[PATCH v15 4/7] drm/i915: Refactor intel_can_enable_sagv

Stanislav Lisovskiy stanislav.lisovskiy at intel.com
Tue Feb 18 14:47:27 UTC 2020


Currently intel_can_enable_sagv function contains
a mix of workarounds for different platforms
some of them are not valid for gens >= 11 already,
so lets split it into separate functions.

v2:
    - Rework watermark calculation algorithm to
      attempt to calculate Level 0 watermark
      with added sagv block time latency and
      check if it fits in DBuf in order to
      determine if SAGV can be enabled already
      at this stage, just as BSpec 49325 states.
      if that fails rollback to usual Level 0
      latency and disable SAGV.
    - Remove unneeded tabs(James Ausmus)

v3: Rebased the patch

v4: - Added back interlaced check for Gen12 and
      added separate function for TGL SAGV check
      (thanks to James Ausmus for spotting)
    - Removed unneeded gen check
    - Extracted Gen12 SAGV decision making code
      to a separate function from skl_compute_wm

v5: - Added SAGV global state to dev_priv, because
      we need to track all pipes, not only those
      in atomic state. Each pipe has now correspondent
      bit mask reflecting, whether it can tolerate
      SAGV or not(thanks to Ville Syrjala for suggestions).
    - Now using active flag instead of enable in crc
      usage check.

v6: - Fixed rebase conflicts

v7: - kms_cursor_legacy seems to get broken because of multiple memcpy
      calls when copying level 0 water marks for enabled SAGV, to
      fix this now simply using that field right away, without copying,
      for that introduced a new wm_level accessor which decides which
      wm_level to return based on SAGV state.

v8: - Protect crtc_sagv_mask same way as we do for other global state
      changes: i.e check if changes are needed, then grab all crtc locks
      to serialize the changes(Ville Syrjälä)
    - Add crtc_sagv_mask caching in order to avoid needless recalculations
      (Matthew Roper)
    - Put back Gen12 SAGV switch in order to get it enabled in separate
      patch(Matthew Roper)
    - Rename *_set_sagv_mask to *_compute_sagv_mask(Matthew Roper)
    - Check if there are no active pipes in intel_can_enable_sagv
      instead of platform specific functions(Matthew Roper), same
      for intel_has_sagv check.

v9  - Switched to u8 for crtc_sagv_mask(Ville Syrjälä)
    - crtc_sagv_mask now is pipe_sagv_mask(Ville Syrjälä)
    - Extracted sagv checking logic from skl/icl/tgl_compute_sagv_mask
    - Extracted skl_plane_wm_level function and passing latency to
      separate patches(Ville Syrjälä)
    - Removed part of unneeded copy-paste from tgl_check_pipe_fits_sagv_wm
      (Ville Syrjälä)
    - Now using simple assignment for sagv_wm0 as it contains only
      pod types and no pointers(Ville Syrjälä)
    - Fixed intel_can_enable_sagv not to do double duty, now it only
      check SAGV bits by ANDing those between local and global state.
      The SAGV masks are now computed after watermarks are available,
      in order to be able to figure out if ddb ranges are fitting nicely.
      (Ville Syrjälä)
    - Now having uv_sagv_wm0 and sagv_wm0, otherwise we have wrong logic
      when using skl_plane_wm_level accessor, as we had previously for Gen11+
      color plane and regular wm levels, so probably both has to be recalculated
      with additional SAGV block time for Level 0.

v10: - Starting to use new global state for storing pipe_sagv_mask

v11: - Fixed rebase conflict with recent drm-tip
     - Check if we really need to recalculate SAGV mask, otherwise
       bail out without making any changes.

Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy at intel.com>
Cc: Ville Syrjälä <ville.syrjala at intel.com>
Cc: James Ausmus <james.ausmus at intel.com>
---
 drivers/gpu/drm/i915/display/intel_bw.h       |   6 +
 drivers/gpu/drm/i915/display/intel_display.c  |  22 +-
 .../drm/i915/display/intel_display_types.h    |   8 +
 .../gpu/drm/i915/display/intel_global_state.c |  18 +
 .../gpu/drm/i915/display/intel_global_state.h |   2 +
 drivers/gpu/drm/i915/intel_pm.c               | 432 ++++++++++++++++--
 drivers/gpu/drm/i915/intel_pm.h               |   4 +-
 7 files changed, 450 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h
index ac004d6f4276..6c33d3af50a9 100644
--- a/drivers/gpu/drm/i915/display/intel_bw.h
+++ b/drivers/gpu/drm/i915/display/intel_bw.h
@@ -18,6 +18,12 @@ struct intel_crtc_state;
 struct intel_bw_state {
 	struct intel_global_state base;
 
