struct ntb_transport_ctx *transport;
struct ntb_dev *ndev;
void *cb_data;
- struct dma_chan *dma_chan;
+ struct dma_chan *tx_dma_chan;
+ struct dma_chan *rx_dma_chan;
bool client_ready;
bool link_is_up;
static int ntb_bus_init(struct ntb_transport_ctx *nt)
{
- list_add(&nt->entry, &ntb_transport_list);
+ list_add_tail(&nt->entry, &ntb_transport_list);
return 0;
}
out_offset = 0;
out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "NTB QP stats\n");
+ "\nNTB QP stats:\n\n");
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_bytes - \t%llu\n", qp->rx_bytes);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_err_ver - \t%llu\n", qp->rx_err_ver);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "rx_buff - \t%p\n", qp->rx_buff);
+ "rx_buff - \t0x%p\n", qp->rx_buff);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"rx_index - \t%u\n", qp->rx_index);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "rx_max_entry - \t%u\n", qp->rx_max_entry);
+ "rx_max_entry - \t%u\n\n", qp->rx_max_entry);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_bytes - \t%llu\n", qp->tx_bytes);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_err_no_buf - %llu\n", qp->tx_err_no_buf);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "tx_mw - \t%p\n", qp->tx_mw);
+ "tx_mw - \t0x%p\n", qp->tx_mw);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "tx_index - \t%u\n", qp->tx_index);
+ "tx_index (H) - \t%u\n", qp->tx_index);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "RRI (T) - \t%u\n",
+ qp->remote_rx_info->entry);
out_offset += snprintf(buf + out_offset, out_count - out_offset,
"tx_max_entry - \t%u\n", qp->tx_max_entry);
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "free tx - \t%u\n",
+ ntb_transport_tx_free_entry(qp));
out_offset += snprintf(buf + out_offset, out_count - out_offset,
- "\nQP Link %s\n",
+ "\n");
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "Using TX DMA - \t%s\n",
+ qp->tx_dma_chan ? "Yes" : "No");
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "Using RX DMA - \t%s\n",
+ qp->rx_dma_chan ? "Yes" : "No");
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "QP Link - \t%s\n",
qp->link_is_up ? "Up" : "Down");
+ out_offset += snprintf(buf + out_offset, out_count - out_offset,
+ "\n");
+
if (out_offset > out_count)
out_offset = out_count;
}
entry = list_first_entry(list, struct ntb_queue_entry, entry);
list_del(&entry->entry);
+
out:
spin_unlock_irqrestore(lock, flags);
num_qps_mw = qp_count / mw_count;
rx_size = (unsigned int)mw->xlat_size / num_qps_mw;
- qp->rx_buff = mw->virt_addr + rx_size * qp_num / mw_count;
+ qp->rx_buff = mw->virt_addr + rx_size * (qp_num / mw_count);
rx_size -= sizeof(struct ntb_rx_info);
qp->remote_rx_info = qp->rx_buff + rx_size;
size = max_mw_size;
spad = MW0_SZ_HIGH + (i * 2);
- ntb_peer_spad_write(ndev, spad, (u32)(size >> 32));
+ ntb_peer_spad_write(ndev, spad, upper_32_bits(size));
spad = MW0_SZ_LOW + (i * 2);
- ntb_peer_spad_write(ndev, spad, (u32)size);
+ ntb_peer_spad_write(ndev, spad, lower_32_bits(size));
}
ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count);
unsigned int qp_num)
{
struct ntb_transport_qp *qp;
- struct ntb_transport_mw *mw;
phys_addr_t mw_base;
resource_size_t mw_size;
unsigned int num_qps_mw, tx_size;
