Merge tag 'drm-habanalabs-next-2023-06-08' of https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/linux into drm-next

This tag contains additional habanalabs driver changes for v6.5:

- uAPI changes:
  - Return 0 when user queries if there was a h/w or f/w error and no such error happened.
    Previously we returned an error in such case.

- New features and improvements:
  - 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.
  - Reduce amount of code under mutex in the command submission of signal event.

- Firmware related fixes:
  - Fixes to the handshake protocol during f/w initialization.
  - Display information that the f/w sends us when encountering a DMA error.
  - Do soft-reset using a message sent to firmware instead of writing to MMIO.
  - Prepare generic code to extract f/w version numbers.

- Bug fixes and code cleanups. Notable fixes are:
  - Unsecure certain TPC registers that the user should access.
  - Fix handling of QMAN errors
  - Fix memory leak when recording errors (to later pass them to the user)
  - Multiple fixes to razwi interrupt handling code

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

From: Oded Gabbay <ogabbay@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20230608103043.GA2699019@ogabbay-vm-u20.habana-labs.com

23 files changed, 557 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 */