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;
From:   Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
To:     linux-rdma@vger.kernel.org, leonro@nvidia.com, jgg@nvidia.com,
        zyjzyj2000@gmail.com
Cc:     linux-kernel@vger.kernel.org, rpearsonhpe@gmail.com,
        yangx.jy@fujitsu.com, lizhijian@fujitsu.com,
        Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Subject: [PATCH for-next v4 5/8] RDMA/rxe: Add page invalidation support
Date:   Wed, 19 Apr 2023 14:51:57 +0900
Message-Id: <6746c75a554639ce5473c03c80d7582cca6bf2eb.1681882651.git.matsuda-daisuke@fujitsu.com>
In-Reply-To: <cover.1681882651.git.matsuda-daisuke@fujitsu.com>
References: <cover.1681882651.git.matsuda-daisuke@fujitsu.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

On page invalidation, an MMU notifier callback is invoked to unmap DMA
addresses and update the driver page table(umem_odp->dma_list). It also
set the corresponding entries in MR xarray to NULL to prevent any access.
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  |  2 ++
 drivers/infiniband/sw/rxe/rxe_odp.c | 56 +++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+)
 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 5395a581f4bb..93134f1d1d0c 100644
--- a/drivers/infiniband/sw/rxe/Makefile
+++ b/drivers/infiniband/sw/rxe/Makefile
@@ -23,3 +23,5 @@ rdma_rxe-y := \
 	rxe_task.o \
 	rxe_net.o \
 	rxe_hw_counters.o
+
+rdma_rxe-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += 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..b69b25e0fef6
--- /dev/null
+++ b/drivers/infiniband/sw/rxe/rxe_odp.c
@@ -0,0 +1,56 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2022-2023 Fujitsu Ltd. All rights reserved.
+ */
+
+#include <linux/hmm.h>
+
+#include <rdma/ib_umem_odp.h>
+
+#include "rxe.h"
+
+static void rxe_mr_unset_xarray(struct rxe_mr *mr, unsigned long start,
+				unsigned long end)
+{
+	unsigned long lower, upper, idx;
+
+	lower = rxe_mr_iova_to_index(mr, start);
+	upper = rxe_mr_iova_to_index(mr, end);
+
+	/* make elements in xarray NULL */
+	spin_lock(&mr->page_list.xa_lock);
+	for (idx = lower; idx <= upper; idx++)
+		__xa_erase(&mr->page_list, idx);
+	spin_unlock(&mr->page_list.xa_lock);
+}
+
+static 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);
+	struct rxe_mr *mr = umem_odp->private;
+	unsigned long start, 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);
+
+	rxe_mr_unset_xarray(mr, start, end);
+
+	/* update umem_odp->dma_list */
+	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,
+};
-- 
2.39.1