mxs-dma : rewrite the last parameter of mxs_dma_prep_slave_sg()

[1] Background :
    The GPMI does ECC read page operation with a DMA chain consist of three DMA
    Command Structures. The middle one of the chain is used to enable the BCH,
    and read out the NAND page.

    The WAIT4END(wait for command end) is a comunication signal between
    the GPMI and MXS-DMA.

[2] The current DMA code sets the WAIT4END bit at the last one, such as:

    +-----+               +-----+                      +-----+
    | cmd | ------------> | cmd | ------------------>  | cmd |
    +-----+               +-----+                      +-----+
                                                          ^
                                                          |
                                                          |
                                                     set WAIT4END here

    This chain works fine in the mx23/mx28.

[3] But in the new GPMI version (used in MX50/MX60), the WAIT4END bit should
    be set not only at the last DMA Command Structure,
    but also at the middle one, such as:

    +-----+               +-----+                      +-----+
    | cmd | ------------> | cmd | ------------------>  | cmd |
    +-----+               +-----+                      +-----+
                             ^                            ^
                             |                            |
                             |                            |
                        set WAIT4END here too        set WAIT4END here

    If we do not set WAIT4END, the BCH maybe stalls in "ECC reading page" state.
    In the next ECC write page operation, a DMA-timeout occurs.
    This has been catched in the MX6Q board.

[4] In order to fix the bug, rewrite the last parameter of mxs_dma_prep_slave_sg(),
    and use the dma_ctrl_flags:
    ---------------------------------------------------------
      DMA_PREP_INTERRUPT : append a new DMA Command Structrue.
      DMA_CTRL_ACK       : set the WAIT4END bit for this DMA Command Structure.
    ---------------------------------------------------------

[5] changes to the relative drivers:
    <1> For mxs-mmc driver, just use the new flags, do not change any logic.
    <2> For gpmi-nand driver, and use the new flags to set the DMA
        chain, especially for ecc read page.

Acked-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Huang Shijie <b32955@freescale.com>
Acked-by: Vinod Koul <vinod.koul@linux.intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

1 files changed, 28 insertions, 4 deletions

diff --git a/drivers/dma/mxs-dma.c b/drivers/dma/mxs-dma.c
index 0afcedbe247..0ddfd30b56a 100644
--- a/drivers/dma/mxs-dma.c
+++ b/drivers/dma/mxs-dma.c
@@ -349,10 +349,32 @@ static void mxs_dma_free_chan_resources(struct dma_chan *chan)
         clk_disable_unprepare(mxs_dma->clk);
 }
 
+/*
+ * How to use the flags for ->device_prep_slave_sg() :
+ *    [1] If there is only one DMA command in the DMA chain, the code should be:
+ *            ......
+ *            ->device_prep_slave_sg(DMA_CTRL_ACK);
+ *            ......
+ *    [2] If there are two DMA commands in the DMA chain, the code should be
+ *            ......
+ *            ->device_prep_slave_sg(0);
+ *            ......
+ *            ->device_prep_slave_sg(DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+ *            ......
+ *    [3] If there are more than two DMA commands in the DMA chain, the code
+ *        should be:
+ *            ......
+ *            ->device_prep_slave_sg(0);                                // First
+ *            ......
+ *            ->device_prep_slave_sg(DMA_PREP_INTERRUPT [| DMA_CTRL_ACK]);
+ *            ......
+ *            ->device_prep_slave_sg(DMA_PREP_INTERRUPT | DMA_CTRL_ACK); // Last
+ *            ......
+ */
 static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
                 struct dma_chan *chan, struct scatterlist *sgl,
                 unsigned int sg_len, enum dma_transfer_direction direction,
-                unsigned long append)
+                unsigned long flags)
 {
         struct mxs_dma_chan *mxs_chan = to_mxs_dma_chan(chan);
         struct mxs_dma_engine *mxs_dma = mxs_chan->mxs_dma;
@@ -360,6 +382,7 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
         struct scatterlist *sg;
         int i, j;
         u32 *pio;
+        bool append = flags & DMA_PREP_INTERRUPT;
         int idx = append ? mxs_chan->desc_count : 0;
 
         if (mxs_chan->status == DMA_IN_PROGRESS && !append)
@@ -386,7 +409,6 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
                 ccw->bits |= CCW_CHAIN;
                 ccw->bits &= ~CCW_IRQ;
                 ccw->bits &= ~CCW_DEC_SEM;
-                ccw->bits &= ~CCW_WAIT4END;
         } else {
                 idx = 0;
         }
@@ -401,7 +423,8 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
                 ccw->bits = 0;
                 ccw->bits |= CCW_IRQ;
                 ccw->bits |= CCW_DEC_SEM;
-                ccw->bits |= CCW_WAIT4END;
+                if (flags & DMA_CTRL_ACK)
+                        ccw->bits |= CCW_WAIT4END;
                 ccw->bits |= CCW_HALT_ON_TERM;
                 ccw->bits |= CCW_TERM_FLUSH;
                 ccw->bits |= BF_CCW(sg_len, PIO_NUM);
@@ -432,7 +455,8 @@ static struct dma_async_tx_descriptor *mxs_dma_prep_slave_sg(
                                 ccw->bits &= ~CCW_CHAIN;
                                 ccw->bits |= CCW_IRQ;
                                 ccw->bits |= CCW_DEC_SEM;
-                                ccw->bits |= CCW_WAIT4END;
+                                if (flags & DMA_CTRL_ACK)
+                                        ccw->bits |= CCW_WAIT4END;
                         }
                 }
         }