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

Pull x86 fixes from Thomas Gleixner:
 "A collection of assorted fixes:

   - Fix for the pinned cr0/4 fallout which escaped all testing efforts
     because the kvm-intel module was never loaded when the kernel was
     compiled with CONFIG_PARAVIRT=n. The cr0/4 accessors are moved out
     of line and static key is now solely used in the core code and
     therefore can stay in the RO after init section. So the kvm-intel
     and other modules do not longer reference the (read only) static
     key which the module loader tried to update.

   - Prevent an infinite loop in arch_stack_walk_user() by breaking out
     of the loop once the return address is detected to be 0.

   - Prevent the int3_emulate_call() selftest from corrupting the stack
     when KASAN is enabled. KASASN clobbers more registers than covered
     by the emulated call implementation. Convert the int3_magic()
     selftest to a ASM function so the compiler cannot KASANify it.

   - Unbreak the build with old GCC versions and with the Gold linker by
     reverting the 'Move of _etext to the actual end of .text'. In both
     cases the build fails with 'Invalid absolute R_X86_64_32S
     relocation: _etext'

   - Initialize the context lock for init_mm, which was never an issue
     until the alternatives code started to use a temporary mm for
     patching.

   - Fix a build warning vs. the LOWMEM_PAGES constant where clang
     complains rightfully about a signed integer overflow in the shift
     operation by converting the operand to an ULL.

   - Adjust the misnamed ENDPROC() of common_spurious in the 32bit entry
     code"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/stacktrace: Prevent infinite loop in arch_stack_walk_user()
  x86/asm: Move native_write_cr0/4() out of line
  x86/pgtable/32: Fix LOWMEM_PAGES constant
  x86/alternatives: Fix int3_emulate_call() selftest stack corruption
  x86/entry/32: Fix ENDPROC of common_spurious
  Revert "x86/build: Move _etext to actual end of .text"
  x86/ldt: Initialize the context lock for init_mm

arch/x86/kernel/cpu/common.c

@@ -366,10 +366,62 @@ out:
 	cr4_clear_bits(X86_CR4_UMIP);
 }
 
-DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
-EXPORT_SYMBOL(cr_pinning);
-unsigned long cr4_pinned_bits __ro_after_init;
-EXPORT_SYMBOL(cr4_pinned_bits);
+static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning);
+static unsigned long cr4_pinned_bits __ro_after_init;
+
+void native_write_cr0(unsigned long val)
+{
+	unsigned long bits_missing = 0;
+
+set_register:
+	asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order));
+
+	if (static_branch_likely(&cr_pinning)) {
+		if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) {
+			bits_missing = X86_CR0_WP;
+			val |= bits_missing;
+			goto set_register;
+		}
+		/* Warn after we've set the missing bits. */
+		WARN_ONCE(bits_missing, "CR0 WP bit went missing!?\n");
+	}
+}
+EXPORT_SYMBOL(native_write_cr0);
+
+void native_write_cr4(unsigned long val)
+{
+	unsigned long bits_missing = 0;
+
+set_register:
+	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
+
+	if (static_branch_likely(&cr_pinning)) {
+		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
+			bits_missing = ~val & cr4_pinned_bits;
+			val |= bits_missing;
+			goto set_register;
+		}
+		/* Warn after we've set the missing bits. */
+		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
+			  bits_missing);
+	}
+}
+EXPORT_SYMBOL(native_write_cr4);
+
+void cr4_init(void)
+{
+	unsigned long cr4 = __read_cr4();
+
+	if (boot_cpu_has(X86_FEATURE_PCID))
+		cr4 |= X86_CR4_PCIDE;
+	if (static_branch_likely(&cr_pinning))
+		cr4 |= cr4_pinned_bits;
+
+	__write_cr4(cr4);
+
+	/* Initialize cr4 shadow for this CPU. */
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+}
 
 /*
  * Once CPU feature detection is finished (and boot params have been
@@ -1723,12 +1775,6 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
-
 	if (cpu)
 		load_ucode_ap();
 
@@ -1823,12 +1869,6 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
-	/*
-	 * Initialize the CR4 shadow before doing anything that could
-	 * try to read it.
-	 */
-	cr4_init_shadow();
-
 	show_ucode_info_early();
 
 	pr_info("Initializing CPU#%d\n", cpu);