,%eax
-	call *%esi
+	pushl_cfi %eax
+	call schedule_tail
+	GET_THREAD_INFO(%ebp)
+	popl_cfi %eax
+	pushl_cfi $0x0202		# Reset kernel eflags
+	popfl_cfi
+	movl PT_EBP(%esp),%eax
+	call *PT_EBX(%esp)
 	call do_exit
 	ud2			# padding for call trace
 	CFI_ENDPROC
-ENDPROC(kernel_thread_helper)
+ENDPROC(ret_from_kernel_thread)
 
 #ifdef CONFIG_XEN
 /* Xen doesn't set %esp to be precisely what the normal sysenter
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 69babd8c834f..5526d17db676 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -450,7 +450,7 @@ ENTRY(ret_from_fork)
 	RESTORE_REST
 
 	testl $3, CS-ARGOFFSET(%rsp)		# from kernel_thread?
-	jz   retint_restore_args
+	jz   1f
 
 	testl $_TIF_IA32, TI_flags(%rcx)	# 32-bit compat task needs IRET
 	jnz  int_ret_from_sys_call
@@ -458,6 +458,16 @@ ENTRY(ret_from_fork)
 	RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
 	jmp ret_from_sys_call			# go to the SYSRET fastpath
 
+1:
+	subq $REST_SKIP, %rsp	# move the stack pointer back
+	CFI_ADJUST_CFA_OFFSET	REST_SKIP
+	movq %rbp, %rdi
+	call *%rbx
+	# exit
+	mov %eax, %edi
+	call do_exit
+	ud2			# padding for call trace
+
 	CFI_ENDPROC
 END(ret_from_fork)
 
@@ -1206,21 +1216,6 @@ bad_gs:
 	jmp  2b
 	.previous
 
-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.
-	 */
-	call *%rsi
-	# exit
-	mov %eax, %edi
-	call do_exit
-	ud2			# padding for call trace
-	CFI_ENDPROC
-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/process.c b/arch/x86/kernel/process.c
index 7162e9c1f598..6947ec968bf8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -298,44 +298,6 @@ sys_clone(unsigned long clone_flags, unsigned long newsp,
 	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;
-#else
-	regs.ss = __KERNEL_DS;
-#endif
-
-	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_BIT1;
-
-	/* 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.
  */
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 75fcad146def..c9939875d267 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -57,6 +57,7 @@
 #include <asm/switch_to.h>
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
+asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread");
 
 /*
  * Return saved PC of a blocked thread.
@@ -127,23 +128,39 @@ void release_thread(struct task_struct *dead_task)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-	unsigned long unused,
+	unsigned long arg,
 	struct task_struct *p, struct pt_regs *regs)
 {
-	struct pt_regs *childregs;
+	struct pt_regs *childregs = task_pt_regs(p);
 	struct task_struct *tsk;
 	int err;
 
-	childregs = task_pt_regs(p);
+	p->thread.sp = (unsigned long) childregs;
+	p->thread.sp0 = (unsigned long) (childregs+1);
+
+	if (unlikely(!regs)) {
+		/* kernel thread */
+		memset(childregs, 0, sizeof(struct pt_regs));
+		p->thread.ip = (unsigned long) ret_from_kernel_thread;
+		task_user_gs(p) = __KERNEL_STACK_CANARY;
+		childregs->ds = __USER_DS;
+		childregs->es = __USER_DS;
+		childregs->fs = __KERNEL_PERCPU;
+		childregs->bx = sp;	/* function */
+		childregs->bp = arg;
+		childregs->orig_ax = -1;
+		childregs->cs = __KERNEL_CS | get_kernel_rpl();
+		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+		p->fpu_counter = 0;
+		p->thread.io_bitmap_ptr = NULL;
+		memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+		return 0;
+	}
 	*childregs = *regs;
 	childregs->ax = 0;
 	childregs->sp = sp;
 
-	p->thread.sp = (unsigned long) childregs;
-	p->thread.sp0 = (unsigned long) (childregs+1);
-
 	p->thread.ip = (unsigned long) ret_from_fork;
-
 	task_user_gs(p) = get_user_gs(regs);
 
 	p->fpu_counter = 0;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 0a980c9d7cb8..937f2af6f2d4 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -146,29 +146,18 @@ static inline u32 read_32bit_tls(struct task_struct *t, int tls)
 }
 
 int copy_thread(unsigned long clone_flags, unsigned long sp,
-		unsigned long unused,
+		unsigned long arg,
 	struct task_struct *p, struct pt_regs *regs)
 {
 	int err;
 	struct pt_regs *childregs;
 	struct task_struct *me = current;
 
