From: Leon Romanovsky <leon@kernel.org>
To: Christoph Hellwig <hch@lst.de>,
Robin Murphy <robin.murphy@arm.com>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
Jason Gunthorpe <jgg@ziepe.ca>,
Chaitanya Kulkarni <chaitanyak@nvidia.com>
Cc: "Leon Romanovsky" <leonro@nvidia.com>,
"Jonathan Corbet" <corbet@lwn.net>,
"Jens Axboe" <axboe@kernel.dk>, "Keith Busch" <kbusch@kernel.org>,
"Sagi Grimberg" <sagi@grimberg.me>,
"Yishai Hadas" <yishaih@nvidia.com>,
"Shameer Kolothum" <shameerali.kolothum.thodi@huawei.com>,
"Kevin Tian" <kevin.tian@intel.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
iommu@lists.linux.dev, linux-nvme@lists.infradead.org,
kvm@vger.kernel.org, linux-mm@kvack.org,
"Bart Van Assche" <bvanassche@acm.org>,
"Damien Le Moal" <damien.lemoal@opensource.wdc.com>,
"Amir Goldstein" <amir73il@gmail.com>,
"josef@toxicpanda.com" <josef@toxicpanda.com>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
"daniel@iogearbox.net" <daniel@iogearbox.net>,
"Dan Williams" <dan.j.williams@intel.com>,
"jack@suse.com" <jack@suse.com>,
"Zhu Yanjun" <zyjzyj2000@gmail.com>
Subject: [RFC 07/16] RDMA/umem: Preallocate and cache IOVA for UMEM ODP
Date: Tue, 5 Mar 2024 12:15:17 +0200 [thread overview]
Message-ID: <47cc27fbaf9f4bd19edbcaac380bdd9684c5d12f.1709631413.git.leon@kernel.org> (raw)
In-Reply-To: <a77609c9c9a09214e38b04133e44eee67fe50ab0.1709631413.git.leon@kernel.org>
From: Leon Romanovsky <leonro@nvidia.com>
As a preparation to provide two step interface to map pages,
preallocate IOVA when UMEM is initialized.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
drivers/infiniband/core/umem_odp.c | 16 +++++++++++++++-
include/rdma/ib_umem_odp.h | 1 +
include/rdma/ib_verbs.h | 18 ++++++++++++++++++
3 files changed, 34 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index e9fa22d31c23..f69d1233dc82 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -50,6 +50,7 @@
static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
const struct mmu_interval_notifier_ops *ops)
{
+ struct ib_device *dev = umem_odp->umem.ibdev;
int ret;
umem_odp->umem.is_odp = 1;
@@ -87,15 +88,25 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
goto out_pfn_list;
}
+ umem_odp->iova.dev = dev->dma_device;
+ umem_odp->iova.size = end - start;
+ umem_odp->iova.dir = DMA_BIDIRECTIONAL;
+ ret = ib_dma_alloc_iova(dev, &umem_odp->iova);
+ if (ret)
+ goto out_dma_list;
+
+
ret = mmu_interval_notifier_insert(&umem_odp->notifier,
umem_odp->umem.owning_mm,
start, end - start, ops);
if (ret)
- goto out_dma_list;
+ goto out_free_iova;
}
return 0;
+out_free_iova:
+ ib_dma_free_iova(dev, &umem_odp->iova);
out_dma_list:
kvfree(umem_odp->dma_list);
out_pfn_list:
@@ -262,6 +273,8 @@ EXPORT_SYMBOL(ib_umem_odp_get);
void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
{
+ struct ib_device *dev = umem_odp->umem.ibdev;
+
/*
* Ensure that no more pages are mapped in the umem.
*
@@ -274,6 +287,7 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
ib_umem_end(umem_odp));
mutex_unlock(&umem_odp->umem_mutex);
mmu_interval_notifier_remove(&umem_odp->notifier);
+ ib_dma_free_iova(dev, &umem_odp->iova);
kvfree(umem_odp->dma_list);
kvfree(umem_odp->pfn_list);
}
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 0844c1d05ac6..bb2d7f2a5b04 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -23,6 +23,7 @@ struct ib_umem_odp {
* See ODP_READ_ALLOWED_BIT and ODP_WRITE_ALLOWED_BIT.
