Merge master.kernel.org:BK/linux-2.5

into home.transmeta.com:/home/torvalds/v2.5/linux

arch/i386/kernel/entry.S

@@ -69,24 +69,27 @@ IF_MASK		= 0x00000200
 NT_MASK		= 0x00004000
 VM_MASK		= 0x00020000
 
-/* These are offsets into the irq_stat structure
+/*
+ * These are offsets into the irq_stat structure
  * There is one per cpu and it is aligned to 32
  * byte boundry (we put that here as a shift count)
  */
-irq_array_shift			= CONFIG_X86_L1_CACHE_SHIFT
-irq_stat_local_irq_count	= 4
-irq_stat_local_bh_count		= 8
+irq_array_shift	= CONFIG_X86_L1_CACHE_SHIFT
+local_irq_count	= 4
+local_bh_count	= 8
 
 #ifdef CONFIG_SMP
-#define GET_CPU_INDX	movl TI_CPU(%ebx),%eax;  \
-                        shll $irq_array_shift,%eax
-#define GET_CURRENT_CPU_INDX GET_THREAD_INFO(%ebx); \
-                             GET_CPU_INDX
-#define CPU_INDX (,%eax)
+#define GET_CPU_IDX \
+		movl TI_CPU(%ebx), %eax;  \
+		shll $irq_array_shift, %eax
+#define GET_CURRENT_CPU_IDX \
+		GET_THREAD_INFO(%ebx); \
+		GET_CPU_IDX
+#define CPU_IDX (,%eax)
 #else
-#define GET_CPU_INDX
-#define GET_CURRENT_CPU_INDX GET_THREAD_INFO(%ebx)
-#define CPU_INDX
+#define GET_CPU_IDX
+#define GET_CURRENT_CPU_IDX GET_THREAD_INFO(%ebx)
+#define CPU_IDX
 #endif
 
 #ifdef CONFIG_PREEMPT
@@ -111,9 +114,9 @@ irq_stat_local_bh_count		= 8
 	pushl %edx; \
 	pushl %ecx; \
 	pushl %ebx; \
-	movl $(__KERNEL_DS),%edx; \
-	movl %edx,%ds; \
-	movl %edx,%es;
+	movl $(__KERNEL_DS), %edx; \
+	movl %edx, %ds; \
+	movl %edx, %es;
 
 #define RESTORE_ALL	\
 	popl %ebx;	\
@@ -125,7 +128,7 @@ irq_stat_local_bh_count		= 8
 	popl %eax;	\
 1:	popl %ds;	\
 2:	popl %es;	\
-	addl $4,%esp;	\
+	addl $4, %esp;	\
 3:	iret;		\
 .section .fixup,"ax";	\
 4:	movl $0,(%esp);	\
@@ -147,20 +150,21 @@ irq_stat_local_bh_count		= 8
 .previous
 
 ENTRY(lcall7)
-	pushfl			# We get a different stack layout with call gates,
-	pushl %eax		# which has to be cleaned up later..
+	pushfl			# We get a different stack layout with call
+				# gates, which has to be cleaned up later..
+	pushl %eax
 	SAVE_ALL
-	movl EIP(%esp),%eax	# due to call gates, this is eflags, not eip..
-	movl CS(%esp),%edx	# this is eip..
-	movl EFLAGS(%esp),%ecx	# and this is cs..
+	movl EIP(%esp), %eax	# due to call gates, this is eflags, not eip..
+	movl CS(%esp), %edx	# this is eip..
+	movl EFLAGS(%esp), %ecx	# and this is cs..
 	movl %eax,EFLAGS(%esp)	#
 	movl %edx,EIP(%esp)	# Now we move them to their "normal" places
 	movl %ecx,CS(%esp)	#
-	movl %esp,%ebx
+	movl %esp, %ebx
 	pushl %ebx
-	andl $-8192,%ebx	# GET_THREAD_INFO
-	movl TI_EXEC_DOMAIN(%ebx),%edx	# Get the execution domain
-	movl 4(%edx),%edx	# Get the lcall7 handler for the domain
+	andl $-8192, %ebx	# GET_THREAD_INFO
+	movl TI_EXEC_DOMAIN(%ebx), %edx	# Get the execution domain
+	movl 4(%edx), %edx	# Get the lcall7 handler for the domain
 	pushl $0x7
 	call *%edx
 	addl $4, %esp
@@ -168,20 +172,21 @@ ENTRY(lcall7)
 	jmp resume_userspace
 
