From: Andy Lutomirski <l...@kernel.org>
With the new FSGSBASE instructions, FS/GS base can be efficiently read
and written 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 GS base
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.
[ chang: 5~10% performance improvements were seen by a context switch
benchmark that ran threads with different FS/GS base values (to the
baseline 4.16). ]
Signed-off-by: Andy Lutomirski <l...@kernel.org>
Signed-off-by: Chang S. Bae <chang.seok....@intel.com>
Signed-off-by: Sasha Levin <sas...@kernel.org>
Reviewed-by: Tony Luck <tony.l...@intel.com>
Cc: Thomas Gleixner <t...@linutronix.de>
Cc: Borislav Petkov <b...@alien8.de>
Cc: Andy Lutomirski <l...@kernel.org>
Cc: H. Peter Anvin <h...@zytor.com>
Cc: Dave Hansen <dave.han...@intel.com>
Cc: Tony Luck <tony.l...@intel.com>
Cc: Andi Kleen <a...@linux.intel.com>
---
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 aaa65f284b9b9..e066750be89a0 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -199,8 +199,18 @@ 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 = x86_gsbase_read_cpu_inactive();
+ } else {
+ save_base_legacy(task, task->thread.fsindex, FS);
+ save_base_legacy(task, task->thread.gsindex, GS);
+ }
}
#if IS_ENABLED(CONFIG_KVM)
@@ -279,10 +289,22 @@ 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);
+ x86_gsbase_write_cpu_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,
--
2.20.1
