On Sun, Oct 4, 2020 at 9:21 PM Rob Clark wrote:
>
> From: Rob Clark
>
> Rather than relying on the big dev->struct_mutex hammer, introduce a
> more specific lock for protecting the bo lists.
>
> Signed-off-by: Rob Clark
> ---
> drivers/gpu/drm/msm/msm_debugfs.c | 7 +++
> drivers/gpu/drm/msm/msm_drv.c | 1 +
> drivers/gpu/drm/msm/msm_drv.h | 13 +++-
> drivers/gpu/drm/msm/msm_gem.c | 28 +++---
> drivers/gpu/drm/msm/msm_gem_shrinker.c | 12 +++
> drivers/gpu/drm/msm/msm_gpu.h | 5 -
> 6 files changed, 52 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/msm/msm_debugfs.c
> b/drivers/gpu/drm/msm/msm_debugfs.c
> index ee2e270f464c..64afbed89821 100644
> --- a/drivers/gpu/drm/msm/msm_debugfs.c
> +++ b/drivers/gpu/drm/msm/msm_debugfs.c
> @@ -112,6 +112,11 @@ static int msm_gem_show(struct drm_device *dev, struct
> seq_file *m)
> {
> struct msm_drm_private *priv = dev->dev_private;
> struct msm_gpu *gpu = priv->gpu;
> + int ret;
> +
> + ret = mutex_lock_interruptible(>mm_lock);
> + if (ret)
> + return ret;
>
> if (gpu) {
> seq_printf(m, "Active Objects (%s):\n", gpu->name);
> @@ -121,6 +126,8 @@ static int msm_gem_show(struct drm_device *dev, struct
> seq_file *m)
> seq_printf(m, "Inactive Objects:\n");
> msm_gem_describe_objects(>inactive_list, m);
>
> + mutex_unlock(>mm_lock);
> +
> return 0;
> }
>
> diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
> index 49685571dc0e..dc6efc089285 100644
> --- a/drivers/gpu/drm/msm/msm_drv.c
> +++ b/drivers/gpu/drm/msm/msm_drv.c
> @@ -441,6 +441,7 @@ static int msm_drm_init(struct device *dev, struct
> drm_driver *drv)
> init_llist_head(>free_list);
>
> INIT_LIST_HEAD(>inactive_list);
> + mutex_init(>mm_lock);
I highly recommend you drop a
fs_reclaim_acquire(GFP_KERNEL);
might_lock(>mm_lock);
fs_reclaim_release(GFP_KERNEL);
in here to teach lockdep about your ordering against the shrinker.
Gives you full testing every boot, even if your shrinker never gets
called.
-Daniel
>
> drm_mode_config_init(ddev);
>
> diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
> index b9dd8f8f4887..50978e5db376 100644
> --- a/drivers/gpu/drm/msm/msm_drv.h
> +++ b/drivers/gpu/drm/msm/msm_drv.h
> @@ -174,8 +174,19 @@ struct msm_drm_private {
> struct msm_rd_state *hangrd; /* debugfs to dump hanging submits */
> struct msm_perf_state *perf;
>
> - /* list of GEM objects: */
> + /*
> +* List of inactive GEM objects. Every bo is either in the
> inactive_list
> +* or gpu->active_list (for the gpu it is active on[1])
> +*
> +* These lists are protected by mm_lock. If struct_mutex is
> involved, it
> +* should be aquired prior to mm_lock. One should *not* hold mm_lock
> in
> +* get_pages()/vmap()/etc paths, as they can trigger the shrinker.
> +*
> +* [1] if someone ever added support for the old 2d cores, there
> could be
> +* more than one gpu object
> +*/
> struct list_head inactive_list;
> + struct mutex mm_lock;
>
> /* worker for delayed free of objects: */
> struct work_struct free_work;
> diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
> index a870b3ad129d..b04ed8b52f9d 100644
> --- a/drivers/gpu/drm/msm/msm_gem.c
> +++ b/drivers/gpu/drm/msm/msm_gem.c
> @@ -746,13 +746,17 @@ int msm_gem_sync_object(struct drm_gem_object *obj,
> void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu)
> {
> struct msm_gem_object *msm_obj = to_msm_bo(obj);
> - WARN_ON(!mutex_is_locked(>dev->struct_mutex));
> + struct msm_drm_private *priv = obj->dev->dev_private;
> +
> + might_sleep();
> WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED);
>
> if (!atomic_fetch_inc(_obj->active_count)) {
> + mutex_lock(>mm_lock);
> msm_obj->gpu = gpu;
> list_del_init(_obj->mm_list);
> list_add_tail(_obj->mm_list, >active_list);
> + mutex_unlock(>mm_lock);
> }
> }
>
> @@ -761,12 +765,14 @@ void msm_gem_active_put(struct drm_gem_object *obj)
> struct msm_gem_object *msm_obj = to_msm_bo(obj);
> struct msm_drm_private *priv = obj->dev->dev_private;
>
> - WARN_ON(!mutex_is_locked(>dev->struct_mutex));
> + might_sleep();
>
> if (!atomic_dec_return(_obj->active_count)) {
> + mutex_lock(>mm_lock);
> msm_obj->gpu = NULL;
> list_del_init(_obj->mm_list);
> list_add_tail(_obj->mm_list, >inactive_list);
> + mutex_unlock(>mm_lock);
> }
> }
>
> @@ -921,13 +927,16 @@ static void free_object(struct msm_gem_object *msm_obj)
> {