+	/*
+	 * Contains a bit mask, whether correspondent
+	 * pipe allows SAGV or not.
+	 */
+	u8 pipe_sagv_mask;
+
 	unsigned int data_rate[I915_MAX_PIPES];
 	u8 num_active_planes[I915_MAX_PIPES];
 };
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 24542281a73e..ef2e9155090f 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -14105,7 +14105,10 @@ static void verify_wm_state(struct intel_crtc *crtc,
 		/* Watermarks */
 		for (level = 0; level <= max_level; level++) {
 			if (skl_wm_level_equals(&hw_plane_wm->wm[level],
-						&sw_plane_wm->wm[level]))
+						&sw_plane_wm->wm[level]) ||
+			   (skl_wm_level_equals(&hw_plane_wm->wm[level],
+						&sw_plane_wm->sagv_wm0) &&
+			   (level == 0)))
 				continue;
 
 			drm_err(&dev_priv->drm,
@@ -14160,7 +14163,10 @@ static void verify_wm_state(struct intel_crtc *crtc,
 		/* Watermarks */
 		for (level = 0; level <= max_level; level++) {
 			if (skl_wm_level_equals(&hw_plane_wm->wm[level],
-						&sw_plane_wm->wm[level]))
+						&sw_plane_wm->wm[level]) ||
+			   (skl_wm_level_equals(&hw_plane_wm->wm[level],
+						&sw_plane_wm->sagv_wm0) &&
+			   (level == 0)))
 				continue;
 
 			drm_err(&dev_priv->drm,
@@ -15712,8 +15718,9 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		 * SKL workaround: bspec recommends we disable the SAGV when we
 		 * have more then one pipe enabled
 		 */
-		if (!intel_can_enable_sagv(state))
-			intel_disable_sagv(dev_priv);
+		if (INTEL_GEN(dev_priv) < 11)
+			if (!intel_can_enable_sagv(dev_priv))
+				intel_disable_sagv(dev_priv);
 
 		intel_modeset_verify_disabled(dev_priv, state);
 	}
@@ -15813,8 +15820,10 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	if (state->modeset)
 		intel_verify_planes(state);
 
-	if (state->modeset && intel_can_enable_sagv(state))
-		intel_enable_sagv(dev_priv);
+	if (INTEL_GEN(dev_priv) < 11) {
+		if (state->modeset && intel_can_enable_sagv(dev_priv))
+			intel_enable_sagv(dev_priv);
+	}
 
 	drm_atomic_helper_commit_hw_done(&state->base);
 
@@ -15966,7 +15975,6 @@ static int intel_atomic_commit(struct drm_device *dev,
 
 	if (state->global_state_changed) {
 		assert_global_state_locked(dev_priv);
-
 		dev_priv->active_pipes = state->active_pipes;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 283c622f8ba1..b5f7986dd1dc 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -478,6 +478,12 @@ struct intel_atomic_state {
 	 */
 	u8 active_pipe_changes;
 
+	/*
+	 * Used to determine if we already had calculated
+	 * SAGV mask for this state once.
+	 */
+	bool sagv_calculated;
+
 	u8 active_pipes;
 
 	struct intel_shared_dpll_state shared_dpll[I915_NUM_PLLS];
@@ -651,6 +657,8 @@ struct skl_plane_wm {
 	struct skl_wm_level wm[8];
 	struct skl_wm_level uv_wm[8];
 	struct skl_wm_level trans_wm;
+	struct skl_wm_level sagv_wm0;
+	struct skl_wm_level uv_sagv_wm0;
 	bool is_planar;
 };
 
diff --git a/drivers/gpu/drm/i915/display/intel_global_state.c b/drivers/gpu/drm/i915/display/intel_global_state.c
index 520be492e455..d928d3fddebb 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.c
+++ b/drivers/gpu/drm/i915/display/intel_global_state.c
@@ -53,6 +53,19 @@ static bool modeset_lock_is_held(struct drm_modeset_acquire_ctx *ctx,
 	return false;
 }
 
