Merge tag 'drm-intel-gt-next-2022-11-03' of git://anongit.freedesktop…

….org/drm/drm-intel into drm-next

Driver Changes:

- Fix for #7306: [Arc A380] white flickering when using arc as a
  secondary gpu (Matt A)
- Add Wa_18017747507 for DG2 (Wayne)
- Avoid spurious WARN on DG1 due to incorrect cache_dirty flag
  (Niranjana, Matt A)
- Corrections to CS timestamp support for Gen5 and earlier (Ville)

- Fix a build error used with clang compiler on hwmon (GG)
- Improvements to LMEM handling with RPM (Anshuman, Matt A)
- Cleanups in dmabuf code (Mike)

- Selftest improvements (Matt A)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Y2N11wu175p6qeEN@jlahtine-mobl.ger.corp.intel.com

Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon

@@ -0,0 +1,75 @@
+What:		/sys/devices/.../hwmon/hwmon<i>/in0_input
+Date:		February 2023
+KernelVersion:	6.2
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RO. Current Voltage in millivolt.
+
+		Only supported for particular Intel i915 graphics platforms.
+
+What:		/sys/devices/.../hwmon/hwmon<i>/power1_max
+Date:		February 2023
+KernelVersion:	6.2
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RW. Card reactive sustained  (PL1/Tau) power limit in microwatts.
+
+		The power controller will throttle the operating frequency
+		if the power averaged over a window (typically seconds)
+		exceeds this limit.
+
+		Only supported for particular Intel i915 graphics platforms.
+
+What:		/sys/devices/.../hwmon/hwmon<i>/power1_rated_max
+Date:		February 2023
+KernelVersion:	6.2
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RO. Card default power limit (default TDP setting).
+
+		Only supported for particular Intel i915 graphics platforms.
+
+What:		/sys/devices/.../hwmon/hwmon<i>/power1_max_interval
+Date:		February 2023
+KernelVersion:	6.2
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RW. Sustained power limit interval (Tau in PL1/Tau) in
+		milliseconds over which sustained power is averaged.
+
+		Only supported for particular Intel i915 graphics platforms.
+
+What:		/sys/devices/.../hwmon/hwmon<i>/power1_crit
+Date:		February 2023
+KernelVersion:	6.2
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RW. Card reactive critical (I1) power limit in microwatts.
+
+		Card reactive critical (I1) power limit in microwatts is exposed
+		for client products. The power controller will throttle the
+		operating frequency if the power averaged over a window exceeds
+		this limit.
+
+		Only supported for particular Intel i915 graphics platforms.
+
+What:		/sys/devices/.../hwmon/hwmon<i>/curr1_crit
+Date:		February 2023
+KernelVersion:	6.2
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RW. Card reactive critical (I1) power limit in milliamperes.
+
+		Card reactive critical (I1) power limit in milliamperes is
+		exposed for server products. The power controller will throttle
+		the operating frequency if the power averaged over a window
+		exceeds this limit.
+
+		Only supported for particular Intel i915 graphics platforms.
+
+What:		/sys/devices/.../hwmon/hwmon<i>/energy1_input
+Date:		February 2023
+KernelVersion:	6.2
+Contact:	intel-gfx@lists.freedesktop.org
+Description:	RO. Energy input of device or gt in microjoules.
+
+		For i915 device level hwmon devices (name "i915") this
+		reflects energy input for the entire device. For gt level
+		hwmon devices (name "i915_gtN") this reflects energy input
+		for the gt.
+
+		Only supported for particular Intel i915 graphics platforms.

