13 files changed, 177 insertions, 352 deletions

diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
index 7a1ad3af08e3..20e956e14c21 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
@@ -98,21 +98,6 @@ static const struct drm_plane_funcs mdp4_plane_funcs = {
                 .atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
 };
 
-static int mdp4_plane_prepare_fb(struct drm_plane *plane,
-                                 struct drm_plane_state *new_state)
-{
-        struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
-        struct mdp4_kms *mdp4_kms = get_kms(plane);
-        struct msm_kms *kms = &mdp4_kms->base.base;
-        struct drm_framebuffer *fb = new_state->fb;
-
-        if (!fb)
-                return 0;
-
-        DBG("%s: prepare: FB[%u]", mdp4_plane->name, fb->base.id);
-        return msm_framebuffer_prepare(fb, kms->aspace);
-}
-
 static void mdp4_plane_cleanup_fb(struct drm_plane *plane,
                                   struct drm_plane_state *old_state)
 {
@@ -152,7 +137,7 @@ static void mdp4_plane_atomic_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs mdp4_plane_helper_funcs = {
-                .prepare_fb = mdp4_plane_prepare_fb,
+                .prepare_fb = msm_atomic_prepare_fb,
                 .cleanup_fb = mdp4_plane_cleanup_fb,
                 .atomic_check = mdp4_plane_atomic_check,
                 .atomic_update = mdp4_plane_atomic_update,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 76b96081916f..10271359789e 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -430,6 +430,7 @@ static void mdp5_crtc_atomic_disable(struct drm_crtc *crtc,
         struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc->state);
         struct mdp5_kms *mdp5_kms = get_kms(crtc);
         struct device *dev = &mdp5_kms->pdev->dev;
+        unsigned long flags;
 
         DBG("%s", crtc->name);
 
@@ -445,6 +446,14 @@ static void mdp5_crtc_atomic_disable(struct drm_crtc *crtc,
         mdp_irq_unregister(&mdp5_kms->base, &mdp5_crtc->err);
         pm_runtime_put_sync(dev);
 
+        if (crtc->state->event && !crtc->state->active) {
+                WARN_ON(mdp5_crtc->event);
+                spin_lock_irqsave(&mdp5_kms->dev->event_lock, flags);
+                drm_crtc_send_vblank_event(crtc, crtc->state->event);
+                crtc->state->event = NULL;
+                spin_unlock_irqrestore(&mdp5_kms->dev->event_lock, flags);
+        }
+
         mdp5_crtc->enabled = false;
 }
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 6d8e3a9a6fc0..6e12e275deba 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -70,60 +70,110 @@ static int mdp5_hw_init(struct msm_kms *kms)
         return 0;
 }
 
-struct mdp5_state *mdp5_get_state(struct drm_atomic_state *s)
+/* Global/shared object state funcs */
+
+/*
+ * This is a helper that returns the private state currently in operation.
+ * Note that this would return the "old_state" if called in the atomic check
+ * path, and the "new_state" after the atomic swap has been done.
+ */
+struct mdp5_global_state *
+mdp5_get_existing_global_state(struct mdp5_kms *mdp5_kms)
+{
+        return to_mdp5_global_state(mdp5_kms->glob_state.state);
+}
+
+/*
+ * This acquires the modeset lock set aside for global state, creates
+ * a new duplicated private object state.
+ */
+struct mdp5_global_state *mdp5_get_global_state(struct drm_atomic_state *s)
 {
         struct msm_drm_private *priv = s->dev->dev_private;
         struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms));
-        struct msm_kms_state *state = to_kms_state(s);
-        struct mdp5_state *new_state;
+        struct drm_private_state *priv_state;
         int ret;
 
-        if (state->state)
-                return state->state;
-
-        ret = drm_modeset_lock(&mdp5_kms->state_lock, s->acquire_ctx);
+        ret = drm_modeset_lock(&mdp5_kms->glob_state_lock, s->acquire_ctx);
         if (ret)
                 return ERR_PTR(ret);
 
-        new_state = kmalloc(sizeof(*mdp5_kms->state), GFP_KERNEL);
-        if (!new_state)
-                return ERR_PTR(-ENOMEM);
+        priv_state = drm_atomic_get_private_obj_state(s, &mdp5_kms->glob_state);
+        if (IS_ERR(priv_state))
+                return ERR_CAST(priv_state);
 
-        /* Copy state: */
-        new_state->hwpipe = mdp5_kms->state->hwpipe;
-        new_state->hwmixer = mdp5_kms->state->hwmixer;
-        if (mdp5_kms->smp)
-                new_state->smp = mdp5_kms->state->smp;
+        return to_mdp5_global_state(priv_state);
+}
+
+static struct drm_private_state *
+mdp5_global_duplicate_state(struct drm_private_obj *obj)
+{
+        struct mdp5_global_state *state;
+
+        state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL);
+        if (!state)
+                return NULL;
 
-        state->state = new_state;
+        __drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
 
-        return new_state;
+        return &state->base;
 }
 
-static void mdp5_swap_state(struct msm_kms *kms, struct drm_atomic_state *state)
+static void mdp5_global_destroy_state(struct drm_private_obj *obj,
+                                      struct drm_private_state *state)
 {
-        struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
-        swap(to_kms_state(state)->state, mdp5_kms->state);
+        struct mdp5_global_state *mdp5_state = to_mdp5_global_state(state);
+
+        kfree(mdp5_state);
+}
+
+static const struct drm_private_state_funcs mdp5_global_state_funcs = {
+        .atomic_duplicate_state = mdp5_global_duplicate_state,
+        .atomic_destroy_state = mdp5_global_destroy_state,
+};
+
+static int mdp5_global_obj_init(struct mdp5_kms *mdp5_kms)
+{
+        struct mdp5_global_state *state;
+
+        drm_modeset_lock_init(&mdp5_kms->glob_state_lock);
+
+        state = kzalloc(sizeof(*state), GFP_KERNEL);
+        if (!state)
+                return -ENOMEM;
+
+        state->mdp5_kms = mdp5_kms;
+
+        drm_atomic_private_obj_init(&mdp5_kms->glob_state,
+                                    &state->base,
+                                    &mdp5_global_state_funcs);
+        return 0;
 }
 
 static void mdp5_prepare_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
         struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
         struct device *dev = &mdp5_kms->pdev->dev;
+        struct mdp5_global_state *global_state;
+
+        global_state = mdp5_get_existing_global_state(mdp5_kms);
 
         pm_runtime_get_sync(dev);
 
         if (mdp5_kms->smp)
-                mdp5_smp_prepare_commit(mdp5_kms->smp, &mdp5_kms->state->smp);
+                mdp5_smp_prepare_commit(mdp5_kms->smp, &global_state->smp);
 }
 
 static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
         struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
         struct device *dev = &mdp5_kms->pdev->dev;
+        struct mdp5_global_state *global_state;
+
+        global_state = mdp5_get_existing_global_state(mdp5_kms);
 
         if (mdp5_kms->smp)
-                mdp5_smp_complete_commit(mdp5_kms->smp, &mdp5_kms->state->smp);
+                mdp5_smp_complete_commit(mdp5_kms->smp, &global_state->smp);
 
         pm_runtime_put_sync(dev);
 }
@@ -229,7 +279,6 @@ static const struct mdp_kms_funcs kms_funcs = {
                 .irq             = mdp5_irq,
                 .enable_vblank   = mdp5_enable_vblank,
                 .disable_vblank  = mdp5_disable_vblank,
-                .swap_state      = mdp5_swap_state,
                 .prepare_commit  = mdp5_prepare_commit,
                 .complete_commit = mdp5_complete_commit,
                 .wait_for_crtc_commit_done = mdp5_wait_for_crtc_commit_done,
@@ -727,7 +776,8 @@ static void mdp5_destroy(struct platform_device *pdev)
         if (mdp5_kms->rpm_enabled)
                 pm_runtime_disable(&pdev->dev);
 
-        kfree(mdp5_kms->state);
+        drm_atomic_private_obj_fini(&mdp5_kms->glob_state);
+        drm_modeset_lock_fini(&mdp5_kms->glob_state_lock);
 }
 
 static int construct_pipes(struct mdp5_kms *mdp5_kms, int cnt,
@@ -880,12 +930,9 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
         mdp5_kms->dev = dev;
         mdp5_kms->pdev = pdev;
 
-        drm_modeset_lock_init(&mdp5_kms->state_lock);
-        mdp5_kms->state = kzalloc(sizeof(*mdp5_kms->state), GFP_KERNEL);
-        if (!mdp5_kms->state) {
-                ret = -ENOMEM;
+        ret = mdp5_global_obj_init(mdp5_kms);
+        if (ret)
                 goto fail;
-        }
 
         mdp5_kms->mmio = msm_ioremap(pdev, "mdp_phys", "MDP5");
         if (IS_ERR(mdp5_kms->mmio)) {
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
index 425a03d213e5..854dfd30e829 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
@@ -28,8 +28,6 @@
 #include "mdp5_ctl.h"
 #include "mdp5_smp.h"
 
-struct mdp5_state;
-
 struct mdp5_kms {
         struct mdp_kms base;
 
@@ -49,11 +47,12 @@ struct mdp5_kms {
         struct mdp5_cfg_handler *cfg;
         uint32_t caps;  /* MDP capabilities (MDP_CAP_XXX bits) */
 
-        /**
-         * Global atomic state.  Do not access directly, use mdp5_get_state()
+        /*
+         * Global private object state, Do not access directly, use
+         * mdp5_global_get_state()
          */
-        struct mdp5_state *state;
-        struct drm_modeset_lock state_lock;
+        struct drm_modeset_lock glob_state_lock;
+        struct drm_private_obj glob_state;
 
         struct mdp5_smp *smp;
         struct mdp5_ctl_manager *ctlm;
@@ -81,19 +80,23 @@ struct mdp5_kms {
 };
 #define to_mdp5_kms(x) container_of(x, struct mdp5_kms, base)
 
-/* Global atomic state for tracking resources that are shared across
+/* Global private object state for tracking resources that are shared across
  * multiple kms objects (planes/crtcs/etc).
- *
- * For atomic updates which require modifying global state,
  */
-struct mdp5_state {
+#define to_mdp5_global_state(x) container_of(x, struct mdp5_global_state, base)
+struct mdp5_global_state {
+        struct drm_private_state base;
+
+        struct drm_atomic_state *state;
+        struct mdp5_kms *mdp5_kms;
+
         struct mdp5_hw_pipe_state hwpipe;
         struct mdp5_hw_mixer_state hwmixer;
         struct mdp5_smp_state smp;
 };
 
-struct mdp5_state *__must_check
-mdp5_get_state(struct drm_atomic_state *s);
+struct mdp5_global_state * mdp5_get_existing_global_state(struct mdp5_kms *mdp5_kms);
+struct mdp5_global_state *__must_check mdp5_get_global_state(struct drm_atomic_state *s);
 
 /* Atomic plane state.  Subclasses the base drm_plane_state in order to
  * track assigned hwpipe and hw specific state.
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mixer.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mixer.c
index 8a00991f03c7..113e6b569562 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mixer.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mixer.c
@@ -52,14 +52,14 @@ int mdp5_mixer_assign(struct drm_atomic_state *s, struct drm_crtc *crtc,
 {
         struct msm_drm_private *priv = s->dev->dev_private;
         struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms));
-        struct mdp5_state *state = mdp5_get_state(s);
+        struct mdp5_global_state *global_state = mdp5_get_global_state(s);
         struct mdp5_hw_mixer_state *new_state;
         int i;
 
-        if (IS_ERR(state))
-                return PTR_ERR(state);
+        if (IS_ERR(global_state))
+                return PTR_ERR(global_state);
 
-        new_state = &state->hwmixer;
+        new_state = &global_state->hwmixer;
 
         for (i = 0; i < mdp5_kms->num_hwmixers; i++) {
                 struct mdp5_hw_mixer *cur = mdp5_kms->hwmixers[i];
@@ -129,8 +129,8 @@ int mdp5_mixer_assign(struct drm_atomic_state *s, struct drm_crtc *crtc,
 
 void mdp5_mixer_release(struct drm_atomic_state *s, struct mdp5_hw_mixer *mixer)
 {
-        struct mdp5_state *state = mdp5_get_state(s);
-        struct mdp5_hw_mixer_state *new_state = &state->hwmixer;
+        struct mdp5_global_state *global_state = mdp5_get_global_state(s);
+        struct mdp5_hw_mixer_state *new_state = &global_state->hwmixer;
 
         if (!mixer)
                 return;
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c
index ff52c49095f9..1ef26bc63163 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_pipe.c
@@ -24,17 +24,19 @@ int mdp5_pipe_assign(struct drm_atomic_state *s, struct drm_plane *plane,
 {
         struct msm_drm_private *priv = s->dev->dev_private;
         struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms));
-        struct mdp5_state *state;
+        struct mdp5_global_state *new_global_state, *old_global_state;
         struct mdp5_hw_pipe_state *old_state, *new_state;
         int i, j;
 
