[net-next v9 01/10] net: tso: Introduce tso_dma_map and helpers

[Joe Damato <joe@dama.to>]

Add struct tso_dma_map to tso.h for tracking DMA addresses of mapped
GSO payload data and tso_dma_map_completion_state.

The tso_dma_map combines DMA mapping storage with iterator state, allowing
drivers to walk pre-mapped DMA regions linearly. Includes fields for
the DMA IOVA path (iova_state, iova_offset, total_len) and a fallback
per-region path (linear_dma, frags[], frag_idx, offset).

The tso_dma_map_completion_state makes the IOVA completion state opaque
for drivers. Drivers are expected to allocate this and use the added
helpers to update the completion state.

Adds skb_frag_phys() to skbuff.h, returning the physical address
of a paged fragment's data, which is used by the tso_dma_map helpers
introduced in this commit described below.

The added TSO DMA map helpers are:

tso_dma_map_init(): DMA-maps the linear payload region and all frags
upfront. Prefers the DMA IOVA API for a single contiguous mapping with
one IOTLB sync; falls back to per-region dma_map_phys() otherwise.
Returns 0 on success, cleans up partial mappings on failure.

tso_dma_map_cleanup(): Handles both IOVA and fallback teardown paths.

tso_dma_map_count(): counts how many descriptors the next N bytes of
payload will need. Returns 1 if IOVA is used since the mapping is
contiguous.

tso_dma_map_next(): yields the next (dma_addr, chunk_len) pair.
On the IOVA path, each segment is a single contiguous chunk. On the
fallback path, indicates when a chunk starts a new DMA mapping so the
driver can set dma_unmap_len on that descriptor for completion-time
unmapping.

tso_dma_map_completion_save(): updates the completion state. Drivers
will call this at xmit time.

tso_dma_map_complete(): tears down the mapping at completion time and
returns true if the IOVA path was used. If it was not used, this is a
no-op and returns false.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Joe Damato <joe@dama.to>
---
 v9:
   - Fix typo in commit message.
   - Fix kdoc.
   - Initialize tso_dma_map before early return in tso_dma_map_init
     (suggested by AI).

 v7:
   - Squashed the struct and helpers (patch 1 and 2 from v6) into this one
     patch.
   - Added tso_dma_map_completion_state and helpers
     tso_dma_map_completion_save and tso_dma_map_complete to operate on the
     struct and keep the DMA IOVA completely opaque from drivers.
   - Removed unnecessary duplicated code in tso_dma_map_next and
     tso_dma_map_cleanup.

 v4:
   - Fix the kdoc for the TSO helpers. No functional changes.

 v3:
   - struct tso_dma_map extended to track IOVA state and
     a fallback per-region path.
   - Added skb_frag_phys helper include/linux/skbuff.h.
   - Added tso_dma_map_use_iova() inline helper in tso.h.
   - Updated the helpers to use the DMA IOVA API and falls back to per-region
     mapping instead.

 include/linux/skbuff.h |  11 ++
 include/net/tso.h      | 100 +++++++++++++++
 net/core/tso.c         | 269 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 380 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 26fe18bcfad8..2bcf78a4de7b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3763,6 +3763,17 @@ static inline void *skb_frag_address_safe(const skb_frag_t *frag)
 	return ptr + skb_frag_off(frag);
 }
 
+/**
+ * skb_frag_phys - gets the physical address of the data in a paged fragment
+ * @frag: the paged fragment buffer
+ *
+ * Returns: the physical address of the data within @frag.
+ */
+static inline phys_addr_t skb_frag_phys(const skb_frag_t *frag)
+{
+	return page_to_phys(skb_frag_page(frag)) + skb_frag_off(frag);
+}
+
 /**
  * skb_frag_page_copy() - sets the page in a fragment from another fragment
  * @fragto: skb fragment where page is set
diff --git a/include/net/tso.h b/include/net/tso.h
index e7e157ae0526..da82aabd1d48 100644
--- a/include/net/tso.h
+++ b/include/net/tso.h
@@ -3,6 +3,7 @@
 #define _TSO_H
 
 #include <linux/skbuff.h>
+#include <linux/dma-mapping.h>
 #include <net/ip.h>
 
 #define TSO_HEADER_SIZE		256
@@ -28,4 +29,103 @@ void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso,
 void tso_build_data(const struct sk_buff *skb, struct tso_t *tso, int size);
 int tso_start(struct sk_buff *skb, struct tso_t *tso);
 
