Merge tag 'dmaengine-fix-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine fixes from Vinod Koul:
 "Misc minor driver fixes and a big pile of at_hdmac driver fixes. More
  work on this driver is done and sitting in next:

   - Pile of at_hdmac driver rework which fixes many long standing
     issues for this driver.

   - couple of stm32 driver fixes for clearing structure and race fix

   - idxd fixes for RO device state and batch size

   - ti driver mem leak fix

   - apple fix for grabbing channels in xlate

   - resource leak fix in mv xor"

* tag 'dmaengine-fix-6.1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (24 commits)
  dmaengine: at_hdmac: Check return code of dma_async_device_register
  dmaengine: at_hdmac: Fix impossible condition
  dmaengine: at_hdmac: Don't allow CPU to reorder channel enable
  dmaengine: at_hdmac: Fix completion of unissued descriptor in case of errors
  dmaengine: at_hdmac: Fix descriptor handling when issuing it to hardware
  dmaengine: at_hdmac: Fix concurrency over the active list
  dmaengine: at_hdmac: Free the memset buf without holding the chan lock
  dmaengine: at_hdmac: Fix concurrency over descriptor
  dmaengine: at_hdmac: Fix concurrency problems by removing atc_complete_all()
  dmaengine: at_hdmac: Protect atchan->status with the channel lock
  dmaengine: at_hdmac: Do not call the complete callback on device_terminate_all
  dmaengine: at_hdmac: Fix premature completion of desc in issue_pending
  dmaengine: at_hdmac: Start transfer for cyclic channels in issue_pending
  dmaengine: at_hdmac: Don't start transactions at tx_submit level
  dmaengine: at_hdmac: Fix at_lli struct definition
  dmaengine: stm32-dma: fix potential race between pause and resume
  dmaengine: ti: k3-udma-glue: fix memory leak when register device fail
  dmaengine: mv_xor_v2: Fix a resource leak in mv_xor_v2_remove()
  dmaengine: apple-admac: Fix grabbing of channels in of_xlate
  dmaengine: idxd: fix RO device state error after been disabled/reset
  ...

Author: torvalds

drivers/dma/apple-admac.c

@@ -493,7 +493,7 @@ static struct dma_chan *admac_dma_of_xlate(struct of_phandle_args *dma_spec,
 		return NULL;
 	}
 
-	return &ad->channels[index].chan;
+	return dma_get_slave_channel(&ad->channels[index].chan);
 }
 
 static int admac_drain_reports(struct admac_data *ad, int channo)

drivers/dma/at_hdmac.c

@@ -256,6 +256,8 @@ static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first)
 		       ATC_SPIP_BOUNDARY(first->boundary));
 	channel_writel(atchan, DPIP, ATC_DPIP_HOLE(first->dst_hole) |
 		       ATC_DPIP_BOUNDARY(first->boundary));
+	/* Don't allow CPU to reorder channel enable. */
+	wmb();
 	dma_writel(atdma, CHER, atchan->mask);
 
 	vdbg_dump_regs(atchan);
@@ -316,7 +318,8 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 	struct at_desc *desc_first = atc_first_active(atchan);
 	struct at_desc *desc;
 	int ret;
-	u32 ctrla, dscr, trials;
+	u32 ctrla, dscr;
+	unsigned int i;
 
 	/*
 	 * If the cookie doesn't match to the currently running transfer then
@@ -386,7 +389,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		dscr = channel_readl(atchan, DSCR);
 		rmb(); /* ensure DSCR is read before CTRLA */
 		ctrla = channel_readl(atchan, CTRLA);
-		for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) {
+		for (i = 0; i < ATC_MAX_DSCR_TRIALS; ++i) {
 			u32 new_dscr;
 
 			rmb(); /* ensure DSCR is read after CTRLA */
@@ -412,7 +415,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 			rmb(); /* ensure DSCR is read before CTRLA */
 			ctrla = channel_readl(atchan, CTRLA);
 		}
-		if (unlikely(trials >= ATC_MAX_DSCR_TRIALS))
+		if (unlikely(i == ATC_MAX_DSCR_TRIALS))
 			return -ETIMEDOUT;
 
 		/* for the first descriptor we can be more accurate */
@@ -462,18 +465,6 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	if (!atc_chan_is_cyclic(atchan))
 		dma_cookie_complete(txd);
 
-	/* If the transfer was a memset, free our temporary buffer */
-	if (desc->memset_buffer) {
-		dma_pool_free(atdma->memset_pool, desc->memset_vaddr,
-			      desc->memset_paddr);
-		desc->memset_buffer = false;
-	}
-
-	/* move children to free_list */
-	list_splice_init(&desc->tx_list, &atchan->free_list);
-	/* move myself to free_list */
-	list_move(&desc->desc_node, &atchan->free_list);
-
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
 	dma_descriptor_unmap(txd);
@@ -483,42 +474,20 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 		dmaengine_desc_get_callback_invoke(txd, NULL);
 
 	dma_run_dependencies(txd);
-}
-
-/**
- * atc_complete_all - finish work for all transactions
- * @atchan: channel to complete transactions for
- *
- * Eventually submit queued descriptors if any
- *
- * Assume channel is idle while calling this function
- * Called with atchan->lock held and bh disabled
- */
-static void atc_complete_all(struct at_dma_chan *atchan)
-{
-	struct at_desc *desc, *_desc;
-	LIST_HEAD(list);
-	unsigned long flags;
-
-	dev_vdbg(chan2dev(&atchan->chan_common), "complete all\n");
 
 	spin_lock_irqsave(&atchan->lock, flags);
-
-	/*
-	 * Submit queued descriptors ASAP, i.e. before we go through
-	 * the completed ones.
-	 */
-	if (!list_empty(&atchan->queue))
-		atc_dostart(atchan, atc_first_queued(atchan));
-	/* empty active_list now it is completed */
-	list_splice_init(&atchan->active_list, &list);
-	/* empty queue list by moving descriptors (if any) to active_list */
-	list_splice_init(&atchan->queue, &atchan->active_list);
-
+	/* move children to free_list */
+	list_splice_init(&desc->tx_list, &atchan->free_list);
+	/* add myself to free_list */
+	list_add(&desc->desc_node, &atchan->free_list);
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
-	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		atc_chain_complete(atchan, desc);
+	/* If the transfer was a memset, free our temporary buffer */
+	if (desc->memset_buffer) {
+		dma_pool_free(atdma->memset_pool, desc->memset_vaddr,
+			      desc->memset_paddr);
+		desc->memset_buffer = false;
+	}
 }
 
 /**
@@ -527,26 +496,28 @@ static void atc_complete_all(struct at_dma_chan *atchan)
  */
 static void atc_advance_work(struct at_dma_chan *atchan)
 {
+	struct at_desc *desc;
 	unsigned long flags;
-	int ret;
 
 	dev_vdbg(chan2dev(&atchan->chan_common), "advance_work\n");
 
 	spin_lock_irqsave(&atchan->lock, flags);
-	ret = atc_chan_is_enabled(atchan);
-	spin_unlock_irqrestore(&atchan->lock, flags);
-	if (ret)
-		return;
-
-	if (list_empty(&atchan->active_list) ||
-	    list_is_singular(&atchan->active_list))
-		return atc_complete_all(atchan);
+	if (atc_chan_is_enabled(atchan) || list_empty(&atchan->active_list))
+		return spin_unlock_irqrestore(&atchan->lock, flags);
 
-	atc_chain_complete(atchan, atc_first_active(atchan));
+	desc = atc_first_active(atchan);
+	/* Remove the transfer node from the active list. */
+	list_del_init(&desc->desc_node);
+	spin_unlock_irqrestore(&atchan->lock, flags);
+	atc_chain_complete(atchan, desc);
 
 	/* advance work */
 	spin_lock_irqsave(&atchan->lock, flags);
-	atc_dostart(atchan, atc_first_active(atchan));
+	if (!list_empty(&atchan->active_list)) {
+		desc = atc_first_queued(atchan);
+		list_move_tail(&desc->desc_node, &atchan->active_list);
+		atc_dostart(atchan, desc);
+	}
 	spin_unlock_irqrestore(&atchan->lock, flags);
 }
 
@@ -558,6 +529,7 @@ static void atc_advance_work(struct at_dma_chan *atchan)
 static void atc_handle_error(struct at_dma_chan *atchan)
 {
 	struct at_desc *bad_desc;
+	struct at_desc *desc;
 	struct at_desc *child;
 	unsigned long flags;
 
@@ -570,13 +542,12 @@ static void atc_handle_error(struct at_dma_chan *atchan)
 	bad_desc = atc_first_active(atchan);
 	list_del_init(&bad_desc->desc_node);
 
-	/* As we are stopped, take advantage to push queued descriptors
-	 * in active_list */
-	list_splice_init(&atchan->queue, atchan->active_list.prev);
-
 	/* Try to restart the controller */
-	if (!list_empty(&atchan->active_list))
-		atc_dostart(atchan, atc_first_active(atchan));
+	if (!list_empty(&atchan->active_list)) {
+		desc = atc_first_queued(atchan);
+		list_move_tail(&desc->desc_node, &atchan->active_list);
+		atc_dostart(atchan, desc);
+	}
 
