[PATCH v8 00/11] Introduce atomic support for SCMI transports

@@ -339,11 +339,16 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id);
  * @dev: Reference to device in the SCMI hierarchy corresponding to this
  *	 channel
  * @handle: Pointer to SCMI entity handle
+ * @no_completion_irq: Flag to indicate that this channel has no completion
+ *		       interrupt mechanism for synchronous commands.
+ *		       This can be dynamically set by transports at run-time
+ *		       inside their provided .chan_setup().
  * @transport_info: Transport layer related information
  */
 struct scmi_chan_info {
 	struct device *dev;
 	struct scmi_handle *handle;
+	bool no_completion_irq;
 	void *transport_info;
 };
 

@@ -402,6 +407,8 @@ struct scmi_device *scmi_child_dev_find(struct device *parent,
  *	be pending simultaneously in the system. May be overridden by the
  *	get_max_msg op.
  * @max_msg_size: Maximum size of data per message that can be handled.
+ * @force_polling: Flag to force this whole transport to use SCMI core polling
+ *		   mechanism instead of completion interrupts even if available.
  */
 struct scmi_desc {
 	int (*transport_init)(void);

@@ -410,6 +417,7 @@ struct scmi_desc {
 	int max_rx_timeout_ms;
 	int max_msg;
 	int max_msg_size;
+	const bool force_polling;
 };
 
 #ifdef CONFIG_ARM_SCMI_TRANSPORT_MAILBOX

@@ -36,6 +36,23 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/scmi.h>
 
+#define IS_POLLING_REQUIRED(__c, __i)					\
+	((__c)->no_completion_irq || (__i)->desc->force_polling)	\
+
+#define IS_TRANSPORT_POLLING_CAPABLE(__i)				\
+	((__i)->desc->ops->poll_done)
+
+#define IS_POLLING_ENABLED(__c, __i)					\
+({									\
+	bool __ret;							\
+	typeof(__c) c_ = __c;						\
+	typeof(__i) i_ = __i;						\
+									\
+	__ret = (IS_POLLING_REQUIRED(c_, i_) &&				\
+			IS_TRANSPORT_POLLING_CAPABLE(i_));		\
+	__ret;								\
+})
+
 enum scmi_error_codes {
 	SCMI_SUCCESS = 0,	/* Success */
 	SCMI_ERR_SUPPORT = -1,	/* Not supported */

@@ -817,6 +834,7 @@ static int do_xfer(const struct scmi_protocol_handle *ph,
 	struct device *dev = info->dev;
 	struct scmi_chan_info *cinfo;
 
+	/* Check for polling request on custom command xfers at first */
 	if (xfer->hdr.poll_completion && !info->desc->ops->poll_done) {
 		dev_warn_once(dev,
 			      "Polling mode is not supported by transport.\n");

@@ -827,6 +845,10 @@ static int do_xfer(const struct scmi_protocol_handle *ph,
 	if (unlikely(!cinfo))
 		return -EINVAL;
 
+	/* True ONLY if also supported by transport. */
+	if (IS_POLLING_ENABLED(cinfo, info))
+		xfer->hdr.poll_completion = true;
+
 	/*
 	 * Initialise protocol id now from protocol handle to avoid it being
 	 * overridden by mistake (or malice) by the protocol code mangling with

@@ -1527,6 +1549,16 @@ static int scmi_chan_setup(struct scmi_info *info, struct device *dev,
 	if (ret)
 		return ret;
 
+	if (tx && IS_POLLING_REQUIRED(cinfo, info)) {
+		if (IS_TRANSPORT_POLLING_CAPABLE(info))
+			dev_info(dev,
+				 "Enabled polling mode TX channel - prot_id:%d\n",
+				 prot_id);
+		else
+			dev_warn(dev,
+				 "Polling mode NOT supported by transport.\n");
+	}
+
 idr_alloc:
 	ret = idr_alloc(idr, cinfo, prot_id, prot_id + 1, GFP_KERNEL);
 	if (ret != prot_id) {

@@ -25,8 +25,6 @@
  * @shmem: Transmit/Receive shared memory area
  * @shmem_lock: Lock to protect access to Tx/Rx shared memory area
  * @func_id: smc/hvc call function id
- * @irq: Optional; employed when platforms indicates msg completion by intr.
- * @tx_complete: Optional, employed only when irq is valid.
  */
 
 struct scmi_smc {

@@ -34,15 +32,14 @@ struct scmi_smc {
 	struct scmi_shared_mem __iomem *shmem;
 	struct mutex shmem_lock;
 	u32 func_id;
-	int irq;
-	struct completion tx_complete;
 };
 
 static irqreturn_t smc_msg_done_isr(int irq, void *data)
 {
 	struct scmi_smc *scmi_info = data;
 
-	complete(&scmi_info->tx_complete);
+	scmi_rx_callback(scmi_info->cinfo,
+			 shmem_read_header(scmi_info->shmem), NULL);
 
 	return IRQ_HANDLED;
 }

@@ -111,8 +108,8 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
 			dev_err(dev, "failed to setup SCMI smc irq\n");
 			return ret;
 		}
-		init_completion(&scmi_info->tx_complete);
-		scmi_info->irq = irq;
+	} else {
+		cinfo->no_completion_irq = true;
 	}
 
 	scmi_info->func_id = func_id;

@@ -142,26 +139,22 @@ static int smc_send_message(struct scmi_chan_info *cinfo,
 	struct scmi_smc *scmi_info = cinfo->transport_info;
 	struct arm_smccc_res res;
 
+	/*
+	 * Channel lock will be released only once response has been
+	 * surely fully retrieved, so after .mark_txdone()
+	 */
 	mutex_lock(&scmi_info->shmem_lock);
 
 	shmem_tx_prepare(scmi_info->shmem, xfer);
 
-	if (scmi_info->irq)
-		reinit_completion(&scmi_info->tx_complete);
-
 	arm_smccc_1_1_invoke(scmi_info->func_id, 0, 0, 0, 0, 0, 0, 0, &res);
 
-	if (scmi_info->irq)
-		wait_for_completion(&scmi_info->tx_complete);
-
-	scmi_rx_callback(scmi_info->cinfo,
-			 shmem_read_header(scmi_info->shmem), NULL);
-
-	mutex_unlock(&scmi_info->shmem_lock);
-
 	/* Only SMCCC_RET_NOT_SUPPORTED is valid error code */
-	if (res.a0)
+	if (res.a0) {
+		mutex_unlock(&scmi_info->shmem_lock);
 		return -EOPNOTSUPP;
+	}
+
 	return 0;
 }
 

@@ -173,6 +166,13 @@ static void smc_fetch_response(struct scmi_chan_info *cinfo,
 	shmem_fetch_response(scmi_info->shmem, xfer);
 }
 
+static void smc_mark_txdone(struct scmi_chan_info *cinfo, int ret)
+{
+	struct scmi_smc *scmi_info = cinfo->transport_info;
+
+	mutex_unlock(&scmi_info->shmem_lock);
+}
+
 static bool
 smc_poll_done(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer)
 {

@@ -186,6 +186,7 @@ static const struct scmi_transport_ops scmi_smc_ops = {
 	.chan_setup = smc_chan_setup,
 	.chan_free = smc_chan_free,
 	.send_message = smc_send_message,
+	.mark_txdone = smc_mark_txdone,
 	.fetch_response = smc_fetch_response,
 	.poll_done = smc_poll_done,
 };

@@ -409,6 +409,13 @@ struct scmi_device *scmi_child_dev_find(struct device *parent,
  * @max_msg_size: Maximum size of data per message that can be handled.
  * @force_polling: Flag to force this whole transport to use SCMI core polling
  *		   mechanism instead of completion interrupts even if available.
+ * @sync_cmds_completed_on_ret: Flag to indicate that the transport assures
+ *				synchronous-command messages are atomically
+ *				completed on .send_message: no need to poll
+ *				actively waiting for a response.
+ *				Used by core internally only when polling is
+ *				selected as a waiting for reply method: i.e.
+ *				if a completion irq was found use that anyway.
  */
 struct scmi_desc {
 	int (*transport_init)(void);

@@ -418,6 +425,7 @@ struct scmi_desc {
 	int max_msg;
 	int max_msg_size;
 	const bool force_polling;
+	const bool sync_cmds_completed_on_ret;
 };
 
 #ifdef CONFIG_ARM_SCMI_TRANSPORT_MAILBOX

@@ -40,7 +40,14 @@
 	((__c)->no_completion_irq || (__i)->desc->force_polling)	\
 
 #define IS_TRANSPORT_POLLING_CAPABLE(__i)				\
-	((__i)->desc->ops->poll_done)
+({									\
+	bool __ret;							\
+	typeof(__i) i_ = __i;						\
+									\
+	__ret = ((i_)->desc->ops->poll_done ||				\
+			(i_)->desc->sync_cmds_completed_on_ret);	\
+	__ret;								\
+})
 