-        state = mdp5_get_state(s);
-        if (IS_ERR(state))
-                return PTR_ERR(state);
+        new_global_state = mdp5_get_global_state(s);
+        if (IS_ERR(new_global_state))
+                return PTR_ERR(new_global_state);
 
-        /* grab old_state after mdp5_get_state(), since now we hold lock: */
-        old_state = &mdp5_kms->state->hwpipe;
-        new_state = &state->hwpipe;
+        /* grab old_state after mdp5_get_global_state(), since now we hold lock: */
+        old_global_state = mdp5_get_existing_global_state(mdp5_kms);
+
+        old_state = &old_global_state->hwpipe;
+        new_state = &new_global_state->hwpipe;
 
         for (i = 0; i < mdp5_kms->num_hwpipes; i++) {
                 struct mdp5_hw_pipe *cur = mdp5_kms->hwpipes[i];
@@ -107,7 +109,7 @@ int mdp5_pipe_assign(struct drm_atomic_state *s, struct drm_plane *plane,
                 WARN_ON(r_hwpipe);
 
                 DBG("%s: alloc SMP blocks", (*hwpipe)->name);
-                ret = mdp5_smp_assign(mdp5_kms->smp, &state->smp,
+                ret = mdp5_smp_assign(mdp5_kms->smp, &new_global_state->smp,
                                 (*hwpipe)->pipe, blkcfg);
                 if (ret)
                         return -ENOMEM;
@@ -132,7 +134,7 @@ void mdp5_pipe_release(struct drm_atomic_state *s, struct mdp5_hw_pipe *hwpipe)
 {
         struct msm_drm_private *priv = s->dev->dev_private;
         struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(priv->kms));
-        struct mdp5_state *state = mdp5_get_state(s);
+        struct mdp5_global_state *state = mdp5_get_global_state(s);
         struct mdp5_hw_pipe_state *new_state = &state->hwpipe;
 
         if (!hwpipe)
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index a9f31da7d45a..e09bc53a0e65 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -245,20 +245,6 @@ static const struct drm_plane_funcs mdp5_plane_funcs = {
                 .atomic_print_state = mdp5_plane_atomic_print_state,
 };
 
-static int mdp5_plane_prepare_fb(struct drm_plane *plane,
-                                 struct drm_plane_state *new_state)
-{
-        struct mdp5_kms *mdp5_kms = get_kms(plane);
-        struct msm_kms *kms = &mdp5_kms->base.base;
-        struct drm_framebuffer *fb = new_state->fb;
-
-        if (!new_state->fb)
-                return 0;
-
-        DBG("%s: prepare: FB[%u]", plane->name, fb->base.id);
-        return msm_framebuffer_prepare(fb, kms->aspace);
-}
-
 static void mdp5_plane_cleanup_fb(struct drm_plane *plane,
                                   struct drm_plane_state *old_state)
 {
@@ -543,7 +529,7 @@ static void mdp5_plane_atomic_async_update(struct drm_plane *plane,
 }
 
 static const struct drm_plane_helper_funcs mdp5_plane_helper_funcs = {
-                .prepare_fb = mdp5_plane_prepare_fb,
+                .prepare_fb = msm_atomic_prepare_fb,
                 .cleanup_fb = mdp5_plane_cleanup_fb,
                 .atomic_check = mdp5_plane_atomic_check,
                 .atomic_update = mdp5_plane_atomic_update,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
index ae4983d9d0a5..96c2b828dba4 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
@@ -340,17 +340,20 @@ void mdp5_smp_dump(struct mdp5_smp *smp, struct drm_printer *p)
         struct mdp5_kms *mdp5_kms = get_kms(smp);
         struct mdp5_hw_pipe_state *hwpstate;
         struct mdp5_smp_state *state;
+        struct mdp5_global_state *global_state;
         int total = 0, i, j;
 
         drm_printf(p, "name\tinuse\tplane\n");
         drm_printf(p, "----\t-----\t-----\n");
 
         if (drm_can_sleep())
-                drm_modeset_lock(&mdp5_kms->state_lock, NULL);
+                drm_modeset_lock(&mdp5_kms->glob_state_lock, NULL);
+
+        global_state = mdp5_get_existing_global_state(mdp5_kms);
 
