Merge tag 'x86-urgent-2023-08-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "Fix an FPU invalidation bug on exec(), and fix a performance
  regression due to a missing setting of X86_FEATURE_OSXSAVE"

* tag 'x86-urgent-2023-08-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/fpu: Set X86_FEATURE_OSXSAVE feature after enabling OSXSAVE in CR4
  x86/fpu: Invalidate FPU state correctly on exec()

arch/x86/kernel/fpu/context.h

@@ -19,8 +19,7 @@
  * FPU state for a task MUST let the rest of the kernel know that the
  * FPU registers are no longer valid for this task.
  *
- * Either one of these invalidation functions is enough. Invalidate
- * a resource you control: CPU if using the CPU for something else
+ * Invalidate a resource you control: CPU if using the CPU for something else
  * (with preemption disabled), FPU for the current task, or a task that
  * is prevented from running by the current task.
  */

arch/x86/kernel/fpu/core.c

@@ -679,7 +679,7 @@ static void fpu_reset_fpregs(void)
 	struct fpu *fpu = &current->thread.fpu;
 
 	fpregs_lock();
-	fpu__drop(fpu);
+	__fpu_invalidate_fpregs_state(fpu);
 	/*
 	 * This does not change the actual hardware registers. It just
 	 * resets the memory image and sets TIF_NEED_FPU_LOAD so a

arch/x86/kernel/fpu/xstate.c

@@ -882,6 +882,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 		goto out_disable;
 	}
 
+	/*
+	 * CPU capabilities initialization runs before FPU init. So
+	 * X86_FEATURE_OSXSAVE is not set. Now that XSAVE is completely
+	 * functional, set the feature bit so depending code works.
+	 */
+	setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
+
 	print_xstate_offset_size();
 	pr_info("x86/fpu: Enabled xstate features 0x%llx, context size is %d bytes, using '%s' format.\n",
 		fpu_kernel_cfg.max_features,