Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 16 Nov 2022 08:50:37 +0100
From:   Alexander Gordeev <agordeev@linux.ibm.com>
To:     Linus Torvalds <torvalds@linux-foundation.org>
Cc:     Hugh Dickins <hughd@google.com>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        Nadav Amit <nadav.amit@gmail.com>,
        Will Deacon <will@kernel.org>,
        Aneesh Kumar <aneesh.kumar@linux.ibm.com>,
        Nick Piggin <npiggin@gmail.com>,
        Heiko Carstens <hca@linux.ibm.com>,
        Vasily Gorbik <gor@linux.ibm.com>,
        Christian Borntraeger <borntraeger@linux.ibm.com>,
        Sven Schnelle <svens@linux.ibm.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Subject: mm: mmu_gather: do not define delayed_rmap if not used
Message-ID: <Y3SWTXMotahiqvBO@li-4a3a4a4c-28e5-11b2-a85c-a8d192c6f089.ibm.com>
References: <20221109203051.1835763-1-torvalds@linux-foundation.org>
 <20221109203051.1835763-4-torvalds@linux-foundation.org>
 <CAHk-=wjf+gN25grUT3o3XK8-B-b2jhBuN8YMLQvq-=AXTcuFXg@mail.gmail.com>
 <CAHk-=wiFmm+X92Ghkz_LDG53djReK=idAj0uvSdES+yeG1X=Dw@mail.gmail.com>
 <Y3SVqePHGXRUagyF@li-4a3a4a4c-28e5-11b2-a85c-a8d192c6f089.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <Y3SVqePHGXRUagyF@li-4a3a4a4c-28e5-11b2-a85c-a8d192c6f089.ibm.com>
Precedence: bulk

In cases the delayed rmap removal is not used (which are
currently UP and s390) skip delayed_rmap flag and make
the related code paths no-op.

Signed-off-by: Alexander Gordeev <agordeev@linux.ibm.com>
---
 include/asm-generic/tlb.h | 32 +++++++++++++++++++-------------
 mm/mmu_gather.c           |  8 ++++----
 2 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 154c774d6307..317bef9eee3c 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -265,24 +265,14 @@ extern bool __tlb_remove_page_size(struct mmu_gather *tlb,
  * This both sets 'delayed_rmap', and returns true. It would be an inline
  * function, except we define it before the 'struct mmu_gather'.
  */
-#define tlb_delay_rmap(tlb) (((tlb)->delayed_rmap = 1), true)
+#define tlb_delay_rmap(tlb)		(((tlb)->delayed_rmap = 1), true)
+#define tlb_reset_delay_rmap(tlb)	((tlb)->delayed_rmap = 0)
+#define tlb_rmap_delayed(tlb)		((tlb)->delayed_rmap)
 extern void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma);
 #endif
 
 #endif
 
-/*
- * We have a no-op version of the rmap removal that doesn't
- * delay anything. That is used on S390, which flushes remote
- * TLBs synchronously, and on UP, which doesn't have any
- * remote TLBs to flush and is not preemptible due to this
- * all happening under the page table lock.
- */
-#ifndef tlb_delay_rmap
-#define tlb_delay_rmap(tlb) (false)
-static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
-#endif
-
 /*
  * struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
@@ -313,10 +303,12 @@ struct mmu_gather {
 	 */
 	unsigned int		freed_tables : 1;
 
+#ifdef tlb_delay_rmap
 	/*
 	 * Do we have pending delayed rmap removals?
 	 */
 	unsigned int		delayed_rmap : 1;
+#endif
 
 	/*
 	 * at which levels have we cleared entries?
@@ -346,6 +338,20 @@ struct mmu_gather {
 #endif
 };
 
+/*
+ * We have a no-op version of the rmap removal that doesn't
+ * delay anything. That is used on S390, which flushes remote
+ * TLBs synchronously, and on UP, which doesn't have any
+ * remote TLBs to flush and is not preemptible due to this
+ * all happening under the page table lock.
+ */
+#ifndef tlb_delay_rmap
+#define tlb_delay_rmap(tlb)		(false)
+#define tlb_reset_delay_rmap(tlb)	do { } while (0)
+#define tlb_rmap_delayed(tlb)		(false)
+static inline void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+#endif
+
 void tlb_flush_mmu(struct mmu_gather *tlb);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 9f22309affee..b0f1bd20af2f 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -20,7 +20,7 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 	struct mmu_gather_batch *batch;
 
 	/* No more batching if we have delayed rmaps pending */
-	if (tlb->delayed_rmap)
+	if (tlb_rmap_delayed(tlb))
 		return false;
 
 	batch = tlb->active;
@@ -60,7 +60,7 @@ void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma)
 {
 	struct mmu_gather_batch *batch;
 
-	if (!tlb->delayed_rmap)
+	if (!tlb_rmap_delayed(tlb))
 		return;
 
 	batch = tlb->active;
@@ -73,7 +73,7 @@ void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma)
 		}
 	}
 
-	tlb->delayed_rmap = 0;
+	tlb_reset_delay_rmap(tlb);
 }
 #endif
 
@@ -311,7 +311,7 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	tlb->active     = &tlb->local;
 	tlb->batch_count = 0;
 #endif
-	tlb->delayed_rmap = 0;
+	tlb_reset_delay_rmap(tlb);
 
 	tlb_table_init(tlb);
 #ifdef CONFIG_MMU_GATHER_PAGE_SIZE
-- 
2.31.1