x86/fpu/xstate: Define new functions for clearing fpregs and xstates

Currently, fpu__clear() clears all fpregs and xstates.  Once XSAVES
supervisor states are introduced, supervisor settings (e.g. CET xstates)
must remain active for signals; It is necessary to have separate functions:

- Create fpu__clear_user_states(): clear only user settings for signals;
- Create fpu__clear_all(): clear both user and supervisor settings in
   flush_thread().

Also modify copy_init_fpstate_to_fpregs() to take a mask from above two
functions.

Remove obvious side-comment in fpu__clear(), while at it.

 [ bp: Make the second argument of fpu__clear() bool after requesting it
   a bunch of times during review.
  - Add a comment about copy_init_fpstate_to_fpregs() locking needs. ]

Co-developed-by: Yu-cheng Yu <[email protected]>
Signed-off-by: Fenghua Yu <[email protected]>
Signed-off-by: Yu-cheng Yu <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Dave Hansen <[email protected]>
Reviewed-by: Tony Luck <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: Fenghua Yu

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

@@ -31,7 +31,8 @@ extern void fpu__save(struct fpu *fpu);
 extern int  fpu__restore_sig(void __user *buf, int ia32_frame);
 extern void fpu__drop(struct fpu *fpu);
 extern int  fpu__copy(struct task_struct *dst, struct task_struct *src);
-extern void fpu__clear(struct fpu *fpu);
+extern void fpu__clear_user_states(struct fpu *fpu);
+extern void fpu__clear_all(struct fpu *fpu);
 extern int  fpu__exception_code(struct fpu *fpu, int trap_nr);
 extern int  dump_fpu(struct pt_regs *ptregs, struct user_i387_struct *fpstate);
 

arch/x86/kernel/fpu/core.c

@@ -291,25 +291,20 @@ void fpu__drop(struct fpu *fpu)
 }
 
 /*
- * Clear FPU registers by setting them up from
- * the init fpstate:
+ * Clear FPU registers by setting them up from the init fpstate.
+ * Caller must do fpregs_[un]lock() around it.
  */
-static inline void copy_init_fpstate_to_fpregs(void)
+static inline void copy_init_fpstate_to_fpregs(u64 features_mask)
 {
-	fpregs_lock();
-
 	if (use_xsave())
-		copy_kernel_to_xregs(&init_fpstate.xsave, -1);
+		copy_kernel_to_xregs(&init_fpstate.xsave, features_mask);
 	else if (static_cpu_has(X86_FEATURE_FXSR))
 		copy_kernel_to_fxregs(&init_fpstate.fxsave);
 	else
 		copy_kernel_to_fregs(&init_fpstate.fsave);
 
 	if (boot_cpu_has(X86_FEATURE_OSPKE))
 		copy_init_pkru_to_fpregs();
-
-	fpregs_mark_activate();
-	fpregs_unlock();
 }
 
 /*
@@ -318,18 +313,40 @@ static inline void copy_init_fpstate_to_fpregs(void)
  * Called by sys_execve(), by the signal handler code and by various
  * error paths.
  */
-void fpu__clear(struct fpu *fpu)
+static void fpu__clear(struct fpu *fpu, bool user_only)
 {
-	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
+	WARN_ON_FPU(fpu != &current->thread.fpu);
 
-	fpu__drop(fpu);
+	if (!static_cpu_has(X86_FEATURE_FPU)) {
+		fpu__drop(fpu);
+		fpu__initialize(fpu);
+		return;
+	}
 
-	/*
-	 * Make sure fpstate is cleared and initialized.
-	 */
-	fpu__initialize(fpu);
-	if (static_cpu_has(X86_FEATURE_FPU))
-		copy_init_fpstate_to_fpregs();
+	fpregs_lock();
+
+	if (user_only) {
+		if (!fpregs_state_valid(fpu, smp_processor_id()) &&
+		    xfeatures_mask_supervisor())
+			copy_kernel_to_xregs(&fpu->state.xsave,
+					     xfeatures_mask_supervisor());
+		copy_init_fpstate_to_fpregs(xfeatures_mask_user());
+	} else {
+		copy_init_fpstate_to_fpregs(xfeatures_mask_all);
+	}
+
+	fpregs_mark_activate();
+	fpregs_unlock();
+}
+
+void fpu__clear_user_states(struct fpu *fpu)
+{
+	fpu__clear(fpu, true);
+}
+
+void fpu__clear_all(struct fpu *fpu)
+{
+	fpu__clear(fpu, false);
 }
 
 /*

arch/x86/kernel/fpu/signal.c

@@ -289,7 +289,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 			 IS_ENABLED(CONFIG_IA32_EMULATION));
 
 	if (!buf) {
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 		return 0;
 	}
 
@@ -416,7 +416,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
 
 err_out:
 	if (ret)
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 	return ret;
 }
 

arch/x86/kernel/process.c

@@ -191,7 +191,7 @@ void flush_thread(void)
 	flush_ptrace_hw_breakpoint(tsk);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));
 
-	fpu__clear(&tsk->thread.fpu);
+	fpu__clear_all(&tsk->thread.fpu);
 }
 
 void disable_TSC(void)

arch/x86/kernel/signal.c

@@ -732,7 +732,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		/*
 		 * Ensure the signal handler starts with the new fpu state.
 		 */
-		fpu__clear(fpu);
+		fpu__clear_user_states(fpu);
 	}
 	signal_setup_done(failed, ksig, stepping);
 }