From 4e9599781d67dd61d14a944a6103401f21146fbf Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 8 Jul 2020 18:37:47 +0100
Subject: drm/i915: Release shortlived maps of longlived objects
Git-commit: 89d19b2b456af1b8e009eee5966bf29c850b200a
Patch-mainline: v5.9-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322
Some objects we map once during their construction, and then never
access their mappings again, even if they are kept around for the
duration of the driver. Keeping those pages mapped, often vmapped, is
therefore wasteful and we should release the maps as soon as we no
longer need them.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200708173748.32734-3-chris@chris-wilson.co.uk
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/i915/gem/i915_gem_object.h | 2 ++
drivers/gpu/drm/i915/gem/i915_gem_pages.c | 15 +++++++++++++++
drivers/gpu/drm/i915/gt/gen7_renderclear.c | 2 +-
drivers/gpu/drm/i915/gt/intel_lrc.c | 2 +-
drivers/gpu/drm/i915/gt/intel_renderstate.c | 2 +-
drivers/gpu/drm/i915/gt/intel_ring_submission.c | 2 +-
drivers/gpu/drm/i915/i915_perf.c | 4 ++--
7 files changed, 23 insertions(+), 6 deletions(-)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 2faa481cc18f..9cf4ad78ece6 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -394,6 +394,8 @@ static inline void i915_gem_object_unpin_map(struct drm_i915_gem_object *obj)
i915_gem_object_unpin_pages(obj);
}
+void __i915_gem_object_release_map(struct drm_i915_gem_object *obj);
+
void
i915_gem_object_flush_write_domain(struct drm_i915_gem_object *obj,
unsigned int flush_domains);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index af9e48ee4a33..7e54657cf67b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -408,6 +408,21 @@ void __i915_gem_object_flush_map(struct drm_i915_gem_object *obj,
}
}
+void __i915_gem_object_release_map(struct drm_i915_gem_object *obj)
+{
+ GEM_BUG_ON(!obj->mm.mapping);
+
+ /*
+ * We allow removing the mapping from underneath pinned pages!
+ *
+ * Furthermore, since this is an unsafe operation reserved only
+ * for construction time manipulation, we ignore locking prudence.
+ */
+ unmap_object(obj, page_mask_bits(fetch_and_zero(&obj->mm.mapping)));
+
+ i915_gem_object_unpin_map(obj);
+}
+
struct scatterlist *
i915_gem_object_get_sg(struct drm_i915_gem_object *obj,
unsigned int n,
diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
index de595b66a746..d93d85cd3027 100644
--- a/drivers/gpu/drm/i915/gt/gen7_renderclear.c
+++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
@@ -396,7 +396,7 @@ int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine,
emit_batch(vma, memset(batch, 0, bv.max_size), &bv);
i915_gem_object_flush_map(vma->obj);
- i915_gem_object_unpin_map(vma->obj);
+ __i915_gem_object_release_map(vma->obj);
return 0;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index be738b04adae..a6afc239da35 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -3937,7 +3937,7 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine)
GEM_BUG_ON(batch_ptr - batch > CTX_WA_BB_OBJ_SIZE);
__i915_gem_object_flush_map(wa_ctx->vma->obj, 0, batch_ptr - batch);
- i915_gem_object_unpin_map(wa_ctx->vma->obj);
+ __i915_gem_object_release_map(wa_ctx->vma->obj);
if (ret)
lrc_destroy_wa_ctx(engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index 6db23389e427..1bfad589c63b 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -150,7 +150,7 @@ static int render_state_setup(struct intel_renderstate *so,
ret = 0;
out:
__i915_gem_object_flush_map(so->vma->obj, 0, i * sizeof(u32));
- i915_gem_object_unpin_map(so->vma->obj);
+ __i915_gem_object_release_map(so->vma->obj);
return ret;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index b09b83deecef..94915f668715 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -543,7 +543,7 @@ alloc_context_vma(struct intel_engine_cs *engine)
vaddr, engine->context_size);
i915_gem_object_flush_map(obj);
- i915_gem_object_unpin_map(obj);
+ __i915_gem_object_release_map(obj);
}
vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 3b867b523811..c6f6370283cf 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1773,7 +1773,7 @@ static int alloc_noa_wait(struct i915_perf_stream *stream)
GEM_BUG_ON(cs - batch > PAGE_SIZE / sizeof(*batch));
i915_gem_object_flush_map(bo);
- i915_gem_object_unpin_map(bo);
+ __i915_gem_object_release_map(bo);
stream->noa_wait = vma;
return 0;
@@ -1868,7 +1868,7 @@ alloc_oa_config_buffer(struct i915_perf_stream *stream,
*cs++ = 0;
i915_gem_object_flush_map(obj);
- i915_gem_object_unpin_map(obj);
+ __i915_gem_object_release_map(obj);
oa_bo->vma = i915_vma_instance(obj,
&stream->engine->gt->ggtt->vm,
--
2.29.2