2 files changed, 41 insertions, 3 deletions

diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 64f5d1bdbb48..8e304b1befc5 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -176,6 +176,7 @@
 #define AT_XDMAC_MAX_CHAN       0x20
 #define AT_XDMAC_MAX_CSIZE      16      /* 16 data */
 #define AT_XDMAC_MAX_DWIDTH     8       /* 64 bits */
+#define AT_XDMAC_RESIDUE_MAX_RETRIES    5
 
 #define AT_XDMAC_DMA_BUSWIDTHS\
         (BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
@@ -1395,8 +1396,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
         struct at_xdmac_desc    *desc, *_desc;
         struct list_head        *descs_list;
         enum dma_status         ret;
-        int                     residue;
-        u32                     cur_nda, mask, value;
+        int                     residue, retry;
+        u32                     cur_nda, check_nda, cur_ubc, mask, value;
         u8                      dwidth = 0;
         unsigned long           flags;
 
@@ -1433,7 +1434,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
                         cpu_relax();
         }
 
+        /*
+         * When processing the residue, we need to read two registers but we
+         * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
+         * we stand in the descriptor list and AT_XDMAC_CUBC is used
+         * to know how many data are remaining for the current descriptor.
+         * Since the dma channel is not paused to not loose data, between the
+         * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
+         * descriptor.
+         * For that reason, after reading AT_XDMAC_CUBC, we check if we are
+         * still using the same descriptor by reading a second time
+         * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
+         * read again AT_XDMAC_CUBC.
+         * Memory barriers are used to ensure the read order of the registers.
+         * A max number of retries is set because unlikely it can never ends if
+         * we are transferring a lot of data with small buffers.
+         */
         cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+        rmb();
+        cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+        for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
+                rmb();
+                check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+
+                if (likely(cur_nda == check_nda))
+                        break;
+
+                cur_nda = check_nda;
+                rmb();
+                cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+        }
+
+        if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
+                ret = DMA_ERROR;
+                goto spin_unlock;
+        }
+
         /*
          * Remove size of all microblocks already transferred and the current
          * one. Then add the remaining size to transfer of the current
@@ -1446,7 +1482,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
                 if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda)
                         break;
         }
-        residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
+        residue += cur_ubc << dwidth;
 
         dma_set_residue(txstate, residue);
 
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 2209f75fdf05..aac85c30c2cf 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -522,6 +522,8 @@ static dma_cookie_t fsldma_run_tx_complete_actions(struct fsldma_chan *chan,
                         chan_dbg(chan, "LD %p callback\n", desc);
                         txd->callback(txd->callback_param);
                 }
+
+                dma_descriptor_unmap(txd);
         }
 
         /* Run any dependencies */