From: Danilo Krummrich <dakr@redhat.com>
To: airlied@gmail.com, daniel@ffwll.ch, tzimmermann@suse.de,
mripard@kernel.org, corbet@lwn.net, christian.koenig@amd.com,
bskeggs@redhat.com, Liam.Howlett@oracle.com,
matthew.brost@intel.com, boris.brezillon@collabora.com,
alexdeucher@gmail.com, ogabbay@kernel.org, bagasdotme@gmail.com,
willy@infradead.org, jason@jlekstrand.net
Cc: linux-doc@vger.kernel.org, nouveau@lists.freedesktop.org,
linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
linux-mm@kvack.org
Subject: [Nouveau] [PATCH drm-next v4 09/14] drm/nouveau: fence: separate fence alloc and emit
Date: Wed, 7 Jun 2023 00:31:25 +0200 [thread overview]
Message-ID: <20230606223130.6132-10-dakr@redhat.com> (raw)
In-Reply-To: <20230606223130.6132-1-dakr@redhat.com>
The new (VM_BIND) UAPI exports DMA fences through DRM syncobjs. Hence,
in order to emit fences within DMA fence signalling critical sections
(e.g. as typically done in the DRM GPU schedulers run_job() callback) we
need to separate fence allocation and fence emitting.
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
---
drivers/gpu/drm/nouveau/dispnv04/crtc.c | 9 ++++-
drivers/gpu/drm/nouveau/nouveau_bo.c | 52 +++++++++++++++----------
drivers/gpu/drm/nouveau/nouveau_chan.c | 6 ++-
drivers/gpu/drm/nouveau/nouveau_dmem.c | 9 +++--
drivers/gpu/drm/nouveau/nouveau_fence.c | 16 +++-----
drivers/gpu/drm/nouveau/nouveau_fence.h | 3 +-
drivers/gpu/drm/nouveau/nouveau_gem.c | 5 ++-
7 files changed, 59 insertions(+), 41 deletions(-)
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index a6f2e681bde9..a34924523133 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -1122,11 +1122,18 @@ nv04_page_flip_emit(struct nouveau_channel *chan,
PUSH_NVSQ(push, NV_SW, NV_SW_PAGE_FLIP, 0x00000000);
PUSH_KICK(push);
- ret = nouveau_fence_new(chan, false, pfence);
+ ret = nouveau_fence_new(pfence);
if (ret)
goto fail;
+ ret = nouveau_fence_emit(*pfence, chan);
+ if (ret)
+ goto fail_fence_unref;
+
return 0;
+
+fail_fence_unref:
+ nouveau_fence_unref(pfence);
fail:
spin_lock_irqsave(&dev->event_lock, flags);
list_del(&s->head);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 057bc995f19b..e9cbbf594e6f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -820,29 +820,39 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict,
mutex_lock(&cli->mutex);
else
mutex_lock_nested(&cli->mutex, SINGLE_DEPTH_NESTING);
+
ret = nouveau_fence_sync(nouveau_bo(bo), chan, true, ctx->interruptible);
- if (ret == 0) {
- ret = drm->ttm.move(chan, bo, bo->resource, new_reg);
- if (ret == 0) {
- ret = nouveau_fence_new(chan, false, &fence);
- if (ret == 0) {
- /* TODO: figure out a better solution here
- *
- * wait on the fence here explicitly as going through
- * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
- *
- * Without this the operation can timeout and we'll fallback to a
- * software copy, which might take several minutes to finish.
- */
- nouveau_fence_wait(fence, false, false);
- ret = ttm_bo_move_accel_cleanup(bo,
- &fence->base,
- evict, false,
- new_reg);
- nouveau_fence_unref(&fence);
- }
- }
+ if (ret)
+ goto out_unlock;
+
+ ret = drm->ttm.move(chan, bo, bo->resource, new_reg);
+ if (ret)
+ goto out_unlock;
+
+ ret = nouveau_fence_new(&fence);
+ if (ret)
+ goto out_unlock;
+
+ ret = nouveau_fence_emit(fence, chan);
+ if (ret) {
+ nouveau_fence_unref(&fence);
+ goto out_unlock;
}
+
+ /* TODO: figure out a better solution here
+ *
+ * wait on the fence here explicitly as going through
+ * ttm_bo_move_accel_cleanup somehow doesn't seem to do it.