+void show_locks(struct intel_atomic_state *state)
+{
+	struct drm_modeset_acquire_ctx *ctx = state->base.acquire_ctx;
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc *crtc;
+
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		if (modeset_lock_is_held(ctx, &crtc->base.mutex)) {
+			DRM_DEBUG_KMS("State %p crtc %d lock is held\n", state, crtc->pipe);
+		}
+	}
+}
+
 static void assert_global_state_read_locked(struct intel_atomic_state *state)
 {
 	struct drm_modeset_acquire_ctx *ctx = state->base.acquire_ctx;
@@ -76,6 +89,11 @@ intel_atomic_get_global_obj_state(struct intel_atomic_state *state,
 	size_t size;
 	struct __intel_global_objs_state *arr;
 	struct intel_global_state *obj_state;
+	int i;
+
+	for (i = 0; i < state->num_global_objs; i++)
+		if (obj == state->global_objs[i].ptr)
+			return state->global_objs[i].state;
 
 	for (i = 0; i < state->num_global_objs; i++)
 		if (obj == state->global_objs[i].ptr)
diff --git a/drivers/gpu/drm/i915/display/intel_global_state.h b/drivers/gpu/drm/i915/display/intel_global_state.h
index e6163a469029..0f05f47b4d24 100644
--- a/drivers/gpu/drm/i915/display/intel_global_state.h
+++ b/drivers/gpu/drm/i915/display/intel_global_state.h
@@ -84,4 +84,6 @@ void intel_atomic_clear_global_state(struct intel_atomic_state *state);
 int intel_atomic_lock_global_state(struct intel_global_state *obj_state);
 int intel_atomic_serialize_global_state(struct intel_global_state *obj_state);
 
+void show_locks(struct intel_atomic_state *state);
+
 #endif
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index e1d167429489..a6aad0cd6bdb 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -42,6 +42,7 @@
 #include "i915_drv.h"
 #include "i915_irq.h"
 #include "i915_trace.h"
+#include "display/intel_bw.h"
 #include "intel_pm.h"
 #include "intel_sideband.h"
 #include "../../../platform/x86/intel_ips.h"
@@ -3620,7 +3621,7 @@ static bool skl_needs_memory_bw_wa(struct drm_i915_private *dev_priv)
 	return IS_GEN9_BC(dev_priv) || IS_BROXTON(dev_priv);
 }
 
-static bool
+bool
 intel_has_sagv(struct drm_i915_private *dev_priv)
 {
 	/* HACK! */
@@ -3743,39 +3744,24 @@ intel_disable_sagv(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-bool intel_can_enable_sagv(struct intel_atomic_state *state)
+static bool skl_can_enable_sagv_on_pipe(struct intel_atomic_state *state,
+					enum pipe pipe)
 {
 	struct drm_device *dev = state->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *crtc;
 	struct intel_plane *plane;
 	struct intel_crtc_state *crtc_state;
-	enum pipe pipe;
 	int level, latency;
 
-	if (!intel_has_sagv(dev_priv))
-		return false;
-
-	/*
-	 * If there are no active CRTCs, no additional checks need be performed
-	 */
-	if (hweight8(state->active_pipes) == 0)
-		return true;
-
-	/*
-	 * SKL+ workaround: bspec recommends we disable SAGV when we have
-	 * more then one pipe enabled
-	 */
-	if (hweight8(state->active_pipes) > 1)
-		return false;
-
-	/* Since we're now guaranteed to only have one active CRTC... */
-	pipe = ffs(state->active_pipes) - 1;
 	crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
 	crtc_state = to_intel_crtc_state(crtc->base.state);
 
-	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE)
+	if (crtc_state->hw.adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) {
+		DRM_DEBUG_KMS("No SAGV for interlaced mode on pipe %c\n",
+			      pipe_name(pipe));
 		return false;
+	}
 
 	for_each_intel_plane_on_crtc(dev, crtc, plane) {
 		struct skl_plane_wm *wm =
@@ -3802,7 +3788,163 @@ bool intel_can_enable_sagv(struct intel_atomic_state *state)
 		 * incur memory latencies higher than sagv_block_time_us we
 		 * can't enable SAGV.
 		 */
-		if (latency < dev_priv->sagv_block_time_us)
+		if (latency < dev_priv->sagv_block_time_us) {
+			DRM_DEBUG_KMS("Latency %d < sagv block time %d, no SAGV for pipe %c\n",
+				      latency, dev_priv->sagv_block_time_us, pipe_name(pipe));
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static void skl_compute_sagv_mask(struct intel_atomic_state *state)
+{
+	struct intel_crtc *crtc;
+	enum pipe pipe;
+	struct intel_bw_state *new_bw_state = intel_atomic_get_bw_state(state);
+
+	if (IS_ERR(new_bw_state)) {
+		WARN(1, "Could not get bw_state\n");
+		return;
+	}
+
+
+	if (state->active_pipes != 1) {
+		new_bw_state->pipe_sagv_mask = 0;
+		DRM_DEBUG_KMS("No SAGV for multiple pipes on Gen 9\n");
+		return;
+	}
+
+	/* Since we're now guaranteed to only have one active CRTC... */
+	pipe = ffs(state->active_pipes) - 1;
+
+	if (skl_can_enable_sagv_on_pipe(state, pipe))
+		new_bw_state->pipe_sagv_mask |= BIT(crtc->pipe);
+	else
+		new_bw_state->pipe_sagv_mask &= ~BIT(crtc->pipe);
+}
+
+static void tgl_compute_sagv_mask(struct intel_atomic_state *state);
+
+static void icl_compute_sagv_mask(struct intel_atomic_state *state)
+{
+	struct intel_crtc *crtc;
+	struct intel_crtc_state *new_crtc_state;
+	int i;
+	struct intel_bw_state *new_bw_state = intel_atomic_get_bw_state(state);
+
+	if (IS_ERR(new_bw_state)) {
+		WARN(1, "Could not get bw_state\n");
+		return;
+	}
+
+	for_each_new_intel_crtc_in_state(state, crtc,
+					 new_crtc_state, i) {
+		if (skl_can_enable_sagv_on_pipe(state, crtc->pipe))
+			new_bw_state->pipe_sagv_mask |= BIT(crtc->pipe);
+		else
+			new_bw_state->pipe_sagv_mask &= ~BIT(crtc->pipe);
+	}
+}
+
+void intel_compute_sagv_mask(struct intel_atomic_state *state, int total_affected_planes)
+{
+	int ret;
+	struct drm_device *dev = state->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_bw_state *new_bw_state = intel_atomic_get_bw_state(state);
+	struct intel_bw_state *old_bw_state = intel_atomic_get_old_bw_state(state);
+
+	if (IS_ERR(new_bw_state) || IS_ERR(old_bw_state)) {
+		WARN(1, "Could not get bw_state\n");
+		return;
+	}
+
+	show_locks(state);
+
+	/*
+	 * If active_pipes had changed, means we have added/removed crtc,
+	 * if total_affected_planes had changed - means we have changed wm/ddb.
+	 * Both require SAGV recalculation - otherwise just return and SAGV mask
+	 * will stay the same.
+	 * Also we will have crtc locks grabbed only in mentioned above cases.
+	 */
+	if ((state->active_pipes == dev_priv->active_pipes) &&
+	    (total_affected_planes == 0))
+		return;
+
+	/*
+	 * Now once we got wm levels calculated,
+	 * check if we can have SAGV.
+	 */
+	if (INTEL_GEN(dev_priv) >= 12)
+		tgl_compute_sagv_mask(state);
+	else if (INTEL_GEN(dev_priv) == 11)
+		icl_compute_sagv_mask(state);
+	else
+		skl_compute_sagv_mask(state);
+
+	state->sagv_calculated = true;
+
+	/*
+	 * For SAGV we need to account all the pipes,
+	 * not only the ones which are in state currently.
+	 * Grab all locks if we detect that we are actually
+	 * going to do something.
+	 */
+	if (new_bw_state->pipe_sagv_mask != old_bw_state->pipe_sagv_mask) {
+		ret = intel_atomic_serialize_global_state(&new_bw_state->base);
+		if (ret) {
+			DRM_DEBUG_KMS("Could not serialize global state\n");
+			return;
+		}
+	}
+
+	show_locks(state);
+}
+
+/*
+ * This function to be used before swap state
+ */
+bool intel_can_enable_sagv_for_state(struct intel_atomic_state *state)
+{
+	struct drm_device *dev = state->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int i;
+	struct intel_crtc *crtc;
+	struct intel_crtc_state *new_crtc_state;
+	struct intel_bw_state *new_bw_state  = intel_atomic_get_bw_state(state);
+
+	if (IS_ERR(new_bw_state)) {
+		WARN(1, "Could not get bw_state\n");
+		return false;
+	}
+
+	if (!intel_has_sagv(dev_priv)) {
+		DRM_DEBUG_KMS("No SAGV support detected\n");
+		return false;
+	}
+
+	/*
+	 * Should have this calculated by that time,
+	 * means something got changed or wrong in the driver
+	 * currently, supposed places which call this function are:
+	 * intel_atomic_commit_tail, intel_atomic_bw_check,
+	 * skl_allocate_pipe_ddb, skl_write_plane_wm.
+	 * All of those are supposed to be called after
+	 * skl_compute_wm->intel_compute_sagv_mask is called.
+	 */
+	drm_WARN_ON(&dev_priv->drm, !state->sagv_calculated);
+
+	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
+		u32 mask = BIT(crtc->pipe);
+		bool state_sagv_masked = (mask & new_bw_state->pipe_sagv_mask) == 0;
+
+		if (!new_crtc_state->hw.active)
+			continue;
+
+		if (state_sagv_masked)
 			return false;
 	}
 
