diff mbox series

[3/4] spi: Fix cache corruption due to DMA/PIO overlap

Message ID 20220916113951.228398-4-vincent.whitchurch@axis.com (mailing list archive)
State New
Headers show
Series spi: Fix DMA bugs in (not only) spi-s3c64xx | expand

Commit Message

Vincent Whitchurch Sept. 16, 2022, 11:39 a.m. UTC
The SPI core DMA mapping support performs cache management once for the
entire message and not between transfers, and this leads to cache
corruption if a message has two or more RX transfers with both
transfers targeting the same cache line, and the controller driver
decides to handle one using DMA and the other using PIO (for example,
because one is much larger than the other).

Fix it by syncing before/after the actual transfers.  This also means
that we can skip the sync during the map/unmap of the message.

Fixes: 99adef310f682d6343 ("spi: Provide core support for DMA mapping transfers")
Signed-off-by: Vincent Whitchurch <vincent.whitchurch@axis.com>
---
 drivers/spi/spi.c | 107 +++++++++++++++++++++++++++++++++++++---------
 1 file changed, 86 insertions(+), 21 deletions(-)

Comments

kernel test robot Sept. 16, 2022, 4:06 p.m. UTC | #1
Hi Vincent,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on broonie-spi/for-next]
[also build test WARNING on krzk/for-next linus/master v6.0-rc5 next-20220916]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Vincent-Whitchurch/spi-Fix-DMA-bugs-in-not-only-spi-s3c64xx/20220916-194234
base:   https://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi.git for-next
config: sh-allmodconfig (https://download.01.org/0day-ci/archive/20220916/202209162337.7NbxJFXD-lkp@intel.com/config)
compiler: sh4-linux-gcc (GCC) 12.1.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/intel-lab-lkp/linux/commit/d9c81b85380dadb07e24d2f5dd6b27bacb72845a
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Vincent-Whitchurch/spi-Fix-DMA-bugs-in-not-only-spi-s3c64xx/20220916-194234
        git checkout d9c81b85380dadb07e24d2f5dd6b27bacb72845a
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=sh SHELL=/bin/bash drivers/spi/

If you fix the issue, kindly add following tag where applicable
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

>> drivers/spi/spi.c:1243:6: warning: no previous prototype for 'spi_dma_sync_for_device' [-Wmissing-prototypes]
    1243 | void spi_dma_sync_for_device(struct spi_controller *ctrl, struct spi_transfer *xfer)
         |      ^~~~~~~~~~~~~~~~~~~~~~~
>> drivers/spi/spi.c:1247:6: warning: no previous prototype for 'spi_dma_sync_for_cpu' [-Wmissing-prototypes]
    1247 | void spi_dma_sync_for_cpu(struct spi_controller *ctrl, struct spi_transfer *xfer)
         |      ^~~~~~~~~~~~~~~~~~~~


vim +/spi_dma_sync_for_device +1243 drivers/spi/spi.c

  1242	
> 1243	void spi_dma_sync_for_device(struct spi_controller *ctrl, struct spi_transfer *xfer)
  1244	{
  1245	}
  1246	
> 1247	void spi_dma_sync_for_cpu(struct spi_controller *ctrl, struct spi_transfer *xfer)
  1248	{
  1249	}
  1250	#endif /* !CONFIG_HAS_DMA */
  1251
diff mbox series

Patch

diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index a9134d062ff1..f7cd737bbf6f 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1010,9 +1010,9 @@  static void spi_set_cs(struct spi_device *spi, bool enable, bool force)
 }
 
 #ifdef CONFIG_HAS_DMA
-int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
-		struct sg_table *sgt, void *buf, size_t len,
-		enum dma_data_direction dir)
+static int spi_map_buf_attrs(struct spi_controller *ctlr, struct device *dev,
+			     struct sg_table *sgt, void *buf, size_t len,
+			     enum dma_data_direction dir, unsigned long attrs)
 {
 	const bool vmalloced_buf = is_vmalloc_addr(buf);
 	unsigned int max_seg_size = dma_get_max_seg_size(dev);
@@ -1078,28 +1078,39 @@  int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
 		sg = sg_next(sg);
 	}
 
-	ret = dma_map_sg(dev, sgt->sgl, sgt->nents, dir);
-	if (!ret)
-		ret = -ENOMEM;
+	ret = dma_map_sgtable(dev, sgt, dir, attrs);
 	if (ret < 0) {
 		sg_free_table(sgt);
 		return ret;
 	}
 
-	sgt->nents = ret;
-
 	return 0;
 }
 
-void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
-		   struct sg_table *sgt, enum dma_data_direction dir)
+int spi_map_buf(struct spi_controller *ctlr, struct device *dev,
+		struct sg_table *sgt, void *buf, size_t len,
+		enum dma_data_direction dir)
+{
+	return spi_map_buf_attrs(ctlr, dev, sgt, buf, len, dir, 0);
+}
+
+static void spi_unmap_buf_attrs(struct spi_controller *ctlr,
+				struct device *dev, struct sg_table *sgt,
+				enum dma_data_direction dir,
+				unsigned long attrs)
 {
 	if (sgt->orig_nents) {
-		dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir);
+		dma_unmap_sgtable(dev, sgt, dir, attrs);
 		sg_free_table(sgt);
 	}
 }
 
