Merge tag 'drm-next-2023-04-24' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "There is a new Qualcomm accel driver for their QAIC, dma-fence got a
  deadline feature added, lots of refactoring around fbdev emulation,
  and the usual pre-release hw enablements from AMD and Intel and fixes
  everywhere.

  New drivers:
   - add QAIC acceleration driver

  dma-buf:
   - constify kobj_type structs
   - Reject prime DMA-Buf attachment if get_sg_table is missing.

  fbdev:
   - cmdline parser fixes
   - implement fbdev emulation for GEM DMA drivers
   - always use shadow buffer in fbdev emulation helpers

  dma-fence:
   - add deadline hint to fences
   - signal private stub fence

  core:
   - improve DisplayID 2.0 and EDID parsing
   - add gem eviction function + callback
   - prep to convert shmem helper to GEM resv lock
   - move suballocator from radeon/amdgpu to core for Xe
   - HPD polling fixes
   - Documentation improvements
   - Add atomic enable_plane callback
   - use tgid instead of pid for client tracking
   - DP: Add SDP Error Detection Configuration Register
   - Add prime import/export to vram-helper
   - use pci aperture helpers in more drivers

  panel:
   - Radxa 8/10HD support
   - Samsung AMD495QA01 support
   - Elida KD50T048A
   - Sony TD4353
   - Novatek NT36523
   - STARRY 2081101QFH032011-53G
   - B133UAN01.0
   - AUO NE135FBM-N41

  i915:
   - More MTL enabling
   - fix s/r problems with MEI/PXP
   - Implement fb_dirty for PSR,FBC,DRRS fixes
   - Fix eDP+DSI dual panel systems
   - Fix issue #6333: "list_add corruption" and full system lockup from
     performance monitoring
   - Don't use stolen memory or BAR for ring buffers on LLC platforms
   - Make sure DSM size has correct 1MiB granularity on Gen12+
   - Whitelist COMMON_SLICE_CHICKEN3 for UMD access on Gen12+
   - Add engine TLB invalidation for Meteorlake
   - Fix GSC races on driver load/unload on Meteorlake+
   - Make kobj_type structures constant
   - Move fd_install after last use of fence
   - wm/vblank refactoring
   - display code refactoring
   - Create GSC submission targeting HDCP and PXP usages on MTL+
   - Enable HDCP2.x via GSC CS
   - Fix context runtime accounting on sysfs fdinfo for heavy workloads
   - Use i915 instead of dev_priv insied the file_priv structure
   - Replace fake flex-array with flexible-array member

  amdgpu:
   - Make kobj structures const
   - Generalize dmabuf import to work with KFD
   - Add capped/uncapped workload handling for supported APUs
   - Expose additional memory stats via fdinfo
   - Register vga_switcheroo for apple-gmux
   - Initial NBIO7.9, GC 9.4.3, GFXHUB 1.2, MMHUB 1.8 support
   - Initial DC FAM infrastructure
   - Link DC backlight to connector device rather than PCI device
   - Add sysfs nodes for secondary VCN clocks

  amdkfd:
   - Make kobj structures const
   - Support for exporting buffers via dmabuf
   - Multi-VMA page migration fixes
   - initial GC 9.4.3 support

  radeon:
   - iMac fix
   - convert to client based fbdev emulation

  habanalabs:
   - Add opcodes to the CS ioctl to allow user to stall/resume specific
     engines inside Gaudi2.
   - INFO ioctl the amount of device memory that the driver and f/w
     reserve for themselves.
   - INFO ioctl a bit-mask of the available rotator engines
   - INFO ioctl the register's address of the f/w that should be used to
     trigger interrupts
   - INFO ioctl two new opcodes to fetch information on h/w and f/w
     events
   - Enable graceful reset mechanism for compute-reset.
   - Align to the latest firmware specs.
   - Enforce the release order of the compute device and dma-buf.

