Luca Barbieri
2010-Jan-18 00:18 UTC
[Nouveau] [PATCH 1/2] nv30-nv40: support unlimited queries
Currently on NV30/NV40 an assert will be triggered once 32 queries are
outstanding.
This violates the OpenGL/Gallium interface, which requires support for
an unlimited number of fences.
This patch fixes the problem by putting queries in a linked list and
waiting on the oldest one if allocation fails.
nVidia seems to use a similar strategy, but with 1024 instead of 32 fences.
The next patch will improve this.
---
src/gallium/drivers/nv30/nv30_query.c | 26 ++++++++++++++++++--------
src/gallium/drivers/nv30/nv30_screen.c | 2 ++
src/gallium/drivers/nv30/nv30_screen.h | 1 +
src/gallium/drivers/nv40/nv40_query.c | 26 ++++++++++++++++++--------
src/gallium/drivers/nv40/nv40_screen.c | 2 ++
src/gallium/drivers/nv40/nv40_screen.h | 1 +
6 files changed, 42 insertions(+), 16 deletions(-)
diff --git a/src/gallium/drivers/nv30/nv30_query.c
b/src/gallium/drivers/nv30/nv30_query.c
index e27e9cc..c0d192b 100644
--- a/src/gallium/drivers/nv30/nv30_query.c
+++ b/src/gallium/drivers/nv30/nv30_query.c
@@ -3,6 +3,7 @@
#include "nv30_context.h"
struct nv30_query {
+ struct list_head list;
struct nouveau_resource *object;
unsigned type;
boolean ready;
@@ -23,6 +24,8 @@ nv30_query_create(struct pipe_context *pipe, unsigned
query_type)
q = CALLOC(1, sizeof(struct nv30_query));
q->type = query_type;
+ assert(q->type == PIPE_QUERY_OCCLUSION_COUNTER);
+
return (struct pipe_query *)q;
}
@@ -32,7 +35,10 @@ nv30_query_destroy(struct pipe_context *pipe, struct
pipe_query *pq)
struct nv30_query *q = nv30_query(pq);
if (q->object)
+ {
nouveau_resource_free(&q->object);
+ LIST_DEL(&q->list);
+ }
FREE(q);
}
@@ -44,20 +50,25 @@ nv30_query_begin(struct pipe_context *pipe, struct
pipe_query *pq)
struct nv30_screen *screen = nv30->screen;
struct nouveau_channel *chan = screen->base.channel;
struct nouveau_grobj *rankine = screen->rankine;
-
- assert(q->type == PIPE_QUERY_OCCLUSION_COUNTER);
+ uint64_t tmp;
/* Happens when end_query() is called, then another begin_query()
* without querying the result in-between. For now we'll wait for
* the existing query to notify completion, but it could be better.
*/
- if (q->object) {
- uint64_t tmp;
+ if (q->object)
pipe->get_query_result(pipe, pq, 1, &tmp);
+
+ while (nouveau_resource_alloc(nv30->screen->query_heap, 1, NULL,
&q->object))
+ {
+ struct nv30_query* oldestq;
+ assert(!LIST_IS_EMPTY(&nv30->screen->query_list));
+ oldestq = LIST_ENTRY(struct nv30_query, nv30->screen->query_list.next,
list);
+ pipe->get_query_result(pipe, (struct pipe_query*)oldestq, 1, &tmp);
}
- if (nouveau_resource_alloc(nv30->screen->query_heap, 1, NULL,
&q->object))
- assert(0);
+ LIST_ADDTAIL(&q->list, &nv30->screen->query_list);
+
nouveau_notifier_reset(nv30->screen->query, q->object->start);
BEGIN_RING(chan, rankine, NV34TCL_QUERY_RESET, 1);
@@ -90,8 +101,6 @@ nv30_query_result(struct pipe_context *pipe, struct
pipe_query *pq,
struct nv30_context *nv30 = nv30_context(pipe);
struct nv30_query *q = nv30_query(pq);
- assert(q->object && q->type == PIPE_QUERY_OCCLUSION_COUNTER);
-
if (!q->ready) {
unsigned status;
@@ -110,6 +119,7 @@ nv30_query_result(struct pipe_context *pipe, struct
pipe_query *pq,
q->object->start);
q->ready = TRUE;
nouveau_resource_free(&q->object);
+ LIST_DEL(&q->list);
}
*result = q->result;
diff --git a/src/gallium/drivers/nv30/nv30_screen.c
b/src/gallium/drivers/nv30/nv30_screen.c
index 48a562e..2cd5d12 100644
--- a/src/gallium/drivers/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nv30/nv30_screen.c
@@ -252,6 +252,8 @@ nv30_screen_create(struct pipe_winsys *ws, struct
nouveau_device *dev)
return NULL;
}
+ LIST_INITHEAD(&screen->query_list);
+
/* Vtxprog resources */
if (nouveau_resource_init(&screen->vp_exec_heap, 0, 256) ||
nouveau_resource_init(&screen->vp_data_heap, 0, 256)) {
diff --git a/src/gallium/drivers/nv30/nv30_screen.h
b/src/gallium/drivers/nv30/nv30_screen.h
index cbf945f..9190789 100644
