#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/workqueue.h>
+#include <linux/i7300_idle.h>
#include "ioatdma.h"
#include "ioatdma_registers.h"
#include "ioatdma_hw.h"
static void ioat_dma_chan_reset_part2(struct work_struct *work);
static void ioat_dma_chan_watchdog(struct work_struct *work);
+/*
+ * workaround for IOAT ver.3.0 null descriptor issue
+ * (channel returns error when size is 0)
+ */
+#define NULL_DESC_BUFFER_SIZE 1
+
/* internal functions */
static void ioat_dma_start_null_desc(struct ioat_dma_chan *ioat_chan);
static void ioat_dma_memcpy_cleanup(struct ioat_dma_chan *ioat_chan);
int i;
struct ioat_dma_chan *ioat_chan;
+ /*
+ * IOAT ver.3 workarounds
+ */
+ if (device->version == IOAT_VER_3_0) {
+ u32 chan_err_mask;
+ u16 dev_id;
+ u32 dmauncerrsts;
+
+ /*
+ * Write CHANERRMSK_INT with 3E07h to mask out the errors
+ * that can cause stability issues for IOAT ver.3
+ */
+ chan_err_mask = 0x3E07;
+ pci_write_config_dword(device->pdev,
+ IOAT_PCI_CHANERRMASK_INT_OFFSET,
+ chan_err_mask);
+
+ /*
+ * Clear DMAUNCERRSTS Cfg-Reg Parity Error status bit
+ * (workaround for spurious config parity error after restart)
+ */
+ pci_read_config_word(device->pdev,
+ IOAT_PCI_DEVICE_ID_OFFSET,
+ &dev_id);
+ if (dev_id == PCI_DEVICE_ID_INTEL_IOAT_TBG0) {
+ dmauncerrsts = 0x10;
+ pci_write_config_dword(device->pdev,
+ IOAT_PCI_DMAUNCERRSTS_OFFSET,
+ dmauncerrsts);
+ }
+ }
+
device->common.chancnt = readb(device->reg_base + IOAT_CHANCNT_OFFSET);
xfercap_scale = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
xfercap = (xfercap_scale == 0 ? -1 : (1UL << xfercap_scale));
+#ifdef CONFIG_I7300_IDLE_IOAT_CHANNEL
+ if (i7300_idle_platform_probe(NULL, NULL) == 0) {
+ device->common.chancnt--;
+ }
+#endif
for (i = 0; i < device->common.chancnt; i++) {
ioat_chan = kzalloc(sizeof(*ioat_chan), GFP_KERNEL);
if (!ioat_chan) {
prev = new;
} while (len && (new = ioat1_dma_get_next_descriptor(ioat_chan)));
+ if (!new) {
+ dev_err(&ioat_chan->device->pdev->dev,
+ "tx submit failed\n");
+ spin_unlock_bh(&ioat_chan->desc_lock);
+ return -ENOMEM;
+ }
+
hw->ctl = IOAT_DMA_DESCRIPTOR_CTL_CP_STS;
- if (new->async_tx.callback) {
+ if (first->async_tx.callback) {
hw->ctl |= IOAT_DMA_DESCRIPTOR_CTL_INT_GN;
if (first != new) {
/* move callback into to last desc */
/* write address into NextDescriptor field of last desc in chain */
to_ioat_desc(ioat_chan->used_desc.prev)->hw->next =
first->async_tx.phys;
- __list_splice(&new_chain, ioat_chan->used_desc.prev);
+ list_splice_tail(&new_chain, &ioat_chan->used_desc);
ioat_chan->dmacount += desc_count;
ioat_chan->pending += desc_count;
desc_count++;
} while (len && (new = ioat2_dma_get_next_descriptor(ioat_chan)));
- hw->ctl = IOAT_DMA_DESCRIPTOR_CTL_CP_STS;
- if (new->async_tx.callback) {
+ if (!new) {
+ dev_err(&ioat_chan->device->pdev->dev,
+ "tx submit failed\n");
+ spin_unlock_bh(&ioat_chan->desc_lock);
+ return -ENOMEM;
+ }
+
+ hw->ctl |= IOAT_DMA_DESCRIPTOR_CTL_CP_STS;
+ if (first->async_tx.callback) {
hw->ctl |= IOAT_DMA_DESCRIPTOR_CTL_INT_GN;
if (first != new) {
/* move callback into to last desc */
desc_sw->async_tx.tx_submit = ioat1_tx_submit;
break;
case IOAT_VER_2_0:
+ case IOAT_VER_3_0:
desc_sw->async_tx.tx_submit = ioat2_tx_submit;
break;
}
* ioat_dma_alloc_chan_resources - returns the number of allocated descriptors
* @chan: the channel to be filled out
*/
-static int ioat_dma_alloc_chan_resources(struct dma_chan *chan,
- struct dma_client *client)
+static int ioat_dma_alloc_chan_resources(struct dma_chan *chan)
{
struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
struct ioat_desc_sw *desc;
struct ioat_desc_sw *desc, *_desc;
int in_use_descs = 0;
+ /* Before freeing channel resources first check
+ * if they have been previously allocated for this channel.
