x86/fpu: Generalize 'init_xstate_ctx'

So the handling of init_xstate_ctx has a layering violation: both
'struct xsave_struct' and 'union thread_xstate' have a
'struct i387_fxsave_struct' member:

   xsave_struct::i387
   thread_xstate::fxsave

The handling of init_xstate_ctx is generic, it is used on all
CPUs, with or without XSAVE instruction. So it's confusing how
the generic code passes around and handles an XSAVE specific
format.

What we really want is for init_xstate_ctx to be a proper
fpstate and we use its ::fxsave and ::xsave members, as
appropriate.

Since the xsave_struct::i387 and thread_xstate::fxsave aliases
each other this is not a functional problem.

So implement this, and move init_xstate_ctx to the generic FPU
code in the process.

Also, since init_xstate_ctx is not XSAVE specific anymore,
rename it to init_fpstate, and mark it __read_mostly,
because it's only modified once during bootup, and used
as a reference fpstate later on.

There's no change in functionality.

Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@kernel.org>

arch/x86/include/asm/fpu/internal.h

@@ -22,6 +22,8 @@
 
 extern unsigned int mxcsr_feature_mask;
 
+extern union thread_xstate init_fpstate;
+
 extern void fpu__init_cpu(void);
 extern void fpu__init_system_xstate(void);
 extern void fpu__init_cpu_xstate(void);
@@ -342,9 +344,9 @@ static inline void fpregs_deactivate(struct fpu *fpu)
 static inline void restore_init_xstate(void)
 {
 	if (use_xsave())
-		xrstor_state(&init_xstate_ctx, -1);
+		xrstor_state(&init_fpstate.xsave, -1);
 	else
-		fxrstor_checking(&init_xstate_ctx.i387);
+		fxrstor_checking(&init_fpstate.fxsave);
 }
 
 /*

arch/x86/include/asm/fpu/xstate.h

@@ -37,7 +37,6 @@
 extern unsigned int xstate_size;
 extern u64 xfeatures_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
-extern struct xsave_struct init_xstate_ctx;
 
 extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 

arch/x86/kernel/fpu/core.c

@@ -12,6 +12,12 @@
 
 #include <linux/hardirq.h>
 
+/*
+ * Represents the initial FPU state. It's mostly (but not completely) zeroes,
+ * depending on the FPU hardware format:
+ */
+union thread_xstate init_fpstate __read_mostly;
+
 /*
  * Track whether the kernel is using the FPU state
  * currently.

arch/x86/kernel/fpu/init.c

@@ -121,7 +121,7 @@ static void fpu__init_system_generic(void)
 	 * Set up the legacy init FPU context. (xstate init might overwrite this
 	 * with a more modern format, if the CPU supports it.)
 	 */
-	fpstate_init_fxstate(&init_xstate_ctx.i387);
+	fpstate_init_fxstate(&init_fpstate.fxsave);
 
 	fpu__init_system_mxcsr();
 }

arch/x86/kernel/fpu/xstate.c

@@ -31,11 +31,6 @@ static const char *xfeature_names[] =
  */
 u64 xfeatures_mask __read_mostly;
 
-/*
- * Represents init state for the supported extended state.
- */
-struct xsave_struct init_xstate_ctx;
-
 static struct _fpx_sw_bytes fx_sw_reserved, fx_sw_reserved_ia32;
 static unsigned int xstate_offsets[XFEATURES_NR_MAX], xstate_sizes[XFEATURES_NR_MAX];
 static unsigned int xstate_comp_offsets[sizeof(xfeatures_mask)*8];
@@ -150,7 +145,7 @@ void fpstate_sanitize_xstate(struct fpu *fpu)
 			int size = xstate_sizes[feature_bit];
 
 			memcpy((void *)fx + offset,
-			       (void *)&init_xstate_ctx + offset,
+			       (void *)&init_fpstate.xsave + offset,
 			       size);
 		}
 
@@ -377,12 +372,12 @@ static inline int restore_user_xstate(void __user *buf, u64 xbv, int fx_only)
 	if (use_xsave()) {
 		if ((unsigned long)buf % 64 || fx_only) {
 			u64 init_bv = xfeatures_mask & ~XSTATE_FPSSE;
-			xrstor_state(&init_xstate_ctx, init_bv);
+			xrstor_state(&init_fpstate.xsave, init_bv);
 			return fxrstor_user(buf);
 		} else {
 			u64 init_bv = xfeatures_mask & ~xbv;
 			if (unlikely(init_bv))
-				xrstor_state(&init_xstate_ctx, init_bv);
+				xrstor_state(&init_fpstate.xsave, init_bv);
 			return xrestore_user(buf, xbv);
 		}
 	} else if (use_fxsr()) {
@@ -665,20 +660,20 @@ static void setup_init_fpu_buf(void)
 	print_xstate_features();
 
 	if (cpu_has_xsaves) {
-		init_xstate_ctx.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
-		init_xstate_ctx.header.xfeatures = xfeatures_mask;
+		init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask;
+		init_fpstate.xsave.header.xfeatures = xfeatures_mask;
 	}
 
 	/*
 	 * Init all the features state with header_bv being 0x0
 	 */
-	xrstor_state_booting(&init_xstate_ctx, -1);
+	xrstor_state_booting(&init_fpstate.xsave, -1);
 
 	/*
 	 * Dump the init state again. This is to identify the init state
 	 * of any feature which is not represented by all zero's.
 	 */
-	xsave_state_booting(&init_xstate_ctx);
+	xsave_state_booting(&init_fpstate.xsave);
 }
 
 /*