+/**
+ * struct tso_dma_map - DMA mapping state for GSO payload
+ * @dev: device used for DMA mapping
+ * @skb: the GSO skb being mapped
+ * @hdr_len: per-segment header length
+ * @iova_state: DMA IOVA state (when IOMMU available)
+ * @iova_offset: global byte offset into IOVA range (IOVA path only)
+ * @total_len: total payload length
+ * @frag_idx: current region (-1 = linear, 0..nr_frags-1 = frag)
+ * @offset: byte offset within current region
+ * @linear_dma: DMA address of the linear payload
+ * @linear_len: length of the linear payload
+ * @nr_frags: number of frags successfully DMA-mapped
+ * @frags: per-frag DMA address and length
+ *
+ * DMA-maps the payload regions of a GSO skb (linear data + frags).
+ * Prefers the DMA IOVA API for a single contiguous mapping with one
+ * IOTLB sync; falls back to per-region dma_map_phys() otherwise.
+ */
+struct tso_dma_map {
+	struct device		*dev;
+	const struct sk_buff	*skb;
+	unsigned int		hdr_len;
+	/* IOVA path */
+	struct dma_iova_state	iova_state;
+	size_t			iova_offset;
+	size_t			total_len;
+	/* Fallback path if IOVA path fails */
+	int			frag_idx;
+	unsigned int		offset;
+	dma_addr_t		linear_dma;
+	unsigned int		linear_len;
+	unsigned int		nr_frags;
+	struct {
+		dma_addr_t	dma;
+		unsigned int	len;
+	} frags[MAX_SKB_FRAGS];
+};
+
+/**
+ * struct tso_dma_map_completion_state - Completion-time cleanup state
+ * @iova_state: DMA IOVA state (when IOMMU available)
+ * @total_len: total payload length of the IOVA mapping
+ *
+ * Drivers store this on their SW ring at xmit time via
+ * tso_dma_map_completion_save(), then call tso_dma_map_complete() at
+ * completion time.
+ */
+struct tso_dma_map_completion_state {
+	struct dma_iova_state iova_state;
+	size_t total_len;
+};
+
+int tso_dma_map_init(struct tso_dma_map *map, struct device *dev,
+		     const struct sk_buff *skb, unsigned int hdr_len);
+void tso_dma_map_cleanup(struct tso_dma_map *map);
+unsigned int tso_dma_map_count(struct tso_dma_map *map, unsigned int len);
+bool tso_dma_map_next(struct tso_dma_map *map, dma_addr_t *addr,
+		      unsigned int *chunk_len, unsigned int *mapping_len,
+		      unsigned int seg_remaining);
+
+/**
+ * tso_dma_map_completion_save - save state needed for completion-time cleanup
+ * @map: the xmit-time DMA map
+ * @cstate: driver-owned storage that persists until completion
+ *
+ * Should be called at xmit time to update the completion state and later passed
+ * to tso_dma_map_complete().
+ */
+static inline void
+tso_dma_map_completion_save(const struct tso_dma_map *map,
+			    struct tso_dma_map_completion_state *cstate)
+{
+	cstate->iova_state = map->iova_state;
+	cstate->total_len = map->total_len;
+}
+
+/**
+ * tso_dma_map_complete - tear down mapping at completion time
+ * @dev: the device that owns the mapping
+ * @cstate: state saved by tso_dma_map_completion_save()
+ *
+ * Return: true if the IOVA path was used and the mapping has been
+ * destroyed; false if the fallback per-region path was used and the
+ * driver must unmap via its normal completion path.
+ */
+static inline bool
+tso_dma_map_complete(struct device *dev,
+		     struct tso_dma_map_completion_state *cstate)
+{
+	if (dma_use_iova(&cstate->iova_state)) {
+		dma_iova_destroy(dev, &cstate->iova_state, cstate->total_len,
+				 DMA_TO_DEVICE, 0);
+		return true;
+	}
+
+	return false;
+}
+
 #endif	/* _TSO_H */
diff --git a/net/core/tso.c b/net/core/tso.c
index 6df997b9076e..f2e625e7b64f 100644
--- a/net/core/tso.c
+++ b/net/core/tso.c
@@ -3,6 +3,7 @@
 #include <linux/if_vlan.h>
 #include <net/ip.h>
 #include <net/tso.h>
+#include <linux/dma-mapping.h>
 #include <linux/unaligned.h>
 
