x86/mm/64: Flush global TLB on boot and AP bringup

The AP bringup code uses the trampoline_pgd page-table which
establishes global mappings in the user range of the address space.
Flush the global TLB entries after the indentity mappings are removed so
no stale entries remain in the TLB.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211202153226.22946-3-joro@8bytes.org

arch/x86/include/asm/tlbflush.h

@@ -261,4 +261,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 
 #endif /* !MODULE */
 
+static inline void __native_tlb_flush_global(unsigned long cr4)
+{
+	native_write_cr4(cr4 ^ X86_CR4_PGE);
+	native_write_cr4(cr4);
+}
 #endif /* _ASM_X86_TLBFLUSH_H */

arch/x86/kernel/head64.c

@@ -483,6 +483,8 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 	/* Kill off the identity-map trampoline */
 	reset_early_page_tables();
 
+	__native_tlb_flush_global(native_read_cr4());
+
 	clear_bss();
 
 	clear_page(init_top_pgt);

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

arch/x86/mm/tlb.c

@@ -1148,7 +1148,7 @@ void flush_tlb_one_user(unsigned long addr)
  */
 STATIC_NOPV void native_flush_tlb_global(void)
 {
-	unsigned long cr4, flags;
+	unsigned long flags;
 
 	if (static_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
@@ -1168,11 +1168,7 @@ STATIC_NOPV void native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* toggle PGE */
-	native_write_cr4(cr4 ^ X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
+	__native_tlb_flush_global(this_cpu_read(cpu_tlbstate.cr4));
 
 	raw_local_irq_restore(flags);
 }