  msm:
   - UBWC decoder programming rework
   - SM8550, SM8450 bindings update
   - uapi C++ fix
   - a3xx and a4xx devfreq support
   - GPU and GEM updates to avoid allocations which could trigger
     reclaim (shrinker) in fence signaling path
   - dma-fence deadline hint support and wait-boost
   - a640/650 speed bin support

  cirrus:
   - convert to regular atomic helpers
   - add damage clipping

  mediatek:
   - 10-bit overlay support
   - mt8195 support
   - Only trigger DRM HPD events if bridge is attached
   - Change the aux retries times when receiving AUX_DEFER

  rockchip:
   - add 4K support

  vc4:
   - use drm_gem_objects

  virtio:
   - allow KMS support to be disabled
   - add damage clipping

  vmwgfx:
   - buffer object lifetime fixes

  exynos:
   - move MIPI DSI driver to drm bridge for iMX sharing
   - use kernel fbdev emulation

  panfrost:
   - add support for mali MT81xx devices
   - add speed binning support

  lima:
   - add usage stats

  tegra:
   - fbdev client conversion

  vkms:
   - Add primary plane positioning support"

* tag 'drm-next-2023-04-24' of git://anongit.freedesktop.org/drm/drm: (1495 commits)
  drm/i915/dp_mst: Fix active port PLL selection for secondary MST streams
  drm/exynos: Implement fbdev emulation as in-kernel client
  drm/exynos: Initialize fbdev DRM client
  drm/exynos: Remove fb_helper from struct exynos_drm_private
  drm/exynos: Remove struct exynos_drm_fbdev
  drm/exynos: Remove exynos_gem from struct exynos_drm_fbdev
  drm/i915: Fix memory leaks in i915 selftests
  drm/i915: Make intel_get_crtc_new_encoder() less oopsy
  drm/i915/gt: Avoid out-of-bounds access when loading HuC
  drm/amdgpu: add some basic elements for multiple XCD case
  drm/amdgpu: move vmhub out of amdgpu_ring_funcs (v4)
  Revert "drm/amdgpu: enable ras for mp0 v13_0_10 on SRIOV"
  drm/amdgpu: add common ip block for GC 9.4.3
  drm/amd/display: Add logging when DP link training Clock recovery is Successful
  drm/amdgpu: add common early init support for GC 9.4.3
  drm/amdgpu: switch to v9_4_3 gfx_funcs callbacks for GC 9.4.3
  drm/amd/display: Add logging when setting DP sink power state fails
  drm/amdkfd: Add gfx_target_version for GC 9.4.3
  drm/amdkfd: Enable HW_UPDATE_RPTR on GC 9.4.3
  drm/amdgpu: reserve the old gc_11_0_*_mes.bin
  ...

1 files changed, 24 insertions, 2 deletions

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2P.h b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
index 2687404d9d21..1cebe707772e 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2P.h
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
@@ -240,6 +240,8 @@
 #define GAUDI2_SOB_INCREMENT_BY_ONE	(FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_VAL_MASK, 1) | \
 					FIELD_PREP(DCORE0_SYNC_MNGR_OBJS_SOB_OBJ_INC_MASK, 1))
 
+#define GAUDI2_NUM_TESTED_QS (GAUDI2_QUEUE_ID_CPU_PQ - GAUDI2_QUEUE_ID_PDMA_0_0)
+
 #define GAUDI2_NUM_OF_GLBL_ERR_CAUSE		8
 
 enum gaudi2_reserved_sob_id {
@@ -387,6 +389,8 @@ enum gaudi2_edma_id {
  * We have 64 CQ's per dcore, CQ0 in dcore 0 is reserved for legacy mode
  */
 #define GAUDI2_NUM_USER_INTERRUPTS 255
+#define GAUDI2_NUM_RESERVED_INTERRUPTS 1
+#define GAUDI2_TOTAL_USER_INTERRUPTS (GAUDI2_NUM_USER_INTERRUPTS + GAUDI2_NUM_RESERVED_INTERRUPTS)
 
