linux-kernel - [PATCH 1/5] udmabuf: cancel mmap page fault, direct map it

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240801104512.4056860-2-link@vivo.com>
Date: Thu,  1 Aug 2024 18:45:05 +0800
From: Huan Yang <link@...o.com>
To: Gerd Hoffmann <kraxel@...hat.com>,
	Sumit Semwal <sumit.semwal@...aro.org>,
	Christian König <christian.koenig@....com>,
	dri-devel@...ts.freedesktop.org,
	linux-media@...r.kernel.org,
	linaro-mm-sig@...ts.linaro.org,
	linux-kernel@...r.kernel.org
Cc: opensource.kernel@...o.com,
	Huan Yang <link@...o.com>
Subject: [PATCH 1/5] udmabuf: cancel mmap page fault, direct map it

The current udmabuf mmap uses a page fault mechanism to populate the vma.

However, the current udmabuf has already obtained and pinned the folio
upon completion of the creation.This means that the physical memory has
already been acquired, rather than being accessed dynamically. The
current page fault method only saves some page table memory.

As a result, the page fault mechanism has lost its purpose as a demanding
page. Due to the fact that page fault requires trapping into kernel mode
and filling in when accessing the corresponding virtual address in mmap,
this means that user mode access to virtual addresses needs to trap into
kernel mode.

Therefore, when creating a large size udmabuf, this represents a
considerable overhead.

Therefore, the current patch removes the page fault method of mmap and
instead fills it directly when mmap is triggered.

Signed-off-by: Huan Yang <link@...o.com>
---
 drivers/dma-buf/udmabuf.c | 70 ++++++++++++++++++++++-----------------
 1 file changed, 39 insertions(+), 31 deletions(-)

diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 047c3cd2ceff..d69aeada7367 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -38,36 +38,39 @@ struct udmabuf_folio {
 	struct list_head list;
 };
 
-static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
-{
-	struct vm_area_struct *vma = vmf->vma;
-	struct udmabuf *ubuf = vma->vm_private_data;
-	pgoff_t pgoff = vmf->pgoff;
-	unsigned long pfn;
-
-	if (pgoff >= ubuf->pagecount)
-		return VM_FAULT_SIGBUS;
-
-	pfn = folio_pfn(ubuf->folios[pgoff]);
-	pfn += ubuf->offsets[pgoff] >> PAGE_SHIFT;
-
-	return vmf_insert_pfn(vma, vmf->address, pfn);
-}
-
-static const struct vm_operations_struct udmabuf_vm_ops = {
-	.fault = udmabuf_vm_fault,
-};
+static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
+				     enum dma_data_direction direction);
 
 static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
 {
 	struct udmabuf *ubuf = buf->priv;
+	struct sg_table *table = ubuf->sg;
+	unsigned long addr = vma->vm_start;
+	struct sg_page_iter piter;
+	int ret;
 
 	if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
 		return -EINVAL;
 
-	vma->vm_ops = &udmabuf_vm_ops;
-	vma->vm_private_data = ubuf;
-	vm_flags_set(vma, VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP);
+	if (!table) {
+		table = get_sg_table(NULL, buf, 0);
+		if (IS_ERR(table))
+			return PTR_ERR(table);
+		ubuf->sg = table;
+	}
+
+	for_each_sgtable_page(table, &piter, vma->vm_pgoff) {
+		struct page *page = sg_page_iter_page(&piter);
+
+		ret = remap_pfn_range(vma, addr, page_to_pfn(page), PAGE_SIZE,
+				      vma->vm_page_prot);
+		if (ret)
+			return ret;
+		addr += PAGE_SIZE;
+		if (addr >= vma->vm_end)
+			return 0;
+	}
+
 	return 0;
 }
 
@@ -126,6 +129,10 @@ static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
 		sg_set_folio(sgl, ubuf->folios[i], PAGE_SIZE,
 			     ubuf->offsets[i]);
 
+	// if dev is NULL, no need to sync.
+	if (!dev)
+		return sg;
+
 	ret = dma_map_sgtable(dev, sg, direction, 0);
 	if (ret < 0)
 		goto err_map;
@@ -206,20 +213,21 @@ static int begin_cpu_udmabuf(struct dma_buf *buf,
 {
 	struct udmabuf *ubuf = buf->priv;
 	struct device *dev = ubuf->device->this_device;
-	int ret = 0;
+	struct sg_table *sg;
 
-	if (!ubuf->sg) {
-		ubuf->sg = get_sg_table(dev, buf, direction);
-		if (IS_ERR(ubuf->sg)) {
-			ret = PTR_ERR(ubuf->sg);
-			ubuf->sg = NULL;
-		}
-	} else {
+	if (ubuf->sg) {
 		dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
 				    direction);
+		return 0;
 	}
 
-	return ret;
+	sg = get_sg_table(dev, buf, direction);
+	if (IS_ERR(sg))
+		return PTR_ERR(sg);
+
+	ubuf->sg = sg;
+
+	return 0;
 }
 
 static int end_cpu_udmabuf(struct dma_buf *buf,
-- 
2.45.2