--- a/src/gallium/drivers/nv30/nv30_screen.h
+++ b/src/gallium/drivers/nv30/nv30_screen.h
@@ -19,6 +19,7 @@ struct nv30_screen {
/* Query object resources */
struct nouveau_notifier *query;
struct nouveau_resource *query_heap;
+ struct list_head query_list;
/* Vtxprog resources */
struct nouveau_resource *vp_exec_heap;
diff --git a/src/gallium/drivers/nv40/nv40_query.c
b/src/gallium/drivers/nv40/nv40_query.c
index 8ed4a67..01d35ea 100644
--- a/src/gallium/drivers/nv40/nv40_query.c
+++ b/src/gallium/drivers/nv40/nv40_query.c
@@ -3,6 +3,7 @@
#include "nv40_context.h"
struct nv40_query {
+ struct list_head list;
struct nouveau_resource *object;
unsigned type;
boolean ready;
@@ -23,6 +24,8 @@ nv40_query_create(struct pipe_context *pipe, unsigned
query_type)
q = CALLOC(1, sizeof(struct nv40_query));
q->type = query_type;
+ assert(q->type == PIPE_QUERY_OCCLUSION_COUNTER);
+
return (struct pipe_query *)q;
}
@@ -32,7 +35,10 @@ nv40_query_destroy(struct pipe_context *pipe, struct
pipe_query *pq)
struct nv40_query *q = nv40_query(pq);
if (q->object)
+ {
nouveau_resource_free(&q->object);
+ LIST_DEL(&q->list);
+ }
FREE(q);
}
@@ -44,20 +50,25 @@ nv40_query_begin(struct pipe_context *pipe, struct
pipe_query *pq)
struct nv40_screen *screen = nv40->screen;
struct nouveau_channel *chan = screen->base.channel;
struct nouveau_grobj *curie = screen->curie;
-
- assert(q->type == PIPE_QUERY_OCCLUSION_COUNTER);
+ uint64_t tmp;
/* Happens when end_query() is called, then another begin_query()
* without querying the result in-between. For now we'll wait for
* the existing query to notify completion, but it could be better.
*/
- if (q->object) {
- uint64_t tmp;
+ if (q->object)
pipe->get_query_result(pipe, pq, 1, &tmp);
+
+ while (nouveau_resource_alloc(nv40->screen->query_heap, 1, NULL,
&q->object))
+ {
+ struct nv40_query* oldestq;
+ assert(!LIST_IS_EMPTY(&nv40->screen->query_list));
+ oldestq = LIST_ENTRY(struct nv40_query, nv40->screen->query_list.next,
list);
+ pipe->get_query_result(pipe, (struct pipe_query*)oldestq, 1, &tmp);
}
- if (nouveau_resource_alloc(nv40->screen->query_heap, 1, NULL,
&q->object))
- assert(0);
+ LIST_ADDTAIL(&q->list, &nv40->screen->query_list);
+
nouveau_notifier_reset(nv40->screen->query, q->object->start);
BEGIN_RING(chan, curie, NV40TCL_QUERY_RESET, 1);
@@ -90,8 +101,6 @@ nv40_query_result(struct pipe_context *pipe, struct
pipe_query *pq,
struct nv40_context *nv40 = nv40_context(pipe);
struct nv40_query *q = nv40_query(pq);
- assert(q->object && q->type == PIPE_QUERY_OCCLUSION_COUNTER);
-
if (!q->ready) {
unsigned status;
@@ -110,6 +119,7 @@ nv40_query_result(struct pipe_context *pipe, struct
pipe_query *pq,
q->object->start);
q->ready = TRUE;
nouveau_resource_free(&q->object);
+ LIST_DEL(&q->list);
}
*result = q->result;
diff --git a/src/gallium/drivers/nv40/nv40_screen.c
b/src/gallium/drivers/nv40/nv40_screen.c
index 2939572..a8c14f9 100644
--- a/src/gallium/drivers/nv40/nv40_screen.c
+++ b/src/gallium/drivers/nv40/nv40_screen.c
@@ -237,6 +237,8 @@ nv40_screen_create(struct pipe_winsys *ws, struct
nouveau_device *dev)
return NULL;
}
+ LIST_INITHEAD(&screen->query_list);
+
/* Vtxprog resources */
if (nouveau_resource_init(&screen->vp_exec_heap, 0, 512) ||
nouveau_resource_init(&screen->vp_data_heap, 0, 256)) {
diff --git a/src/gallium/drivers/nv40/nv40_screen.h
b/src/gallium/drivers/nv40/nv40_screen.h
index 77bf94b..f3569a2 100644
--- a/src/gallium/drivers/nv40/nv40_screen.h
+++ b/src/gallium/drivers/nv40/nv40_screen.h
@@ -18,6 +18,7 @@ struct nv40_screen {
/* Query object resources */
struct nouveau_notifier *query;
struct nouveau_resource *query_heap;
+ struct list_head query_list;
/* Vtxprog resources */
struct nouveau_resource *vp_exec_heap;
--
1.6.3.3
Luca Barbieri
2010-Jan-18 00:18 UTC
[Nouveau] [PATCH 2/2] nv30/nv40: allocate a bigger block for queries
This patch allocates a bigger chunk of memory to store queries in,
increasing the (hidden) outstanding query limit from 32 to 125.