 ENTRY(lcall27)
-	pushfl			# We get a different stack layout with call gates,
-	pushl %eax		# which has to be cleaned up later..
+	pushfl			# We get a different stack layout with call
+				# gates, which has to be cleaned up later..
+	pushl %eax
 	SAVE_ALL
-	movl EIP(%esp),%eax	# due to call gates, this is eflags, not eip..
-	movl CS(%esp),%edx	# this is eip..
-	movl EFLAGS(%esp),%ecx	# and this is cs..
+	movl EIP(%esp), %eax	# due to call gates, this is eflags, not eip..
+	movl CS(%esp), %edx	# this is eip..
+	movl EFLAGS(%esp), %ecx	# and this is cs..
 	movl %eax,EFLAGS(%esp)	#
 	movl %edx,EIP(%esp)	# Now we move them to their "normal" places
 	movl %ecx,CS(%esp)	#
-	movl %esp,%ebx
+	movl %esp, %ebx
 	pushl %ebx
-	andl $-8192,%ebx	# GET_THREAD_INFO
-	movl TI_EXEC_DOMAIN(%ebx),%edx	# Get the execution domain
-	movl 4(%edx),%edx	# Get the lcall7 handler for the domain
+	andl $-8192, %ebx	# GET_THREAD_INFO
+	movl TI_EXEC_DOMAIN(%ebx), %edx	# Get the execution domain
+	movl 4(%edx), %edx	# Get the lcall7 handler for the domain
 	pushl $0x27
 	call *%edx
 	addl $4, %esp
@@ -211,15 +216,17 @@ ENTRY(ret_from_intr)
 	GET_THREAD_INFO(%ebx)
 	init_ret_intr
 ret_from_exception:
-	movl EFLAGS(%esp),%eax		# mix EFLAGS and CS
-	movb CS(%esp),%al
-	testl $(VM_MASK | 3),%eax
+	movl EFLAGS(%esp), %eax		# mix EFLAGS and CS
+	movb CS(%esp), %al
+	testl $(VM_MASK | 3), %eax
 	jz resume_kernel		# returning to kernel or vm86-space
 ENTRY(resume_userspace)
- 	cli				# make sure we don't miss an interrupt setting need_resched
- 					# or sigpending between sampling and the iret
-	movl TI_FLAGS(%ebx),%ecx
-	andl $_TIF_WORK_MASK,%ecx	# is there any work to be done on int/excp return?
+ 	cli				# make sure we don't miss an interrupt
+					# setting need_resched or sigpending
+					# between sampling and the iret
+	movl TI_FLAGS(%ebx), %ecx
+	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done on
+					# int/exception return?
 	jne work_pending
 	jmp restore_all
 
@@ -227,15 +234,17 @@ ENTRY(resume_userspace)
 ENTRY(resume_kernel)
 	cmpl $0,TI_PRE_COUNT(%ebx)
 	jnz restore_all
-	movl TI_FLAGS(%ebx),%ecx
-	testb $_TIF_NEED_RESCHED,%cl
+	movl TI_FLAGS(%ebx), %ecx
+	testb $_TIF_NEED_RESCHED, %cl
 	jz restore_all
-	movl SYMBOL_NAME(irq_stat)+irq_stat_local_bh_count CPU_INDX,%ecx
-	addl SYMBOL_NAME(irq_stat)+irq_stat_local_irq_count CPU_INDX,%ecx
+	movl SYMBOL_NAME(irq_stat)+local_bh_count CPU_IDX, %ecx
+	addl SYMBOL_NAME(irq_stat)+local_irq_count CPU_IDX, %ecx
 	jnz restore_all
 	incl TI_PRE_COUNT(%ebx)
 	sti
-	call SYMBOL_NAME(preempt_schedule)
+	movl TI_TASK(%ebx), %ecx		# ti->task
+	movl $0,(%ecx)			# current->state = TASK_RUNNING
+	call SYMBOL_NAME(schedule)
 	jmp ret_from_intr
 #endif
 
