Merge remote-tracking branch 'drm-intel/drm-intel-gt-next' into drm-tip

# Conflicts:
#	drivers/gpu/drm/i915/gt/intel_ggtt.c
#	drivers/gpu/drm/i915/i915_drv.h
#	drivers/gpu/drm/i915/i915_vma.c

Author: jlahtine-intel

Documentation/gpu/drm-usage-stats.rst

@@ -0,0 +1,112 @@
+.. _drm-client-usage-stats:
+
+======================
+DRM client usage stats
+======================
+
+DRM drivers can choose to export partly standardised text output via the
+`fops->show_fdinfo()` as part of the driver specific file operations registered
+in the `struct drm_driver` object registered with the DRM core.
+
+One purpose of this output is to enable writing as generic as practicaly
+feasible `top(1)` like userspace monitoring tools.
+
+Given the differences between various DRM drivers the specification of the
+output is split between common and driver specific parts. Having said that,
+wherever possible effort should still be made to standardise as much as
+possible.
+
+File format specification
+=========================
+
+- File shall contain one key value pair per one line of text.
+- Colon character (`:`) must be used to delimit keys and values.
+- All keys shall be prefixed with `drm-`.
+- Whitespace between the delimiter and first non-whitespace character shall be
+  ignored when parsing.
+- Neither keys or values are allowed to contain whitespace characters.
+- Numerical key value pairs can end with optional unit string.
+- Data type of the value is fixed as defined in the specification.
+
+Key types
+---------
+
+1. Mandatory, fully standardised.
+2. Optional, fully standardised.
+3. Driver specific.
+
+Data types
+----------
+
+- <uint> - Unsigned integer without defining the maximum value.
+- <str> - String excluding any above defined reserved characters or whitespace.
+
+Mandatory fully standardised keys
+---------------------------------
+
+- drm-driver: <str>
+
+String shall contain the name this driver registered as via the respective
+`struct drm_driver` data structure.
+
+Optional fully standardised keys
+--------------------------------
+
+- drm-pdev: <aaaa:bb.cc.d>
+
+For PCI devices this should contain the PCI slot address of the device in
+question.
+
+- drm-client-id: <uint>
+
+Unique value relating to the open DRM file descriptor used to distinguish
+duplicated and shared file descriptors. Conceptually the value should map 1:1
+to the in kernel representation of `struct drm_file` instances.
+
+Uniqueness of the value shall be either globally unique, or unique within the
+scope of each device, in which case `drm-pdev` shall be present as well.
+
+Userspace should make sure to not double account any usage statistics by using
+the above described criteria in order to associate data to individual clients.
+
+- drm-engine-<str>: <uint> ns
+
+GPUs usually contain multiple execution engines. Each shall be given a stable
+and unique name (str), with possible values documented in the driver specific
+documentation.
+
+Value shall be in specified time units which the respective GPU engine spent
+busy executing workloads belonging to this client.
+
+Values are not required to be constantly monotonic if it makes the driver
+implementation easier, but are required to catch up with the previously reported
+larger value within a reasonable period. Upon observing a value lower than what
+was previously read, userspace is expected to stay with that larger previous
+value until a monotonic update is seen.
+
+- drm-engine-capacity-<str>: <uint>
+
+Engine identifier string must be the same as the one specified in the
+drm-engine-<str> tag and shall contain a greater than zero number in case the
+exported engine corresponds to a group of identical hardware engines.
+
+In the absence of this tag parser shall assume capacity of one. Zero capacity
+is not allowed.
+
+- drm-memory-<str>: <uint> [KiB|MiB]
+
+Each possible memory type which can be used to store buffer objects by the
+GPU in question shall be given a stable and unique name to be returned as the
+string here.
+
+Value shall reflect the amount of storage currently consumed by the buffer
+object belong to this client, in the respective memory region.
+
+Default unit shall be bytes with optional unit specifiers of 'KiB' or 'MiB'
+indicating kibi- or mebi-bytes.
+
+===============================
+Driver specific implementations
+===============================
+
+:ref:`i915-usage-stats`

Documentation/gpu/i915.rst

@@ -697,3 +697,31 @@ The style guide for ``i915_reg.h``.
 
 .. kernel-doc:: drivers/gpu/drm/i915/i915_reg.h
    :doc: The i915 register macro definition style guide
+
+.. _i915-usage-stats:
+
+i915 DRM client usage stats implementation
+==========================================
+
+The drm/i915 driver implements the DRM client usage stats specification as
+documented in :ref:`drm-client-usage-stats`.
+
+Example of the output showing the implemented key value pairs and entirety of
+the currently possible format options:
+
+::
+
+      pos:    0
+      flags:  0100002
+      mnt_id: 21
+      drm-driver: i915
+      drm-pdev:   0000:00:02.0
+      drm-client-id:      7
+      drm-engine-render:  9288864723 ns
+      drm-engine-copy:    2035071108 ns
+      drm-engine-video:   0 ns
+      drm-engine-capacity-video:   2
+      drm-engine-video-enhance:   0 ns
+
+Possible `drm-engine-` key names are: `render`, `copy`, `video` and
+`video-enhance`.

Documentation/gpu/index.rst

@@ -10,6 +10,7 @@ Linux GPU Driver Developer's Guide
    drm-kms
    drm-kms-helpers
    drm-uapi
+   drm-usage-stats
    driver-uapi
    drm-client
    drivers

drivers/gpu/drm/i915/Kconfig

@@ -4,7 +4,7 @@ config DRM_I915
 	depends on DRM
 	depends on X86 && PCI
 	depends on !PREEMPT_RT
-	select INTEL_GTT
+	select INTEL_GTT if X86
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs

drivers/gpu/drm/i915/Makefile

@@ -33,6 +33,7 @@ subdir-ccflags-y += -I$(srctree)/$(src)
 
 # core driver code
 i915-y += i915_driver.o \
+	  i915_drm_client.o \
 	  i915_config.o \
 	  i915_getparam.o \
 	  i915_ioctl.o \
@@ -106,6 +107,8 @@ gt-y += \
 	gt/intel_gt_pm_debugfs.o \
 	gt/intel_gt_pm_irq.o \
 	gt/intel_gt_requests.o \
+	gt/intel_gt_sysfs.o \
+	gt/intel_gt_sysfs_pm.o \
 	gt/intel_gtt.o \
 	gt/intel_llc.o \
 	gt/intel_lrc.o \
@@ -125,6 +128,8 @@ gt-y += \
 	gt/intel_workarounds.o \
 	gt/shmem_utils.o \
 	gt/sysfs_engines.o
+# x86 intel-gtt module support
+gt-$(CONFIG_X86) += gt/intel_gt_gmch.o
 # autogenerated null render state
 gt-y += \
 	gt/gen6_renderstate.o \
@@ -185,9 +190,11 @@ i915-y += gt/uc/intel_uc.o \
 	  gt/uc/intel_uc_fw.o \
 	  gt/uc/intel_guc.o \
 	  gt/uc/intel_guc_ads.o \
+	  gt/uc/intel_guc_capture.o \
 	  gt/uc/intel_guc_ct.o \
 	  gt/uc/intel_guc_debugfs.o \
 	  gt/uc/intel_guc_fw.o \
+	  gt/uc/intel_guc_hwconfig.o \
 	  gt/uc/intel_guc_log.o \
 	  gt/uc/intel_guc_log_debugfs.o \
 	  gt/uc/intel_guc_rc.o \

drivers/gpu/drm/i915/display/intel_dpt.c

@@ -300,5 +300,5 @@ void intel_dpt_destroy(struct i915_address_space *vm)
 {
 	struct i915_dpt *dpt = i915_vm_to_dpt(vm);
 
-	i915_vm_close(&dpt->vm);
+	i915_vm_put(&dpt->vm);
 }

drivers/gpu/drm/i915/display/intel_fb.c

@@ -2029,7 +2029,7 @@ intel_user_framebuffer_create(struct drm_device *dev,
 
 	/* object is backed with LMEM for discrete */
 	i915 = to_i915(obj->base.dev);
-	if (HAS_LMEM(i915) && !i915_gem_object_can_migrate(obj, INTEL_REGION_LMEM)) {
+	if (HAS_LMEM(i915) && !i915_gem_object_can_migrate(obj, INTEL_REGION_LMEM_0)) {
 		/* object is "remote", not in local memory */
 		i915_gem_object_put(obj);
 		return ERR_PTR(-EREMOTE);

drivers/gpu/drm/i915/display/intel_fb_pin.c

@@ -140,7 +140,7 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 	if (!ret && phys_cursor)
 		ret = i915_gem_object_attach_phys(obj, alignment);
 	else if (!ret && HAS_LMEM(dev_priv))
-		ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM);
+		ret = i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0);
 	/* TODO: Do we need to sync when migration becomes async? */
 	if (!ret)
 		ret = i915_gem_object_pin_pages(obj);

