Merge tag 'drm-next-2023-06-29' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "There is one set of patches to misc for a i915 gsc/mei proxy driver.

  Otherwise it's mostly amdgpu/i915/msm, lots of hw enablement and lots
  of refactoring.

  core:
   - replace strlcpy with strscpy
   - EDID changes to support further conversion to struct drm_edid
   - Move i915 DSC parameter code to common DRM helpers
   - Add Colorspace functionality

  aperture:
   - ignore framebuffers with non-primary devices

  fbdev:
   - use fbdev i/o helpers
   - add Kconfig options for fb_ops helpers
   - use new fb io helpers directly in drivers

  sysfs:
   - export DRM connector ID

  scheduler:
   - Avoid an infinite loop

  ttm:
   - store function table in .rodata
   - Add query for TTM mem limit
   - Add NUMA awareness to pools
   - Export ttm_pool_fini()

  bridge:
   - fsl-ldb: support i.MX6SX
   - lt9211, lt9611: remove blanking packets
   - tc358768: implement input bus formats, devm cleanups
   - ti-snd65dsi86: implement wait_hpd_asserted
   - analogix: fix endless probe loop
   - samsung-dsim: support swapped clock, fix enabling, support var
     clock
   - display-connector: Add support for external power supply
   - imx: Fix module linking
   - tc358762: Support reset GPIO

  panel:
   - nt36523: Support Lenovo J606F
   - st7703: Support Anbernic RG353V-V2
   - InnoLux G070ACE-L01 support
   - boe-tv101wum-nl6: Improve initialization
   - sharp-ls043t1le001: Mode fixes
   - simple: BOE EV121WXM-N10-1850, S6D7AA0
   - Ampire AM-800480L1TMQW-T00H
   - Rocktech RK043FN48H
   - Starry himax83102-j02
   - Starry ili9882t

  amdgpu:
   - add new ctx query flag to handle reset better
   - add new query/set shadow buffer for rdna3
   - DCN 3.2/3.1.x/3.0.x updates
   - Enable DC_FP on loongarch
   - PCIe fix for RDNA2
   - improve DC FAMS/SubVP support for better power management
   - partition support for lots of engines
   - Take NUMA into account when allocating memory
   - Add new DRM_AMDGPU_WERROR config parameter to help with CI
   - Initial SMU13 overdrive support
   - Add support for new colorspace KMS API
   - W=1 fixes

  amdkfd:
   - Query TTM mem limit rather than hardcoding it
   - GC 9.4.3 partition support
   - Handle NUMA for partitions
   - Add debugger interface for enabling gdb
   - Add KFD event age tracking

  radeon:
   - Fix possible UAF

  i915:
   - new getparam for PXP support
   - GSC/MEI proxy driver
   - Meteorlake display enablement
   - avoid clearing preallocated framebuffers with TTM
   - implement framebuffer mmap support
   - Disable sampler indirect state in bindless heap
   - Enable fdinfo for GuC backends
   - GuC loading and firmware table handling fixes
   - Various refactors for multi-tile enablement
   - Define MOCS and PAT tables for MTL
   - GSC/MEI support for Meteorlake
   - PMU multi-tile support
   - Large driver kernel doc cleanup
   - Allow VRR toggling and arbitrary refresh rates
   - Support async flips on linear buffers on display ver 12+
   - Expose CRTC CTM property on ILK/SNB/VLV
   - New debugfs for display clock frequencies
   - Hotplug refactoring
   - Display refactoring
   - I915_GEM_CREATE_EXT_SET_PAT for Mesa on Meteorlake
   - Use large rings for compute contexts
   - HuC loading for MTL
   - Allow user to set cache at BO creation
   - MTL powermanagement enhancements
   - Switch to dedicated workqueues to stop using flush_scheduled_work()
   - Move display runtime init under display/
   - Remove 10bit gamma on desktop gen3 parts, they don't support it

  habanalabs:
   - uapi: return 0 for user queries if there was a h/w or f/w error
   - Add pci health check when we lose connection with the firmware.
     This can be used to distinguish between pci link down and firmware
     getting stuck.
   - Add more info to the error print when TPC interrupt occur.
   - Firmware fixes

  msm:
   - Adreno A660 bindings
   - SM8350 MDSS bindings fix
   - Added support for DPU on sm6350 and sm6375 platforms
   - Implemented tearcheck support to support vsync on SM150 and newer
     platforms
   - Enabled missing features (DSPP, DSC, split display) on sc8180x,
     sc8280xp, sm8450
   - Added support for DSI and 28nm DSI PHY on MSM8226 platform
   - Added support for DSI on sm6350 and sm6375 platforms
   - Added support for display controller on MSM8226 platform
   - A690 GPU support
   - Move cmdstream dumping out of fence signaling path
   - a610 support
   - Support for a6xx devices without GMU

  nouveau:
   - NULL ptr before deref fixes

  armada:
   - implement fbdev emulation as client

  sun4i:
   - fix mipi-dsi dotclock
   - release clocks

  vc4:
   - rgb range toggle property
   - BT601 / BT2020 HDMI support

  vkms:
   - convert to drmm helpers
   - add reflection and rotation support
   - fix rgb565 conversion

  gma500:
   - fix iomem access

  shmobile:
   - support renesas soc platform
   - enable fbdev

  mxsfb:
   - Add support for i.MX93 LCDIF

  stm:
   - dsi: Use devm_ helper
   - ltdc: Fix potential invalid pointer deref

  renesas:
   - Group drivers in renesas subdirectory to prepare for new platform
   - Drop deprecated R-Car H3 ES1.x support

  meson:
   - Add support for MIPI DSI displays

  virtio:
   - add sync object support

  mediatek:
   - Add display binding document for MT6795"

* tag 'drm-next-2023-06-29' of git://anongit.freedesktop.org/drm/drm: (1791 commits)
  drm/i915: Fix a NULL vs IS_ERR() bug
  drm/i915: make i915_drm_client_fdinfo() reference conditional again
  drm/i915/huc: Fix missing error code in intel_huc_init()
  drm/i915/gsc: take a wakeref for the proxy-init-completion check
  drm/msm/a6xx: Add A610 speedbin support
  drm/msm/a6xx: Add A619_holi speedbin support
  drm/msm/a6xx: Use adreno_is_aXYZ macros in speedbin matching
  drm/msm/a6xx: Use "else if" in GPU speedbin rev matching
  drm/msm/a6xx: Fix some A619 tunables
  drm/msm/a6xx: Add A610 support
  drm/msm/a6xx: Add support for A619_holi
  drm/msm/adreno: Disable has_cached_coherent in GMU wrapper configurations
  drm/msm/a6xx: Introduce GMU wrapper support
  drm/msm/a6xx: Move CX GMU power counter enablement to hw_init
  drm/msm/a6xx: Extend and explain UBWC config
  drm/msm/a6xx: Remove both GBIF and RBBM GBIF halt on hw init
  drm/msm/a6xx: Add a helper for software-resetting the GPU
  drm/msm/a6xx: Improve a6xx_bus_clear_pending_transactions()
  drm/msm/a6xx: Move a6xx_bus_clear_pending_transactions to a6xx_gpu
  drm/msm/a6xx: Move force keepalive vote removal to a6xx_gmu_force_off()
  ...

22 files changed, 547 insertions, 696 deletions

diff --git a/drivers/accel/habanalabs/common/command_buffer.c b/drivers/accel/habanalabs/common/command_buffer.c
index 6e09f48750a0..08f7aee42624 100644
--- a/drivers/accel/habanalabs/common/command_buffer.c
+++ b/drivers/accel/habanalabs/common/command_buffer.c
@@ -27,12 +27,6 @@ static int cb_map_mem(struct hl_ctx *ctx, struct hl_cb *cb)
 		return -EINVAL;
 	}
 
-	if (!hdev->mmu_enable) {
-		dev_err_ratelimited(hdev->dev,
-				"Cannot map CB because MMU is disabled\n");
-		return -EINVAL;
-	}
-
 	if (cb->is_mmu_mapped)
 		return 0;
 
diff --git a/drivers/accel/habanalabs/common/command_submission.c b/drivers/accel/habanalabs/common/command_submission.c
index af9d2e22c6e7..c23829dab97a 100644
--- a/drivers/accel/habanalabs/common/command_submission.c
+++ b/drivers/accel/habanalabs/common/command_submission.c
@@ -280,14 +280,8 @@ bool cs_needs_timeout(struct hl_cs *cs)
 
 static bool is_cb_patched(struct hl_device *hdev, struct hl_cs_job *job)
 {
-	/*
-	 * Patched CB is created for external queues jobs, and for H/W queues
-	 * jobs if the user CB was allocated by driver and MMU is disabled.
-	 */
-	return (job->queue_type == QUEUE_TYPE_EXT ||
-			(job->queue_type == QUEUE_TYPE_HW &&
-					job->is_kernel_allocated_cb &&
-					!hdev->mmu_enable));
+	/* Patched CB is created for external queues jobs */
+	return (job->queue_type == QUEUE_TYPE_EXT);
 }
 
 /*
@@ -363,14 +357,13 @@ static void hl_complete_job(struct hl_device *hdev, struct hl_cs_job *job)
 		}
 	}
 
-	/* For H/W queue jobs, if a user CB was allocated by driver and MMU is
-	 * enabled, the user CB isn't released in cs_parser() and thus should be
+	/* For H/W queue jobs, if a user CB was allocated by driver,
+	 * the user CB isn't released in cs_parser() and thus should be
 	 * released here. This is also true for INT queues jobs which were
 	 * allocated by driver.
 	 */
-	if ((job->is_kernel_allocated_cb &&
-		((job->queue_type == QUEUE_TYPE_HW && hdev->mmu_enable) ||
-				job->queue_type == QUEUE_TYPE_INT))) {
+	if (job->is_kernel_allocated_cb &&
+			(job->queue_type == QUEUE_TYPE_HW || job->queue_type == QUEUE_TYPE_INT)) {
 		atomic_dec(&job->user_cb->cs_cnt);
 		hl_cb_put(job->user_cb);
 	}
@@ -804,12 +797,14 @@ out:
 
 static void cs_timedout(struct work_struct *work)
 {
+	struct hl_cs *cs = container_of(work, struct hl_cs, work_tdr.work);
+	bool skip_reset_on_timeout, device_reset = false;
 	struct hl_device *hdev;
 	u64 event_mask = 0x0;
+	uint timeout_sec;
 	int rc;
-	struct hl_cs *cs = container_of(work, struct hl_cs,
-						 work_tdr.work);
-	bool skip_reset_on_timeout = cs->skip_reset_on_timeout, device_reset = false;
+
+	skip_reset_on_timeout = cs->skip_reset_on_timeout;
 
 	rc = cs_get_unless_zero(cs);
 	if (!rc)
@@ -840,29 +835,31 @@ static void cs_timedout(struct work_struct *work)
 		event_mask |= HL_NOTIFIER_EVENT_CS_TIMEOUT;
 	}
 
+	timeout_sec = jiffies_to_msecs(hdev->timeout_jiffies) / 1000;
+
 	switch (cs->type) {
 	case CS_TYPE_SIGNAL:
 		dev_err(hdev->dev,
-			"Signal command submission %llu has not finished in time!\n",
-			cs->sequence);
+			"Signal command submission %llu has not finished in %u seconds!\n",
+			cs->sequence, timeout_sec);
 		break;
 
 	case CS_TYPE_WAIT:
 		dev_err(hdev->dev,
-			"Wait command submission %llu has not finished in time!\n",
-			cs->sequence);
+			"Wait command submission %llu has not finished in %u seconds!\n",
+			cs->sequence, timeout_sec);
 		break;
 
 	case CS_TYPE_COLLECTIVE_WAIT:
 		dev_err(hdev->dev,
-			"Collective Wait command submission %llu has not finished in time!\n",
-			cs->sequence);
+			"Collective Wait command submission %llu has not finished in %u seconds!\n",
+			cs->sequence, timeout_sec);
 		break;
 
 	default:
 		dev_err(hdev->dev,
-			"Command submission %llu has not finished in time!\n",
-			cs->sequence);
+			"Command submission %llu has not finished in %u seconds!\n",
+			cs->sequence, timeout_sec);
 		break;
 	}
 
@@ -1139,11 +1136,10 @@ static void force_complete_cs(struct hl_device *hdev)
 	spin_unlock(&hdev->cs_mirror_lock);
 }
 
-void hl_abort_waitings_for_completion(struct hl_device *hdev)
+void hl_abort_waiting_for_cs_completions(struct hl_device *hdev)
 {
 	force_complete_cs(hdev);
 	force_complete_multi_cs(hdev);
-	hl_release_pending_user_interrupts(hdev);
 }
 
 static void job_wq_completion(struct work_struct *work)
@@ -1948,8 +1944,7 @@ static int cs_ioctl_signal_wait_create_jobs(struct hl_device *hdev,
 	else
 		cb_size = hdev->asic_funcs->get_signal_cb_size(hdev);
 
-	cb = hl_cb_kernel_create(hdev, cb_size,
-				q_type == QUEUE_TYPE_HW && hdev->mmu_enable);
+	cb = hl_cb_kernel_create(hdev, cb_size, q_type == QUEUE_TYPE_HW);
 	if (!cb) {
 		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
 		atomic64_inc(&cntr->out_of_mem_drop_cnt);
@@ -2152,7 +2147,7 @@ static int cs_ioctl_unreserve_signals(struct hl_fpriv *hpriv, u32 handle_id)
 
 			hdev->asic_funcs->hw_queues_unlock(hdev);
 			rc = -EINVAL;
-			goto out;
+			goto out_unlock;
 		}
 
 		/*
@@ -2167,15 +2162,21 @@ static int cs_ioctl_unreserve_signals(struct hl_fpriv *hpriv, u32 handle_id)
 
 		/* Release the id and free allocated memory of the handle */
 		idr_remove(&mgr->handles, handle_id);
+
+		/* unlock before calling ctx_put, where we might sleep */
+		spin_unlock(&mgr->lock);
 		hl_ctx_put(encaps_sig_hdl->ctx);
 		kfree(encaps_sig_hdl);
+		goto out;
 	} else {
 		rc = -EINVAL;
 		dev_err(hdev->dev, "failed to unreserve signals, cannot find handler\n");
 	}
-out:
+
+out_unlock:
 	spin_unlock(&mgr->lock);
 
+out:
 	return rc;
 }
 
diff --git a/drivers/accel/habanalabs/common/debugfs.c b/drivers/accel/habanalabs/common/debugfs.c
index 22dd17c077c0..9e84a47a21dc 100644
--- a/drivers/accel/habanalabs/common/debugfs.c
+++ b/drivers/accel/habanalabs/common/debugfs.c
@@ -255,9 +255,6 @@ static int vm_show(struct seq_file *s, void *data)
 	u64 j;
 	int i;
 
-	if (!dev_entry->hdev->mmu_enable)
-		return 0;
-
 	mutex_lock(&dev_entry->ctx_mem_hash_mutex);
 
 	list_for_each_entry(ctx, &dev_entry->ctx_mem_hash_list, debugfs_list) {
@@ -436,9 +433,6 @@ static int mmu_show(struct seq_file *s, void *data)
 	u64 virt_addr = dev_entry->mmu_addr, phys_addr;
 	int i;
 
-	if (!hdev->mmu_enable)
-		return 0;
-
 	if (dev_entry->mmu_asid == HL_KERNEL_ASID_ID)
 		ctx = hdev->kernel_ctx;
 	else
@@ -496,9 +490,6 @@ static ssize_t mmu_asid_va_write(struct file *file, const char __user *buf,
 	char *c;
 	ssize_t rc;
 
-	if (!hdev->mmu_enable)
-		return count;
-
 	if (count > sizeof(kbuf) - 1)
 		goto err;
 	if (copy_from_user(kbuf, buf, count))
@@ -535,9 +526,6 @@ static int mmu_ack_error(struct seq_file *s, void *data)
 	struct hl_device *hdev = dev_entry->hdev;
 	int rc;
 
-	if (!hdev->mmu_enable)
-		return 0;
-
 	if (!dev_entry->mmu_cap_mask) {
 		dev_err(hdev->dev, "mmu_cap_mask is not set\n");
 		goto err;
@@ -563,9 +551,6 @@ static ssize_t mmu_ack_error_value_write(struct file *file,
 	char kbuf[MMU_KBUF_SIZE];
 	ssize_t rc;
 
-	if (!hdev->mmu_enable)
-		return count;
-
 	if (count > sizeof(kbuf) - 1)
 		goto err;
 
@@ -661,9 +646,6 @@ static bool hl_is_device_va(struct hl_device *hdev, u64 addr)
 {
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 
-	if (!hdev->mmu_enable)
-		goto out;
-
 	if (prop->dram_supports_virtual_memory &&
 		(addr >= prop->dmmu.start_addr && addr < prop->dmmu.end_addr))
 		return true;
@@ -675,7 +657,7 @@ static bool hl_is_device_va(struct hl_device *hdev, u64 addr)
 	if (addr >= prop->pmmu_huge.start_addr &&
 		addr < prop->pmmu_huge.end_addr)
 		return true;
-out:
+
 	return false;
 }
 
@@ -685,9 +667,6 @@ static bool hl_is_device_internal_memory_va(struct hl_device *hdev, u64 addr,
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u64 dram_start_addr, dram_end_addr;
 
-	if (!hdev->mmu_enable)
-		return false;
-
 	if (prop->dram_supports_virtual_memory) {
 		dram_start_addr = prop->dmmu.start_addr;
 		dram_end_addr = prop->dmmu.end_addr;
@@ -1756,17 +1735,15 @@ static void add_files_to_device(struct hl_device *hdev, struct hl_dbg_device_ent
 	}
 }
 
-void hl_debugfs_add_device(struct hl_device *hdev)
+int hl_debugfs_device_init(struct hl_device *hdev)
 {
 	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
 	int count = ARRAY_SIZE(hl_debugfs_list);
 
 	dev_entry->hdev = hdev;
-	dev_entry->entry_arr = kmalloc_array(count,
-					sizeof(struct hl_debugfs_entry),
-					GFP_KERNEL);
+	dev_entry->entry_arr = kmalloc_array(count, sizeof(struct hl_debugfs_entry), GFP_KERNEL);
 	if (!dev_entry->entry_arr)
-		return;
+		return -ENOMEM;
 
 	dev_entry->data_dma_blob_desc.size = 0;
 	dev_entry->data_dma_blob_desc.data = NULL;
@@ -1787,21 +1764,14 @@ void hl_debugfs_add_device(struct hl_device *hdev)
 	spin_lock_init(&dev_entry->userptr_spinlock);
 	mutex_init(&dev_entry->ctx_mem_hash_mutex);
 
-	dev_entry->root = debugfs_create_dir(dev_name(hdev->dev),
-						hl_debug_root);
-
-	add_files_to_device(hdev, dev_entry, dev_entry->root);
-	if (!hdev->asic_prop.fw_security_enabled)
-		add_secured_nodes(dev_entry, dev_entry->root);
+	return 0;
 }
 
-void hl_debugfs_remove_device(struct hl_device *hdev)
+void hl_debugfs_device_fini(struct hl_device *hdev)
 {
 	struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
 	int i;
 
-	debugfs_remove_recursive(entry->root);
-
 	mutex_destroy(&entry->ctx_mem_hash_mutex);
 	mutex_destroy(&entry->file_mutex);
 
@@ -1814,6 +1784,24 @@ void hl_debugfs_remove_device(struct hl_device *hdev)
 	kfree(entry->entry_arr);
 }
 
+void hl_debugfs_add_device(struct hl_device *hdev)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	dev_entry->root = debugfs_create_dir(dev_name(hdev->dev), hl_debug_root);
+
+	add_files_to_device(hdev, dev_entry, dev_entry->root);
+	if (!hdev->asic_prop.fw_security_enabled)
+		add_secured_nodes(dev_entry, dev_entry->root);
+}
+
+void hl_debugfs_remove_device(struct hl_device *hdev)
+{
+	struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
+
+	debugfs_remove_recursive(entry->root);
+}
+
 void hl_debugfs_add_file(struct hl_fpriv *hpriv)
 {
 	struct hl_dbg_device_entry *dev_entry = &hpriv->hdev->hl_debugfs;
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index fabfc501ef54..b97339d1f7c6 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -674,7 +674,7 @@ static int device_init_cdev(struct hl_device *hdev, struct class *class,
 	return 0;
 }
 
-static int device_cdev_sysfs_add(struct hl_device *hdev)
+static int cdev_sysfs_debugfs_add(struct hl_device *hdev)
 {
 	int rc;
 
@@ -699,7 +699,9 @@ static int device_cdev_sysfs_add(struct hl_device *hdev)
 		goto delete_ctrl_cdev_device;
 	}
 
-	hdev->cdev_sysfs_created = true;
+	hl_debugfs_add_device(hdev);
+
+	hdev->cdev_sysfs_debugfs_created = true;
 
 	return 0;
 
@@ -710,11 +712,12 @@ delete_cdev_device:
 	return rc;
 }
 
-static void device_cdev_sysfs_del(struct hl_device *hdev)
+static void cdev_sysfs_debugfs_remove(struct hl_device *hdev)
 {
-	if (!hdev->cdev_sysfs_created)
+	if (!hdev->cdev_sysfs_debugfs_created)
 		goto put_devices;
 
+	hl_debugfs_remove_device(hdev);
 	hl_sysfs_fini(hdev);
 	cdev_device_del(&hdev->cdev_ctrl, hdev->dev_ctrl);
 	cdev_device_del(&hdev->cdev, hdev->dev);
@@ -981,6 +984,18 @@ static void device_early_fini(struct hl_device *hdev)
 		hdev->asic_funcs->early_fini(hdev);
 }
 
+static bool is_pci_link_healthy(struct hl_device *hdev)
+{
+	u16 vendor_id;
+
+	if (!hdev->pdev)
+		return false;
+
+	pci_read_config_word(hdev->pdev, PCI_VENDOR_ID, &vendor_id);
+
+	return (vendor_id == PCI_VENDOR_ID_HABANALABS);
+}
+
 static void hl_device_heartbeat(struct work_struct *work)
 {
 	struct hl_device *hdev = container_of(work, struct hl_device,
@@ -995,7 +1010,8 @@ static void hl_device_heartbeat(struct work_struct *work)
 		goto reschedule;
 
 	if (hl_device_operational(hdev, NULL))
-		dev_err(hdev->dev, "Device heartbeat failed!\n");
+		dev_err(hdev->dev, "Device heartbeat failed! PCI link is %s\n",
+			is_pci_link_healthy(hdev) ? "healthy" : "broken");
 
 	info.err_type = HL_INFO_FW_HEARTBEAT_ERR;
 	info.event_mask = &event_mask;
@@ -1157,6 +1173,16 @@ static void take_release_locks(struct hl_device *hdev)
 	mutex_unlock(&hdev->fpriv_ctrl_list_lock);
 }
 
+static void hl_abort_waiting_for_completions(struct hl_device *hdev)
+{
+	hl_abort_waiting_for_cs_completions(hdev);
+
+	/* Release all pending user interrupts, each pending user interrupt
+	 * holds a reference to a user context.
+	 */
+	hl_release_pending_user_interrupts(hdev);
+}
+
 static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_reset,
 				bool skip_wq_flush)
 {
@@ -1176,10 +1202,7 @@ static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_r
 	/* flush the MMU prefetch workqueue */
 	flush_workqueue(hdev->prefetch_wq);
 
-	/* Release all pending user interrupts, each pending user interrupt
-	 * holds a reference to user context
-	 */
-	hl_release_pending_user_interrupts(hdev);
+	hl_abort_waiting_for_completions(hdev);
 }
 
 /*
@@ -1921,7 +1944,7 @@ out:
 
 	hl_ctx_put(ctx);
 
-	hl_abort_waitings_for_completion(hdev);
+	hl_abort_waiting_for_completions(hdev);
 
 	return 0;
 
@@ -2034,7 +2057,7 @@ out_err:
 int hl_device_init(struct hl_device *hdev)
 {
 	int i, rc, cq_cnt, user_interrupt_cnt, cq_ready_cnt;
-	bool add_cdev_sysfs_on_err = false;
+	bool expose_interfaces_on_err = false;
 
 	rc = create_cdev(hdev);
 	if (rc)
@@ -2150,16 +2173,22 @@ int hl_device_init(struct hl_device *hdev)
 	hdev->device_release_watchdog_timeout_sec = HL_DEVICE_RELEASE_WATCHDOG_TIMEOUT_SEC;
 
 	hdev->memory_scrub_val = MEM_SCRUB_DEFAULT_VAL;
-	hl_debugfs_add_device(hdev);
 
-	/* debugfs nodes are created in hl_ctx_init so it must be called after
-	 * hl_debugfs_add_device.
+	rc = hl_debugfs_device_init(hdev);
+	if (rc) {
+		dev_err(hdev->dev, "failed to initialize debugfs entry structure\n");
+		kfree(hdev->kernel_ctx);
+		goto mmu_fini;
+	}
+
+	/* The debugfs entry structure is accessed in hl_ctx_init(), so it must be called after
+	 * hl_debugfs_device_init().
 	 */
 	rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
 	if (rc) {
 		dev_err(hdev->dev, "failed to initialize kernel context\n");
 		kfree(hdev->kernel_ctx);
-		goto remove_device_from_debugfs;
+		goto debugfs_device_fini;
 	}
 
 	rc = hl_cb_pool_init(hdev);
@@ -2175,11 +2204,10 @@ int hl_device_init(struct hl_device *hdev)
 	}
 
 	/*
-	 * From this point, override rc (=0) in case of an error to allow
-	 * debugging (by adding char devices and create sysfs nodes as part of
-	 * the error flow).
+	 * From this point, override rc (=0) in case of an error to allow debugging
+	 * (by adding char devices and creating sysfs/debugfs files as part of the error flow).
 	 */
-	add_cdev_sysfs_on_err = true;
+	expose_interfaces_on_err = true;
 
 	/* Device is now enabled as part of the initialization requires
 	 * communication with the device firmware to get information that
@@ -2221,15 +2249,13 @@ int hl_device_init(struct hl_device *hdev)
 	}
 
 	/*
-	 * Expose devices and sysfs nodes to user.
-	 * From here there is no need to add char devices and create sysfs nodes
-	 * in case of an error.
+	 * Expose devices and sysfs/debugfs files to user.
+	 * From here there is no need to expose them in case of an error.
 	 */
-	add_cdev_sysfs_on_err = false;
-	rc = device_cdev_sysfs_add(hdev);
+	expose_interfaces_on_err = false;
+	rc = cdev_sysfs_debugfs_add(hdev);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to add char devices and sysfs nodes\n");
+		dev_err(hdev->dev, "Failed to add char devices and sysfs/debugfs files\n");
 		rc = 0;
 		goto out_disabled;
 	}
@@ -2275,8 +2301,8 @@ release_ctx:
 	if (hl_ctx_put(hdev->kernel_ctx) != 1)
 		dev_err(hdev->dev,
 			"kernel ctx is still alive on initialization failure\n");
-remove_device_from_debugfs:
-	hl_debugfs_remove_device(hdev);
+debugfs_device_fini:
+	hl_debugfs_device_fini(hdev);
 mmu_fini:
 	hl_mmu_fini(hdev);
 eq_fini:
@@ -2300,15 +2326,11 @@ free_dev:
 	put_device(hdev->dev);
 out_disabled:
 	hdev->disabled = true;
-	if (add_cdev_sysfs_on_err)
-		device_cdev_sysfs_add(hdev);
-	if (hdev->pdev)
-		dev_err(&hdev->pdev->dev,
-			"Failed to initialize hl%d. Device %s is NOT usable !\n",
-			hdev->cdev_idx, dev_name(&(hdev)->pdev->dev));
-	else
-		pr_err("Failed to initialize hl%d. Device %s is NOT usable !\n",
-			hdev->cdev_idx, dev_name(&(hdev)->pdev->dev));
+	if (expose_interfaces_on_err)
+		cdev_sysfs_debugfs_add(hdev);
+	dev_err(&hdev->pdev->dev,
+		"Failed to initialize hl%d. Device %s is NOT usable !\n",
+		hdev->cdev_idx, dev_name(&hdev->pdev->dev));
 
 	return rc;
 }
@@ -2427,8 +2449,6 @@ void hl_device_fini(struct hl_device *hdev)
 	if ((hdev->kernel_ctx) && (hl_ctx_put(hdev->kernel_ctx) != 1))
 		dev_err(hdev->dev, "kernel ctx is still alive\n");
 
-	hl_debugfs_remove_device(hdev);
-
 	hl_dec_fini(hdev);
 
 	hl_vm_fini(hdev);
@@ -2453,8 +2473,10 @@ void hl_device_fini(struct hl_device *hdev)
 
 	device_early_fini(hdev);
 
-	/* Hide devices and sysfs nodes from user */
-	device_cdev_sysfs_del(hdev);
+	/* Hide devices and sysfs/debugfs files from user */
+	cdev_sysfs_debugfs_remove(hdev);
+
+	hl_debugfs_device_fini(hdev);
 
 	pr_info("removed device successfully\n");
 }
@@ -2667,3 +2689,11 @@ void hl_handle_fw_err(struct hl_device *hdev, struct hl_info_fw_err_info *info)
 	if (info->event_mask)
 		*info->event_mask |= HL_NOTIFIER_EVENT_CRITICL_FW_ERR;
 }
+
+void hl_enable_err_info_capture(struct hl_error_info *captured_err_info)
+{
+	vfree(captured_err_info->page_fault_info.user_mappings);
+	memset(captured_err_info, 0, sizeof(struct hl_error_info));
+	atomic_set(&captured_err_info->cs_timeout.write_enable, 1);
+	captured_err_info->undef_opcode.write_enable = true;
+}
diff --git a/drivers/accel/habanalabs/common/firmware_if.c b/drivers/accel/habanalabs/common/firmware_if.c
index 59f61ec66445..acbc1a6b5cb1 100644
--- a/drivers/accel/habanalabs/common/firmware_if.c
+++ b/drivers/accel/habanalabs/common/firmware_if.c
@@ -71,38 +71,124 @@ free_fw_ver:
 	return NULL;
 }
 
-static int hl_get_preboot_major_minor(struct hl_device *hdev, char *preboot_ver)
+/**
+ * extract_u32_until_given_char() - given a string of the format "<u32><char>*", extract the u32.
+ * @str: the given string
+ * @ver_num: the pointer to the extracted u32 to be returned to the caller.
+ * @given_char: the given char at the end of the u32 in the string
+ *
+ * Return: Upon success, return a pointer to the given_char in the string. Upon failure, return NULL
+ */
+static char *extract_u32_until_given_char(char *str, u32 *ver_num, char given_char)
 {
-	char major[8], minor[8], *first_dot, *second_dot;
-	int rc;
+	char num_str[8] = {}, *ch;
 
