drm/i915: Compute the ELSP register location once

Similar to the issue with reading from the context status buffer,
see commit 26720ab97fea ("drm/i915: Move CSB MMIO reads out of the
execlists lock"), we frequently write to the ELSP register (4 writes per
interrupt) and know we hold the required spinlock and forcewake throughout.
We can further reduce the cost of writing these registers beyond the
I915_WRITE_FW() by precomputing the address of the ELSP register. We also
note that the subsequent read serves no purpose here, and are happy to
see it go.

v2: Address I915_WRITE mistakes in changelog

   text    data     bss     dec     hex filename
1259784    4581     576 1264941  134d2d drivers/gpu/drm/i915/i915.ko
1259720    4581     576 1264877  134ced drivers/gpu/drm/i915/i915.ko

Saves 64 bytes of address recomputation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-4-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d7fa9b3..a6b9033 100644 (file)
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -331,10 +331,11 @@ uint64_t intel_lr_context_descriptor(struct i915_gem_context *ctx,
 static void execlists_elsp_write(struct drm_i915_gem_request *rq0,
                                 struct drm_i915_gem_request *rq1)
 {
-
        struct intel_engine_cs *engine = rq0->engine;
        struct drm_i915_private *dev_priv = rq0->i915;
-       uint64_t desc[2];
+       u32 __iomem *elsp =
+               dev_priv->regs + i915_mmio_reg_offset(RING_ELSP(engine));
+       u64 desc[2];
 
        if (rq1) {
                desc[1] = intel_lr_context_descriptor(rq1->ctx, rq1->engine);
@@ -347,15 +348,12 @@ static void execlists_elsp_write(struct drm_i915_gem_request *rq0,
        rq0->elsp_submitted++;
 
        /* You must always write both descriptors in the order below. */
-       I915_WRITE_FW(RING_ELSP(engine), upper_32_bits(desc[1]));
-       I915_WRITE_FW(RING_ELSP(engine), lower_32_bits(desc[1]));
+       writel(upper_32_bits(desc[1]), elsp);
+       writel(lower_32_bits(desc[1]), elsp);
 
-       I915_WRITE_FW(RING_ELSP(engine), upper_32_bits(desc[0]));
+       writel(upper_32_bits(desc[0]), elsp);
        /* The context is automatically loaded after the following */
-       I915_WRITE_FW(RING_ELSP(engine), lower_32_bits(desc[0]));
-
-       /* ELSP is a wo register, use another nearby reg for posting */
-       POSTING_READ_FW(RING_EXECLIST_STATUS_LO(engine));
+       writel(lower_32_bits(desc[0]), elsp);
 }
 
 static void