[PATCH 1/3] habanalabs: restructure hl_mmap

[PATCH 1/3] habanalabs: restructure hl_mmap

[Oded Gabbay]

Arrange the hl_mmap code to be more structured and expandable for the
future. Add better defines that describe our usage of the vm_pgoff.

Note that I shamelessly took the code and defines from the amdkfd driver
(my previous driver).

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_buffer.c |  2 +-
 drivers/misc/habanalabs/common/device.c         |  8 ++++++--
 drivers/misc/habanalabs/common/habanalabs.h     | 14 +++++++++++++-
 3 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index e4bbe6a8e00f..68dfbafe3354 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -183,7 +183,7 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
 	 * idr is 32-bit so we can safely OR it with a mask that is above
 	 * 32 bit
 	 */
-	*handle = cb->id | HL_MMAP_CB_MASK;
+	*handle = cb->id | HL_MMAP_TYPE_CB;
 	*handle <<= PAGE_SHIFT;
 
 	hl_debugfs_add_cb(cb);
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 6e916cc22a4c..aa7fa9e94651 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -123,9 +123,13 @@ static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
 static int hl_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct hl_fpriv *hpriv = filp->private_data;
+	unsigned long vm_pgoff;
 
-	if ((vma->vm_pgoff & HL_MMAP_CB_MASK) == HL_MMAP_CB_MASK) {
-		vma->vm_pgoff ^= HL_MMAP_CB_MASK;
+	vm_pgoff = vma->vm_pgoff;
+	vma->vm_pgoff = HL_MMAP_OFFSET_VALUE_GET(vm_pgoff);
+
+	switch (vm_pgoff & HL_MMAP_TYPE_MASK) {
+	case HL_MMAP_TYPE_CB:
 		return hl_cb_mmap(hpriv, vma);
 	}
 
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 6912f88a4b01..cdb7a672ed30 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -22,7 +22,19 @@
 
 #define HL_NAME				"habanalabs"
 
-#define HL_MMAP_CB_MASK			(0x8000000000000000ull >> PAGE_SHIFT)
+/* Use upper bits of mmap offset to store habana driver specific information.
+ * bits[63:62] - Encode mmap type
+ * bits[45:0]  - mmap offset value
+ *
+ * NOTE: struct vm_area_struct.vm_pgoff uses offset in pages. Hence, these
+ *  defines are w.r.t to PAGE_SIZE
+ */
+#define HL_MMAP_TYPE_SHIFT		(62 - PAGE_SHIFT)
+#define HL_MMAP_TYPE_MASK		(0x3ull << HL_MMAP_TYPE_SHIFT)
+#define HL_MMAP_TYPE_CB			(0x2ull << HL_MMAP_TYPE_SHIFT)
+
+#define HL_MMAP_OFFSET_VALUE_MASK	(0x3FFFFFFFFFFFull >> PAGE_SHIFT)
+#define HL_MMAP_OFFSET_VALUE_GET(off)	(off & HL_MMAP_OFFSET_VALUE_MASK)
 
 #define HL_PENDING_RESET_PER_SEC	30
 
-- 
2.17.1

[PATCH 2/3] habanalabs: clear vm_pgoff before doing the mmap

[Oded Gabbay]

The driver use vm_pgoff to hold the CB idr handle. Before we actually call
the mapping function, we need to clear the handle so there won't be any
garbage left in vm_pgoff.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_buffer.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 68dfbafe3354..6563e4dfe7b6 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -304,7 +304,11 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
 	u32 handle, user_cb_size;
 	int rc;
 
+	/* We use the page offset to hold the idr and thus we need to clear
+	 * it before doing the mmap itself
+	 */
 	handle = vma->vm_pgoff;
+	vma->vm_pgoff = 0;
 
 	/* reference was taken here */
 	cb = hl_cb_get(hdev, &hpriv->cb_mgr, handle);
-- 
2.17.1

[PATCH 3/3] habanalabs: make use of dma_mmap_coherent

[Oded Gabbay]

From: Hillf Danton <hdanton@sina.com>

Add dma_mmap_coherent() for goya and gaudi to match their use of
dma_alloc_coherent(), see the Link tag for why.