-	first_dot = strnstr(preboot_ver, ".", 10);
-	if (first_dot) {
-		strscpy(major, preboot_ver, first_dot - preboot_ver + 1);
-		rc = kstrtou32(major, 10, &hdev->fw_major_version);
-	} else {
-		rc = -EINVAL;
+	ch = strchrnul(str, given_char);
+	if (*ch == '\0' || ch == str || ch - str >= sizeof(num_str))
+		return NULL;
+
+	memcpy(num_str, str, ch - str);
+	if (kstrtou32(num_str, 10, ver_num))
+		return NULL;
+	return ch;
+}
+
+/**
+ * hl_get_sw_major_minor_subminor() - extract the FW's SW version major, minor, sub-minor
+ *				      from the version string
+ * @hdev: pointer to the hl_device
+ * @fw_str: the FW's version string
+ *
+ * The extracted version is set in the hdev fields: fw_sw_{major/minor/sub_minor}_ver.
+ *
+ * fw_str is expected to have one of two possible formats, examples:
+ * 1) 'Preboot version hl-gaudi2-1.9.0-fw-42.0.1-sec-3'
+ * 2) 'Preboot version hl-gaudi2-1.9.0-rc-fw-42.0.1-sec-3'
+ * In those examples, the SW major,minor,subminor are correspondingly: 1,9,0.
+ *
+ * Return: 0 for success or a negative error code for failure.
+ */
+static int hl_get_sw_major_minor_subminor(struct hl_device *hdev, const char *fw_str)
+{
+	char *end, *start;
+
+	end = strnstr(fw_str, "-rc-", VERSION_MAX_LEN);
+	if (end == fw_str)
+		return -EINVAL;
+
+	if (!end)
+		end = strnstr(fw_str, "-fw-", VERSION_MAX_LEN);
+
+	if (end == fw_str)
+		return -EINVAL;
+
+	if (!end)
+		return -EINVAL;
+
+	for (start = end - 1; start != fw_str; start--) {
+		if (*start == '-')
+			break;
 	}
 
-	if (rc) {
-		dev_err(hdev->dev, "Error %d parsing preboot major version\n", rc);
-		return rc;
+	if (start == fw_str)
+		return -EINVAL;
+
+	/* start/end point each to the starting and ending hyphen of the sw version e.g. -1.9.0- */
+	start++;
+	start = extract_u32_until_given_char(start, &hdev->fw_sw_major_ver, '.');
+	if (!start)
+		goto err_zero_ver;
+
+	start++;
+	start = extract_u32_until_given_char(start, &hdev->fw_sw_minor_ver, '.');
+	if (!start)
+		goto err_zero_ver;
+
+	start++;
+	start = extract_u32_until_given_char(start, &hdev->fw_sw_sub_minor_ver, '-');
+	if (!start)
+		goto err_zero_ver;
+
+	return 0;
+
+err_zero_ver:
+	hdev->fw_sw_major_ver = 0;
+	hdev->fw_sw_minor_ver = 0;
+	hdev->fw_sw_sub_minor_ver = 0;
+	return -EINVAL;
+}
+
+/**
+ * hl_get_preboot_major_minor() - extract the FW's version major, minor from the version string.
+ * @hdev: pointer to the hl_device
+ * @preboot_ver: the FW's version string
+ *
+ * preboot_ver is expected to be the format of <major>.<minor>.<sub minor>*, e.g: 42.0.1-sec-3
+ * The extracted version is set in the hdev fields: fw_inner_{major/minor}_ver.
+ *
+ * Return: 0 on success, negative error code for failure.
+ */
+static int hl_get_preboot_major_minor(struct hl_device *hdev, char *preboot_ver)
+{
+	preboot_ver = extract_u32_until_given_char(preboot_ver, &hdev->fw_inner_major_ver, '.');
+	if (!preboot_ver) {
+		dev_err(hdev->dev, "Error parsing preboot major version\n");
+		goto err_zero_ver;
 	}
 
-	/* skip the first dot */
-	first_dot++;
+	preboot_ver++;
 
-	second_dot = strnstr(first_dot, ".", 10);
-	if (second_dot) {
-		strscpy(minor, first_dot, second_dot - first_dot + 1);
-		rc = kstrtou32(minor, 10, &hdev->fw_minor_version);
-	} else {
-		rc = -EINVAL;
+	preboot_ver = extract_u32_until_given_char(preboot_ver, &hdev->fw_inner_minor_ver, '.');
+	if (!preboot_ver) {
+		dev_err(hdev->dev, "Error parsing preboot minor version\n");
+		goto err_zero_ver;
 	}
+	return 0;
 
-	if (rc)
-		dev_err(hdev->dev, "Error %d parsing preboot minor version\n", rc);
-	return rc;
+err_zero_ver:
+	hdev->fw_inner_major_ver = 0;
+	hdev->fw_inner_minor_ver = 0;
+	return -EINVAL;
 }
 
 static int hl_request_fw(struct hl_device *hdev,
@@ -505,6 +591,20 @@ void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size,
 			size);
 }
 
+int hl_fw_send_soft_reset(struct hl_device *hdev)
+{
+	struct cpucp_packet pkt;
+	int rc;
+
+	memset(&pkt, 0, sizeof(pkt));
+	pkt.ctl = cpu_to_le32(CPUCP_PACKET_SOFT_RESET << CPUCP_PKT_CTL_OPCODE_SHIFT);
+	rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), 0, NULL);
+	if (rc)
+		dev_err(hdev->dev, "failed to send soft-reset msg (err = %d)\n", rc);
+
+	return rc;
+}
+
 int hl_fw_send_device_activity(struct hl_device *hdev, bool open)
 {
 	struct cpucp_packet pkt;
@@ -1268,8 +1368,10 @@ void hl_fw_ask_hard_reset_without_linux(struct hl_device *hdev)
 
 void hl_fw_ask_halt_machine_without_linux(struct hl_device *hdev)
 {
-	struct static_fw_load_mgr *static_loader =
-			&hdev->fw_loader.static_loader;
+	struct fw_load_mgr *fw_loader = &hdev->fw_loader;
+	u32 status, cpu_boot_status_reg, cpu_timeout;
+	struct static_fw_load_mgr *static_loader;
+	struct pre_fw_load_props *pre_fw_load;
 	int rc;
 
 	if (hdev->device_cpu_is_halted)
@@ -1277,12 +1379,28 @@ void hl_fw_ask_halt_machine_without_linux(struct hl_device *hdev)
 
 	/* Stop device CPU to make sure nothing bad happens */
 	if (hdev->asic_prop.dynamic_fw_load) {
+		pre_fw_load = &fw_loader->pre_fw_load;
+		cpu_timeout = fw_loader->cpu_timeout;
+		cpu_boot_status_reg = pre_fw_load->cpu_boot_status_reg;
+
 		rc = hl_fw_dynamic_send_protocol_cmd(hdev, &hdev->fw_loader,
-				COMMS_GOTO_WFE, 0, false,
-				hdev->fw_loader.cpu_timeout);
-		if (rc)
+				COMMS_GOTO_WFE, 0, false, cpu_timeout);
+		if (rc) {
 			dev_err(hdev->dev, "Failed sending COMMS_GOTO_WFE\n");
+		} else {
+			rc = hl_poll_timeout(
+				hdev,
+				cpu_boot_status_reg,
+				status,
+				status == CPU_BOOT_STATUS_IN_WFE,
+				hdev->fw_poll_interval_usec,
+				cpu_timeout);
+			if (rc)
+				dev_err(hdev->dev, "Current status=%u. Timed-out updating to WFE\n",
+						status);
+		}
 	} else {
+		static_loader = &hdev->fw_loader.static_loader;
 		WREG32(static_loader->kmd_msg_to_cpu_reg, KMD_MSG_GOTO_WFE);
 		msleep(static_loader->cpu_reset_wait_msec);
 
@@ -2151,6 +2269,7 @@ static int hl_fw_dynamic_read_device_fw_version(struct hl_device *hdev,
 	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	char *preboot_ver, *boot_ver;
 	char btl_ver[32];
+	int rc;
 
 	switch (fwc) {
 	case FW_COMP_BOOT_FIT:
@@ -2164,20 +2283,20 @@ static int hl_fw_dynamic_read_device_fw_version(struct hl_device *hdev,
 		break;
 	case FW_COMP_PREBOOT:
 		strscpy(prop->preboot_ver, fw_version, VERSION_MAX_LEN);
-		preboot_ver = strnstr(prop->preboot_ver, "Preboot",
-						VERSION_MAX_LEN);
+		preboot_ver = strnstr(prop->preboot_ver, "Preboot", VERSION_MAX_LEN);
+		dev_info(hdev->dev, "preboot full version: '%s'\n", preboot_ver);
+
 		if (preboot_ver && preboot_ver != prop->preboot_ver) {
 			strscpy(btl_ver, prop->preboot_ver,
 				min((int) (preboot_ver - prop->preboot_ver), 31));
 			dev_info(hdev->dev, "%s\n", btl_ver);
 		}
 
+		rc = hl_get_sw_major_minor_subminor(hdev, preboot_ver);
+		if (rc)
+			return rc;
 		preboot_ver = extract_fw_ver_from_str(prop->preboot_ver);
 		if (preboot_ver) {
-			int rc;
-
-			dev_info(hdev->dev, "preboot version %s\n", preboot_ver);
-
 			rc = hl_get_preboot_major_minor(hdev, preboot_ver);
 			kfree(preboot_ver);
 			if (rc)
@@ -2367,16 +2486,6 @@ static int hl_fw_dynamic_load_image(struct hl_device *hdev,
 	if (rc)
 		goto release_fw;
 
-	/* update state according to boot stage */
-	if (cur_fwc == FW_COMP_BOOT_FIT) {
-		struct cpu_dyn_regs *dyn_regs;
-
-		dyn_regs = &fw_loader->dynamic_loader.comm_desc.cpu_dyn_regs;
-		hl_fw_boot_fit_update_state(hdev,
-				le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
-				le32_to_cpu(dyn_regs->cpu_boot_dev_sts1));
-	}
-
 	/* copy boot fit to space allocated by FW */
 	rc = hl_fw_dynamic_copy_image(hdev, fw, fw_loader);
 	if (rc)
@@ -2679,6 +2788,14 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 		goto protocol_err;
 	}
 
+	rc = hl_fw_dynamic_wait_for_boot_fit_active(hdev, fw_loader);
+	if (rc)
+		goto protocol_err;
+
+	hl_fw_boot_fit_update_state(hdev,
+			le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
+			le32_to_cpu(dyn_regs->cpu_boot_dev_sts1));
+
 	/*
 	 * when testing FW load (without Linux) on PLDM we don't want to
 	 * wait until boot fit is active as it may take several hours.
@@ -2688,10 +2805,6 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 	if (hdev->pldm && !(hdev->fw_components & FW_TYPE_LINUX))
 		return 0;
 
-	rc = hl_fw_dynamic_wait_for_boot_fit_active(hdev, fw_loader);
-	if (rc)
-		goto protocol_err;
-
 	/* Enable DRAM scrambling before Linux boot and after successful
 	 *  UBoot
 	 */
@@ -2725,7 +2838,8 @@ static int hl_fw_dynamic_init_cpu(struct hl_device *hdev,
 	if (rc)
 		goto protocol_err;
 
-	hl_fw_linux_update_state(hdev, le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
+	hl_fw_linux_update_state(hdev,
+				le32_to_cpu(dyn_regs->cpu_boot_dev_sts0),
 				le32_to_cpu(dyn_regs->cpu_boot_dev_sts1));
 
 	hl_fw_dynamic_update_linux_interrupt_if(hdev);
diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index eaae69a9f817..d92ba2e30e31 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -36,6 +36,8 @@
 struct hl_device;
 struct hl_fpriv;
 
+#define PCI_VENDOR_ID_HABANALABS	0x1da3
+
 /* Use upper bits of mmap offset to store habana driver specific information.
  * bits[63:59] - Encode mmap type
  * bits[45:0]  - mmap offset value
@@ -113,18 +115,6 @@ enum hl_mmu_page_table_location {
 	MMU_NUM_PGT_LOCATIONS	/* num of PGT locations */
 };
 
-/**
- * enum hl_mmu_enablement - what mmu modules to enable
- * @MMU_EN_NONE: mmu disabled.
- * @MMU_EN_ALL: enable all.
- * @MMU_EN_PMMU_ONLY: Enable only the PMMU leaving the DMMU disabled.
- */
-enum hl_mmu_enablement {
-	MMU_EN_NONE = 0,
-	MMU_EN_ALL = 1,
-	MMU_EN_PMMU_ONLY = 3,	/* N/A for Goya/Gaudi */
-};
-
 /*
  * HL_RSVD_SOBS 'sync stream' reserved sync objects per QMAN stream
  * HL_RSVD_MONS 'sync stream' reserved monitors per QMAN stream
@@ -2568,12 +2558,7 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 	ktime_t __timeout; \
 	u32 __elbi_read; \
 	int __rc = 0; \
-	if (hdev->pdev) \
-		__timeout = ktime_add_us(ktime_get(), timeout_us); \
-	else \
-		__timeout = ktime_add_us(ktime_get(),\
-				min((u64)(timeout_us * 10), \
-					(u64) HL_SIM_MAX_TIMEOUT_US)); \
+	__timeout = ktime_add_us(ktime_get(), timeout_us); \
 	might_sleep_if(sleep_us); \
 	for (;;) { \
 		if (elbi) { \
@@ -2625,13 +2610,7 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 	u8 __arr_idx;	\
 	int __rc = 0; \
 	\
-	if (hdev->pdev) \
-		__timeout = ktime_add_us(ktime_get(), timeout_us); \
-	else \
-		__timeout = ktime_add_us(ktime_get(),\
-				min(((u64)timeout_us * 10), \
-					(u64) HL_SIM_MAX_TIMEOUT_US)); \
-	\
+	__timeout = ktime_add_us(ktime_get(), timeout_us); \
 	might_sleep_if(sleep_us); \
 	if (arr_size >= 64) \
 		__rc = -EINVAL; \
@@ -2689,12 +2668,8 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val);
 				mem_written_by_device) \
 ({ \
 	ktime_t __timeout; \
-	if (hdev->pdev) \
-		__timeout = ktime_add_us(ktime_get(), timeout_us); \
-	else \
-		__timeout = ktime_add_us(ktime_get(),\
-				min((u64)(timeout_us * 100), \
-					(u64) HL_SIM_MAX_TIMEOUT_US)); \
+	\
+	__timeout = ktime_add_us(ktime_get(), timeout_us); \
 	might_sleep_if(sleep_us); \
 	for (;;) { \
 		/* Verify we read updates done by other cores or by device */ \
@@ -3225,8 +3200,11 @@ struct hl_reset_info {
  * @captured_err_info: holds information about errors.
  * @reset_info: holds current device reset information.
  * @stream_master_qid_arr: pointer to array with QIDs of master streams.
- * @fw_major_version: major version of current loaded preboot.
- * @fw_minor_version: minor version of current loaded preboot.
+ * @fw_inner_major_ver: the major of current loaded preboot inner version.
+ * @fw_inner_minor_ver: the minor of current loaded preboot inner version.
+ * @fw_sw_major_ver: the major of current loaded preboot SW version.
+ * @fw_sw_minor_ver: the minor of current loaded preboot SW version.
+ * @fw_sw_sub_minor_ver: the sub-minor of current loaded preboot SW version.
  * @dram_used_mem: current DRAM memory consumption.
  * @memory_scrub_val: the value to which the dram will be scrubbed to using cb scrub_device_dram
  * @timeout_jiffies: device CS timeout value.
@@ -3287,7 +3265,7 @@ struct hl_reset_info {
  * @in_debug: whether the device is in a state where the profiling/tracing infrastructure
  *            can be used. This indication is needed because in some ASICs we need to do
  *            specific operations to enable that infrastructure.
- * @cdev_sysfs_created: were char devices and sysfs nodes created.
+ * @cdev_sysfs_debugfs_created: were char devices and sysfs/debugfs files created.
  * @stop_on_err: true if engines should stop on error.
  * @supports_sync_stream: is sync stream supported.
  * @sync_stream_queue_idx: helper index for sync stream queues initialization.
@@ -3314,7 +3292,7 @@ struct hl_reset_info {
  * @nic_ports_mask: Controls which NIC ports are enabled. Used only for testing.
  * @fw_components: Controls which f/w components to load to the device. There are multiple f/w
  *                 stages and sometimes we want to stop at a certain stage. Used only for testing.
- * @mmu_enable: Whether to enable or disable the device MMU(s). Used only for testing.
+ * @mmu_disable: Disable the device MMU(s). Used only for testing.
  * @cpu_queues_enable: Whether to enable queues communication vs. the f/w. Used only for testing.
  * @pldm: Whether we are running in Palladium environment. Used only for testing.
  * @hard_reset_on_fw_events: Whether to do device hard-reset when a fatal event is received from
@@ -3412,8 +3390,11 @@ struct hl_device {
 	struct hl_reset_info		reset_info;
 
 	u32				*stream_master_qid_arr;
-	u32				fw_major_version;
-	u32				fw_minor_version;
+	u32				fw_inner_major_ver;
+	u32				fw_inner_minor_ver;
+	u32				fw_sw_major_ver;
+	u32				fw_sw_minor_ver;
+	u32				fw_sw_sub_minor_ver;
 	atomic64_t			dram_used_mem;
 	u64				memory_scrub_val;
 	u64				timeout_jiffies;
@@ -3451,7 +3432,7 @@ struct hl_device {
 	u8				init_done;
 	u8				device_cpu_disabled;
 	u8				in_debug;
-	u8				cdev_sysfs_created;
+	u8				cdev_sysfs_debugfs_created;
 	u8				stop_on_err;
 	u8				supports_sync_stream;
 	u8				sync_stream_queue_idx;
@@ -3474,7 +3455,7 @@ struct hl_device {
 	/* Parameters for bring-up to be upstreamed */
 	u64				nic_ports_mask;
 	u64				fw_components;
-	u8				mmu_enable;
+	u8				mmu_disable;
 	u8				cpu_queues_enable;
 	u8				pldm;
 	u8				hard_reset_on_fw_events;
@@ -3547,9 +3528,15 @@ struct hl_ioctl_desc {
 	hl_ioctl_t *func;
 };
 
