tso_dma_map_next(9)

💅 tso_dma_map_next(9)

okay so bestie, welcome to the tso_dma_map_next page — straight out of the Kernel API Manual, and honestly? it's a little iterator baddie. it yields the next DMA address range and we're gonna walk through it together 🫶

---

✨ NAME ✨

tso_dma_map_next — yield the next DMA address range 🌈

---

✨ SYNOPSIS ✨

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 );

like, yes, that's a whole lot of parameters. deep breaths, we got this 💜

---

✨ ARGUMENTS ✨

• map — the payload map 🗺️ the main character of this whole operation, no cap.
• addr — output DMA address ✨ this is where the address gets written, it's an output bestie.
• chunk_len — output chunk length 📏 also an output, also important.
• mapping_len — full DMA mapping length when this chunk starts a new mapping region, or 0 when it's continuing a previous one. 🎀 on the IOVA path this is always 0 — and the driver must not do per-region unmaps, okay? use tso_dma_map_cleanup instead. that's the rule, periodt.
• seg_remaining — bytes left in current segment 🍓 literally just how many bytes are chilling in the segment rn.

---

✨ DESCRIPTION ✨

so what it does: yields the next (dma_addr, chunk_len) pair and advances the iterator. that's the vibe 💅

and on the IOVA path? the entire payload is contiguous, so each segment is always a single chunk. clean, simple, iconic ✨

---

✨ RETURN ✨

• true — a chunk was yielded 🔥 slay, we got data.
• false — when seg_remaining is 0. 😭 that's it, we're done, nothing left.

---

✨ SEE ALSO ✨

• Kernel file ./net/core/tso.c
• tso_dma_map_init(9)
• tso_dma_map_cleanup(9)
• tso_dma_map_count(9)

---

that's the whole page bestie, go forth and iterate 🦋

sign-off time 🎀 this one lives in ./net/core, dated October 2026 — mwah, bye! 💖