         /* grab these *after* we hold the state_lock */
-        hwpstate = &mdp5_kms->state->hwpipe;
-        state = &mdp5_kms->state->smp;
+        hwpstate = &global_state->hwpipe;
+        state = &global_state->smp;
 
         for (i = 0; i < mdp5_kms->num_hwpipes; i++) {
                 struct mdp5_hw_pipe *hwpipe = mdp5_kms->hwpipes[i];
@@ -374,7 +377,7 @@ void mdp5_smp_dump(struct mdp5_smp *smp, struct drm_printer *p)
                         bitmap_weight(state->state, smp->blk_cnt));
 
         if (drm_can_sleep())
-                drm_modeset_unlock(&mdp5_kms->state_lock);
+                drm_modeset_unlock(&mdp5_kms->glob_state_lock);
 }
 
 void mdp5_smp_destroy(struct mdp5_smp *smp)
@@ -384,7 +387,8 @@ void mdp5_smp_destroy(struct mdp5_smp *smp)
 
 struct mdp5_smp *mdp5_smp_init(struct mdp5_kms *mdp5_kms, const struct mdp5_smp_block *cfg)
 {
-        struct mdp5_smp_state *state = &mdp5_kms->state->smp;
+        struct mdp5_smp_state *state;
+        struct mdp5_global_state *global_state;
         struct mdp5_smp *smp = NULL;
         int ret;
 
@@ -398,6 +402,9 @@ struct mdp5_smp *mdp5_smp_init(struct mdp5_kms *mdp5_kms, const struct mdp5_smp_
         smp->blk_cnt = cfg->mmb_count;
         smp->blk_size = cfg->mmb_size;
 
+        global_state = mdp5_get_existing_global_state(mdp5_kms);
+        state = &global_state->smp;
+
         /* statically tied MMBs cannot be re-allocated: */
         bitmap_copy(state->state, cfg->reserved_state, smp->blk_cnt);
         memcpy(smp->reserved, cfg->reserved, sizeof(smp->reserved));
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 8baba30d6c65..2f1a2780658a 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1036,7 +1036,6 @@ static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
 
                 ret = msm_gem_get_iova(msm_host->tx_gem_obj,
                                 priv->kms->aspace, &iova);
-                mutex_unlock(&dev->struct_mutex);
                 if (ret) {
                         pr_err("%s: failed to get iova, %d\n", __func__, ret);
                         return ret;
@@ -1067,9 +1066,20 @@ static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
 static void dsi_tx_buf_free(struct msm_dsi_host *msm_host)
 {
         struct drm_device *dev = msm_host->dev;
+        struct msm_drm_private *priv;
 
+        /*
+         * This is possible if we're tearing down before we've had a chance to
+         * fully initialize. A very real possibility if our probe is deferred,
+         * in which case we'll hit msm_dsi_host_destroy() without having run
+         * through the dsi_tx_buf_alloc().
+         */
+        if (!dev)
+                return;
+
+        priv = dev->dev_private;
         if (msm_host->tx_gem_obj) {
-                msm_gem_put_iova(msm_host->tx_gem_obj, 0);
+                msm_gem_put_iova(msm_host->tx_gem_obj, priv->kms->aspace);
                 drm_gem_object_put_unlocked(msm_host->tx_gem_obj);
                 msm_host->tx_gem_obj = NULL;
         }
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index bf5f8c39f34d..f0635c3da7f4 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -16,69 +16,8 @@
  */
 
 #include "msm_drv.h"
-#include "msm_kms.h"
 #include "msm_gem.h"
-#include "msm_fence.h"
-
-struct msm_commit {
-        struct drm_device *dev;
-        struct drm_atomic_state *state;
-        struct work_struct work;
-        uint32_t crtc_mask;
-};
-
-static void commit_worker(struct work_struct *work);
-
-/* block until specified crtcs are no longer pending update, and
- * atomically mark them as pending update
- */
-static int start_atomic(struct msm_drm_private *priv, uint32_t crtc_mask)
-{
-        int ret;
-
-        spin_lock(&priv->pending_crtcs_event.lock);
-        ret = wait_event_interruptible_locked(priv->pending_crtcs_event,
-                        !(priv->pending_crtcs & crtc_mask));
-        if (ret == 0) {
-                DBG("start: %08x", crtc_mask);
-                priv->pending_crtcs |= crtc_mask;
-        }
-        spin_unlock(&priv->pending_crtcs_event.lock);
-
-        return ret;
-}
-
-/* clear specified crtcs (no longer pending update)
- */
-static void end_atomic(struct msm_drm_private *priv, uint32_t crtc_mask)
-{
-        spin_lock(&priv->pending_crtcs_event.lock);
-        DBG("end: %08x", crtc_mask);
-        priv->pending_crtcs &= ~crtc_mask;
-        wake_up_all_locked(&priv->pending_crtcs_event);
-        spin_unlock(&priv->pending_crtcs_event.lock);
-}
-
-static struct msm_commit *commit_init(struct drm_atomic_state *state)
-{
-        struct msm_commit *c = kzalloc(sizeof(*c), GFP_KERNEL);
-
-        if (!c)
-                return NULL;
-
-        c->dev = state->dev;
-        c->state = state;
-
-        INIT_WORK(&c->work, commit_worker);
-
-        return c;
-}
-
-static void commit_destroy(struct msm_commit *c)
-{
-        end_atomic(c->dev->dev_private, c->crtc_mask);
-        kfree(c);
-}
+#include "msm_kms.h"
 
 static void msm_atomic_wait_for_commit_done(struct drm_device *dev,
                 struct drm_atomic_state *old_state)
@@ -97,195 +36,48 @@ static void msm_atomic_wait_for_commit_done(struct drm_device *dev,
         }
 }
 
-/* The (potentially) asynchronous part of the commit.  At this point
- * nothing can fail short of armageddon.
- */
-static void complete_commit(struct msm_commit *c, bool async)
+int msm_atomic_prepare_fb(struct drm_plane *plane,
+                          struct drm_plane_state *new_state)
 {
-        struct drm_atomic_state *state = c->state;
-        struct drm_device *dev = state->dev;
-        struct msm_drm_private *priv = dev->dev_private;
+        struct msm_drm_private *priv = plane->dev->dev_private;
         struct msm_kms *kms = priv->kms;
+        struct drm_gem_object *obj;
+        struct msm_gem_object *msm_obj;
+        struct dma_fence *fence;
 
-        drm_atomic_helper_wait_for_fences(dev, state, false);
-
-        kms->funcs->prepare_commit(kms, state);
-
-        drm_atomic_helper_commit_modeset_disables(dev, state);
-
-        drm_atomic_helper_commit_planes(dev, state, 0);
-
-        drm_atomic_helper_commit_modeset_enables(dev, state);
-
-        /* NOTE: _wait_for_vblanks() only waits for vblank on
-         * enabled CRTCs.  So we end up faulting when disabling
-         * due to (potentially) unref'ing the outgoing fb's
-         * before the vblank when the disable has latched.
-         *
-         * But if it did wait on disabled (or newly disabled)
-         * CRTCs, that would be racy (ie. we could have missed
-         * the irq.  We need some way to poll for pipe shut
-         * down.  Or just live with occasionally hitting the
-         * timeout in the CRTC disable path (which really should
-         * not be critical path)
-         */
-
-        msm_atomic_wait_for_commit_done(dev, state);
-
-        drm_atomic_helper_cleanup_planes(dev, state);
+        if (!new_state->fb)
+                return 0;
 
-        kms->funcs->complete_commit(kms, state);
+        obj = msm_framebuffer_bo(new_state->fb, 0);
+        msm_obj = to_msm_bo(obj);
+        fence = reservation_object_get_excl_rcu(msm_obj->resv);
 
-        drm_atomic_state_put(state);
+        drm_atomic_set_fence_for_plane(new_state, fence);
 
-        commit_destroy(c);
-}
-
-static void commit_worker(struct work_struct *work)
-{
-        complete_commit(container_of(work, struct msm_commit, work), true);
+        return msm_framebuffer_prepare(new_state->fb, kms->aspace);
 }
 
-/**
- * drm_atomic_helper_commit - commit validated state object
- * @dev: DRM device
- * @state: the driver state object
- * @nonblock: nonblocking commit
- *
- * This function commits a with drm_atomic_helper_check() pre-validated state
- * object. This can still fail when e.g. the framebuffer reservation fails.
- *
- * RETURNS
- * Zero for success or -errno.
- */
-int msm_atomic_commit(struct drm_device *dev,
-                struct drm_atomic_state *state, bool nonblock)
+void msm_atomic_commit_tail(struct drm_atomic_state *state)
 {
+        struct drm_device *dev = state->dev;
         struct msm_drm_private *priv = dev->dev_private;
-        struct msm_commit *c;
-        struct drm_crtc *crtc;
-        struct drm_crtc_state *crtc_state;
-        struct drm_plane *plane;
-        struct drm_plane_state *old_plane_state, *new_plane_state;
-        int i, ret;
-
-        ret = drm_atomic_helper_prepare_planes(dev, state);
-        if (ret)
-                return ret;
-
-        /*
-         * Note that plane->atomic_async_check() should fail if we need
-         * to re-assign hwpipe or anything that touches global atomic
-         * state, so we'll never go down the async update path in those
-         * cases.
-         */
-        if (state->async_update) {
-                drm_atomic_helper_async_commit(dev, state);
-                drm_atomic_helper_cleanup_planes(dev, state);
-                return 0;
-        }
-
-        c = commit_init(state);
-        if (!c) {
-                ret = -ENOMEM;
-                goto error;
-        }
-
-        /*
-         * Figure out what crtcs we have:
-         */
-        for_each_new_crtc_in_state(state, crtc, crtc_state, i)
-                c->crtc_mask |= drm_crtc_mask(crtc);
-
-        /*
-         * Figure out what fence to wait for:
-         */
-        for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
-                if ((new_plane_state->fb != old_plane_state->fb) && new_plane_state->fb) {
-                        struct drm_gem_object *obj = msm_framebuffer_bo(new_plane_state->fb, 0);
-                        struct msm_gem_object *msm_obj = to_msm_bo(obj);
-                        struct dma_fence *fence = reservation_object_get_excl_rcu(msm_obj->resv);
+        struct msm_kms *kms = priv->kms;
 
-                        drm_atomic_set_fence_for_plane(new_plane_state, fence);
-                }
-        }
+        kms->funcs->prepare_commit(kms, state);
 
-        /*
-         * Wait for pending updates on any of the same crtc's and then
-         * mark our set of crtc's as busy:
-         */
-        ret = start_atomic(dev->dev_private, c->crtc_mask);
-        if (ret)
-                goto err_free;
+        drm_atomic_helper_commit_modeset_disables(dev, state);
 
-        BUG_ON(drm_atomic_helper_swap_state(state, false) < 0);
+        drm_atomic_helper_commit_planes(dev, state, 0);
 
-        /*
-         * This is the point of no return - everything below never fails except
-         * when the hw goes bonghits. Which means we can commit the new state on
-         * the software side now.
-         *
-         * swap driver private state while still holding state_lock
-         */
-        if (to_kms_state(state)->state)
-                priv->kms->funcs->swap_state(priv->kms, state);
+        drm_atomic_helper_commit_modeset_enables(dev, state);
 
-        /*
-         * Everything below can be run asynchronously without the need to grab
-         * any modeset locks at all under one conditions: It must be guaranteed
-         * that the asynchronous work has either been cancelled (if the driver
-         * supports it, which at least requires that the framebuffers get
-         * cleaned up with drm_atomic_helper_cleanup_planes()) or completed
-         * before the new state gets committed on the software side with
-         * drm_atomic_helper_swap_state().
-         *
-         * This scheme allows new atomic state updates to be prepared and
-         * checked in parallel to the asynchronous completion of the previous
-         * update. Which is important since compositors need to figure out the
-         * composition of the next frame right after having submitted the
-         * current layout.
-         */
+        msm_atomic_wait_for_commit_done(dev, state);
 
-        drm_atomic_state_get(state);
-        if (nonblock) {
-                queue_work(priv->atomic_wq, &c->work);
-                return 0;
-        }
+        kms->funcs->complete_commit(kms, state);
 
-        complete_commit(c, false);
+        drm_atomic_helper_wait_for_vblanks(dev, state);
 
-        return 0;
+        drm_atomic_helper_commit_hw_done(state);
 
