Merge branch 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fpu updates from Ingo Molnar:
 "The main x86 FPU changes in this cycle were:

   - a large series of cleanups, fixes and enhancements to re-enable the
     XSAVES instruction on Intel CPUs - which is the most advanced
     instruction to do FPU context switches (Yu-cheng Yu, Fenghua Yu)

   - Add FPU tracepoints for the FPU state machine (Dave Hansen)"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Do not BUG_ON() in early FPU code
  x86/fpu/xstate: Re-enable XSAVES
  x86/fpu/xstate: Fix fpstate_init() for XRSTORS
  x86/fpu/xstate: Return NULL for disabled xstate component address
  x86/fpu/xstate: Fix __fpu_restore_sig() for XSAVES
  x86/fpu/xstate: Fix xstate_offsets, xstate_sizes for non-extended xstates
  x86/fpu/xstate: Fix XSTATE component offset print out
  x86/fpu/xstate: Fix PTRACE frames for XSAVES
  x86/fpu/xstate: Fix supervisor xstate component offset
  x86/fpu/xstate: Align xstate components according to CPUID
  x86/fpu/xstate: Copy xstate registers directly to the signal frame when compacted format is in use
  x86/fpu/xstate: Keep init_fpstate.xsave.header.xfeatures as zero for init optimization
  x86/fpu/xstate: Rename 'xstate_size' to 'fpu_kernel_xstate_size', to distinguish it from 'fpu_user_xstate_size'
  x86/fpu/xstate: Define and use 'fpu_user_xstate_size'
  x86/fpu: Add tracepoints to dump FPU state at key points

5 files changed, 141 insertions, 3 deletions

diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 31ac8e6d9f36..116b58347501 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -18,6 +18,7 @@
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
 #include <asm/cpufeature.h>
+#include <asm/trace/fpu.h>
 
 /*
  * High level FPU state handling functions:
@@ -524,6 +525,7 @@ static inline void __fpregs_deactivate(struct fpu *fpu)
 
 	fpu->fpregs_active = 0;
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+	trace_x86_fpu_regs_deactivated(fpu);
 }
 
 /* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
@@ -533,6 +535,7 @@ static inline void __fpregs_activate(struct fpu *fpu)
 
 	fpu->fpregs_active = 1;
 	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+	trace_x86_fpu_regs_activated(fpu);
 }
 
 /*
@@ -604,11 +607,13 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 
 		/* But leave fpu_fpregs_owner_ctx! */
 		old_fpu->fpregs_active = 0;
+		trace_x86_fpu_regs_deactivated(old_fpu);
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
 			new_fpu->counter++;
 			__fpregs_activate(new_fpu);
+			trace_x86_fpu_regs_activated(new_fpu);
 			prefetch(&new_fpu->state);
 		} else {
 			__fpregs_deactivate_hw();
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 36b90bbfc69f..48df486b02f9 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -122,6 +122,7 @@ enum xfeature {
 #define XFEATURE_MASK_OPMASK		(1 << XFEATURE_OPMASK)
 #define XFEATURE_MASK_ZMM_Hi256		(1 << XFEATURE_ZMM_Hi256)
 #define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
+#define XFEATURE_MASK_PT		(1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
 #define XFEATURE_MASK_PKRU		(1 << XFEATURE_PKRU)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
@@ -231,6 +232,12 @@ struct xstate_header {
 } __attribute__((packed));
 
 /*
+ * xstate_header.xcomp_bv[63] indicates that the extended_state_area
+ * is in compacted format.
+ */
+#define XCOMP_BV_COMPACTED_FORMAT ((u64)1 << 63)
+
+/*
  * This is our most modern FPU state format, as saved by the XSAVE
  * and restored by the XRSTOR instructions.
  *
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 38951b0fcc5a..ae55a43e09c0 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -18,6 +18,9 @@
 #define XSAVE_YMM_SIZE	    256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
+/* Supervisor features */
+#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
+
 /* Supported features which support lazy state saving */
 #define XFEATURE_MASK_LAZY	(XFEATURE_MASK_FP | \
 				 XFEATURE_MASK_SSE | \
@@ -39,7 +42,6 @@
 #define REX_PREFIX
 #endif
 
-extern unsigned int xstate_size;
 extern u64 xfeatures_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
@@ -48,5 +50,9 @@ extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
-
+int using_compacted_format(void);
+int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+			void __user *ubuf, struct xregs_state *xsave);
+int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+		     struct xregs_state *xsave);
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 89314ed74fee..63def9537a2d 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -367,7 +367,8 @@ DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
 DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
-extern unsigned int xstate_size;
+extern unsigned int fpu_kernel_xstate_size;
+extern unsigned int fpu_user_xstate_size;
 
 struct perf_event;
 
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
new file mode 100644
index 000000000000..9217ab1f5bf6
--- /dev/null
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -0,0 +1,119 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM x86_fpu
+
+#if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FPU_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(x86_fpu,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu),
+
+	TP_STRUCT__entry(
+		__field(struct fpu *, fpu)
+		__field(bool, fpregs_active)
+		__field(bool, fpstate_active)
+		__field(int, counter)
+		__field(u64, xfeatures)
+		__field(u64, xcomp_bv)
+		),
+
+	TP_fast_assign(
+		__entry->fpu		= fpu;
+		__entry->fpregs_active	= fpu->fpregs_active;
+		__entry->fpstate_active	= fpu->fpstate_active;
+		__entry->counter	= fpu->counter;
+		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
+			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
+		}
+	),
+	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d counter: %d xfeatures: %llx xcomp_bv: %llx",
+			__entry->fpu,
+			__entry->fpregs_active,
+			__entry->fpstate_active,
+			__entry->counter,
+			__entry->xfeatures,
+			__entry->xcomp_bv
+	)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_before_save,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_after_save,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_before_restore,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_after_restore,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_activate_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_dropped,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_copy_src,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE fpu
+#endif /* _TRACE_FPU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>