drm/i915: Allow userspace to specify ringsize on construction

No good reason why we must always use a static ringsize, so let
userspace select one during construction.

Link: intel/compute-runtime#261
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Steve Carbonari <steven.carbonari@intel.com>
Reviewed-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200225192206.1107336-2-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/Makefile

@@ -82,6 +82,7 @@ gt-y += \
 	gt/gen8_ppgtt.o \
 	gt/intel_breadcrumbs.o \
 	gt/intel_context.o \
+	gt/intel_context_param.o \
 	gt/intel_context_sseu.o \
 	gt/intel_engine_cs.o \
 	gt/intel_engine_heartbeat.o \

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -71,6 +71,7 @@
 
 #include "gt/gen6_ppgtt.h"
 #include "gt/intel_context.h"
+#include "gt/intel_context_param.h"
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_engine_user.h"
 #include "gt/intel_ring.h"
@@ -668,23 +669,30 @@ __create_context(struct drm_i915_private *i915)
 	return ERR_PTR(err);
 }
 
-static void
+static int
 context_apply_all(struct i915_gem_context *ctx,
-		  void (*fn)(struct intel_context *ce, void *data),
+		  int (*fn)(struct intel_context *ce, void *data),
 		  void *data)
 {
 	struct i915_gem_engines_iter it;
 	struct intel_context *ce;
+	int err = 0;
 
-	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it)
-		fn(ce, data);
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		err = fn(ce, data);
+		if (err)
+			break;
+	}
 	i915_gem_context_unlock_engines(ctx);
+
+	return err;
 }
 
-static void __apply_ppgtt(struct intel_context *ce, void *vm)
+static int __apply_ppgtt(struct intel_context *ce, void *vm)
 {
 	i915_vm_put(ce->vm);
 	ce->vm = i915_vm_get(vm);
+	return 0;
 }
 
 static struct i915_address_space *
@@ -722,9 +730,10 @@ static void __set_timeline(struct intel_timeline **dst,
 		intel_timeline_put(old);
 }
 
-static void __apply_timeline(struct intel_context *ce, void *timeline)
+static int __apply_timeline(struct intel_context *ce, void *timeline)
 {
 	__set_timeline(&ce->timeline, timeline);
+	return 0;
 }
 
 static void __assign_timeline(struct i915_gem_context *ctx,
@@ -1215,6 +1224,63 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 	return err;
 }
 
+static int __apply_ringsize(struct intel_context *ce, void *sz)
+{
+	return intel_context_set_ring_size(ce, (unsigned long)sz);
+}
+
+static int set_ringsize(struct i915_gem_context *ctx,
+			struct drm_i915_gem_context_param *args)
+{
+	if (!HAS_LOGICAL_RING_CONTEXTS(ctx->i915))
+		return -ENODEV;
+
+	if (args->size)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(args->value, I915_GTT_PAGE_SIZE))
+		return -EINVAL;
+
+	if (args->value < I915_GTT_PAGE_SIZE)
+		return -EINVAL;
+
+	if (args->value > 128 * I915_GTT_PAGE_SIZE)
+		return -EINVAL;
+
+	return context_apply_all(ctx,
+				 __apply_ringsize,
+				 __intel_context_ring_size(args->value));
+}
+
+static int __get_ringsize(struct intel_context *ce, void *arg)
+{
+	long sz;
+
+	sz = intel_context_get_ring_size(ce);
+	GEM_BUG_ON(sz > INT_MAX);
+
+	return sz; /* stop on first engine */
+}
+
+static int get_ringsize(struct i915_gem_context *ctx,
+			struct drm_i915_gem_context_param *args)
+{
+	int sz;
+
+	if (!HAS_LOGICAL_RING_CONTEXTS(ctx->i915))
+		return -ENODEV;
+
+	if (args->size)
+		return -EINVAL;
+
+	sz = context_apply_all(ctx, __get_ringsize, NULL);
+	if (sz < 0)
+		return sz;
+
+	args->value = sz;
+	return 0;
+}
+
 static int
 user_to_context_sseu(struct drm_i915_private *i915,
 		     const struct drm_i915_gem_context_param_sseu *user,
@@ -1852,17 +1918,19 @@ set_persistence(struct i915_gem_context *ctx,
 	return __context_set_persistence(ctx, args->value);
 }
 
-static void __apply_priority(struct intel_context *ce, void *arg)
+static int __apply_priority(struct intel_context *ce, void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 
 	if (!intel_engine_has_semaphores(ce->engine))
-		return;
+		return 0;
 
 	if (ctx->sched.priority >= I915_PRIORITY_NORMAL)
 		intel_context_set_use_semaphores(ce);
 	else
 		intel_context_clear_use_semaphores(ce);
+
+	return 0;
 }
 
 static int set_priority(struct i915_gem_context *ctx,
@@ -1955,6 +2023,10 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 		ret = set_persistence(ctx, args);
 		break;
 
+	case I915_CONTEXT_PARAM_RINGSIZE:
+		ret = set_ringsize(ctx, args);
+		break;
+
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	default:
 		ret = -EINVAL;
@@ -1983,6 +2055,18 @@ static int create_setparam(struct i915_user_extension __user *ext, void *data)
 	return ctx_setparam(arg->fpriv, arg->ctx, &local.param);
 }
 
+static int copy_ring_size(struct intel_context *dst,
+			  struct intel_context *src)
+{
+	long sz;
+
+	sz = intel_context_get_ring_size(src);
+	if (sz < 0)
+		return sz;
+
+	return intel_context_set_ring_size(dst, sz);
+}
+
 static int clone_engines(struct i915_gem_context *dst,
 			 struct i915_gem_context *src)
 {
@@ -2026,6 +2110,12 @@ static int clone_engines(struct i915_gem_context *dst,
 		}
 
 		intel_context_set_gem(clone->engines[n], dst);
+
+		/* Copy across the preferred ringsize */
+		if (copy_ring_size(clone->engines[n], e->engines[n])) {
+			__free_engines(clone, n + 1);
+			goto err_unlock;
+		}
 	}
 	clone->num_engines = n;
 
@@ -2388,6 +2478,10 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		args->value = i915_gem_context_is_persistent(ctx);
 		break;
 
+	case I915_CONTEXT_PARAM_RINGSIZE:
+		ret = get_ringsize(ctx, args);
+		break;
+
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	default:
 		ret = -EINVAL;

drivers/gpu/drm/i915/gt/intel_context_param.c

@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_active.h"
+#include "intel_context.h"
+#include "intel_context_param.h"
+#include "intel_ring.h"
+
+int intel_context_set_ring_size(struct intel_context *ce, long sz)
+{
+	int err;
+
+	if (intel_context_lock_pinned(ce))
+		return -EINTR;
+
+	err = i915_active_wait(&ce->active);
+	if (err < 0)
+		goto unlock;
+
+	if (intel_context_is_pinned(ce)) {
+		err = -EBUSY; /* In active use, come back later! */
+		goto unlock;
+	}
+
+	if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
+		struct intel_ring *ring;
+
+		/* Replace the existing ringbuffer */
+		ring = intel_engine_create_ring(ce->engine, sz);
+		if (IS_ERR(ring)) {
+			err = PTR_ERR(ring);
+			goto unlock;
+		}
+
+		intel_ring_put(ce->ring);
+		ce->ring = ring;
+
+		/* Context image will be updated on next pin */
+	} else {
+		ce->ring = __intel_context_ring_size(sz);
+	}
+
+unlock:
+	intel_context_unlock_pinned(ce);
+	return err;
+}
+
+long intel_context_get_ring_size(struct intel_context *ce)
+{
+	long sz = (unsigned long)READ_ONCE(ce->ring);
+
+	if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
+		if (intel_context_lock_pinned(ce))
+			return -EINTR;
+
+		sz = ce->ring->size;
+		intel_context_unlock_pinned(ce);
+	}
+
+	return sz;
+}

drivers/gpu/drm/i915/gt/intel_context_param.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_CONTEXT_PARAM_H
+#define INTEL_CONTEXT_PARAM_H
+
+struct intel_context;
+
+int intel_context_set_ring_size(struct intel_context *ce, long sz);
+long intel_context_get_ring_size(struct intel_context *ce);
+
+#endif /* INTEL_CONTEXT_PARAM_H */

drivers/gpu/drm/i915/gt/intel_lrc.c

@@ -2966,6 +2966,7 @@ __execlists_update_reg_state(const struct intel_context *ce,
 	regs[CTX_RING_START] = i915_ggtt_offset(ring->vma);
 	regs[CTX_RING_HEAD] = head;
 	regs[CTX_RING_TAIL] = ring->tail;
+	regs[CTX_RING_CTL] = RING_CTL_SIZE(ring->size) | RING_VALID;
 
 	/* RPCS */
 	if (engine->class == RENDER_CLASS) {

include/uapi/drm/i915_drm.h

@@ -1619,6 +1619,27 @@ struct drm_i915_gem_context_param {
  * By default, new contexts allow persistence.
  */
 #define I915_CONTEXT_PARAM_PERSISTENCE	0xb
+
+/*
+ * I915_CONTEXT_PARAM_RINGSIZE:
+ *
+ * Sets the size of the CS ringbuffer to use for logical ring contexts. This
+ * applies a limit of how many batches can be queued to HW before the caller
+ * is blocked due to lack of space for more commands.
+ *
+ * Only reliably possible to be set prior to first use, i.e. during
+ * construction. At any later point, the current execution must be flushed as
+ * the ring can only be changed while the context is idle. Note, the ringsize
+ * can be specified as a constructor property, see
+ * I915_CONTEXT_CREATE_EXT_SETPARAM, but can also be set later if required.
+ *
+ * Only applies to the current set of engine and lost when those engines
+ * are replaced by a new mapping (see I915_CONTEXT_PARAM_ENGINES).
+ *
+ * Must be between 4 - 512 KiB, in intervals of page size [4 KiB].
+ * Default is 16 KiB.
+ */
+#define I915_CONTEXT_PARAM_RINGSIZE	0xc
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;