[PATCH v4 1/2] dmaengine: change dmaengine_get_unmap_data() first arg to dma_chan

[PATCH v4 1/2] dmaengine: change dmaengine_get_unmap_data() first arg to dma_chan

[Frank.Li]

From: Frank Li <Frank.Li@nxp.com>

Replace the struct device *dev argument with struct dma_chan *chan so
callers do not need to reach into the dma_device internals to obtain
the device pointer.  The implementation now derives the device via
dmaengine_get_dma_device(chan), which correctly handles the per-channel
IOMMU mapping case.

Prepare to make dma_device private and make dmaengine API consistent.

Acked-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
V4: none, just respin to miss patch2
V3 split from origianl thread
https://lore.kernel.org/dmaengine/20260923-dmaengine_prep_dma_pq-v2-0-32ed65b8a9b4@nxp.com/
V2 change collect Dave Jiang ack tags
v1 version at
https://lore.kernel.org/imx/b40fa0d7-fbd0-4ee8-b99c-781d08c18838@intel.com/T/#t
---
 crypto/async_tx/async_memcpy.c      | 4 ++--
 crypto/async_tx/async_pq.c          | 8 ++++----
 crypto/async_tx/async_raid6_recov.c | 8 ++++----
 crypto/async_tx/async_xor.c         | 8 ++++----
 drivers/dma/dmaengine.c             | 4 ++--
 drivers/dma/dmatest.c               | 2 +-
 drivers/dma/mv_xor.c                | 4 ++--
 drivers/ntb/ntb_transport.c         | 4 ++--
 drivers/ntb/test/ntb_perf.c         | 2 +-
 include/linux/dmaengine.h           | 4 ++--
 10 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/crypto/async_tx/async_memcpy.c b/crypto/async_tx/async_memcpy.c
index c538e30e99094..893e7e17f1f61 100644
--- a/crypto/async_tx/async_memcpy.c
+++ b/crypto/async_tx/async_memcpy.c
@@ -39,8 +39,8 @@ async_memcpy(struct page *dest, struct page *src, unsigned int dest_offset,
 	struct dma_async_tx_descriptor *tx = NULL;
 	struct dmaengine_unmap_data *unmap = NULL;
 
-	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
+	if (chan)
+		unmap = dmaengine_get_unmap_data(chan, 2, GFP_NOWAIT);
 
 	if (unmap && is_dma_copy_aligned(device, src_offset, dest_offset, len)) {
 		unsigned long dma_prep_flags = 0;
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 27f99349e310b..733af24a2762b 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -187,8 +187,8 @@ async_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 
 	BUG_ON(disks > MAX_DISKS || !(P(blocks, disks) || Q(blocks, disks)));
 
-	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
+	if (chan)
+		unmap = dmaengine_get_unmap_data(chan, disks, GFP_NOWAIT);
 
 	/* XORing P/Q is only implemented in software */
 	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
@@ -309,8 +309,8 @@ async_syndrome_val(struct page **blocks, unsigned int *offsets, int disks,
 
 	BUG_ON(disks < 4 || disks > MAX_DISKS);
 
-	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
+	if (chan)
+		unmap = dmaengine_get_unmap_data(chan, disks, GFP_NOWAIT);
 
 	if (unmap && disks <= dma_maxpq(device, 0) &&
 	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index e53870d84bc55..306448c47aa00 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -28,8 +28,8 @@ async_sum_product(struct page *dest, unsigned int d_off,
 	u8 ax, bx;
 	u8 *a, *b, *c;
 
-	if (dma)
-		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT);
+	if (chan)
+		unmap = dmaengine_get_unmap_data(chan, 3, GFP_NOWAIT);
 
 	if (unmap) {
 		struct device *dev = dma->dev;
@@ -96,8 +96,8 @@ async_mult(struct page *dest, unsigned int d_off, struct page *src,
 	const u8 *qmul; /* Q multiplier table */
 	u8 *d, *s;
 
-	if (dma)
-		unmap = dmaengine_get_unmap_data(dma->dev, 3, GFP_NOWAIT);
+	if (chan)
+		unmap = dmaengine_get_unmap_data(chan, 3, GFP_NOWAIT);
 
 	if (unmap) {
 		dma_addr_t dma_dest[2];
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 84458375b202b..40caee262a4ab 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -178,8 +178,8 @@ async_xor_offs(struct page *dest, unsigned int offset,
 
 	BUG_ON(src_cnt <= 1);
 
-	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, src_cnt+1, GFP_NOWAIT);
+	if (chan)
+		unmap = dmaengine_get_unmap_data(chan, src_cnt + 1, GFP_NOWAIT);
 
 	if (unmap && dma_xor_aligned_offsets(device, offset,
 				src_offs, src_cnt, len)) {
@@ -310,8 +310,8 @@ async_xor_val_offs(struct page *dest, unsigned int offset,
 
 	BUG_ON(src_cnt <= 1);
 
-	if (device)
-		unmap = dmaengine_get_unmap_data(device->dev, src_cnt, GFP_NOWAIT);
+	if (chan)
+		unmap = dmaengine_get_unmap_data(chan, src_cnt, GFP_NOWAIT);
 
 	if (unmap && src_cnt <= device->max_xor &&
 	    dma_xor_aligned_offsets(device, offset, src_offs, src_cnt, len)) {
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 34be53487a21d..52e7dcc4e5822 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1477,7 +1477,7 @@ static int __init dmaengine_init_unmap_pool(void)
 }
 
 struct dmaengine_unmap_data *
-dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
+dmaengine_get_unmap_data(struct dma_chan *chan, int nr, gfp_t flags)
 {
 	struct dmaengine_unmap_data *unmap;
 
@@ -1487,7 +1487,7 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 
 	memset(unmap, 0, sizeof(*unmap));
 	kref_init(&unmap->kref);
-	unmap->dev = dev;
+	unmap->dev = dmaengine_get_dma_device(chan);
 	unmap->map_cnt = nr;
 
 	return unmap;
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 2ae3469397f37..043bb065dd68a 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -748,7 +748,7 @@ static int dmatest_func(void *data)
 			filltime = ktime_add(filltime, diff);
 		}
 
-		um = dmaengine_get_unmap_data(dma_dev, src->cnt + dst->cnt,
+		um = dmaengine_get_unmap_data(chan, src->cnt + dst->cnt,
 					      GFP_KERNEL);
 		if (!um) {
 			failed_tests++;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index c4e0dce3ca64e..dec01b6264d7a 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -794,7 +794,7 @@ static int mv_chan_memcpy_self_test(struct mv_xor_chan *mv_chan)
 		goto out;
 	}
 
-	unmap = dmaengine_get_unmap_data(dma_chan->device->dev, 2, GFP_KERNEL);
+	unmap = dmaengine_get_unmap_data(dma_chan, 2, GFP_KERNEL);
 	if (!unmap) {
 		err = -ENOMEM;
 		goto free_resources;
@@ -927,7 +927,7 @@ mv_chan_xor_self_test(struct mv_xor_chan *mv_chan)
 		goto out;
 	}
 
-	unmap = dmaengine_get_unmap_data(dma_chan->device->dev, src_count + 1,
+	unmap = dmaengine_get_unmap_data(dma_chan, src_count + 1,
 					 GFP_KERNEL);
 	if (!unmap) {
 		err = -ENOMEM;
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index f9caa1a653c5b..e1cb55890d72b 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -1532,7 +1532,7 @@ static int ntb_async_rx_submit(struct ntb_queue_entry *entry, void *offset)
 	if (!is_dma_copy_aligned(device, pay_off, buff_off, len))
 		goto err;
 
-	unmap = dmaengine_get_unmap_data(device->dev, 2, GFP_NOWAIT);
+	unmap = dmaengine_get_unmap_data(chan, 2, GFP_NOWAIT);
 	if (!unmap)
 		goto err;
 
@@ -1872,7 +1872,7 @@ static int ntb_async_tx_submit(struct ntb_transport_qp *qp,
 	if (!is_dma_copy_aligned(device, buff_off, dest_off, len))
 		goto err;
 
-	unmap = dmaengine_get_unmap_data(device->dev, 1, GFP_NOWAIT);
+	unmap = dmaengine_get_unmap_data(chan, 1, GFP_NOWAIT);
 	if (!unmap)
 		goto err;
 
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index dfd175f79e8f0..5fea36432ba92 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -809,7 +809,7 @@ static int perf_copy_chunk(struct perf_thread *pthr,
 	dst_vaddr = dst;
 	dst_dma_addr = peer->dma_dst_addr + (dst_vaddr - vbase);
 
-	unmap = dmaengine_get_unmap_data(dma_dev, 1, GFP_NOWAIT);
+	unmap = dmaengine_get_unmap_data(pthr->dma_chan, 1, GFP_NOWAIT);
 	if (!unmap)
 		return -ENOMEM;
 