It also tries to make use of a 16KB notifier block if the kernel
supports that.
The blob supports 1024 queries due to their 16KB query block and
16-byte rather than 32-byte sized queries.
---
src/gallium/drivers/nv30/nv30_screen.c | 13 +++++++++----
src/gallium/drivers/nv40/nv40_screen.c | 13 ++++++++++---
2 files changed, 19 insertions(+), 7 deletions(-)
diff --git a/src/gallium/drivers/nv30/nv30_screen.c
b/src/gallium/drivers/nv30/nv30_screen.c
index 2cd5d12..0f26d39 100644
--- a/src/gallium/drivers/nv30/nv30_screen.c
+++ b/src/gallium/drivers/nv30/nv30_screen.c
@@ -238,22 +238,27 @@ nv30_screen_create(struct pipe_winsys *ws, struct
nouveau_device *dev)
}
/* Query objects */
- ret = nouveau_notifier_alloc(chan, 0xbeef0302, 32, &screen->query);
+ unsigned query_sizes[] = {(16384 - 3 * 32) / 32, 15 * 1024 / 32, (4096 - 32 *
3) / 32, 3 * 1024 / 32, 2 * 1024 / 32, 1024 / 32};
+ for(i = 0; i < sizeof(query_sizes) / sizeof(query_sizes[0]); ++i)
+ {
+ ret = nouveau_notifier_alloc(chan, 0xbeef0302, query_sizes[i],
&screen->query);
+ if(!ret)
+ break;
+ }
+
if (ret) {
NOUVEAU_ERR("Error initialising query objects: %d\n", ret);
nv30_screen_destroy(pscreen);
return NULL;
}
- ret = nouveau_resource_init(&screen->query_heap, 0, 32);
+ nouveau_resource_init(&screen->query_heap, 0, query_sizes[i]);
if (ret) {
NOUVEAU_ERR("Error initialising query object heap: %d\n", ret);
nv30_screen_destroy(pscreen);
return NULL;
}
- LIST_INITHEAD(&screen->query_list);
-
/* Vtxprog resources */
if (nouveau_resource_init(&screen->vp_exec_heap, 0, 256) ||
nouveau_resource_init(&screen->vp_data_heap, 0, 256)) {
diff --git a/src/gallium/drivers/nv40/nv40_screen.c
b/src/gallium/drivers/nv40/nv40_screen.c
index a8c14f9..4264d18 100644
--- a/src/gallium/drivers/nv40/nv40_screen.c
+++ b/src/gallium/drivers/nv40/nv40_screen.c
@@ -161,7 +161,7 @@ nv40_screen_create(struct pipe_winsys *ws, struct
nouveau_device *dev)
struct pipe_screen *pscreen;
struct nouveau_stateobj *so;
unsigned curie_class = 0;
- int ret;
+ int ret, i;
if (!screen)
return NULL;
@@ -223,14 +223,21 @@ nv40_screen_create(struct pipe_winsys *ws, struct
nouveau_device *dev)
}
/* Query objects */
- ret = nouveau_notifier_alloc(chan, 0xbeef0302, 32, &screen->query);
+ unsigned query_sizes[] = {(16384 - 3 * 32) / 32, 15 * 1024 / 32, (4096 - 32 *
3) / 32, 3 * 1024 / 32, 2 * 1024 / 32, 1024 / 32};
+ for(i = 0; i < sizeof(query_sizes) / sizeof(query_sizes[0]); ++i)
+ {
+ ret = nouveau_notifier_alloc(chan, 0xbeef0302, query_sizes[i],
&screen->query);
+ if(!ret)
+ break;
+ }
+
if (ret) {
NOUVEAU_ERR("Error initialising query objects: %d\n", ret);
nv40_screen_destroy(pscreen);
return NULL;
}
- nouveau_resource_init(&screen->query_heap, 0, 32);
+ nouveau_resource_init(&screen->query_heap, 0, query_sizes[i]);
if (ret) {
NOUVEAU_ERR("Error initialising query object heap: %d\n", ret);
nv40_screen_destroy(pscreen);
--
1.6.3.3
Reasonably Related Threads
- [PATCH] nv30-nv40: support unlimited queries (v2)
- [PATCH] nv50: Fix allocation size for querys
- Clean up of nv40_context->state.hw and nv40_screen->state
- [PATCH 1/2] Unreference state/buffer objects on context/screen destruction
- [PATCH v2] nv50: Handle ARB_conditional_render_inverted and enable it