Commit 1ab5f3f7 authored by Andy Lutomirski's avatar Andy Lutomirski Committed by Thomas Gleixner

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.

[ 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: default avatarAndy Lutomirski <luto@kernel.org>
Signed-off-by: default avatarChang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Reviewed-by: default avatarAndi Kleen <ak@linux.intel.com>
Cc: Ravi Shankar <ravi.v.shankar@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Link: https://lkml.kernel.org/r/1557309753-24073-8-git-send-email-chang.seok.bae@intel.com
parent a86b4625
...@@ -244,8 +244,18 @@ static __always_inline void save_fsgs(struct task_struct *task) ...@@ -244,8 +244,18 @@ static __always_inline void save_fsgs(struct task_struct *task)
{ {
savesegment(fs, task->thread.fsindex); savesegment(fs, task->thread.fsindex);
savesegment(gs, task->thread.gsindex); savesegment(gs, task->thread.gsindex);
save_base_legacy(task, task->thread.fsindex, FS); if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
save_base_legacy(task, task->thread.gsindex, GS); /*
* 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);
}
} }
#if IS_ENABLED(CONFIG_KVM) #if IS_ENABLED(CONFIG_KVM)
...@@ -324,10 +334,22 @@ static __always_inline void load_seg_legacy(unsigned short prev_index, ...@@ -324,10 +334,22 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
static __always_inline void x86_fsgsbase_load(struct thread_struct *prev, static __always_inline void x86_fsgsbase_load(struct thread_struct *prev,
struct thread_struct *next) struct thread_struct *next)
{ {
load_seg_legacy(prev->fsindex, prev->fsbase, if (static_cpu_has(X86_FEATURE_FSGSBASE)) {
next->fsindex, next->fsbase, FS); /* Update the FS and GS selectors if they could have changed. */
load_seg_legacy(prev->gsindex, prev->gsbase, if (unlikely(prev->fsindex || next->fsindex))
next->gsindex, next->gsbase, GS); 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, static unsigned long x86_fsgsbase_read_task(struct task_struct *task,
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment