[RFC 29/37] ASoC: Intel: avs: Coredump and recovery flow

[Cezary Rojewski <cezary.rojewski@intel.com>]

In rare occassions, under stress conditions or hardware malfunction, DSP
firmware may fail. Software is notified about such situation with
EXCEPTION_CAUGHT notification. IPC timeout is also counted as critical
device failure. More often than not, driver can recover from such
situations by performing full reset: killing and restarting ADSP.

Signed-off-by: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Signed-off-by: Cezary Rojewski <cezary.rojewski@intel.com>
---
 sound/soc/intel/Kconfig        |  1 +
 sound/soc/intel/avs/avs.h      |  3 ++
 sound/soc/intel/avs/ipc.c      | 87 ++++++++++++++++++++++++++++++++--
 sound/soc/intel/avs/messages.h |  5 ++
 4 files changed, 93 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig
index b01c492d3514..8c059e2a5a36 100644
--- a/sound/soc/intel/Kconfig
+++ b/sound/soc/intel/Kconfig
@@ -220,6 +220,7 @@ config SND_SOC_INTEL_AVS
 	select SND_HDA_EXT_CORE
 	select SND_HDA_DSP_LOADER
 	select SND_INTEL_NHLT
+	select WANT_DEV_COREDUMP
 	help
 	  Enable support for Intel(R) cAVS 1.5 platforms with DSP
 	  capabilities. This includes Skylake, Kabylake, Amberlake and
diff --git a/sound/soc/intel/avs/avs.h b/sound/soc/intel/avs/avs.h
index 74194d8c04fe..4562f187939d 100644
--- a/sound/soc/intel/avs/avs.h
+++ b/sound/soc/intel/avs/avs.h
@@ -33,6 +33,7 @@ struct avs_dsp_ops {
 	int (* const load_lib)(struct avs_dev *, struct firmware *, u32);
 	int (* const transfer_mods)(struct avs_dev *, bool,
 				    struct avs_module_entry *, u32);
+	int (* const coredump)(struct avs_dev *, union avs_notify_msg *);
 };
 
 #define avs_dsp_op(adev, op, ...) \
@@ -147,6 +148,8 @@ struct avs_ipc {
 	struct mutex msg_mutex;
 	struct completion done_completion;
 	struct completion busy_completion;
+
+	struct work_struct recovery_work;
 };
 
 #define AVS_EIPC	EREMOTEIO
diff --git a/sound/soc/intel/avs/ipc.c b/sound/soc/intel/avs/ipc.c
index c461f7db3683..a8d2323e07a7 100644
--- a/sound/soc/intel/avs/ipc.c
+++ b/sound/soc/intel/avs/ipc.c
@@ -14,6 +14,78 @@
 
 #define AVS_IPC_TIMEOUT_MS	300
 
+static void avs_dsp_recovery(struct avs_dev *adev)
+{
+	struct avs_soc_component *acomp;
+	unsigned int core_mask;
+	int ret;
+
+	mutex_lock(&adev->comp_list_mutex);
+	/* disconnect all running streams */
+	list_for_each_entry(acomp, &adev->comp_list, node) {
+		struct snd_soc_pcm_runtime *rtd;
+		struct snd_soc_card *card;
+
+		card = acomp->base.card;
+		if (!card)
+			continue;
+
+		for_each_card_rtds(card, rtd) {
+			struct snd_pcm *pcm;
+			int dir;
+
+			pcm = rtd->pcm;
+			if (!pcm || rtd->dai_link->no_pcm)
+				continue;
+
+			for_each_pcm_streams(dir) {
+				struct snd_pcm_substream *substream;
+
+				substream = pcm->streams[dir].substream;
+				if (!substream || !substream->runtime)
+					continue;
+
+				snd_pcm_stop(substream, SNDRV_PCM_STATE_DISCONNECTED);
+			}
+		}
+	}
+	mutex_unlock(&adev->comp_list_mutex);
+
+	/* forcibly shutdown all cores */
+	core_mask = GENMASK(adev->hw_cfg.dsp_cores - 1, 0);
+	avs_dsp_core_disable(adev, core_mask);
+
+	/* attempt dsp reboot */
+	ret = avs_dsp_boot_firmware(adev, true);
+	if (ret < 0)
+		dev_err(adev->dev, "firmware reboot failed: %d\n", ret);
+
+	pm_runtime_mark_last_busy(adev->dev);
+	pm_runtime_enable(adev->dev);
+	pm_request_autosuspend(adev->dev);
+}
+
+static void avs_dsp_recovery_work(struct work_struct *work)
+{
+	struct avs_ipc *ipc = container_of(work, struct avs_ipc, recovery_work);
+
+	avs_dsp_recovery(to_avs_dev(ipc->dev));
+}
+
+static void avs_dsp_exception_caught(struct avs_dev *adev, union avs_notify_msg *msg)
+{
+	dev_crit(adev->dev, "communication severed, rebooting dsp..\n");
+
+	/* Re-enabled on recovery completion. */
+	avs_ipc_block(adev->ipc);
+	pm_runtime_disable(adev->dev);
+
+	/* Process received notification. */
+	avs_dsp_op(adev, coredump, msg);
+
+	schedule_work(&adev->ipc->recovery_work);
+}
+
 static void avs_dsp_receive_rx(struct avs_dev *adev, u64 header)
 {
 	struct avs_ipc *ipc = adev->ipc;
@@ -51,6 +123,9 @@ static void avs_dsp_process_notification(struct avs_dev *adev, u64 header)
 		data_size = sizeof(struct avs_notify_res_data);
 		break;
 
+	case AVS_NOTIFY_EXCEPTION_CAUGHT:
+		break;
+
 	case AVS_NOTIFY_MODULE_EVENT:
 		memcpy_fromio(&mod_data, avs_uplink_addr(adev), sizeof(mod_data));
 		data_size = sizeof(mod_data) + mod_data.data_size;
@@ -78,6 +153,10 @@ static void avs_dsp_process_notification(struct avs_dev *adev, u64 header)
 		complete(&adev->fw_ready);
 		break;
 
+	case AVS_NOTIFY_EXCEPTION_CAUGHT:
+		avs_dsp_exception_caught(adev, &msg);
+		break;
+
 	default:
 		break;
 	}
@@ -264,10 +343,10 @@ static int avs_dsp_do_send_msg(struct avs_dev *adev, struct avs_ipc_msg *request
 	ret = avs_ipc_wait_busy_completion(ipc, timeout);
 	if (ret) {
 		if (ret == -ETIMEDOUT) {
-			dev_crit(adev->dev, "communication severed: %d, rebooting dsp..\n",
-				 ret);
+			union avs_notify_msg msg = AVS_NOTIFICATION(EXCEPTION_CAUGHT);
 
-			avs_ipc_block(ipc);
+			/* Same treatment as on exception, just stack_dump=0. */
+			avs_dsp_exception_caught(adev, &msg);
 		}
 		goto exit;
 	}
@@ -389,6 +468,7 @@ int avs_ipc_init(struct avs_ipc *ipc, struct device *dev)
 	ipc->dev = dev;
 	ipc->ready = false;
 	ipc->default_timeout_ms = AVS_IPC_TIMEOUT_MS;
+	INIT_WORK(&ipc->recovery_work, avs_dsp_recovery_work);
 	init_completion(&ipc->done_completion);
 	init_completion(&ipc->busy_completion);
 	spin_lock_init(&ipc->rx_lock);
@@ -400,4 +480,5 @@ int avs_ipc_init(struct avs_ipc *ipc, struct device *dev)
 void avs_ipc_block(struct avs_ipc *ipc)
 {
 	ipc->ready = false;
+	cancel_work_sync(&ipc->recovery_work);
 }
diff --git a/sound/soc/intel/avs/messages.h b/sound/soc/intel/avs/messages.h
index a79aadba161d..f289c3498096 100644
--- a/sound/soc/intel/avs/messages.h
+++ b/sound/soc/intel/avs/messages.h
@@ -192,6 +192,7 @@ enum avs_notify_msg_type {
 	AVS_NOTIFY_PHRASE_DETECTED = 4,
 	AVS_NOTIFY_RESOURCE_EVENT = 5,
 	AVS_NOTIFY_FW_READY = 8,
+	AVS_NOTIFY_EXCEPTION_CAUGHT = 10,
 	AVS_NOTIFY_MODULE_EVENT = 12,
 };
 
@@ -210,6 +211,10 @@ union avs_notify_msg {
 		};
 		union {
 			u32 val;
+			struct {
+				u32 core_id:2;
+				u32 stack_dump_size:16;
+			} coredump;
 		} ext;
 	};
 } __packed;
-- 
2.25.1