@@ -245,18 +254,20 @@ ENTRY(system_call)
 	pushl %eax			# save orig_eax
 	SAVE_ALL
 	GET_THREAD_INFO(%ebx)
-	cmpl $(NR_syscalls),%eax
+	cmpl $(NR_syscalls), %eax
 	jae syscall_badsys
-	testb $_TIF_SYSCALL_TRACE,TI_FLAGS(%ebx)	# system call tracing in operation
+					# system call tracing in operation
+	testb $_TIF_SYSCALL_TRACE,TI_FLAGS(%ebx)
 	jnz syscall_trace_entry
 syscall_call:
 	call *SYMBOL_NAME(sys_call_table)(,%eax,4)
 	movl %eax,EAX(%esp)		# store the return value
 syscall_exit:
- 	cli				# make sure we don't miss an interrupt setting need_resched
- 					# or sigpending between sampling and the iret
-	movl TI_FLAGS(%ebx),%ecx
-	testw $_TIF_ALLWORK_MASK,%cx	# current->work
+	cli				# make sure we don't miss an interrupt
+					# setting need_resched or sigpending
+					# between sampling and the iret
+	movl TI_FLAGS(%ebx), %ecx
+	testw $_TIF_ALLWORK_MASK, %cx	# current->work
 	jne syscall_exit_work
 restore_all:
 	RESTORE_ALL
@@ -264,23 +275,27 @@ restore_all:
 	# perform work that needs to be done immediately before resumption
 	ALIGN
 work_pending:
-	testb $_TIF_NEED_RESCHED,%cl
+	testb $_TIF_NEED_RESCHED, %cl
 	jz work_notifysig
 work_resched:
 	call SYMBOL_NAME(schedule)
- 	cli				# make sure we don't miss an interrupt setting need_resched
- 					# or sigpending between sampling and the iret
-	movl TI_FLAGS(%ebx),%ecx
-	andl $_TIF_WORK_MASK,%ecx	# is there any work to be done other than syscall tracing?
+	cli				# make sure we don't miss an interrupt
+					# setting need_resched or sigpending
+					# between sampling and the iret
+	movl TI_FLAGS(%ebx), %ecx
+	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done other
+					# than syscall tracing?
 	jz restore_all
-	testb $_TIF_NEED_RESCHED,%cl
+	testb $_TIF_NEED_RESCHED, %cl
 	jnz work_resched
 
-work_notifysig:				# deal with pending signals and notify-resume requests
+work_notifysig:				# deal with pending signals and
+					# notify-resume requests
 	testl $(VM_MASK),EFLAGS(%esp)
-	movl %esp,%eax
-	jne work_notifysig_v86		# returning to kernel-space or vm86-space
-	xorl %edx,%edx
+	movl %esp, %eax
+	jne work_notifysig_v86		# returning to kernel-space or
+					# vm86-space
+	xorl %edx, %edx
 	call SYMBOL_NAME(do_notify_resume)
 	jmp restore_all
 
@@ -289,8 +304,8 @@ work_notifysig_v86:
 	pushl %ecx
 	call SYMBOL_NAME(save_v86_state)
 	popl %ecx
-	movl %eax,%esp
-	xorl %edx,%edx
+	movl %eax, %esp
+	xorl %edx, %edx
 	call SYMBOL_NAME(do_notify_resume)
 	jmp restore_all
 
@@ -298,22 +313,23 @@ work_notifysig_v86:
 	ALIGN
 syscall_trace_entry:
 	movl $-ENOSYS,EAX(%esp)
-	movl %esp,%eax
+	movl %esp, %eax
 	xorl %edx,%edx
 	call SYMBOL_NAME(do_syscall_trace)
-	movl ORIG_EAX(%esp),%eax
-	cmpl $(NR_syscalls),%eax
+	movl ORIG_EAX(%esp), %eax
+	cmpl $(NR_syscalls), %eax
 	jnae syscall_call
 	jmp syscall_exit
 