@@ -3842,6 +3984,34 @@ static u16 intel_get_ddb_size(struct drm_i915_private *dev_priv)
 	return ddb_size;
 }
 
+/*
+ * To be used after we swap state
+ */
+bool intel_can_enable_sagv(struct drm_i915_private *dev_priv)
+{
+	int i;
+	struct intel_global_state *global_state;
+	struct intel_bw_state *bw_state;
+
+	global_state = dev_priv->bw_obj.state;
+	if (IS_ERR(global_state)) {
+		WARN(1, "Could not get global state\n");
+		return false;
+	}
+
+	bw_state = to_intel_bw_state(global_state);
+
+	for (i = 0; i < I915_MAX_PIPES; i++) {
+		int active_pipe_bit = dev_priv->active_pipes & BIT(i);
+		if (active_pipe_bit) {
+			if ((bw_state->pipe_sagv_mask & BIT(i)) == 0)
+				return false;
+		}
+	}
+
+	return true;
+}
+
 static u8 skl_compute_dbuf_slices(const struct intel_crtc_state *crtc_state,
 				  u32 active_pipes);
 
@@ -4028,6 +4198,7 @@ skl_cursor_allocation(const struct intel_crtc_state *crtc_state,
 		u32 latency = dev_priv->wm.skl_latency[level];
 
 		skl_compute_plane_wm(crtc_state, level, latency, &wp, &wm, &wm);
+
 		if (wm.min_ddb_alloc == U16_MAX)
 			break;
 
@@ -4554,12 +4725,93 @@ skl_plane_wm_level(struct intel_plane *plane,
 		   int level,
 		   int color_plane)
 {
+	struct drm_atomic_state *state = crtc_state->uapi.state;
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	const struct skl_plane_wm *wm =
 		&crtc_state->wm.skl.optimal.planes[plane->id];
 
+	if (!level) {
+		bool can_sagv = false;
+
+		/*
+		 * If we haven't yet swapped our state, we should use
+		 * the state to determine SAGV, otherwise use global
+		 * state as atomic state pointer might become stale
+		 * and zeroed out.
+		 */
+		if (state) {
+			struct intel_atomic_state *intel_state =
+				to_intel_atomic_state(state);
+			can_sagv = intel_can_enable_sagv_for_state(intel_state);
+		} else {
+			can_sagv = intel_can_enable_sagv(dev_priv);
+		}
+
+		if (can_sagv)
+			return color_plane ? &wm->uv_sagv_wm0 : &wm->sagv_wm0;
+	}
+
 	return color_plane ? &wm->uv_wm[level] : &wm->wm[level];
 }
 
