dmaengine fixes for v6.9

Driver fixes for:
  - Revert pl330 issue_pending waits until WFP state due to regression
    reported in Bluetooth loading
  - Xilinx driver fixes for synchronization, buffer offsets, locking and kdoc
  - idxd fixes for spinlock and preventing the migration of the perf
    context to an invalid target
  - idma driver fix for interrupt handling when powered off
  - Tegra driver residual calculation fix
  - Owl driver register access fix
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE+vs47OPLdNbVcHzyfBQHDyUjg0cFAmYsjEcACgkQfBQHDyUj
 g0dOXA//QjGv2paJuKSQXwY0Am6ovjYVztYKKJmX42eiRPf2elt3/eRyfwrvnnNx
 6bCedPlLjt230VxQ+DQWA+U6XRSEZ55xTqu+NE8Owoqy3WuS7Q7l5p1Lx3nPMg9O
 2W0GkJ7q++i4XBnDBPSGQZqOf3sFAaM4fEv2Yq7s4qHUipyGVKUH6IKBBQFIf//q
 slw32tL77/pcViYkNLJW6fDgRY8ZnrBNuLPoWpp7DRraYxRjiPk4WAy7mA2/UnzE
 kPrPZUxJXlXVBeRcaTEjse3TkRGp6QK4XOW8XQlBIUv9IVsN1WNPQaYcTcrywBwY
 18mJt6JNLZVR/31Va/QQfYG6y1mw5Fja9fiLhT9lKqD3iBwLBzxCmrs+NUZgBneg
 sJyR/JYxnUR7d8enNfLCUwZDvCiqwHdHXjeakWNg/7gec7OG6WjpWeFd8SEbpxfU
 XGaXJTSAFpgHFbLOZvIXWn1nWarpEBBqCNz3dOHN34eCCnh5j+bx5za4k4u/jjSz
 9sZjYLO+gn8dqhPNAtIs0wkyEIECoJ8iIhd6sTTkdTKebw8REXbIbey3hY83TTb1
 PRuevuoYOBACCs4QS1Gs+8hM5gjU9qw8MVeFk5WuNxY7y2Gxeh+4NmXow/Nerd24
 +NoWibWv/pzlnWCPOfHmbEPG8QRljnLa07nXQMkLrbCbKu0DALI=
 =Q5fC
 -----END PGP SIGNATURE-----

Merge tag 'dmaengine-fix-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine fixes from Vinod Koul:

 - Revert pl330 issue_pending waits until WFP state due to regression
   reported in Bluetooth loading

 - Xilinx driver fixes for synchronization, buffer offsets, locking and
   kdoc

 - idxd fixes for spinlock and preventing the migration of the perf
   context to an invalid target

 - idma driver fix for interrupt handling when powered off

 - Tegra driver residual calculation fix

 - Owl driver register access fix

* tag 'dmaengine-fix-6.9' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine:
  dmaengine: idxd: Fix oops during rmmod on single-CPU platforms
  dmaengine: xilinx: xdma: Clarify kdoc in XDMA driver
  dmaengine: xilinx: xdma: Fix synchronization issue
  dmaengine: xilinx: xdma: Fix wrong offsets in the buffers addresses in dma descriptor
  dma: xilinx_dpdma: Fix locking
  dmaengine: idxd: Convert spinlock to mutex to lock evl workqueue
  idma64: Don't try to serve interrupts when device is powered off
  dmaengine: tegra186: Fix residual calculation
  dmaengine: owl: fix register access functions
  dmaengine: Revert "dmaengine: pl330: issue_pending waits until WFP state"

drivers/dma/idma64.c

@@ -171,6 +171,10 @@ static irqreturn_t idma64_irq(int irq, void *dev)
 	u32 status_err;
 	unsigned short i;
 
+	/* Since IRQ may be shared, check if DMA controller is powered on */
+	if (status == GENMASK(31, 0))
+		return IRQ_NONE;
+
 	dev_vdbg(idma64->dma.dev, "%s: status=%#x\n", __func__, status);
 
 	/* Check if we have any interrupt from the DMA controller */

drivers/dma/idxd/cdev.c

@@ -342,7 +342,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 	if (!evl)
 		return;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = status.tail;
 	h = status.head;
@@ -354,9 +354,8 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid)
 			set_bit(h, evl->bmap);
 		h = (h + 1) % size;
 	}
-	spin_unlock(&evl->lock);
-
 	drain_workqueue(wq->wq);
+	mutex_unlock(&evl->lock);
 }
 
 static int idxd_cdev_release(struct inode *node, struct file *filep)

drivers/dma/idxd/debugfs.c

@@ -66,7 +66,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d)
 	if (!evl || !evl->log)
 		return 0;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 
 	evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
 	t = evl_status.tail;
@@ -87,7 +87,7 @@ static int debugfs_evl_show(struct seq_file *s, void *d)
 		dump_event_entry(idxd, s, i, &count, processed);
 	}
 
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 	return 0;
 }
 

drivers/dma/idxd/device.c

@@ -775,7 +775,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd)
 		goto err_alloc;
 	}
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	evl->log = addr;
 	evl->dma = dma_addr;
 	evl->log_size = size;
@@ -796,7 +796,7 @@ static int idxd_device_evl_setup(struct idxd_device *idxd)
 	gencfg.evl_en = 1;
 	iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
 
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 	return 0;
 
 err_alloc:
@@ -819,7 +819,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	if (!gencfg.evl_en)
 		return;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	gencfg.evl_en = 0;
 	iowrite32(gencfg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
 
@@ -836,7 +836,7 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	evl_dma = evl->dma;
 	evl->log = NULL;
 	evl->size = IDXD_EVL_SIZE_MIN;
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 
 	dma_free_coherent(dev, evl_log_size, evl_log, evl_dma);
 }

drivers/dma/idxd/idxd.h

@@ -293,7 +293,7 @@ struct idxd_driver_data {
 
 struct idxd_evl {
 	/* Lock to protect event log access. */
-	spinlock_t lock;
+	struct mutex lock;
 	void *log;
 	dma_addr_t dma;
 	/* Total size of event log = number of entries * entry size. */

drivers/dma/idxd/init.c

@@ -354,7 +354,7 @@ static int idxd_init_evl(struct idxd_device *idxd)
 	if (!evl)
 		return -ENOMEM;
 
-	spin_lock_init(&evl->lock);
+	mutex_init(&evl->lock);
 	evl->size = IDXD_EVL_SIZE_MIN;
 
 	idxd_name = dev_name(idxd_confdev(idxd));

drivers/dma/idxd/irq.c

@@ -363,7 +363,7 @@ static void process_evl_entries(struct idxd_device *idxd)
 	evl_status.bits = 0;
 	evl_status.int_pending = 1;
 
-	spin_lock(&evl->lock);
+	mutex_lock(&evl->lock);
 	/* Clear interrupt pending bit */
 	iowrite32(evl_status.bits_upper32,
 		  idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32));
@@ -380,7 +380,7 @@ static void process_evl_entries(struct idxd_device *idxd)
 
 	evl_status.head = h;
 	iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET);
-	spin_unlock(&evl->lock);
+	mutex_unlock(&evl->lock);
 }
 
 irqreturn_t idxd_misc_thread(int vec, void *data)

drivers/dma/idxd/perfmon.c

@@ -528,14 +528,11 @@ static int perf_event_cpu_offline(unsigned int cpu, struct hlist_node *node)
 		return 0;
 
 	target = cpumask_any_but(cpu_online_mask, cpu);
-
 	/* migrate events if there is a valid target */
-	if (target < nr_cpu_ids)
+	if (target < nr_cpu_ids) {
 		cpumask_set_cpu(target, &perfmon_dsa_cpu_mask);
-	else
-		target = -1;
-
 		perf_pmu_migrate_context(&idxd_pmu->pmu, cpu, target);
+	}
 
 	return 0;
 }

drivers/dma/owl-dma.c

@@ -250,7 +250,7 @@ static void pchan_update(struct owl_dma_pchan *pchan, u32 reg,
 	else
 		regval &= ~val;
 
-	writel(val, pchan->base + reg);
+	writel(regval, pchan->base + reg);
 }
 
 static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data)
@@ -274,7 +274,7 @@ static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state)
 	else
 		regval &= ~val;
 
-	writel(val, od->base + reg);
+	writel(regval, od->base + reg);
 }
 
 static void dma_writel(struct owl_dma *od, u32 reg, u32 data)

drivers/dma/pl330.c

@@ -1053,9 +1053,6 @@ static bool _trigger(struct pl330_thread *thrd)
 
 	thrd->req_running = idx;
 
-	if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM)
-		UNTIL(thrd, PL330_STATE_WFP);
-
 	return true;
 }
 

drivers/dma/tegra186-gpc-dma.c

@@ -746,6 +746,9 @@ static int tegra_dma_get_residual(struct tegra_dma_channel *tdc)
 	bytes_xfer = dma_desc->bytes_xfer +
 		     sg_req[dma_desc->sg_idx].len - (wcount * 4);
 
+	if (dma_desc->bytes_req == bytes_xfer)
+		return 0;
+
 	residual = dma_desc->bytes_req - (bytes_xfer % dma_desc->bytes_req);
 
 	return residual;

drivers/dma/xilinx/xdma-regs.h

@@ -117,6 +117,9 @@ struct xdma_hw_desc {
 			 CHAN_CTRL_IE_WRITE_ERROR |			\
 			 CHAN_CTRL_IE_DESC_ERROR)
 
+/* bits of the channel status register */
+#define XDMA_CHAN_STATUS_BUSY			BIT(0)
+
 #define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
 
 #define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |	\

drivers/dma/xilinx/xdma.c

@@ -71,6 +71,8 @@ struct xdma_chan {
 	enum dma_transfer_direction	dir;
 	struct dma_slave_config		cfg;
 	u32				irq;
+	struct completion		last_interrupt;
+	bool				stop_requested;
 };
 
 /**
@@ -376,6 +378,8 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
 		return ret;
 
 	xchan->busy = true;
+	xchan->stop_requested = false;
+	reinit_completion(&xchan->last_interrupt);
 
 	return 0;
 }
@@ -387,7 +391,6 @@ static int xdma_xfer_start(struct xdma_chan *xchan)
 static int xdma_xfer_stop(struct xdma_chan *xchan)
 {
 	int ret;
-	u32 val;
 	struct xdma_device *xdev = xchan->xdev_hdl;
 
 	/* clear run stop bit to prevent any further auto-triggering */
@@ -395,13 +398,7 @@ static int xdma_xfer_stop(struct xdma_chan *xchan)
 			   CHAN_CTRL_RUN_STOP);
 	if (ret)
 		return ret;
-
-	/* Clear the channel status register */
-	ret = regmap_read(xdev->rmap, xchan->base + XDMA_CHAN_STATUS_RC, &val);
-	if (ret)
 	return ret;
-
-	return 0;
 }
 
 /**
@@ -474,6 +471,8 @@ static int xdma_alloc_channels(struct xdma_device *xdev,
 		xchan->xdev_hdl = xdev;
 		xchan->base = base + i * XDMA_CHAN_STRIDE;
 		xchan->dir = dir;
+		xchan->stop_requested = false;
+		init_completion(&xchan->last_interrupt);
 
 		ret = xdma_channel_init(xchan);
 		if (ret)
@@ -521,6 +520,7 @@ static int xdma_terminate_all(struct dma_chan *chan)
 	spin_lock_irqsave(&xdma_chan->vchan.lock, flags);
 
 	xdma_chan->busy = false;
+	xdma_chan->stop_requested = true;
 	vd = vchan_next_desc(&xdma_chan->vchan);
 	if (vd) {
 		list_del(&vd->node);
@@ -542,17 +542,26 @@ static int xdma_terminate_all(struct dma_chan *chan)
 static void xdma_synchronize(struct dma_chan *chan)
 {
 	struct xdma_chan *xdma_chan = to_xdma_chan(chan);
+	struct xdma_device *xdev = xdma_chan->xdev_hdl;
+	int st = 0;
+
+	/* If the engine continues running, wait for the last interrupt */
+	regmap_read(xdev->rmap, xdma_chan->base + XDMA_CHAN_STATUS, &st);
+	if (st & XDMA_CHAN_STATUS_BUSY)
+		wait_for_completion_timeout(&xdma_chan->last_interrupt, msecs_to_jiffies(1000));
 
 	vchan_synchronize(&xdma_chan->vchan);
 }
 
 /**
- * xdma_fill_descs - Fill hardware descriptors with contiguous memory block addresses
+ * xdma_fill_descs() - Fill hardware descriptors for one contiguous memory chunk.
- * @sw_desc: tx descriptor state container
+ *		       More than one descriptor will be used if the size is bigger
- * @src_addr: Value for a ->src_addr field of a first descriptor
+ *		       than XDMA_DESC_BLEN_MAX.
- * @dst_addr: Value for a ->dst_addr field of a first descriptor
+ * @sw_desc: Descriptor container
- * @size: Total size of a contiguous memory block
+ * @src_addr: First value for the ->src_addr field
- * @filled_descs_num: Number of filled hardware descriptors for corresponding sw_desc
+ * @dst_addr: First value for the ->dst_addr field
+ * @size: Size of the contiguous memory block
+ * @filled_descs_num: Index of the first descriptor to take care of in @sw_desc
  */
 static inline u32 xdma_fill_descs(struct xdma_desc *sw_desc, u64 src_addr,
 				  u64 dst_addr, u32 size, u32 filled_descs_num)
@@ -704,7 +713,7 @@ xdma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t address,
 	desc_num = 0;
 	for (i = 0; i < periods; i++) {
 		desc_num += xdma_fill_descs(sw_desc, *src, *dst, period_size, desc_num);
-		addr += i * period_size;
+		addr += period_size;
 	}
 
 	tx_desc = vchan_tx_prep(&xdma_chan->vchan, &sw_desc->vdesc, flags);
@@ -876,6 +885,9 @@ static irqreturn_t xdma_channel_isr(int irq, void *dev_id)
 	u32 st;
 	bool repeat_tx;
 
+	if (xchan->stop_requested)
+		complete(&xchan->last_interrupt);
+
 	spin_lock(&xchan->vchan.lock);
 
 	/* get submitted request */

drivers/dma/xilinx/xilinx_dpdma.c

@@ -214,7 +214,8 @@ struct xilinx_dpdma_tx_desc {
  * @running: true if the channel is running
  * @first_frame: flag for the first frame of stream
  * @video_group: flag if multi-channel operation is needed for video channels
- * @lock: lock to access struct xilinx_dpdma_chan
+ * @lock: lock to access struct xilinx_dpdma_chan. Must be taken before
+ *        @vchan.lock, if both are to be held.
  * @desc_pool: descriptor allocation pool
  * @err_task: error IRQ bottom half handler
  * @desc: References to descriptors being processed
@@ -1097,12 +1098,14 @@ static void xilinx_dpdma_chan_vsync_irq(struct  xilinx_dpdma_chan *chan)
 	 * Complete the active descriptor, if any, promote the pending
 	 * descriptor to active, and queue the next transfer, if any.
 	 */
+	spin_lock(&chan->vchan.lock);
 	if (chan->desc.active)
 		vchan_cookie_complete(&chan->desc.active->vdesc);
 	chan->desc.active = pending;
 	chan->desc.pending = NULL;
 
 	xilinx_dpdma_chan_queue_transfer(chan);
+	spin_unlock(&chan->vchan.lock);
 
 out:
 	spin_unlock_irqrestore(&chan->lock, flags);
@@ -1264,10 +1267,12 @@ static void xilinx_dpdma_issue_pending(struct dma_chan *dchan)
 	struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan);
 	unsigned long flags;
 
-	spin_lock_irqsave(&chan->vchan.lock, flags);
+	spin_lock_irqsave(&chan->lock, flags);
+	spin_lock(&chan->vchan.lock);
 	if (vchan_issue_pending(&chan->vchan))
 		xilinx_dpdma_chan_queue_transfer(chan);
-	spin_unlock_irqrestore(&chan->vchan.lock, flags);
+	spin_unlock(&chan->vchan.lock);
+	spin_unlock_irqrestore(&chan->lock, flags);
 }
 
 static int xilinx_dpdma_config(struct dma_chan *dchan,
@@ -1495,7 +1500,9 @@ static void xilinx_dpdma_chan_err_task(struct tasklet_struct *t)
 		    XILINX_DPDMA_EINTR_CHAN_ERR_MASK << chan->id);
 
 	spin_lock_irqsave(&chan->lock, flags);
+	spin_lock(&chan->vchan.lock);
 	xilinx_dpdma_chan_queue_transfer(chan);
+	spin_unlock(&chan->vchan.lock);
 	spin_unlock_irqrestore(&chan->lock, flags);
 }