+ *
+ * Without this the operation can timeout and we'll fallback to a
+ * software copy, which might take several minutes to finish.
+ */
+ nouveau_fence_wait(fence, false, false);
+ ret = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false,
+ new_reg);
+ nouveau_fence_unref(&fence);
+
+out_unlock:
mutex_unlock(&cli->mutex);
return ret;
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c
index 1068abe41024..f47c0363683c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_chan.c
+++ b/drivers/gpu/drm/nouveau/nouveau_chan.c
@@ -62,9 +62,11 @@ nouveau_channel_idle(struct nouveau_channel *chan)
struct nouveau_fence *fence = NULL;
int ret;
- ret = nouveau_fence_new(chan, false, &fence);
+ ret = nouveau_fence_new(&fence);
if (!ret) {
- ret = nouveau_fence_wait(fence, false, false);
+ ret = nouveau_fence_emit(fence, chan);
+ if (!ret)
+ ret = nouveau_fence_wait(fence, false, false);
nouveau_fence_unref(&fence);
}
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 789857faa048..4ad40e42cae1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -209,7 +209,8 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
goto done;
}
- nouveau_fence_new(dmem->migrate.chan, false, &fence);
+ if (!nouveau_fence_new(&fence))
+ nouveau_fence_emit(fence, dmem->migrate.chan);
migrate_vma_pages(&args);
nouveau_dmem_fence_done(&fence);
dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
@@ -402,7 +403,8 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk)
}
}
- nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence);
+ if (!nouveau_fence_new(&fence))
+ nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan);
migrate_device_pages(src_pfns, dst_pfns, npages);
nouveau_dmem_fence_done(&fence);
migrate_device_finalize(src_pfns, dst_pfns, npages);
@@ -675,7 +677,8 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm,
addr += PAGE_SIZE;
}
- nouveau_fence_new(drm->dmem->migrate.chan, false, &fence);
+ if (!nouveau_fence_new(&fence))
+ nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan);
migrate_vma_pages(args);
nouveau_dmem_fence_done(&fence);
nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i);
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c
index ee5e9d40c166..e946408f945b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.c
@@ -210,6 +210,9 @@ nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan)
struct nouveau_fence_priv *priv = (void*)chan->drm->fence;
int ret;
+ if (unlikely(!chan->fence))
+ return -ENODEV;
+
fence->channel = chan;
fence->timeout = jiffies + (15 * HZ);
@@ -396,25 +399,16 @@ nouveau_fence_unref(struct nouveau_fence **pfence)
}
int
-nouveau_fence_new(struct nouveau_channel *chan, bool sysmem,
- struct nouveau_fence **pfence)
+nouveau_fence_new(struct nouveau_fence **pfence)
{
struct nouveau_fence *fence;
- int ret = 0;
-
- if (unlikely(!chan->fence))
- return -ENODEV;
fence = kzalloc(sizeof(*fence), GFP_KERNEL);
if (!fence)
return -ENOMEM;
- ret = nouveau_fence_emit(fence, chan);
- if (ret)
- nouveau_fence_unref(&fence);
-
*pfence = fence;
- return ret;
+ return 0;
}
static const char *nouveau_fence_get_get_driver_name(struct dma_fence *fence)
diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h
index 0ca2bc85adf6..7c73c7c9834a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fence.h
+++ b/drivers/gpu/drm/nouveau/nouveau_fence.h
@@ -17,8 +17,7 @@ struct nouveau_fence {
unsigned long timeout;
};
-int nouveau_fence_new(struct nouveau_channel *, bool sysmem,
- struct nouveau_fence **);
+int nouveau_fence_new(struct nouveau_fence **);
void nouveau_fence_unref(struct nouveau_fence **);
int nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *);
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index a48f42aaeab9..9c8d1b911a01 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -873,8 +873,11 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data,
}
}
- ret = nouveau_fence_new(chan, false, &fence);
+ ret = nouveau_fence_new(&fence);
+ if (!ret)
+ ret = nouveau_fence_emit(fence, chan);
if (ret) {
+ nouveau_fence_unref(&fence);
NV_PRINTK(err, cli, "error fencing pushbuf: %d\n", ret);
WIND_RING(chan);
goto out;
--
2.40.1
next prev parent reply other threads:[~2023-06-06 22:32 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-06 22:31 [Nouveau] [PATCH drm-next v4 00/14] [RFC] DRM GPUVA Manager & Nouveau VM_BIND UAPI Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 01/14] drm: execution context for GEM buffers v4 Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 02/14] maple_tree: split up MA_STATE() macro Danilo Krummrich
2023-06-13 17:25 ` Liam R. Howlett
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 03/14] drm: manager to keep track of GPUs VA mappings Danilo Krummrich
2023-06-07 4:36 ` kernel test robot
2023-06-14 0:29 ` Liam R. Howlett
2023-06-15 14:27 ` Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 04/14] drm: debugfs: provide infrastructure to dump a DRM GPU VA space Danilo Krummrich
2023-06-06 23:55 ` kernel test robot
2023-06-07 20:19 ` kernel test robot
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 05/14] drm/nouveau: new VM_BIND uapi interfaces Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 06/14] drm/nouveau: get vmm via nouveau_cli_vmm() Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 07/14] drm/nouveau: bo: initialize GEM GPU VA interface Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 08/14] drm/nouveau: move usercopy helpers to nouveau_drv.h Danilo Krummrich
2023-06-06 22:31 ` Danilo Krummrich [this message]
2023-06-07 15:42 ` [Nouveau] [PATCH drm-next v4 09/14] drm/nouveau: fence: separate fence alloc and emit kernel test robot
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 10/14] drm/nouveau: fence: fail to emit when fence context is killed Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 11/14] drm/nouveau: chan: provide nouveau_channel_kill() Danilo Krummrich
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 12/14] drm/nouveau: nvkm/vmm: implement raw ops to manage uvmm Danilo Krummrich
2023-06-07 15:52 ` kernel test robot
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 13/14] drm/nouveau: implement new VM_BIND uAPI Danilo Krummrich
2023-06-08 12:53 ` kernel test robot
2023-06-06 22:31 ` [Nouveau] [PATCH drm-next v4 14/14] drm/nouveau: debugfs: implement DRM GPU VA debugfs Danilo Krummrich
2023-06-14 1:20 ` Liam R. Howlett
2023-06-09 11:56 ` [Nouveau] [PATCH drm-next v4 00/14] [RFC] DRM GPUVA Manager & Nouveau VM_BIND UAPI Donald Robson
2023-06-13 14:20 ` Danilo Krummrich
2023-06-14 7:58 ` Donald Robson
2023-06-15 16:31 ` Danilo Krummrich
2023-06-15 16:39 ` Danilo Krummrich
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230606223130.6132-10-dakr@redhat.com \
--to=dakr@redhat.com \
--cc=Liam.Howlett@oracle.com \
--cc=airlied@gmail.com \
--cc=alexdeucher@gmail.com \
--cc=bagasdotme@gmail.com \
--cc=boris.brezillon@collabora.com \
--cc=bskeggs@redhat.com \
--cc=christian.koenig@amd.com \
--cc=corbet@lwn.net \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=jason@jlekstrand.net \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=matthew.brost@intel.com \
--cc=mripard@kernel.org \
--cc=nouveau@lists.freedesktop.org \
--cc=ogabbay@kernel.org \
--cc=tzimmermann@suse.de \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).