+static int
+tgl_check_pipe_fits_sagv_wm(struct intel_crtc_state *crtc_state)
+{
+	struct drm_crtc *crtc = crtc_state->uapi.crtc;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	struct skl_ddb_entry *alloc = &crtc_state->wm.skl.ddb;
+	u16 alloc_size;
+	u64 total_data_rate;
+	enum plane_id plane_id;
+	int num_active;
+	u64 plane_data_rate[I915_MAX_PLANES] = {};
+	u32 blocks;
+
+	/*
+	 * No need to check gen here, we call this only for gen12
+	 */
+	total_data_rate =
+		icl_get_total_relative_data_rate(crtc_state,
+						 plane_data_rate);
+
+	skl_ddb_get_pipe_allocation_limits(dev_priv, crtc_state,
+					   total_data_rate,
+					   alloc, &num_active);
+	alloc_size = skl_ddb_entry_size(alloc);
+	if (alloc_size == 0)
+		return -ENOSPC;
+
+	/*
+	 * Do check if we can fit L0 + sagv_block_time and
+	 * disable SAGV if we can't.
+	 */
+	blocks = 0;
+	for_each_plane_id_on_crtc(intel_crtc, plane_id) {
+		/*
+		 * The only place, where we can't use skl_plane_wm_level
+		 * accessor, because if actually calls intel_can_enable_sagv
+		 * which depends on that function.
+		 */
+		const struct skl_plane_wm *wm =
+			&crtc_state->wm.skl.optimal.planes[plane_id];
+
+		blocks += wm->sagv_wm0.min_ddb_alloc;
+		blocks += wm->uv_sagv_wm0.min_ddb_alloc;
+
+		if (blocks > alloc_size) {
+			DRM_DEBUG_KMS("Not enough ddb blocks(%d<%d) for SAGV on pipe %c\n",
+				      alloc_size, blocks, pipe_name(intel_crtc->pipe));
+			return -ENOSPC;
+		}
+	}
+	DRM_DEBUG_KMS("%d total blocks required for SAGV, ddb entry size %d\n",
+		      blocks, alloc_size);
+	return 0;
+}
+
+
 static int
 skl_allocate_pipe_ddb(struct intel_crtc_state *crtc_state)
 {
@@ -5143,11 +5395,19 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state,
 static void
 skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
 		      const struct skl_wm_params *wm_params,
-		      struct skl_wm_level *levels)
+		      struct skl_plane_wm *plane_wm,
+		      bool yuv)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
 	int level, max_level = ilk_wm_max_level(dev_priv);
+	/*
+	 * Check which kind of plane is it and based on that calculate
+	 * correspondent WM levels.
+	 */
+	struct skl_wm_level *levels = yuv ? plane_wm->uv_wm : plane_wm->wm;
 	struct skl_wm_level *result_prev = &levels[0];
+	struct skl_wm_level *sagv_wm = yuv ?
+				&plane_wm->uv_sagv_wm0 : &plane_wm->sagv_wm0;
 
 	for (level = 0; level <= max_level; level++) {
 		struct skl_wm_level *result = &levels[level];
@@ -5158,6 +5418,27 @@ skl_compute_wm_levels(const struct intel_crtc_state *crtc_state,
 
 		result_prev = result;
 	}
+	/*
+	 * For Gen12 if it is an L0 we need to also
+	 * consider sagv_block_time when calculating
+	 * L0 watermark - we will need that when making
+	 * a decision whether enable SAGV or not.
+	 * For older gens we agreed to copy L0 value for
+	 * compatibility.
+	 */
+	if ((INTEL_GEN(dev_priv) >= 12)) {
+		u32 latency = dev_priv->wm.skl_latency[0];
+
+		latency += dev_priv->sagv_block_time_us;
+		skl_compute_plane_wm(crtc_state, 0, latency,
+				     wm_params, &levels[0],
+				     sagv_wm);
+		DRM_DEBUG_KMS("%d L0 blocks required for SAGV vs %d for non-SAGV\n",
+			      sagv_wm->min_ddb_alloc, levels[0].min_ddb_alloc);
+	} else {
+		/* Since all members are POD */
+		*sagv_wm = levels[0];
+	}
 }
 
 static void skl_compute_transition_wm(const struct intel_crtc_state *crtc_state,
@@ -5232,7 +5513,7 @@ static int skl_build_plane_wm_single(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	skl_compute_wm_levels(crtc_state, &wm_params, wm->wm);
+	skl_compute_wm_levels(crtc_state, &wm_params, wm, false);
 	skl_compute_transition_wm(crtc_state, &wm_params, wm);
 
 	return 0;
@@ -5254,7 +5535,7 @@ static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state,
 	if (ret)
 		return ret;
 
-	skl_compute_wm_levels(crtc_state, &wm_params, wm->uv_wm);
+	skl_compute_wm_levels(crtc_state, &wm_params, wm, true);
 
 	return 0;
 }
@@ -5585,10 +5866,29 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 		for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
 			enum plane_id plane_id = plane->id;
 			const struct skl_plane_wm *old_wm, *new_wm;
+			u16 old_plane_res_l, new_plane_res_l;
+			u8  old_plane_res_b, new_plane_res_b;
+			u16 old_min_ddb_alloc, new_min_ddb_alloc;
 
 			old_wm = &old_pipe_wm->planes[plane_id];
 			new_wm = &new_pipe_wm->planes[plane_id];
 
