[PATCH V2 10/15] x86/fsgsbase/64: Preserve FS/GS state in __switch_to if FSGSBASE is on

["Chang S. Bae" <chang.seok.bae@intel.com>]

From: Andy Lutomirski <luto@kernel.org>

With the new FSGSBASE instructions, we can efficiently read and write
the FS and GS bases 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 my
Skylake laptop.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
[chang: 5~10% performance improvement on context switch micro-
benchmark, when FS/GS base is actively switched.]
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/process_64.c | 34 ++++++++++++++++++++++++++++------
 1 file changed, 28 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 8ba947f..55af719 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -234,8 +234,18 @@ 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 = rd_inactive_gsbase();
+	} else {
+		save_base_legacy(task, task->thread.fsindex, FS);
+		save_base_legacy(task, task->thread.gsindex, GS);
+	}
 }
 
 #if IS_ENABLED(CONFIG_KVM)
@@ -314,10 +324,22 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
 static __always_inline void load_fsgs(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);
+		wr_inactive_gsbase(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 task_seg_base(struct task_struct *task,
-- 
2.7.4