Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Oak Zeng <oak.zeng@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [CI v3 06/26] iommu/dma: Implement link/unlink page callbacks
Date: Wed, 29 May 2024 20:47:12 -0400	[thread overview]
Message-ID: <20240530004732.84898-6-oak.zeng@intel.com> (raw)
In-Reply-To: <20240530004732.84898-1-oak.zeng@intel.com>

From: Leon Romanovsky <leonro@nvidia.com>

Add an implementation of link/unlink interface to perform in map/unmap
pages in fast patch for pre-allocated IOVA.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/iommu/dma-iommu.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 7be2999169bd..e90dc56e5ee4 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -1766,6 +1766,21 @@ static void iommu_dma_free_iova(struct device *dev, dma_addr_t iova,
 	__iommu_dma_free_iova(cookie, iova, size, &iotlb_gather);
 }
 
+static dma_addr_t iommu_dma_link_range(struct device *dev, struct page *page,
+				       unsigned long offset, dma_addr_t iova,
+				       size_t size, enum dma_data_direction dir,
+				       unsigned long attrs)
+{
+	return __iommu_dma_map_pages(dev, page, offset, iova, size, dir, attrs);
+}
+
+static void iommu_dma_unlink_range(struct device *dev, dma_addr_t addr,
+				   size_t size, enum dma_data_direction dir,
+				   unsigned long attrs)
+{
+	__iommu_dma_unmap_pages(dev, addr, size, dir, attrs, false);
+}
+
 static const struct dma_map_ops iommu_dma_ops = {
 	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED |
 				  DMA_F_CAN_SKIP_SYNC,
@@ -1792,6 +1807,8 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.max_mapping_size       = iommu_dma_max_mapping_size,
 	.alloc_iova		= iommu_dma_alloc_iova,
 	.free_iova		= iommu_dma_free_iova,
+	.link_range		= iommu_dma_link_range,
+	.unlink_range		= iommu_dma_unlink_range,
 };
 
 void iommu_setup_dma_ops(struct device *dev)
-- 
2.26.3


  parent reply	other threads:[~2024-05-30  0:33 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-30  0:47 [CI v3 01/26] mm/hmm: let users to tag specific PFNs Oak Zeng
2024-05-30  0:47 ` [CI v3 02/26] dma-mapping: provide an interface to allocate IOVA Oak Zeng
2024-05-30  0:47 ` [CI v3 03/26] dma-mapping: provide callbacks to link/unlink pages to specific IOVA Oak Zeng
2024-05-30  0:47 ` [CI v3 04/26] iommu/dma: Provide an interface to allow preallocate IOVA Oak Zeng
2024-05-30  0:47 ` [CI v3 05/26] iommu/dma: Prepare map/unmap page functions to receive IOVA Oak Zeng
2024-05-30  0:47 ` Oak Zeng [this message]
2024-05-30  0:47 ` [CI v3 07/26] drm: move xe_sg_segment_size to drm layer Oak Zeng
2024-05-30  0:47 ` [CI v3 08/26] drm: Move GPUVA_START/LAST to drm_gpuvm.h Oak Zeng
2024-05-30  0:47 ` [CI v3 09/26] drm/svm: add a mm field to drm_gpuvm struct Oak Zeng
2024-05-30  0:47 ` [CI v3 10/26] drm/svm: introduce drm_mem_region concept Oak Zeng
2024-05-30  0:47 ` [CI v3 11/26] drm/svm: introduce hmmptr and helper functions Oak Zeng
2024-05-30  0:47 ` [CI v3 12/26] drm/svm: Introduce helper to remap drm memory region Oak Zeng
2024-05-30  0:47 ` [CI v3 13/26] drm/svm: handle CPU page fault Oak Zeng
2024-05-30  0:47 ` [CI v3 14/26] drm/svm: Migrate a range of hmmptr to vram Oak Zeng
2024-05-30  0:47 ` [CI v3 15/26] drm/svm: Add DRM SVM documentation Oak Zeng
2024-05-30  0:47 ` [CI v3 16/26] drm/xe: s/xe_tile_migrate_engine/xe_tile_migrate_exec_queue Oak Zeng
2024-05-30  0:47 ` [CI v3 17/26] drm/xe: Add xe_vm_pgtable_update_op to xe_vma_ops Oak Zeng
2024-05-30  0:47 ` [CI v3 18/26] drm/xe: Convert multiple bind ops into single job Oak Zeng
2024-05-30  0:47 ` [CI v3 19/26] drm/xe: Update VM trace events Oak Zeng
2024-05-30  0:47 ` [CI v3 20/26] drm/xe: Update PT layer with better error handling Oak Zeng
2024-05-30  0:47 ` [CI v3 21/26] drm/xe: Retry BO allocation Oak Zeng
2024-05-30  0:47 ` [CI v3 22/26] drm/xe: Rework GPU page fault handling Oak Zeng
2024-05-30  0:47 ` [CI v3 23/26] drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_SYSTEM_ALLOCATOR flag Oak Zeng
2024-05-30  0:47 ` [CI v3 24/26] drm/xe: Add dma_addr res cursor Oak Zeng
2024-05-30  0:47 ` [CI v3 25/26] drm/xe: Use drm_mem_region for xe Oak Zeng
2024-05-30  0:47 ` [CI v3 26/26] drm/xe: use drm_hmmptr in xe Oak Zeng
2024-05-30  0:50 ` ✓ CI.Patch_applied: success for series starting with [CI,v3,01/26] mm/hmm: let users to tag specific PFNs Patchwork
2024-05-30  0:51 ` ✗ CI.checkpatch: warning " Patchwork
2024-05-30  0:51 ` ✗ CI.KUnit: failure " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2024-05-29  1:18 [CI v3 01/26] " Oak Zeng
2024-05-29  1:19 ` [CI v3 06/26] iommu/dma: Implement link/unlink page callbacks Oak Zeng

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=20240530004732.84898-6-oak.zeng@intel.com \
    --to=oak.zeng@intel.com \
    --cc=intel-xe@lists.freedesktop.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox