1 files changed, 98 insertions, 80 deletions

diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index c9213ead4a2..4e3549a1613 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -34,11 +34,14 @@
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/workqueue.h>
+#include <linux/prefetch.h>
 #include <linux/i7300_idle.h>
 #include "dma.h"
 #include "registers.h"
 #include "hw.h"
 
+#include "../dmaengine.h"
+
 int ioat_pending_level = 4;
 module_param(ioat_pending_level, int, 0644);
 MODULE_PARM_DESC(ioat_pending_level,
@@ -74,7 +77,8 @@ static irqreturn_t ioat_dma_do_interrupt(int irq, void *data)
 	attnstatus = readl(instance->reg_base + IOAT_ATTNSTATUS_OFFSET);
 	for_each_set_bit(bit, &attnstatus, BITS_PER_LONG) {
 		chan = ioat_chan_by_index(instance, bit);
-		tasklet_schedule(&chan->cleanup_task);
+		if (test_bit(IOAT_RUN, &chan->state))
+			tasklet_schedule(&chan->cleanup_task);
 	}
 
 	writeb(intrctrl, instance->reg_base + IOAT_INTRCTRL_OFFSET);
@@ -90,7 +94,8 @@ static irqreturn_t ioat_dma_do_interrupt_msix(int irq, void *data)
 {
 	struct ioat_chan_common *chan = data;
 
-	tasklet_schedule(&chan->cleanup_task);
+	if (test_bit(IOAT_RUN, &chan->state))
+		tasklet_schedule(&chan->cleanup_task);
 
 	return IRQ_HANDLED;
 }
@@ -106,13 +111,13 @@ void ioat_init_channel(struct ioatdma_device *device, struct ioat_chan_common *c
 	chan->reg_base = device->reg_base + (0x80 * (idx + 1));
 	spin_lock_init(&chan->cleanup_lock);
 	chan->common.device = dma;
+	dma_cookie_init(&chan->common);
 	list_add_tail(&chan->common.device_node, &dma->channels);
 	device->idx[idx] = chan;
 	init_timer(&chan->timer);
 	chan->timer.function = device->timer_fn;
 	chan->timer.data = data;
 	tasklet_init(&chan->cleanup_task, device->cleanup_fn, data);
-	tasklet_disable(&chan->cleanup_task);
 }
 
 /**
@@ -234,12 +239,7 @@ static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
 
 	spin_lock_bh(&ioat->desc_lock);
 	/* cookie incr and addition to used_list must be atomic */
-	cookie = c->cookie;
-	cookie++;
-	if (cookie < 0)
-		cookie = 1;
-	c->cookie = cookie;
-	tx->cookie = cookie;
+	cookie = dma_cookie_assign(tx);
 	dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
 	/* write address into NextDescriptor field of last desc in chain */
@@ -355,13 +355,49 @@ static int ioat1_dma_alloc_chan_resources(struct dma_chan *c)
 	writel(((u64) chan->completion_dma) >> 32,
 	       chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
 
-	tasklet_enable(&chan->cleanup_task);
+	set_bit(IOAT_RUN, &chan->state);
 	ioat1_dma_start_null_desc(ioat);  /* give chain to dma device */
 	dev_dbg(to_dev(chan), "%s: allocated %d descriptors\n",
 		__func__, ioat->desccount);
 	return ioat->desccount;
 }
 
+void ioat_stop(struct ioat_chan_common *chan)
+{
+	struct ioatdma_device *device = chan->device;
+	struct pci_dev *pdev = device->pdev;
+	int chan_id = chan_num(chan);
+	struct msix_entry *msix;
+
+	/* 1/ stop irq from firing tasklets
+	 * 2/ stop the tasklet from re-arming irqs
+	 */
+	clear_bit(IOAT_RUN, &chan->state);
+
+	/* flush inflight interrupts */
+	switch (device->irq_mode) {
+	case IOAT_MSIX:
+		msix = &device->msix_entries[chan_id];
+		synchronize_irq(msix->vector);
+		break;
+	case IOAT_MSI:
+	case IOAT_INTX:
+		synchronize_irq(pdev->irq);
+		break;
+	default:
+		break;
+	}
+
+	/* flush inflight timers */
+	del_timer_sync(&chan->timer);
+
+	/* flush inflight tasklet runs */
+	tasklet_kill(&chan->cleanup_task);
+
+	/* final cleanup now that everything is quiesced and can't re-arm */
+	device->cleanup_fn((unsigned long) &chan->common);
+}
+
 /**
  * ioat1_dma_free_chan_resources - release all the descriptors
  * @chan: the channel to be cleaned
@@ -380,9 +416,7 @@ static void ioat1_dma_free_chan_resources(struct dma_chan *c)
 	if (ioat->desccount == 0)
 		return;
 
-	tasklet_disable(&chan->cleanup_task);
-	del_timer_sync(&chan->timer);
-	ioat1_cleanup(ioat);
+	ioat_stop(chan);
 
 	/* Delay 100ms after reset to allow internal DMA logic to quiesce
 	 * before removing DMA descriptor resources.
@@ -527,29 +561,17 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
 static void ioat1_cleanup_event(unsigned long data)
 {
 	struct ioat_dma_chan *ioat = to_ioat_chan((void *) data);
+	struct ioat_chan_common *chan = &ioat->base;
 
 	ioat1_cleanup(ioat);
+	if (!test_bit(IOAT_RUN, &chan->state))
+		return;
 	writew(IOAT_CHANCTRL_RUN, ioat->base.reg_base + IOAT_CHANCTRL_OFFSET);
 }
 
-void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
-		    size_t len, struct ioat_dma_descriptor *hw)
+dma_addr_t ioat_get_current_completion(struct ioat_chan_common *chan)
 {
-	struct pci_dev *pdev = chan->device->pdev;
-	size_t offset = len - hw->size;
-
-	if (!(flags & DMA_COMPL_SKIP_DEST_UNMAP))
-		ioat_unmap(pdev, hw->dst_addr - offset, len,
-			   PCI_DMA_FROMDEVICE, flags, 1);
-
-	if (!(flags & DMA_COMPL_SKIP_SRC_UNMAP))
-		ioat_unmap(pdev, hw->src_addr - offset, len,
-			   PCI_DMA_TODEVICE, flags, 0);
-}
-
-unsigned long ioat_get_current_completion(struct ioat_chan_common *chan)
-{
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 	u64 completion;
 
 	completion = *chan->completion;
@@ -570,7 +592,7 @@ unsigned long ioat_get_current_completion(struct ioat_chan_common *chan)
 }
 
 bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
-			   unsigned long *phys_complete)
+			   dma_addr_t *phys_complete)
 {
 	*phys_complete = ioat_get_current_completion(chan);
 	if (*phys_complete == chan->last_completion)
@@ -581,14 +603,14 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
 	return true;
 }
 
-static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete)
+static void __cleanup(struct ioat_dma_chan *ioat, dma_addr_t phys_complete)
 {
 	struct ioat_chan_common *chan = &ioat->base;
 	struct list_head *_desc, *n;
 	struct dma_async_tx_descriptor *tx;
 
-	dev_dbg(to_dev(chan), "%s: phys_complete: %lx\n",
-		 __func__, phys_complete);
+	dev_dbg(to_dev(chan), "%s: phys_complete: %llx\n",
+		 __func__, (unsigned long long) phys_complete);
 	list_for_each_safe(_desc, n, &ioat->used_desc) {
 		struct ioat_desc_sw *desc;
 
@@ -602,9 +624,8 @@ static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete)
 		 */
 		dump_desc_dbg(ioat, desc);
 		if (tx->cookie) {
-			chan->completed_cookie = tx->cookie;
-			tx->cookie = 0;
-			ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
+			dma_cookie_complete(tx);
+			dma_descriptor_unmap(tx);
 			ioat->active -= desc->hw->tx_cnt;
 			if (tx->callback) {
 				tx->callback(tx->callback_param);
@@ -654,7 +675,7 @@ static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete)
 static void ioat1_cleanup(struct ioat_dma_chan *ioat)
 {
 	struct ioat_chan_common *chan = &ioat->base;
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 
 	prefetch(chan->completion);
 
@@ -700,7 +721,7 @@ static void ioat1_timer_event(unsigned long data)
 		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
 		spin_unlock_bh(&ioat->desc_lock);
 	} else if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
-		unsigned long phys_complete;
+		dma_addr_t phys_complete;
 
 		spin_lock_bh(&ioat->desc_lock);
 		/* if we haven't made progress and we have already
@@ -732,13 +753,15 @@ ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 {
 	struct ioat_chan_common *chan = to_chan_common(c);
 	struct ioatdma_device *device = chan->device;
+	enum dma_status ret;
 
-	if (ioat_tx_status(c, cookie, txstate) == DMA_SUCCESS)
-		return DMA_SUCCESS;
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
 
 	device->cleanup_fn((unsigned long) c);
 
