4 files changed, 81 insertions, 4 deletions

diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 696d4de3bb8f..edf4f5e5de73 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -134,6 +134,7 @@ static int ioat1_enumerate_channels(struct ioatdma_device *device)
         dma->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));
+        dev_dbg(dev, "%s: xfercap = %d\n", __func__, xfercap);
 
 #ifdef  CONFIG_I7300_IDLE_IOAT_CHANNEL
         if (i7300_idle_platform_probe(NULL, NULL, 1) == 0)
@@ -167,6 +168,8 @@ __ioat1_dma_memcpy_issue_pending(struct ioat_dma_chan *ioat)
 {
         void __iomem *reg_base = ioat->base.reg_base;
 
+        dev_dbg(to_dev(&ioat->base), "%s: pending: %d\n",
+                __func__, ioat->pending);
         ioat->pending = 0;
         writeb(IOAT_CHANCMD_APPEND, reg_base + IOAT1_CHANCMD_OFFSET);
 }
@@ -251,6 +254,7 @@ static void ioat1_reset_channel(struct ioat_dma_chan *ioat)
         if (!ioat->used_desc.prev)
                 return;
 
+        dev_dbg(to_dev(chan), "%s\n", __func__);
         chanerr = readl(reg_base + IOAT_CHANERR_OFFSET);
         chansts = (chan->completion_virt->low
                                         & IOAT_CHANSTS_DMA_TRANSFER_STATUS);
@@ -382,6 +386,7 @@ static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
                 cookie = 1;
         c->cookie = cookie;
         tx->cookie = cookie;
+        dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
 
         /* write address into NextDescriptor field of last desc in chain */
         first = to_ioat_desc(tx->tx_list.next);
@@ -390,6 +395,8 @@ static dma_cookie_t ioat1_tx_submit(struct dma_async_tx_descriptor *tx)
         wmb();
         chain_tail->hw->next = first->txd.phys;
         list_splice_tail_init(&tx->tx_list, &ioat->used_desc);
+        dump_desc_dbg(ioat, chain_tail);
+        dump_desc_dbg(ioat, first);
 
         ioat->pending += desc->tx_cnt;
         if (ioat->pending >= ioat_pending_level)
@@ -429,6 +436,7 @@ ioat_dma_alloc_descriptor(struct ioat_dma_chan *ioat, gfp_t flags)
         desc_sw->txd.tx_submit = ioat1_tx_submit;
         desc_sw->hw = desc;
         desc_sw->txd.phys = phys;
+        set_desc_id(desc_sw, -1);
 
         return desc_sw;
 }
@@ -474,6 +482,7 @@ static int ioat1_dma_alloc_chan_resources(struct dma_chan *c)
                         dev_err(to_dev(chan), "Only %d initial descriptors\n", i);
                         break;
                 }
+                set_desc_id(desc, i);
                 list_add_tail(&desc->node, &tmp_list);
         }
         spin_lock_bh(&ioat->desc_lock);
@@ -495,6 +504,8 @@ static int ioat1_dma_alloc_chan_resources(struct dma_chan *c)
 
         tasklet_enable(&chan->cleanup_task);
         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;
 }
 
@@ -527,8 +538,10 @@ static void ioat1_dma_free_chan_resources(struct dma_chan *c)
         mdelay(100);
 
         spin_lock_bh(&ioat->desc_lock);
-        list_for_each_entry_safe(desc, _desc,
-                                 &ioat->used_desc, node) {
+        list_for_each_entry_safe(desc, _desc, &ioat->used_desc, node) {
+                dev_dbg(to_dev(chan), "%s: freeing %d from used list\n",
+                        __func__, desc_id(desc));
+                dump_desc_dbg(ioat, desc);
                 in_use_descs++;
                 list_del(&desc->node);
                 pci_pool_free(ioatdma_device->dma_pool, desc->hw,
@@ -585,7 +598,8 @@ ioat1_dma_get_next_descriptor(struct ioat_dma_chan *ioat)
                         return NULL;
                 }
         }
-
+        dev_dbg(to_dev(&ioat->base), "%s: allocated: %d\n",
+                __func__, desc_id(new));
         prefetch(new->hw);
         return new;
 }
@@ -630,6 +644,7 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
                         async_tx_ack(&desc->txd);
                         next = ioat1_dma_get_next_descriptor(ioat);
                         hw->next = next ? next->txd.phys : 0;
+                        dump_desc_dbg(ioat, desc);
                         desc = next;
                 } else
                         hw->next = 0;
@@ -652,6 +667,7 @@ ioat1_dma_prep_memcpy(struct dma_chan *c, dma_addr_t dma_dest,
         list_splice(&chain, &desc->txd.tx_list);
         hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
         hw->ctl_f.compl_write = 1;
+        dump_desc_dbg(ioat, desc);
 
         return &desc->txd;
 }
@@ -707,6 +723,9 @@ unsigned long ioat_get_current_completion(struct ioat_chan_common *chan)
         phys_complete = chan->completion_virt->low & IOAT_LOW_COMPLETION_MASK;
 #endif
 
+        dev_dbg(to_dev(chan), "%s: phys_complete: %#llx\n", __func__,
+                (unsigned long long) phys_complete);
+
         if ((chan->completion_virt->full
                 & IOAT_CHANSTS_DMA_TRANSFER_STATUS) ==
                                 IOAT_CHANSTS_DMA_TRANSFER_STATUS_HALTED) {
@@ -758,6 +777,8 @@ static void ioat1_cleanup(struct ioat_dma_chan *ioat)
                 return;
         }
 
+        dev_dbg(to_dev(chan), "%s: phys_complete: %lx\n",
+                 __func__, phys_complete);
         list_for_each_entry_safe(desc, _desc, &ioat->used_desc, node) {
                 tx = &desc->txd;
                 /*
@@ -765,6 +786,7 @@ static void ioat1_cleanup(struct ioat_dma_chan *ioat)
                  * due to exceeding xfercap, perhaps. If so, only the
                  * last one will have a cookie, and require unmapping.
                  */
+                dump_desc_dbg(ioat, desc);
                 if (tx->cookie) {
                         cookie = tx->cookie;
                         ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
@@ -848,6 +870,7 @@ static void ioat1_dma_start_null_desc(struct ioat_dma_chan *ioat)
         async_tx_ack(&desc->txd);
         hw->next = 0;
         list_add_tail(&desc->node, &ioat->used_desc);
+        dump_desc_dbg(ioat, desc);
 
         writel(((u64) desc->txd.phys) & 0x00000000FFFFFFFF,
                chan->reg_base + IOAT1_CHAINADDR_OFFSET_LOW);
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index fa15e77652a0..9f9edc2cd079 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -173,6 +173,7 @@ ioat_is_complete(struct dma_chan *c, dma_cookie_t cookie,
  *     or attached to a transaction list (async_tx.tx_list)
  * @tx_cnt: number of descriptors required to complete the transaction
  * @txd: the generic software descriptor for all engines
+ * @id: identifier for debug
  */
 struct ioat_desc_sw {
         struct ioat_dma_descriptor *hw;
@@ -180,8 +181,35 @@ struct ioat_desc_sw {
         int tx_cnt;
         size_t len;
         struct dma_async_tx_descriptor txd;
+        #ifdef DEBUG
+        int id;
+        #endif
 };
 
+#ifdef DEBUG
+#define set_desc_id(desc, i) ((desc)->id = (i))
+#define desc_id(desc) ((desc)->id)
+#else
+#define set_desc_id(desc, i)
+#define desc_id(desc) (0)
+#endif
+
+static inline void
+__dump_desc_dbg(struct ioat_chan_common *chan, struct ioat_dma_descriptor *hw,
+                struct dma_async_tx_descriptor *tx, int id)
+{
+        struct device *dev = to_dev(chan);
+
+        dev_dbg(dev, "desc[%d]: (%#llx->%#llx) cookie: %d flags: %#x"
+                " ctl: %#x (op: %d int_en: %d compl: %d)\n", id,
+                (unsigned long long) tx->phys,
+                (unsigned long long) hw->next, tx->cookie, tx->flags,
+                hw->ctl, hw->ctl_f.op, hw->ctl_f.int_en, hw->ctl_f.compl_write);
+}
+
+#define dump_desc_dbg(c, d) \
+        ({ if (d) __dump_desc_dbg(&c->base, d->hw, &d->txd, desc_id(d)); 0; })
+
 static inline void ioat_set_tcp_copy_break(unsigned long copybreak)
 {
         #ifdef CONFIG_NET_DMA
diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c
index 49ba1c73d95e..58881860f400 100644
--- a/drivers/dma/ioat/dma_v2.c
+++ b/drivers/dma/ioat/dma_v2.c
@@ -54,7 +54,9 @@ static void __ioat2_issue_pending(struct ioat2_dma_chan *ioat)
         /* make descriptor updates globally visible before notifying channel */
         wmb();
         writew(ioat->dmacount, reg_base + IOAT_CHAN_DMACOUNT_OFFSET);
-
+        dev_dbg(to_dev(&ioat->base),
+                "%s: head: %#x tail: %#x issued: %#x count: %#x\n",
+                __func__, ioat->head, ioat->tail, ioat->issued, ioat->dmacount);
 }
 
 static void ioat2_issue_pending(struct dma_chan *chan)
@@ -101,6 +103,8 @@ static void __ioat2_start_null_desc(struct ioat2_dma_chan *ioat)
                 return;
         }
 
+        dev_dbg(to_dev(&ioat->base), "%s: head: %#x tail: %#x issued: %#x\n",
+                __func__, ioat->head, ioat->tail, ioat->issued);
         idx = ioat2_desc_alloc(ioat, 1);
         desc = ioat2_get_ring_ent(ioat, idx);
 
@@ -118,6 +122,7 @@ static void __ioat2_start_null_desc(struct ioat2_dma_chan *ioat)
                reg_base + IOAT2_CHAINADDR_OFFSET_LOW);
         writel(((u64) desc->txd.phys) >> 32,
                reg_base + IOAT2_CHAINADDR_OFFSET_HIGH);
+        dump_desc_dbg(ioat, desc);
         __ioat2_issue_pending(ioat);
 }
 
@@ -154,6 +159,10 @@ static void ioat2_reset_part2(struct work_struct *work)
         ioat->issued = ioat->tail;
         ioat->dmacount = 0;
 
+        dev_dbg(to_dev(&ioat->base),
+                "%s: head: %#x tail: %#x issued: %#x count: %#x\n",
+                __func__, ioat->head, ioat->tail, ioat->issued, ioat->dmacount);
+
         if (ioat2_ring_pending(ioat)) {
                 struct ioat_ring_ent *desc;
 
@@ -221,6 +230,8 @@ static void ioat2_chan_watchdog(struct work_struct *work)
         u16 active;
         int i;
 
+        dev_dbg(&device->pdev->dev, "%s\n", __func__);
+
         for (i = 0; i < device->common.chancnt; i++) {
                 chan = ioat_chan_by_index(device, i);
                 ioat = container_of(chan, struct ioat2_dma_chan, base);
@@ -295,11 +306,15 @@ static void ioat2_cleanup(struct ioat2_dma_chan *ioat)
 
         spin_lock_bh(&ioat->ring_lock);
 
+        dev_dbg(to_dev(chan), "%s: head: %#x tail: %#x issued: %#x\n",
+                __func__, ioat->head, ioat->tail, ioat->issued);
+
         active = ioat2_ring_active(ioat);
         for (i = 0; i < active && !seen_current; i++) {
                 prefetch(ioat2_get_ring_ent(ioat, ioat->tail + i + 1));
                 desc = ioat2_get_ring_ent(ioat, ioat->tail + i);
                 tx = &desc->txd;
+                dump_desc_dbg(ioat, desc);
                 if (tx->cookie) {
                         ioat_dma_unmap(chan, tx->flags, desc->len, desc->hw);
                         chan->completed_cookie = tx->cookie;
@@ -348,6 +363,7 @@ static int ioat2_enumerate_channels(struct ioatdma_device *device)
         xfercap_log = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
         if (xfercap_log == 0)
                 return 0;
+        dev_dbg(dev, "%s: xfercap = %d\n", __func__, 1 << xfercap_log);
 
         /* FIXME which i/oat version is i7300? */
 #ifdef CONFIG_I7300_IDLE_IOAT_CHANNEL
@@ -381,6 +397,8 @@ static dma_cookie_t ioat2_tx_submit_unlock(struct dma_async_tx_descriptor *tx)
                 cookie = 1;
         tx->cookie = cookie;
         c->cookie = cookie;
+        dev_dbg(to_dev(&ioat->base), "%s: cookie: %d\n", __func__, cookie);
+
         ioat2_update_pending(ioat);
         spin_unlock_bh(&ioat->ring_lock);
 
@@ -480,6 +498,7 @@ static int ioat2_alloc_chan_resources(struct dma_chan *c)
                         kfree(ring);
                         return -ENOMEM;
                 }
+                set_desc_id(ring[i], i);
         }
 
         /* link descs */
@@ -571,12 +590,14 @@ ioat2_dma_prep_memcpy_lock(struct dma_chan *c, dma_addr_t dma_dest,
                 len -= copy;
                 dst += copy;
                 src += copy;
+                dump_desc_dbg(ioat, desc);
         }
 
         desc->txd.flags = flags;
         desc->len = total_len;
         hw->ctl_f.int_en = !!(flags & DMA_PREP_INTERRUPT);
         hw->ctl_f.compl_write = 1;
+        dump_desc_dbg(ioat, desc);
         /* we leave the channel locked to ensure in order submission */
 
         return &desc->txd;
@@ -614,6 +635,7 @@ static void ioat2_free_chan_resources(struct dma_chan *c)
 
         spin_lock_bh(&ioat->ring_lock);
         descs = ioat2_ring_space(ioat);
+        dev_dbg(to_dev(chan), "freeing %d idle descriptors\n", descs);
         for (i = 0; i < descs; i++) {
                 desc = ioat2_get_ring_ent(ioat, ioat->head + i);
                 ioat2_free_ring_ent(desc, c);
@@ -625,6 +647,7 @@ static void ioat2_free_chan_resources(struct dma_chan *c)
 
         for (i = 0; i < total_descs - descs; i++) {
                 desc = ioat2_get_ring_ent(ioat, ioat->tail + i);
+                dump_desc_dbg(ioat, desc);
                 ioat2_free_ring_ent(desc, c);
         }
 
diff --git a/drivers/dma/ioat/dma_v2.h b/drivers/dma/ioat/dma_v2.h
index 94a553eacdbd..c72ccb5dfd5b 100644
--- a/drivers/dma/ioat/dma_v2.h
+++ b/drivers/dma/ioat/dma_v2.h
@@ -116,6 +116,9 @@ struct ioat_ring_ent {
         struct ioat_dma_descriptor *hw;
         struct dma_async_tx_descriptor txd;
         size_t len;
+        #ifdef DEBUG
+        int id;
+        #endif
 };
 
 static inline struct ioat_ring_ent *