summaryrefslogtreecommitdiff
path: root/arch/x86/kernel/i387.c
diff options
context:
space:
mode:
authorSuresh Siddha <suresh.b.siddha@intel.com>2012-08-24 14:13:02 -0700
committerH. Peter Anvin <hpa@linux.intel.com>2012-09-18 15:52:11 -0700
commit304bceda6a18ae0b0240b8aac9a6bdf8ce2d2469 (patch)
tree9ffae43391d69aa4765590b942b907da4a189041 /arch/x86/kernel/i387.c
parent9c6ff8bbb69a4e7b47ac40bfa44509296e89c5c0 (diff)
x86, fpu: use non-lazy fpu restore for processors supporting xsave
Fundamental model of the current Linux kernel is to lazily init and restore FPU instead of restoring the task state during context switch. This changes that fundamental lazy model to the non-lazy model for the processors supporting xsave feature. Reasons driving this model change are: i. Newer processors support optimized state save/restore using xsaveopt and xrstor by tracking the INIT state and MODIFIED state during context-switch. This is faster than modifying the cr0.TS bit which has serializing semantics. ii. Newer glibc versions use SSE for some of the optimized copy/clear routines. With certain workloads (like boot, kernel-compilation etc), application completes its work with in the first 5 task switches, thus taking upto 5 #DNA traps with the kernel not getting a chance to apply the above mentioned pre-load heuristic. iii. Some xstate features (like AMD's LWP feature) don't honor the cr0.TS bit and thus will not work correctly in the presence of lazy restore. Non-lazy state restore is needed for enabling such features. Some data on a two socket SNB system: * Saved 20K DNA exceptions during boot on a two socket SNB system. * Saved 50K DNA exceptions during kernel-compilation workload. * Improved throughput of the AVX based checksumming function inside the kernel by ~15% as xsave/xrstor is faster than the serializing clts/stts pair. Also now kernel_fpu_begin/end() relies on the patched alternative instructions. So move check_fpu() which uses the kernel_fpu_begin/end() after alternative_instructions(). Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Link: http://lkml.kernel.org/r/1345842782-24175-7-git-send-email-suresh.b.siddha@intel.com Merge 32-bit boot fix from, Link: http://lkml.kernel.org/r/1347300665-6209-4-git-send-email-suresh.b.siddha@intel.com Cc: Jim Kukunas <james.t.kukunas@linux.intel.com> Cc: NeilBrown <neilb@suse.de> Cc: Avi Kivity <avi@redhat.com> Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'arch/x86/kernel/i387.c')
-rw-r--r--arch/x86/kernel/i387.c20
1 files changed, 17 insertions, 3 deletions
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index ab6a2e8028ae..528557470ddb 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -22,7 +22,15 @@
/*
* Were we in an interrupt that interrupted kernel mode?
*
- * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * For now, on xsave platforms we will return interrupted
+ * kernel FPU as not-idle. TBD: As we use non-lazy FPU restore
+ * for xsave platforms, ideally we can change the return value
+ * to something like __thread_has_fpu(current). But we need to
+ * be careful of doing __thread_clear_has_fpu() before saving
+ * the FPU etc for supporting nested uses etc. For now, take
+ * the simple route!
+ *
+ * On others, we can do a kernel_fpu_begin/end() pair *ONLY* if that
* pair does nothing at all: the thread must not have fpu (so
* that we don't try to save the FPU state), and TS must
* be set (so that the clts/stts pair does nothing that is
@@ -30,6 +38,9 @@
*/
static inline bool interrupted_kernel_fpu_idle(void)
{
+ if (use_xsave())
+ return 0;
+
return !__thread_has_fpu(current) &&
(read_cr0() & X86_CR0_TS);
}
@@ -73,7 +84,7 @@ void kernel_fpu_begin(void)
__save_init_fpu(me);
__thread_clear_has_fpu(me);
/* We do 'stts()' in kernel_fpu_end() */
- } else {
+ } else if (!use_xsave()) {
this_cpu_write(fpu_owner_task, NULL);
clts();
}
@@ -82,7 +93,10 @@ EXPORT_SYMBOL(kernel_fpu_begin);
void kernel_fpu_end(void)
{
- stts();
+ if (use_xsave())
+ math_state_restore();
+ else
+ stts();
preempt_enable();
}
EXPORT_SYMBOL(kernel_fpu_end);