qp_count = nt->qp_count;
mw_num = QP_TO_MW(nt, qp_num);
- mw = &nt->mw_vec[mw_num];
qp = &nt->qp_vec[qp_num];
qp->qp_num = qp_num;
mw_size = nt->mw_vec[mw_num].phys_size;
tx_size = (unsigned int)mw_size / num_qps_mw;
- qp_offset = tx_size * qp_num / mw_count;
+ qp_offset = tx_size * (qp_num / mw_count);
qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
if (!qp->tx_mw)
GFP_KERNEL, node);
if (!nt->qp_vec) {
rc = -ENOMEM;
- goto err2;
+ goto err1;
}
if (nt_debugfs_dir) {
for (i = 0; i < qp_count; i++) {
rc = ntb_transport_init_queue(nt, i);
if (rc)
- goto err3;
+ goto err2;
}
INIT_DELAYED_WORK(&nt->link_work, ntb_transport_link_work);
rc = ntb_set_ctx(ndev, nt, &ntb_transport_ops);
if (rc)
- goto err3;
+ goto err2;
INIT_LIST_HEAD(&nt->client_devs);
rc = ntb_bus_init(nt);
if (rc)
- goto err4;
+ goto err3;
nt->link_is_up = false;
ntb_link_enable(ndev, NTB_SPEED_AUTO, NTB_WIDTH_AUTO);
return 0;
-err4:
- ntb_clear_ctx(ndev);
err3:
- kfree(nt->qp_vec);
+ ntb_clear_ctx(ndev);
err2:
- kfree(nt->mw_vec);
+ kfree(nt->qp_vec);
err1:
while (i--) {
mw = &nt->mw_vec[i];
iounmap(mw->vbase);
}
+ kfree(nt->mw_vec);
err:
kfree(nt);
return rc;
{
struct dma_async_tx_descriptor *txd;
struct ntb_transport_qp *qp = entry->qp;
- struct dma_chan *chan = qp->dma_chan;
+ struct dma_chan *chan = qp->rx_dma_chan;
struct dma_device *device;
size_t pay_off, buff_off, len;
struct dmaengine_unmap_data *unmap;
goto err;
if (len < copy_bytes)
- goto err_wait;
+ goto err;
device = chan->device;
pay_off = (size_t)offset & ~PAGE_MASK;
buff_off = (size_t)buf & ~PAGE_MASK;
if (!is_dma_copy_aligned(device, pay_off, buff_off, len))
- goto err_wait;
+ goto err;
unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
if (!unmap)
- goto err_wait;
+ goto err;
unmap->len = len;
unmap->addr[0] = dma_map_page(device->dev, virt_to_page(offset),
dmaengine_unmap_put(unmap);
err_get_unmap:
dmaengine_unmap_put(unmap);
-err_wait:
- /* If the callbacks come out of order, the writing of the index to the
- * last completed will be out of order. This may result in the
- * receive stalling forever.
- */
- dma_sync_wait(chan, qp->last_cookie);
err:
ntb_memcpy_rx(entry, offset);
qp->rx_memcpy++;
break;
}
- if (i && qp->dma_chan)
- dma_async_issue_pending(qp->dma_chan);
+ if (i && qp->rx_dma_chan)
+ dma_async_issue_pending(qp->rx_dma_chan);
if (i == qp->rx_max_entry) {
/* there is more work to do */
{
struct ntb_payload_header __iomem *hdr;
struct dma_async_tx_descriptor *txd;
- struct dma_chan *chan = qp->dma_chan;
+ struct dma_chan *chan = qp->tx_dma_chan;
struct dma_device *device;
size_t dest_off, buff_off;
struct dmaengine_unmap_data *unmap;
dma_cap_set(DMA_MEMCPY, dma_mask);
if (use_dma) {
- qp->dma_chan = dma_request_channel(dma_mask, ntb_dma_filter_fn,
- (void *)(unsigned long)node);
- if (!qp->dma_chan)
- dev_info(&pdev->dev, "Unable to allocate DMA channel\n");
+ qp->tx_dma_chan =
+ dma_request_channel(dma_mask, ntb_dma_filter_fn,
+ (void *)(unsigned long)node);
+ if (!qp->tx_dma_chan)
+ dev_info(&pdev->dev, "Unable to allocate TX DMA channel\n");
+
+ qp->rx_dma_chan =
+ dma_request_channel(dma_mask, ntb_dma_filter_fn,
+ (void *)(unsigned long)node);
+ if (!qp->rx_dma_chan)
+ dev_info(&pdev->dev, "Unable to allocate RX DMA channel\n");
