drm/nouveau: don't fini scheduler if not initialized

nouveau_abi16_ioctl_channel_alloc() and nouveau_cli_init() simply call
their corresponding *_fini() counterpart. This can lead to
nouveau_sched_fini() being called without struct nouveau_sched ever
being initialized in the first place.

Instead of embedding struct nouveau_sched into struct nouveau_cli and
struct nouveau_chan_abi16, allocate struct nouveau_sched separately,
such that we can check for the corresponding pointer to be NULL in the
particular *_fini() functions.

It makes sense to allocate struct nouveau_sched separately anyway, since
in a subsequent commit we can also avoid to allocate a struct
nouveau_sched in nouveau_abi16_ioctl_channel_alloc() at all, if the
VM_BIND uAPI has been disabled due to the legacy uAPI being used.

Fixes: 5f03a507b29e ("drm/nouveau: implement 1:1 scheduler - entity relationship")
Reported-by: Timur Tabi <ttabi@nvidia.com>
Tested-by: Timur Tabi <ttabi@nvidia.com>
Closes: https://lore.kernel.org/nouveau/20240131213917.1545604-1-ttabi@nvidia.com/
Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240202000606.3526-1-dakr@redhat.com

diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index a04156ca8390ba6fea6a21e07e9eb5bba3ec7605..ca4b5ab3e59e6c5cb1e7494cd1e8567150b25e51 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -128,12 +128,14 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
        struct nouveau_abi16_ntfy *ntfy, *temp;
 
        /* Cancel all jobs from the entity's queue. */
-       drm_sched_entity_fini(&chan->sched.entity);
+       if (chan->sched)
+               drm_sched_entity_fini(&chan->sched->entity);
 
        if (chan->chan)
                nouveau_channel_idle(chan->chan);
 
-       nouveau_sched_fini(&chan->sched);
+       if (chan->sched)
+               nouveau_sched_destroy(&chan->sched);
 
        /* cleanup notifier state */
        list_for_each_entry_safe(ntfy, temp, &chan->notifiers, head) {
@@ -337,8 +339,8 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS)
        if (ret)
                goto done;
 
-       ret = nouveau_sched_init(&chan->sched, drm, drm->sched_wq,
-                                chan->chan->dma.ib_max);
+       ret = nouveau_sched_create(&chan->sched, drm, drm->sched_wq,
+                                  chan->chan->dma.ib_max);
        if (ret)
                goto done;
 

diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h
index 1f5e243c0c759ef759dbba7d4f89279c90bce5d4..11c8c4a80079bbb2b658816dd42d05f68a5eaab6 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.h
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h
@@ -26,7 +26,7 @@ struct nouveau_abi16_chan {
        struct nouveau_bo *ntfy;
        struct nouveau_vma *ntfy_vma;
        struct nvkm_mm  heap;
-       struct nouveau_sched sched;
+       struct nouveau_sched *sched;
 };
 
 struct nouveau_abi16 {

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 6f6c31a9937b2fe751c6cffe429cc21a6b47a385..a947e1d5f309ae525e8087d13899f1efd1e8e73b 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -201,7 +201,8 @@ nouveau_cli_fini(struct nouveau_cli *cli)
        WARN_ON(!list_empty(&cli->worker));
 
        usif_client_fini(cli);
-       nouveau_sched_fini(&cli->sched);
+       if (cli->sched)
+               nouveau_sched_destroy(&cli->sched);
        if (uvmm)
                nouveau_uvmm_fini(uvmm);
        nouveau_vmm_fini(&cli->svm);
@@ -311,7 +312,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
        cli->mem = &mems[ret];
 