 	# perform syscall exit tracing
 	ALIGN
 syscall_exit_work:
-	testb $_TIF_SYSCALL_TRACE,%cl
+	testb $_TIF_SYSCALL_TRACE, %cl
 	jz work_pending
-	sti				# could let do_syscall_trace() call schedule() instead
-	movl %esp,%eax
-	movl $1,%edx
+	sti				# could let do_syscall_trace() call
+					# schedule() instead
+	movl %esp, %eax
+	movl $1, %edx
 	call SYMBOL_NAME(do_syscall_trace)
 	jmp resume_userspace
 
@@ -323,13 +339,13 @@ syscall_badsys:
 	jmp resume_userspace
 
 ENTRY(divide_error)
-	pushl $0		# no error code
+	pushl $0			# no error code
 	pushl $ SYMBOL_NAME(do_divide_error)
 	ALIGN
 error_code:
 	pushl %ds
 	pushl %eax
-	xorl %eax,%eax
+	xorl %eax, %eax
 	pushl %ebp
 	pushl %edi
 	pushl %esi
@@ -338,20 +354,20 @@ error_code:
 	pushl %ecx
 	pushl %ebx
 	cld
-	movl %es,%ecx
+	movl %es, %ecx
 	movl ORIG_EAX(%esp), %esi	# get the error code
 	movl ES(%esp), %edi		# get the function address
 	movl %eax, ORIG_EAX(%esp)
 	movl %ecx, ES(%esp)
-	movl %esp,%edx
+	movl %esp, %edx
 	pushl %esi			# push the error code
 	pushl %edx			# push the pt_regs pointer
-	movl $(__KERNEL_DS),%edx
-	movl %edx,%ds
-	movl %edx,%es
+	movl $(__KERNEL_DS), %edx
+	movl %edx, %ds
+	movl %edx, %es
 	GET_THREAD_INFO(%ebx)
 	call *%edi
-	addl $8,%esp
+	addl $8, %esp
 	preempt_stop
 	jmp ret_from_exception
 
@@ -366,19 +382,19 @@ ENTRY(simd_coprocessor_error)
 	jmp error_code
 
 ENTRY(device_not_available)
-	pushl $-1		# mark this as an int
+	pushl $-1			# mark this as an int
 	SAVE_ALL
 	GET_THREAD_INFO(%ebx)
-	movl %cr0,%eax
-	testl $0x4,%eax			# EM (math emulation bit)
+	movl %cr0, %eax
+	testl $0x4, %eax		# EM (math emulation bit)
 	jne device_not_available_emulate
 	preempt_stop
 	call SYMBOL_NAME(math_state_restore)
 	jmp ret_from_exception
 device_not_available_emulate:
-	pushl $0		# temporary storage for ORIG_EIP
+	pushl $0			# temporary storage for ORIG_EIP
 	call  SYMBOL_NAME(math_emulate)
-	addl $4,%esp
+	addl $4, %esp
 	preempt_stop
 	jmp ret_from_exception
 
@@ -390,11 +406,11 @@ ENTRY(debug)
 ENTRY(nmi)
 	pushl %eax
 	SAVE_ALL
-	movl %esp,%edx
+	movl %esp, %edx
 	pushl $0
 	pushl %edx
 	call SYMBOL_NAME(do_nmi)
-	addl $8,%esp
+	addl $8, %esp
 	RESTORE_ALL
 