MAINTAINERS

@@ -10224,6 +10224,7 @@ Q:	http://patchwork.freedesktop.org/project/intel-gfx/
 B:	https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 C:	irc://irc.oftc.net/intel-gfx
 T:	git git://anongit.freedesktop.org/drm-intel
+F:	Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
 F:	Documentation/gpu/i915.rst
 F:	drivers/gpu/drm/i915/
 F:	include/drm/i915*

drivers/gpu/drm/i915/Kconfig.profile

@@ -57,10 +57,28 @@ config DRM_I915_PREEMPT_TIMEOUT
 	default 640 # milliseconds
 	help
 	  How long to wait (in milliseconds) for a preemption event to occur
-	  when submitting a new context via execlists. If the current context
-	  does not hit an arbitration point and yield to HW before the timer
-	  expires, the HW will be reset to allow the more important context
-	  to execute.
+	  when submitting a new context. If the current context does not hit
+	  an arbitration point and yield to HW before the timer expires, the
+	  HW will be reset to allow the more important context to execute.
+
+	  This is adjustable via
+	  /sys/class/drm/card?/engine/*/preempt_timeout_ms
+
+	  May be 0 to disable the timeout.
+
+	  The compiled in default may get overridden at driver probe time on
+	  certain platforms and certain engines which will be reflected in the
+	  sysfs control.
+
+config DRM_I915_PREEMPT_TIMEOUT_COMPUTE
+	int "Preempt timeout for compute engines (ms, jiffy granularity)"
+	default 7500 # milliseconds
+	help
+	  How long to wait (in milliseconds) for a preemption event to occur
+	  when submitting a new context to a compute capable engine. If the
+	  current context does not hit an arbitration point and yield to HW
+	  before the timer expires, the HW will be reset to allow the more
+	  important context to execute.
 
 	  This is adjustable via
 	  /sys/class/drm/card?/engine/*/preempt_timeout_ms

drivers/gpu/drm/i915/Makefile

@@ -209,6 +209,9 @@ i915-y += gt/uc/intel_uc.o \
 # graphics system controller (GSC) support
 i915-y += gt/intel_gsc.o
 
+# graphics hardware monitoring (HWMON) support
+i915-$(CONFIG_HWMON) += i915_hwmon.o
+
 # modesetting core code
 i915-y += \
 	display/hsw_ips.o \
@@ -310,15 +313,18 @@ i915-y += \
 
 i915-y += i915_perf.o
 
-# Protected execution platform (PXP) support
-i915-$(CONFIG_DRM_I915_PXP) += \
+# Protected execution platform (PXP) support. Base support is required for HuC
+i915-y += \
 	pxp/intel_pxp.o \
+	pxp/intel_pxp_tee.o \
+	pxp/intel_pxp_huc.o
+
+i915-$(CONFIG_DRM_I915_PXP) += \
 	pxp/intel_pxp_cmd.o \
 	pxp/intel_pxp_debugfs.o \
 	pxp/intel_pxp_irq.o \
 	pxp/intel_pxp_pm.o \
-	pxp/intel_pxp_session.o \
-	pxp/intel_pxp_tee.o
+	pxp/intel_pxp_session.o
 
 # Post-mortem debug and GPU hang state capture
 i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o

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

@@ -5,6 +5,7 @@
 
 #include "gem/i915_gem_domain.h"
 #include "gem/i915_gem_internal.h"
+#include "gem/i915_gem_lmem.h"
 #include "gt/gen8_ppgtt.h"
 
 #include "i915_drv.h"

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

@@ -167,7 +167,6 @@ intel_pin_and_fence_fb_obj(struct drm_framebuffer *fb,
 		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_0);
-	/* TODO: Do we need to sync when migration becomes async? */
 	if (!ret)
 		ret = i915_gem_object_pin_pages(obj);
 	if (ret)

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

@@ -100,9 +100,9 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv)
 	rsc[0].flags    = IORESOURCE_IRQ;
 	rsc[0].name     = "hdmi-lpe-audio-irq";
 
