drm/i915: Move fence register tracking from i915->mm to ggtt

As the fence registers only apply to regions inside the GGTT is makes
more sense that we track these as part of the i915_ggtt and not the
general mm. In the next patch, we will then pull the register locking
underneath the i915_ggtt.mutex.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190613073254.24048-1-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/gem/i915_gem_mman.c

@@ -310,9 +310,9 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	/* Mark as being mmapped into userspace for later revocation */
 	assert_rpm_wakelock_held(i915);
 	if (!i915_vma_set_userfault(vma) && !obj->userfault_count++)
-		list_add(&obj->userfault_link, &i915->mm.userfault_list);
+		list_add(&obj->userfault_link, &i915->ggtt.userfault_list);
 	if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)
-		intel_wakeref_auto(&i915->mm.userfault_wakeref,
+		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 	GEM_BUG_ON(!obj->userfault_count);
 

drivers/gpu/drm/i915/gem/i915_gem_pm.c

@@ -126,7 +126,7 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 {
 	GEM_TRACE("\n");
 
-	intel_wakeref_auto(&i915->mm.userfault_wakeref, 0);
+	intel_wakeref_auto(&i915->ggtt.userfault_wakeref, 0);
 	flush_workqueue(i915->wq);
 
 	mutex_lock(&i915->drm.struct_mutex);

drivers/gpu/drm/i915/gt/intel_reset.c

@@ -695,19 +695,19 @@ static void revoke_mmaps(struct drm_i915_private *i915)
 {
 	int i;
 
-	for (i = 0; i < i915->num_fence_regs; i++) {
+	for (i = 0; i < i915->ggtt.num_fences; i++) {
 		struct drm_vma_offset_node *node;
 		struct i915_vma *vma;
 		u64 vma_offset;
 
-		vma = READ_ONCE(i915->fence_regs[i].vma);
+		vma = READ_ONCE(i915->ggtt.fence_regs[i].vma);
 		if (!vma)
 			continue;
 
 		if (!i915_vma_has_userfault(vma))
 			continue;
 
-		GEM_BUG_ON(vma->fence != &i915->fence_regs[i]);
+		GEM_BUG_ON(vma->fence != &i915->ggtt.fence_regs[i]);
 		node = &vma->obj->base.vma_node;
 		vma_offset = vma->ggtt_view.partial.offset << PAGE_SHIFT;
 		unmap_mapping_range(i915->drm.anon_inode->i_mapping,

drivers/gpu/drm/i915/gvt/aperture_gm.c

@@ -35,6 +35,7 @@
  */
 
 #include "i915_drv.h"
+#include "i915_gem_fence_reg.h"
 #include "gvt.h"
 
 static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
@@ -128,7 +129,7 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu,
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
-	struct drm_i915_fence_reg *reg;
+	struct i915_fence_reg *reg;
 	i915_reg_t fence_reg_lo, fence_reg_hi;
 
 	assert_rpm_wakelock_held(dev_priv);
@@ -163,7 +164,7 @@ static void free_vgpu_fence(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
-	struct drm_i915_fence_reg *reg;
+	struct i915_fence_reg *reg;
 	u32 i;
 
 	if (WARN_ON(!vgpu_fence_sz(vgpu)))
@@ -187,7 +188,7 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 	struct drm_i915_private *dev_priv = gvt->dev_priv;
-	struct drm_i915_fence_reg *reg;
+	struct i915_fence_reg *reg;
 	int i;
 
 	intel_runtime_pm_get(dev_priv);

drivers/gpu/drm/i915/gvt/gvt.h

@@ -87,7 +87,7 @@ struct intel_vgpu_gm {
 
 /* Fences owned by a vGPU */
 struct intel_vgpu_fence {
-	struct drm_i915_fence_reg *regs[INTEL_GVT_MAX_NUM_FENCES];
+	struct i915_fence_reg *regs[INTEL_GVT_MAX_NUM_FENCES];
 	u32 base;
 	u32 size;
 };
@@ -390,7 +390,7 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt);
 #define gvt_hidden_gmadr_end(gvt) (gvt_hidden_gmadr_base(gvt) \
 				   + gvt_hidden_sz(gvt) - 1)
 
-#define gvt_fence_sz(gvt) (gvt->dev_priv->num_fence_regs)
+#define gvt_fence_sz(gvt) ((gvt)->dev_priv->ggtt.num_fences)
 
 /* Aperture/GM space definitions for vGPU */
 #define vgpu_aperture_offset(vgpu)	((vgpu)->gm.low_gm_node.start)

drivers/gpu/drm/i915/i915_debugfs.c

@@ -143,8 +143,6 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	unsigned int frontbuffer_bits;
 	int pin_count = 0;
 
-	lockdep_assert_held(&obj->base.dev->struct_mutex);
-
 	seq_printf(m, "%pK: %c%c%c%c%c %8zdKiB %02x %02x %s%s%s",
 		   &obj->base,
 		   get_active_flag(obj),
@@ -160,17 +158,17 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   obj->mm.madv == I915_MADV_DONTNEED ? " purgeable" : "");
 	if (obj->base.name)
 		seq_printf(m, " (name: %d)", obj->base.name);
-	list_for_each_entry(vma, &obj->vma.list, obj_link) {
-		if (i915_vma_is_pinned(vma))
-			pin_count++;
-	}
-	seq_printf(m, " (pinned x %d)", pin_count);
-	if (obj->pin_global)
-		seq_printf(m, " (global)");
+
+	spin_lock(&obj->vma.lock);
 	list_for_each_entry(vma, &obj->vma.list, obj_link) {
 		if (!drm_mm_node_allocated(&vma->node))
 			continue;
 
+		spin_unlock(&obj->vma.lock);
+
+		if (i915_vma_is_pinned(vma))
+			pin_count++;
+
 		seq_printf(m, " (%sgtt offset: %08llx, size: %08llx, pages: %s",
 			   i915_vma_is_ggtt(vma) ? "g" : "pp",
 			   vma->node.start, vma->node.size,
@@ -221,9 +219,16 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 				   vma->fence->id,
 				   i915_active_request_isset(&vma->last_fence) ? "*" : "");
 		seq_puts(m, ")");
+
+		spin_lock(&obj->vma.lock);
 	}
+	spin_unlock(&obj->vma.lock);
+
+	seq_printf(m, " (pinned x %d)", pin_count);
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08llx)", obj->stolen->start);
+	if (obj->pin_global)
+		seq_printf(m, " (global)");
 
 	engine = i915_gem_object_last_write_engine(obj);
 	if (engine)
@@ -698,28 +703,25 @@ static int i915_interrupt_info(struct seq_file *m, void *data)
 
 static int i915_gem_fence_regs_info(struct seq_file *m, void *data)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	int i, ret;
+	struct drm_i915_private *i915 = node_to_i915(m->private);
+	unsigned int i;
 
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
+	seq_printf(m, "Total fences = %d\n", i915->ggtt.num_fences);
 
-	seq_printf(m, "Total fences = %d\n", dev_priv->num_fence_regs);
-	for (i = 0; i < dev_priv->num_fence_regs; i++) {
-		struct i915_vma *vma = dev_priv->fence_regs[i].vma;
+	rcu_read_lock();
+	for (i = 0; i < i915->ggtt.num_fences; i++) {
+		struct i915_vma *vma = i915->ggtt.fence_regs[i].vma;
 
 		seq_printf(m, "Fence %d, pin count = %d, object = ",
-			   i, dev_priv->fence_regs[i].pin_count);
+			   i, i915->ggtt.fence_regs[i].pin_count);
 		if (!vma)
 			seq_puts(m, "unused");
 		else
 			describe_obj(m, vma->obj);
 		seq_putc(m, '\n');
 	}
+	rcu_read_unlock();
 
-	mutex_unlock(&dev->struct_mutex);
 	return 0;
 }
 

drivers/gpu/drm/i915/i915_drv.c

@@ -350,7 +350,7 @@ static int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = pdev->revision;
 		break;
 	case I915_PARAM_NUM_FENCES_AVAIL:
-		value = dev_priv->num_fence_regs;
+		value = dev_priv->ggtt.num_fences;
 		break;
 	case I915_PARAM_HAS_OVERLAY:
 		value = dev_priv->overlay ? 1 : 0;
@@ -1625,7 +1625,6 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 	intel_uncore_sanitize(dev_priv);
 
 	intel_gt_init_workarounds(dev_priv);
-	i915_gem_load_init_fences(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
 	 * integrated graphics even though the support isn't actually there

drivers/gpu/drm/i915/i915_drv.h

@@ -757,14 +757,6 @@ struct i915_gem_mm {
 	 */
 	struct list_head shrink_list;
 
-	/** List of all objects in gtt_space, currently mmaped by userspace.
-	 * All objects within this list must also be on bound_list.
-	 */
-	struct list_head userfault_list;
-
-	/* Manual runtime pm autosuspend delay for user GGTT mmaps */
-	struct intel_wakeref_auto userfault_wakeref;
-
 	/**
 	 * List of objects which are pending destruction.
 	 */
@@ -794,9 +786,6 @@ struct i915_gem_mm {
 	struct notifier_block vmap_notifier;
 	struct shrinker shrinker;
 
-	/** LRU list of objects with fence regs on them. */
-	struct list_head fence_list;
-
 	/**
 	 * Workqueue to fault in userptr pages, flushed by the execbuf
 	 * when required but otherwise left to userspace to try again
@@ -1485,9 +1474,6 @@ struct drm_i915_private {
 	/* protects panel power sequencer state */
 	struct mutex pps_mutex;
 
-	struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; /* assume 965 */
-	int num_fence_regs; /* 8 on pre-965, 16 otherwise */
-
 	unsigned int fsb_freq, mem_freq, is_ddr3;
 	unsigned int skl_preferred_vco_freq;
 	unsigned int max_cdclk_freq;
@@ -2541,7 +2527,6 @@ void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv);
 void i915_gem_sanitize(struct drm_i915_private *i915);
 int i915_gem_init_early(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
-void i915_gem_load_init_fences(struct drm_i915_private *dev_priv);
 int i915_gem_freeze(struct drm_i915_private *dev_priv);
 int i915_gem_freeze_late(struct drm_i915_private *dev_priv);
 
