drm/i915: Introduce & use new lightweight SGL iterators
The existing for_each_sg_page() iterator is somewhat heavyweight, and is
limiting i915 driver performance in a few benchmarks. So here we
introduce somewhat lighter weight iterators, primarily for use with GEM
objects or other case where we need only deal with whole aligned pages.
Unlike the old iterator, the new iterators use an internal state
structure which is not intended to be accessed by the caller; instead
each takes as a parameter an output variable which is set before each
iteration. This makes them particularly simple to use :)
One of the new iterators provides the caller with the DMA address of
each page in turn; the other provides the 'struct page' pointer required
by many memory management operations.
Various uses of for_each_sg_page() are then converted to the new macros.
v2: Force inlining of the sg_iter constructor and make the union
anonymous.
Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1463741647-15666-4-git-send-email-chris@chris-wilson.co.uk
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6894d8e..63ff5fa 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2251,9 +2251,56 @@
};
#define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
-void i915_gem_track_fb(struct drm_i915_gem_object *old,
- struct drm_i915_gem_object *new,
- unsigned frontbuffer_bits);
+/*
+ * Optimised SGL iterator for GEM objects
+ */
+static __always_inline struct sgt_iter {
+ struct scatterlist *sgp;
+ union {
+ unsigned long pfn;
+ dma_addr_t dma;
+ };
+ unsigned int curr;
+ unsigned int max;
+} __sgt_iter(struct scatterlist *sgl, bool dma) {
+ struct sgt_iter s = { .sgp = sgl };
+
+ if (s.sgp) {
+ s.max = s.curr = s.sgp->offset;
+ s.max += s.sgp->length;
+ if (dma)
+ s.dma = sg_dma_address(s.sgp);
+ else
+ s.pfn = page_to_pfn(sg_page(s.sgp));
+ }
+
+ return s;
+}
+
+/**
+ * for_each_sgt_dma - iterate over the DMA addresses of the given sg_table
+ * @__dmap: DMA address (output)
+ * @__iter: 'struct sgt_iter' (iterator state, internal)
+ * @__sgt: sg_table to iterate over (input)
+ */
+#define for_each_sgt_dma(__dmap, __iter, __sgt) \
+ for ((__iter) = __sgt_iter((__sgt)->sgl, true); \
+ ((__dmap) = (__iter).dma + (__iter).curr); \
+ (((__iter).curr += PAGE_SIZE) < (__iter).max) || \
+ ((__iter) = __sgt_iter(sg_next((__iter).sgp), true), 0))
+
+/**
+ * for_each_sgt_page - iterate over the pages of the given sg_table
+ * @__pp: page pointer (output)
+ * @__iter: 'struct sgt_iter' (iterator state, internal)
+ * @__sgt: sg_table to iterate over (input)
+ */
+#define for_each_sgt_page(__pp, __iter, __sgt) \
+ for ((__iter) = __sgt_iter((__sgt)->sgl, false); \
+ ((__pp) = (__iter).pfn == 0 ? NULL : \
+ pfn_to_page((__iter).pfn + ((__iter).curr >> PAGE_SHIFT))); \
+ (((__iter).curr += PAGE_SIZE) < (__iter).max) || \
+ ((__iter) = __sgt_iter(sg_next((__iter).sgp), false), 0))
/**
* Request queue structure.
@@ -3108,6 +3155,11 @@
struct drm_mode_create_dumb *args);
int i915_gem_mmap_gtt(struct drm_file *file_priv, struct drm_device *dev,
uint32_t handle, uint64_t *offset);
+
+void i915_gem_track_fb(struct drm_i915_gem_object *old,
+ struct drm_i915_gem_object *new,
+ unsigned frontbuffer_bits);
+
/**
* Returns true if seq1 is later than seq2.
*/