nvdimm.lists.linux.dev archive mirror
 help / color / mirror / Atom feed
From: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
To: linux-rdma@vger.kernel.org, leonro@nvidia.com, jgg@nvidia.com,
	zyjzyj2000@gmail.com
Cc: nvdimm@lists.linux.dev, linux-kernel@vger.kernel.org,
	rpearsonhpe@gmail.com, yangx.jy@fujitsu.com,
	lizhijian@fujitsu.com, y-goto@fujitsu.com,
	Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Subject: [RFC PATCH 4/7] RDMA/rxe: Add page invalidation support
Date: Wed,  7 Sep 2022 11:43:02 +0900	[thread overview]
Message-ID: <592ea028dff90a324af62623933b6c3c60a1dfde.1662461897.git.matsuda-daisuke@fujitsu.com> (raw)
In-Reply-To: <cover.1662461897.git.matsuda-daisuke@fujitsu.com>

On page invalidation, an MMU notifier callback is invoked to unmap DMA
addresses and update umem_odp->dma_list. The callback is registered when an
ODP-enabled MR is created.

Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
---
 drivers/infiniband/sw/rxe/Makefile  |  3 ++-
 drivers/infiniband/sw/rxe/rxe_odp.c | 34 +++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 1 deletion(-)
 create mode 100644 drivers/infiniband/sw/rxe/rxe_odp.c

diff --git a/drivers/infiniband/sw/rxe/Makefile b/drivers/infiniband/sw/rxe/Makefile
index 358f6b06aa64..924f4acb2816 100644
--- a/drivers/infiniband/sw/rxe/Makefile
+++ b/drivers/infiniband/sw/rxe/Makefile
@@ -22,4 +22,5 @@ rdma_rxe-y := \
 	rxe_mcast.o \
 	rxe_wq.o \
 	rxe_net.o \
-	rxe_hw_counters.o
+	rxe_hw_counters.o \
+	rxe_odp.o
diff --git a/drivers/infiniband/sw/rxe/rxe_odp.c b/drivers/infiniband/sw/rxe/rxe_odp.c
new file mode 100644
index 000000000000..0f702787a66e
--- /dev/null
+++ b/drivers/infiniband/sw/rxe/rxe_odp.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2022 Fujitsu Ltd. All rights reserved.
+ */
+
+#include <rdma/ib_umem_odp.h>
+
+bool rxe_ib_invalidate_range(struct mmu_interval_notifier *mni,
+			     const struct mmu_notifier_range *range,
+			     unsigned long cur_seq)
+{
+	struct ib_umem_odp *umem_odp =
+		container_of(mni, struct ib_umem_odp, notifier);
+	unsigned long start;
+	unsigned long end;
+
+	if (!mmu_notifier_range_blockable(range))
+		return false;
+
+	mutex_lock(&umem_odp->umem_mutex);
+	mmu_interval_set_seq(mni, cur_seq);
+
+	start = max_t(u64, ib_umem_start(umem_odp), range->start);
+	end = min_t(u64, ib_umem_end(umem_odp), range->end);
+
+	ib_umem_odp_unmap_dma_pages(umem_odp, start, end);
+
+	mutex_unlock(&umem_odp->umem_mutex);
+	return true;
+}
+
+const struct mmu_interval_notifier_ops rxe_mn_ops = {
+	.invalidate = rxe_ib_invalidate_range,
+};
-- 
2.31.1


  parent reply	other threads:[~2022-09-07  2:44 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-07  2:42 [RFC PATCH 0/7] RDMA/rxe: On-Demand Paging on SoftRoCE Daisuke Matsuda
2022-09-07  2:42 ` [RFC PATCH 1/7] IB/mlx5: Change ib_umem_odp_map_dma_single_page() to retain umem_mutex Daisuke Matsuda
2022-09-07  2:43 ` [RFC PATCH 2/7] RDMA/rxe: Convert the triple tasklets to workqueues Daisuke Matsuda
2022-09-09 19:39   ` Bob Pearson
2022-09-12  8:27     ` matsuda-daisuke
2022-09-11  7:10   ` Yanjun Zhu
2022-09-11 15:08     ` Bart Van Assche
2022-09-12  7:58       ` matsuda-daisuke
2022-09-12  8:29         ` Yanjun Zhu
2022-09-12 19:52         ` Bob Pearson
2022-09-28  6:40           ` matsuda-daisuke
2022-09-12  8:25       ` Yanjun Zhu
2022-09-07  2:43 ` [RFC PATCH 3/7] RDMA/rxe: Cleanup code for responder Atomic operations Daisuke Matsuda
2022-09-07  2:43 ` Daisuke Matsuda [this message]
2022-09-07  2:43 ` [RFC PATCH 5/7] RDMA/rxe: Allow registering MRs for On-Demand Paging Daisuke Matsuda
2022-09-08 16:57   ` Haris Iqbal
2022-09-09  0:55     ` matsuda-daisuke
2022-09-07  2:43 ` [RFC PATCH 6/7] RDMA/rxe: Add support for Send/Recv/Write/Read operations with ODP Daisuke Matsuda
2022-09-08  8:29   ` Leon Romanovsky
2022-09-09  2:45     ` matsuda-daisuke
2022-09-07  2:43 ` [RFC PATCH 7/7] RDMA/rxe: Add support for the traditional Atomic " Daisuke Matsuda
2022-09-08  8:40 ` [RFC PATCH 0/7] RDMA/rxe: On-Demand Paging on SoftRoCE Zhu Yanjun
2022-09-08 10:25   ` matsuda-daisuke
2022-09-09  3:07 ` Li Zhijian
2022-09-12  9:21   ` matsuda-daisuke

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=592ea028dff90a324af62623933b6c3c60a1dfde.1662461897.git.matsuda-daisuke@fujitsu.com \
    --to=matsuda-daisuke@fujitsu.com \
    --cc=jgg@nvidia.com \
    --cc=leonro@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=lizhijian@fujitsu.com \
    --cc=nvdimm@lists.linux.dev \
    --cc=rpearsonhpe@gmail.com \
    --cc=y-goto@fujitsu.com \
    --cc=yangx.jy@fujitsu.com \
    --cc=zyjzyj2000@gmail.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).