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 805668fbe4376..6d918ccf852f9 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -676,7 +676,7 @@ static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
 }
 
 struct dmaengine_unmap_data *
-dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags);
+dmaengine_get_unmap_data(struct dma_chan *chan, int nr, gfp_t flags);
 void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap);
 #else
 static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
@@ -684,7 +684,7 @@ static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx,
 {
 }
 static inline struct dmaengine_unmap_data *
-dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
+dmaengine_get_unmap_data(struct dma_chan *chan, int nr, gfp_t flags)
 {
 	return NULL;
 }
-- 
2.43.0

[PATCH v4 2/2] dmaengine: replace dma_maxqp() with dmaengine_maxpq() taking struct dma_chan *

[Frank.Li]

From: Frank Li <Frank.Li@nxp.com>

Replace dma_maxpq() with  dmaengine_maxpq(chan, flags) as a channel-based
API, consistent with the convention of other dmaengine_*() helpers that
take struct dma_chan * rather than struct dma_device *.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
---
change in v4: none, just respin because missed patch 2
Change in v3
split from original thread
https://lore.kernel.org/dmaengine/20260923-dmaengine_prep_dma_pq-v2-0-32ed65b8a9b4@nxp.com/
---
 crypto/async_tx/async_pq.c | 8 ++++----
 drivers/dma/dmatest.c      | 2 +-
 include/linux/dmaengine.h  | 6 ++++--
 3 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 733af24a2762b..37bc48bbda821 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -51,7 +51,7 @@ do_async_gen_syndrome(struct dma_chan *chan,
 
 	while (src_cnt > 0) {
 		submit->flags = flags_orig;
-		pq_src_cnt = min(src_cnt, dma_maxpq(dma, dma_flags));
+		pq_src_cnt = min(src_cnt, dmaengine_maxpq(chan, dma_flags));
 		/* if we are submitting additional pqs, leave the chain open,
 		 * clear the callback parameters, and leave the destination
 		 * buffers mapped
@@ -192,8 +192,8 @@ async_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 
 	/* XORing P/Q is only implemented in software */
 	if (unmap && !(submit->flags & ASYNC_TX_PQ_XOR_DST) &&
-	    (src_cnt <= dma_maxpq(device, 0) ||
-	     dma_maxpq(device, DMA_PREP_CONTINUE) > 0) &&
+	    (src_cnt <= dmaengine_maxpq(chan, 0) ||
+	     dmaengine_maxpq(chan, DMA_PREP_CONTINUE) > 0) &&
 	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = 0;
@@ -312,7 +312,7 @@ async_syndrome_val(struct page **blocks, unsigned int *offsets, int disks,
 	if (chan)
 		unmap = dmaengine_get_unmap_data(chan, disks, GFP_NOWAIT);
 
-	if (unmap && disks <= dma_maxpq(device, 0) &&
+	if (unmap && disks <= dmaengine_maxpq(chan, 0) &&
 	    is_dma_pq_aligned_offs(device, offsets, disks, len)) {
 		struct device *dev = device->dev;
 		dma_addr_t pq[2];
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 043bb065dd68a..01ab33580da81 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -636,7 +636,7 @@ static int dmatest_func(void *data)
 						params->alignment;
 	} else if (thread->type == DMA_PQ) {
 		/* force odd to ensure dst = src */
-		src->cnt = min_odd(params->pq_sources | 1, dma_maxpq(dev, 0));
+		src->cnt = min_odd(params->pq_sources | 1, dmaengine_maxpq(chan, 0));
 		dst->cnt = 2;
 		align = params->alignment < 0 ? dev->pq_align :
 						params->alignment;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 6d918ccf852f9..ef141892651d6 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1720,7 +1720,7 @@ static inline unsigned short dma_dev_to_maxpq(struct dma_device *dma)
 	return dma->max_pq & ~DMA_HAS_PQ_CONTINUE;
 }
 
-/* dma_maxpq - reduce maxpq in the face of continued operations
+/* dmaengine_maxpq - reduce maxpq in the face of continued operations
  * @dma - dma device with PQ capability
  * @flags - to check if DMA_PREP_CONTINUE and DMA_PREP_PQ_DISABLE_P are set
  *
@@ -1733,8 +1733,10 @@ static inline unsigned short dma_dev_to_maxpq(struct dma_device *dma)
  * In the case where P is disabled we only need 1 extra source:
  * 1/ {01} * Q : use Q to continue Q' calculation
  */
-static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags)
+static inline int dmaengine_maxpq(struct dma_chan *chan, enum dma_ctrl_flags flags)
 {
+	struct dma_device *dma = chan->device;
+
 	if (dma_dev_has_pq_continue(dma) || !dmaf_continue(flags))
 		return dma_dev_to_maxpq(dma);
 	if (dmaf_p_disabled_continue(flags))
-- 
2.43.0