-	rsc[1].start    = pci_resource_start(pdev, GTTMMADR_BAR) +
+	rsc[1].start    = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) +
 		I915_HDMI_LPE_AUDIO_BASE;
-	rsc[1].end      = pci_resource_start(pdev, GTTMMADR_BAR) +
+	rsc[1].end      = pci_resource_start(pdev, GEN4_GTTMMADR_BAR) +
 		I915_HDMI_LPE_AUDIO_BASE + I915_HDMI_LPE_AUDIO_SIZE - 1;
 	rsc[1].flags    = IORESOURCE_MEM;
 	rsc[1].name     = "hdmi-lpe-audio-mmio";

drivers/gpu/drm/i915/gem/i915_gem_context.c

@@ -1452,7 +1452,7 @@ static void engines_idle_release(struct i915_gem_context *ctx,
 		int err;
 
 		/* serialises with execbuf */
-		set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
+		intel_context_close(ce);
 		if (!intel_context_pin_if_active(ce))
 			continue;
 
@@ -2298,7 +2298,6 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	}
 
 	args->ctx_id = id;
-	drm_dbg(&i915->drm, "HW context %d created\n", args->ctx_id);
 
 	return 0;
 

drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c

@@ -25,43 +25,44 @@ static struct drm_i915_gem_object *dma_buf_to_obj(struct dma_buf *buf)
 	return to_intel_bo(buf->priv);
 }
 
-static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attachment,
+static struct sg_table *i915_gem_map_dma_buf(struct dma_buf_attachment *attach,
 					     enum dma_data_direction dir)
 {
-	struct drm_i915_gem_object *obj = dma_buf_to_obj(attachment->dmabuf);
-	struct sg_table *st;
+	struct drm_i915_gem_object *obj = dma_buf_to_obj(attach->dmabuf);
+	struct sg_table *sgt;
 	struct scatterlist *src, *dst;
 	int ret, i;
 
-	/* Copy sg so that we make an independent mapping */
-	st = kmalloc(sizeof(struct sg_table), GFP_KERNEL);
-	if (st == NULL) {
+	/*
+	 * Make a copy of the object's sgt, so that we can make an independent
+	 * mapping
+	 */
+	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
+	if (!sgt) {
 		ret = -ENOMEM;
 		goto err;
 	}
 
-	ret = sg_alloc_table(st, obj->mm.pages->nents, GFP_KERNEL);
+	ret = sg_alloc_table(sgt, obj->mm.pages->orig_nents, GFP_KERNEL);
 	if (ret)
 		goto err_free;
 
-	src = obj->mm.pages->sgl;
-	dst = st->sgl;
-	for (i = 0; i < obj->mm.pages->nents; i++) {
+	dst = sgt->sgl;
+	for_each_sg(obj->mm.pages->sgl, src, obj->mm.pages->orig_nents, i) {
 		sg_set_page(dst, sg_page(src), src->length, 0);
 		dst = sg_next(dst);
-		src = sg_next(src);
 	}
 
-	ret = dma_map_sgtable(attachment->dev, st, dir, DMA_ATTR_SKIP_CPU_SYNC);
+	ret = dma_map_sgtable(attach->dev, sgt, dir, DMA_ATTR_SKIP_CPU_SYNC);
 	if (ret)
 		goto err_free_sg;
 
-	return st;
+	return sgt;
 
 err_free_sg:
-	sg_free_table(st);
+	sg_free_table(sgt);
 err_free:
-	kfree(st);
+	kfree(sgt);
 err:
 	return ERR_PTR(ret);
 }
@@ -236,15 +237,15 @@ struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags)
 static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct sg_table *pages;
+	struct sg_table *sgt;
 	unsigned int sg_page_sizes;
 
 	assert_object_held(obj);
 
-	pages = dma_buf_map_attachment(obj->base.import_attach,
-				       DMA_BIDIRECTIONAL);
-	if (IS_ERR(pages))
-		return PTR_ERR(pages);
+	sgt = dma_buf_map_attachment(obj->base.import_attach,
+				     DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt))
+		return PTR_ERR(sgt);
 
 	/*
 	 * DG1 is special here since it still snoops transactions even with
@@ -261,16 +262,16 @@ static int i915_gem_object_get_pages_dmabuf(struct drm_i915_gem_object *obj)
 	    (!HAS_LLC(i915) && !IS_DG1(i915)))
 		wbinvd_on_all_cpus();
 
