Subject: x86-preempt-lazy.patch
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 01 Nov 2012 11:03:47 +0100

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/Kconfig                   |    1 +
 arch/x86/include/asm/thread_info.h |    6 ++++++
 arch/x86/kernel/asm-offsets.c      |    1 +
 arch/x86/kernel/entry_32.S         |   18 +++++++++++++-----
 arch/x86/kernel/entry_64.S         |   24 +++++++++++++++---------
 5 files changed, 36 insertions(+), 14 deletions(-)

Index: linux-stable/arch/x86/Kconfig
===================================================================
--- linux-stable.orig/arch/x86/Kconfig
+++ linux-stable/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 HAVE_PREEMPT_LAZY
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS || UPROBES)
Index: linux-stable/arch/x86/include/asm/thread_info.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/thread_info.h
+++ linux-stable/arch/x86/include/asm/thread_info.h
@@ -31,6 +31,8 @@ struct thread_info {
 	__u32			cpu;		/* current CPU */
 	int			preempt_count;	/* 0 => preemptable,
 						   <0 => BUG */
+	int			preempt_lazy_count;	/* 0 => lazy preemptable,
+							   <0 => BUG */
 	mm_segment_t		addr_limit;
 	struct restart_block    restart_block;
 	void __user		*sysenter_return;
@@ -83,6 +85,7 @@ struct thread_info {
 #define TIF_SYSCALL_EMU		6	/* syscall emulation active */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
+#define TIF_NEED_RESCHED_LAZY	9	/* lazy rescheduling necessary */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
@@ -108,6 +111,7 @@ struct thread_info {
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
@@ -155,6 +159,8 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
 
+#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
+
 #define PREEMPT_ACTIVE		0x10000000
 
 #ifdef CONFIG_X86_32
Index: linux-stable/arch/x86/kernel/asm-offsets.c
===================================================================
--- linux-stable.orig/arch/x86/kernel/asm-offsets.c
+++ linux-stable/arch/x86/kernel/asm-offsets.c
@@ -33,6 +33,7 @@ void common(void) {
 	OFFSET(TI_status, thread_info, status);
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
 	OFFSET(TI_preempt_count, thread_info, preempt_count);
+	OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count);
 
 	BLANK();
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
Index: linux-stable/arch/x86/kernel/entry_32.S
===================================================================
--- linux-stable.orig/arch/x86/kernel/entry_32.S
+++ linux-stable/arch/x86/kernel/entry_32.S
@@ -349,14 +349,22 @@ ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	cmpl $0,TI_preempt_count(%ebp)	# non-zero preempt_count ?
 	jnz restore_all
-need_resched:
 	movl TI_flags(%ebp), %ecx	# need_resched set ?
 	testb $_TIF_NEED_RESCHED, %cl
+	jnz 1f
+
+	cmpl $0,TI_preempt_lazy_count(%ebp)	# non-zero preempt_lazy_count ?
+	jnz  restore_all
+	testl $_TIF_NEED_RESCHED_LAZY, %ecx
 	jz restore_all
-	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)	# interrupts off (exception path) ?
+
+1:	testl $X86_EFLAGS_IF,PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz restore_all
 	call preempt_schedule_irq
-	jmp need_resched
+	movl TI_flags(%ebp), %ecx	# need_resched set ?
+	testl $_TIF_NEED_RESCHED_MASK, %ecx
+	jnz 1b
+	jmp restore_all
 END(resume_kernel)
 #endif
 	CFI_ENDPROC
@@ -589,7 +597,7 @@ ENDPROC(system_call)
 	ALIGN
 	RING0_PTREGS_FRAME		# can't unwind into user space anyway
 work_pending:
-	testb $_TIF_NEED_RESCHED, %cl
+	testl $_TIF_NEED_RESCHED_MASK, %ecx
 	jz work_notifysig
 work_resched:
 	call schedule
@@ -602,7 +610,7 @@ work_resched:
 	andl $_TIF_WORK_MASK, %ecx	# is there any work to be done other
 					# than syscall tracing?
 	jz restore_all
-	testb $_TIF_NEED_RESCHED, %cl
+	testl $_TIF_NEED_RESCHED_MASK, %ecx
 	jnz work_resched
 
 work_notifysig:				# deal with pending signals and
Index: linux-stable/arch/x86/kernel/entry_64.S
===================================================================
--- linux-stable.orig/arch/x86/kernel/entry_64.S
+++ linux-stable/arch/x86/kernel/entry_64.S
@@ -560,8 +560,8 @@ sysret_check:
 	/* Handle reschedules */
 	/* edx:	work, edi: workmask */
 sysret_careful:
-	bt $TIF_NEED_RESCHED,%edx
-	jnc sysret_signal
+	testl $_TIF_NEED_RESCHED_MASK,%edx
+	jz sysret_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
@@ -673,8 +673,8 @@ GLOBAL(int_with_check)
 	/* First do a reschedule test. */
 	/* edx:	work, edi: workmask */
 int_careful:
-	bt $TIF_NEED_RESCHED,%edx
-	jnc  int_very_careful
+	testl $_TIF_NEED_RESCHED_MASK,%edx
+	jz  int_very_careful
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
@@ -969,8 +969,8 @@ bad_iret:
 	/* edi: workmask, edx: work */
 retint_careful:
 	CFI_RESTORE_STATE
-	bt    $TIF_NEED_RESCHED,%edx
-	jnc   retint_signal
+	testl $_TIF_NEED_RESCHED_MASK,%edx
+	jz   retint_signal
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushq_cfi %rdi
@@ -1003,9 +1003,15 @@ retint_signal:
 ENTRY(retint_kernel)
 	cmpl $0,TI_preempt_count(%rcx)
 	jnz  retint_restore_args
-	bt  $TIF_NEED_RESCHED,TI_flags(%rcx)
+	bt   $TIF_NEED_RESCHED,TI_flags(%rcx)
+	jc   1f
+
+	cmpl $0,TI_preempt_lazy_count(%rcx)
+	jnz  retint_restore_args
+	bt   $TIF_NEED_RESCHED_LAZY,TI_flags(%rcx)
 	jnc  retint_restore_args
-	bt   $9,EFLAGS-ARGOFFSET(%rsp)	/* interrupts off? */
+
+1:	bt   $9,EFLAGS-ARGOFFSET(%rsp)	/* interrupts off? */
 	jnc  retint_restore_args
 	call preempt_schedule_irq
 	jmp exit_intr
@@ -1437,7 +1443,7 @@ paranoid_userspace:
 	movq %rsp,%rdi			/* &pt_regs */
 	call sync_regs
 	movq %rax,%rsp			/* switch stack for scheduling */
-	testl $_TIF_NEED_RESCHED,%ebx
+	testl $_TIF_NEED_RESCHED_MASK,%ebx
 	jnz paranoid_schedule
 	movl %ebx,%edx			/* arg3: thread flags */
 	TRACE_IRQS_ON