-err_free:
-        kfree(c);
-error:
         drm_atomic_helper_cleanup_planes(dev, state);
-        return ret;
-}
-
-struct drm_atomic_state *msm_atomic_state_alloc(struct drm_device *dev)
-{
-        struct msm_kms_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
-
-        if (!state || drm_atomic_state_init(dev, &state->base) < 0) {
-                kfree(state);
-                return NULL;
-        }
-
-        return &state->base;
-}
-
-void msm_atomic_state_clear(struct drm_atomic_state *s)
-{
-        struct msm_kms_state *state = to_kms_state(s);
-        drm_atomic_state_default_clear(&state->base);
-        kfree(state->state);
-        state->state = NULL;
-}
-
-void msm_atomic_state_free(struct drm_atomic_state *state)
-{
-        kfree(to_kms_state(state)->state);
-        drm_atomic_state_default_release(state);
-        kfree(state);
 }
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 30cd514d8f7c..021a0b6f9a59 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -41,10 +41,11 @@ static const struct drm_mode_config_funcs mode_config_funcs = {
         .fb_create = msm_framebuffer_create,
         .output_poll_changed = drm_fb_helper_output_poll_changed,
         .atomic_check = drm_atomic_helper_check,
-        .atomic_commit = msm_atomic_commit,
-        .atomic_state_alloc = msm_atomic_state_alloc,
-        .atomic_state_clear = msm_atomic_state_clear,
-        .atomic_state_free = msm_atomic_state_free,
+        .atomic_commit = drm_atomic_helper_commit,
+};
+
+static const struct drm_mode_config_helper_funcs mode_config_helper_funcs = {
+        .atomic_commit_tail = msm_atomic_commit_tail,
 };
 
 #ifdef CONFIG_DRM_MSM_REGISTER_LOGGING
@@ -384,7 +385,6 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
         priv->wq = alloc_ordered_workqueue("msm", 0);
         priv->atomic_wq = alloc_ordered_workqueue("msm:atomic", 0);
-        init_waitqueue_head(&priv->pending_crtcs_event);
 
         INIT_LIST_HEAD(&priv->inactive_list);
         INIT_LIST_HEAD(&priv->vblank_ctrl.event_list);
@@ -442,6 +442,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
         }
 
         ddev->mode_config.funcs = &mode_config_funcs;
+        ddev->mode_config.helper_private = &mode_config_helper_funcs;
 
         ret = drm_vblank_init(ddev, priv->num_crtcs);
         if (ret < 0) {
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 48ed5b9a8580..b2da1fbf81e0 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -117,10 +117,6 @@ struct msm_drm_private {
         struct workqueue_struct *wq;
         struct workqueue_struct *atomic_wq;
 
-        /* crtcs pending async atomic updates: */
-        uint32_t pending_crtcs;
-        wait_queue_head_t pending_crtcs_event;
-
         unsigned int num_planes;
         struct drm_plane *planes[16];
 
@@ -160,8 +156,9 @@ struct msm_format {
         uint32_t pixel_format;
 };
 
-int msm_atomic_commit(struct drm_device *dev,
-                struct drm_atomic_state *state, bool nonblock);
+int msm_atomic_prepare_fb(struct drm_plane *plane,
+                          struct drm_plane_state *new_state);
+void msm_atomic_commit_tail(struct drm_atomic_state *state);
 struct drm_atomic_state *msm_atomic_state_alloc(struct drm_device *dev);
 void msm_atomic_state_clear(struct drm_atomic_state *state);
 void msm_atomic_state_free(struct drm_atomic_state *state);
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index aaa329dc020e..dfd92947de2c 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -40,8 +40,6 @@ struct msm_kms_funcs {
         irqreturn_t (*irq)(struct msm_kms *kms);
         int (*enable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc);
         void (*disable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc);
-        /* swap global atomic state: */
-        void (*swap_state)(struct msm_kms *kms, struct drm_atomic_state *state);
         /* modeset, bracketing atomic_commit(): */
         void (*prepare_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
         void (*complete_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
@@ -80,18 +78,6 @@ struct msm_kms {
         struct msm_gem_address_space *aspace;
 };
 
-/**
- * Subclass of drm_atomic_state, to allow kms backend to have driver
- * private global state.  The kms backend can do whatever it wants
- * with the ->state ptr.  On ->atomic_state_clear() the ->state ptr
- * is kfree'd and set back to NULL.
- */
-struct msm_kms_state {
-        struct drm_atomic_state base;
-        void *state;
-};
-#define to_kms_state(x) container_of(x, struct msm_kms_state, base)
-
 static inline void msm_kms_init(struct msm_kms *kms,
                 const struct msm_kms_funcs *funcs)
 {