-static inline bool hl_is_fw_ver_below_1_9(struct hl_device *hdev)
+static inline bool hl_is_fw_sw_ver_below(struct hl_device *hdev, u32 fw_sw_major, u32 fw_sw_minor)
 {
-	return (hdev->fw_major_version < 42);
+	if (hdev->fw_sw_major_ver < fw_sw_major)
+		return true;
+	if (hdev->fw_sw_major_ver > fw_sw_major)
+		return false;
+	if (hdev->fw_sw_minor_ver < fw_sw_minor)
+		return true;
+	return false;
 }
 
 /*
@@ -3813,8 +3800,6 @@ struct pgt_info *hl_mmu_hr_get_alloc_next_hop(struct hl_ctx *ctx,
 							u64 curr_pte, bool *is_new_hop);
 int hl_mmu_hr_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr, struct hl_mmu_hop_info *hops,
 							struct hl_hr_mmu_funcs *hr_func);
-void hl_mmu_swap_out(struct hl_ctx *ctx);
-void hl_mmu_swap_in(struct hl_ctx *ctx);
 int hl_mmu_if_set_funcs(struct hl_device *hdev);
 void hl_mmu_v1_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu);
 void hl_mmu_v2_hr_set_funcs(struct hl_device *hdev, struct hl_mmu_funcs *mmu);
@@ -3872,6 +3857,7 @@ int hl_fw_dram_replaced_row_get(struct hl_device *hdev,
 int hl_fw_dram_pending_row_get(struct hl_device *hdev, u32 *pend_rows_num);
 int hl_fw_cpucp_engine_core_asid_set(struct hl_device *hdev, u32 asid);
 int hl_fw_send_device_activity(struct hl_device *hdev, bool open);
+int hl_fw_send_soft_reset(struct hl_device *hdev);
 int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3],
 			bool is_wc[3]);
 int hl_pci_elbi_read(struct hl_device *hdev, u64 addr, u32 *data);
@@ -3921,7 +3907,7 @@ void hl_dec_fini(struct hl_device *hdev);
 void hl_dec_ctx_fini(struct hl_ctx *ctx);
 
 void hl_release_pending_user_interrupts(struct hl_device *hdev);
-void hl_abort_waitings_for_completion(struct hl_device *hdev);
+void hl_abort_waiting_for_cs_completions(struct hl_device *hdev);
 int hl_cs_signal_sob_wraparound_handler(struct hl_device *hdev, u32 q_idx,
 			struct hl_hw_sob **hw_sob, u32 count, bool encaps_sig);
 
@@ -3958,11 +3944,14 @@ void hl_handle_page_fault(struct hl_device *hdev, u64 addr, u16 eng_id, bool is_
 				u64 *event_mask);
 void hl_handle_critical_hw_err(struct hl_device *hdev, u16 event_id, u64 *event_mask);
 void hl_handle_fw_err(struct hl_device *hdev, struct hl_info_fw_err_info *info);
+void hl_enable_err_info_capture(struct hl_error_info *captured_err_info);
 
 #ifdef CONFIG_DEBUG_FS
 
 void hl_debugfs_init(void);
 void hl_debugfs_fini(void);
+int hl_debugfs_device_init(struct hl_device *hdev);
+void hl_debugfs_device_fini(struct hl_device *hdev);
 void hl_debugfs_add_device(struct hl_device *hdev);
 void hl_debugfs_remove_device(struct hl_device *hdev);
 void hl_debugfs_add_file(struct hl_fpriv *hpriv);
diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index d9df64e75f33..7263e84c1a4d 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -13,6 +13,7 @@
 
 #include <linux/pci.h>
 #include <linux/module.h>
+#include <linux/vmalloc.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/habanalabs.h>
@@ -54,8 +55,6 @@ module_param(boot_error_status_mask, ulong, 0444);
 MODULE_PARM_DESC(boot_error_status_mask,
 	"Mask of the error status during device CPU boot (If bitX is cleared then error X is masked. Default all 1's)");
 
-#define PCI_VENDOR_ID_HABANALABS	0x1da3
-
 #define PCI_IDS_GOYA			0x0001
 #define PCI_IDS_GAUDI			0x1000
 #define PCI_IDS_GAUDI_SEC		0x1010
@@ -220,9 +219,7 @@ int hl_device_open(struct inode *inode, struct file *filp)
 
 	hl_debugfs_add_file(hpriv);
 
-	memset(&hdev->captured_err_info, 0, sizeof(hdev->captured_err_info));
-	atomic_set(&hdev->captured_err_info.cs_timeout.write_enable, 1);
-	hdev->captured_err_info.undef_opcode.write_enable = true;
+	hl_enable_err_info_capture(&hdev->captured_err_info);
 
 	hdev->open_counter++;
 	hdev->last_successful_open_jif = jiffies;
@@ -307,7 +304,6 @@ static void set_driver_behavior_per_device(struct hl_device *hdev)
 {
 	hdev->nic_ports_mask = 0;
 	hdev->fw_components = FW_TYPE_ALL_TYPES;
-	hdev->mmu_enable = MMU_EN_ALL;
 	hdev->cpu_queues_enable = 1;
 	hdev->pldm = 0;
 	hdev->hard_reset_on_fw_events = 1;
@@ -382,7 +378,6 @@ static int fixup_device_params(struct hl_device *hdev)
 	/* If CPU queues not enabled, no way to do heartbeat */
 	if (!hdev->cpu_queues_enable)
 		hdev->heartbeat = 0;
-
 	fixup_device_params_per_asic(hdev, tmp_timeout);
 
 	return 0;
diff --git a/drivers/accel/habanalabs/common/habanalabs_ioctl.c b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
index 203ee857810c..6a45a92344e9 100644
--- a/drivers/accel/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/accel/habanalabs/common/habanalabs_ioctl.c
@@ -62,7 +62,7 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
 	hw_ip.device_id = hdev->asic_funcs->get_pci_id(hdev);
 	hw_ip.sram_base_address = prop->sram_user_base_address;
 	hw_ip.dram_base_address =
-			hdev->mmu_enable && prop->dram_supports_virtual_memory ?
+			prop->dram_supports_virtual_memory ?
 			prop->dmmu.start_addr : prop->dram_user_base_address;
 	hw_ip.tpc_enabled_mask = prop->tpc_enabled_mask & 0xFF;
 	hw_ip.tpc_enabled_mask_ext = prop->tpc_enabled_mask;
@@ -71,11 +71,8 @@ static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args)
 
 	dram_available_size = prop->dram_size - dram_kmd_size;
 
-	if (hdev->mmu_enable == MMU_EN_ALL)
-		hw_ip.dram_size = DIV_ROUND_DOWN_ULL(dram_available_size,
-				prop->dram_page_size) * prop->dram_page_size;
-	else
-		hw_ip.dram_size = dram_available_size;
+	hw_ip.dram_size = DIV_ROUND_DOWN_ULL(dram_available_size, prop->dram_page_size) *
+				prop->dram_page_size;
 
 	if (hw_ip.dram_size > PAGE_SIZE)
 		hw_ip.dram_enabled = 1;
@@ -842,15 +839,15 @@ static int hw_err_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 	struct hw_err_info *info;
 	int rc;
 
-	if ((!user_buf_size) || (!user_buf))
+	if (!user_buf)
 		return -EINVAL;
 
-	if (user_buf_size < sizeof(struct hl_info_hw_err_event))
-		return -ENOMEM;
-
 	info = &hdev->captured_err_info.hw_err;
 	if (!info->event_info_available)
-		return -ENOENT;
+		return 0;
+
+	if (user_buf_size < sizeof(struct hl_info_hw_err_event))
+		return -ENOMEM;
 
 	rc = copy_to_user(user_buf, &info->event, sizeof(struct hl_info_hw_err_event));
 	return rc ? -EFAULT : 0;
@@ -864,15 +861,15 @@ static int fw_err_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 	struct fw_err_info *info;
 	int rc;
 
-	if ((!user_buf_size) || (!user_buf))
+	if (!user_buf)
 		return -EINVAL;
 
-	if (user_buf_size < sizeof(struct hl_info_fw_err_event))
-		return -ENOMEM;
-
 	info = &hdev->captured_err_info.fw_err;
 	if (!info->event_info_available)
-		return -ENOENT;
+		return 0;
+
+	if (user_buf_size < sizeof(struct hl_info_fw_err_event))
+		return -ENOMEM;
 
 	rc = copy_to_user(user_buf, &info->event, sizeof(struct hl_info_fw_err_event));
 	return rc ? -EFAULT : 0;
@@ -1198,7 +1195,7 @@ static long _hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg,
 
 out_err:
 	if (retcode)
-		dev_dbg(dev, "error in ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
+		dev_dbg_ratelimited(dev, "error in ioctl: pid=%d, cmd=0x%02x, nr=0x%02x\n",
 			  task_pid_nr(current), cmd, nr);
 
 	if (kdata != stack_kdata)
@@ -1222,7 +1219,7 @@ long hl_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) {
 		ioctl = &hl_ioctls[nr];
 	} else {
-		dev_err(hdev->dev, "invalid ioctl: pid=%d, nr=0x%02x\n",
+		dev_dbg_ratelimited(hdev->dev, "invalid ioctl: pid=%d, nr=0x%02x\n",
 			task_pid_nr(current), nr);
 		return -ENOTTY;
 	}
@@ -1245,7 +1242,7 @@ long hl_ioctl_control(struct file *filep, unsigned int cmd, unsigned long arg)
 	if (nr == _IOC_NR(HL_IOCTL_INFO)) {
 		ioctl = &hl_ioctls_control[nr];
 	} else {
-		dev_err(hdev->dev_ctrl, "invalid ioctl: pid=%d, nr=0x%02x\n",
+		dev_dbg_ratelimited(hdev->dev_ctrl, "invalid ioctl: pid=%d, nr=0x%02x\n",
 			task_pid_nr(current), nr);
 		return -ENOTTY;
 	}
diff --git a/drivers/accel/habanalabs/common/irq.c b/drivers/accel/habanalabs/common/irq.c
index c67895b1cdeb..b1010d206c2e 100644
--- a/drivers/accel/habanalabs/common/irq.c
+++ b/drivers/accel/habanalabs/common/irq.c
@@ -430,7 +430,7 @@ irqreturn_t hl_irq_handler_eq(int irq, void *arg)
 		cur_eqe_index = FIELD_GET(EQ_CTL_INDEX_MASK, cur_eqe);
 		if ((hdev->event_queue.check_eqe_index) &&
 				(((eq->prev_eqe_index + 1) & EQ_CTL_INDEX_MASK) != cur_eqe_index)) {
-			dev_dbg(hdev->dev,
+			dev_err(hdev->dev,
 				"EQE %#x in queue is ready but index does not match %d!=%d",
 				cur_eqe,
 				((eq->prev_eqe_index + 1) & EQ_CTL_INDEX_MASK),
diff --git a/drivers/accel/habanalabs/common/memory.c b/drivers/accel/habanalabs/common/memory.c
index a7b6a273ce21..4fc72a07d2f5 100644
--- a/drivers/accel/habanalabs/common/memory.c
+++ b/drivers/accel/habanalabs/common/memory.c
@@ -1034,30 +1034,6 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
 	}
 }
 
-static int get_paddr_from_handle(struct hl_ctx *ctx, struct hl_mem_in *args,
-					u64 *paddr)
-{
-	struct hl_device *hdev = ctx->hdev;
-	struct hl_vm *vm = &hdev->vm;
-	struct hl_vm_phys_pg_pack *phys_pg_pack;
-	u32 handle;
-
-	handle = lower_32_bits(args->map_device.handle);
-	spin_lock(&vm->idr_lock);
-	phys_pg_pack = idr_find(&vm->phys_pg_pack_handles, handle);
-	if (!phys_pg_pack) {
-		spin_unlock(&vm->idr_lock);
-		dev_err(hdev->dev, "no match for handle %u\n", handle);
-		return -EINVAL;
-	}
-
-	*paddr = phys_pg_pack->pages[0];
-
-	spin_unlock(&vm->idr_lock);
-
-	return 0;
-}
-
 /**
  * map_device_va() - map the given memory.
  * @ctx: pointer to the context structure.
@@ -2094,76 +2070,6 @@ err_free_dmabuf_wrapper:
 	return rc;
 }
 
-static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args)
-{
-	struct hl_device *hdev = hpriv->hdev;
-	u64 block_handle, device_addr = 0;
-	struct hl_ctx *ctx = hpriv->ctx;
-	u32 handle = 0, block_size;
-	int rc;
-
-	switch (args->in.op) {
-	case HL_MEM_OP_ALLOC:
-		if (args->in.alloc.mem_size == 0) {
-			dev_err(hdev->dev, "alloc size must be larger than 0\n");
-			rc = -EINVAL;
-			goto out;
-		}
-
-		/* Force contiguous as there are no real MMU
-		 * translations to overcome physical memory gaps
-		 */
-		args->in.flags |= HL_MEM_CONTIGUOUS;
-		rc = alloc_device_memory(ctx, &args->in, &handle);
-
-		memset(args, 0, sizeof(*args));
-		args->out.handle = (__u64) handle;
-		break;
-
-	case HL_MEM_OP_FREE:
-		rc = free_device_memory(ctx, &args->in);
-		break;
-
-	case HL_MEM_OP_MAP:
-		if (args->in.flags & HL_MEM_USERPTR) {
-			dev_err(hdev->dev, "Failed to map host memory when MMU is disabled\n");
-			rc = -EPERM;
-		} else {
-			rc = get_paddr_from_handle(ctx, &args->in, &device_addr);
-			memset(args, 0, sizeof(*args));
-			args->out.device_virt_addr = device_addr;
-		}
-
-		break;
-
-	case HL_MEM_OP_UNMAP:
-		rc = 0;
-		break;
-
-	case HL_MEM_OP_MAP_BLOCK:
-		rc = map_block(hdev, args->in.map_block.block_addr, &block_handle, &block_size);
-		args->out.block_handle = block_handle;
-		args->out.block_size = block_size;
-		break;
-
-	case HL_MEM_OP_EXPORT_DMABUF_FD:
-		dev_err(hdev->dev, "Failed to export dma-buf object when MMU is disabled\n");
-		rc = -EPERM;
-		break;
-
-	case HL_MEM_OP_TS_ALLOC:
-		rc = allocate_timestamps_buffers(hpriv, &args->in, &args->out.handle);
-		break;
-	default:
-		dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n");
-		rc = -EINVAL;
-		break;
-	}
-
-out:
-	return rc;
-}
-
 static void ts_buff_release(struct hl_mmap_mem_buf *buf)
 {
 	struct hl_ts_buff *ts_buff = buf->private;
@@ -2282,9 +2188,6 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data)
 		return -EBUSY;
 	}
 
