[Intel-gfx] [PATCH v2 2/7] drm: Add drm_memcpy_from_wc() variant which accepts destination address

[Balasubramani Vivekanandan]

Fast copy using non-temporal instructions for x86 currently exists at two
locations. One is implemented in i915 driver at i915/i915_memcpy.c and
another copy at drm_cache.c. The plan is to remove the duplicate
implementation in i915 driver and use the functions from drm_cache.c.

A variant of drm_memcpy_from_wc() is added in drm_cache.c which accepts
address as argument instead of iosys_map for destination. It is a very
common scenario in i915 to copy from a WC memory type, which may be an
io memory or a system memory to a destination address pointing to system
memory. To avoid the overhead of creating iosys_map type for the
destination, new variant is created to accept the address directly.

Also a new function is exported in drm_cache.c to find if the fast copy
is supported by the platform or not. It is required for i915.

Cc: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
Cc: Maxime Ripard <mripard at kernel.org>
Cc: Thomas Zimmermann <tzimmermann at suse.de>
Cc: David Airlie <airlied at linux.ie>
Cc: Daniel Vetter <daniel at ffwll.ch>
Cc: Thomas Hellstr_m <thomas.hellstrom at linux.intel.com>
Cc: Lucas De Marchi <lucas.demarchi at intel.com>

Signed-off-by: Balasubramani Vivekanandan <balasubramani.vivekanandan at intel.com>
---
 drivers/gpu/drm/drm_cache.c | 54 +++++++++++++++++++++++++++++++++++++
 include/drm/drm_cache.h     |  3 +++
 2 files changed, 57 insertions(+)

diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index a21c1350eb09..97959eecc300 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -358,6 +358,54 @@ void drm_memcpy_from_wc(struct iosys_map *dst,
 }
 EXPORT_SYMBOL(drm_memcpy_from_wc);
 
+/**
+ * drm_memcpy_from_wc_vaddr - Perform the fastest available memcpy from a source
+ * that may be WC to a destination in system memory.
+ * @dst: The destination pointer
+ * @src: The source pointer
+ * @len: The size of the area to transfer in bytes
+ *
+ * Same as drm_memcpy_from_wc except destination is accepted as system memory
+ * address. Useful in situations where passing destination address as iosys_map
+ * is simply an overhead and can be avoided.
+ */
+void drm_memcpy_from_wc_vaddr(void *dst, const struct iosys_map *src,
+			      unsigned long len)
+{
+	if (WARN_ON(in_interrupt())) {
+		iosys_map_memcpy_from(dst, src, 0, len);
+		return;
+	}
+
+	if (static_branch_likely(&has_movntdqa)) {
+		__drm_memcpy_from_wc(dst,
+				     src->is_iomem ?
+				     (void const __force *)src->vaddr_iomem :
+				     src->vaddr,
+				     len);
+		return;
+	}
+
+	iosys_map_memcpy_from(dst, src, 0, len);
+}
+EXPORT_SYMBOL(drm_memcpy_from_wc_vaddr);
+
+/*
+ * drm_memcpy_fastcopy_supported - Returns if fast copy using non-temporal
+ * instructions is supported
+ *
+ * Returns true if platform has support for fast copying from wc memory type
+ * using non-temporal instructions. Else false.
+ */
+bool drm_memcpy_fastcopy_supported(void)
+{
+	if (static_branch_likely(&has_movntdqa))
+		return true;
+
+	return false;
+}
+EXPORT_SYMBOL(drm_memcpy_fastcopy_supported);
+
 /*
  * drm_memcpy_init_early - One time initialization of the WC memcpy code
  */
@@ -382,6 +430,12 @@ void drm_memcpy_from_wc(struct iosys_map *dst,
 }
 EXPORT_SYMBOL(drm_memcpy_from_wc);
 
+bool drm_memcpy_fastcopy_supported(void)
+{
+	return false;
+}
+EXPORT_SYMBOL(drm_memcpy_fastcopy_supported);
+
 void drm_memcpy_init_early(void)
 {
 }
diff --git a/include/drm/drm_cache.h b/include/drm/drm_cache.h
index 22deb216b59c..8f48e4dcd7dc 100644
--- a/include/drm/drm_cache.h
+++ b/include/drm/drm_cache.h
@@ -77,4 +77,7 @@ void drm_memcpy_init_early(void);
 void drm_memcpy_from_wc(struct iosys_map *dst,
 			const struct iosys_map *src,
 			unsigned long len);
+bool drm_memcpy_fastcopy_supported(void);
+void drm_memcpy_from_wc_vaddr(void *dst, const struct iosys_map *src,
+			      unsigned long len);
 #endif
-- 
2.25.1