[PATCH RFC 2/3] x86/mm: implement redundant IPI elimination for PMD unsharing

[Lance Yang]

From: Lance Yang <lance.yang@xxxxxxxxx>

Pass both freed_tables and unshared_tables to flush_tlb_mm_range() to
ensure lazy-TLB CPUs receive IPIs and flush their paging-structure caches:

	flush_tlb_mm_range(..., freed_tables || unshared_tables);

Implement tlb_table_flush_implies_ipi_broadcast() for x86: on native x86
without paravirt or INVLPGB, the TLB flush IPI already provides necessary
synchronization, allowing the second IPI to be skipped. For paravirt with
non-native flush_tlb_multi and for INVLPGB, conservatively keep both IPIs.

Suggested-by: David Hildenbrand (Red Hat) <david@xxxxxxxxxx>
Signed-off-by: Lance Yang <lance.yang@xxxxxxxxx>
---
 arch/x86/include/asm/tlb.h | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 866ea78ba156..96602b7b7210 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -5,10 +5,24 @@
 #define tlb_flush tlb_flush
 static inline void tlb_flush(struct mmu_gather *tlb);
 
+#define tlb_table_flush_implies_ipi_broadcast tlb_table_flush_implies_ipi_broadcast
+static inline bool tlb_table_flush_implies_ipi_broadcast(void);
+
 #include <asm-generic/tlb.h>
 #include <linux/kernel.h>
 #include <vdso/bits.h>
 #include <vdso/page.h>
+#include <asm/paravirt.h>
+
+static inline bool tlb_table_flush_implies_ipi_broadcast(void)
+{
+#ifdef CONFIG_PARAVIRT
+	/* Paravirt may use hypercalls that don't send real IPIs. */
+	if (pv_ops.mmu.flush_tlb_multi != native_flush_tlb_multi)
+		return false;
+#endif
+	return !cpu_feature_enabled(X86_FEATURE_INVLPGB);
+}
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
@@ -20,7 +34,8 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		end = tlb->end;
 	}
 
-	flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables);
+	flush_tlb_mm_range(tlb->mm, start, end, stride_shift,
+			   tlb->freed_tables || tlb->unshared_tables);
 }
 
 static inline void invlpg(unsigned long addr)
-- 
2.49.0