-	if (!hdev->mmu_enable)
-		return mem_ioctl_no_mmu(hpriv, args);
-
 	switch (args->in.op) {
 	case HL_MEM_OP_ALLOC:
 		if (args->in.alloc.mem_size == 0) {
@@ -2779,13 +2682,10 @@ int hl_vm_ctx_init(struct hl_ctx *ctx)
 	atomic64_set(&ctx->dram_phys_mem, 0);
 
 	/*
-	 * - If MMU is enabled, init the ranges as usual.
-	 * - If MMU is disabled, in case of host mapping, the returned address
-	 *   is the given one.
 	 *   In case of DRAM mapping, the returned address is the physical
 	 *   address of the memory related to the given handle.
 	 */
-	if (!ctx->hdev->mmu_enable)
+	if (ctx->hdev->mmu_disable)
 		return 0;
 
 	dram_range_start = prop->dmmu.start_addr;
@@ -2835,7 +2735,7 @@ void hl_vm_ctx_fini(struct hl_ctx *ctx)
 	struct hl_mem_in args;
 	int i;
 
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return;
 
 	hl_debugfs_remove_ctx_mem_hash(hdev, ctx);
diff --git a/drivers/accel/habanalabs/common/mmu/mmu.c b/drivers/accel/habanalabs/common/mmu/mmu.c
index f379e5b461a6..b2145716c605 100644
--- a/drivers/accel/habanalabs/common/mmu/mmu.c
+++ b/drivers/accel/habanalabs/common/mmu/mmu.c
@@ -44,7 +44,7 @@ int hl_mmu_init(struct hl_device *hdev)
 {
 	int rc = -EOPNOTSUPP;
 
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return 0;
 
 	mutex_init(&hdev->mmu_lock);
@@ -82,7 +82,7 @@ fini_dr_mmu:
  */
 void hl_mmu_fini(struct hl_device *hdev)
 {
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return;
 
 	if (hdev->mmu_func[MMU_DR_PGT].fini != NULL)
@@ -107,7 +107,7 @@ int hl_mmu_ctx_init(struct hl_ctx *ctx)
 	struct hl_device *hdev = ctx->hdev;
 	int rc = -EOPNOTSUPP;
 
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return 0;
 
 	if (hdev->mmu_func[MMU_DR_PGT].ctx_init != NULL) {
@@ -145,7 +145,7 @@ void hl_mmu_ctx_fini(struct hl_ctx *ctx)
 {
 	struct hl_device *hdev = ctx->hdev;
 
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return;
 
 	if (hdev->mmu_func[MMU_DR_PGT].ctx_fini != NULL)
@@ -233,7 +233,7 @@ int hl_mmu_unmap_page(struct hl_ctx *ctx, u64 virt_addr, u32 page_size, bool flu
 	u64 real_virt_addr;
 	bool is_dram_addr;
 
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return 0;
 
 	is_dram_addr = hl_is_dram_va(hdev, virt_addr);
@@ -301,7 +301,7 @@ int hl_mmu_map_page(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_s
 	bool is_dram_addr;
 
 
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return 0;
 
 	is_dram_addr = hl_is_dram_va(hdev, virt_addr);
@@ -472,46 +472,6 @@ int hl_mmu_unmap_contiguous(struct hl_ctx *ctx, u64 virt_addr, u32 size)
 	return rc;
 }
 
-/*
- * hl_mmu_swap_out - marks all mapping of the given ctx as swapped out
- *
- * @ctx: pointer to the context structure
- *
- */
-void hl_mmu_swap_out(struct hl_ctx *ctx)
-{
-	struct hl_device *hdev = ctx->hdev;
-
-	if (!hdev->mmu_enable)
-		return;
-
-	if (hdev->mmu_func[MMU_DR_PGT].swap_out != NULL)
-		hdev->mmu_func[MMU_DR_PGT].swap_out(ctx);
-
-	if (hdev->mmu_func[MMU_HR_PGT].swap_out != NULL)
-		hdev->mmu_func[MMU_HR_PGT].swap_out(ctx);
-}
-
-/*
- * hl_mmu_swap_in - marks all mapping of the given ctx as swapped in
- *
- * @ctx: pointer to the context structure
- *
- */
-void hl_mmu_swap_in(struct hl_ctx *ctx)
-{
-	struct hl_device *hdev = ctx->hdev;
-
-	if (!hdev->mmu_enable)
-		return;
-
-	if (hdev->mmu_func[MMU_DR_PGT].swap_in != NULL)
-		hdev->mmu_func[MMU_DR_PGT].swap_in(ctx);
-
-	if (hdev->mmu_func[MMU_HR_PGT].swap_in != NULL)
-		hdev->mmu_func[MMU_HR_PGT].swap_in(ctx);
-}
-
 static void hl_mmu_pa_page_with_offset(struct hl_ctx *ctx, u64 virt_addr,
 						struct hl_mmu_hop_info *hops,
 						u64 *phys_addr)
@@ -594,7 +554,7 @@ int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 	int pgt_residency, rc;
 	bool is_dram_addr;
 
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return -EOPNOTSUPP;
 
 	prop = &hdev->asic_prop;
@@ -625,7 +585,7 @@ int hl_mmu_get_tlb_info(struct hl_ctx *ctx, u64 virt_addr,
 
 int hl_mmu_if_set_funcs(struct hl_device *hdev)
 {
-	if (!hdev->mmu_enable)
+	if (hdev->mmu_disable)
 		return 0;
 
 	switch (hdev->asic_type) {
diff --git a/drivers/accel/habanalabs/common/security.c b/drivers/accel/habanalabs/common/security.c
index 297e6e44fd0c..fe913965dbad 100644
--- a/drivers/accel/habanalabs/common/security.c
+++ b/drivers/accel/habanalabs/common/security.c
@@ -284,14 +284,14 @@ void hl_secure_block(struct hl_device *hdev,
  * @instance_offset: offset between instances
  * @pb_blocks: blocks array
  * @blocks_array_size: blocks array size
- * @regs_array: register array
- * @regs_array_size: register array size
+ * @user_regs_array: unsecured register array
+ * @user_regs_array_size: unsecured register array size
  * @mask: enabled instances mask: 1- enabled, 0- disabled
  */
 int hl_init_pb_with_mask(struct hl_device *hdev, u32 num_dcores,
 		u32 dcore_offset, u32 num_instances, u32 instance_offset,
 		const u32 pb_blocks[], u32 blocks_array_size,
-		const u32 *regs_array, u32 regs_array_size, u64 mask)
+		const u32 *user_regs_array, u32 user_regs_array_size, u64 mask)
 {
 	int i, j;
 	struct hl_block_glbl_sec *glbl_sec;
@@ -303,8 +303,8 @@ int hl_init_pb_with_mask(struct hl_device *hdev, u32 num_dcores,
 		return -ENOMEM;
 
 	hl_secure_block(hdev, glbl_sec, blocks_array_size);
-	hl_unsecure_registers(hdev, regs_array, regs_array_size, 0, pb_blocks,
-			glbl_sec, blocks_array_size);
+	hl_unsecure_registers(hdev, user_regs_array, user_regs_array_size, 0,
+			pb_blocks, glbl_sec, blocks_array_size);
 
 	/* Fill all blocks with the same configuration */
 	for (i = 0 ; i < num_dcores ; i++) {
@@ -336,19 +336,19 @@ int hl_init_pb_with_mask(struct hl_device *hdev, u32 num_dcores,
  * @instance_offset: offset between instances
  * @pb_blocks: blocks array
  * @blocks_array_size: blocks array size
- * @regs_array: register array
- * @regs_array_size: register array size
+ * @user_regs_array: unsecured register array
+ * @user_regs_array_size: unsecured register array size
  *
  */
 int hl_init_pb(struct hl_device *hdev, u32 num_dcores, u32 dcore_offset,
 		u32 num_instances, u32 instance_offset,
 		const u32 pb_blocks[], u32 blocks_array_size,
-		const u32 *regs_array, u32 regs_array_size)
+		const u32 *user_regs_array, u32 user_regs_array_size)
 {
 	return hl_init_pb_with_mask(hdev, num_dcores, dcore_offset,
 			num_instances, instance_offset, pb_blocks,
-			blocks_array_size, regs_array, regs_array_size,
-			ULLONG_MAX);
+			blocks_array_size, user_regs_array,
+			user_regs_array_size, ULLONG_MAX);
 }
 
 /**
@@ -364,15 +364,15 @@ int hl_init_pb(struct hl_device *hdev, u32 num_dcores, u32 dcore_offset,
  * @instance_offset: offset between instances
  * @pb_blocks: blocks array
  * @blocks_array_size: blocks array size
- * @regs_range_array: register range array
- * @regs_range_array_size: register range array size
+ * @user_regs_range_array: unsecured register range array
+ * @user_regs_range_array_size: unsecured register range array size
  * @mask: enabled instances mask: 1- enabled, 0- disabled
  */
 int hl_init_pb_ranges_with_mask(struct hl_device *hdev, u32 num_dcores,
 		u32 dcore_offset, u32 num_instances, u32 instance_offset,
 		const u32 pb_blocks[], u32 blocks_array_size,
-		const struct range *regs_range_array, u32 regs_range_array_size,
-		u64 mask)
+		const struct range *user_regs_range_array,
+		u32 user_regs_range_array_size, u64 mask)
 {
 	int i, j, rc = 0;
 	struct hl_block_glbl_sec *glbl_sec;
@@ -384,8 +384,8 @@ int hl_init_pb_ranges_with_mask(struct hl_device *hdev, u32 num_dcores,
 		return -ENOMEM;
 
 	hl_secure_block(hdev, glbl_sec, blocks_array_size);
-	rc = hl_unsecure_registers_range(hdev, regs_range_array,
-			regs_range_array_size, 0, pb_blocks, glbl_sec,
+	rc = hl_unsecure_registers_range(hdev, user_regs_range_array,
+			user_regs_range_array_size, 0, pb_blocks, glbl_sec,
 			blocks_array_size);
 	if (rc)
 		goto free_glbl_sec;
@@ -422,19 +422,20 @@ free_glbl_sec:
  * @instance_offset: offset between instances
  * @pb_blocks: blocks array
  * @blocks_array_size: blocks array size
- * @regs_range_array: register range array
- * @regs_range_array_size: register range array size
+ * @user_regs_range_array: unsecured register range array
+ * @user_regs_range_array_size: unsecured register range array size
  *
  */
 int hl_init_pb_ranges(struct hl_device *hdev, u32 num_dcores,
 		u32 dcore_offset, u32 num_instances, u32 instance_offset,
 		const u32 pb_blocks[], u32 blocks_array_size,
-		const struct range *regs_range_array, u32 regs_range_array_size)
+		const struct range *user_regs_range_array,
+		u32 user_regs_range_array_size)
 {
 	return hl_init_pb_ranges_with_mask(hdev, num_dcores, dcore_offset,
 			num_instances, instance_offset, pb_blocks,
-			blocks_array_size, regs_range_array,
-			regs_range_array_size, ULLONG_MAX);
+			blocks_array_size, user_regs_range_array,
+			user_regs_range_array_size, ULLONG_MAX);
 }
 
 /**
@@ -447,14 +448,14 @@ int hl_init_pb_ranges(struct hl_device *hdev, u32 num_dcores,
  * @instance_offset: offset between instances
  * @pb_blocks: blocks array
  * @blocks_array_size: blocks array size
- * @regs_array: register array
- * @regs_array_size: register array size
+ * @user_regs_array: unsecured register array
+ * @user_regs_array_size: unsecured register array size
  *
  */
 int hl_init_pb_single_dcore(struct hl_device *hdev, u32 dcore_offset,
 		u32 num_instances, u32 instance_offset,
 		const u32 pb_blocks[], u32 blocks_array_size,
-		const u32 *regs_array, u32 regs_array_size)
+		const u32 *user_regs_array, u32 user_regs_array_size)
 {
 	int i, rc = 0;
 	struct hl_block_glbl_sec *glbl_sec;
@@ -466,8 +467,8 @@ int hl_init_pb_single_dcore(struct hl_device *hdev, u32 dcore_offset,
 		return -ENOMEM;
 
 	hl_secure_block(hdev, glbl_sec, blocks_array_size);
-	rc = hl_unsecure_registers(hdev, regs_array, regs_array_size, 0,
-			pb_blocks, glbl_sec, blocks_array_size);
+	rc = hl_unsecure_registers(hdev, user_regs_array, user_regs_array_size,
+			0, pb_blocks, glbl_sec, blocks_array_size);
 	if (rc)
 		goto free_glbl_sec;
 
@@ -495,8 +496,8 @@ free_glbl_sec:
  * @instance_offset: offset between instances
  * @pb_blocks: blocks array
  * @blocks_array_size: blocks array size
- * @regs_range_array: register range array
- * @regs_range_array_size: register range array size
+ * @user_regs_range_array: unsecured register range array
+ * @user_regs_range_array_size: unsecured register range array size
  *
  */
 int hl_init_pb_ranges_single_dcore(struct hl_device *hdev, u32 dcore_offset,
diff --git a/drivers/accel/habanalabs/gaudi/gaudi.c b/drivers/accel/habanalabs/gaudi/gaudi.c
index a29aa8f7b6f3..056e2ef44afb 100644
--- a/drivers/accel/habanalabs/gaudi/gaudi.c
+++ b/drivers/accel/habanalabs/gaudi/gaudi.c
@@ -114,13 +114,6 @@ static u32 gaudi_stream_master[GAUDI_STREAM_MASTER_ARR_SIZE] = {
 	GAUDI_QUEUE_ID_DMA_1_3
 };
 
-static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = {
-		"gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3",
-		"gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3",
-		"gaudi cq 5_0", "gaudi cq 5_1", "gaudi cq 5_2", "gaudi cq 5_3",
-		"gaudi cpu eq"
-};
-
 static const u8 gaudi_dma_assignment[GAUDI_DMA_MAX] = {
 	[GAUDI_PCI_DMA_1] = GAUDI_ENGINE_ID_DMA_0,
 	[GAUDI_PCI_DMA_2] = GAUDI_ENGINE_ID_DMA_1,
@@ -1476,8 +1469,7 @@ static int gaudi_collective_wait_create_job(struct hl_device *hdev,
 	}
 
 	/* Allocate internal mapped CB for non patched CBs */
-	cb = hl_cb_kernel_create(hdev, cb_size,
-			hdev->mmu_enable && !patched_cb);
+	cb = hl_cb_kernel_create(hdev, cb_size, !patched_cb);
 	if (!cb) {
 		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
 		atomic64_inc(&cntr->out_of_mem_drop_cnt);
@@ -3651,9 +3643,6 @@ static int gaudi_mmu_init(struct hl_device *hdev)
 	u64 hop0_addr;
 	int rc, i;
 
-	if (!hdev->mmu_enable)
-		return 0;
-
 	if (gaudi->hw_cap_initialized & HW_CAP_MMU)
 		return 0;
 
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2.c b/drivers/accel/habanalabs/gaudi2/gaudi2.c
index b778cf764a68..20c4583f12b0 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2.c
@@ -57,13 +57,13 @@
 