+void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
+		   struct sg_table *sgt, enum dma_data_direction dir)
+{
+	spi_unmap_buf_attrs(ctlr, dev, sgt, dir, 0);
+}
+
 static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 {
 	struct device *tx_dev, *rx_dev;
@@ -1124,24 +1135,30 @@  static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 		rx_dev = ctlr->dev.parent;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		/* The sync is done before each transfer. */
+		unsigned long attrs = DMA_ATTR_SKIP_CPU_SYNC;
+
 		if (!ctlr->can_dma(ctlr, msg->spi, xfer))
 			continue;
 
 		if (xfer->tx_buf != NULL) {
-			ret = spi_map_buf(ctlr, tx_dev, &xfer->tx_sg,
-					  (void *)xfer->tx_buf, xfer->len,
-					  DMA_TO_DEVICE);
+			ret = spi_map_buf_attrs(ctlr, tx_dev, &xfer->tx_sg,
+						(void *)xfer->tx_buf,
+						xfer->len, DMA_TO_DEVICE,
+						attrs);
 			if (ret != 0)
 				return ret;
 		}
 
 		if (xfer->rx_buf != NULL) {
-			ret = spi_map_buf(ctlr, rx_dev, &xfer->rx_sg,
-					  xfer->rx_buf, xfer->len,
-					  DMA_FROM_DEVICE);
+			ret = spi_map_buf_attrs(ctlr, rx_dev, &xfer->rx_sg,
+						xfer->rx_buf, xfer->len,
+						DMA_FROM_DEVICE, attrs);
 			if (ret != 0) {
-				spi_unmap_buf(ctlr, tx_dev, &xfer->tx_sg,
-					      DMA_TO_DEVICE);
+				spi_unmap_buf_attrs(ctlr, tx_dev,
+						&xfer->tx_sg, DMA_TO_DEVICE,
+						attrs);
+
 				return ret;
 			}
 		}
@@ -1164,17 +1181,52 @@  static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)
 		return 0;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		/* The sync has already been done after each transfer. */
+		unsigned long attrs = DMA_ATTR_SKIP_CPU_SYNC;
+
 		if (!ctlr->can_dma(ctlr, msg->spi, xfer))
 			continue;
 
-		spi_unmap_buf(ctlr, rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
-		spi_unmap_buf(ctlr, tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
+		spi_unmap_buf_attrs(ctlr, rx_dev, &xfer->rx_sg,
+				    DMA_FROM_DEVICE, attrs);
+		spi_unmap_buf_attrs(ctlr, tx_dev, &xfer->tx_sg,
+				    DMA_TO_DEVICE, attrs);
 	}
 
 	ctlr->cur_msg_mapped = false;
 
 	return 0;
 }
+
+static void spi_dma_sync_for_device(struct spi_controller *ctlr,
+				    struct spi_transfer *xfer)
+{
+	struct device *rx_dev = ctlr->cur_rx_dma_dev;
+	struct device *tx_dev = ctlr->cur_tx_dma_dev;
+
+	if (!ctlr->cur_msg_mapped)
+		return;
+
+	if (xfer->tx_sg.orig_nents)
+		dma_sync_sgtable_for_device(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
+	if (xfer->rx_sg.orig_nents)
+		dma_sync_sgtable_for_device(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
+}
+
+static void spi_dma_sync_for_cpu(struct spi_controller *ctlr,
+				 struct spi_transfer *xfer)
+{
+	struct device *rx_dev = ctlr->cur_rx_dma_dev;
+	struct device *tx_dev = ctlr->cur_tx_dma_dev;
+
+	if (!ctlr->cur_msg_mapped)
+		return;
+
+	if (xfer->rx_sg.orig_nents)
+		dma_sync_sgtable_for_cpu(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
+	if (xfer->tx_sg.orig_nents)
+		dma_sync_sgtable_for_cpu(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
+}
 #else /* !CONFIG_HAS_DMA */
 static inline int __spi_map_msg(struct spi_controller *ctlr,
 				struct spi_message *msg)
@@ -1187,6 +1239,14 @@  static inline int __spi_unmap_msg(struct spi_controller *ctlr,
 {
 	return 0;
 }
+
+void spi_dma_sync_for_device(struct spi_controller *ctrl, struct spi_transfer *xfer)
+{
+}
+
+void spi_dma_sync_for_cpu(struct spi_controller *ctrl, struct spi_transfer *xfer)
+{
+}
 #endif /* !CONFIG_HAS_DMA */
 
 static inline int spi_unmap_msg(struct spi_controller *ctlr,
@@ -1444,8 +1504,11 @@  static int spi_transfer_one_message(struct spi_controller *ctlr,
 			reinit_completion(&ctlr->xfer_completion);
 
 fallback_pio:
+			spi_dma_sync_for_device(ctlr, xfer);
 			ret = ctlr->transfer_one(ctlr, msg->spi, xfer);
 			if (ret < 0) {
+				spi_dma_sync_for_cpu(ctlr, xfer);
+
 				if (ctlr->cur_msg_mapped &&
 				   (xfer->error & SPI_TRANS_FAIL_NO_START)) {
 					__spi_unmap_msg(ctlr, msg);
@@ -1468,6 +1531,8 @@  static int spi_transfer_one_message(struct spi_controller *ctlr,
 				if (ret < 0)
 					msg->status = ret;
 			}
+
+			spi_dma_sync_for_cpu(ctlr, xfer);
 		} else {
 			if (xfer->len)
 				dev_err(&msg->spi->dev,