*/
dma_addr_t *dma_list;
+ struct dma_iova_attrs iova;
/*
* The umem_mutex protects the page_list and dma_list fields of an ODP
* umem, allowing only a single thread to map/unmap pages. The mutex
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b7b6b58dd348..e71fa19187cc 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4077,6 +4077,24 @@ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
return dma_mapping_error(dev->dma_device, dma_addr);
}
+static inline int ib_dma_alloc_iova(struct ib_device *dev,
+ struct dma_iova_attrs *iova)
+{
+ if (ib_uses_virt_dma(dev))
+ return 0;
+
+ return dma_alloc_iova(iova);
+}
+
+static inline void ib_dma_free_iova(struct ib_device *dev,
+ struct dma_iova_attrs *iova)
+{
+ if (ib_uses_virt_dma(dev))
+ return;
+
+ dma_free_iova(iova);
+}
+
/**
* ib_dma_map_single - Map a kernel virtual address to DMA address
* @dev: The device for which the dma_addr is to be created
--
2.44.0
WARNING: multiple messages have this Message-ID (diff)
From: Leon Romanovsky <leon@kernel.org>
To: Christoph Hellwig <hch@lst.de>,
Robin Murphy <robin.murphy@arm.com>,
Marek Szyprowski <m.szyprowski@samsung.com>,
Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
Jason Gunthorpe <jgg@ziepe.ca>,
Chaitanya Kulkarni <chaitanyak@nvidia.com>
Cc: "Leon Romanovsky" <leonro@nvidia.com>,
"Jonathan Corbet" <corbet@lwn.net>,
"Jens Axboe" <axboe@kernel.dk>, "Keith Busch" <kbusch@kernel.org>,
"Sagi Grimberg" <sagi@grimberg.me>,
"Yishai Hadas" <yishaih@nvidia.com>,
"Shameer Kolothum" <shameerali.kolothum.thodi@huawei.com>,
"Kevin Tian" <kevin.tian@intel.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-block@vger.kernel.org, linux-rdma@vger.kernel.org,
iommu@lists.linux.dev, linux-nvme@lists.infradead.org,
kvm@vger.kernel.org, linux-mm@kvack.org,
"Bart Van Assche" <bvanassche@acm.org>,
"Damien Le Moal" <damien.lemoal@opensource.wdc.com>,
"Amir Goldstein" <amir73il@gmail.com>,
"josef@toxicpanda.com" <josef@toxicpanda.com>,
"Martin K. Petersen" <martin.petersen@oracle.com>,
"daniel@iogearbox.net" <daniel@iogearbox.net>,
"Dan Williams" <dan.j.williams@intel.com>,
"jack@suse.com" <jack@suse.com>,
"Zhu Yanjun" <zyjzyj2000@gmail.com>
Subject: [RFC 07/16] RDMA/umem: Preallocate and cache IOVA for UMEM ODP
Date: Tue, 5 Mar 2024 12:22:08 +0200 [thread overview]
Message-ID: <47cc27fbaf9f4bd19edbcaac380bdd9684c5d12f.1709631413.git.leon@kernel.org> (raw)
Message-ID: <20240305102208.ql3iAsHqocj2Y3046jA9RR9hk0_b2gO9yTrHjv79CN0@z> (raw)
In-Reply-To: <cover.1709631800.git.leon@kernel.org>
From: Leon Romanovsky <leonro@nvidia.com>
As a preparation to provide two step interface to map pages,
preallocate IOVA when UMEM is initialized.
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
drivers/infiniband/core/umem_odp.c | 16 +++++++++++++++-
include/rdma/ib_umem_odp.h | 1 +
include/rdma/ib_verbs.h | 18 ++++++++++++++++++
3 files changed, 34 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index e9fa22d31c23..f69d1233dc82 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -50,6 +50,7 @@
static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
const struct mmu_interval_notifier_ops *ops)
{
+ struct ib_device *dev = umem_odp->umem.ibdev;
int ret;
umem_odp->umem.is_odp = 1;
@@ -87,15 +88,25 @@ static inline int ib_init_umem_odp(struct ib_umem_odp *umem_odp,
goto out_pfn_list;
}
+ umem_odp->iova.dev = dev->dma_device;
+ umem_odp->iova.size = end - start;
+ umem_odp->iova.dir = DMA_BIDIRECTIONAL;
+ ret = ib_dma_alloc_iova(dev, &umem_odp->iova);
+ if (ret)
+ goto out_dma_list;
+
+
ret = mmu_interval_notifier_insert(&umem_odp->notifier,
umem_odp->umem.owning_mm,
start, end - start, ops);
if (ret)
- goto out_dma_list;
+ goto out_free_iova;
}
return 0;
+out_free_iova:
+ ib_dma_free_iova(dev, &umem_odp->iova);
out_dma_list:
kvfree(umem_odp->dma_list);
out_pfn_list:
@@ -262,6 +273,8 @@ EXPORT_SYMBOL(ib_umem_odp_get);
void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
{
+ struct ib_device *dev = umem_odp->umem.ibdev;
+
/*
* Ensure that no more pages are mapped in the umem.