 ENTRY(int3)
@@ -479,7 +495,7 @@ ENTRY(sys_call_table)
 	.long SYMBOL_NAME(sys_mknod)
 	.long SYMBOL_NAME(sys_chmod)		/* 15 */
 	.long SYMBOL_NAME(sys_lchown16)
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old break syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old break syscall holder */
 	.long SYMBOL_NAME(sys_stat)
 	.long SYMBOL_NAME(sys_lseek)
 	.long SYMBOL_NAME(sys_getpid)		/* 20 */
@@ -493,11 +509,12 @@ ENTRY(sys_call_table)
 	.long SYMBOL_NAME(sys_fstat)
 	.long SYMBOL_NAME(sys_pause)
 	.long SYMBOL_NAME(sys_utime)		/* 30 */
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old stty syscall holder */
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old gtty syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old stty syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old gtty syscall holder */
 	.long SYMBOL_NAME(sys_access)
 	.long SYMBOL_NAME(sys_nice)
-	.long SYMBOL_NAME(sys_ni_syscall)	/* 35 */		/* old ftime syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* 35 */
+						/* old ftime syscall holder */
 	.long SYMBOL_NAME(sys_sync)
 	.long SYMBOL_NAME(sys_kill)
 	.long SYMBOL_NAME(sys_rename)
@@ -506,7 +523,7 @@ ENTRY(sys_call_table)
 	.long SYMBOL_NAME(sys_dup)
 	.long SYMBOL_NAME(sys_pipe)
 	.long SYMBOL_NAME(sys_times)
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old prof syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old prof syscall holder */
 	.long SYMBOL_NAME(sys_brk)		/* 45 */
 	.long SYMBOL_NAME(sys_setgid16)
 	.long SYMBOL_NAME(sys_getgid16)
@@ -514,13 +531,13 @@ ENTRY(sys_call_table)
 	.long SYMBOL_NAME(sys_geteuid16)
 	.long SYMBOL_NAME(sys_getegid16)	/* 50 */
 	.long SYMBOL_NAME(sys_acct)
-	.long SYMBOL_NAME(sys_umount)					/* recycled never used phys() */
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old lock syscall holder */
+	.long SYMBOL_NAME(sys_umount)		/* recycled never used phys() */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old lock syscall holder */
 	.long SYMBOL_NAME(sys_ioctl)
 	.long SYMBOL_NAME(sys_fcntl)		/* 55 */
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old mpx syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old mpx syscall holder */
 	.long SYMBOL_NAME(sys_setpgid)
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old ulimit syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old ulimit syscall holder */
 	.long SYMBOL_NAME(sys_olduname)
 	.long SYMBOL_NAME(sys_umask)		/* 60 */
 	.long SYMBOL_NAME(sys_chroot)
@@ -560,7 +577,7 @@ ENTRY(sys_call_table)
 	.long SYMBOL_NAME(sys_fchown16)		/* 95 */
 	.long SYMBOL_NAME(sys_getpriority)
 	.long SYMBOL_NAME(sys_setpriority)
-	.long SYMBOL_NAME(sys_ni_syscall)				/* old profil syscall holder */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* old profil syscall holder */
 	.long SYMBOL_NAME(sys_statfs)
 	.long SYMBOL_NAME(sys_fstatfs)		/* 100 */
 	.long SYMBOL_NAME(sys_ioperm)
@@ -650,8 +667,8 @@ ENTRY(sys_call_table)
 	.long SYMBOL_NAME(sys_capset)           /* 185 */
 	.long SYMBOL_NAME(sys_sigaltstack)
 	.long SYMBOL_NAME(sys_sendfile)
-	.long SYMBOL_NAME(sys_ni_syscall)		/* streams1 */
-	.long SYMBOL_NAME(sys_ni_syscall)		/* streams2 */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* streams1 */
+	.long SYMBOL_NAME(sys_ni_syscall)	/* streams2 */
 	.long SYMBOL_NAME(sys_vfork)            /* 190 */
 	.long SYMBOL_NAME(sys_getrlimit)
 	.long SYMBOL_NAME(sys_mmap2)
@@ -700,7 +717,7 @@ ENTRY(sys_call_table)
 	.long SYMBOL_NAME(sys_removexattr)	/* 235 */
 	.long SYMBOL_NAME(sys_lremovexattr)
 	.long SYMBOL_NAME(sys_fremovexattr)
- 	.long SYMBOL_NAME(sys_tkill)
+	.long SYMBOL_NAME(sys_tkill)
 
 	.rept NR_syscalls-(.-sys_call_table)/4
 		.long SYMBOL_NAME(sys_ni_syscall)

arch/i386/kernel/ptrace.c

@@ -455,9 +455,11 @@ void do_syscall_trace(struct pt_regs *regs, int entryexit)
 	   between a syscall stop and SIGTRAP delivery */
 	current->exit_code = SIGTRAP | ((current->ptrace & PT_TRACESYSGOOD)
 					? 0x80 : 0);
+	preempt_disable();
 	current->state = TASK_STOPPED;
 	notify_parent(current, SIGCHLD);
 	schedule();
+	preempt_enable();
 	/*
 	 * this isn't the same as continuing with a signal, but it will do
 	 * for normal use.  strace only continues with a signal if the

arch/i386/kernel/signal.c

@@ -610,9 +610,11 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 		if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
 			/* Let the debugger run.  */
 			current->exit_code = signr;
+			preempt_disable();
 			current->state = TASK_STOPPED;
 			notify_parent(current, SIGCHLD);
 			schedule();
+			preempt_enable();
 
