kaiser: asm/tlbflush.h handle noPGE at lower level

I found asm/tlbflush.h too twisty, and think it safer not to avoid
__native_flush_tlb_global_irq_disabled() in the kaiser_enabled case,
but instead let it handle kaiser_enabled along with cr3: it can just
use __native_flush_tlb() for that, no harm in re-disabling preemption.

(This is not the same change as Kirill and Dave have suggested for
upstream, flipping PGE in cr4: that's neat, but needs a cpu_has_pge
check; cr3 is enough for kaiser, and thought to be cheaper than cr4.)

Also delete the X86_FEATURE_INVPCID invpcid_flush_all_nonglobals()
preference from __native_flush_tlb(): unlike the invpcid_flush_all()
preference in __native_flush_tlb_global(), it's not seen in upstream
4.14, and was recently reported to be surprisingly slow.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/include/asm/tlbflush.h

@@ -151,14 +151,6 @@ static inline void kaiser_flush_tlb_on_return_to_user(void)
 
 static inline void __native_flush_tlb(void)
 {
-	if (this_cpu_has(X86_FEATURE_INVPCID)) {
-		/*
-		 * Note, this works with CR4.PCIDE=0 or 1.
-		 */
-		invpcid_flush_all_nonglobals();
-		return;
-	}
-
 	/*
 	 * If current->mm == NULL then we borrow a mm which may change during a
 	 * task switch and therefore we must not be preempted while we write CR3
@@ -182,11 +174,8 @@ static inline void __native_flush_tlb_global_irq_disabled(void)
 		/* restore PGE as it was before */
 		native_write_cr4(cr4);
 	} else {
-		/*
-		 * x86_64 microcode update comes this way when CR4.PGE is not
-		 * enabled, and it's safer for all callers to allow this case.
-		 */
-		native_write_cr3(native_read_cr3());
+		/* do it with cr3, letting kaiser flush user PCID */
+		__native_flush_tlb();
 	}
 }
 
@@ -194,12 +183,6 @@ static inline void __native_flush_tlb_global(void)
 {
 	unsigned long flags;
 
-	if (kaiser_enabled) {
-		/* Globals are not used at all */
-		__native_flush_tlb();
-		return;
-	}
-
 	if (this_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
 		 * Using INVPCID is considerably faster than a pair of writes
@@ -255,11 +238,7 @@ static inline void __native_flush_tlb_single(unsigned long addr)
 
 static inline void __flush_tlb_all(void)
 {
-	if (cpu_has_pge)
-		__flush_tlb_global();
-	else
-		__flush_tlb();
-
+	__flush_tlb_global();
 	/*
 	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
 	 * we'd end up flushing kernel translations for the current ASID but