*
@@ -274,6 +287,7 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp)
ib_umem_end(umem_odp));
mutex_unlock(&umem_odp->umem_mutex);
mmu_interval_notifier_remove(&umem_odp->notifier);
+ ib_dma_free_iova(dev, &umem_odp->iova);
kvfree(umem_odp->dma_list);
kvfree(umem_odp->pfn_list);
}
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 0844c1d05ac6..bb2d7f2a5b04 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -23,6 +23,7 @@ struct ib_umem_odp {
* See ODP_READ_ALLOWED_BIT and ODP_WRITE_ALLOWED_BIT.
*/
dma_addr_t *dma_list;
+ struct dma_iova_attrs iova;
/*
* The umem_mutex protects the page_list and dma_list fields of an ODP
* umem, allowing only a single thread to map/unmap pages. The mutex
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b7b6b58dd348..e71fa19187cc 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4077,6 +4077,24 @@ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr)
return dma_mapping_error(dev->dma_device, dma_addr);
}
+static inline int ib_dma_alloc_iova(struct ib_device *dev,
+ struct dma_iova_attrs *iova)
+{
+ if (ib_uses_virt_dma(dev))
+ return 0;
+
+ return dma_alloc_iova(iova);
+}
+
+static inline void ib_dma_free_iova(struct ib_device *dev,
+ struct dma_iova_attrs *iova)
+{
+ if (ib_uses_virt_dma(dev))
+ return;
+
+ dma_free_iova(iova);
+}
+
/**
* ib_dma_map_single - Map a kernel virtual address to DMA address
* @dev: The device for which the dma_addr is to be created
--
2.44.0
next prev parent reply other threads:[~2024-03-05 10:16 UTC|newest]
Thread overview: 35+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-05 10:15 [RFC 00/16] Split IOMMU DMA mapping operation to two steps Leon Romanovsky
2024-03-05 10:15 ` [RFC 01/16] mm/hmm: let users to tag specific PFNs Leon Romanovsky
2024-03-05 10:15 ` [RFC 02/16] dma-mapping: provide an interface to allocate IOVA Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 03/16] dma-mapping: provide callbacks to link/unlink pages to specific IOVA Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 04/16] iommu/dma: Provide an interface to allow preallocate IOVA Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 05/16] iommu/dma: Prepare map/unmap page functions to receive IOVA Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 06/16] iommu/dma: Implement link/unlink page callbacks Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` Leon Romanovsky [this message]
2024-03-05 10:22 ` [RFC 07/16] RDMA/umem: Preallocate and cache IOVA for UMEM ODP Leon Romanovsky
2024-03-05 10:15 ` [RFC 08/16] RDMA/umem: Store ODP access mask information in PFN Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 09/16] RDMA/core: Separate DMA mapping to caching IOVA and page linkage Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 10/16] RDMA/umem: Prevent UMEM ODP creation with SWIOTLB Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 11/16] vfio/mlx5: Explicitly use number of pages instead of allocated length Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 12/16] vfio/mlx5: Rewrite create mkey flow to allow better code reuse Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 13/16] vfio/mlx5: Explicitly store page list Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 14/16] vfio/mlx5: Convert vfio to use DMA link API Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 15/16] block: add dma_link_range() based API Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:15 ` [RFC 16/16] nvme-pci: use blk_rq_dma_map() for NVMe SGL Leon Romanovsky
2024-03-05 10:22 ` Leon Romanovsky
2024-03-05 10:22 ` [RFC 01/16] mm/hmm: let users to tag specific PFNs Leon Romanovsky
2024-03-05 10:22 ` [RFC 00/16] Split IOMMU DMA mapping operation to two steps Leon Romanovsky
2024-03-05 10:23 ` Leon Romanovsky
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=47cc27fbaf9f4bd19edbcaac380bdd9684c5d12f.1709631413.git.leon@kernel.org \
--to=leon@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=alex.williamson@redhat.com \
--cc=amir73il@gmail.com \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=chaitanyak@nvidia.com \
--cc=corbet@lwn.net \
--cc=damien.lemoal@opensource.wdc.com \
--cc=dan.j.williams@intel.com \
--cc=daniel@iogearbox.net \
--cc=hch@lst.de \
--cc=iommu@lists.linux.dev \
--cc=jack@suse.com \
--cc=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=joro@8bytes.org \
--cc=josef@toxicpanda.com \
--cc=kbusch@kernel.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=leonro@nvidia.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvme@lists.infradead.org \
--cc=linux-rdma@vger.kernel.org \
--cc=m.szyprowski@samsung.com \
--cc=martin.petersen@oracle.com \
--cc=robin.murphy@arm.com \
--cc=sagi@grimberg.me \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=will@kernel.org \
--cc=yishaih@nvidia.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 read-only IMAP folder(s) and NNTP newsgroup(s).