[PATCH 4.9 55/92] x86/asm: Move status from thread_struct to thread_info

[Greg Kroah-Hartman]

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <luto@xxxxxxxxxx>


(cherry picked from commit 37a8f7c38339b22b69876d6f5a0ab851565284e3)

The TS_COMPAT bit is very hot and is accessed from code paths that mostly
also touch thread_info::flags.  Move it into struct thread_info to improve
cache locality.

The only reason it was in thread_struct is that there was a brief period
during which arch-specific fields were not allowed in struct thread_info.

Linus suggested further changing:

  ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);

to:

  if (unlikely(ti->status & (TS_COMPAT|TS_I386_REGS_POKED)))
          ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);

on the theory that frequently dirtying the cacheline even in pure 64-bit
code that never needs to modify status hurts performance.  That could be a
reasonable followup patch, but I suspect it matters less on top of this
patch.

Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reviewed-by: Ingo Molnar <mingo@xxxxxxxxxx>
Acked-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Kernel Hardening <kernel-hardening@xxxxxxxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/03148bcc1b217100e6e8ecf6a5468c45cf4304b6.1517164461.git.luto@xxxxxxxxxx
Signed-off-by: David Woodhouse <dwmw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 arch/x86/entry/common.c            |    4 ++--
 arch/x86/include/asm/processor.h   |    2 --
 arch/x86/include/asm/syscall.h     |    6 +++---
 arch/x86/include/asm/thread_info.h |    3 ++-
 arch/x86/kernel/process_64.c       |    4 ++--
 arch/x86/kernel/ptrace.c           |    2 +-
 arch/x86/kernel/signal.c           |    2 +-
 7 files changed, 11 insertions(+), 12 deletions(-)

--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -201,7 +201,7 @@ __visible inline void prepare_exit_to_us
 	 * special case only applies after poking regs and before the
 	 * very next return to user mode.
 	 */
-	current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
+	ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
 #endif
 
 	user_enter_irqoff();
@@ -299,7 +299,7 @@ static __always_inline void do_syscall_3
 	unsigned int nr = (unsigned int)regs->orig_ax;
 
 #ifdef CONFIG_IA32_EMULATION
-	current->thread.status |= TS_COMPAT;
+	ti->status |= TS_COMPAT;
 #endif
 
 	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -391,8 +391,6 @@ struct thread_struct {
 	unsigned short		gsindex;
 #endif
 
-	u32			status;		/* thread synchronous flags */
-
 #ifdef CONFIG_X86_64
 	unsigned long		fsbase;
 	unsigned long		gsbase;
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -60,7 +60,7 @@ static inline long syscall_get_error(str
 	 * TS_COMPAT is set for 32-bit syscall entries and then
 	 * remains set until we return to user mode.
 	 */
-	if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED))
 		/*
 		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
 		 * and will match correctly in comparisons.
@@ -116,7 +116,7 @@ static inline void syscall_get_arguments
 					 unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread.status & TS_COMPAT)
+	if (task->thread_info.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
@@ -177,7 +177,7 @@ static inline void syscall_set_arguments
 					 const unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread.status & TS_COMPAT)
+	if (task->thread_info.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -54,6 +54,7 @@ struct task_struct;
 
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
+	u32			status;		/* thread synchronous flags */
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -213,7 +214,7 @@ static inline int arch_within_stack_fram
 #define in_ia32_syscall() true
 #else
 #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \
-			   current->thread.status & TS_COMPAT)
+			   current_thread_info()->status & TS_COMPAT)
 #endif
 
 /*
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -538,7 +538,7 @@ void set_personality_ia32(bool x32)
 		current->personality &= ~READ_IMPLIES_EXEC;
 		/* in_compat_syscall() uses the presence of the x32
 		   syscall bit flag to determine compat status */
-		current->thread.status &= ~TS_COMPAT;
+		current_thread_info()->status &= ~TS_COMPAT;
 	} else {
 		set_thread_flag(TIF_IA32);
 		clear_thread_flag(TIF_X32);
@@ -546,7 +546,7 @@ void set_personality_ia32(bool x32)
 			current->mm->context.ia32_compat = TIF_IA32;
 		current->personality |= force_personality32;
 		/* Prepare the first "return" to user space */
-		current->thread.status |= TS_COMPAT;
+		current_thread_info()->status |= TS_COMPAT;
 	}
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -934,7 +934,7 @@ static int putreg32(struct task_struct *
 		 */
 		regs->orig_ax = value;
 		if (syscall_get_nr(child, regs) >= 0)
-			child->thread.status |= TS_I386_REGS_POKED;
+			child->thread_info.status |= TS_I386_REGS_POKED;
 		break;
 
 	case offsetof(struct user32, regs.eflags):
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -785,7 +785,7 @@ static inline unsigned long get_nr_resta
 	 * than the tracee.
 	 */
 #ifdef CONFIG_IA32_EMULATION
-	if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
 		return __NR_ia32_restart_syscall;
 #endif
 #ifdef CONFIG_X86_X32_ABI