-	return ioat_tx_status(c, cookie, txstate);
+	return dma_cookie_status(c, cookie, txstate);
 }
 
 static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat)
@@ -782,7 +805,7 @@ static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat)
  */
 #define IOAT_TEST_SIZE 2000
 
-static void __devinit ioat_dma_test_callback(void *dma_async_param)
+static void ioat_dma_test_callback(void *dma_async_param)
 {
 	struct completion *cmp = dma_async_param;
 
@@ -793,7 +816,7 @@ static void __devinit ioat_dma_test_callback(void *dma_async_param)
  * ioat_dma_self_test - Perform a IOAT transaction to verify the HW works.
  * @device: device to be tested
  */
-int __devinit ioat_dma_self_test(struct ioatdma_device *device)
+int ioat_dma_self_test(struct ioatdma_device *device)
 {
 	int i;
 	u8 *src;
@@ -832,15 +855,22 @@ int __devinit ioat_dma_self_test(struct ioatdma_device *device)
 	}
 
 	dma_src = dma_map_single(dev, src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev, dma_src)) {
+		dev_err(dev, "mapping src buffer failed\n");
+		goto free_resources;
+	}
 	dma_dest = dma_map_single(dev, dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
-	flags = DMA_COMPL_SRC_UNMAP_SINGLE | DMA_COMPL_DEST_UNMAP_SINGLE |
-		DMA_PREP_INTERRUPT;
+	if (dma_mapping_error(dev, dma_dest)) {
+		dev_err(dev, "mapping dest buffer failed\n");
+		goto unmap_src;
+	}
+	flags = DMA_PREP_INTERRUPT;
 	tx = device->common.device_prep_dma_memcpy(dma_chan, dma_dest, dma_src,
 						   IOAT_TEST_SIZE, flags);
 	if (!tx) {
 		dev_err(dev, "Self-test prep failed, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 
 	async_tx_ack(tx);
@@ -851,7 +881,7 @@ int __devinit ioat_dma_self_test(struct ioatdma_device *device)
 	if (cookie < 0) {
 		dev_err(dev, "Self-test setup failed, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 	dma->device_issue_pending(dma_chan);
 
@@ -859,10 +889,10 @@ int __devinit ioat_dma_self_test(struct ioatdma_device *device)
 
 	if (tmo == 0 ||
 	    dma->device_tx_status(dma_chan, cookie, NULL)
-					!= DMA_SUCCESS) {
+					!= DMA_COMPLETE) {
 		dev_err(dev, "Self-test copy timed out, disabling\n");
 		err = -ENODEV;
-		goto free_resources;
+		goto unmap_dma;
 	}
 	if (memcmp(src, dest, IOAT_TEST_SIZE)) {
 		dev_err(dev, "Self-test copy failed compare, disabling\n");
@@ -870,6 +900,10 @@ int __devinit ioat_dma_self_test(struct ioatdma_device *device)
 		goto free_resources;
 	}
 
+unmap_dma:
+	dma_unmap_single(dev, dma_dest, IOAT_TEST_SIZE, DMA_FROM_DEVICE);
+unmap_src:
+	dma_unmap_single(dev, dma_src, IOAT_TEST_SIZE, DMA_TO_DEVICE);
 free_resources:
 	dma->device_free_chan_resources(dma_chan);
 out:
@@ -882,14 +916,13 @@ static char ioat_interrupt_style[32] = "msix";
 module_param_string(ioat_interrupt_style, ioat_interrupt_style,
 		    sizeof(ioat_interrupt_style), 0644);
 MODULE_PARM_DESC(ioat_interrupt_style,
-		 "set ioat interrupt style: msix (default), "
-		 "msix-single-vector, msi, intx)");
+		 "set ioat interrupt style: msix (default), msi, intx");
 
 /**
  * ioat_dma_setup_interrupts - setup interrupt handler
  * @device: ioat device
  */
-static int ioat_dma_setup_interrupts(struct ioatdma_device *device)
+int ioat_dma_setup_interrupts(struct ioatdma_device *device)
 {
 	struct ioat_chan_common *chan;
 	struct pci_dev *pdev = device->pdev;
@@ -901,8 +934,6 @@ static int ioat_dma_setup_interrupts(struct ioatdma_device *device)
 
 	if (!strcmp(ioat_interrupt_style, "msix"))
 		goto msix;
-	if (!strcmp(ioat_interrupt_style, "msix-single-vector"))
-		goto msix_single_vector;
 	if (!strcmp(ioat_interrupt_style, "msi"))
 		goto msi;
 	if (!strcmp(ioat_interrupt_style, "intx"))
@@ -917,10 +948,8 @@ msix:
 		device->msix_entries[i].entry = i;
 