 			/* We're back.  Did the debugger cancel the sig?  */
 			if (!(signr = current->exit_code))
@@ -667,12 +669,14 @@ int do_signal(struct pt_regs *regs, sigset_t *oldset)
 
 			case SIGSTOP: {
 				struct signal_struct *sig;
-				current->state = TASK_STOPPED;
 				current->exit_code = signr;
 				sig = current->p_pptr->sig;
+				preempt_disable();
+				current->state = TASK_STOPPED;
 				if (sig && !(sig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDSTOP))
 					notify_parent(current, SIGCHLD);
 				schedule();
+				preempt_enable();
 				continue;
 			}
 

include/asm-i386/bitops.h

@@ -415,6 +415,25 @@ static __inline__ unsigned long __ffs(unsigned long word)
 
 #ifdef __KERNEL__
 
+/*
+ * Every architecture must define this function. It's the fastest
+ * way of searching a 140-bit bitmap where the first 100 bits are
+ * unlikely to be set. It's guaranteed that at least one of the 140
+ * bits is cleared.
+ */
+static inline int sched_find_first_bit(unsigned long *b)
+{
+	if (unlikely(b[0]))
+		return __ffs(b[0]);
+	if (unlikely(b[1]))
+		return __ffs(b[1]) + 32;
+	if (unlikely(b[2]))
+		return __ffs(b[2]) + 64;
+	if (b[3])
+		return __ffs(b[3]) + 96;
+	return __ffs(b[4]) + 128;
+}
+
 /**
  * ffs - find first bit set
  * @x: the word to search

include/asm-i386/mmu_context.h

@@ -6,24 +6,6 @@
 #include <asm/atomic.h>
 #include <asm/pgalloc.h>
 
-/*
- * Every architecture must define this function. It's the fastest
- * way of searching a 140-bit bitmap where the first 100 bits are
- * unlikely to be set. It's guaranteed that at least one of the 140
- * bits is cleared.
- */
-static inline int sched_find_first_bit(unsigned long *b)
-{
-	if (unlikely(b[0]))
-		return __ffs(b[0]);
-	if (unlikely(b[1]))
-		return __ffs(b[1]) + 32;
-	if (unlikely(b[2]))
-		return __ffs(b[2]) + 64;
-	if (b[3])
-		return __ffs(b[3]) + 96;
-	return __ffs(b[4]) + 128;
-}
 /*
  * possibly do the LDT unload here?
  */

include/asm-i386/system.h

@@ -13,24 +13,23 @@ struct task_struct;	/* one of the stranger aspects of C forward declarations.. *
 extern void FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next));
 
 #define prepare_to_switch()	do { } while(0)
-#define switch_to(prev,next,last) do {					\
+
+#define switch_to(prev,next) do {					\
 	asm volatile("pushl %%esi\n\t"					\
 		     "pushl %%edi\n\t"					\
 		     "pushl %%ebp\n\t"					\
 		     "movl %%esp,%0\n\t"	/* save ESP */		\
-		     "movl %3,%%esp\n\t"	/* restore ESP */	\
+		     "movl %2,%%esp\n\t"	/* restore ESP */	\
 		     "movl $1f,%1\n\t"		/* save EIP */		\
-		     "pushl %4\n\t"		/* restore EIP */	\
+		     "pushl %3\n\t"		/* restore EIP */	\
 		     "jmp __switch_to\n"				\
 		     "1:\t"						\
 		     "popl %%ebp\n\t"					\
 		     "popl %%edi\n\t"					\
 		     "popl %%esi\n\t"					\
-		     :"=m" (prev->thread.esp),"=m" (prev->thread.eip),	\
-		      "=b" (last)					\
+		     :"=m" (prev->thread.esp),"=m" (prev->thread.eip)	\
 		     :"m" (next->thread.esp),"m" (next->thread.eip),	\
-		      "a" (prev), "d" (next),				\
-		      "b" (prev));					\
+		      "a" (prev), "d" (next));				\
 } while (0)
 
