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:
 "Misc preparatory changes for an upcoming FPU optimization that will
  delay the loading of FPU registers to return-to-userspace"

* 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Don't export __kernel_fpu_{begin,end}()
  x86/fpu: Update comment for __raw_xsave_addr()
  x86/fpu: Add might_fault() to user_insn()
  x86/pkeys: Make init_pkru_value static
  x86/thread_info: Remove _TIF_ALLWORK_MASK
  x86/process/32: Remove asm/math_emu.h include
  x86/fpu: Use unsigned long long shift in xfeature_uncompacted_offset()

arch/x86/include/asm/efi.h

@@ -82,8 +82,7 @@ struct efi_scratch {
 #define arch_efi_call_virt_setup()					\
 ({									\
 	efi_sync_low_kernel_mappings();					\
-	preempt_disable();						\
-	__kernel_fpu_begin();						\
+	kernel_fpu_begin();						\
 	firmware_restrict_branch_speculation_start();			\
 									\
 	if (!efi_enabled(EFI_OLD_MEMMAP))				\
@@ -99,8 +98,7 @@ struct efi_scratch {
 		efi_switch_mm(efi_scratch.prev_mm);			\
 									\
 	firmware_restrict_branch_speculation_end();			\
-	__kernel_fpu_end();						\
-	preempt_enable();						\
+	kernel_fpu_end();						\
 })
 
 extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,

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

@@ -12,17 +12,12 @@
 #define _ASM_X86_FPU_API_H
 
 /*
- * Careful: __kernel_fpu_begin/end() must be called with preempt disabled
- * and they don't touch the preempt state on their own.
- * If you enable preemption after __kernel_fpu_begin(), preempt notifier
- * should call the __kernel_fpu_end() to prevent the kernel/user FPU
- * state from getting corrupted. KVM for example uses this model.
- *
- * All other cases use kernel_fpu_begin/end() which disable preemption
- * during kernel FPU usage.
+ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It
+ * disables preemption so be careful if you intend to use it for long periods
+ * of time.
+ * If you intend to use the FPU in softirq you need to check first with
+ * irq_fpu_usable() if it is possible.
  */
-extern void __kernel_fpu_begin(void);
-extern void __kernel_fpu_end(void);
 extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
 extern bool irq_fpu_usable(void);

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

@@ -106,6 +106,9 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu);
 #define user_insn(insn, output, input...)				\
 ({									\
 	int err;							\
+									\
+	might_fault();							\
+									\
 	asm volatile(ASM_STAC "\n"					\
 		     "1:" #insn "\n\t"					\
 		     "2: " ASM_CLAC "\n"				\

arch/x86/include/asm/thread_info.h

@@ -140,14 +140,6 @@ struct thread_info {
 	 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT |	\
 	 _TIF_NOHZ)
 
-/* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK						\
-	(_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING |	\
-	 _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU |	\
-	 _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE |	\
-	 _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT |	\
-	 _TIF_FSCHECK)
-
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW_BASE						\
 	(_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|		\

arch/x86/kernel/fpu/core.c

@@ -93,7 +93,7 @@ bool irq_fpu_usable(void)
 }
 EXPORT_SYMBOL(irq_fpu_usable);
 
-void __kernel_fpu_begin(void)
+static void __kernel_fpu_begin(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
@@ -111,9 +111,8 @@ void __kernel_fpu_begin(void)
 		__cpu_invalidate_fpregs_state();
 	}
 }
-EXPORT_SYMBOL(__kernel_fpu_begin);
 
-void __kernel_fpu_end(void)
+static void __kernel_fpu_end(void)
 {
 	struct fpu *fpu = &current->thread.fpu;
 
@@ -122,7 +121,6 @@ void __kernel_fpu_end(void)
 
 	kernel_fpu_enable();
 }
-EXPORT_SYMBOL(__kernel_fpu_end);
 
 void kernel_fpu_begin(void)
 {

arch/x86/kernel/fpu/xstate.c

@@ -444,7 +444,7 @@ static int xfeature_uncompacted_offset(int xfeature_nr)
 	 * format. Checking a supervisor state's uncompacted offset is
 	 * an error.
 	 */
-	if (XFEATURE_MASK_SUPERVISOR & (1 << xfeature_nr)) {
+	if (XFEATURE_MASK_SUPERVISOR & BIT_ULL(xfeature_nr)) {
 		WARN_ONCE(1, "No fixed offset for xstate %d\n", xfeature_nr);
 		return -1;
 	}
@@ -808,8 +808,6 @@ void fpu__resume_cpu(void)
  * Given an xstate feature mask, calculate where in the xsave
  * buffer the state is.  Callers should ensure that the buffer
  * is valid.
- *
- * Note: does not work for compacted buffers.
  */
 static void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
 {

arch/x86/kernel/process_32.c

@@ -44,9 +44,6 @@
 #include <asm/processor.h>
 #include <asm/fpu/internal.h>
 #include <asm/desc.h>
-#ifdef CONFIG_MATH_EMULATION
-#include <asm/math_emu.h>
-#endif
 
 #include <linux/err.h>
 

arch/x86/mm/pkeys.c

@@ -131,6 +131,7 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
  * in the process's lifetime will not accidentally get access
  * to data which is pkey-protected later on.
  */
+static
 u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
 		      PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) |
 		      PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) |