dmaengine: stm32-dma3: prevent LL refactoring thanks to DT configuration

stm32-dma3 driver refactors the linked-list in order to address the memory
with the highest possible data width.
It means that it can introduce up to 2 linked-list items. One with a
transfer length multiple of channel maximum burst length and so with the
highest possible data width. And an extra one with the latest bytes, with
lower data width.
Some devices (e.g. FMC ECC) don't support having several transfers instead
of only one.
So add the possibility to prevent linked-list refactoring, when bit 17 of
the 'DMA transfer requirements' bit mask is set in device tree.
When NOPACK feature is used (bit 16 pf the 'DMA transfer requirements' bit
mask in device tree), linked-list refactoring can be avoided, since the
memory data width and burst will be aligned with the device ones.

Signed-off-by: Amelie Delaunay <amelie.delaunay@foss.st.com>
Link: https://lore.kernel.org/r/20241016-dma3-mp25-updates-v3-5-8311fe6f228d@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>

Author: ADESTM

drivers/dma/stm32/stm32-dma3.c

@@ -222,6 +222,7 @@ enum stm32_dma3_port_data_width {
 #define STM32_DMA3_DT_PFREQ		BIT(9) /* CTR2_PFREQ */
 #define STM32_DMA3_DT_TCEM		GENMASK(13, 12) /* CTR2_TCEM */
 #define STM32_DMA3_DT_NOPACK		BIT(16) /* CTR1_PAM */
+#define STM32_DMA3_DT_NOREFACT		BIT(17)
 
 /* struct stm32_dma3_chan .config_set bitfield */
 #define STM32_DMA3_CFG_SET_DT		BIT(0)
@@ -1126,10 +1127,13 @@ static void stm32_dma3_free_chan_resources(struct dma_chan *c)
 	chan->config_set = 0;
 }
 
-static u32 stm32_dma3_get_ll_count(struct stm32_dma3_chan *chan, size_t len)
+static u32 stm32_dma3_get_ll_count(struct stm32_dma3_chan *chan, size_t len, bool prevent_refactor)
 {
 	u32 count;
 
+	if (prevent_refactor)
+		return DIV_ROUND_UP(len, STM32_DMA3_MAX_BLOCK_SIZE);
+
 	count = len / STM32_DMA3_MAX_BLOCK_SIZE;
 	len -= (len / STM32_DMA3_MAX_BLOCK_SIZE) * STM32_DMA3_MAX_BLOCK_SIZE;
 
@@ -1179,8 +1183,10 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_memcpy(struct dma_cha
 	struct stm32_dma3_swdesc *swdesc;
 	size_t next_size, offset;
 	u32 count, i, ctr1, ctr2;
+	bool prevent_refactor = !!FIELD_GET(STM32_DMA3_DT_NOPACK, chan->dt_config.tr_conf) ||
+				!!FIELD_GET(STM32_DMA3_DT_NOREFACT, chan->dt_config.tr_conf);
 
-	count = stm32_dma3_get_ll_count(chan, len);
+	count = stm32_dma3_get_ll_count(chan, len, prevent_refactor);
 
 	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
 	if (!swdesc)
@@ -1196,7 +1202,8 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_dma_memcpy(struct dma_cha
 		remaining = len - offset;
 		next_size = min_t(size_t, remaining, STM32_DMA3_MAX_BLOCK_SIZE);
 
-		if (next_size < STM32_DMA3_MAX_BLOCK_SIZE && next_size >= chan->max_burst)
+		if (!prevent_refactor &&
+		    (next_size < STM32_DMA3_MAX_BLOCK_SIZE && next_size >= chan->max_burst))
 			next_size = chan->max_burst * (remaining / chan->max_burst);
 
 		ret = stm32_dma3_chan_prep_hw(chan, DMA_MEM_TO_MEM, &swdesc->ccr, &ctr1, &ctr2,
@@ -1235,11 +1242,13 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan
 	size_t len;
 	dma_addr_t sg_addr, dev_addr, src, dst;
 	u32 i, j, count, ctr1, ctr2;
+	bool prevent_refactor = !!FIELD_GET(STM32_DMA3_DT_NOPACK, chan->dt_config.tr_conf) ||
+				!!FIELD_GET(STM32_DMA3_DT_NOREFACT, chan->dt_config.tr_conf);
 	int ret;
 
 	count = 0;
 	for_each_sg(sgl, sg, sg_len, i)
-		count += stm32_dma3_get_ll_count(chan, sg_dma_len(sg));
+		count += stm32_dma3_get_ll_count(chan, sg_dma_len(sg), prevent_refactor);
 
 	swdesc = stm32_dma3_chan_desc_alloc(chan, count);
 	if (!swdesc)
@@ -1256,7 +1265,8 @@ static struct dma_async_tx_descriptor *stm32_dma3_prep_slave_sg(struct dma_chan
 		do {
 			size_t chunk = min_t(size_t, len, STM32_DMA3_MAX_BLOCK_SIZE);
 
-			if (chunk < STM32_DMA3_MAX_BLOCK_SIZE && chunk >= chan->max_burst)
+			if (!prevent_refactor &&
+			    (chunk < STM32_DMA3_MAX_BLOCK_SIZE && chunk >= chan->max_burst))
 				chunk = chan->max_burst * (len / chan->max_burst);
 
 			if (dir == DMA_MEM_TO_DEV) {