 #define _set_base(addr,base) do { unsigned long __pr; \

include/linux/sched.h

@@ -92,7 +92,6 @@ extern unsigned long nr_running(void);
 #define TASK_UNINTERRUPTIBLE	2
 #define TASK_ZOMBIE		4
 #define TASK_STOPPED		8
-#define PREEMPT_ACTIVE		0x4000000
 
 #define __set_task_state(tsk, state_value)		\
 	do { (tsk)->state = (state_value); } while (0)

include/linux/spinlock.h

@@ -177,9 +177,8 @@ do { \
 do { \
 	--current_thread_info()->preempt_count; \
 	barrier(); \
-	if (unlikely(!(current_thread_info()->preempt_count) && \
-		test_thread_flag(TIF_NEED_RESCHED))) \
-			preempt_schedule(); \
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \
+		preempt_schedule(); \
 } while (0)
 
 #define spin_lock(lock)	\

kernel/exit.c

@@ -476,7 +476,12 @@ static void exit_notify(void)
 			write_lock_irq(&tasklist_lock);
 		}
 	}
-	write_unlock_irq(&tasklist_lock);
+	/*
+	 * No need to unlock IRQs, we'll schedule() immediately
+	 * anyway. In the preemption case this also makes it
+	 * impossible for the task to get runnable again.
+	 */
+	write_unlock(&tasklist_lock);
 }
 
 NORET_TYPE void do_exit(long code)

kernel/sched.c

@@ -435,17 +435,8 @@ static inline void context_switch(task_t *prev, task_t *next)
 		mmdrop(oldmm);
 	}
 
-	/*
-	 * Here we just switch the register state and the stack. There are
-	 * 3 processes affected by a context switch:
-	 *
-	 * prev ==> .... ==> (last => next)
-	 *
-	 * It's the 'much more previous' 'prev' that is on next's stack,
-	 * but prev is set to (the just run) 'last' process by switch_to().
-	 * This might sound slightly confusing but makes tons of sense.
-	 */
-	switch_to(prev, next, prev);
+	/* Here we just switch the register state and the stack. */
+	switch_to(prev, next);
 }
 
 unsigned long nr_running(void)
@@ -770,6 +761,7 @@ asmlinkage void schedule(void)
 
 	if (unlikely(in_interrupt()))
 		BUG();
+need_resched:
 	preempt_disable();
 	prev = current;
 	rq = this_rq();
@@ -778,15 +770,6 @@ asmlinkage void schedule(void)
 	prev->sleep_timestamp = jiffies;
 	spin_lock_irq(&rq->lock);
 
-#ifdef CONFIG_PREEMPT
-	/*
-	 * if entering from preempt_schedule, off a kernel preemption,
-	 * go straight to picking the next task.
-	 */
-	if (unlikely(preempt_get_count() & PREEMPT_ACTIVE))
-		goto pick_next_task;
-#endif
-
 	switch (prev->state) {
 	case TASK_INTERRUPTIBLE:
 		if (unlikely(signal_pending(prev))) {
@@ -798,7 +781,7 @@ asmlinkage void schedule(void)
 	case TASK_RUNNING:
 		;
 	}
-#if CONFIG_SMP || CONFIG_PREEMPT
+#if CONFIG_SMP
 pick_next_task:
 #endif
 	if (unlikely(!rq->nr_running)) {
@@ -847,6 +830,8 @@ asmlinkage void schedule(void)
 
 	reacquire_kernel_lock(current);
 	preempt_enable_no_resched();
+	if (test_thread_flag(TIF_NEED_RESCHED))
+		goto need_resched;
 	return;
 }
 
@@ -856,12 +841,10 @@ asmlinkage void schedule(void)
  */
 asmlinkage void preempt_schedule(void)
 {
-	do {
-		current_thread_info()->preempt_count += PREEMPT_ACTIVE;
-		schedule();
-		current_thread_info()->preempt_count -= PREEMPT_ACTIVE;
-		barrier();
-	} while (test_thread_flag(TIF_NEED_RESCHED));
+	if (unlikely(preempt_get_count()))
+		return;
+	current->state = TASK_RUNNING;
+	schedule();
 }
 #endif /* CONFIG_PREEMPT */