/*
* Intel I/OAT DMA Linux driver
- * Copyright(c) 2004 - 2007 Intel Corporation.
+ * Copyright(c) 2004 - 2009 Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms and conditions of the GNU General Public License,
#include <linux/dmaengine.h>
#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"
#define to_ioat_desc(lh) container_of(lh, struct ioat_desc_sw, node)
#define tx_to_ioat_desc(tx) container_of(tx, struct ioat_desc_sw, async_tx)
+#define chan_num(ch) ((int)((ch)->reg_base - (ch)->device->reg_base) / 0x80)
static int ioat_pending_level = 4;
module_param(ioat_pending_level, int, 0644);
MODULE_PARM_DESC(ioat_pending_level,
"high-water mark for pushing ioat descriptors (default: 4)");
+#define RESET_DELAY msecs_to_jiffies(100)
+#define WATCHDOG_DELAY round_jiffies(msecs_to_jiffies(2000))
+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) {
ioat_chan->reg_base = device->reg_base + (0x80 * (i + 1));
ioat_chan->xfercap = xfercap;
ioat_chan->desccount = 0;
- if (ioat_chan->device->version != IOAT_VER_1_2) {
- writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE
- | IOAT_DMA_DCA_ANY_CPU,
- ioat_chan->reg_base + IOAT_DCACTRL_OFFSET);
- }
+ INIT_DELAYED_WORK(&ioat_chan->work, ioat_dma_chan_reset_part2);
+ if (ioat_chan->device->version == IOAT_VER_2_0)
+ writel(IOAT_DCACTRL_CMPL_WRITE_ENABLE |
+ IOAT_DMA_DCA_ANY_CPU,
+ ioat_chan->reg_base + IOAT_DCACTRL_OFFSET);
+ else if (ioat_chan->device->version == IOAT_VER_3_0)
+ writel(IOAT_DMA_DCA_ANY_CPU,
+ ioat_chan->reg_base + IOAT_DCACTRL_OFFSET);
spin_lock_init(&ioat_chan->cleanup_lock);
spin_lock_init(&ioat_chan->desc_lock);
INIT_LIST_HEAD(&ioat_chan->free_desc);
{
struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
- if (ioat_chan->pending != 0) {
+ if (ioat_chan->pending > 0) {
spin_lock_bh(&ioat_chan->desc_lock);
__ioat1_dma_memcpy_issue_pending(ioat_chan);
spin_unlock_bh(&ioat_chan->desc_lock);
{
struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
- if (ioat_chan->pending != 0) {
+ if (ioat_chan->pending > 0) {
spin_lock_bh(&ioat_chan->desc_lock);
__ioat2_dma_memcpy_issue_pending(ioat_chan);
spin_unlock_bh(&ioat_chan->desc_lock);
}
}
+
+/**
+ * ioat_dma_chan_reset_part2 - reinit the channel after a reset
+ */
+static void ioat_dma_chan_reset_part2(struct work_struct *work)
+{
+ struct ioat_dma_chan *ioat_chan =
+ container_of(work, struct ioat_dma_chan, work.work);
+ struct ioat_desc_sw *desc;
+
+ spin_lock_bh(&ioat_chan->cleanup_lock);
+ spin_lock_bh(&ioat_chan->desc_lock);
+
+ ioat_chan->completion_virt->low = 0;
+ ioat_chan->completion_virt->high = 0;
+ ioat_chan->pending = 0;
+
+ /*
+ * count the descriptors waiting, and be sure to do it
+ * right for both the CB1 line and the CB2 ring
+ */
+ ioat_chan->dmacount = 0;
+ if (ioat_chan->used_desc.prev) {
+ desc = to_ioat_desc(ioat_chan->used_desc.prev);
+ do {
+ ioat_chan->dmacount++;
+ desc = to_ioat_desc(desc->node.next);
+ } while (&desc->node != ioat_chan->used_desc.next);
+ }
+
+ /*
+ * write the new starting descriptor address
+ * this puts channel engine into ARMED state
+ */
+ desc = to_ioat_desc(ioat_chan->used_desc.prev);
+ switch (ioat_chan->device->version) {
+ case IOAT_VER_1_2:
+ writel(((u64) desc->async_tx.phys) & 0x00000000FFFFFFFF,
+ ioat_chan->reg_base + IOAT1_CHAINADDR_OFFSET_LOW);
+ writel(((u64) desc->async_tx.phys) >> 32,
+ ioat_chan->reg_base + IOAT1_CHAINADDR_OFFSET_HIGH);
+
+ writeb(IOAT_CHANCMD_START, ioat_chan->reg_base
+ + IOAT_CHANCMD_OFFSET(ioat_chan->device->version));
+ break;
+ case IOAT_VER_2_0:
+ writel(((u64) desc->async_tx.phys) & 0x00000000FFFFFFFF,
+ ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
+ writel(((u64) desc->async_tx.phys) >> 32,
+ ioat_chan->reg_base + IOAT2_CHAINADDR_OFFSET_HIGH);
+
+ /* tell the engine to go with what's left to be done */
+ writew(ioat_chan->dmacount,
+ ioat_chan->reg_base + IOAT_CHAN_DMACOUNT_OFFSET);
+
+ break;
+ }
+ dev_err(&ioat_chan->device->pdev->dev,
+ "chan%d reset - %d descs waiting, %d total desc\n",
+ chan_num(ioat_chan), ioat_chan->dmacount, ioat_chan->desccount);
+
+ spin_unlock_bh(&ioat_chan->desc_lock);
+ spin_unlock_bh(&ioat_chan->cleanup_lock);
+}
+
+/**
+ * ioat_dma_reset_channel - restart a channel
+ * @ioat_chan: IOAT DMA channel handle
+ */
+static void ioat_dma_reset_channel(struct ioat_dma_chan *ioat_chan)
+{
+ u32 chansts, chanerr;
+
+ if (!ioat_chan->used_desc.prev)
+ return;
+
+ chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+ chansts = (ioat_chan->completion_virt->low
+ & IOAT_CHANSTS_DMA_TRANSFER_STATUS);
+ if (chanerr) {
+ dev_err(&ioat_chan->device->pdev->dev,
+ "chan%d, CHANSTS = 0x%08x CHANERR = 0x%04x, clearing\n",
+ chan_num(ioat_chan), chansts, chanerr);
+ writel(chanerr, ioat_chan->reg_base + IOAT_CHANERR_OFFSET);
+ }
+
+ /*
+ * whack it upside the head with a reset
+ * and wait for things to settle out.
+ * force the pending count to a really big negative
+ * to make sure no one forces an issue_pending
+ * while we're waiting.
+ */
+
+ spin_lock_bh(&ioat_chan->desc_lock);
+ ioat_chan->pending = INT_MIN;
+ writeb(IOAT_CHANCMD_RESET,
+ ioat_chan->reg_base
+ + IOAT_CHANCMD_OFFSET(ioat_chan->device->version));
+ spin_unlock_bh(&ioat_chan->desc_lock);
+
+ /* schedule the 2nd half instead of sleeping a long time */
+ schedule_delayed_work(&ioat_chan->work, RESET_DELAY);
+}
+
+/**
+ * ioat_dma_chan_watchdog - watch for stuck channels
+ */
+static void ioat_dma_chan_watchdog(struct work_struct *work)
+{
+ struct ioatdma_device *device =
+ container_of(work, struct ioatdma_device, work.work);
+ struct ioat_dma_chan *ioat_chan;
+ int i;
+
+ union {
+ u64 full;
+ struct {
+ u32 low;
+ u32 high;
+ };
+ } completion_hw;
+ unsigned long compl_desc_addr_hw;
+
+ for (i = 0; i < device->common.chancnt; i++) {
+ ioat_chan = ioat_lookup_chan_by_index(device, i);
+
+ if (ioat_chan->device->version == IOAT_VER_1_2
+ /* have we started processing anything yet */
+ && ioat_chan->last_completion
+ /* have we completed any since last watchdog cycle? */
+ && (ioat_chan->last_completion ==
+ ioat_chan->watchdog_completion)
+ /* has TCP stuck on one cookie since last watchdog? */
+ && (ioat_chan->watchdog_tcp_cookie ==
+ ioat_chan->watchdog_last_tcp_cookie)
+ && (ioat_chan->watchdog_tcp_cookie !=
+ ioat_chan->completed_cookie)
+ /* is there something in the chain to be processed? */
+ /* CB1 chain always has at least the last one processed */
+ && (ioat_chan->used_desc.prev != ioat_chan->used_desc.next)
+ && ioat_chan->pending == 0) {
+
+ /*
+ * check CHANSTS register for completed
+ * descriptor address.
+ * if it is different than completion writeback,
+ * it is not zero
+ * and it has changed since the last watchdog
+ * we can assume that channel
+ * is still working correctly
+ * and the problem is in completion writeback.
+ * update completion writeback
+ * with actual CHANSTS value
+ * else
+ * try resetting the channel
+ */
+
+ completion_hw.low = readl(ioat_chan->reg_base +
+ IOAT_CHANSTS_OFFSET_LOW(ioat_chan->device->version));
+ completion_hw.high = readl(ioat_chan->reg_base +
+ IOAT_CHANSTS_OFFSET_HIGH(ioat_chan->device->version));
+#if (BITS_PER_LONG == 64)
+ compl_desc_addr_hw =
+ completion_hw.full
+ & IOAT_CHANSTS_COMPLETED_DESCRIPTOR_ADDR;
+#else
+ compl_desc_addr_hw =
+ completion_hw.low & IOAT_LOW_COMPLETION_MASK;
+#endif
+
+ if ((compl_desc_addr_hw != 0)
+ && (compl_desc_addr_hw != ioat_chan->watchdog_completion)
+ && (compl_desc_addr_hw != ioat_chan->last_compl_desc_addr_hw)) {
+ ioat_chan->last_compl_desc_addr_hw = compl_desc_addr_hw;
+ ioat_chan->completion_virt->low = completion_hw.low;
+ ioat_chan->completion_virt->high = completion_hw.high;
+ } else {
+ ioat_dma_reset_channel(ioat_chan);
+ ioat_chan->watchdog_completion = 0;
+ ioat_chan->last_compl_desc_addr_hw = 0;
+ }
+
+ /*
+ * for version 2.0 if there are descriptors yet to be processed
+ * and the last completed hasn't changed since the last watchdog
+ * if they haven't hit the pending level
+ * issue the pending to push them through
+ * else
+ * try resetting the channel
+ */
+ } else if (ioat_chan->device->version == IOAT_VER_2_0
+ && ioat_chan->used_desc.prev
+ && ioat_chan->last_completion
+ && ioat_chan->last_completion == ioat_chan->watchdog_completion) {
+
+ if (ioat_chan->pending < ioat_pending_level)
+ ioat2_dma_memcpy_issue_pending(&ioat_chan->common);
+ else {
+ ioat_dma_reset_channel(ioat_chan);
+ ioat_chan->watchdog_completion = 0;
+ }
+ } else {
+ ioat_chan->last_compl_desc_addr_hw = 0;
+ ioat_chan->watchdog_completion
+ = ioat_chan->last_completion;
+ }
+
+ ioat_chan->watchdog_last_tcp_cookie =
+ ioat_chan->watchdog_tcp_cookie;
+ }
+
+ schedule_delayed_work(&device->work, WATCHDOG_DELAY);
+}
+
static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
{
struct ioat_dma_chan *ioat_chan = to_ioat_chan(tx->chan);
u32 copy;
size_t len;
dma_addr_t src, dst;
- int orig_ack;
+ unsigned long orig_flags;
unsigned int desc_count = 0;
/* src and dest and len are stored in the initial descriptor */
len = first->len;
src = first->src;
dst = first->dst;
- orig_ack = first->async_tx.ack;
+ orig_flags = first->async_tx.flags;
new = first;
spin_lock_bh(&ioat_chan->desc_lock);
do {
copy = min_t(size_t, len, ioat_chan->xfercap);
- new->async_tx.ack = 1;
+ async_tx_ack(&new->async_tx);
hw = new->hw;
hw->size = copy;
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 */
}
new->tx_cnt = desc_count;
- new->async_tx.ack = orig_ack; /* client is in control of this ack */
+ new->async_tx.flags = orig_flags; /* client is in control of this ack */
/* store the original values for use in later cleanup */
if (new != first) {
/* 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;
u32 copy;
size_t len;
dma_addr_t src, dst;
- int orig_ack;
+ unsigned long orig_flags;
unsigned int desc_count = 0;
/* src and dest and len are stored in the initial descriptor */
len = first->len;
src = first->src;
dst = first->dst;
- orig_ack = first->async_tx.ack;
+ orig_flags = first->async_tx.flags;
new = first;
/*
do {
copy = min_t(size_t, len, ioat_chan->xfercap);
- new->async_tx.ack = 1;
+ async_tx_ack(&new->async_tx);
hw = new->hw;
hw->size = copy;
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 */
}
new->tx_cnt = desc_count;
- new->async_tx.ack = orig_ack; /* client is in control of this ack */
+ new->async_tx.flags = orig_flags; /* client is in control of this ack */
/* store the original values for use in later cleanup */
if (new != first) {
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;
}
- INIT_LIST_HEAD(&desc_sw->async_tx.tx_list);
desc_sw->hw = desc;
desc_sw->async_tx.phys = phys;
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 =
+ ioat_chan->watchdog_last_tcp_cookie = 0;
}
/**
/* 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;
}
new->len = len;
new->dst = dma_dest;
new->src = dma_src;
+ new->async_tx.flags = flags;
return &new->async_tx;
- } else
+ } else {
+ dev_err(&ioat_chan->device->pdev->dev,
+ "chan%d - get_next_desc failed: %d descs waiting, %d total desc\n",
+ chan_num(ioat_chan), ioat_chan->dmacount, ioat_chan->desccount);
return NULL;
+ }
}
static struct dma_async_tx_descriptor *ioat2_dma_prep_memcpy(
new->len = len;
new->dst = dma_dest;
new->src = dma_src;
+ new->async_tx.flags = flags;
return &new->async_tx;
- } else
+ } else {
+ spin_unlock_bh(&ioat_chan->desc_lock);
+ dev_err(&ioat_chan->device->pdev->dev,
+ "chan%d - get_next_desc failed: %d descs waiting, %d total desc\n",
+ chan_num(ioat_chan), ioat_chan->dmacount, ioat_chan->desccount);
return NULL;
+ }
}
static void ioat_dma_cleanup_tasklet(unsigned long data)
chan->reg_base + IOAT_CHANCTRL_OFFSET);
}
+static void
+ioat_dma_unmap(struct ioat_dma_chan *ioat_chan, struct ioat_desc_sw *desc)
+{
+ /*
+ * yes we are unmapping both _page and _single
+ * alloc'd regions with unmap_page. Is this
+ * *really* that bad?
+ */
+ if (!(desc->async_tx.flags & DMA_COMPL_SKIP_DEST_UNMAP))
+ pci_unmap_page(ioat_chan->device->pdev,
+ pci_unmap_addr(desc, dst),
+ pci_unmap_len(desc, len),
+ PCI_DMA_FROMDEVICE);
+
+ if (!(desc->async_tx.flags & DMA_COMPL_SKIP_SRC_UNMAP))
+ pci_unmap_page(ioat_chan->device->pdev,
+ pci_unmap_addr(desc, src),
+ pci_unmap_len(desc, len),
+ PCI_DMA_TODEVICE);
+}
+
/**
* ioat_dma_memcpy_cleanup - cleanup up finished descriptors
* @chan: ioat channel to be cleaned up
if (phys_complete == ioat_chan->last_completion) {
spin_unlock_bh(&ioat_chan->cleanup_lock);
+ /*
+ * perhaps we're stuck so hard that the watchdog can't go off?
+ * try to catch it after 2 seconds
+ */
+ 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;
}
+ ioat_chan->last_completion_time = jiffies;
cookie = 0;
- spin_lock_bh(&ioat_chan->desc_lock);
+ if (!spin_trylock_bh(&ioat_chan->desc_lock)) {
+ spin_unlock_bh(&ioat_chan->cleanup_lock);
+ return;
+ }
+
switch (ioat_chan->device->version) {
case IOAT_VER_1_2:
list_for_each_entry_safe(desc, _desc,
*/
if (desc->async_tx.cookie) {
cookie = desc->async_tx.cookie;
-
- /*
- * yes we are unmapping both _page and _single
- * alloc'd regions with unmap_page. Is this
- * *really* that bad?
- */
- pci_unmap_page(ioat_chan->device->pdev,
- pci_unmap_addr(desc, dst),
- pci_unmap_len(desc, len),
- PCI_DMA_FROMDEVICE);
- pci_unmap_page(ioat_chan->device->pdev,
- pci_unmap_addr(desc, src),
- pci_unmap_len(desc, len),
- PCI_DMA_TODEVICE);
-
+ ioat_dma_unmap(ioat_chan, desc);
if (desc->async_tx.callback) {
desc->async_tx.callback(desc->async_tx.callback_param);
desc->async_tx.callback = NULL;
* a completed entry, but not the last, so clean
* up if the client is done with the descriptor
*/
- if (desc->async_tx.ack) {
- list_del(&desc->node);
- list_add_tail(&desc->node,
- &ioat_chan->free_desc);
+ if (async_tx_test_ack(&desc->async_tx)) {
+ list_move_tail(&desc->node,
+ &ioat_chan->free_desc);
} else
desc->async_tx.cookie = 0;
} else {
}
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;
if (desc->async_tx.cookie) {
cookie = desc->async_tx.cookie;
desc->async_tx.cookie = 0;
-
- pci_unmap_page(ioat_chan->device->pdev,
- pci_unmap_addr(desc, dst),
- pci_unmap_len(desc, len),
- PCI_DMA_FROMDEVICE);
- pci_unmap_page(ioat_chan->device->pdev,
- pci_unmap_addr(desc, src),
- pci_unmap_len(desc, len),
- PCI_DMA_TODEVICE);
-
+ ioat_dma_unmap(ioat_chan, desc);
if (desc->async_tx.callback) {
desc->async_tx.callback(desc->async_tx.callback_param);
desc->async_tx.callback = NULL;
spin_unlock_bh(&ioat_chan->cleanup_lock);
}
-static void ioat_dma_dependency_added(struct dma_chan *chan)
-{
- struct ioat_dma_chan *ioat_chan = to_ioat_chan(chan);
- spin_lock_bh(&ioat_chan->desc_lock);
- if (ioat_chan->pending == 0) {
- spin_unlock_bh(&ioat_chan->desc_lock);
- ioat_dma_memcpy_cleanup(ioat_chan);
- } else
- spin_unlock_bh(&ioat_chan->desc_lock);
-}
-
/**
* ioat_dma_is_complete - poll the status of a IOAT DMA transaction
* @chan: IOAT DMA channel handle
last_used = chan->cookie;
last_complete = ioat_chan->completed_cookie;
+ ioat_chan->watchdog_tcp_cookie = cookie;
if (done)
*done = last_complete;
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;
- desc->async_tx.ack = 1;
+ async_tx_ack(&desc->async_tx);
switch (ioat_chan->device->version) {
case IOAT_VER_1_2:
desc->hw->next = 0;
+ 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;
+ unsigned long tmo;
src = kzalloc(sizeof(u8) * IOAT_TEST_SIZE, GFP_KERNEL);
if (!src)
}
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);
- if (device->common.device_is_tx_complete(dma_chan, cookie, NULL, NULL)
+ tmo = wait_for_completion_timeout(&cmp, msecs_to_jiffies(3000));
+
+ if (tmo == 0 ||
+ device->common.device_is_tx_complete(dma_chan, cookie, NULL, NULL)
!= DMA_SUCCESS) {
dev_err(&device->pdev->dev,
"Self-test copy timed out, disabling\n");
dma_cap_set(DMA_MEMCPY, device->common.cap_mask);
device->common.device_is_tx_complete = ioat_dma_is_complete;
- device->common.device_dependency_added = ioat_dma_dependency_added;
switch (device->version) {
case IOAT_VER_1_2:
device->common.device_prep_dma_memcpy = ioat1_dma_prep_memcpy;
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;
" %d channels, device version 0x%02x, driver version %s\n",
device->common.chancnt, device->version, IOAT_DMA_VERSION);
+ if (!device->common.chancnt) {
+ dev_err(&device->pdev->dev,
+ "Intel(R) I/OAT DMA Engine problem found: "
+ "zero channels detected\n");
+ goto err_setup_interrupts;
+ }
+
err = ioat_dma_setup_interrupts(device);
if (err)
goto err_setup_interrupts;
if (err)
goto err_self_test;
+ ioat_set_tcp_copy_break(device);
+
dma_async_device_register(&device->common);
+ 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;
err_self_test:
struct dma_chan *chan, *_chan;
struct ioat_dma_chan *ioat_chan;
+ if (device->version != IOAT_VER_3_0)
+ cancel_delayed_work(&device->work);
+
ioat_dma_remove_interrupts(device);
dma_async_device_unregister(&device->common);