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>

arch/x86/include/asm/page_64.h

@@ -5,6 +5,7 @@
 #include <asm/page_64_types.h>
 
 #ifndef __ASSEMBLY__
+#include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 
 /* duplicated to the one in bootmem.h */

arch/x86/include/asm/pgtable.h

@@ -22,6 +22,7 @@
 #define pgprot_decrypted(prot)	__pgprot(__sme_clr(pgprot_val(prot)))
 
 #ifndef __ASSEMBLY__
+#include <linux/spinlock.h>
 #include <asm/x86_init.h>
 #include <asm/pkru.h>
 #include <asm/fpu/api.h>

arch/x86/include/asm/realmode.h

@@ -89,6 +89,7 @@ static inline void set_real_mode_mem(phys_addr_t mem)
 }
 
 void reserve_real_mode(void);
+void load_trampoline_pgtable(void);
 
 #endif /* __ASSEMBLY__ */
 

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/cpu/common.c

@@ -384,7 +384,7 @@ void native_write_cr0(unsigned long val)
 }
 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;
 

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));

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/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

arch/x86/mm/init.c

@@ -714,6 +714,11 @@ static void __init memory_map_bottom_up(unsigned long map_start,
 static void __init init_trampoline(void)
 {
 #ifdef CONFIG_X86_64
+	/*
+	 * The code below will alias kernel page-tables in the user-range of the
+	 * address space, including the Global bit. So global TLB entries will
+	 * be created when using the trampoline page-table.
+	 */
 	if (!kaslr_memory_enabled())
 		trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
 	else

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);
 }

arch/x86/realmode/init.c

@@ -17,6 +17,32 @@ u32 *trampoline_cr4_features;
 /* Hold the pgd entry used on booting additional CPUs */
 pgd_t trampoline_pgd_entry;
 
+void load_trampoline_pgtable(void)
+{
+#ifdef CONFIG_X86_32
+	load_cr3(initial_page_table);
+#else
+	/*
+	 * This function is called before exiting to real-mode and that will
+	 * fail with CR4.PCIDE still set.
+	 */
+	if (boot_cpu_has(X86_FEATURE_PCID))
+		cr4_clear_bits(X86_CR4_PCIDE);
+
+	write_cr3(real_mode_header->trampoline_pgd);
+#endif
+
+	/*
+	 * The CR3 write above will not flush global TLB entries.
+	 * Stale, global entries from previous page tables may still be
+	 * present.  Flush those stale entries.
+	 *
+	 * This ensures that memory accessed while running with
+	 * trampoline_pgd is *actually* mapped into trampoline_pgd.
+	 */
+	__flush_tlb_all();
+}
+
 void __init reserve_real_mode(void)
 {
 	phys_addr_t mem;