 #define GAUDI2_NA_EVENT_CAUSE			0xFF
 #define GAUDI2_NUM_OF_QM_ERR_CAUSE		18
-#define GAUDI2_NUM_OF_QM_LCP_ERR_CAUSE		25
+#define GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE	25
 #define GAUDI2_NUM_OF_QM_ARB_ERR_CAUSE		3
 #define GAUDI2_NUM_OF_ARC_SEI_ERR_CAUSE		14
 #define GAUDI2_NUM_OF_CPU_SEI_ERR_CAUSE		3
 #define GAUDI2_NUM_OF_QM_SEI_ERR_CAUSE		2
 #define GAUDI2_NUM_OF_ROT_ERR_CAUSE		22
-#define GAUDI2_NUM_OF_TPC_INTR_CAUSE		30
+#define GAUDI2_NUM_OF_TPC_INTR_CAUSE		31
 #define GAUDI2_NUM_OF_DEC_ERR_CAUSE		25
 #define GAUDI2_NUM_OF_MME_ERR_CAUSE		16
 #define GAUDI2_NUM_OF_MME_SBTE_ERR_CAUSE	5
@@ -162,6 +162,9 @@
 #define PSOC_RAZWI_ENG_STR_SIZE 128
 #define PSOC_RAZWI_MAX_ENG_PER_RTR 5
 
+/* HW scrambles only bits 0-25 */
+#define HW_UNSCRAMBLED_BITS_MASK GENMASK_ULL(63, 26)
+
 struct gaudi2_razwi_info {
 	u32 axuser_xy;
 	u32 rtr_ctrl;
@@ -801,7 +804,7 @@ static const char * const gaudi2_qman_error_cause[GAUDI2_NUM_OF_QM_ERR_CAUSE] =
 	"PQC L2H error"
 };
 
-static const char * const gaudi2_qman_lower_cp_error_cause[GAUDI2_NUM_OF_QM_LCP_ERR_CAUSE] = {
+static const char * const gaudi2_lower_qman_error_cause[GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE] = {
 	"RSVD0",
 	"CQ AXI HBW error",
 	"CP AXI HBW error",
@@ -891,6 +894,7 @@ static const char * const gaudi2_tpc_interrupts_cause[GAUDI2_NUM_OF_TPC_INTR_CAU
 	"invalid_lock_access",
 	"LD_L protection violation",
 	"ST_L protection violation",
+	"D$ L0CS mismatch",
 };
 
 static const char * const guadi2_mme_error_cause[GAUDI2_NUM_OF_MME_ERR_CAUSE] = {
@@ -3615,6 +3619,12 @@ static int gaudi2_sw_init(struct hl_device *hdev)
 
 	prop->supports_compute_reset = true;
 
+	/* Event queue sanity check added in FW version 1.11 */
+	if (hl_is_fw_sw_ver_below(hdev, 1, 11))
+		hdev->event_queue.check_eqe_index = false;
+	else
+		hdev->event_queue.check_eqe_index = true;
+
 	hdev->asic_funcs->set_pci_memory_regions(hdev);
 
 	rc = gaudi2_special_blocks_iterator_config(hdev);
@@ -3630,8 +3640,8 @@ static int gaudi2_sw_init(struct hl_device *hdev)
 special_blocks_free:
 	gaudi2_special_blocks_iterator_free(hdev);
 free_scratchpad_mem:
-	hl_asic_dma_pool_free(hdev, gaudi2->scratchpad_kernel_address,
-				gaudi2->scratchpad_bus_address);
+	hl_asic_dma_free_coherent(hdev, PAGE_SIZE, gaudi2->scratchpad_kernel_address,
+				  gaudi2->scratchpad_bus_address);
 free_virt_msix_db_mem:
 	hl_cpu_accessible_dma_pool_free(hdev, prop->pmmu.page_size, gaudi2->virt_msix_db_cpu_addr);
 free_cpu_accessible_dma_pool:
@@ -4526,7 +4536,7 @@ static int gaudi2_set_tpc_engine_mode(struct hl_device *hdev, u32 engine_id, u32
 	reg_base = gaudi2_tpc_cfg_blocks_bases[tpc_id];
 	reg_addr = reg_base + TPC_CFG_STALL_OFFSET;
 	reg_val = FIELD_PREP(DCORE0_TPC0_CFG_TPC_STALL_V_MASK,
-			!!(engine_command == HL_ENGINE_STALL));
+			(engine_command == HL_ENGINE_STALL) ? 1 : 0);
 	WREG32(reg_addr, reg_val);
 
 	if (engine_command == HL_ENGINE_RESUME) {
@@ -4550,7 +4560,7 @@ static int gaudi2_set_mme_engine_mode(struct hl_device *hdev, u32 engine_id, u32
 	reg_base = gaudi2_mme_ctrl_lo_blocks_bases[mme_id];
 	reg_addr = reg_base + MME_CTRL_LO_QM_STALL_OFFSET;
 	reg_val = FIELD_PREP(DCORE0_MME_CTRL_LO_QM_STALL_V_MASK,
-			!!(engine_command == HL_ENGINE_STALL));
+			(engine_command == HL_ENGINE_STALL) ? 1 : 0);
 	WREG32(reg_addr, reg_val);
 
 	return 0;
@@ -4571,7 +4581,7 @@ static int gaudi2_set_edma_engine_mode(struct hl_device *hdev, u32 engine_id, u3
 	reg_base = gaudi2_dma_core_blocks_bases[edma_id];
 	reg_addr = reg_base + EDMA_CORE_CFG_STALL_OFFSET;
 	reg_val = FIELD_PREP(DCORE0_EDMA0_CORE_CFG_1_HALT_MASK,
-			!!(engine_command == HL_ENGINE_STALL));
+			(engine_command == HL_ENGINE_STALL) ? 1 : 0);
 	WREG32(reg_addr, reg_val);
 
 	if (engine_command == HL_ENGINE_STALL) {
@@ -6148,18 +6158,24 @@ static int gaudi2_execute_soft_reset(struct hl_device *hdev, bool driver_perform
 						u32 poll_timeout_us)
 {
 	struct cpu_dyn_regs *dyn_regs = &hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
+	int rc = 0;
 
 	if (!driver_performs_reset) {
-		/* set SP to indicate reset request sent to FW */
-		if (dyn_regs->cpu_rst_status)
-			WREG32(le32_to_cpu(dyn_regs->cpu_rst_status), CPU_RST_STATUS_NA);
-		else
-			WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
-
-		WREG32(le32_to_cpu(dyn_regs->gic_host_soft_rst_irq),
-			gaudi2_irq_map_table[GAUDI2_EVENT_CPU_SOFT_RESET].cpu_id);
-
-		return gaudi2_get_soft_rst_done_indication(hdev, poll_timeout_us);
+		if (hl_is_fw_sw_ver_below(hdev, 1, 10)) {
+			/* set SP to indicate reset request sent to FW */
+			if (dyn_regs->cpu_rst_status)
+				WREG32(le32_to_cpu(dyn_regs->cpu_rst_status), CPU_RST_STATUS_NA);
+			else
+				WREG32(mmCPU_RST_STATUS_TO_HOST, CPU_RST_STATUS_NA);
+			WREG32(le32_to_cpu(dyn_regs->gic_host_soft_rst_irq),
+				gaudi2_irq_map_table[GAUDI2_EVENT_CPU_SOFT_RESET].cpu_id);
+
+			/* wait for f/w response */
+			rc = gaudi2_get_soft_rst_done_indication(hdev, poll_timeout_us);
+		} else {
+			rc = hl_fw_send_soft_reset(hdev);
+		}
+		return rc;
 	}
 
 	/* Block access to engines, QMANs and SM during reset, these
@@ -7231,7 +7247,7 @@ static bool gaudi2_get_tpc_idle_status(struct hl_device *hdev, u64 *mask_arr, u8
 
 	gaudi2_iterate_tpcs(hdev, &tpc_iter);
 
-	return tpc_idle_data.is_idle;
+	return *tpc_idle_data.is_idle;
 }
 
 static bool gaudi2_get_decoder_idle_status(struct hl_device *hdev, u64 *mask_arr, u8 mask_len,
@@ -7737,137 +7753,28 @@ static bool gaudi2_handle_ecc_event(struct hl_device *hdev, u16 event_type,
 	return !!ecc_data->is_critical;
 }
 
-/*
- * gaudi2_queue_idx_dec - decrement queue index (pi/ci) and handle wrap
- *
- * @idx: the current pi/ci value
- * @q_len: the queue length (power of 2)
- *
- * @return the cyclically decremented index
- */
-static inline u32 gaudi2_queue_idx_dec(u32 idx, u32 q_len)
-{
-	u32 mask = q_len - 1;
-
-	/*
-	 * modular decrement is equivalent to adding (queue_size -1)
-	 * later we take LSBs to make sure the value is in the
-	 * range [0, queue_len - 1]
-	 */
-	return (idx + q_len - 1) & mask;
-}
-
-/**
- * gaudi2_print_sw_config_stream_data - print SW config stream data
- *
- * @hdev: pointer to the habanalabs device structure
- * @stream: the QMAN's stream
- * @qman_base: base address of QMAN registers block
- */
-static void gaudi2_print_sw_config_stream_data(struct hl_device *hdev,
-						u32 stream, u64 qman_base)
-{
-	u64 cq_ptr_lo, cq_ptr_hi, cq_tsize, cq_ptr;
-	u32 cq_ptr_lo_off, size;
-
-	cq_ptr_lo_off = mmDCORE0_TPC0_QM_CQ_PTR_LO_1 - mmDCORE0_TPC0_QM_CQ_PTR_LO_0;
-
-	cq_ptr_lo = qman_base + (mmDCORE0_TPC0_QM_CQ_PTR_LO_0 - mmDCORE0_TPC0_QM_BASE) +
-									stream * cq_ptr_lo_off;
-
-	cq_ptr_hi = cq_ptr_lo + (mmDCORE0_TPC0_QM_CQ_PTR_HI_0 - mmDCORE0_TPC0_QM_CQ_PTR_LO_0);
-
-	cq_tsize = cq_ptr_lo + (mmDCORE0_TPC0_QM_CQ_TSIZE_0 - mmDCORE0_TPC0_QM_CQ_PTR_LO_0);
-
-	cq_ptr = (((u64) RREG32(cq_ptr_hi)) << 32) | RREG32(cq_ptr_lo);
-	size = RREG32(cq_tsize);
-	dev_info(hdev->dev, "stop on err: stream: %u, addr: %#llx, size: %x\n",
-		stream, cq_ptr, size);
-}
-
-/**
- * gaudi2_print_last_pqes_on_err - print last PQEs on error
- *
- * @hdev: pointer to the habanalabs device structure
- * @qid_base: first QID of the QMAN (out of 4 streams)
- * @stream: the QMAN's stream
- * @qman_base: base address of QMAN registers block
- * @pr_sw_conf: if true print the SW config stream data (CQ PTR and SIZE)
- */
-static void gaudi2_print_last_pqes_on_err(struct hl_device *hdev, u32 qid_base, u32 stream,
-						u64 qman_base, bool pr_sw_conf)
+static void print_lower_qman_data_on_err(struct hl_device *hdev, u64 qman_base)
 {
-	u32 ci, qm_ci_stream_off;
-	struct hl_hw_queue *q;
-	u64 pq_ci;
-	int i;
-
-	q = &hdev->kernel_queues[qid_base + stream];
-
-	qm_ci_stream_off = mmDCORE0_TPC0_QM_PQ_CI_1 - mmDCORE0_TPC0_QM_PQ_CI_0;
-	pq_ci = qman_base + (mmDCORE0_TPC0_QM_PQ_CI_0 - mmDCORE0_TPC0_QM_BASE) +
-						stream * qm_ci_stream_off;
-
-	hdev->asic_funcs->hw_queues_lock(hdev);
-
-	if (pr_sw_conf)
-		gaudi2_print_sw_config_stream_data(hdev, stream, qman_base);
-
-	ci = RREG32(pq_ci);
-
-	/* we should start printing form ci -1 */
-	ci = gaudi2_queue_idx_dec(ci, HL_QUEUE_LENGTH);
-
-	for (i = 0; i < PQ_FETCHER_CACHE_SIZE; i++) {
-		struct hl_bd *bd;
-		u64 addr;
-		u32 len;
-
-		bd = q->kernel_address;
-		bd += ci;
-
-		len = le32_to_cpu(bd->len);
-		/* len 0 means uninitialized entry- break */
-		if (!len)
-			break;
-
-		addr = le64_to_cpu(bd->ptr);
-
-		dev_info(hdev->dev, "stop on err PQE(stream %u): ci: %u, addr: %#llx, size: %x\n",
-			stream, ci, addr, len);
-
-		/* get previous ci, wrap if needed */
-		ci = gaudi2_queue_idx_dec(ci, HL_QUEUE_LENGTH);
-	}
-
-	hdev->asic_funcs->hw_queues_unlock(hdev);
-}
+	u32 lo, hi, cq_ptr_size, arc_cq_ptr_size;
+	u64 cq_ptr, arc_cq_ptr, cp_current_inst;
 
-/**
- * print_qman_data_on_err - extract QMAN data on error
- *
- * @hdev: pointer to the habanalabs device structure
- * @qid_base: first QID of the QMAN (out of 4 streams)
- * @stream: the QMAN's stream
- * @qman_base: base address of QMAN registers block
- *
- * This function attempt to extract as much data as possible on QMAN error.
- * On upper CP print the SW config stream data and last 8 PQEs.
- * On lower CP print SW config data and last PQEs of ALL 4 upper CPs
- */
-static void print_qman_data_on_err(struct hl_device *hdev, u32 qid_base, u32 stream, u64 qman_base)
-{
-	u32 i;
+	lo = RREG32(qman_base + QM_CQ_PTR_LO_4_OFFSET);
+	hi = RREG32(qman_base + QM_CQ_PTR_HI_4_OFFSET);
+	cq_ptr = ((u64) hi) << 32 | lo;
+	cq_ptr_size = RREG32(qman_base + QM_CQ_TSIZE_4_OFFSET);
 
-	if (stream != QMAN_STREAMS) {
-		gaudi2_print_last_pqes_on_err(hdev, qid_base, stream, qman_base, true);
-		return;
-	}
+	lo = RREG32(qman_base + QM_ARC_CQ_PTR_LO_OFFSET);
+	hi = RREG32(qman_base + QM_ARC_CQ_PTR_HI_OFFSET);
+	arc_cq_ptr = ((u64) hi) << 32 | lo;
+	arc_cq_ptr_size = RREG32(qman_base + QM_ARC_CQ_TSIZE_OFFSET);
 
-	gaudi2_print_sw_config_stream_data(hdev, stream, qman_base);
+	lo = RREG32(qman_base + QM_CP_CURRENT_INST_LO_4_OFFSET);
+	hi = RREG32(qman_base + QM_CP_CURRENT_INST_HI_4_OFFSET);
+	cp_current_inst = ((u64) hi) << 32 | lo;
 
-	for (i = 0 ; i < QMAN_STREAMS ; i++)
-		gaudi2_print_last_pqes_on_err(hdev, qid_base, i, qman_base, false);
+	dev_info(hdev->dev,
+		"LowerQM. CQ: {ptr %#llx, size %u}, ARC_CQ: {ptr %#llx, size %u}, CP: {instruction %#llx}\n",
+		cq_ptr, cq_ptr_size, arc_cq_ptr, arc_cq_ptr_size, cp_current_inst);
 }
 
 static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type,
@@ -7888,8 +7795,8 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
 			continue;
 
 		if (i == QMAN_STREAMS) {
-			snprintf(reg_desc, ARRAY_SIZE(reg_desc), "LowerCP");
-			num_error_causes = GAUDI2_NUM_OF_QM_LCP_ERR_CAUSE;
+			snprintf(reg_desc, ARRAY_SIZE(reg_desc), "LowerQM");
+			num_error_causes = GAUDI2_NUM_OF_LOWER_QM_ERR_CAUSE;
 		} else {
 			snprintf(reg_desc, ARRAY_SIZE(reg_desc), "stream%u", i);
 			num_error_causes = GAUDI2_NUM_OF_QM_ERR_CAUSE;
@@ -7900,12 +7807,13 @@ static int gaudi2_handle_qman_err_generic(struct hl_device *hdev, u16 event_type
 				gaudi2_print_event(hdev, event_type, true,
 					"%s. err cause: %s", reg_desc,
 					i == QMAN_STREAMS ?
-					gaudi2_qman_lower_cp_error_cause[j] :
+					gaudi2_lower_qman_error_cause[j] :
 					gaudi2_qman_error_cause[j]);
 				error_count++;
 			}
 
