[PATCH v3 9/9] drm/amdgpu/gem: Return Handle to MMIO_REMAP Singleton in GEM_CREATE

[Srinivasan Shanmugam]

Enable userspace to obtain a handle to the kernel-owned MMIO_REMAP
singleton when AMDGPU_GEM_DOMAIN_MMIO_REMAP is requested via
amdgpu_gem_create_ioctl().

Validate the fixed 4K constraint: if PAGE_SIZE > AMDGPU_GPU_PAGE_SIZE
return -EINVAL; when provided, size and alignment must equal
AMDGPU_GPU_PAGE_SIZE.

If the singleton BO is not available, return -ENODEV.

v2:
- Drop READ_ONCE() on adev->mmio_remap.bo (use a plain pointer load).
  The pointer is set `bo = adev->mmio_remap.bo;` ie., The pointer is
  written once during init and not changed while IOCTLs run. There’s no
  concurrent writer in this execution path, so a normal read is safe.
  (Alex)

Cc: Christian König <christian.koenig at amd.com>
Suggested-by: Alex Deucher <alexander.deucher at amd.com>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 59 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 18 +++-----
 2 files changed, 66 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index d3c369742124..465f9d4a79d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -424,6 +424,38 @@ const struct drm_gem_object_funcs amdgpu_gem_object_funcs = {
 	.vm_ops = &amdgpu_gem_vm_ops,
 };
 
+/**
+ * amdgpu_gem_get_mmio_remap_handle - Create a GEM handle for the MMIO_REMAP BO
+ * @file_priv: DRM file corresponding to the calling process
+ * @adev: amdgpu device
+ * @handle: returned userspace GEM handle (out)
+ *
+ * Creates a GEM handle to the kernel-owned singleton MMIO_REMAP buffer object
+ * (adev->rmmio_remap.bo). The BO is expected to be allocated during TTM init
+ * when the hardware exposes a remap base and PAGE_SIZE <= 4K.
+ *
+ * drm_gem_handle_create() acquires the handle reference, which will be dropped
+ * by GEM_CLOSE in userspace.
+ *
+ * * Return:
+ * * 0 on success
+ * * -ENODEV if the MMIO_REMAP BO is not available
+ * * A negative errno from drm_gem_handle_create() on failure
+ *
+ */
+static int amdgpu_gem_get_mmio_remap_handle(struct drm_file *file_priv,
+					    struct amdgpu_device *adev,
+					    u32 *handle)
+{
+	struct amdgpu_bo *bo = adev->rmmio_remap.bo;
+
+	if (!bo)
+		return -ENODEV;
+
+	/* drm_gem_handle_create() gets the ref; GEM_CLOSE drops it */
+	return drm_gem_handle_create(file_priv, &bo->tbo.base, handle);
+}
+
 /*
  * GEM ioctls.
  */
@@ -468,6 +500,33 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	if (args->in.domains & AMDGPU_GEM_DOMAIN_MMIO_REMAP)
 		return -EINVAL;
 
+	/*
+	 * === MMIO remap (HDP flush) fast-path ===
+	 * If userspace asks for the MMIO_REMAP domain, don't allocate a new BO.
+	 * Return a handle to the singleton BO created at ttm init.
+	 */
+	if (args->in.domains & AMDGPU_GEM_DOMAIN_MMIO_REMAP) {
+		/*
+		 * The MMIO remap page is fixed 4K on the GPU side. Do not
+		 * allow use if the system PAGE_SIZE is larger than the GPU
+		 * page size.
+		 */
+		if (PAGE_SIZE > AMDGPU_GPU_PAGE_SIZE)
+			return -EINVAL;
+
+		/* Enforce fixed size/alignment when provided by userspace. */
+		if (size && size != AMDGPU_GPU_PAGE_SIZE)
+			return -EINVAL;
+		if (args->in.alignment && args->in.alignment != AMDGPU_GPU_PAGE_SIZE)
+			return -EINVAL;
+
+		r = amdgpu_gem_get_mmio_remap_handle(filp, adev, &handle);
+		if (r)
+			return r;
+		args->out.handle = handle;
+		return 0;
+	}
+
 	/* create a gem object to contain this object in */
 	if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
 	    AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 0e301cab74e0..14af9b0b8673 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1854,14 +1854,13 @@ static void amdgpu_ttm_pools_fini(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_ttm_mmio_remap_bo_init - allocate the singleton 4K MMIO_REMAP BO
+ * amdgpu_ttm_mmio_remap_bo_init - Allocate the singleton 4K MMIO_REMAP BO
  * @adev: amdgpu device
  *
  * Allocates a one-page (4K) GEM BO in AMDGPU_GEM_DOMAIN_MMIO_REMAP when the
  * hardware exposes a remap base (adev->rmmio_remap.bus_addr) and the host
  * PAGE_SIZE is <= AMDGPU_GPU_PAGE_SIZE (4K). The BO is created as a regular
- * GEM object (amdgpu_bo_create), then reserved and kmap’ed once to exercise
- * the io-mem setup path. If prerequisites are not met, this is a no-op.
+ * GEM object (amdgpu_bo_create).
  *
  * Return:
  *  * 0 on success or intentional skip (feature not present/unsupported)
@@ -1871,16 +1870,13 @@ static int amdgpu_ttm_mmio_remap_bo_init(struct amdgpu_device *adev)
 {
 	int r;
 	struct amdgpu_bo_param bp = { 0 };
-	void *kptr;
 
-	/* Skip if HW doesn’t expose remap or system PAGE > GPU 4K */
+	/* Skip if HW doesn’t expose remap or
+	 * Hardware remap page is fixed 4K; skip on larger PAGE_SIZE.
+	 */
 	if (!adev->rmmio_remap.bus_addr || PAGE_SIZE > AMDGPU_GPU_PAGE_SIZE)
 		return 0;
 
-	/* Hardware remap page is fixed 4K; skip on larger PAGE_SIZE. */
-	if (PAGE_SIZE > AMDGPU_GPU_PAGE_SIZE)
-		return 0;
-
 	/* Create exactly one GEM BO in the MMIO_REMAP domain. */
 	bp.type        = ttm_bo_type_device;          /* userspace-mappable GEM */
 	bp.size        = AMDGPU_GPU_PAGE_SIZE;        /* 4K */
@@ -1898,7 +1894,7 @@ static int amdgpu_ttm_mmio_remap_bo_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_ttm_mmio_remap_bo_fini - free the singleton MMIO_REMAP BO
+ * amdgpu_ttm_mmio_remap_bo_fini - Free the singleton MMIO_REMAP BO
  * @adev: amdgpu device
  *
  * Frees the kernel-owned MMIO_REMAP BO if it was allocated by
@@ -1907,7 +1903,7 @@ static int amdgpu_ttm_mmio_remap_bo_init(struct amdgpu_device *adev)
 static void amdgpu_ttm_mmio_remap_bo_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_unref(&adev->rmmio_remap.bo);
-	adev->mmio_remap.bo = NULL;
+	adev->rmmio_remap.bo = NULL;
 }
 
 /*
-- 
2.34.1