 	/*
 	 * KERN_CRITICAL may seem harsh, but since this only happens
@@ -691,19 +662,11 @@ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx)
 	spin_lock_irqsave(&atchan->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	if (list_empty(&atchan->active_list)) {
-		dev_vdbg(chan2dev(tx->chan), "tx_submit: started %u\n",
-				desc->txd.cookie);
-		atc_dostart(atchan, desc);
-		list_add_tail(&desc->desc_node, &atchan->active_list);
-	} else {
-		dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
-				desc->txd.cookie);
-		list_add_tail(&desc->desc_node, &atchan->queue);
-	}
-
+	list_add_tail(&desc->desc_node, &atchan->queue);
 	spin_unlock_irqrestore(&atchan->lock, flags);
 
+	dev_vdbg(chan2dev(tx->chan), "tx_submit: queued %u\n",
+		 desc->txd.cookie);
 	return cookie;
 }
 
@@ -1445,11 +1408,8 @@ static int atc_terminate_all(struct dma_chan *chan)
 	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
 	struct at_dma		*atdma = to_at_dma(chan->device);
 	int			chan_id = atchan->chan_common.chan_id;
-	struct at_desc		*desc, *_desc;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	/*
@@ -1468,19 +1428,15 @@ static int atc_terminate_all(struct dma_chan *chan)
 		cpu_relax();
 
 	/* active_list entries will end up before queued entries */
-	list_splice_init(&atchan->queue, &list);
-	list_splice_init(&atchan->active_list, &list);
-
-	spin_unlock_irqrestore(&atchan->lock, flags);
-
-	/* Flush all pending and queued descriptors */
-	list_for_each_entry_safe(desc, _desc, &list, desc_node)
-		atc_chain_complete(atchan, desc);
+	list_splice_tail_init(&atchan->queue, &atchan->free_list);
+	list_splice_tail_init(&atchan->active_list, &atchan->free_list);
 
 	clear_bit(ATC_IS_PAUSED, &atchan->status);
 	/* if channel dedicated to cyclic operations, free it */
 	clear_bit(ATC_IS_CYCLIC, &atchan->status);
 
+	spin_unlock_irqrestore(&atchan->lock, flags);
+
 	return 0;
 }
 
@@ -1535,20 +1491,26 @@ atc_tx_status(struct dma_chan *chan,
 }
 
 /**
- * atc_issue_pending - try to finish work
+ * atc_issue_pending - takes the first transaction descriptor in the pending
+ * queue and starts the transfer.
  * @chan: target DMA channel
  */
 static void atc_issue_pending(struct dma_chan *chan)
 {
-	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma_chan *atchan = to_at_dma_chan(chan);
+	struct at_desc *desc;
+	unsigned long flags;
 
 	dev_vdbg(chan2dev(chan), "issue_pending\n");
 
-	/* Not needed for cyclic transfers */
-	if (atc_chan_is_cyclic(atchan))
-		return;
+	spin_lock_irqsave(&atchan->lock, flags);
+	if (atc_chan_is_enabled(atchan) || list_empty(&atchan->queue))
+		return spin_unlock_irqrestore(&atchan->lock, flags);
 
-	atc_advance_work(atchan);
+	desc = atc_first_queued(atchan);
+	list_move_tail(&desc->desc_node, &atchan->active_list);
+	atc_dostart(atchan, desc);
+	spin_unlock_irqrestore(&atchan->lock, flags);
 }
 
 /**
@@ -1966,7 +1928,11 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	  dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)  ? "slave " : "",
 	  plat_dat->nr_channels);
 
-	dma_async_device_register(&atdma->dma_common);
+	err = dma_async_device_register(&atdma->dma_common);
+	if (err) {
+		dev_err(&pdev->dev, "Unable to register: %d.\n", err);
+		goto err_dma_async_device_register;
+	}
 
 	/*
 	 * Do not return an error if the dmac node is not present in order to
@@ -1986,6 +1952,7 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 err_of_dma_controller_register:
 	dma_async_device_unregister(&atdma->dma_common);
+err_dma_async_device_register:
 	dma_pool_destroy(atdma->memset_pool);
 err_memset_pool_create:
 	dma_pool_destroy(atdma->dma_desc_pool);

drivers/dma/at_hdmac_regs.h

@@ -186,13 +186,13 @@
 /* LLI == Linked List Item; aka DMA buffer descriptor */
 struct at_lli {
 	/* values that are not changed by hardware */
-	dma_addr_t	saddr;
-	dma_addr_t	daddr;
+	u32 saddr;
+	u32 daddr;
 	/* value that may get written back: */
-	u32		ctrla;
+	u32 ctrla;
 	/* more values that are not changed by hardware */
-	u32		ctrlb;
-	dma_addr_t	dscr;	/* chain to next lli */
+	u32 ctrlb;
+	u32 dscr;	/* chain to next lli */
 };
 