 void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso,
@@ -87,3 +88,271 @@ int tso_start(struct sk_buff *skb, struct tso_t *tso)
 	return hdr_len;
 }
 EXPORT_SYMBOL(tso_start);
+
+static int tso_dma_iova_try(struct device *dev, struct tso_dma_map *map,
+			    phys_addr_t phys, size_t linear_len, size_t total_len,
+			    size_t *offset)
+{
+	const struct sk_buff *skb;
+	unsigned int nr_frags;
+	int i;
+
+	if (!dma_iova_try_alloc(dev, &map->iova_state, phys, total_len))
+		return 1;
+
+	skb = map->skb;
+	nr_frags = skb_shinfo(skb)->nr_frags;
+
+	if (linear_len) {
+		if (dma_iova_link(dev, &map->iova_state,
+				  phys, *offset, linear_len,
+				  DMA_TO_DEVICE, 0))
+			goto iova_fail;
+		map->linear_len = linear_len;
+		*offset += linear_len;
+	}
+
+	for (i = 0; i < nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		unsigned int frag_len = skb_frag_size(frag);
+
+		if (dma_iova_link(dev, &map->iova_state,
+				  skb_frag_phys(frag), *offset,
+				  frag_len, DMA_TO_DEVICE, 0)) {
+			map->nr_frags = i;
+			goto iova_fail;
+		}
+		map->frags[i].len = frag_len;
+		*offset += frag_len;
+		map->nr_frags = i + 1;
+	}
+
+	if (dma_iova_sync(dev, &map->iova_state, 0, total_len))
+		goto iova_fail;
+
+	return 0;
+
+iova_fail:
+	dma_iova_destroy(dev, &map->iova_state, *offset,
+			 DMA_TO_DEVICE, 0);
+	memset(&map->iova_state, 0, sizeof(map->iova_state));
+
+	/* reset map state */
+	map->frag_idx = -1;
+	map->offset = 0;
+	map->linear_len = 0;
+	map->nr_frags = 0;
+
+	return 1;
+}
+
+/**
+ * tso_dma_map_init - DMA-map GSO payload regions
+ * @map: map struct to initialize
+ * @dev: device for DMA mapping
+ * @skb: the GSO skb
+ * @hdr_len: per-segment header length in bytes
+ *
+ * DMA-maps the linear payload (after headers) and all frags.
+ * Prefers the DMA IOVA API (one contiguous mapping, one IOTLB sync);
+ * falls back to per-region dma_map_phys() when IOVA is not available.
+ * Positions the iterator at byte 0 of the payload.
+ *
+ * Return: 0 on success, -ENOMEM on DMA mapping failure (partial mappings
+ * are cleaned up internally).
+ */
+int tso_dma_map_init(struct tso_dma_map *map, struct device *dev,
+		     const struct sk_buff *skb, unsigned int hdr_len)
+{
+	unsigned int linear_len = skb_headlen(skb) - hdr_len;
+	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
+	size_t total_len = skb->len - hdr_len;
+	size_t offset = 0;
+	phys_addr_t phys;
+	int i;
+
+	map->dev = dev;
+	map->skb = skb;
+	map->hdr_len = hdr_len;
+	map->frag_idx = -1;
+	map->offset = 0;
+	map->iova_offset = 0;
+	map->total_len = total_len;
+	map->linear_len = 0;
+	map->nr_frags = 0;
+	memset(&map->iova_state, 0, sizeof(map->iova_state));
+
+	if (!total_len)
+		return 0;
+
+	if (linear_len)
+		phys = virt_to_phys(skb->data + hdr_len);
+	else
+		phys = skb_frag_phys(&skb_shinfo(skb)->frags[0]);
+
+	if (tso_dma_iova_try(dev, map, phys, linear_len, total_len, &offset)) {
+		/* IOVA path failed, map state was reset. Fallback to
+		 * per-region dma_map_phys()
+		 */
+		if (linear_len) {
+			map->linear_dma = dma_map_phys(dev, phys, linear_len,
+						       DMA_TO_DEVICE, 0);
+			if (dma_mapping_error(dev, map->linear_dma))
+				return -ENOMEM;
+			map->linear_len = linear_len;
+		}
+
+		for (i = 0; i < nr_frags; i++) {
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+			unsigned int frag_len = skb_frag_size(frag);
+
+			map->frags[i].len = frag_len;
+			map->frags[i].dma = dma_map_phys(dev, skb_frag_phys(frag),
+							 frag_len, DMA_TO_DEVICE, 0);
+			if (dma_mapping_error(dev, map->frags[i].dma)) {
+				tso_dma_map_cleanup(map);
+				return -ENOMEM;
+			}
+			map->nr_frags = i + 1;
+		}
+	}
+
+	if (linear_len == 0 && nr_frags > 0)
+		map->frag_idx = 0;
+
+	return 0;
+}
+EXPORT_SYMBOL(tso_dma_map_init);
+
+/**