 #define IS_POLLING_ENABLED(__c, __i)					\
 ({									\

@@ -780,10 +787,28 @@ static int scmi_wait_for_message_response(struct scmi_chan_info *cinfo,
 				      xfer->hdr.poll_completion);
 
 	if (xfer->hdr.poll_completion) {
-		ktime_t stop = ktime_add_ms(ktime_get(), timeout_ms);
+		/*
+		 * Real polling is needed only if transport has NOT declared
+		 * itself to support synchronous commands replies.
+		 */
+		if (!info->desc->sync_cmds_completed_on_ret) {
+			/*
+			 * Poll on xfer using transport provided .poll_done();
+			 * assumes no completion interrupt was available.
+			 */
+			ktime_t stop = ktime_add_ms(ktime_get(), timeout_ms);
+
+			spin_until_cond(scmi_xfer_done_no_timeout(cinfo,
+								  xfer, stop));
+			if (ktime_after(ktime_get(), stop)) {
+				dev_err(dev,
+					"timed out in resp(caller: %pS) - polling\n",
+					(void *)_RET_IP_);
+				ret = -ETIMEDOUT;
+			}
+		}
 
-		spin_until_cond(scmi_xfer_done_no_timeout(cinfo, xfer, stop));
-		if (ktime_before(ktime_get(), stop)) {
+		if (!ret) {
 			unsigned long flags;
 
 			/*

@@ -796,11 +821,6 @@ static int scmi_wait_for_message_response(struct scmi_chan_info *cinfo,
 				xfer->state = SCMI_XFER_RESP_OK;
 			}
 			spin_unlock_irqrestore(&xfer->lock, flags);
-		} else {
-			dev_err(dev,
-				"timed out in resp(caller: %pS) - polling\n",
-				(void *)_RET_IP_);
-			ret = -ETIMEDOUT;
 		}
 	} else {
 		/* And we wait for the response. */

@@ -835,7 +855,7 @@ static int do_xfer(const struct scmi_protocol_handle *ph,
 	struct scmi_chan_info *cinfo;
 
 	/* Check for polling request on custom command xfers at first */
-	if (xfer->hdr.poll_completion && !info->desc->ops->poll_done) {
+	if (xfer->hdr.poll_completion && !IS_TRANSPORT_POLLING_CAPABLE(info)) {
 		dev_warn_once(dev,
 			      "Polling mode is not supported by transport.\n");
 		return -EINVAL;

@@ -173,14 +173,6 @@ static void smc_mark_txdone(struct scmi_chan_info *cinfo, int ret)
 	mutex_unlock(&scmi_info->shmem_lock);
 }
 
-static bool
-smc_poll_done(struct scmi_chan_info *cinfo, struct scmi_xfer *xfer)
-{
-	struct scmi_smc *scmi_info = cinfo->transport_info;
-
-	return shmem_poll_done(scmi_info->shmem, xfer);
-}
-
 static const struct scmi_transport_ops scmi_smc_ops = {
 	.chan_available = smc_chan_available,
 	.chan_setup = smc_chan_setup,

@@ -188,7 +180,6 @@ static const struct scmi_transport_ops scmi_smc_ops = {
 	.send_message = smc_send_message,
 	.mark_txdone = smc_mark_txdone,
 	.fetch_response = smc_fetch_response,
-	.poll_done = smc_poll_done,
 };
 
 const struct scmi_desc scmi_smc_desc = {

@@ -196,4 +187,13 @@ const struct scmi_desc scmi_smc_desc = {
 	.max_rx_timeout_ms = 30,
 	.max_msg = 20,
 	.max_msg_size = 128,
+	/*
+	 * Setting .sync_cmds_atomic_replies to true for SMC assumes that,
+	 * once the SMC instruction has completed successfully, the issued
+	 * SCMI command would have been already fully processed by the SCMI
+	 * platform firmware and so any possible response value expected
+	 * for the issued command will be immmediately ready to be fetched
+	 * from the shared memory area.
+	 */
+	.sync_cmds_completed_on_ret = true,
 };

@@ -78,6 +78,20 @@ config ARM_SCMI_TRANSPORT_SMC
 	  If you want the ARM SCMI PROTOCOL stack to include support for a
 	  transport based on SMC, answer Y.
 
+config ARM_SCMI_TRANSPORT_SMC_ATOMIC_ENABLE
+	bool "Enable atomic mode support for SCMI SMC transport"
+	depends on ARM_SCMI_TRANSPORT_SMC
+	help
+	  Enable support of atomic operation for SCMI SMC based transport.
+
+	  If you want the SCMI SMC based transport to operate in atomic
+	  mode, avoiding any kind of sleeping behaviour for selected
+	  transactions on the TX path, answer Y.
+	  Enabling atomic mode operations allows any SCMI driver using this
+	  transport to optionally ask for atomic SCMI transactions and operate
+	  in atomic context too, at the price of using a number of busy-waiting
+	  primitives all over instead. If unsure say N.
+
 config ARM_SCMI_TRANSPORT_VIRTIO
 	bool "SCMI transport based on VirtIO"
 	depends on VIRTIO=y || VIRTIO=ARM_SCMI_PROTOCOL

@@ -7,6 +7,7 @@
  */
 
 #include <linux/arm-smccc.h>
+#include <linux/atomic.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>

@@ -14,6 +15,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/processor.h>
 #include <linux/slab.h>
 
 #include "common.h"

@@ -23,14 +25,20 @@
  *
  * @cinfo: SCMI channel info
  * @shmem: Transmit/Receive shared memory area
- * @shmem_lock: Lock to protect access to Tx/Rx shared memory area
+ * @shmem_lock: Lock to protect access to Tx/Rx shared memory area.
+ *		Used when NOT operating in atomic mode.
+ * @inflight: Atomic flag to protect access to Tx/Rx shared memory area.
+ *	      Used when operating in atomic mode.
  * @func_id: smc/hvc call function id
  */
 
 struct scmi_smc {
 	struct scmi_chan_info *cinfo;
 	struct scmi_shared_mem __iomem *shmem;
+	/* Protect access to shmem area */
 	struct mutex shmem_lock;
+#define INFLIGHT_NONE	MSG_TOKEN_MAX
+	atomic_t inflight;
 	u32 func_id;
 };
 

@@ -54,6 +62,41 @@ static bool smc_chan_available(struct device *dev, int idx)
 	return true;
 }
 
+static inline void smc_channel_lock_init(struct scmi_smc *scmi_info)
+{
+	if (IS_ENABLED(CONFIG_ARM_SCMI_TRANSPORT_SMC_ATOMIC_ENABLE))
+		atomic_set(&scmi_info->inflight, INFLIGHT_NONE);
+	else
+		mutex_init(&scmi_info->shmem_lock);
+}
+
+static bool smc_xfer_inflight(struct scmi_xfer *xfer, atomic_t *inflight)
+{
+	int ret;
+
+	ret = atomic_cmpxchg(inflight, INFLIGHT_NONE, xfer->hdr.seq);
+
+	return ret == INFLIGHT_NONE;
+}
+
+static inline void
+smc_channel_lock_acquire(struct scmi_smc *scmi_info,
+			 struct scmi_xfer *xfer __maybe_unused)
+{
+	if (IS_ENABLED(CONFIG_ARM_SCMI_TRANSPORT_SMC_ATOMIC_ENABLE))
+		spin_until_cond(smc_xfer_inflight(xfer, &scmi_info->inflight));
+	else
+		mutex_lock(&scmi_info->shmem_lock);
+}
+
+static inline void smc_channel_lock_release(struct scmi_smc *scmi_info)
+{
+	if (IS_ENABLED(CONFIG_ARM_SCMI_TRANSPORT_SMC_ATOMIC_ENABLE))
+		atomic_set(&scmi_info->inflight, INFLIGHT_NONE);
+	else
+		mutex_unlock(&scmi_info->shmem_lock);
+}
+
 static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
 			  bool tx)
 {

@@ -114,7 +157,7 @@ static int smc_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
 
 	scmi_info->func_id = func_id;
 	scmi_info->cinfo = cinfo;
-	mutex_init(&scmi_info->shmem_lock);
+	smc_channel_lock_init(scmi_info);
 	cinfo->transport_info = scmi_info;
 
 	return 0;

@@ -140,10 +183,10 @@ static int smc_send_message(struct scmi_chan_info *cinfo,
 	struct arm_smccc_res res;
 
 	/*
-	 * Channel lock will be released only once response has been
+	 * Channel will be released only once response has been
 	 * surely fully retrieved, so after .mark_txdone()
 	 */
-	mutex_lock(&scmi_info->shmem_lock);
+	smc_channel_lock_acquire(scmi_info, xfer);
 
 	shmem_tx_prepare(scmi_info->shmem, xfer);
 

@@ -151,7 +194,7 @@ static int smc_send_message(struct scmi_chan_info *cinfo,
 
 	/* Only SMCCC_RET_NOT_SUPPORTED is valid error code */
 	if (res.a0) {
-		mutex_unlock(&scmi_info->shmem_lock);
+		smc_channel_lock_release(scmi_info);
 		return -EOPNOTSUPP;
 	}
 

@@ -170,7 +213,7 @@ static void smc_mark_txdone(struct scmi_chan_info *cinfo, int ret)
 {
 	struct scmi_smc *scmi_info = cinfo->transport_info;
 
-	mutex_unlock(&scmi_info->shmem_lock);
+	smc_channel_lock_release(scmi_info);
 }
 
 static const struct scmi_transport_ops scmi_smc_ops = {

@@ -196,4 +239,5 @@ const struct scmi_desc scmi_smc_desc = {
 	 * from the shared memory area.
 	 */
 	.sync_cmds_completed_on_ret = true,
+	.atomic_enabled = IS_ENABLED(CONFIG_ARM_SCMI_TRANSPORT_SMC_ATOMIC_ENABLE),
 };

@@ -378,7 +378,8 @@ struct scmi_transport_ops {
 	unsigned int (*get_max_msg)(struct scmi_chan_info *base_cinfo);
 	int (*send_message)(struct scmi_chan_info *cinfo,
 			    struct scmi_xfer *xfer);
-	void (*mark_txdone)(struct scmi_chan_info *cinfo, int ret);
+	void (*mark_txdone)(struct scmi_chan_info *cinfo, int ret,
+			    struct scmi_xfer *xfer);
 	void (*fetch_response)(struct scmi_chan_info *cinfo,
 			       struct scmi_xfer *xfer);
 	void (*fetch_notification)(struct scmi_chan_info *cinfo,

@@ -902,7 +902,7 @@ static int do_xfer(const struct scmi_protocol_handle *ph,
 		ret = scmi_to_linux_errno(xfer->hdr.status);
 
 	if (info->desc->ops->mark_txdone)
-		info->desc->ops->mark_txdone(cinfo, ret);
+		info->desc->ops->mark_txdone(cinfo, ret, xfer);
 
 	trace_scmi_xfer_end(xfer->transfer_id, xfer->hdr.id,
 			    xfer->hdr.protocol_id, xfer->hdr.seq, ret);

@@ -140,7 +140,8 @@ static int mailbox_send_message(struct scmi_chan_info *cinfo,
 	return ret;
 }
 
-static void mailbox_mark_txdone(struct scmi_chan_info *cinfo, int ret)
+static void mailbox_mark_txdone(struct scmi_chan_info *cinfo, int ret,
+				struct scmi_xfer *__unused)
 {
 	struct scmi_mailbox *smbox = cinfo->transport_info;
 

@@ -441,7 +441,8 @@ static void scmi_optee_fetch_response(struct scmi_chan_info *cinfo,
 	shmem_fetch_response(shmem, xfer);
 }
 
-static void scmi_optee_mark_txdone(struct scmi_chan_info *cinfo, int ret)
+static void scmi_optee_mark_txdone(struct scmi_chan_info *cinfo, int ret,
+				   struct scmi_xfer *__unused)
 {
 	struct scmi_optee_channel *channel = cinfo->transport_info;
 

@@ -209,7 +209,8 @@ static void smc_fetch_response(struct scmi_chan_info *cinfo,
 	shmem_fetch_response(scmi_info->shmem, xfer);
 }
 
-static void smc_mark_txdone(struct scmi_chan_info *cinfo, int ret)
+static void smc_mark_txdone(struct scmi_chan_info *cinfo, int ret,
+			    struct scmi_xfer *__unused)
 {
 	struct scmi_smc *scmi_info = cinfo->transport_info;
 

@@ -416,6 +416,9 @@ struct scmi_device *scmi_child_dev_find(struct device *parent,
  *				Used by core internally only when polling is
  *				selected as a waiting for reply method: i.e.
  *				if a completion irq was found use that anyway.
+ * @atomic_enabled: Flag to indicate that this transport, which is assured not
+ *		    to sleep anywhere on the TX path, can be used in atomic mode
+ *		    when requested.
  */
 struct scmi_desc {
 	int (*transport_init)(void);

@@ -426,6 +429,7 @@ struct scmi_desc {
 	int max_msg_size;
 	const bool force_polling;
 	const bool sync_cmds_completed_on_ret;
+	const bool atomic_enabled;
 };
 
 #ifdef CONFIG_ARM_SCMI_TRANSPORT_MAILBOX

@@ -928,6 +928,20 @@ static void reset_rx_to_maxsz(const struct scmi_protocol_handle *ph,
  * @ph: Pointer to SCMI protocol handle
  * @xfer: Transfer to initiate and wait for response
  *
+ * Using asynchronous commands in atomic/polling mode should be avoided since
+ * it could cause long busy-waiting here, so ignore polling for the delayed
+ * response and WARN if it was requested for this command transaction since
+ * upper layers should refrain from issuing such kind of requests.
+ *
+ * The only other option would have been to refrain from using any asynchronous
+ * command even if made available, when an atomic transport is detected, and
+ * instead forcibly use the synchronous version (thing that can be easily
+ * attained at the protocol layer), but this would also have led to longer
+ * stalls of the channel for synchronous commands and possibly timeouts.
+ * (in other words there is usually a good reason if a platform provides an
+ *  asynchronous version of a command and we should prefer to use it...just not
+ *  when using atomic/polling mode)
+ *
  * Return: -ETIMEDOUT in case of no delayed response, if transmit error,
  *	return corresponding error, else if all goes well, return 0.
  */

@@ -939,12 +953,24 @@ static int do_xfer_with_response(const struct scmi_protocol_handle *ph,
 
 	xfer->async_done = &async_response;
 
+	/*
+	 * Delayed responses should not be polled, so an async command should
+	 * not have been used when requiring an atomic/poll context; WARN and
+	 * perform instead a sleeping wait.
+	 * (Note Async + IgnoreDelayedResponses are sent via do_xfer)
+	 */
+	WARN_ON_ONCE(xfer->hdr.poll_completion);
+
 	ret = do_xfer(ph, xfer);
 	if (!ret) {
-		if (!wait_for_completion_timeout(xfer->async_done, timeout))
+		if (!wait_for_completion_timeout(xfer->async_done, timeout)) {
+			dev_err(ph->dev,
+				"timed out in delayed resp(caller: %pS)\n",
+				(void *)_RET_IP_);
 			ret = -ETIMEDOUT;
-		else if (xfer->hdr.status)
+		} else if (xfer->hdr.status) {
 			ret = scmi_to_linux_errno(xfer->hdr.status);
+		}
 	}
 
 	xfer->async_done = NULL;

@@ -1378,6 +1404,22 @@ static void scmi_devm_protocol_put(struct scmi_device *sdev, u8 protocol_id)
 	WARN_ON(ret);
 }
 
+/**
+ * scmi_is_transport_atomic  - Method to check if underlying transport for an
+ * SCMI instance is configured as atomic.
+ *
+ * @handle: A reference to the SCMI platform instance.
+ *
+ * Return: True if transport is configured as atomic
+ */
+static bool scmi_is_transport_atomic(const struct scmi_handle *handle)
+{
+	struct scmi_info *info = handle_to_scmi_info(handle);
+
+	return info->desc->atomic_enabled &&
+		IS_TRANSPORT_POLLING_CAPABLE(info);
+}
+
 static inline
 struct scmi_handle *scmi_handle_get_from_info_unlocked(struct scmi_info *info)
 {

@@ -1915,6 +1957,7 @@ static int scmi_probe(struct platform_device *pdev)
 	handle->version = &info->version;
 	handle->devm_protocol_get = scmi_devm_protocol_get;
 	handle->devm_protocol_put = scmi_devm_protocol_put;
+	handle->is_transport_atomic = scmi_is_transport_atomic;
 
 	if (desc->ops->link_supplier) {
 		ret = desc->ops->link_supplier(dev);

@@ -1933,6 +1976,10 @@ static int scmi_probe(struct platform_device *pdev)
 	if (scmi_notification_init(handle))
 		dev_err(dev, "SCMI Notifications NOT available.\n");
 
+	if (info->desc->atomic_enabled && !IS_TRANSPORT_POLLING_CAPABLE(info))
+		dev_err(dev,
+			"Transport is not polling capable. Atomic mode not supported.\n");
+
 	/*
 	 * Trigger SCMI Base protocol initialization.
 	 * It's mandatory and won't be ever released/deinit until the

@@ -612,6 +612,13 @@ struct scmi_notify_ops {
  * @devm_protocol_get: devres managed method to acquire a protocol and get specific
  *		       operations and a dedicated protocol handler
  * @devm_protocol_put: devres managed method to release a protocol
+ * @is_transport_atomic: method to check if the underlying transport for this
+ *			 instance handle is configured to support atomic
+ *			 transactions for commands.
+ *			 Some users of the SCMI stack in the upper layers could
+ *			 be interested to know if they can assume SCMI
+ *			 command transactions associated to this handle will
+ *			 never sleep and act accordingly.
  * @notify_ops: pointer to set of notifications related operations
  */
 struct scmi_handle {

@@ -622,6 +629,7 @@ struct scmi_handle {
 		(*devm_protocol_get)(struct scmi_device *sdev, u8 proto,
 				     struct scmi_protocol_handle **ph);
 	void (*devm_protocol_put)(struct scmi_device *sdev, u8 proto);
+	bool (*is_transport_atomic)(const struct scmi_handle *handle);
 
 	const struct scmi_notify_ops *notify_ops;
 };

@@ -363,6 +363,9 @@ static int scmi_optee_chan_setup(struct scmi_chan_info *cinfo, struct device *de
 	if (ret)
 		goto err_close_sess;
 
+	/* Enable polling */
+	cinfo->no_completion_irq = true;
+
 	mutex_lock(&scmi_optee_private->mu);
 	list_add(&channel->link, &scmi_optee_private->channel_list);
 	mutex_unlock(&scmi_optee_private->mu);

@@ -423,9 +426,8 @@ static int scmi_optee_send_message(struct scmi_chan_info *cinfo,
 	shmem_tx_prepare(shmem, xfer);
 
 	ret = invoke_process_smt_channel(channel);
-
-	scmi_rx_callback(cinfo, shmem_read_header(shmem), NULL);
-	mutex_unlock(&channel->mu);
+	if (ret)
+		mutex_unlock(&channel->mu);
 
 	return ret;
 }

@@ -439,13 +441,11 @@ static void scmi_optee_fetch_response(struct scmi_chan_info *cinfo,
 	shmem_fetch_response(shmem, xfer);
 }
 
-static bool scmi_optee_poll_done(struct scmi_chan_info *cinfo,
-				 struct scmi_xfer *xfer)
+static void scmi_optee_mark_txdone(struct scmi_chan_info *cinfo, int ret)
 {
 	struct scmi_optee_channel *channel = cinfo->transport_info;
-	struct scmi_shared_mem *shmem = get_channel_shm(channel, xfer);
 
-	return shmem_poll_done(shmem, xfer);
+	mutex_unlock(&channel->mu);
 }
 
 static struct scmi_transport_ops scmi_optee_ops = {

@@ -454,9 +454,9 @@ static struct scmi_transport_ops scmi_optee_ops = {
 	.chan_setup = scmi_optee_chan_setup,
 	.chan_free = scmi_optee_chan_free,
 	.send_message = scmi_optee_send_message,
+	.mark_txdone = scmi_optee_mark_txdone,
 	.fetch_response = scmi_optee_fetch_response,
 	.clear_channel = scmi_optee_clear_channel,
-	.poll_done = scmi_optee_poll_done,
 };
 
 static int scmi_optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data)

@@ -562,4 +562,5 @@ const struct scmi_desc scmi_optee_desc = {
 	.max_rx_timeout_ms = 30,
 	.max_msg = 20,
 	.max_msg_size = SCMI_OPTEE_MAX_MSG_SIZE,
+	.sync_cmds_completed_on_ret = true,
 };

@@ -118,6 +118,21 @@ config ARM_SCMI_TRANSPORT_VIRTIO_VERSION1_COMPLIANCE
 	  the ones implemented by kvmtool) and let the core Kernel VirtIO layer
 	  take care of the needed conversions, say N.
 
+config ARM_SCMI_TRANSPORT_VIRTIO_ATOMIC_ENABLE
+	bool "Enable atomic mode for SCMI VirtIO transport"
+	depends on ARM_SCMI_TRANSPORT_VIRTIO
+	help
+	  Enable support of atomic operation for SCMI VirtIO based transport.
+
+	  If you want the SCMI VirtIO based transport to operate in atomic
+	  mode, avoiding any kind of sleeping behaviour for selected
+	  transactions on the TX path, answer Y.
+
+	  Enabling atomic mode operations allows any SCMI driver using this
+	  transport to optionally ask for atomic SCMI transactions and operate
+	  in atomic context too, at the price of using a number of busy-waiting
+	  primitives all over instead. If unsure say N.
+
 endif #ARM_SCMI_PROTOCOL
 
 config ARM_SCMI_POWER_DOMAIN

@@ -3,8 +3,8 @@
  * Virtio Transport driver for Arm System Control and Management Interface
  * (SCMI).
  *
- * Copyright (C) 2020-2021 OpenSynergy.
- * Copyright (C) 2021 ARM Ltd.
+ * Copyright (C) 2020-2022 OpenSynergy.
+ * Copyright (C) 2021-2022 ARM Ltd.
  */
 
 /**

@@ -38,6 +38,9 @@
  * @vqueue: Associated virtqueue
  * @cinfo: SCMI Tx or Rx channel
  * @free_list: List of unused scmi_vio_msg, maintained for Tx channels only
+ * @deferred_tx_work: Worker for TX deferred replies processing
+ * @deferred_tx_wq: Workqueue for TX deferred replies
+ * @pending_cmds_list: List of pre-fetched commands queueud for later processing
  * @is_rx: Whether channel is an Rx channel
  * @ready: Whether transport user is ready to hear about channel
  * @max_msg: Maximum number of pending messages for this channel.

@@ -49,6 +52,9 @@ struct scmi_vio_channel {
 	struct virtqueue *vqueue;
 	struct scmi_chan_info *cinfo;
 	struct list_head free_list;
+	struct list_head pending_cmds_list;
+	struct work_struct deferred_tx_work;
+	struct workqueue_struct *deferred_tx_wq;
 	bool is_rx;
 	bool ready;
 	unsigned int max_msg;

@@ -65,12 +71,22 @@ struct scmi_vio_channel {
  * @input: SDU used for (delayed) responses and notifications
  * @list: List which scmi_vio_msg may be part of
  * @rx_len: Input SDU size in bytes, once input has been received
+ * @poll_idx: Last used index registered for polling purposes if this message
+ *	      transaction reply was configured for polling.
+ *	      Note that since virtqueue used index is an unsigned 16-bit we can
+ *	      use some out-of-scale values to signify particular conditions.
+ * @poll_lock: Protect access to @poll_idx.
  */
 struct scmi_vio_msg {
 	struct scmi_msg_payld *request;
 	struct scmi_msg_payld *input;
 	struct list_head list;
 	unsigned int rx_len;
+#define VIO_MSG_NOT_POLLED	0xeeeeeeeeUL
+#define VIO_MSG_POLL_DONE	0xffffffffUL
+	unsigned int poll_idx;
+	/* lock to protect access to poll_idx. */
+	spinlock_t poll_lock;
 };
 
