[PATCH 1/4] x86/boot: Synchronize trampoline_cr4_features and mmu_cr4_features directly

[Andy Lutomirski]

The initialization process for trampoline_cr4_features and
mmu_cr4_features was confusing.  The intent is for mmu_cr4_features
and *trampoline_cr4_features to stay in sync, but
trampoline_cr4_features is NULL until setup_real_mode() runs.  The
old code synchronized *trampoline_cr4_features *twice*, once in
setup_real_mode() and once in setup_arch().  It also initialized
mmu_cr4_features in setup_real_mode(), which causes the actual value
of mmu_cr4_features to potentially depend on when setup_real_mode()
is called.

With this patch, mmu_cr4_features is initialized directly in
setup_arch(), and *trampoline_cr4_features is synchronized to
mmu_cr4_features when the trampoline is set up.

After this patch, it should be safe to defer setup_real_mode().

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
 arch/x86/kernel/setup.c  | 17 ++++++++++-------
 arch/x86/realmode/init.c |  3 ++-
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0825c493f475..f292a58356fb 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1134,6 +1134,16 @@ void __init setup_arch(char **cmdline_p)
 
 	early_trap_pf_init();
 
+	/*
+	 * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features)
+	 * with the current CR4 value.  This may not be necessary, but
+	 * auditing all the early-boot CR4 manipulation would be needed to
+	 * rule it out.
+	 */
+	if (boot_cpu_data.cpuid_level >= 0)
+		/* A CPU has %cr4 if and only if it has CPUID. */
+		mmu_cr4_features = __read_cr4();
+
 	setup_real_mode();
 
 	memblock_set_current_limit(get_max_mapped());
@@ -1183,13 +1193,6 @@ void __init setup_arch(char **cmdline_p)
 
 	kasan_init();
 
-	if (boot_cpu_data.cpuid_level >= 0) {
-		/* A CPU has %cr4 if and only if it has CPUID */
-		mmu_cr4_features = __read_cr4();
-		if (trampoline_cr4_features)
-			*trampoline_cr4_features = mmu_cr4_features;
-	}
-
 #ifdef CONFIG_X86_32
 	/* sync back kernel address range */
 	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 705e3fffb4a1..c5bdc4e473e7 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -4,6 +4,7 @@
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 #include <asm/realmode.h>
+#include <asm/tlbflush.h>
 
 struct real_mode_header *real_mode_header;
 u32 *trampoline_cr4_features;
@@ -84,7 +85,7 @@ void __init setup_real_mode(void)
 
 	trampoline_header->start = (u64) secondary_startup_64;
 	trampoline_cr4_features = &trampoline_header->cr4;
-	*trampoline_cr4_features = __read_cr4();
+	*trampoline_cr4_features = mmu_cr4_features;
 
 	trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
 	trampoline_pgd[0] = trampoline_pgd_entry.pgd;
-- 
2.7.4