-	childregs = ((struct pt_regs *)
-			(THREAD_SIZE + task_stack_page(p))) - 1;
-	*childregs = *regs;
-
-	childregs->ax = 0;
-	if (user_mode(regs))
-		childregs->sp = sp;
-	else
-		childregs->sp = (unsigned long)childregs;
-
+	p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
+	childregs = task_pt_regs(p);
 	p->thread.sp = (unsigned long) childregs;
-	p->thread.sp0 = (unsigned long) (childregs+1);
 	p->thread.usersp = me->thread.usersp;
-
 	set_tsk_thread_flag(p, TIF_FORK);
-
 	p->fpu_counter = 0;
 	p->thread.io_bitmap_ptr = NULL;
 
@@ -178,6 +167,24 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	p->thread.fs = p->thread.fsindex ? 0 : me->thread.fs;
 	savesegment(es, p->thread.es);
 	savesegment(ds, p->thread.ds);
+	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
+
+	if (unlikely(!regs)) {
+		/* kernel thread */
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->sp = (unsigned long)childregs;
+		childregs->ss = __KERNEL_DS;
+		childregs->bx = sp; /* function */
+		childregs->bp = arg;
+		childregs->orig_ax = -1;
+		childregs->cs = __KERNEL_CS | get_kernel_rpl();
+		childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_BIT1;
+		return 0;
+	}
+	*childregs = *regs;
+
+	childregs->ax = 0;
+	childregs->sp = sp;
 
 	err = -ENOMEM;
 	memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-- 
cgit v1.2.3


From 6783eaa2e1253fbcbe2c2f6bb4c843abf1343caf Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 2 Aug 2012 23:05:11 +0400
Subject: 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/x86/ia32/ia32entry.S        |  2 +-
 arch/x86/ia32/sys_ia32.c         | 15 -------------
 arch/x86/include/asm/sys_ia32.h  |  2 --
 arch/x86/include/asm/syscalls.h  |  2 +-
 arch/x86/include/asm/unistd.h    |  2 ++
 arch/x86/kernel/Makefile         |  2 +-
 arch/x86/kernel/asm-offsets.c    |  3 +++
 arch/x86/kernel/entry_32.S       | 11 +++++++---
 arch/x86/kernel/entry_64.S       | 47 ++++++++++++----------------------------
 arch/x86/kernel/process.c        | 19 ----------------
 arch/x86/kernel/process_32.c     |  1 +
 arch/x86/kernel/sys_i386_32.c    | 40 ----------------------------------
 arch/x86/syscalls/syscall_32.tbl |  2 +-
 arch/x86/um/sys_call_table_32.c  |  1 -
 14 files changed, 32 insertions(+), 117 deletions(-)
 delete mode 100644 arch/x86/kernel/sys_i386_32.c

(limited to 'arch/x86')

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 20e5f7ba0e6b..e75f941bd2b2 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/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
diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 4540bece0946..6b31144589d0 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/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)
 {
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 3fda9db48819..1ac127f41fe6 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/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);
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index f1d8b441fc77..2be0b880417e 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/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 *);
 
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 0d9776e9e2dc..55d155560fdf 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/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
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 8215e5652d97..566100002233 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 68de2dc962ec..28610822fb3c 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/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));
 }
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index ac1107346fc9..b6bb69239296 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/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)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 5526d17db676..053c9552ffd9 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/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)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6947ec968bf8..eae2dd5cd5a0 100644
--- a/arch/x86/kernel/process.c
+++ b/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
  */
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c9939875d267..25e7e9390d26 100644
--- a/arch/x86/kernel/process_32.c
+++ b/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
 	 */
diff --git a/arch/x86/kernel/sys_i386_32.c b/arch/x86/kernel/sys_i386_32.c
deleted file mode 100644
index 0b0cb5fede19..000000000000
--- a/arch/x86/kernel/sys_i386_32.c
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * 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;
-}
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 7a35a6e71d44..a47103fbc692 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/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
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index b5408cecac6c..232e60504b3a 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/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
-- 
cgit v1.2.3


From 1f02ab4a237086095bd584f3446da307ac2d02e6 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 21 Sep 2012 20:32:29 -0400
Subject: um: switch to generic kernel_thread()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/x86/um/Kconfig | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 9926e11a772d..da85b6fc8e8e 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -13,6 +13,7 @@ endmenu
 config UML_X86
 	def_bool y
 	select GENERIC_FIND_FIRST_BIT
+	select GENERIC_KERNEL_THREAD
 
 config 64BIT
 	bool "64-bit kernel" if SUBARCH = "x86"
-- 
cgit v1.2.3