Merge tag 'x86_mm_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Borislav Petkov:

 - Flush *all* mappings from the TLB after switching to the trampoline
   pagetable to prevent any stale entries' presence

 - Flush global mappings from the TLB, in addition to the CR3-write,
   after switching off of the trampoline_pgd during boot to clear the
   identity mappings

 - Prevent instrumentation issues resulting from the above changes

* tag 'x86_mm_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Prevent early boot triple-faults with instrumentation
  x86/mm: Include spinlock_t definition in pgtable.
  x86/mm: Flush global TLB when switching to trampoline page-table
  x86/mm/64: Flush global TLB on boot and AP bringup
  x86/realmode: Add comment for Global bit usage in trampoline_pgd
  x86/mm: Add missing <asm/cpufeatures.h> dependency to <asm/page_64.h>

4 files changed, 35 insertions, 12 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0083464de5e3..79b3d67addcc 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -384,7 +384,7 @@ set_register:
 }
 EXPORT_SYMBOL(native_write_cr0);
 
-void native_write_cr4(unsigned long val)
+void __no_profile native_write_cr4(unsigned long val)
 {
 	unsigned long bits_changed = 0;
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 3be9dd213dad..de563db9cdcd 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -487,6 +487,10 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 
 	clear_bss();
 
+	/*
+	 * This needs to happen *before* kasan_early_init() because latter maps stuff
+	 * into that page.
+	 */
 	clear_page(init_top_pgt);
 
 	/*
@@ -498,6 +502,16 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 
 	kasan_early_init();
 
+	/*
+	 * Flush global TLB entries which could be left over from the trampoline page
+	 * table.
+	 *
+	 * This needs to happen *after* kasan_early_init() as KASAN-enabled .configs
+	 * instrument native_write_cr4() so KASAN must be initialized for that
+	 * instrumentation to work.
+	 */
+	__native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));
+
 	idt_setup_early_handler();
 
 	copy_bootdata(__va(real_mode_data));
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d8b3ebd2bb85..9c63fc5988cd 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -166,9 +166,26 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	call	sev_verify_cbit
 	popq	%rsi
 
-	/* Switch to new page-table */
+	/*
+	 * Switch to new page-table
+	 *
+	 * For the boot CPU this switches to early_top_pgt which still has the
+	 * indentity mappings present. The secondary CPUs will switch to the
+	 * init_top_pgt here, away from the trampoline_pgd and unmap the
+	 * indentity mapped ranges.
+	 */
 	movq	%rax, %cr3
 
+	/*
+	 * Do a global TLB flush after the CR3 switch to make sure the TLB
+	 * entries from the identity mapping are flushed.
+	 */
+	movq	%cr4, %rcx
+	movq	%rcx, %rax
+	xorq	$X86_CR4_PGE, %rcx
+	movq	%rcx, %cr4
+	movq	%rax, %cr4
+
 	/* Ensure I am executing from virtual addresses */
 	movq	$1f, %rax
 	ANNOTATE_RETPOLINE_SAFE
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 0a40df66a40d..fa700b46588e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -113,17 +113,9 @@ void __noreturn machine_real_restart(unsigned int type)
 	spin_unlock(&rtc_lock);
 
 	/*
-	 * Switch back to the initial page table.
+	 * Switch to the trampoline page table.
 	 */
-#ifdef CONFIG_X86_32
-	load_cr3(initial_page_table);
-#else
-	write_cr3(real_mode_header->trampoline_pgd);
-
-	/* Exiting long mode will fail if CR4.PCIDE is set. */
-	if (boot_cpu_has(X86_FEATURE_PCID))
-		cr4_clear_bits(X86_CR4_PCIDE);
-#endif
+	load_trampoline_pgtable();
 
 	/* Jump to the identity-mapped low memory code */
 #ifdef CONFIG_X86_32