+ */
+ if (ioat_chan->desccount == 0)
+ return;
+
tasklet_disable(&ioat_chan->cleanup_task);
ioat_dma_memcpy_cleanup(ioat_chan);
}
break;
case IOAT_VER_2_0:
+ case IOAT_VER_3_0:
list_for_each_entry_safe(desc, _desc,
ioat_chan->free_desc.next, node) {
list_del(&desc->node);
ioat_chan->last_completion = ioat_chan->completion_addr = 0;
ioat_chan->pending = 0;
ioat_chan->dmacount = 0;
+ ioat_chan->desccount = 0;
ioat_chan->watchdog_completion = 0;
ioat_chan->last_compl_desc_addr_hw = 0;
ioat_chan->watchdog_tcp_cookie =
/* set up the noop descriptor */
noop_desc = to_ioat_desc(ioat_chan->used_desc.next);
- noop_desc->hw->size = 0;
+ /* set size to non-zero value (channel returns error when size is 0) */
+ noop_desc->hw->size = NULL_DESC_BUFFER_SIZE;
noop_desc->hw->ctl = IOAT_DMA_DESCRIPTOR_NUL;
noop_desc->hw->src_addr = 0;
noop_desc->hw->dst_addr = 0;
switch (ioat_chan->device->version) {
case IOAT_VER_1_2:
return ioat1_dma_get_next_descriptor(ioat_chan);
- break;
case IOAT_VER_2_0:
+ case IOAT_VER_3_0:
return ioat2_dma_get_next_descriptor(ioat_chan);
- break;
}
return NULL;
}
* perhaps we're stuck so hard that the watchdog can't go off?
* try to catch it after 2 seconds
*/
- if (time_after(jiffies,
- ioat_chan->last_completion_time + HZ*WATCHDOG_DELAY)) {
- ioat_dma_chan_watchdog(&(ioat_chan->device->work.work));
- ioat_chan->last_completion_time = jiffies;
+ if (ioat_chan->device->version != IOAT_VER_3_0) {
+ if (time_after(jiffies,
+ ioat_chan->last_completion_time + HZ*WATCHDOG_DELAY)) {
+ ioat_dma_chan_watchdog(&(ioat_chan->device->work.work));
+ ioat_chan->last_completion_time = jiffies;
+ }
}
return;
}
}
break;
case IOAT_VER_2_0:
+ case IOAT_VER_3_0:
/* has some other thread has already cleaned up? */
if (ioat_chan->used_desc.prev == NULL)
break;
spin_lock_bh(&ioat_chan->desc_lock);
desc = ioat_dma_get_next_descriptor(ioat_chan);
+
+ if (!desc) {
+ dev_err(&ioat_chan->device->pdev->dev,
+ "Unable to start null desc - get next desc failed\n");
+ spin_unlock_bh(&ioat_chan->desc_lock);
+ return;
+ }
+
desc->hw->ctl = IOAT_DMA_DESCRIPTOR_NUL
| IOAT_DMA_DESCRIPTOR_CTL_INT_GN
| IOAT_DMA_DESCRIPTOR_CTL_CP_STS;
- desc->hw->size = 0;
+ /* set size to non-zero value (channel returns error when size is 0) */
+ desc->hw->size = NULL_DESC_BUFFER_SIZE;
desc->hw->src_addr = 0;
desc->hw->dst_addr = 0;
async_tx_ack(&desc->async_tx);
+ IOAT_CHANCMD_OFFSET(ioat_chan->device->version));
break;
case IOAT_VER_2_0:
+ case IOAT_VER_3_0:
writel(((u64) desc->async_tx.phys) & 0x00000000FFFFFFFF,
ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
writel(((u64) desc->async_tx.phys) >> 32,
static void ioat_dma_test_callback(void *dma_async_param)
{
- printk(KERN_ERR "ioatdma: ioat_dma_test_callback(%p)\n",
- dma_async_param);
+ struct completion *cmp = dma_async_param;
+
+ complete(cmp);
}
/**
dma_addr_t dma_dest, dma_src;
dma_cookie_t cookie;
int err = 0;
+ struct completion cmp;
src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
if (!src)
dma_chan = container_of(device->common.channels.next,
struct dma_chan,
device_node);
- if (device->common.device_alloc_chan_resources(dma_chan, NULL) < 1) {
+ if (device->common.device_alloc_chan_resources(dma_chan) < 1) {
dev_err(&device->pdev->dev,
"selftest cannot allocate chan resource\n");
err = -ENODEV;
}
async_tx_ack(tx);
+ init_completion(&cmp);
tx->callback = ioat_dma_test_callback;
- tx->callback_param = (void *)0x8086;
+ tx->callback_param = &cmp;
cookie = tx->tx_submit(tx);
if (cookie < 0) {
dev_err(&device->pdev->dev,
goto free_resources;
}
device->common.device_issue_pending(dma_chan);
- msleep(1);
+
+ wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
if (device->common.device_is_tx_complete(dma_chan, cookie, NULL, NULL)
!= DMA_SUCCESS) {
ioat1_dma_memcpy_issue_pending;
break;
case IOAT_VER_2_0:
+ case IOAT_VER_3_0:
device->common.device_prep_dma_memcpy = ioat2_dma_prep_memcpy;
device->common.device_issue_pending =
ioat2_dma_memcpy_issue_pending;
dma_async_device_register(&device->common);
- INIT_DELAYED_WORK(&device->work, ioat_dma_chan_watchdog);
- schedule_delayed_work(&device->work,
- WATCHDOG_DELAY);
+ if (device->version != IOAT_VER_3_0) {
+ INIT_DELAYED_WORK(&device->work, ioat_dma_chan_watchdog);
+ schedule_delayed_work(&device->work,
+ WATCHDOG_DELAY);
+ }
return device;
pci_release_regions(device->pdev);
pci_disable_device(device->pdev);
- cancel_delayed_work(&device->work);
+ if (device->version != IOAT_VER_3_0) {
+ cancel_delayed_work(&device->work);
+ }
list_for_each_entry_safe(chan, _chan,
&device->common.channels, device_node) {