 	err = pci_enable_msix(pdev, device->msix_entries, msixcnt);
-	if (err < 0)
+	if (err)
 		goto msi;
-	if (err > 0)
-		goto msix_single_vector;
 
 	for (i = 0; i < msixcnt; i++) {
 		msix = &device->msix_entries[i];
@@ -934,25 +963,11 @@ msix:
 				chan = ioat_chan_by_index(device, j);
 				devm_free_irq(dev, msix->vector, chan);
 			}
-			goto msix_single_vector;
+			goto msi;
 		}
 	}
 	intrctrl |= IOAT_INTRCTRL_MSIX_VECTOR_CONTROL;
-	goto done;
-
-msix_single_vector:
-	msix = &device->msix_entries[0];
-	msix->entry = 0;
-	err = pci_enable_msix(pdev, device->msix_entries, 1);
-	if (err)
-		goto msi;
-
-	err = devm_request_irq(dev, msix->vector, ioat_dma_do_interrupt, 0,
-			       "ioat-msix", device);
-	if (err) {
-		pci_disable_msix(pdev);
-		goto msi;
-	}
+	device->irq_mode = IOAT_MSIX;
 	goto done;
 
 msi:
@@ -966,6 +981,7 @@ msi:
 		pci_disable_msi(pdev);
 		goto intx;
 	}
+	device->irq_mode = IOAT_MSI;
 	goto done;
 
 intx:
@@ -974,6 +990,7 @@ intx:
 	if (err)
 		goto err_no_irq;
 
+	device->irq_mode = IOAT_INTX;
 done:
 	if (device->intr_quirk)
 		device->intr_quirk(device);
@@ -984,9 +1001,11 @@ done:
 err_no_irq:
 	/* Disable all interrupt generation */
 	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
+	device->irq_mode = IOAT_NOIRQ;
 	dev_err(dev, "no usable interrupts\n");
 	return err;
 }
+EXPORT_SYMBOL(ioat_dma_setup_interrupts);
 
 static void ioat_disable_interrupts(struct ioatdma_device *device)
 {
@@ -994,7 +1013,7 @@ static void ioat_disable_interrupts(struct ioatdma_device *device)
 	writeb(0, device->reg_base + IOAT_INTRCTRL_OFFSET);
 }
 
-int __devinit ioat_probe(struct ioatdma_device *device)
+int ioat_probe(struct ioatdma_device *device)
 {
 	int err = -ENODEV;
 	struct dma_device *dma = &device->common;
@@ -1049,7 +1068,7 @@ err_dma_pool:
 	return err;
 }
 
-int __devinit ioat_register(struct ioatdma_device *device)
+int ioat_register(struct ioatdma_device *device)
 {
 	int err = dma_async_device_register(&device->common);
 
@@ -1096,12 +1115,11 @@ static ssize_t cap_show(struct dma_chan *c, char *page)
 {
 	struct dma_device *dma = c->device;
 
-	return sprintf(page, "copy%s%s%s%s%s%s\n",
+	return sprintf(page, "copy%s%s%s%s%s\n",
 		       dma_has_cap(DMA_PQ, dma->cap_mask) ? " pq" : "",
 		       dma_has_cap(DMA_PQ_VAL, dma->cap_mask) ? " pq_val" : "",
 		       dma_has_cap(DMA_XOR, dma->cap_mask) ? " xor" : "",
 		       dma_has_cap(DMA_XOR_VAL, dma->cap_mask) ? " xor_val" : "",
-		       dma_has_cap(DMA_MEMSET, dma->cap_mask)  ? " fill" : "",
 		       dma_has_cap(DMA_INTERRUPT, dma->cap_mask) ? " intr" : "");
 
 }
@@ -1183,7 +1201,7 @@ void ioat_kobject_del(struct ioatdma_device *device)
 	}
 }
 
-int __devinit ioat1_dma_probe(struct ioatdma_device *device, int dca)
+int ioat1_dma_probe(struct ioatdma_device *device, int dca)
 {
 	struct pci_dev *pdev = device->pdev;
 	struct dma_device *dma;
@@ -1216,7 +1234,7 @@ int __devinit ioat1_dma_probe(struct ioatdma_device *device, int dca)
 	return err;
 }
 
-void __devexit ioat_dma_remove(struct ioatdma_device *device)
+void ioat_dma_remove(struct ioatdma_device *device)
 {
 	struct dma_device *dma = &device->common;