summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2016-06-19 06:52:20 -1000
committerLinus Torvalds <torvalds@linux-foundation.org>2016-06-19 06:52:20 -1000
commit9af1f5d8f20f97884da55817ab80a6fcd170f296 (patch)
treebad9c34daa7c4e864e47b1a103b2442995279954
parent049a40c0a2d4b458583161ec1b9ce109408cb1aa (diff)
parent5156463588c3999b630d9ffc6061a54962f3c2d9 (diff)
downloadop-kernel-dev-9af1f5d8f20f97884da55817ab80a6fcd170f296.zip
op-kernel-dev-9af1f5d8f20f97884da55817ab80a6fcd170f296.tar.gz
Merge tag 'dmaengine-fix-4.7-rc4' of git://git.infradead.org/users/vkoul/slave-dma
Pull dmaengine fixes from Vinod Koul: "Some fixes has piled up, so time to send them upstream. These fixes include: - at_xdmac fixes for residue and other stuff - update MAINTAINERS for dma dt bindings - mv_xor fix for incorrect offset" * tag 'dmaengine-fix-4.7-rc4' of git://git.infradead.org/users/vkoul/slave-dma: dmaengine: mv_xor: Fix incorrect offset in dma_map_page() dmaengine: at_xdmac: double FIFO flush needed to compute residue dmaengine: at_xdmac: fix residue corruption dmaengine: at_xdmac: align descriptors on 64 bits MAINTAINERS: Add file patterns for dma device tree bindings
-rw-r--r--MAINTAINERS1
-rw-r--r--drivers/dma/at_xdmac.c82
-rw-r--r--drivers/dma/mv_xor.c10
3 files changed, 64 insertions, 29 deletions
diff --git a/MAINTAINERS b/MAINTAINERS
index 98f8a5c..e1b090f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3778,6 +3778,7 @@ Q: https://patchwork.kernel.org/project/linux-dmaengine/list/
S: Maintained
F: drivers/dma/
F: include/linux/dmaengine.h
+F: Documentation/devicetree/bindings/dma/
F: Documentation/dmaengine/
T: git git://git.infradead.org/users/vkoul/slave-dma.git
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 8e304b1..75bd662 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -242,7 +242,7 @@ struct at_xdmac_lld {
u32 mbr_dus; /* Destination Microblock Stride Register */
};
-
+/* 64-bit alignment needed to update CNDA and CUBC registers in an atomic way. */
struct at_xdmac_desc {
struct at_xdmac_lld lld;
enum dma_transfer_direction direction;
@@ -253,7 +253,7 @@ struct at_xdmac_desc {
unsigned int xfer_size;
struct list_head descs_list;
struct list_head xfer_node;
-};
+} __aligned(sizeof(u64));
static inline void __iomem *at_xdmac_chan_reg_base(struct at_xdmac *atxdmac, unsigned int chan_nb)
{
@@ -1400,6 +1400,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
u32 cur_nda, check_nda, cur_ubc, mask, value;
u8 dwidth = 0;
unsigned long flags;
+ bool initd;
ret = dma_cookie_status(chan, cookie, txstate);
if (ret == DMA_COMPLETE)
@@ -1424,7 +1425,16 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
residue = desc->xfer_size;
/*
* Flush FIFO: only relevant when the transfer is source peripheral
- * synchronized.
+ * synchronized. Flush is needed before reading CUBC because data in
+ * the FIFO are not reported by CUBC. Reporting a residue of the
+ * transfer length while we have data in FIFO can cause issue.
+ * Usecase: atmel USART has a timeout which means I have received
+ * characters but there is no more character received for a while. On
+ * timeout, it requests the residue. If the data are in the DMA FIFO,
+ * we will return a residue of the transfer length. It means no data
+ * received. If an application is waiting for these data, it will hang
+ * since we won't have another USART timeout without receiving new
+ * data.
*/
mask = AT_XDMAC_CC_TYPE | AT_XDMAC_CC_DSYNC;
value = AT_XDMAC_CC_TYPE_PER_TRAN | AT_XDMAC_CC_DSYNC_PER2MEM;
@@ -1435,34 +1445,43 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
}
/*
- * 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.
+ * The easiest way to compute the residue should be to pause the DMA
+ * but doing this can lead to miss some data as some devices don't
+ * have FIFO.
+ * We need to read several registers because:
+ * - DMA is running therefore a descriptor change is possible while
+ * reading these registers
+ * - When the block transfer is done, the value of the CUBC register
+ * is set to its initial value until the fetch of the next descriptor.
+ * This value will corrupt the residue calculation so we have to skip
+ * it.
+ *
+ * INITD -------- ------------
+ * |____________________|
+ * _______________________ _______________
+ * NDA @desc2 \/ @desc3
+ * _______________________/\_______________
+ * __________ ___________ _______________
+ * CUBC 0 \/ MAX desc1 \/ MAX desc2
+ * __________/\___________/\_______________
+ *
+ * Since descriptors are aligned on 64 bits, we can assume that
+ * the update of NDA and CUBC is atomic.
* 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.
+ * A max number of retries is set because unlikely it could never ends.
*/
- 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();
+ initd = !!(at_xdmac_chan_read(atchan, AT_XDMAC_CC) & AT_XDMAC_CC_INITD);
rmb();
cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+ rmb();
+ cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+ rmb();
+
+ if ((check_nda == cur_nda) && initd)
+ break;
}
if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
@@ -1471,6 +1490,19 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
}
/*
+ * Flush FIFO: only relevant when the transfer is source peripheral
+ * synchronized. Another flush is needed here because CUBC is updated
+ * when the controller sends the data write command. It can lead to
+ * report data that are not written in the memory or the device. The
+ * FIFO flush ensures that data are really written.
+ */
+ if ((desc->lld.mbr_cfg & mask) == value) {
+ at_xdmac_write(atxdmac, AT_XDMAC_GSWF, atchan->mask);
+ while (!(at_xdmac_chan_read(atchan, AT_XDMAC_CIS) & AT_XDMAC_CIS_FIS))
+ cpu_relax();
+ }
+
+ /*
* Remove size of all microblocks already transferred and the current
* one. Then add the remaining size to transfer of the current
* microblock.
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 25d1dad..d0446a7 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -703,8 +703,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan)
goto free_resources;
}
- src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src), 0,
- PAGE_SIZE, DMA_TO_DEVICE);
+ src_dma = dma_map_page(dma_chan->device->dev, virt_to_page(src),
+ (size_t)src & ~PAGE_MASK, PAGE_SIZE,
+ DMA_TO_DEVICE);
unmap->addr[0] = src_dma;
ret = dma_mapping_error(dma_chan->device->dev, src_dma);
@@ -714,8 +715,9 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan)
}
unmap->to_cnt = 1;
- dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest), 0,
- PAGE_SIZE, DMA_FROM_DEVICE);
+ dest_dma = dma_map_page(dma_chan->device->dev, virt_to_page(dest),
+ (size_t)dest & ~PAGE_MASK, PAGE_SIZE,
+ DMA_FROM_DEVICE);
unmap->addr[1] = dest_dma;
ret = dma_mapping_error(dma_chan->device->dev, dest_dma);
OpenPOWER on IntegriCloud