[PATCH v5 12/12] x86/mm: only invalidate final translations with INVLPGB

[Rik van Riel]

Use the INVLPGB_FINAL_ONLY flag when invalidating mappings with INVPLGB.
This way only leaf mappings get removed from the TLB, leaving intermediate
translations cached.

On the (rare) occasions where we free page tables we do a full flush,
ensuring intermediate translations get flushed from the TLB.

Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
---
 arch/x86/include/asm/invlpgb.h | 10 ++++++++--
 arch/x86/mm/tlb.c              |  8 ++++----
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/invlpgb.h b/arch/x86/include/asm/invlpgb.h
index 4dfd09e65fa6..418402535319 100644
--- a/arch/x86/include/asm/invlpgb.h
+++ b/arch/x86/include/asm/invlpgb.h
@@ -63,9 +63,15 @@ static inline void invlpgb_flush_user(unsigned long pcid,
 static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid,
 						unsigned long addr,
 						u16 nr,
-						bool pmd_stride)
+						bool pmd_stride,
+						bool freed_tables)
 {
-	__invlpgb(0, pcid, addr, nr - 1, pmd_stride, INVLPGB_PCID | INVLPGB_VA);
+	unsigned long flags = INVLPGB_PCID | INVLPGB_VA;
+
+	if (!freed_tables)
+		flags |= INVLPGB_FINAL_ONLY;
+
+	__invlpgb(0, pcid, addr, nr - 1, pmd_stride, flags);
 }
 
 /* Flush all mappings for a given PCID, not including globals. */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 81f847c94321..82fed9fd5ac2 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -538,10 +538,10 @@ static void broadcast_tlb_flush(struct flush_tlb_info *info)
 		nr = min(maxnr, (info->end - addr) >> info->stride_shift);
 		nr = max(nr, 1);
 
-		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd);
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), addr, nr, pmd, info->freed_tables);
 		/* Do any CPUs supporting INVLPGB need PTI? */
 		if (static_cpu_has(X86_FEATURE_PTI))
-			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd);
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), addr, nr, pmd, info->freed_tables);
 	}
 
 	finish_asid_transition(info);
@@ -1700,10 +1700,10 @@ void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch,
 			batch->used_invlpgb = true;
 			migrate_disable();
 		}
-		invlpgb_flush_user_nr_nosync(kern_pcid(asid), uaddr, 1, false);
+		invlpgb_flush_user_nr_nosync(kern_pcid(asid), uaddr, 1, false, false);
 		/* Do any CPUs supporting INVLPGB need PTI? */
 		if (static_cpu_has(X86_FEATURE_PTI))
-			invlpgb_flush_user_nr_nosync(user_pcid(asid), uaddr, 1, false);
+			invlpgb_flush_user_nr_nosync(user_pcid(asid), uaddr, 1, false, false);
 
 		/*
 		 * Some CPUs might still be using a local ASID for this
-- 
2.47.1