        /* Don't pass in the (shared) sched_wq in order to let
-        * nouveau_sched_init() create a dedicated one for VM_BIND jobs.
+        * nouveau_sched_create() create a dedicated one for VM_BIND jobs.
         *
         * This is required to ensure that for VM_BIND jobs free_job() work and
         * run_job() work can always run concurrently and hence, free_job() work
@@ -320,7 +321,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname,
         * locks which indirectly or directly are held for allocations
         * elsewhere.
         */
-       ret = nouveau_sched_init(&cli->sched, drm, NULL, 1);
+       ret = nouveau_sched_create(&cli->sched, drm, NULL, 1);
        if (ret)
                goto done;
 

diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 8a6d94c8b1631fd7ab8bbc193f35b064057a0185..e239c6bf4afa4f75d4ca30c63583af82f2ab9621 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -98,7 +98,7 @@ struct nouveau_cli {
                bool disabled;
        } uvmm;
 
-       struct nouveau_sched sched;
+       struct nouveau_sched *sched;
 
        const struct nvif_mclass *mem;
 

diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c
index bc5d71b79ab203ff7e874c612f3ea1e7c36323de..e65c0ef23bc73d59f3066ff02ae9360253b93e6d 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_exec.c
+++ b/drivers/gpu/drm/nouveau/nouveau_exec.c
@@ -389,7 +389,7 @@ nouveau_exec_ioctl_exec(struct drm_device *dev,
        if (ret)
                goto out;
 
-       args.sched = &chan16->sched;
+       args.sched = chan16->sched;
        args.file_priv = file_priv;
        args.chan = chan;
 

diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c
index dd98f6910f9cab7b19117186339a138277e77b78..32fa2e273965bf140a4cb2e05262b638c312cd6e 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_sched.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.c
@@ -398,7 +398,7 @@ static const struct drm_sched_backend_ops nouveau_sched_ops = {
        .free_job = nouveau_sched_free_job,
 };
 
-int
+static int
 nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
                   struct workqueue_struct *wq, u32 credit_limit)
 {
@@ -453,7 +453,30 @@ fail_wq:
        return ret;
 }
 
-void
+int
+nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+                    struct workqueue_struct *wq, u32 credit_limit)
+{
+       struct nouveau_sched *sched;
+       int ret;
+
+       sched = kzalloc(sizeof(*sched), GFP_KERNEL);
+       if (!sched)
+               return -ENOMEM;
+
+       ret = nouveau_sched_init(sched, drm, wq, credit_limit);
+       if (ret) {
+               kfree(sched);
+               return ret;
+       }
+
+       *psched = sched;
+
+       return 0;
+}
+
+
+static void
 nouveau_sched_fini(struct nouveau_sched *sched)
 {
        struct drm_gpu_scheduler *drm_sched = &sched->base;
@@ -471,3 +494,14 @@ nouveau_sched_fini(struct nouveau_sched *sched)
        if (sched->wq)
                destroy_workqueue(sched->wq);
 }
+
+void
+nouveau_sched_destroy(struct nouveau_sched **psched)
+{
+       struct nouveau_sched *sched = *psched;
+
+       nouveau_sched_fini(sched);
+       kfree(sched);
+
+       *psched = NULL;
+}

diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h
index a6528f5981e6a6e8182a44e0ec3c0336302e6154..e1f01a23e6f6e84cf2700bde86e4fb5e3e013df1 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_sched.h
+++ b/drivers/gpu/drm/nouveau/nouveau_sched.h
@@ -111,8 +111,8 @@ struct nouveau_sched {
        } job;
 };
 
-int nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm,
-                      struct workqueue_struct *wq, u32 credit_limit);
-void nouveau_sched_fini(struct nouveau_sched *sched);
+int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm,
+                        struct workqueue_struct *wq, u32 credit_limit);
+void nouveau_sched_destroy(struct nouveau_sched **psched);
 
 #endif

diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 4f223c972c6a8cb3bab7873dfa2a1c38756648b2..0a0a11dc9ec03eeba855f47ca57c1ad1c5669f54 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -1740,7 +1740,7 @@ nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev,
        if (ret)
                return ret;
 
-       args.sched = &cli->sched;
+       args.sched = cli->sched;
        args.file_priv = file_priv;
 
        ret = nouveau_uvmm_vm_bind(&args);