+			old_plane_res_l = intel_can_enable_sagv(dev_priv) ?
+					  old_wm->sagv_wm0.plane_res_l : old_wm->wm[0].plane_res_l;
+			old_plane_res_b = intel_can_enable_sagv(dev_priv) ?
+					  old_wm->sagv_wm0.plane_res_b : old_wm->wm[0].plane_res_b;
+
+			new_plane_res_l = intel_can_enable_sagv_for_state(state) ?
+					  new_wm->sagv_wm0.plane_res_l : new_wm->wm[0].plane_res_l;
+			new_plane_res_b = intel_can_enable_sagv_for_state(state) ?
+					  new_wm->sagv_wm0.plane_res_b : new_wm->wm[0].plane_res_b;
+
+			old_min_ddb_alloc = intel_can_enable_sagv(dev_priv) ?
+					    old_wm->sagv_wm0.min_ddb_alloc : old_wm->wm[0].min_ddb_alloc;
+
+			new_min_ddb_alloc = intel_can_enable_sagv_for_state(state) ?
+					    new_wm->sagv_wm0.min_ddb_alloc : new_wm->wm[0].min_ddb_alloc;
+
 			if (skl_plane_wm_equals(dev_priv, old_wm, new_wm))
 				continue;
 
@@ -5611,7 +5911,7 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 				    "[PLANE:%d:%s]   lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d"
 				      " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d\n",
 				    plane->base.base.id, plane->base.name,
-				    enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].plane_res_l,
+				    enast(old_wm->wm[0].ignore_lines), old_plane_res_l,
 				    enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].plane_res_l,
 				    enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].plane_res_l,
 				    enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].plane_res_l,
@@ -5621,7 +5921,7 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 				    enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].plane_res_l,
 				    enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.plane_res_l,
 
-				    enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].plane_res_l,
+				    enast(new_wm->wm[0].ignore_lines), new_plane_res_l,
 				    enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].plane_res_l,
 				    enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].plane_res_l,
 				    enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].plane_res_l,
@@ -5635,12 +5935,12 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 				    "[PLANE:%d:%s]  blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
 				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
 				    plane->base.base.id, plane->base.name,
-				    old_wm->wm[0].plane_res_b, old_wm->wm[1].plane_res_b,
+				    old_plane_res_b, old_wm->wm[1].plane_res_b,
 				    old_wm->wm[2].plane_res_b, old_wm->wm[3].plane_res_b,
 				    old_wm->wm[4].plane_res_b, old_wm->wm[5].plane_res_b,
 				    old_wm->wm[6].plane_res_b, old_wm->wm[7].plane_res_b,
 				    old_wm->trans_wm.plane_res_b,
-				    new_wm->wm[0].plane_res_b, new_wm->wm[1].plane_res_b,
+				    new_plane_res_b, new_wm->wm[1].plane_res_b,
 				    new_wm->wm[2].plane_res_b, new_wm->wm[3].plane_res_b,
 				    new_wm->wm[4].plane_res_b, new_wm->wm[5].plane_res_b,
 				    new_wm->wm[6].plane_res_b, new_wm->wm[7].plane_res_b,
@@ -5650,12 +5950,12 @@ skl_print_wm_changes(struct intel_atomic_state *state)
 				    "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d"
 				    " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d\n",
 				    plane->base.base.id, plane->base.name,
-				    old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
+				    old_min_ddb_alloc, old_wm->wm[1].min_ddb_alloc,
 				    old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc,
 				    old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc,
 				    old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc,
 				    old_wm->trans_wm.min_ddb_alloc,
-				    new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
+				    new_min_ddb_alloc, new_wm->wm[1].min_ddb_alloc,
 				    new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc,
 				    new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc,
 				    new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc,
@@ -5755,7 +6055,8 @@ skl_ddb_add_affected_pipes(struct intel_atomic_state *state)
  * default value of the watermarks registers is not zero.
  */
 static int skl_wm_add_affected_planes(struct intel_atomic_state *state,
-				      struct intel_crtc *crtc)
+				      struct intel_crtc *crtc,
+				      int *num_affected_planes)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct intel_crtc_state *old_crtc_state =
@@ -5764,6 +6065,8 @@ static int skl_wm_add_affected_planes(struct intel_atomic_state *state,
 		intel_atomic_get_new_crtc_state(state, crtc);
 	struct intel_plane *plane;
 
