From 1215d28e722ce27172de7708ead6824fcfb19364 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 19 Apr 2019 12:17:48 +0100 Subject: [PATCH] drm/i915: Enable render context support for Ironlake (gen5) MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Ironlake does support being able to saving and reloading context specific registers between contexts, providing isolation of the basic GPU state (as programmable by userspace). This allows userspace to assume that the GPU retains their state from one batch to the next, minimising the amount of state it needs to reload, or manually save and restore. v2: Fix off-by-one in reading CXT_SIZE, and add a comment that the CXT_SIZE and context-layout do not match in bspec, but the difference is irrelevant as we overallocate the full page anyway (Ville). Signed-off-by: Chris Wilson Cc: Ville Syrjälä Cc: Kenneth Graunke Reviewed-by: Ville Syrjälä Link: https://patchwork.freedesktop.org/patch/msgid/20190419111749.3910-2-chris@chris-wilson.co.uk --- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 16 ++++++++++++++++ drivers/gpu/drm/i915/gt/intel_ringbuffer.c | 13 +++++++++++++ 2 files changed, 29 insertions(+) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index cbebe812b317..ce52030bf71d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -213,6 +213,22 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class) return round_up(GEN6_CXT_TOTAL_SIZE(cxt_size) * 64, PAGE_SIZE); case 5: + /* + * There is a discrepancy here between the size reported + * by the register and the size of the context layout + * in the docs. Both are described as authorative! + * + * The discrepancy is on the order of a few cachelines, + * but the total is under one page (4k), which is our + * minimum allocation anyway so it should all come + * out in the wash. + */ + cxt_size = I915_READ(CXT_SIZE) + 1; + DRM_DEBUG_DRIVER("gen%d CXT_SIZE = %d bytes [0x%08x]\n", + INTEL_GEN(dev_priv), + cxt_size * 64, + cxt_size - 1); + return round_up(cxt_size * 64, PAGE_SIZE); case 4: case 3: case 2: diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c index 1418ed0c4875..875dd458c447 100644 --- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/gt/intel_ringbuffer.c @@ -1645,11 +1645,14 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) /* These flags are for resource streamer on HSW+ */ flags |= HSW_MI_RS_SAVE_STATE_EN | HSW_MI_RS_RESTORE_STATE_EN; else + /* We need to save the extended state for powersaving modes */ flags |= MI_SAVE_EXT_STATE_EN | MI_RESTORE_EXT_STATE_EN; len = 4; if (IS_GEN(i915, 7)) len += 2 + (num_engines ? 4 * num_engines + 6 : 0); + else if (IS_GEN(i915, 5)) + len += 2; if (flags & MI_FORCE_RESTORE) { GEM_BUG_ON(flags & MI_RESTORE_INHIBIT); flags &= ~MI_FORCE_RESTORE; @@ -1678,6 +1681,14 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) GEN6_PSMI_SLEEP_MSG_DISABLE); } } + } else if (IS_GEN(i915, 5)) { + /* + * This w/a is only listed for pre-production ilk a/b steppings, + * but is also mentioned for programming the powerctx. To be + * safe, just apply the workaround; we do not use SyncFlush so + * this should never take effect and so be a no-op! + */ + *cs++ = MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN; } if (force_restore) { @@ -1731,6 +1742,8 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) *cs++ = MI_NOOP; } *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; + } else if (IS_GEN(i915, 5)) { + *cs++ = MI_SUSPEND_FLUSH; } intel_ring_advance(rq, cs); -- 2.30.2