x86/mm: Introduce the 'no5lvl' kernel parameter

This kernel parameter allows to force kernel to use 4-level paging even
if hardware and kernel support 5-level paging.

The option may be useful to work around regressions related to 5-level
paging.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180518103528.59260-5-kirill.shutemov@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/admin-guide/kernel-parameters.txt

@@ -2600,6 +2600,9 @@
 			emulation library even if a 387 maths coprocessor
 			is present.
 
+	no5lvl		[X86-64] Disable 5-level paging mode. Forces
+			kernel to use 4-level paging instead.
+
 	no_console_suspend
 			[HW] Never suspend the console
 			Disable suspending of consoles during suspend and

arch/x86/boot/compressed/cmdline.c

@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 
-#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE
+#if CONFIG_EARLY_PRINTK || CONFIG_RANDOMIZE_BASE || CONFIG_X86_5LEVEL
 
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)

arch/x86/boot/compressed/head_64.S

@@ -365,6 +365,7 @@ ENTRY(startup_64)
 	 * this function call.
 	 */
 	pushq	%rsi
+	movq	%rsi, %rdi		/* real mode address */
 	call	paging_prepare
 	popq	%rsi
 

arch/x86/boot/compressed/pgtable_64.c

@@ -31,23 +31,31 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
  */
 unsigned long *trampoline_32bit __section(.data);
 
-struct paging_config paging_prepare(void)
+extern struct boot_params *boot_params;
+int cmdline_find_option_bool(const char *option);
+
+struct paging_config paging_prepare(void *rmode)
 {
 	struct paging_config paging_config = {};
 	unsigned long bios_start, ebda_start;
 
+	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
+	boot_params = rmode;
+
 	/*
 	 * Check if LA57 is desired and supported.
 	 *
-	 * There are two parts to the check:
+	 * There are several parts to the check:
 	 *   - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y
+	 *   - if user asked to disable 5-level paging: no5lvl in cmdline
 	 *   - if the machine supports 5-level paging:
 	 *     + CPUID leaf 7 is supported
 	 *     + the leaf has the feature bit set
 	 *
 	 * That's substitute for boot_cpu_has() in early boot code.
 	 */
 	if (IS_ENABLED(CONFIG_X86_5LEVEL) &&
+			!cmdline_find_option_bool("no5lvl") &&
 			native_cpuid_eax(0) >= 7 &&
 			(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
 		paging_config.l5_required = 1;

arch/x86/kernel/cpu/common.c

@@ -1028,6 +1028,21 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	setup_clear_cpu_cap(X86_FEATURE_PCID);
 #endif
+
+	/*
+	 * Later in the boot process pgtable_l5_enabled() relies on
+	 * cpu_feature_enabled(X86_FEATURE_LA57). If 5-level paging is not
+	 * enabled by this point we need to clear the feature bit to avoid
+	 * false-positives at the later stage.
+	 *
+	 * pgtable_l5_enabled() can be false here for several reasons:
+	 *  - 5-level paging is disabled compile-time;
+	 *  - it's 32-bit kernel;
+	 *  - machine doesn't support 5-level paging;
+	 *  - user specified 'no5lvl' in kernel command line.
+	 */
+	if (!pgtable_l5_enabled())
+		setup_clear_cpu_cap(X86_FEATURE_LA57);
 }
 
 void __init early_cpu_init(void)

arch/x86/kernel/head64.c

@@ -80,10 +80,11 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr)
 
 static bool __head check_la57_support(unsigned long physaddr)
 {
-	if (native_cpuid_eax(0) < 7)
-		return false;
-
-	if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+	/*
+	 * 5-level paging is detected and enabled at kernel decomression
+	 * stage. Only check if it has been enabled there.
+	 */
+	if (!(native_read_cr4() & X86_CR4_LA57))
 		return false;
 
 	*fixup_int(&__pgtable_l5_enabled, physaddr) = 1;