@@ -2661,19 +2646,6 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 				struct drm_gem_object *gem_obj, int flags);
 
-/* i915_gem_fence_reg.c */
-struct drm_i915_fence_reg *
-i915_reserve_fence(struct drm_i915_private *dev_priv);
-void i915_unreserve_fence(struct drm_i915_fence_reg *fence);
-
-void i915_gem_restore_fences(struct drm_i915_private *dev_priv);
-
-void i915_gem_detect_bit_6_swizzle(struct drm_i915_private *dev_priv);
-void i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj,
-				       struct sg_table *pages);
-void i915_gem_object_save_bit_17_swizzle(struct drm_i915_gem_object *obj,
-					 struct sg_table *pages);
-
 static inline struct i915_gem_context *
 __i915_gem_context_lookup_rcu(struct drm_i915_file_private *file_priv, u32 id)
 {

drivers/gpu/drm/i915/i915_gem.c

@@ -884,7 +884,7 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
-void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
+void i915_gem_runtime_suspend(struct drm_i915_private *i915)
 {
 	struct drm_i915_gem_object *obj, *on;
 	int i;
@@ -897,17 +897,19 @@ void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv)
 	 */
 
 	list_for_each_entry_safe(obj, on,
-				 &dev_priv->mm.userfault_list, userfault_link)
+				 &i915->ggtt.userfault_list, userfault_link)
 		__i915_gem_object_release_mmap(obj);
 
-	/* The fence will be lost when the device powers down. If any were
+	/*
+	 * The fence will be lost when the device powers down. If any were
 	 * in use by hardware (i.e. they are pinned), we should not be powering
 	 * down! All other fences will be reacquired by the user upon waking.
 	 */
-	for (i = 0; i < dev_priv->num_fence_regs; i++) {
-		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
+	for (i = 0; i < i915->ggtt.num_fences; i++) {
+		struct i915_fence_reg *reg = &i915->ggtt.fence_regs[i];
 
-		/* Ideally we want to assert that the fence register is not
+		/*
+		 * Ideally we want to assert that the fence register is not
 		 * live at this point (i.e. that no piece of code will be
 		 * trying to write through fence + GTT, as that both violates
 		 * our tracking of activity and associated locking/barriers,
@@ -1687,7 +1689,7 @@ void i915_gem_fini_hw(struct drm_i915_private *dev_priv)
 {
 	GEM_BUG_ON(dev_priv->gt.awake);
 
-	intel_wakeref_auto_fini(&dev_priv->mm.userfault_wakeref);
+	intel_wakeref_auto_fini(&dev_priv->ggtt.userfault_wakeref);
 
 	i915_gem_suspend_late(dev_priv);
 	intel_disable_gt_powersave(dev_priv);
@@ -1729,38 +1731,6 @@ void i915_gem_init_mmio(struct drm_i915_private *i915)
 	i915_gem_sanitize(i915);
 }
 
-void
-i915_gem_load_init_fences(struct drm_i915_private *dev_priv)
-{
-	int i;
-
-	if (INTEL_GEN(dev_priv) >= 7 && !IS_VALLEYVIEW(dev_priv) &&
-	    !IS_CHERRYVIEW(dev_priv))
-		dev_priv->num_fence_regs = 32;
-	else if (INTEL_GEN(dev_priv) >= 4 ||
-		 IS_I945G(dev_priv) || IS_I945GM(dev_priv) ||
-		 IS_G33(dev_priv) || IS_PINEVIEW(dev_priv))
-		dev_priv->num_fence_regs = 16;
-	else
-		dev_priv->num_fence_regs = 8;
-
-	if (intel_vgpu_active(dev_priv))
-		dev_priv->num_fence_regs =
-				I915_READ(vgtif_reg(avail_rs.fence_num));
-
-	/* Initialize fence registers to zero */
-	for (i = 0; i < dev_priv->num_fence_regs; i++) {
-		struct drm_i915_fence_reg *fence = &dev_priv->fence_regs[i];
-
-		fence->i915 = dev_priv;
-		fence->id = i;
-		list_add_tail(&fence->link, &dev_priv->mm.fence_list);
-	}
-	i915_gem_restore_fences(dev_priv);
-
-	i915_gem_detect_bit_6_swizzle(dev_priv);
-}
-
 static void i915_gem_init__mm(struct drm_i915_private *i915)
 {
 	spin_lock_init(&i915->mm.obj_lock);
@@ -1770,10 +1740,6 @@ static void i915_gem_init__mm(struct drm_i915_private *i915)
 
 	INIT_LIST_HEAD(&i915->mm.purge_list);
 	INIT_LIST_HEAD(&i915->mm.shrink_list);
-	INIT_LIST_HEAD(&i915->mm.fence_list);
-
-	INIT_LIST_HEAD(&i915->mm.userfault_list);
-	intel_wakeref_auto_init(&i915->mm.userfault_wakeref, i915);
 
 	i915_gem_init__objects(i915);
 }