drivers/gpu/drm/i915/display/intel_fbdev.c

@@ -279,7 +279,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		/* Our framebuffer is the entirety of fbdev's system memory */
 		info->fix.smem_start =
 			(unsigned long)(ggtt->gmadr.start + vma->node.start);
-		info->fix.smem_len = vma->node.size;
+		info->fix.smem_len = vma->size;
 	}
 
 	vaddr = i915_vma_pin_iomap(vma);
@@ -290,7 +290,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		goto out_unpin;
 	}
 	info->screen_base = vaddr;
-	info->screen_size = vma->node.size;
+	info->screen_size = vma->size;
 
 	drm_fb_helper_fill_info(info, &ifbdev->helper, sizes);
 

drivers/gpu/drm/i915/display/intel_plane_initial.c

@@ -3,6 +3,7 @@
  * Copyright © 2021 Intel Corporation
  */
 
+#include "gem/i915_gem_region.h"
 #include "i915_drv.h"
 #include "intel_atomic_plane.h"
 #include "intel_display.h"
@@ -46,16 +47,55 @@ static struct i915_vma *
 initial_plane_vma(struct drm_i915_private *i915,
 		  struct intel_initial_plane_config *plane_config)
 {
-	struct intel_memory_region *mem = i915->mm.stolen_region;
+	struct intel_memory_region *mem;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
+	resource_size_t phys_base;
 	u32 base, size;
+	u64 pinctl;
 
-	if (!mem || plane_config->size == 0)
+	if (plane_config->size == 0)
+		return NULL;
+
+	base = round_down(plane_config->base, I915_GTT_MIN_ALIGNMENT);
+	if (IS_DGFX(i915)) {
+		gen8_pte_t __iomem *gte = to_gt(i915)->ggtt->gsm;
+		gen8_pte_t pte;
+
+		gte += base / I915_GTT_PAGE_SIZE;
+
+		pte = ioread64(gte);
+		if (!(pte & GEN12_GGTT_PTE_LM)) {
+			drm_err(&i915->drm,
+				"Initial plane programming missing PTE_LM bit\n");
+			return NULL;
+		}
+
+		phys_base = pte & I915_GTT_PAGE_MASK;
+		mem = i915->mm.regions[INTEL_REGION_LMEM_0];
+
+		/*
+		 * We don't currently expect this to ever be placed in the
+		 * stolen portion.
+		 */
+		if (phys_base >= resource_size(&mem->region)) {
+			drm_err(&i915->drm,
+				"Initial plane programming using invalid range, phys_base=%pa\n",
+				&phys_base);
+			return NULL;
+		}
+
+		drm_dbg(&i915->drm,
+			"Using phys_base=%pa, based on initial plane programming\n",
+			&phys_base);
+	} else {
+		phys_base = base;
+		mem = i915->mm.stolen_region;
+	}
+
+	if (!mem)
 		return NULL;
 
-	base = round_down(plane_config->base,
-			  I915_GTT_MIN_ALIGNMENT);
 	size = round_up(plane_config->base + plane_config->size,
 			mem->min_page_size);
 	size -= base;
@@ -66,10 +106,11 @@ initial_plane_vma(struct drm_i915_private *i915,
 	 * features.
 	 */
 	if (IS_ENABLED(CONFIG_FRAMEBUFFER_CONSOLE) &&
+	    mem == i915->mm.stolen_region &&
 	    size * 2 > i915->stolen_usable_size)
 		return NULL;
 
-	obj = i915_gem_object_create_stolen_for_preallocated(i915, base, size);
+	obj = i915_gem_object_create_region_at(mem, phys_base, size, 0);
 	if (IS_ERR(obj))
 		return NULL;
 
@@ -99,7 +140,10 @@ initial_plane_vma(struct drm_i915_private *i915,
 	if (IS_ERR(vma))
 		goto err_obj;
 
-	if (i915_ggtt_pin(vma, NULL, 0, PIN_MAPPABLE | PIN_OFFSET_FIXED | base))
+	pinctl = PIN_GLOBAL | PIN_OFFSET_FIXED | base;
+	if (HAS_GMCH(i915))
+		pinctl |= PIN_MAPPABLE;
+	if (i915_vma_pin(vma, 0, 0, pinctl))
 		goto err_obj;
 
 	if (i915_gem_object_is_tiled(obj) &&