All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nicholas Piggin <npiggin@gmail.com>
To: linux-mm@kvack.org
Cc: linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
	linux-arm-kernel@lists.infradead.org,
	Nicholas Piggin <npiggin@gmail.com>
Subject: [RFC PATCH 3/4] mm: allow arch to have tlb_flush caled on an empty TLB range
Date: Thu, 26 Jul 2018 00:06:40 +1000	[thread overview]
Message-ID: <20180725140641.30372-4-npiggin@gmail.com> (raw)
In-Reply-To: <20180725140641.30372-1-npiggin@gmail.com>

powerpc wants to de-couple page table caching structure flushes
from TLB flushes, which will make it possible to have mmu_gather
with freed page table pages but no TLB range. These must be sent
to tlb_flush, so allow the arch to specify when mmu_gather with
empty ranges should have tlb_flush called.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 include/asm-generic/tlb.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index b3353e21f3b3..b320c0cc8996 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -139,14 +139,27 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+/*
+ * arch_tlb_mustflush specifies if tlb_flush is to be called even if the
+ * TLB range is empty (this can be the case for freeing page table pages
+ * if the arch does not adjust TLB range to cover them).
+ */
+#ifndef arch_tlb_mustflush
+#define arch_tlb_mustflush(tlb) false
+#endif
+
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
+	unsigned long start = tlb->start;
+	unsigned long end = tlb->end;
+
+	if (!(end || arch_tlb_mustflush(tlb)))
 		return;
 
 	tlb_flush(tlb);
-	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 	__tlb_reset_range(tlb);
+	if (end)
+		mmu_notifier_invalidate_range(tlb->mm, start, end);
 }
 
 static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-- 
2.17.0

WARNING: multiple messages have this Message-ID (diff)
From: Nicholas Piggin <npiggin@gmail.com>
To: linux-mm@kvack.org
Cc: Nicholas Piggin <npiggin@gmail.com>,
	linuxppc-dev@lists.ozlabs.org, linux-arch@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org
Subject: [RFC PATCH 3/4] mm: allow arch to have tlb_flush caled on an empty TLB range
Date: Thu, 26 Jul 2018 00:06:40 +1000	[thread overview]
Message-ID: <20180725140641.30372-4-npiggin@gmail.com> (raw)
Message-ID: <20180725140640.eADH5H5jaxNriU_7fwt8nZjTOmjzmwE0rZjZIeq3q1o@z> (raw)
In-Reply-To: <20180725140641.30372-1-npiggin@gmail.com>

powerpc wants to de-couple page table caching structure flushes
from TLB flushes, which will make it possible to have mmu_gather
with freed page table pages but no TLB range. These must be sent
to tlb_flush, so allow the arch to specify when mmu_gather with
empty ranges should have tlb_flush called.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 include/asm-generic/tlb.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index b3353e21f3b3..b320c0cc8996 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -139,14 +139,27 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+/*
+ * arch_tlb_mustflush specifies if tlb_flush is to be called even if the
+ * TLB range is empty (this can be the case for freeing page table pages
+ * if the arch does not adjust TLB range to cover them).
+ */
+#ifndef arch_tlb_mustflush
+#define arch_tlb_mustflush(tlb) false
+#endif
+
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
+	unsigned long start = tlb->start;
+	unsigned long end = tlb->end;
+
+	if (!(end || arch_tlb_mustflush(tlb)))
 		return;
 
 	tlb_flush(tlb);
-	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 	__tlb_reset_range(tlb);
+	if (end)
+		mmu_notifier_invalidate_range(tlb->mm, start, end);
 }
 
 static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-- 
2.17.0

WARNING: multiple messages have this Message-ID (diff)
From: npiggin@gmail.com (Nicholas Piggin)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC PATCH 3/4] mm: allow arch to have tlb_flush caled on an empty TLB range
Date: Thu, 26 Jul 2018 00:06:40 +1000	[thread overview]
Message-ID: <20180725140641.30372-4-npiggin@gmail.com> (raw)
In-Reply-To: <20180725140641.30372-1-npiggin@gmail.com>

powerpc wants to de-couple page table caching structure flushes
from TLB flushes, which will make it possible to have mmu_gather
with freed page table pages but no TLB range. These must be sent
to tlb_flush, so allow the arch to specify when mmu_gather with
empty ranges should have tlb_flush called.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 include/asm-generic/tlb.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index b3353e21f3b3..b320c0cc8996 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -139,14 +139,27 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	}
 }
 
+/*
+ * arch_tlb_mustflush specifies if tlb_flush is to be called even if the
+ * TLB range is empty (this can be the case for freeing page table pages
+ * if the arch does not adjust TLB range to cover them).
+ */
+#ifndef arch_tlb_mustflush
+#define arch_tlb_mustflush(tlb) false
+#endif
+
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
+	unsigned long start = tlb->start;
+	unsigned long end = tlb->end;
+
+	if (!(end || arch_tlb_mustflush(tlb)))
 		return;
 
 	tlb_flush(tlb);
-	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 	__tlb_reset_range(tlb);
+	if (end)
+		mmu_notifier_invalidate_range(tlb->mm, start, end);
 }
 
 static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-- 
2.17.0

  parent reply	other threads:[~2018-07-25 14:06 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-25 14:06 [RFC PATCH 0/4] mm: mmu_gather changes to support explicit paging Nicholas Piggin
2018-07-25 14:06 ` Nicholas Piggin
2018-07-25 14:06 ` Nicholas Piggin
2018-07-25 14:06 ` [RFC PATCH 1/4] mm: move tlb_table_flush to tlb_flush_mmu_free Nicholas Piggin
2018-07-25 14:06   ` Nicholas Piggin
2018-07-25 14:06   ` Nicholas Piggin
2018-07-25 14:06 ` [RFC PATCH 2/4] mm: mmu_notifier fix for tlb_end_vma Nicholas Piggin
2018-07-25 14:06   ` Nicholas Piggin
2018-07-25 14:06   ` Nicholas Piggin
2018-07-25 14:06 ` Nicholas Piggin [this message]
2018-07-25 14:06   ` [RFC PATCH 3/4] mm: allow arch to have tlb_flush caled on an empty TLB range Nicholas Piggin
2018-07-25 14:06   ` Nicholas Piggin
2018-07-25 14:06 ` [RFC PATCH 4/4] powerpc/64s/radix: optimise TLB flush with precise TLB ranges in mmu_gather Nicholas Piggin
2018-07-25 14:06   ` Nicholas Piggin
2018-07-25 14:06   ` Nicholas Piggin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180725140641.30372-4-npiggin@gmail.com \
    --to=npiggin@gmail.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.