} else {
- qp->dma_chan = NULL;
+ qp->tx_dma_chan = NULL;
+ qp->rx_dma_chan = NULL;
}
- dev_dbg(&pdev->dev, "Using %s memcpy\n", qp->dma_chan ? "DMA" : "CPU");
+
+ dev_dbg(&pdev->dev, "Using %s memcpy for TX\n",
+ qp->tx_dma_chan ? "DMA" : "CPU");
+
+ dev_dbg(&pdev->dev, "Using %s memcpy for RX\n",
+ qp->rx_dma_chan ? "DMA" : "CPU");
for (i = 0; i < NTB_QP_DEF_NUM_ENTRIES; i++) {
entry = kzalloc_node(sizeof(*entry), GFP_ATOMIC, node);
err1:
while ((entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_free_q)))
kfree(entry);
- if (qp->dma_chan)
- dma_release_channel(qp->dma_chan);
+ if (qp->tx_dma_chan)
+ dma_release_channel(qp->tx_dma_chan);
+ if (qp->rx_dma_chan)
+ dma_release_channel(qp->rx_dma_chan);
nt->qp_bitmap_free |= qp_bit;
err:
return NULL;
pdev = qp->ndev->pdev;
- if (qp->dma_chan) {
- struct dma_chan *chan = qp->dma_chan;
+ if (qp->tx_dma_chan) {
+ struct dma_chan *chan = qp->tx_dma_chan;
/* Putting the dma_chan to NULL will force any new traffic to be
* processed by the CPU instead of the DAM engine
*/
- qp->dma_chan = NULL;
+ qp->tx_dma_chan = NULL;
+
+ /* Try to be nice and wait for any queued DMA engine
+ * transactions to process before smashing it with a rock
+ */
+ dma_sync_wait(chan, qp->last_cookie);
+ dmaengine_terminate_all(chan);
+ dma_release_channel(chan);
+ }
+
+ if (qp->rx_dma_chan) {
+ struct dma_chan *chan = qp->rx_dma_chan;
+ /* Putting the dma_chan to NULL will force any new traffic to be
+ * processed by the CPU instead of the DAM engine
+ */
+ qp->rx_dma_chan = NULL;
/* Try to be nice and wait for any queued DMA engine
* transactions to process before smashing it with a rock
entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q);
if (!entry) {
qp->tx_err_no_buf++;
- return -ENOMEM;
+ return -EBUSY;
}
entry->cb_data = cb;
*/
void ntb_transport_link_down(struct ntb_transport_qp *qp)
{
- struct pci_dev *pdev;
int val;
if (!qp)
return;
- pdev = qp->ndev->pdev;
qp->client_ready = false;
val = ntb_spad_read(qp->ndev, QP_LINKS);
*/
unsigned int ntb_transport_max_size(struct ntb_transport_qp *qp)
{
- unsigned int max;
+ unsigned int max_size;
+ unsigned int copy_align;
+ struct dma_chan *rx_chan, *tx_chan;
if (!qp)
return 0;
- if (!qp->dma_chan)
- return qp->tx_max_frame - sizeof(struct ntb_payload_header);
+ rx_chan = qp->rx_dma_chan;
+ tx_chan = qp->tx_dma_chan;
+
+ copy_align = max(rx_chan ? rx_chan->device->copy_align : 0,
+ tx_chan ? tx_chan->device->copy_align : 0);
/* If DMA engine usage is possible, try to find the max size for that */
- max = qp->tx_max_frame - sizeof(struct ntb_payload_header);
- max -= max % (1 << qp->dma_chan->device->copy_align);
+ max_size = qp->tx_max_frame - sizeof(struct ntb_payload_header);
+ max_size = round_down(max_size, 1 << copy_align);
- return max;
+ return max_size;
}
EXPORT_SYMBOL_GPL(ntb_transport_max_size);
+unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp)
+{
+ unsigned int head = qp->tx_index;
+ unsigned int tail = qp->remote_rx_info->entry;
+
+ return tail > head ? tail - head : qp->tx_max_entry + tail - head;
+}
+EXPORT_SYMBOL_GPL(ntb_transport_tx_free_entry);
+
static void ntb_transport_doorbell_callback(void *data, int vector)
{
struct ntb_transport_ctx *nt = data;
projects / karo-tx-linux.git / blobdiff