x86/process/64: Use FSBSBASE in switch_to() if available

With the new FSGSBASE instructions, FS and GSABSE can be efficiently read
and writen in __switch_to().  Use that capability to preserve the full
state.

This will enable user code to do whatever it wants with the new
instructions without any kernel-induced gotchas.  (There can still be
architectural gotchas: movl %gs,%eax; movl %eax,%gs may change GSBASE if
WRGSBASE was used, but users are expected to read the CPU manual before
doing things like that.)

This is a considerable speedup.  It seems to save about 100 cycles
per context switch compared to the baseline 4.6-rc1 behavior on a
Skylake laptop. This is mostly due to avoiding the WRMSR operation.

[ chang: 5~10% performance improvements were seen with a context switch
  benchmark that ran threads with different FS/GSBASE values (to the
  baseline 4.16). Minor edit on the changelog. ]

[ tglx: Masaage changelog ]

Signed-off-by: Andy Lutomirski <[email protected]>
Signed-off-by: Chang S. Bae <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]

Author: amluto

arch/x86/kernel/process_64.c

@@ -236,8 +236,18 @@ static __always_inline void save_fsgs(struct task_struct *task)
 {
 	savesegment(fs, task->thread.fsindex);
 	savesegment(gs, task->thread.gsindex);
-	save_base_legacy(task, task->thread.fsindex, FS);
-	save_base_legacy(task, task->thread.gsindex, GS);
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		/*
+		 * If FSGSBASE is enabled, we can't make any useful guesses
+		 * about the base, and user code expects us to save the current
+		 * value.  Fortunately, reading the base directly is efficient.
+		 */
+		task->thread.fsbase = rdfsbase();
+		task->thread.gsbase = __rdgsbase_inactive();
+	} else {
+		save_base_legacy(task, task->thread.fsindex, FS);
+		save_base_legacy(task, task->thread.gsindex, GS);
+	}
 }
 
 /*
@@ -319,10 +329,22 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
 static __always_inline void x86_fsgsbase_load(struct thread_struct *prev,
 					      struct thread_struct *next)
 {
-	load_seg_legacy(prev->fsindex, prev->fsbase,
-			next->fsindex, next->fsbase, FS);
-	load_seg_legacy(prev->gsindex, prev->gsbase,
-			next->gsindex, next->gsbase, GS);
+	if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
+		/* Update the FS and GS selectors if they could have changed. */
+		if (unlikely(prev->fsindex || next->fsindex))
+			loadseg(FS, next->fsindex);
+		if (unlikely(prev->gsindex || next->gsindex))
+			loadseg(GS, next->gsindex);
+
+		/* Update the bases. */
+		wrfsbase(next->fsbase);
+		__wrgsbase_inactive(next->gsbase);
+	} else {
+		load_seg_legacy(prev->fsindex, prev->fsbase,
+				next->fsindex, next->fsbase, FS);
+		load_seg_legacy(prev->gsindex, prev->gsbase,
+				next->gsindex, next->gsbase, GS);
+	}
 }
 
 static unsigned long x86_fsgsbase_read_task(struct task_struct *task,