+	*num_affected_planes = 0;
+
 	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
 		struct intel_plane_state *plane_state;
 		enum plane_id plane_id = plane->id;
@@ -5787,11 +6090,64 @@ static int skl_wm_add_affected_planes(struct intel_atomic_state *state,
 			return PTR_ERR(plane_state);
 
 		new_crtc_state->update_planes |= BIT(plane_id);
+		*num_affected_planes += 1;
 	}
 
 	return 0;
 }
 
+static void tgl_compute_sagv_mask(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc *crtc;
+	struct intel_crtc_state *new_crtc_state;
+	struct intel_crtc_state *old_crtc_state;
+	int ret;
+	int i;
+	struct intel_plane *plane;
+	struct intel_bw_state *new_bw_state  = intel_atomic_get_bw_state(state);
+
+	if (IS_ERR(new_bw_state)) {
+		WARN(1, "Could not get bw_state\n");
+		return;
+	}
+
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		int pipe_bit = BIT(crtc->pipe);
+		bool skip = true;
+
+		/*
+		 * If we had set this mast already once for this state,
+		 * no need to waste CPU cycles for doing this again.
+		 */
+		for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+			enum plane_id plane_id = plane->id;
+
+			if (!skl_plane_wm_equals(dev_priv,
+						 &old_crtc_state->wm.skl.optimal.planes[plane_id],
+						 &new_crtc_state->wm.skl.optimal.planes[plane_id])) {
+				skip = false;
+				break;
+			}
+		}
+
+		/*
+		 * Check if wm levels are actually the same as for previous
+		 * state, which means we can just skip doing this long check
+		 * and just  copy correspondent bit from previous state.
+		 */
+		if (skip)
+			continue;
+
+		ret = tgl_check_pipe_fits_sagv_wm(new_crtc_state);
+		if (!ret)
+			new_bw_state->pipe_sagv_mask |= pipe_bit;
+		else
+			new_bw_state->pipe_sagv_mask &= ~pipe_bit;
+	}
+}
+
 static int
 skl_compute_wm(struct intel_atomic_state *state)
 {
@@ -5799,6 +6155,7 @@ skl_compute_wm(struct intel_atomic_state *state)
 	struct intel_crtc_state *new_crtc_state;
 	struct intel_crtc_state *old_crtc_state;
 	int ret, i;
+	int affected_planes; int total_affected_planes = 0;
 
 	ret = skl_ddb_add_affected_pipes(state);
 	if (ret)
@@ -5815,11 +6172,15 @@ skl_compute_wm(struct intel_atomic_state *state)
 		if (ret)
 			return ret;
 
-		ret = skl_wm_add_affected_planes(state, crtc);
+		ret = skl_wm_add_affected_planes(state, crtc, &affected_planes);
 		if (ret)
 			return ret;
+
+		total_affected_planes += affected_planes;
 	}
 
+	intel_compute_sagv_mask(state, total_affected_planes);
+
 	ret = skl_compute_ddb(state);
 	if (ret)
 		return ret;
@@ -5939,6 +6300,9 @@ void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc,
 				val = I915_READ(CUR_WM(pipe, level));
 
 			skl_wm_level_from_reg_val(val, &wm->wm[level]);
+			if (level == 0)
+				memcpy(&wm->sagv_wm0, &wm->wm[level],
+				       sizeof(struct skl_wm_level));
 		}
 
 		if (plane_id != PLANE_CURSOR)
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index d60a85421c5a..561a17a5d4e0 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -41,7 +41,9 @@ void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc,
 			      struct skl_pipe_wm *out);
 void g4x_wm_sanitize(struct drm_i915_private *dev_priv);
 void vlv_wm_sanitize(struct drm_i915_private *dev_priv);
-bool intel_can_enable_sagv(struct intel_atomic_state *state);
+bool intel_can_enable_sagv(struct drm_i915_private *dev_priv);
+bool intel_can_enable_sagv_for_state(struct intel_atomic_state *state);
+bool intel_has_sagv(struct drm_i915_private *dev_priv);
 int intel_enable_sagv(struct drm_i915_private *dev_priv);
 int intel_disable_sagv(struct drm_i915_private *dev_priv);
 bool skl_wm_level_equals(const struct skl_wm_level *l1,
-- 
2.24.1.485.gad05a3d8e5



More information about the Intel-gfx-trybot mailing list