-	sg_page_sizes = i915_sg_dma_sizes(pages->sgl);
-	__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
+	sg_page_sizes = i915_sg_dma_sizes(sgt->sgl);
+	__i915_gem_object_set_pages(obj, sgt, sg_page_sizes);
 
 	return 0;
 }
 
 static void i915_gem_object_put_pages_dmabuf(struct drm_i915_gem_object *obj,
-					     struct sg_table *pages)
+					     struct sg_table *sgt)
 {
-	dma_buf_unmap_attachment(obj->base.import_attach, pages,
+	dma_buf_unmap_attachment(obj->base.import_attach, sgt,
 				 DMA_BIDIRECTIONAL);
 }
 
@@ -313,7 +314,7 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 	get_dma_buf(dma_buf);
 
 	obj = i915_gem_object_alloc();
-	if (obj == NULL) {
+	if (!obj) {
 		ret = -ENOMEM;
 		goto fail_detach;
 	}

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -2954,11 +2954,6 @@ await_fence_array(struct i915_execbuffer *eb,
 	int err;
 
 	for (n = 0; n < eb->num_fences; n++) {
-		struct drm_syncobj *syncobj;
-		unsigned int flags;
-
-		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
-
 		if (!eb->fences[n].dma_fence)
 			continue;
 

drivers/gpu/drm/i915/gem/i915_gem_internal.c

@@ -6,7 +6,6 @@
 
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
-#include <linux/swiotlb.h>
 
 #include "i915_drv.h"
 #include "i915_gem.h"
@@ -38,22 +37,12 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
 	struct scatterlist *sg;
 	unsigned int sg_page_sizes;
 	unsigned int npages;
-	int max_order;
+	int max_order = MAX_ORDER;
+	unsigned int max_segment;
 	gfp_t gfp;
 
-	max_order = MAX_ORDER;
-#ifdef CONFIG_SWIOTLB
-	if (is_swiotlb_active(obj->base.dev->dev)) {
-		unsigned int max_segment;
-
-		max_segment = swiotlb_max_segment();
-		if (max_segment) {
-			max_segment = max_t(unsigned int, max_segment,
-					    PAGE_SIZE) >> PAGE_SHIFT;
-			max_order = min(max_order, ilog2(max_segment));
-		}
-	}
-#endif
+	max_segment = i915_sg_segment_size(i915->drm.dev) >> PAGE_SHIFT;
+	max_order = min(max_order, get_order(max_segment));
 
 	gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE;
 	if (IS_I965GM(i915) || IS_I965G(i915)) {

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

@@ -413,7 +413,7 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
 	vma->mmo = mmo;
 
 	if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)
-		intel_wakeref_auto(&to_gt(i915)->userfault_wakeref,
+		intel_wakeref_auto(&i915->runtime_pm.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
 	if (write) {
@@ -557,11 +557,13 @@ void i915_gem_object_runtime_pm_release_mmap_offset(struct drm_i915_gem_object *
 
 	drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping);
 
-	if (obj->userfault_count) {
-		/* rpm wakeref provide exclusive access */
-		list_del(&obj->userfault_link);
-		obj->userfault_count = 0;
-	}
+	/*
+	 * We have exclusive access here via runtime suspend. All other callers
+	 * must first grab the rpm wakeref.
+	 */
+	GEM_BUG_ON(!obj->userfault_count);
+	list_del(&obj->userfault_link);
+	obj->userfault_count = 0;
 }
 
 void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj)
@@ -587,13 +589,6 @@ void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj)
 		spin_lock(&obj->mmo.lock);
 	}
 	spin_unlock(&obj->mmo.lock);
-
-	if (obj->userfault_count) {
-		mutex_lock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock);
-		list_del(&obj->userfault_link);
-		mutex_unlock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock);
-		obj->userfault_count = 0;
-	}
 }
 
 static struct i915_mmap_offset *