 enum gaudi2_irq_num {
 	GAUDI2_IRQ_NUM_EVENT_QUEUE = GAUDI2_EVENT_QUEUE_MSIX_IDX,
@@ -410,12 +414,15 @@ enum gaudi2_irq_num {
 	GAUDI2_IRQ_NUM_SHARED_DEC0_ABNRM,
 	GAUDI2_IRQ_NUM_SHARED_DEC1_NRM,
 	GAUDI2_IRQ_NUM_SHARED_DEC1_ABNRM,
+	GAUDI2_IRQ_NUM_DEC_LAST = GAUDI2_IRQ_NUM_SHARED_DEC1_ABNRM,
 	GAUDI2_IRQ_NUM_COMPLETION,
 	GAUDI2_IRQ_NUM_NIC_PORT_FIRST,
 	GAUDI2_IRQ_NUM_NIC_PORT_LAST = (GAUDI2_IRQ_NUM_NIC_PORT_FIRST + NIC_NUMBER_OF_PORTS - 1),
+	GAUDI2_IRQ_NUM_TPC_ASSERT,
 	GAUDI2_IRQ_NUM_RESERVED_FIRST,
-	GAUDI2_IRQ_NUM_RESERVED_LAST = (GAUDI2_MSIX_ENTRIES - GAUDI2_NUM_USER_INTERRUPTS - 1),
-	GAUDI2_IRQ_NUM_USER_FIRST,
+	GAUDI2_IRQ_NUM_RESERVED_LAST = (GAUDI2_MSIX_ENTRIES - GAUDI2_TOTAL_USER_INTERRUPTS - 1),
+	GAUDI2_IRQ_NUM_UNEXPECTED_ERROR = RESERVED_MSIX_UNEXPECTED_USER_ERROR_INTERRUPT,
+	GAUDI2_IRQ_NUM_USER_FIRST = GAUDI2_IRQ_NUM_UNEXPECTED_ERROR + 1,
 	GAUDI2_IRQ_NUM_USER_LAST = (GAUDI2_IRQ_NUM_USER_FIRST + GAUDI2_NUM_USER_INTERRUPTS - 1),
 	GAUDI2_IRQ_NUM_LAST = (GAUDI2_MSIX_ENTRIES - 1)
 };
@@ -448,6 +455,17 @@ struct dup_block_ctx {
 };
 
 /**
+ * struct gaudi2_queues_test_info - Holds the address of a the messages used for testing the
+ *                                  device queues.
+ * @dma_addr: the address used by the HW for accessing the message.
+ * @kern_addr: The address used by the driver for accessing the message.
+ */
+struct gaudi2_queues_test_info {
+	dma_addr_t dma_addr;
+	void *kern_addr;
+};
+
+/**
  * struct gaudi2_device - ASIC specific manage structure.
  * @cpucp_info_get: get information on device from CPU-CP
  * @mapped_blocks: array that holds the base address and size of all blocks
@@ -505,6 +523,7 @@ struct dup_block_ctx {
  * @flush_db_fifo: flag to force flush DB FIFO after a write.
  * @hbm_cfg: HBM subsystem settings
  * @hw_queues_lock_mutex: used by simulator instead of hw_queues_lock.
+ * @queues_test_info: information used by the driver when testing the HW queues.
  */
 struct gaudi2_device {
 	int (*cpucp_info_get)(struct hl_device *hdev);
@@ -532,6 +551,9 @@ struct gaudi2_device {
 	u32				events_stat[GAUDI2_EVENT_SIZE];
 	u32				events_stat_aggregate[GAUDI2_EVENT_SIZE];
 	u32				num_of_valid_hw_events;
+
+	/* Queue testing */
+	struct gaudi2_queues_test_info	queues_test_info[GAUDI2_NUM_TESTED_QS];
 };
 
 /*