x86/entry/64: Pass SP0 directly to load_sp0()

load_sp0() had an odd signature:

  void load_sp0(struct tss_struct *tss, struct thread_struct *thread);

Simplify it to:

  void load_sp0(unsigned long sp0);

Also simplify a few get_cpu()/put_cpu() sequences to
preempt_disable()/preempt_enable().

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/2655d8b42ed940aa384fe18ee1129bbbcf730a08.1509609304.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/paravirt.h

@@ -15,10 +15,9 @@
 #include <linux/cpumask.h>
 #include <asm/frame.h>
 
-static inline void load_sp0(struct tss_struct *tss,
-			     struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
+	PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0);
 }
 
 /* The paravirtualized CPUID instruction. */

arch/x86/include/asm/paravirt_types.h

@@ -133,7 +133,7 @@ struct pv_cpu_ops {
 	void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
 	void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
 
-	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
+	void (*load_sp0)(unsigned long sp0);
 
 	void (*set_iopl_mask)(unsigned mask);
 

arch/x86/include/asm/processor.h

@@ -517,9 +517,9 @@ static inline void native_set_iopl_mask(unsigned mask)
 }
 
 static inline void
-native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
+native_load_sp0(unsigned long sp0)
 {
-	tss->x86_tss.sp0 = thread->sp0;
+	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
 }
 
 static inline void native_swapgs(void)
@@ -544,10 +544,9 @@ static inline unsigned long current_top_of_stack(void)
 #else
 #define __cpuid			native_cpuid
 
-static inline void load_sp0(struct tss_struct *tss,
-			    struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	native_load_sp0(tss, thread);
+	native_load_sp0(sp0);
 }
 
 #define set_iopl_mask native_set_iopl_mask

arch/x86/kernel/cpu/common.c

@@ -1570,7 +1570,7 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, me);
 
-	load_sp0(t, &current->thread);
+	load_sp0(current->thread.sp0);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
 	load_mm_ldt(&init_mm);
@@ -1625,7 +1625,7 @@ void cpu_init(void)
 	initialize_tlbstate_and_flush();
 	enter_lazy_tlb(&init_mm, curr);
 
-	load_sp0(t, thread);
+	load_sp0(thread->sp0);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
 	load_mm_ldt(&init_mm);

arch/x86/kernel/process_32.c

@@ -287,7 +287,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
-	load_sp0(tss, next);
+	load_sp0(next->sp0);
 	refresh_sysenter_cs(next);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +

arch/x86/kernel/process_64.c

@@ -465,7 +465,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(current_task, next_p);
 
 	/* Reload sp0. */
-	load_sp0(tss, next);
+	load_sp0(next->sp0);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps

arch/x86/kernel/vm86_32.c

@@ -94,7 +94,6 @@
 
 void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 {
-	struct tss_struct *tss;
 	struct task_struct *tsk = current;
 	struct vm86plus_struct __user *user;
 	struct vm86 *vm86 = current->thread.vm86;
@@ -146,13 +145,13 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 		do_exit(SIGSEGV);
 	}
 
-	tss = &per_cpu(cpu_tss, get_cpu());
+	preempt_disable();
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
-	load_sp0(tss, &tsk->thread);
+	load_sp0(tsk->thread.sp0);
 	refresh_sysenter_cs(&tsk->thread);
 	vm86->saved_sp0 = 0;
-	put_cpu();
+	preempt_enable();
 
 	memcpy(&regs->pt, &vm86->regs32, sizeof(struct pt_regs));
 
@@ -238,7 +237,6 @@ SYSCALL_DEFINE2(vm86, unsigned long, cmd, unsigned long, arg)
 
 static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 {
-	struct tss_struct *tss;
 	struct task_struct *tsk = current;
 	struct vm86 *vm86 = tsk->thread.vm86;
 	struct kernel_vm86_regs vm86regs;
@@ -366,8 +364,8 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	vm86->saved_sp0 = tsk->thread.sp0;
 	lazy_save_gs(vm86->regs32.gs);
 
-	tss = &per_cpu(cpu_tss, get_cpu());
 	/* make room for real-mode segments */
+	preempt_disable();
 	tsk->thread.sp0 += 16;
 
 	if (static_cpu_has(X86_FEATURE_SEP)) {
@@ -375,8 +373,8 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 		refresh_sysenter_cs(&tsk->thread);
 	}
 
-	load_sp0(tss, &tsk->thread);
-	put_cpu();
+	load_sp0(tsk->thread.sp0);
+	preempt_enable();
 
 	if (vm86->flags & VM86_SCREEN_BITMAP)
 		mark_screen_rdonly(tsk->mm);

arch/x86/xen/enlighten_pv.c

@@ -810,15 +810,14 @@ static void __init xen_write_gdt_entry_boot(struct desc_struct *dt, int entry,
 	}
 }
 
-static void xen_load_sp0(struct tss_struct *tss,
-			 struct thread_struct *thread)
+static void xen_load_sp0(unsigned long sp0)
 {
 	struct multicall_space mcs;
 
 	mcs = xen_mc_entry(0);
-	MULTI_stack_switch(mcs.mc, __KERNEL_DS, thread->sp0);
+	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
 	xen_mc_issue(PARAVIRT_LAZY_CPU);
-	tss->x86_tss.sp0 = thread->sp0;
+	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
 }
 
 void xen_set_iopl_mask(unsigned mask)