 /**

drivers/dma/idxd/cdev.c

@@ -312,6 +312,24 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev)
 	if (idxd->state != IDXD_DEV_ENABLED)
 		return -ENXIO;
 
+	/*
+	 * User type WQ is enabled only when SVA is enabled for two reasons:
+	 *   - If no IOMMU or IOMMU Passthrough without SVA, userspace
+	 *     can directly access physical address through the WQ.
+	 *   - The IDXD cdev driver does not provide any ways to pin
+	 *     user pages and translate the address from user VA to IOVA or
+	 *     PA without IOMMU SVA. Therefore the application has no way
+	 *     to instruct the device to perform DMA function. This makes
+	 *     the cdev not usable for normal application usage.
+	 */
+	if (!device_user_pasid_enabled(idxd)) {
+		idxd->cmd_status = IDXD_SCMD_WQ_USER_NO_IOMMU;
+		dev_dbg(&idxd->pdev->dev,
+			"User type WQ cannot be enabled without SVA.\n");
+
+		return -EOPNOTSUPP;
+	}
+
 	mutex_lock(&wq->wq_lock);
 	wq->type = IDXD_WQT_USER;
 	rc = drv_enable_wq(wq);

drivers/dma/idxd/device.c

@@ -390,7 +390,7 @@ static void idxd_wq_disable_cleanup(struct idxd_wq *wq)
 	clear_bit(WQ_FLAG_ATS_DISABLE, &wq->flags);
 	memset(wq->name, 0, WQ_NAME_SIZE);
 	wq->max_xfer_bytes = WQ_DEFAULT_MAX_XFER;
-	wq->max_batch_size = WQ_DEFAULT_MAX_BATCH;
+	idxd_wq_set_max_batch_size(idxd->data->type, wq, WQ_DEFAULT_MAX_BATCH);
 	if (wq->opcap_bmap)
 		bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS);
 }
@@ -730,13 +730,21 @@ static void idxd_device_wqs_clear_state(struct idxd_device *idxd)
 
 void idxd_device_clear_state(struct idxd_device *idxd)
 {
-	if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
-		return;
+	/* IDXD is always disabled. Other states are cleared only when IDXD is configurable. */
+	if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) {
+		/*
+		 * Clearing wq state is protected by wq lock.
+		 * So no need to be protected by device lock.
+		 */
+		idxd_device_wqs_clear_state(idxd);
+
+		spin_lock(&idxd->dev_lock);
+		idxd_groups_clear_state(idxd);
+		idxd_engines_clear_state(idxd);
+	} else {
+		spin_lock(&idxd->dev_lock);
+	}
 
-	idxd_device_wqs_clear_state(idxd);
-	spin_lock(&idxd->dev_lock);
-	idxd_groups_clear_state(idxd);
-	idxd_engines_clear_state(idxd);
 	idxd->state = IDXD_DEV_DISABLED;
 	spin_unlock(&idxd->dev_lock);
 }
@@ -869,7 +877,7 @@ static int idxd_wq_config_write(struct idxd_wq *wq)
 
 	/* bytes 12-15 */
 	wq->wqcfg->max_xfer_shift = ilog2(wq->max_xfer_bytes);
-	wq->wqcfg->max_batch_shift = ilog2(wq->max_batch_size);
+	idxd_wqcfg_set_max_batch_shift(idxd->data->type, wq->wqcfg, ilog2(wq->max_batch_size));
 
 	/* bytes 32-63 */
 	if (idxd->hw.wq_cap.op_config && wq->opcap_bmap) {
@@ -1051,7 +1059,7 @@ static int idxd_wq_load_config(struct idxd_wq *wq)
 	wq->priority = wq->wqcfg->priority;
 
 	wq->max_xfer_bytes = 1ULL << wq->wqcfg->max_xfer_shift;
-	wq->max_batch_size = 1ULL << wq->wqcfg->max_batch_shift;
+	idxd_wq_set_max_batch_size(idxd->data->type, wq, 1U << wq->wqcfg->max_batch_shift);
 
 	for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
 		wqcfg_offset = WQCFG_OFFSET(idxd, wq->id, i);