 /* Only one SCMI VirtIO device can possibly exist */

@@ -81,40 +97,43 @@ static bool scmi_vio_have_vq_rx(struct virtio_device *vdev)
 	return virtio_has_feature(vdev, VIRTIO_SCMI_F_P2A_CHANNELS);
 }
 
+/* Expect to be called with vioch->lock acquired by the caller and IRQs off */
 static int scmi_vio_feed_vq_rx(struct scmi_vio_channel *vioch,
 			       struct scmi_vio_msg *msg,
 			       struct device *dev)
 {
 	struct scatterlist sg_in;
 	int rc;
-	unsigned long flags;
 
 	sg_init_one(&sg_in, msg->input, VIRTIO_SCMI_MAX_PDU_SIZE);
 
-	spin_lock_irqsave(&vioch->lock, flags);
-
 	rc = virtqueue_add_inbuf(vioch->vqueue, &sg_in, 1, msg, GFP_ATOMIC);
 	if (rc)
 		dev_err(dev, "failed to add to RX virtqueue (%d)\n", rc);
 	else
 		virtqueue_kick(vioch->vqueue);
 
-	spin_unlock_irqrestore(&vioch->lock, flags);
-
 	return rc;
 }
 
+/* Expect to be called with vioch->lock acquired by the caller and IRQs off */
+static inline void scmi_vio_feed_vq_tx(struct scmi_vio_channel *vioch,
+				       struct scmi_vio_msg *msg)
+{
+	spin_lock(&msg->poll_lock);
+	msg->poll_idx = VIO_MSG_NOT_POLLED;
+	spin_unlock(&msg->poll_lock);
+
+	list_add(&msg->list, &vioch->free_list);
+}
+
 static void scmi_finalize_message(struct scmi_vio_channel *vioch,
 				  struct scmi_vio_msg *msg)
 {
-	if (vioch->is_rx) {
+	if (vioch->is_rx)
 		scmi_vio_feed_vq_rx(vioch, msg, vioch->cinfo->dev);
-	} else {
-		/* Here IRQs are assumed to be already disabled by the caller */
-		spin_lock(&vioch->lock);
-		list_add(&msg->list, &vioch->free_list);
-		spin_unlock(&vioch->lock);
-	}
+	else
+		scmi_vio_feed_vq_tx(vioch, msg);
 }
 
 static void scmi_vio_complete_cb(struct virtqueue *vqueue)

@@ -144,6 +163,7 @@ static void scmi_vio_complete_cb(struct virtqueue *vqueue)
 			virtqueue_disable_cb(vqueue);
 			cb_enabled = false;
 		}
+
 		msg = virtqueue_get_buf(vqueue, &length);
 		if (!msg) {
 			if (virtqueue_enable_cb(vqueue))

@@ -157,7 +177,9 @@ static void scmi_vio_complete_cb(struct virtqueue *vqueue)
 			scmi_rx_callback(vioch->cinfo,
 					 msg_read_header(msg->input), msg);
 
+			spin_lock(&vioch->lock);
 			scmi_finalize_message(vioch, msg);
+			spin_unlock(&vioch->lock);
 		}
 
 		/*

@@ -176,6 +198,34 @@ static void scmi_vio_complete_cb(struct virtqueue *vqueue)
 	spin_unlock_irqrestore(&vioch->ready_lock, ready_flags);
 }
 
+static void scmi_vio_deferred_tx_worker(struct work_struct *work)
+{
+	unsigned long flags;
+	struct scmi_vio_channel *vioch;
+	struct scmi_vio_msg *msg, *tmp;
+
+	vioch = container_of(work, struct scmi_vio_channel, deferred_tx_work);
+
+	/* Process pre-fetched messages */
+	spin_lock_irqsave(&vioch->lock, flags);
+
+	/* Scan the list of possibly pre-fetched messages during polling. */
+	list_for_each_entry_safe(msg, tmp, &vioch->pending_cmds_list, list) {
+		list_del(&msg->list);
+
+		scmi_rx_callback(vioch->cinfo,
+				 msg_read_header(msg->input), msg);
+
+		/* Free the processed message once done */
+		scmi_vio_feed_vq_tx(vioch, msg);
+	}
+
+	spin_unlock_irqrestore(&vioch->lock, flags);
+
+	/* Process possibly still pending messages */
+	scmi_vio_complete_cb(vioch->vqueue);
+}
+
 static const char *const scmi_vio_vqueue_names[] = { "tx", "rx" };
 
 static vq_callback_t *scmi_vio_complete_callbacks[] = {