[Mesa-dev] [RFC PATCH 3/8] nv50: allocate and map a notifier buffer object for PM

[Samuel Pitoiset]

This notifier buffer object will be used to read back global performance
counters results written by the kernel.

For each domain, we will store the handle of the perfdom object, an
array of 4 counters and the number of cycles. Like the Gallium's HUD,
we keep a list of busy queries in a ring in order to prevent stalls
when reading queries.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
---
 src/gallium/drivers/nouveau/nv50/nv50_screen.c | 29 ++++++++++++++++++++++++++
 src/gallium/drivers/nouveau/nv50/nv50_screen.h |  6 ++++++
 2 files changed, 35 insertions(+)

diff --git a/src/gallium/drivers/nouveau/nv50/nv50_screen.c b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
index c985344..3a99cc8 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_screen.c
+++ b/src/gallium/drivers/nouveau/nv50/nv50_screen.c
@@ -368,6 +368,7 @@ nv50_screen_destroy(struct pipe_screen *pscreen)
    nouveau_object_del(&screen->m2mf);
    nouveau_object_del(&screen->sync);
    nouveau_object_del(&screen->sw);
+   nouveau_object_del(&screen->query);
 
    nouveau_screen_fini(&screen->base);
 
@@ -699,9 +700,11 @@ nv50_screen_create(struct nouveau_device *dev)
    struct nv50_screen *screen;
    struct pipe_screen *pscreen;
    struct nouveau_object *chan;
+   struct nv04_fifo *fifo;
    uint64_t value;
    uint32_t tesla_class;
    unsigned stack_size;
+   uint32_t length;
    int ret;
 
    screen = CALLOC_STRUCT(nv50_screen);
@@ -727,6 +730,7 @@ nv50_screen_create(struct nouveau_device *dev)
    screen->base.pushbuf->rsvd_kick = 5;
 
    chan = screen->base.channel;
+   fifo = chan->data;
 
    pscreen->destroy = nv50_screen_destroy;
    pscreen->context_create = nv50_create;
@@ -772,6 +776,23 @@ nv50_screen_create(struct nouveau_device *dev)
       goto fail;
    }
 
+   /* Compute size (in bytes) of the notifier buffer object which is used
+    * in order to read back global performance counters results written
+    * by the kernel. For each domain, we store the handle of the perfdom
+    * object, an array of 4 counters and the number of cycles. Like for
+    * the Gallium's HUD, we keep a list of busy queries in a ring in order
+    * to prevent stalls when reading queries. */
+   length = (1 + (NV50_HW_PM_RING_BUFFER_NUM_DOMAINS * 6) *
+      NV50_HW_PM_RING_BUFFER_MAX_QUERIES) * 4;
+
+   ret = nouveau_object_new(chan, 0xbeef0302, NOUVEAU_NOTIFIER_CLASS,
+                            &(struct nv04_notify){ .length = length },
+                            sizeof(struct nv04_notify), &screen->query);
+   if (ret) {
+       NOUVEAU_ERR("Failed to allocate notifier object for PM: %d\n", ret);
+       goto fail;
+   }
+
    ret = nouveau_object_new(chan, 0xbeef506e, 0x506e,
                             NULL, 0, &screen->sw);
    if (ret) {
@@ -845,6 +866,14 @@ nv50_screen_create(struct nouveau_device *dev)
    nouveau_heap_init(&screen->gp_code_heap, 0, 1 << NV50_CODE_BO_SIZE_LOG2);
    nouveau_heap_init(&screen->fp_code_heap, 0, 1 << NV50_CODE_BO_SIZE_LOG2);
 
+   ret = nouveau_bo_wrap(screen->base.device, fifo->notify, &screen->notify_bo);
+   if (ret == 0)
+      nouveau_bo_map(screen->notify_bo, 0, screen->base.client);
+   if (ret) {
+      NOUVEAU_ERR("Failed to map notifier object for PM: %d\n", ret);
+      goto fail;
+   }
+
    nouveau_getparam(dev, NOUVEAU_GETPARAM_GRAPH_UNITS, &value);
 
    screen->TPs = util_bitcount(value & 0xffff);
diff --git a/src/gallium/drivers/nouveau/nv50/nv50_screen.h b/src/gallium/drivers/nouveau/nv50/nv50_screen.h
index 69fdfdb..71a5247 100644
--- a/src/gallium/drivers/nouveau/nv50/nv50_screen.h
+++ b/src/gallium/drivers/nouveau/nv50/nv50_screen.h
@@ -59,6 +59,7 @@ struct nv50_screen {
    struct nouveau_bo *txc; /* TIC (offset 0) and TSC (65536) */
    struct nouveau_bo *stack_bo;
    struct nouveau_bo *tls_bo;
+   struct nouveau_bo *notify_bo;
 
    unsigned TPs;
    unsigned MPsInTP;
@@ -89,6 +90,7 @@ struct nv50_screen {
    } fence;
 
    struct nouveau_object *sync;
+   struct nouveau_object *query;
 
    struct nouveau_object *tesla;
    struct nouveau_object *eng2d;
@@ -96,6 +98,10 @@ struct nv50_screen {
    struct nouveau_object *sw;
 };
 
+/* Parameters of the ring buffer used to read back global PM counters. */
+#define NV50_HW_PM_RING_BUFFER_NUM_DOMAINS 8
+#define NV50_HW_PM_RING_BUFFER_MAX_QUERIES 9 /* HUD_NUM_QUERIES + 1 */
+
 static INLINE struct nv50_screen *
 nv50_screen(struct pipe_screen *screen)
 {
-- 
2.4.4