+ * tso_dma_map_cleanup - unmap all DMA regions in a tso_dma_map
+ * @map: the map to clean up
+ *
+ * Handles both IOVA and fallback paths. For IOVA, calls
+ * dma_iova_destroy(). For fallback, unmaps each region individually.
+ */
+void tso_dma_map_cleanup(struct tso_dma_map *map)
+{
+	int i;
+
+	if (dma_use_iova(&map->iova_state)) {
+		dma_iova_destroy(map->dev, &map->iova_state, map->total_len,
+				 DMA_TO_DEVICE, 0);
+		memset(&map->iova_state, 0, sizeof(map->iova_state));
+	} else {
+		if (map->linear_len)
+			dma_unmap_phys(map->dev, map->linear_dma, map->linear_len,
+				       DMA_TO_DEVICE, 0);
+
+		for (i = 0; i < map->nr_frags; i++)
+			dma_unmap_phys(map->dev, map->frags[i].dma, map->frags[i].len,
+				       DMA_TO_DEVICE, 0);
+	}
+
+	map->linear_len = 0;
+	map->nr_frags = 0;
+}
+EXPORT_SYMBOL(tso_dma_map_cleanup);
+
+/**
+ * tso_dma_map_count - count descriptors for a payload range
+ * @map: the payload map
+ * @len: number of payload bytes in this segment
+ *
+ * Counts how many contiguous DMA region chunks the next @len bytes
+ * will span, without advancing the iterator. On the IOVA path this
+ * is always 1 (contiguous). On the fallback path, uses region sizes
+ * from the current position.
+ *
+ * Return: the number of descriptors needed for @len bytes of payload.
+ */
+unsigned int tso_dma_map_count(struct tso_dma_map *map, unsigned int len)
+{
+	unsigned int offset = map->offset;
+	int idx = map->frag_idx;
+	unsigned int count = 0;
+
+	if (!len)
+		return 0;
+
+	if (dma_use_iova(&map->iova_state))
+		return 1;
+
+	while (len > 0) {
+		unsigned int region_len, chunk;
+
+		if (idx == -1)
+			region_len = map->linear_len;
+		else
+			region_len = map->frags[idx].len;
+
+		chunk = min(len, region_len - offset);
+		len -= chunk;
+		count++;
+		offset = 0;
+		idx++;
+	}
+
+	return count;
+}
+EXPORT_SYMBOL(tso_dma_map_count);
+
+/**
+ * tso_dma_map_next - yield the next DMA address range
+ * @map: the payload map
+ * @addr: output DMA address
+ * @chunk_len: output chunk length
+ * @mapping_len: full DMA mapping length when this chunk starts a new
+ *               mapping region, or 0 when continuing a previous one.
+ *               On the IOVA path this is always 0 (driver must not
+ *               do per-region unmaps; use tso_dma_map_cleanup instead).
+ * @seg_remaining: bytes left in current segment
+ *
+ * Yields the next (dma_addr, chunk_len) pair and advances the iterator.
+ * On the IOVA path, the entire payload is contiguous so each segment
+ * is always a single chunk.
+ *
+ * Return: true if a chunk was yielded, false when @seg_remaining is 0.
+ */
+bool tso_dma_map_next(struct tso_dma_map *map, dma_addr_t *addr,
+		      unsigned int *chunk_len, unsigned int *mapping_len,
+		      unsigned int seg_remaining)
+{
+	unsigned int region_len, chunk;
+
+	if (!seg_remaining)
+		return false;
+
+	/* IOVA path: contiguous DMA range, no region boundaries */
+	if (dma_use_iova(&map->iova_state)) {
+		*addr = map->iova_state.addr + map->iova_offset;
+		*chunk_len = seg_remaining;
+		*mapping_len = 0;
+		map->iova_offset += seg_remaining;
+		return true;
+	}
+
+	/* Fallback path: per-region iteration */
+
+	if (map->frag_idx == -1) {
+		region_len = map->linear_len;
+		chunk = min(seg_remaining, region_len - map->offset);
+		*addr = map->linear_dma + map->offset;
+	} else {
+		region_len = map->frags[map->frag_idx].len;
+		chunk = min(seg_remaining, region_len - map->offset);
+		*addr = map->frags[map->frag_idx].dma + map->offset;
+	}
+
+	*mapping_len = (map->offset == 0) ? region_len : 0;
+	*chunk_len = chunk;
+	map->offset += chunk;
+
+	if (map->offset >= region_len) {
+		map->frag_idx++;
+		map->offset = 0;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(tso_dma_map_next);
-- 
2.52.0