-		print_qman_data_on_err(hdev, qid_base, i, qman_base);
+		if (i == QMAN_STREAMS)
+			print_lower_qman_data_on_err(hdev, qman_base);
 	}
 
 	arb_err_val = RREG32(arb_err_addr);
@@ -8033,7 +7941,7 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
 				u8 module_sub_idx, u64 *event_mask)
 {
 	bool via_sft = false;
-	u32 hbw_rtr_id, lbw_rtr_id, dcore_id, dcore_rtr_id, eng_id;
+	u32 hbw_rtr_id, lbw_rtr_id, dcore_id, dcore_rtr_id, eng_id, binned_idx;
 	u64 hbw_rtr_mstr_if_base_addr, lbw_rtr_mstr_if_base_addr;
 	u32 hbw_shrd_aw = 0, hbw_shrd_ar = 0;
 	u32 lbw_shrd_aw = 0, lbw_shrd_ar = 0;
@@ -8041,15 +7949,21 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
 
 	switch (module) {
 	case RAZWI_TPC:
+		sprintf(initiator_name, "TPC_%u", module_idx);
+		if (hdev->tpc_binning) {
+			binned_idx = __ffs(hdev->tpc_binning);
+			if (binned_idx == module_idx)
+				module_idx = TPC_ID_DCORE0_TPC6;
+		}
+
 		hbw_rtr_id = gaudi2_tpc_initiator_hbw_rtr_id[module_idx];
 
-		if (hl_is_fw_ver_below_1_9(hdev) &&
+		if (hl_is_fw_sw_ver_below(hdev, 1, 9) &&
 				!hdev->asic_prop.fw_security_enabled &&
 				((module_idx == 0) || (module_idx == 1)))
 			lbw_rtr_id = DCORE0_RTR0;
 		else
 			lbw_rtr_id = gaudi2_tpc_initiator_lbw_rtr_id[module_idx];
-		sprintf(initiator_name, "TPC_%u", module_idx);
 		break;
 	case RAZWI_MME:
 		sprintf(initiator_name, "MME_%u", module_idx);
@@ -8108,9 +8022,14 @@ static void gaudi2_ack_module_razwi_event_handler(struct hl_device *hdev,
 		sprintf(initiator_name, "NIC_%u", module_idx);
 		break;
 	case RAZWI_DEC:
+		sprintf(initiator_name, "DEC_%u", module_idx);
+		if (hdev->decoder_binning) {
+			binned_idx = __ffs(hdev->decoder_binning);
+			if (binned_idx == module_idx)
+				module_idx = DEC_ID_PCIE_VDEC1;
+		}
 		hbw_rtr_id = gaudi2_dec_initiator_hbw_rtr_id[module_idx];
 		lbw_rtr_id = gaudi2_dec_initiator_lbw_rtr_id[module_idx];
-		sprintf(initiator_name, "DEC_%u", module_idx);
 		break;
 	case RAZWI_ROT:
 		hbw_rtr_id = gaudi2_rot_initiator_hbw_rtr_id[module_idx];
@@ -8251,6 +8170,7 @@ static bool gaudi2_handle_psoc_razwi_happened(struct hl_device *hdev, u32 razwi_
 	u16 num_of_eng, eng_id[PSOC_RAZWI_MAX_ENG_PER_RTR];
 	char eng_name_str[PSOC_RAZWI_ENG_STR_SIZE];
 	bool razwi_happened = false;
+	u64 addr;
 	int i;
 
 	num_of_eng = gaudi2_psoc_razwi_get_engines(common_razwi_info, ARRAY_SIZE(common_razwi_info),
@@ -8269,43 +8189,53 @@ static bool gaudi2_handle_psoc_razwi_happened(struct hl_device *hdev, u32 razwi_
 		if (RREG32(base[i] + DEC_RAZWI_HBW_AW_SET)) {
 			addr_hi = RREG32(base[i] + DEC_RAZWI_HBW_AW_ADDR_HI);
 			addr_lo = RREG32(base[i] + DEC_RAZWI_HBW_AW_ADDR_LO);
-			dev_err(hdev->dev,
+			addr = ((u64)addr_hi << 32) + addr_lo;
+			if (addr) {
+				dev_err(hdev->dev,
 					"PSOC HBW AW RAZWI: %s, address (aligned to 128 byte): 0x%llX\n",
-					eng_name_str, ((u64)addr_hi << 32) + addr_lo);
-			hl_handle_razwi(hdev, ((u64)addr_hi << 32) + addr_lo, &eng_id[0],
+					eng_name_str, addr);
+				hl_handle_razwi(hdev, addr, &eng_id[0],
 					num_of_eng, HL_RAZWI_HBW | HL_RAZWI_WRITE, event_mask);
-			razwi_happened = true;
+				razwi_happened = true;
+			}
 		}
 
 		if (RREG32(base[i] + DEC_RAZWI_HBW_AR_SET)) {
 			addr_hi = RREG32(base[i] + DEC_RAZWI_HBW_AR_ADDR_HI);
 			addr_lo = RREG32(base[i] + DEC_RAZWI_HBW_AR_ADDR_LO);
-			dev_err(hdev->dev,
+			addr = ((u64)addr_hi << 32) + addr_lo;
+			if (addr) {
+				dev_err(hdev->dev,
 					"PSOC HBW AR RAZWI: %s, address (aligned to 128 byte): 0x%llX\n",
-					eng_name_str, ((u64)addr_hi << 32) + addr_lo);
-			hl_handle_razwi(hdev, ((u64)addr_hi << 32) + addr_lo, &eng_id[0],
+					eng_name_str, addr);
+				hl_handle_razwi(hdev, addr, &eng_id[0],
 					num_of_eng, HL_RAZWI_HBW | HL_RAZWI_READ, event_mask);
-			razwi_happened = true;
+				razwi_happened = true;
+			}
 		}
 
 		if (RREG32(base[i] + DEC_RAZWI_LBW_AW_SET)) {
 			addr_lo = RREG32(base[i] + DEC_RAZWI_LBW_AW_ADDR);
-			dev_err(hdev->dev,
+			if (addr_lo) {
+				dev_err(hdev->dev,
 					"PSOC LBW AW RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
 					eng_name_str, addr_lo);
-			hl_handle_razwi(hdev, addr_lo, &eng_id[0],
+				hl_handle_razwi(hdev, addr_lo, &eng_id[0],
 					num_of_eng, HL_RAZWI_LBW | HL_RAZWI_WRITE, event_mask);
-			razwi_happened = true;
+				razwi_happened = true;
+			}
 		}
 
 		if (RREG32(base[i] + DEC_RAZWI_LBW_AR_SET)) {
 			addr_lo = RREG32(base[i] + DEC_RAZWI_LBW_AR_ADDR);
-			dev_err(hdev->dev,
-					"PSOC LBW AR RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
-					eng_name_str, addr_lo);
-			hl_handle_razwi(hdev, addr_lo, &eng_id[0],
+			if (addr_lo) {
+				dev_err(hdev->dev,
+						"PSOC LBW AR RAZWI: %s, address (aligned to 128 byte): 0x%X\n",
+						eng_name_str, addr_lo);
+				hl_handle_razwi(hdev, addr_lo, &eng_id[0],
 					num_of_eng, HL_RAZWI_LBW | HL_RAZWI_READ, event_mask);
-			razwi_happened = true;
+				razwi_happened = true;
+			}
 		}
 		/* In common case the loop will break, when there is only one engine id, or
 		 * several engines with the same router. The exceptional case is with psoc razwi
@@ -8789,13 +8719,13 @@ static int gaudi2_handle_kdma_core_event(struct hl_device *hdev, u16 event_type,
 	return error_count;
 }
 
-static int gaudi2_handle_dma_core_event(struct hl_device *hdev, u16 event_type, int sts_addr)
+static int gaudi2_handle_dma_core_event(struct hl_device *hdev, u16 event_type, u64 intr_cause)
 {
-	u32 error_count = 0, sts_val = RREG32(sts_addr);
+	u32 error_count = 0;
 	int i;
 
 	for (i = 0 ; i < GAUDI2_NUM_OF_DMA_CORE_INTR_CAUSE ; i++)
-		if (sts_val & BIT(i)) {
+		if (intr_cause & BIT(i)) {
 			gaudi2_print_event(hdev, event_type, true,
 				"err cause: %s", gaudi2_dma_core_interrupts_cause[i]);
 			error_count++;
@@ -8806,27 +8736,6 @@ static int gaudi2_handle_dma_core_event(struct hl_device *hdev, u16 event_type,
 	return error_count;
 }
 
-static int gaudi2_handle_pdma_core_event(struct hl_device *hdev, u16 event_type, int pdma_idx)
-{
-	u32 sts_addr;
-
-	sts_addr = mmPDMA0_CORE_ERR_CAUSE + pdma_idx * PDMA_OFFSET;
-	return gaudi2_handle_dma_core_event(hdev, event_type, sts_addr);
-}
-
-static int gaudi2_handle_edma_core_event(struct hl_device *hdev, u16 event_type, int edma_idx)
-{
-	static const int edma_event_index_map[] = {2, 3, 0, 1, 6, 7, 4, 5};
-	u32 sts_addr, index;
-
-	index = edma_event_index_map[edma_idx];
-
-	sts_addr = mmDCORE0_EDMA0_CORE_ERR_CAUSE +
-				DCORE_OFFSET * (index / NUM_OF_EDMA_PER_DCORE) +
-				DCORE_EDMA_OFFSET * (index % NUM_OF_EDMA_PER_DCORE);
-	return gaudi2_handle_dma_core_event(hdev, event_type, sts_addr);
-}
-
 static void gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(struct hl_device *hdev, u64 *event_mask)
 {
 	u32 mstr_if_base_addr = mmPCIE_MSTR_RR_MSTR_IF_RR_SHRD_HBW_BASE, razwi_happened_addr;
@@ -8866,6 +8775,9 @@ static int gaudi2_print_pcie_addr_dec_info(struct hl_device *hdev, u16 event_typ
 	u32 error_count = 0;
 	int i;
 
+	gaudi2_print_event(hdev, event_type, true,
+		"intr_cause_data: %#llx", intr_cause_data);
+
 	for (i = 0 ; i < GAUDI2_NUM_OF_PCIE_ADDR_DEC_ERR_CAUSE ; i++) {
 		if (!(intr_cause_data & BIT_ULL(i)))
 			continue;
@@ -8874,16 +8786,15 @@ static int gaudi2_print_pcie_addr_dec_info(struct hl_device *hdev, u16 event_typ
 			"err cause: %s", gaudi2_pcie_addr_dec_error_cause[i]);
 		error_count++;
 
-		switch (intr_cause_data & BIT_ULL(i)) {
-		case PCIE_WRAP_PCIE_IC_SEI_INTR_IND_AXI_LBW_ERR_INTR_MASK:
-			hl_check_for_glbl_errors(hdev);
-			break;
-		case PCIE_WRAP_PCIE_IC_SEI_INTR_IND_BAD_ACCESS_INTR_MASK:
-			gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(hdev, event_mask);
-			break;
-		}
+		/*
+		 * Always check for LBW and HBW additional info as the indication itself is
+		 * sometimes missing
+		 */
 	}
 
+	hl_check_for_glbl_errors(hdev);
+	gaudi2_print_pcie_mstr_rr_mstr_if_razwi_info(hdev, event_mask);
+
 	return error_count;
 }
 
@@ -8937,11 +8848,16 @@ static void gaudi2_handle_page_error(struct hl_device *hdev, u64 mmu_base, bool
 	addr <<= 32;
 	addr |= RREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_PAGE_ERROR_CAPTURE_VA));
 
-	if (!is_pmmu)
+	if (is_pmmu) {
+		dev_err_ratelimited(hdev->dev, "PMMU page fault on va 0x%llx\n", addr);
+	} else {
+
 		addr = gaudi2_mmu_descramble_addr(hdev, addr);
+		addr &= HW_UNSCRAMBLED_BITS_MASK;
+		dev_err_ratelimited(hdev->dev, "HMMU page fault on va range 0x%llx - 0x%llx\n",
+				addr, addr + ~HW_UNSCRAMBLED_BITS_MASK);
+	}
 
-	dev_err_ratelimited(hdev->dev, "%s page fault on va 0x%llx\n",
-				is_pmmu ? "PMMU" : "HMMU", addr);
 	hl_handle_page_fault(hdev, addr, 0, is_pmmu, event_mask);
 
 	WREG32(mmu_base + MMU_OFFSET(mmDCORE0_HMMU0_MMU_ACCESS_PAGE_ERROR_VALID), 0);
@@ -9709,19 +9625,19 @@ static void gaudi2_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_ent
 	case GAUDI2_EVENT_KDMA_CH0_AXI_ERR_RSP:
 	case GAUDI2_EVENT_KDMA0_CORE:
 		error_count = gaudi2_handle_kdma_core_event(hdev, event_type,
-					le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
+				le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
 		event_mask |= HL_NOTIFIER_EVENT_GENERAL_HW_ERR;
 		break;
 
 	case GAUDI2_EVENT_HDMA2_CORE ... GAUDI2_EVENT_HDMA5_CORE:
-		index = event_type - GAUDI2_EVENT_HDMA2_CORE;
-		error_count = gaudi2_handle_edma_core_event(hdev, event_type, index);
+		error_count = gaudi2_handle_dma_core_event(hdev, event_type,
+				le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
 		event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
 		break;
 
 	case GAUDI2_EVENT_PDMA0_CORE ... GAUDI2_EVENT_PDMA1_CORE:
-		index = event_type - GAUDI2_EVENT_PDMA0_CORE;
-		error_count = gaudi2_handle_pdma_core_event(hdev, event_type, index);
+		error_count = gaudi2_handle_dma_core_event(hdev, event_type,
+				le64_to_cpu(eq_entry->intr_cause.intr_cause_data));
 		event_mask |= HL_NOTIFIER_EVENT_USER_ENGINE_ERR;
 		break;
 
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2P.h b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
index 1cebe707772e..5f3ce086928e 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2P.h
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2P.h
@@ -98,7 +98,7 @@
 #define GAUDI2_DEFAULT_CARD_NAME		"HL225"
 
