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 05/43] iommu/dma: Prepare map/unmap page functions to receive IOVA
Date: Tue, 11 Jun 2024 22:25:27 -0400	[thread overview]
Message-ID: <20240612022605.385062-5-oak.zeng@intel.com> (raw)
In-Reply-To: <20240612022605.385062-1-oak.zeng@intel.com>

From: Leon Romanovsky <leonro@nvidia.com>

Extend the existing map_page/unmap_page function implementations to get
preallocated IOVA. In such case, the IOVA allocation needs to be
skipped, but rest of the code stays the same.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/iommu/dma-iommu.c | 68 ++++++++++++++++++++++++++-------------
 1 file changed, 45 insertions(+), 23 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 9ce8298047f5..dbef2581a98c 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -822,7 +822,7 @@ static void __iommu_dma_free_iova(struct iommu_dma_cookie *cookie,
 }
 
 static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
-		size_t size)
+			      size_t size, bool free_iova)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -841,17 +841,19 @@ static void __iommu_dma_unmap(struct device *dev, dma_addr_t dma_addr,
 
 	if (!iotlb_gather.queued)
 		iommu_iotlb_sync(domain, &iotlb_gather);
-	__iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather);
+	if (free_iova)
+		__iommu_dma_free_iova(cookie, dma_addr, size, &iotlb_gather);
 }
 
 static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
-		size_t size, int prot, u64 dma_mask)
+				  dma_addr_t iova, size_t size, int prot,
+				  u64 dma_mask)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	size_t iova_off = iova_offset(iovad, phys);
-	dma_addr_t iova;
+	bool no_iova = !iova;
 
 	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
 	    iommu_deferred_attach(dev, domain))
@@ -864,12 +866,14 @@ static dma_addr_t __iommu_dma_map(struct device *dev, phys_addr_t phys,
 
 	size = iova_align(iovad, size + iova_off);
 
-	iova = __iommu_dma_alloc_iova(domain, size, dma_mask, dev);
+	if (no_iova)
+		iova = __iommu_dma_alloc_iova(domain, size, dma_mask, dev);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
 	if (iommu_map(domain, iova, phys - iova_off, size, prot, GFP_ATOMIC)) {
-		__iommu_dma_free_iova(cookie, iova, size, NULL);
+		if (no_iova)
+			__iommu_dma_free_iova(cookie, iova, size, NULL);
 		return DMA_MAPPING_ERROR;
 	}
 	return iova + iova_off;
@@ -1034,7 +1038,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 	return vaddr;
 
 out_unmap:
-	__iommu_dma_unmap(dev, *dma_handle, size);
+	__iommu_dma_unmap(dev, *dma_handle, size, true);
 	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
 	return NULL;
 }
@@ -1063,7 +1067,7 @@ static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
 {
 	struct dma_sgt_handle *sh = sgt_handle(sgt);
 
-	__iommu_dma_unmap(dev, sgt->sgl->dma_address, size);
+	__iommu_dma_unmap(dev, sgt->sgl->dma_address, size, true);
 	__iommu_dma_free_pages(sh->pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
 	sg_free_table(&sh->sgt);
 	kfree(sh);
@@ -1134,9 +1138,11 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
-static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+static dma_addr_t __iommu_dma_map_pages(struct device *dev, struct page *page,
+					unsigned long offset, dma_addr_t iova,
+					size_t size,
+					enum dma_data_direction dir,
+					unsigned long attrs)
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
@@ -1144,7 +1150,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
-	dma_addr_t iova, dma_mask = dma_get_mask(dev);
+	dma_addr_t addr, dma_mask = dma_get_mask(dev);
 
 	/*
 	 * If both the physical buffer start address and size are
@@ -1188,14 +1194,23 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		arch_sync_dma_for_device(phys, size, dir);
 
-	iova = __iommu_dma_map(dev, phys, size, prot, dma_mask);
-	if (iova == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys))
+	addr = __iommu_dma_map(dev, phys, iova, size, prot, dma_mask);
+	if (addr == DMA_MAPPING_ERROR && is_swiotlb_buffer(dev, phys))
 		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
-	return iova;
+	return addr;
 }
 
-static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
+static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir,
+				     unsigned long attrs)
+{
+	return __iommu_dma_map_pages(dev, page, offset, 0, size, dir, attrs);
+}
+
+static void __iommu_dma_unmap_pages(struct device *dev, dma_addr_t dma_handle,
+				    size_t size, enum dma_data_direction dir,
+				    unsigned long attrs, bool free_iova)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	phys_addr_t phys;
@@ -1207,12 +1222,19 @@ static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && !dev_is_dma_coherent(dev))
 		arch_sync_dma_for_cpu(phys, size, dir);
 
-	__iommu_dma_unmap(dev, dma_handle, size);
+	__iommu_dma_unmap(dev, dma_handle, size, free_iova);
 
 	if (unlikely(is_swiotlb_buffer(dev, phys)))
 		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
 }
 
+static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+				 size_t size, enum dma_data_direction dir,
+				 unsigned long attrs)
+{
+	__iommu_dma_unmap_pages(dev, dma_handle, size, dir, attrs, true);
+}
+
 /*
  * Prepare a successfully-mapped scatterlist to give back to the caller.
  *
@@ -1515,13 +1537,13 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	}
 
 	if (end)
-		__iommu_dma_unmap(dev, start, end - start);
+		__iommu_dma_unmap(dev, start, end - start, true);
 }
 
 static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	return __iommu_dma_map(dev, phys, size,
+	return __iommu_dma_map(dev, phys, 0, size,
 			dma_info_to_prot(dir, false, attrs) | IOMMU_MMIO,
 			dma_get_mask(dev));
 }
@@ -1529,7 +1551,7 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	__iommu_dma_unmap(dev, handle, size);
+	__iommu_dma_unmap(dev, handle, size, true);
 }
 
 static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
@@ -1566,7 +1588,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t handle, unsigned long attrs)
 {
-	__iommu_dma_unmap(dev, handle, size);
+	__iommu_dma_unmap(dev, handle, size, true);
 	__iommu_dma_free(dev, size, cpu_addr);
 }
 
@@ -1632,7 +1654,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	if (!cpu_addr)
 		return NULL;
 
-	*handle = __iommu_dma_map(dev, page_to_phys(page), size, ioprot,
+	*handle = __iommu_dma_map(dev, page_to_phys(page), 0, size, ioprot,
 			dev->coherent_dma_mask);
 	if (*handle == DMA_MAPPING_ERROR) {
 		__iommu_dma_free(dev, size, cpu_addr);
-- 
2.26.3


  parent reply	other threads:[~2024-06-12  2:16 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-12  2:25 [CI 01/43] mm/hmm: let users to tag specific PFNs Oak Zeng
2024-06-12  2:25 ` [CI 02/43] dma-mapping: provide an interface to allocate IOVA Oak Zeng
2024-06-12  2:25 ` [CI 03/43] dma-mapping: provide callbacks to link/unlink pages to specific IOVA Oak Zeng
2024-06-12  2:25 ` [CI 04/43] iommu/dma: Provide an interface to allow preallocate IOVA Oak Zeng
2024-06-12  2:25 ` Oak Zeng [this message]
2024-06-12  2:25 ` [CI 06/43] iommu/dma: Implement link/unlink page callbacks Oak Zeng
2024-06-12  2:25 ` [CI 07/43] drm: move xe_sg_segment_size to drm layer Oak Zeng
2024-06-12  2:25 ` [CI 08/43] drm: Move GPUVA_START/LAST to drm_gpuvm.h Oak Zeng
2024-06-12  2:25 ` [CI 09/43] drm/svm: Mark drm_gpuvm to participate SVM Oak Zeng
2024-06-12  2:25 ` [CI 10/43] drm/svm: introduce drm_mem_region concept Oak Zeng
2024-06-12  2:25 ` [CI 11/43] drm/svm: introduce hmmptr and helper functions Oak Zeng
2024-06-12  2:25 ` [CI 12/43] drm/svm: Introduce helper to remap drm memory region Oak Zeng
2024-06-12  2:25 ` [CI 13/43] drm/svm: handle CPU page fault Oak Zeng
2024-06-12  2:25 ` [CI 14/43] drm/svm: Migrate a range of hmmptr to vram Oak Zeng
2024-06-12  2:25 ` [CI 15/43] drm/svm: Add DRM SVM documentation Oak Zeng
2024-06-12  2:25 ` [CI 16/43] drm/xe: s/xe_tile_migrate_engine/xe_tile_migrate_exec_queue Oak Zeng
2024-06-12  2:25 ` [CI 17/43] drm/xe: Add xe_vm_pgtable_update_op to xe_vma_ops Oak Zeng
2024-06-12  2:25 ` [CI 18/43] drm/xe: Convert multiple bind ops into single job Oak Zeng
2024-06-12  2:25 ` [CI 19/43] drm/xe: Update VM trace events Oak Zeng
2024-06-12  2:25 ` [CI 20/43] drm/xe: Update PT layer with better error handling Oak Zeng
2024-06-12  2:25 ` [CI 21/43] drm/xe: Retry BO allocation Oak Zeng
2024-06-12  2:25 ` [CI 22/43] drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_SYSTEM_ALLOCATOR flag Oak Zeng
2024-06-12  2:25 ` [CI 23/43] drm/xe: Add a helper to calculate userptr end address Oak Zeng
2024-06-12  2:25 ` [CI 24/43] drm/xe: Add dma_addr res cursor Oak Zeng
2024-06-12  2:25 ` [CI 25/43] drm/xe: Use drm_mem_region for xe Oak Zeng
2024-06-12  2:25 ` [CI 26/43] drm/xe: use drm_hmmptr in xe Oak Zeng
2024-06-12  2:25 ` [CI 27/43] drm/xe: Moving to range based vma invalidation Oak Zeng
2024-06-12  2:25 ` [CI 28/43] drm/xe: Support range based page table update Oak Zeng
2024-06-12  2:25 ` [CI 29/43] drm/xe/uapi: Add DRM_XE_VM_CREATE_FLAG_PARTICIPATE_SVM flag Oak Zeng
2024-06-12  2:25 ` [CI 30/43] drm/xe/svm: Create userptr if page fault occurs on system_allocator VMA Oak Zeng
2024-06-12  2:25 ` [CI 31/43] drm/xe/svm: Add faulted userptr VMA garbage collector Oak Zeng
2024-06-12  2:25 ` [CI 32/43] drm/xe: Introduce helper to get tile from memory region Oak Zeng
2024-06-12  2:25 ` [CI 33/43] drm/xe/svm: implement functions to allocate and free device memory Oak Zeng
2024-06-12  2:25 ` [CI 34/43] drm/xe/svm: Get drm device from drm memory region Oak Zeng
2024-06-12  2:25 ` [CI 35/43] drm/xe/svm: Get page map owner of a " Oak Zeng
2024-06-12  2:25 ` [CI 36/43] drm/xe/svm: Add migrate layer functions for SVM support Oak Zeng
2024-06-12  2:25 ` [CI 37/43] drm/xe/svm: introduce svm migration function Oak Zeng
2024-06-12  2:26 ` [CI 38/43] drm/xe/svm: Register xe memory region to drm layer Oak Zeng
2024-06-12  2:26 ` [CI 39/43] drm/xe/svm: Introduce DRM_XE_SVM kernel config Oak Zeng
2024-06-12  2:26 ` [CI 40/43] drm/xe/svm: Migration from sram to vram for system allocator Oak Zeng
2024-06-12  2:26 ` [CI 41/43] drm/xe/svm: Determine a vma is backed by device memory Oak Zeng
2024-06-12  2:26 ` [CI 42/43] drm/xe/svm: Introduce hmm_pfn array based resource cursor Oak Zeng
2024-06-12  2:26 ` [CI 43/43] drm/xe: Enable system allocator uAPI Oak Zeng
2024-06-12  3:14 ` ✓ CI.Patch_applied: success for series starting with [CI,01/43] mm/hmm: let users to tag specific PFNs Patchwork
2024-06-12  3:15 ` ✗ CI.checkpatch: warning " Patchwork
2024-06-12  3:16 ` ✗ CI.KUnit: failure " Patchwork

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=20240612022605.385062-5-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