xsk: add support to allow unaligned chunk placement

Currently, addresses are chunk size aligned. This means, we are very
restricted in terms of where we can place chunk within the umem. For
example, if we have a chunk size of 2k, then our chunks can only be placed
at 0,2k,4k,6k,8k... and so on (ie. every 2k starting from 0).

This patch introduces the ability to use unaligned chunks. With these
changes, we are no longer bound to having to place chunks at a 2k (or
whatever your chunk size is) interval. Since we are no longer dealing with
aligned chunks, they can now cross page boundaries. Checks for page
contiguity have been added in order to keep track of which pages are
followed by a physically contiguous page.

Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 62 insertions, 8 deletions

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index dd9e985c2461..eddae4688862 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -134,6 +134,17 @@ static inline bool xskq_has_addrs(struct xsk_queue *q, u32 cnt)
 
 /* UMEM queue */
 
+static inline bool xskq_crosses_non_contig_pg(struct xdp_umem *umem, u64 addr,
+					      u64 length)
+{
+	bool cross_pg = (addr & (PAGE_SIZE - 1)) + length > PAGE_SIZE;
+	bool next_pg_contig =
+		(unsigned long)umem->pages[(addr >> PAGE_SHIFT)].addr &
+			XSK_NEXT_PG_CONTIG_MASK;
+
+	return cross_pg && !next_pg_contig;
+}
+
 static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr)
 {
 	if (addr >= q->size) {
@@ -144,23 +155,51 @@ static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr)
 	return true;
 }
 
-static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr)
+static inline bool xskq_is_valid_addr_unaligned(struct xsk_queue *q, u64 addr,
+						u64 length,
+						struct xdp_umem *umem)
+{
+	u64 base_addr = xsk_umem_extract_addr(addr);
+
+	addr = xsk_umem_add_offset_to_addr(addr);
+	if (base_addr >= q->size || addr >= q->size ||
+	    xskq_crosses_non_contig_pg(umem, addr, length)) {
+		q->invalid_descs++;
+		return false;
+	}
+
+	return true;
+}
+
+static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr,
+				      struct xdp_umem *umem)
 {
 	while (q->cons_tail != q->cons_head) {
 		struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
 		unsigned int idx = q->cons_tail & q->ring_mask;
 
 		*addr = READ_ONCE(ring->desc[idx]) & q->chunk_mask;
+
+		if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) {
+			if (xskq_is_valid_addr_unaligned(q, *addr,
+							 umem->chunk_size_nohr,
+							 umem))
+				return addr;
+			goto out;
+		}
+
 		if (xskq_is_valid_addr(q, *addr))
 			return addr;
 
+out:
 		q->cons_tail++;
 	}
 
 	return NULL;
 }
 
-static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr)
+static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr,
+				  struct xdp_umem *umem)
 {
 	if (q->cons_tail == q->cons_head) {
 		smp_mb(); /* D, matches A */
@@ -171,7 +210,7 @@ static inline u64 *xskq_peek_addr(struct xsk_queue *q, u64 *addr)
 		smp_rmb();
 	}
 
-	return xskq_validate_addr(q, addr);
+	return xskq_validate_addr(q, addr, umem);
 }
 
 static inline void xskq_discard_addr(struct xsk_queue *q)
@@ -230,8 +269,21 @@ static inline int xskq_reserve_addr(struct xsk_queue *q)
 
 /* Rx/Tx queue */
 
-static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d)
+static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d,
+				      struct xdp_umem *umem)
 {
+	if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) {
+		if (!xskq_is_valid_addr_unaligned(q, d->addr, d->len, umem))
+			return false;
+
+		if (d->len > umem->chunk_size_nohr || d->options) {
+			q->invalid_descs++;
+			return false;
+		}
+
+		return true;
+	}
+
 	if (!xskq_is_valid_addr(q, d->addr))
 		return false;
 
@@ -245,14 +297,15 @@ static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d)
 }
 
 static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q,
-						  struct xdp_desc *desc)
+						  struct xdp_desc *desc,
+						  struct xdp_umem *umem)
 {
 	while (q->cons_tail != q->cons_head) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		unsigned int idx = q->cons_tail & q->ring_mask;
 
 		*desc = READ_ONCE(ring->desc[idx]);
-		if (xskq_is_valid_desc(q, desc))
+		if (xskq_is_valid_desc(q, desc, umem))
 			return desc;
 
 		q->cons_tail++;
@@ -262,7 +315,8 @@ static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q,
 }
 
 static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q,
-					      struct xdp_desc *desc)
+					      struct xdp_desc *desc,
+					      struct xdp_umem *umem)
 {
 	if (q->cons_tail == q->cons_head) {
 		smp_mb(); /* D, matches A */
@@ -273,7 +327,7 @@ static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q,
 		smp_rmb(); /* C, matches B */
 	}
 
-	return xskq_validate_desc(q, desc);
+	return xskq_validate_desc(q, desc, umem);
 }
 
 static inline void xskq_discard_desc(struct xsk_queue *q)