Re: [PATCH 3/4] mm/tlb, x86/mm: Support invalidating TLB caches for RCU_TABLE_FREE

[Peter Zijlstra]

On Wed, Aug 22, 2018 at 05:30:15PM +0200, Peter Zijlstra wrote:
> ARM
> which later used this put an explicit TLB invalidate in their
> __p*_free_tlb() functions, and PowerPC-radix followed that example.

> +/*
> + * If we want tlb_remove_table() to imply TLB invalidates.
> + */
> +static inline void tlb_table_invalidate(struct mmu_gather *tlb)
> +{
> +#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
> +	/*
> +	 * Invalidate page-table caches used by hardware walkers. Then we still
> +	 * need to RCU-sched wait while freeing the pages because software
> +	 * walkers can still be in-flight.
> +	 */
> +	__tlb_flush_mmu_tlbonly(tlb);
> +#endif
> +}


Nick, Will is already looking at using this to remove the synchronous
invalidation from __p*_free_tlb() for ARM, could you have a look to see
if PowerPC-radix could benefit from that too?

Basically, using a patch like the below, would give your tlb_flush()
information on if tables were removed or not.

---

--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -96,12 +96,22 @@ struct mmu_gather {
 #endif
 	unsigned long		start;
 	unsigned long		end;
-	/* we are in the middle of an operation to clear
-	 * a full mm and can make some optimizations */
-	unsigned int		fullmm : 1,
-	/* we have performed an operation which
-	 * requires a complete flush of the tlb */
-				need_flush_all : 1;
+	/*
+	 * we are in the middle of an operation to clear
+	 * a full mm and can make some optimizations
+	 */
+	unsigned int		fullmm : 1;
+
+	/*
+	 * we have performed an operation which
+	 * requires a complete flush of the tlb
+	 */
+	unsigned int		need_flush_all : 1;
+
+	/*
+	 * we have removed page directories
+	 */
+	unsigned int		freed_tables : 1;
 
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
@@ -136,6 +146,7 @@ static inline void __tlb_reset_range(str
 		tlb->start = TASK_SIZE;
 		tlb->end = 0;
 	}
+	tlb->freed_tables = 0;
 }
 
 static inline void tlb_remove_page_size(struct mmu_gather *tlb,
@@ -269,6 +280,7 @@ static inline void tlb_remove_check_page
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;			\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 #endif
@@ -276,7 +288,8 @@ static inline void tlb_remove_check_page
 #ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;			\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 #endif
@@ -286,6 +299,7 @@ static inline void tlb_remove_check_page
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;			\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
@@ -295,7 +309,8 @@ static inline void tlb_remove_check_page
 #ifndef p4d_free_tlb
 #define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
+		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb->freed_tables = 1;			\
 		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif