[PATCH 06/87] drm/i915: Consolidate checks for memcpy-from-wc support

[Chris Wilson]

In order to silence sparse:

../drivers/gpu/drm/i915/i915_gpu_error.c:200:39: warning: Using plain integer as NULL pointer

add a helper to check whether we have sse4.1 and that the desired
alignment is valid for acceleration.

v2: Explain the macros and split the two use cases between
i915_has_memcpy_from_wc() and i915_can_memcpy_from_wc().

Reported-by: Ville Syrjälä <ville.syrjala at linux.intel.com>
Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
---
 drivers/gpu/drm/i915/i915_cmd_parser.c     |  2 +-
 drivers/gpu/drm/i915/i915_drv.h            | 16 ++++++++++++++++
 drivers/gpu/drm/i915/i915_gpu_error.c      |  2 +-
 drivers/gpu/drm/i915/i915_guc_submission.c |  2 +-
 4 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 6c310a8a97a7..21b1cd917d81 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1079,7 +1079,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 
 	src = ERR_PTR(-ENODEV);
 	if (src_needs_clflush &&
-	    i915_memcpy_from_wc((void *)(uintptr_t)batch_start_offset, NULL, 0)) {
+	    i915_can_memcpy_from_wc(NULL, batch_start_offset, 0)) {
 		src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
 		if (!IS_ERR(src)) {
 			i915_memcpy_from_wc(dst,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 239a120a0ec1..ce051a5b97ca 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -4021,6 +4021,22 @@ __i915_request_irq_complete(struct drm_i915_gem_request *req)
 void i915_memcpy_init_early(struct drm_i915_private *dev_priv);
 bool i915_memcpy_from_wc(void *dst, const void *src, unsigned long len);
 
+/* The movntdqa instructions used for memcpy-from-wc require 16-byte alignment,
+ * as well as SSE4.1 support. i915_memcpy_from_wc() will report if it cannot
+ * perform the operation. To check beforehand, pass in the parameters to
+ * to i915_can_memcpy_from_wc() - since we only care about the low 4 bits,
+ * you only need to pass in the minor offsets, page-aligned pointers are
+ * always valid.
+ *
+ * For just checking for SSE4.1, in the foreknowledge that the future use
+ * will be correctly aligned, just use i915_has_memcpy_from_wc().
+ */
+#define i915_can_memcpy_from_wc(dst, src, len) \
+	i915_memcpy_from_wc((void *)((unsigned long)(dst) | (unsigned long)(src) | (len)), NULL, 0)
+
+#define i915_has_memcpy_from_wc() \
+	i915_memcpy_from_wc(NULL, NULL, 0)
+
 /* i915_mm.c */
 int remap_io_mapping(struct vm_area_struct *vma,
 		     unsigned long addr, unsigned long pfn, unsigned long size,
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index e34532d98004..396c6f0fd033 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -197,7 +197,7 @@ static bool compress_init(struct compress *c)
 	}
 
 	c->tmp = NULL;
-	if (i915_memcpy_from_wc(NULL, 0, 0))
+	if (i915_has_memcpy_from_wc())
 		c->tmp = (void *)__get_free_page(GFP_ATOMIC | __GFP_NOWARN);
 
 	return true;
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index 30e012b9e93c..710fbb9fc63f 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -1197,7 +1197,7 @@ static void guc_log_create(struct intel_guc *guc)
 		 * it should be present on the chipsets supporting GuC based
 		 * submisssions.
 		 */
-		if (WARN_ON(!i915_memcpy_from_wc(NULL, NULL, 0))) {
+		if (WARN_ON(!i915_has_memcpy_from_wc())) {
 			/* logging will not be enabled */
 			i915.guc_log_level = -1;
 			return;
-- 
2.11.0