Link: https://lore.kernel.org/lkml/20200609091727.GA23814@lst.de/
Cc: Christoph Hellwig <hch@lst.de>
Cc: Zhang Li <li.zhang@bitmain.com>
Cc: Ding Z Nan <oshack@hotmail.com>
Signed-off-by: Hillf Danton <hdanton@sina.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/misc/habanalabs/common/command_buffer.c | 9 ++-------
 drivers/misc/habanalabs/common/habanalabs.h     | 2 +-
 drivers/misc/habanalabs/gaudi/gaudi.c           | 7 +++----
 drivers/misc/habanalabs/goya/goya.c             | 7 +++----
 4 files changed, 9 insertions(+), 16 deletions(-)

diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 6563e4dfe7b6..ba63cee74050 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -300,7 +300,6 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
 {
 	struct hl_device *hdev = hpriv->hdev;
 	struct hl_cb *cb;
-	phys_addr_t address;
 	u32 handle, user_cb_size;
 	int rc;
 
@@ -360,12 +359,8 @@ int hl_cb_mmap(struct hl_fpriv *hpriv, struct vm_area_struct *vma)
 
 	vma->vm_private_data = cb;
 
-	/* Calculate address for CB */
-	address = virt_to_phys((void *) (uintptr_t) cb->kernel_address);
-
-	rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address,
-					address, cb->size);
-
+	rc = hdev->asic_funcs->cb_mmap(hdev, vma, (void *) cb->kernel_address,
+					cb->bus_address, cb->size);
 	if (rc) {
 		spin_lock(&cb->lock);
 		cb->mmap = false;
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index cdb7a672ed30..6ea8ae616cf4 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -710,7 +710,7 @@ struct hl_asic_funcs {
 	int (*suspend)(struct hl_device *hdev);
 	int (*resume)(struct hl_device *hdev);
 	int (*cb_mmap)(struct hl_device *hdev, struct vm_area_struct *vma,
-			u64 kaddress, phys_addr_t paddress, u32 size);
+			void *cpu_addr, dma_addr_t dma_addr, size_t size);
 	void (*ring_doorbell)(struct hl_device *hdev, u32 hw_queue_id, u32 pi);
 	void (*pqe_write)(struct hl_device *hdev, __le64 *pqe,
 			struct hl_bd *bd);
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 084019788e11..bc7e7e3ba3a8 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -3091,17 +3091,16 @@ static int gaudi_resume(struct hl_device *hdev)
 }
 
 static int gaudi_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
-		u64 kaddress, phys_addr_t paddress, u32 size)
+			void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
 	int rc;
 
 	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
 			VM_DONTCOPY | VM_NORESERVE;
 
-	rc = remap_pfn_range(vma, vma->vm_start, paddress >> PAGE_SHIFT,
-				size, vma->vm_page_prot);
+	rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size);
 	if (rc)
-		dev_err(hdev->dev, "remap_pfn_range error %d", rc);
+		dev_err(hdev->dev, "dma_mmap_coherent error %d", rc);
 
 	return rc;
 }
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 88847eb1b472..94b7958ba5fb 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -2661,17 +2661,16 @@ int goya_resume(struct hl_device *hdev)
 }
 
 static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
-		u64 kaddress, phys_addr_t paddress, u32 size)
+			void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
 	int rc;
 
 	vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP |
 			VM_DONTCOPY | VM_NORESERVE;
 
-	rc = remap_pfn_range(vma, vma->vm_start, paddress >> PAGE_SHIFT,
-				size, vma->vm_page_prot);
+	rc = dma_mmap_coherent(hdev->dev, vma, cpu_addr, dma_addr, size);
 	if (rc)
-		dev_err(hdev->dev, "remap_pfn_range error %d", rc);
+		dev_err(hdev->dev, "dma_mmap_coherent error %d", rc);
 
 	return rc;
 }
-- 
2.17.1