 #define QMAN_STREAMS				4
-#define PQ_FETCHER_CACHE_SIZE			8
+
 #define NUM_OF_MME_SBTE_PORTS			5
 #define NUM_OF_MME_WB_PORTS			2
 
diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
index 694735f9e6e6..2742b1f801eb 100644
--- a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
+++ b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
@@ -479,6 +479,7 @@ static const u32 gaudi2_pb_dcr0_edma0_unsecured_regs[] = {
 	mmDCORE0_EDMA0_CORE_CTX_TE_NUMROWS,
 	mmDCORE0_EDMA0_CORE_CTX_IDX,
 	mmDCORE0_EDMA0_CORE_CTX_IDX_INC,
+	mmDCORE0_EDMA0_CORE_RD_LBW_RATE_LIM_CFG,
 	mmDCORE0_EDMA0_QM_CQ_CFG0_0,
 	mmDCORE0_EDMA0_QM_CQ_CFG0_1,
 	mmDCORE0_EDMA0_QM_CQ_CFG0_2,
@@ -1533,6 +1534,10 @@ static const u32 gaudi2_pb_dcr0_tpc0_unsecured_regs[] = {
 	mmDCORE0_TPC0_CFG_QM_KERNEL_CONFIG,
 	mmDCORE0_TPC0_CFG_QM_KERNEL_ID,
 	mmDCORE0_TPC0_CFG_QM_POWER_LOOP,
+	mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_0,
+	mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_1,
+	mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_2,
+	mmDCORE0_TPC0_CFG_TSB_CFG_MTRR_2_3,
 	mmDCORE0_TPC0_CFG_LUT_FUNC32_BASE2_ADDR_LO,
 	mmDCORE0_TPC0_CFG_LUT_FUNC32_BASE2_ADDR_HI,
 	mmDCORE0_TPC0_CFG_LUT_FUNC64_BASE2_ADDR_LO,
@@ -1541,6 +1546,7 @@ static const u32 gaudi2_pb_dcr0_tpc0_unsecured_regs[] = {
 	mmDCORE0_TPC0_CFG_LUT_FUNC128_BASE2_ADDR_HI,
 	mmDCORE0_TPC0_CFG_LUT_FUNC256_BASE2_ADDR_LO,
 	mmDCORE0_TPC0_CFG_LUT_FUNC256_BASE2_ADDR_HI,
+	mmDCORE0_TPC0_CFG_FP8_143_BIAS,
 	mmDCORE0_TPC0_CFG_ROUND_CSR,
 	mmDCORE0_TPC0_CFG_CONV_ROUND_CSR,
 	mmDCORE0_TPC0_CFG_SEMAPHORE,
@@ -3442,15 +3448,6 @@ static int gaudi2_init_protection_bits(struct hl_device *hdev)
 				ARRAY_SIZE(gaudi2_pb_thermal_sensor0), NULL, HL_PB_NA);
 	}
 
-	/* HBM */
-	/* Temporarily skip until SW-63348 is solved
-	 * instance_offset = mmHBM1_MC0_BASE - mmHBM0_MC0_BASE;
-	 * rc |= hl_init_pb_with_mask(hdev, HL_PB_SHARED, HL_PB_NA, GAUDI2_HBM_NUM,
-	 *		instance_offset, gaudi2_pb_hbm,
-	 *		ARRAY_SIZE(gaudi2_pb_hbm), NULL, HL_PB_NA,
-	 *		prop->dram_enabled_mask);
-	 */
-
 	/* Scheduler ARCs */
 	instance_offset = mmARC_FARM_ARC1_AUX_BASE - mmARC_FARM_ARC0_AUX_BASE;
 	rc |= hl_init_pb_ranges(hdev, HL_PB_SHARED, HL_PB_NA,
diff --git a/drivers/accel/habanalabs/goya/goya.c b/drivers/accel/habanalabs/goya/goya.c
index fb0ac9df841a..7c685e6075f6 100644
--- a/drivers/accel/habanalabs/goya/goya.c
+++ b/drivers/accel/habanalabs/goya/goya.c
@@ -2671,9 +2671,6 @@ int goya_mmu_init(struct hl_device *hdev)
 	u64 hop0_addr;
 	int rc, i;
 
-	if (!hdev->mmu_enable)
-		return 0;
-
 	if (goya->hw_cap_initialized & HW_CAP_MMU)
 		return 0;
 
diff --git a/drivers/accel/habanalabs/goya/goya_coresight.c b/drivers/accel/habanalabs/goya/goya_coresight.c
index e7ac3046cfaa..a6d6cc38bcd8 100644
--- a/drivers/accel/habanalabs/goya/goya_coresight.c
+++ b/drivers/accel/habanalabs/goya/goya_coresight.c
@@ -371,13 +371,8 @@ static int goya_etr_validate_address(struct hl_device *hdev, u64 addr,
 		return false;
 	}
 
-	if (hdev->mmu_enable) {
-		range_start = prop->dmmu.start_addr;
-		range_end = prop->dmmu.end_addr;
-	} else {
-		range_start = prop->dram_user_base_address;
-		range_end = prop->dram_end_address;
-	}
+	range_start = prop->dmmu.start_addr;
+	range_end = prop->dmmu.end_addr;
 
 	return hl_mem_area_inside_range(addr, size, range_start, range_end);
 }
diff --git a/drivers/accel/habanalabs/include/common/cpucp_if.h b/drivers/accel/habanalabs/include/common/cpucp_if.h
index 8bbe685458c4..33807b839c37 100644
--- a/drivers/accel/habanalabs/include/common/cpucp_if.h
+++ b/drivers/accel/habanalabs/include/common/cpucp_if.h
@@ -359,7 +359,7 @@ struct hl_eq_entry {
 	union {
 		__le64 data_placeholder;
 		struct hl_eq_ecc_data ecc_data;
-		struct hl_eq_hbm_ecc_data hbm_ecc_data;	/* Gaudi1 HBM */
+		struct hl_eq_hbm_ecc_data hbm_ecc_data;	/* Obsolete */
 		struct hl_eq_sm_sei_data sm_sei_data;
 		struct cpucp_pkt_sync_err pkt_sync_err;
 		struct hl_eq_fw_alive fw_alive;
@@ -653,7 +653,7 @@ enum pq_init_status {
  *       which address is passed via the CpuCp packet. In addition, the host's driver
  *       passes the max size it allows the CpuCP to write to the structure, to prevent
  *       data corruption in case of mismatched driver/FW versions.
- *       Relevant only to Gaudi.
+ *       Obsolete.
  *
  * CPUCP_PACKET_GENERIC_PASSTHROUGH -
  *      Generic opcode for all firmware info that is only passed to host
@@ -665,6 +665,9 @@ enum pq_init_status {
  *
  * CPUCP_PACKET_REGISTER_INTERRUPTS -
  *       Packet to register interrupts indicating LKD is ready to receive events from FW.
+ *
+ * CPUCP_PACKET_SOFT_RESET -
+ *	 Packet to perform soft-reset.
  */
 
 enum cpucp_packet_id {
@@ -731,6 +734,7 @@ enum cpucp_packet_id {
 	CPUCP_PACKET_RESERVED11,		/* not used */
 	CPUCP_PACKET_RESERVED12,		/* internal */
 	CPUCP_PACKET_REGISTER_INTERRUPTS,	/* internal */
+	CPUCP_PACKET_SOFT_RESET,		/* internal */
 	CPUCP_PACKET_ID_MAX			/* must be last */
 };
 
@@ -864,19 +868,19 @@ struct cpucp_array_data_packet {
 enum cpucp_led_index {
 	CPUCP_LED0_INDEX = 0,
 	CPUCP_LED1_INDEX,
-	CPUCP_LED2_INDEX
+	CPUCP_LED2_INDEX,
+	CPUCP_LED_MAX_INDEX = CPUCP_LED2_INDEX
 };
 
 /*
  * enum cpucp_packet_rc - Error return code
  * @cpucp_packet_success	-> in case of success.
- * @cpucp_packet_invalid	-> this is to support Goya and Gaudi platform.
+ * @cpucp_packet_invalid	-> this is to support first generation platforms.
  * @cpucp_packet_fault		-> in case of processing error like failing to
  *                                 get device binding or semaphore etc.
- * @cpucp_packet_invalid_pkt	-> when cpucp packet is un-supported. This is
- *                                 supported Greco onwards.
+ * @cpucp_packet_invalid_pkt	-> when cpucp packet is un-supported.
  * @cpucp_packet_invalid_params	-> when checking parameter like length of buffer
- *				   or attribute value etc. Supported Greco onwards.
+ *				   or attribute value etc.
  * @cpucp_packet_rc_max		-> It indicates size of enum so should be at last.
  */
 enum cpucp_packet_rc {
@@ -1361,7 +1365,7 @@ struct cpucp_dev_info_signed {
 #define DCORE_MON_REGS_SZ	512
 /*
  * struct dcore_monitor_regs_data - DCORE monitor regs data.
- * the structure follows sync manager block layout. relevant only to Gaudi.
+ * the structure follows sync manager block layout. Obsolete.
  * @mon_pay_addrl: array of payload address low bits.
  * @mon_pay_addrh: array of payload address high bits.
  * @mon_pay_data: array of payload data.
@@ -1376,7 +1380,7 @@ struct dcore_monitor_regs_data {
 	__le32 mon_status[DCORE_MON_REGS_SZ];
 };
 
-/* contains SM data for each SYNC_MNGR (relevant only to Gaudi) */
+/* contains SM data for each SYNC_MNGR (Obsolete) */
 struct cpucp_monitor_dump {
 	struct dcore_monitor_regs_data sync_mngr_w_s;
 	struct dcore_monitor_regs_data sync_mngr_e_s;
diff --git a/drivers/accel/habanalabs/include/common/hl_boot_if.h b/drivers/accel/habanalabs/include/common/hl_boot_if.h
index c58d76a2705c..cff79f7f9f75 100644
--- a/drivers/accel/habanalabs/include/common/hl_boot_if.h
+++ b/drivers/accel/habanalabs/include/common/hl_boot_if.h
@@ -35,6 +35,7 @@ enum cpu_boot_err {
 	CPU_BOOT_ERR_TPM_FAIL = 20,
 	CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL = 21,
 	CPU_BOOT_ERR_EEPROM_FAIL = 22,
+	CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL = 23,
 	CPU_BOOT_ERR_ENABLED = 31,
 	CPU_BOOT_ERR_SCND_EN = 63,
 	CPU_BOOT_ERR_LAST = 64 /* we have 2 registers of 32 bits */
@@ -51,6 +52,7 @@ enum cpu_boot_err {
 		 (1 << CPU_BOOT_ERR_DEVICE_UNUSABLE_FAIL) |	\
 		 (1 << CPU_BOOT_ERR_BINNING_FAIL) |		\
 		 (1 << CPU_BOOT_ERR_DRAM_SKIPPED) |		\
+		 (1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL) |	\
 		 (1 << CPU_BOOT_ERR_EEPROM_FAIL))
 
 /*
@@ -132,6 +134,9 @@ enum cpu_boot_err {
  * CPU_BOOT_ERR_EEPROM_FAIL		Failed reading EEPROM data. Defaults
  *					are used.
  *
+ * CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL	Failed scrubbing the Engines/ARCFarm
+ *					memories. Boot disabled until reset.
+ *
  * CPU_BOOT_ERR0_ENABLED		Error registers enabled.
  *					This is a main indication that the
  *					running FW populates the error
@@ -157,6 +162,7 @@ enum cpu_boot_err {
 #define CPU_BOOT_ERR0_TPM_FAIL			(1 << CPU_BOOT_ERR_TPM_FAIL)
 #define CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL	(1 << CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL)
 #define CPU_BOOT_ERR0_EEPROM_FAIL		(1 << CPU_BOOT_ERR_EEPROM_FAIL)
+#define CPU_BOOT_ERR0_ENG_ARC_MEM_SCRUB_FAIL	(1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL)
 #define CPU_BOOT_ERR0_ENABLED			(1 << CPU_BOOT_ERR_ENABLED)
 #define CPU_BOOT_ERR1_ENABLED			(1 << CPU_BOOT_ERR_ENABLED)
 
@@ -744,36 +750,6 @@ struct comms_status {
 	};
 };
 
-/**
- * HL_MODULES_MAX_NUM is determined by the size of modules_mask in struct
- *      hl_component_versions
- */
-enum hl_modules {
-	HL_MODULES_BOOT_INFO = 0,
-	HL_MODULES_EEPROM,
-	HL_MODULES_FDT,
-	HL_MODULES_I2C,
-	HL_MODULES_LZ4,
-	HL_MODULES_MBEDTLS,
-	HL_MODULES_MAX_NUM = 16
-};
-
-/**
- * HL_COMPONENTS_MAX_NUM is determined by the size of components_mask in
- *      struct cpucp_versions
- */
-enum hl_components {
-	HL_COMPONENTS_PID = 0,
-	HL_COMPONENTS_MGMT,
-	HL_COMPONENTS_PREBOOT,
-	HL_COMPONENTS_PPBOOT,
-	HL_COMPONENTS_ARMCP,
-	HL_COMPONENTS_CPLD,
-	HL_COMPONENTS_UBOOT,
-	HL_COMPONENTS_FUSE,
-	HL_COMPONENTS_MAX_NUM = 16
-};
-
 #define NAME_MAX_LEN	32 /* bytes */
 struct hl_module_data {
 	__u8 name[NAME_MAX_LEN];
@@ -787,8 +763,6 @@ struct hl_module_data {
  * @component: version of the component itself.
  * @fw_os: Firmware OS Version.
  * @comp_name: Name of the component.
- * @modules_mask: i'th bit (from LSB) is a flag - on if module i in enum
- *              hl_modules is used.
  * @modules_counter: number of set bits in modules_mask.
  * @reserved: reserved for future use.
  * @modules: versions of the component's modules. Elborated explanation in
@@ -800,9 +774,8 @@ struct hl_component_versions {
 	__u8 component[VERSION_MAX_LEN];
 	__u8 fw_os[VERSION_MAX_LEN];
 	__u8 comp_name[NAME_MAX_LEN];
-	__le16 modules_mask;
 	__u8 modules_counter;
-	__u8 reserved[1];
+	__u8 reserved[3];
 	struct hl_module_data modules[];
 };
 
diff --git a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
index 6c58af614236..a08378d0802b 100644
--- a/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
+++ b/drivers/accel/habanalabs/include/gaudi2/asic_reg/gaudi2_regs.h
@@ -242,6 +242,17 @@
 #define QM_FENCE2_OFFSET		(mmPDMA0_QM_CP_FENCE2_RDATA_0 - mmPDMA0_QM_BASE)
 #define QM_SEI_STATUS_OFFSET		(mmPDMA0_QM_SEI_STATUS - mmPDMA0_QM_BASE)
 
+#define QM_CQ_PTR_LO_4_OFFSET		(mmPDMA0_QM_CQ_PTR_LO_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_PTR_HI_4_OFFSET		(mmPDMA0_QM_CQ_PTR_HI_4 - mmPDMA0_QM_BASE)
+#define QM_CQ_TSIZE_4_OFFSET		(mmPDMA0_QM_CQ_TSIZE_4 - mmPDMA0_QM_BASE)
+
+#define QM_ARC_CQ_PTR_LO_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_LO - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_PTR_HI_OFFSET		(mmPDMA0_QM_ARC_CQ_PTR_HI - mmPDMA0_QM_BASE)
+#define QM_ARC_CQ_TSIZE_OFFSET		(mmPDMA0_QM_ARC_CQ_TSIZE - mmPDMA0_QM_BASE)
+
+#define QM_CP_CURRENT_INST_LO_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_LO_4 - mmPDMA0_QM_BASE)
+#define QM_CP_CURRENT_INST_HI_4_OFFSET	(mmPDMA0_QM_CP_CURRENT_INST_HI_4 - mmPDMA0_QM_BASE)
+
 #define SFT_OFFSET		(mmSFT1_HBW_RTR_IF0_RTR_H3_BASE - mmSFT0_HBW_RTR_IF0_RTR_H3_BASE)
 #define SFT_IF_RTR_OFFSET	(mmSFT0_HBW_RTR_IF1_RTR_H3_BASE - mmSFT0_HBW_RTR_IF0_RTR_H3_BASE)
 
diff --git a/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h b/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h
index 8522f24deac0..18ca147b1c86 100644
--- a/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h
+++ b/drivers/accel/habanalabs/include/gaudi2/gaudi2_fw_if.h
@@ -62,7 +62,7 @@ struct gaudi2_cold_rst_data {
 			u32 fake_security_enable : 1;
 			u32 fake_sig_validation_en : 1;
 			u32 bist_skip_enable : 1;
-			u32 bist_need_iatu_config : 1;
+			u32 reserved1 : 1;
 			u32 fake_bis_compliant : 1;
 			u32 wd_rst_cause_arm : 1;
 			u32 wd_rst_cause_arcpid : 1;