Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-05-23

The following pull-request contains BPF updates for your *net-next* tree.

We've added 50 non-merge commits during the last 8 day(s) which contain
a total of 109 files changed, 2776 insertions(+), 2887 deletions(-).

The main changes are:

1) Add a new AF_XDP buffer allocation API to the core in order to help
   lowering the bar for drivers adopting AF_XDP support. i40e, ice, ixgbe
   as well as mlx5 have been moved over to the new API and also gained a
   small improvement in performance, from Björn Töpel and Magnus Karlsson.

2) Add getpeername()/getsockname() attach types for BPF sock_addr programs
   in order to allow for e.g. reverse translation of load-balancer backend
   to service address/port tuple from a connected peer, from Daniel Borkmann.

3) Improve the BPF verifier is_branch_taken() logic to evaluate pointers
   being non-NULL, e.g. if after an initial test another non-NULL test on
   that pointer follows in a given path, then it can be pruned right away,
   from John Fastabend.

4) Larger rework of BPF sockmap selftests to make output easier to understand
   and to reduce overall runtime as well as adding new BPF kTLS selftests
   that run in combination with sockmap, also from John Fastabend.

5) Batch of misc updates to BPF selftests including fixing up test_align
   to match verifier output again and moving it under test_progs, allowing
   bpf_iter selftest to compile on machines with older vmlinux.h, and
   updating config options for lirc and v6 segment routing helpers, from
   Stanislav Fomichev, Andrii Nakryiko and Alan Maguire.

6) Conversion of BPF tracing samples outdated internal BPF loader to use
   libbpf API instead, from Daniel T. Lee.

7) Follow-up to BPF kernel test infrastructure in order to fix a flake in
   the XDP selftests, from Jesper Dangaard Brouer.

8) Minor improvements to libbpf's internal hashmap implementation, from
   Ian Rogers.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 44 insertions, 73 deletions

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 648733ec24ac..5b5d24d2dd37 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -9,6 +9,9 @@
 #include <linux/types.h>
 #include <linux/if_xdp.h>
 #include <net/xdp_sock.h>
+#include <net/xsk_buff_pool.h>
+
+#include "xsk.h"
 
 struct xdp_ring {
 	u32 producer ____cacheline_aligned_in_smp;
@@ -29,8 +32,6 @@ struct xdp_umem_ring {
 };
 
 struct xsk_queue {
-	u64 chunk_mask;
-	u64 umem_size;
 	u32 ring_mask;
 	u32 nentries;
 	u32 cached_prod;
@@ -103,98 +104,73 @@ struct xsk_queue {
 
 /* Functions that read and validate content from consumer rings. */
 
-static inline bool xskq_cons_crosses_non_contig_pg(struct xdp_umem *umem,
-						   u64 addr,
-						   u64 length)
+static inline bool xskq_cons_read_addr_unchecked(struct xsk_queue *q, u64 *addr)
 {
-	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;
-}
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
 
-static inline bool xskq_cons_is_valid_unaligned(struct xsk_queue *q,
-						u64 addr,
-						u64 length,
-						struct xdp_umem *umem)
-{
-	u64 base_addr = xsk_umem_extract_addr(addr);
+	if (q->cached_cons != q->cached_prod) {
+		u32 idx = q->cached_cons & q->ring_mask;
 
-	addr = xsk_umem_add_offset_to_addr(addr);
-	if (base_addr >= q->umem_size || addr >= q->umem_size ||
-	    xskq_cons_crosses_non_contig_pg(umem, addr, length)) {
-		q->invalid_descs++;
-		return false;
+		*addr = ring->desc[idx];
+		return true;
 	}
 
-	return true;
+	return false;
 }
 
-static inline bool xskq_cons_is_valid_addr(struct xsk_queue *q, u64 addr)
+static inline bool xp_aligned_validate_desc(struct xsk_buff_pool *pool,
+					    struct xdp_desc *desc)
 {
-	if (addr >= q->umem_size) {
-		q->invalid_descs++;
+	u64 chunk, chunk_end;
+
+	chunk = xp_aligned_extract_addr(pool, desc->addr);
+	chunk_end = xp_aligned_extract_addr(pool, desc->addr + desc->len);
+	if (chunk != chunk_end)
+		return false;
+
+	if (chunk >= pool->addrs_cnt)
 		return false;
-	}
 
+	if (desc->options)
+		return false;
 	return true;
 }
 
-static inline bool xskq_cons_read_addr(struct xsk_queue *q, u64 *addr,
-				       struct xdp_umem *umem)
+static inline bool xp_unaligned_validate_desc(struct xsk_buff_pool *pool,
+					      struct xdp_desc *desc)
 {
-	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
-
-	while (q->cached_cons != q->cached_prod) {
-		u32 idx = q->cached_cons & q->ring_mask;
+	u64 addr, base_addr;
 
-		*addr = ring->desc[idx] & q->chunk_mask;
+	base_addr = xp_unaligned_extract_addr(desc->addr);
+	addr = xp_unaligned_add_offset_to_addr(desc->addr);
 
-		if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG) {
-			if (xskq_cons_is_valid_unaligned(q, *addr,
-							 umem->chunk_size_nohr,
-							 umem))
-				return true;
-			goto out;
-		}
+	if (desc->len > pool->chunk_size)
+		return false;
 
-		if (xskq_cons_is_valid_addr(q, *addr))
-			return true;
+	if (base_addr >= pool->addrs_cnt || addr >= pool->addrs_cnt ||
+	    xp_desc_crosses_non_contig_pg(pool, addr, desc->len))
+		return false;
 
-out:
-		q->cached_cons++;
-	}
+	if (desc->options)
+		return false;
+	return true;
+}
 
-	return false;
+static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
+				    struct xdp_desc *desc)
+{
+	return pool->unaligned ? xp_unaligned_validate_desc(pool, desc) :
+		xp_aligned_validate_desc(pool, desc);
 }
 
 static inline bool xskq_cons_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_cons_is_valid_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_cons_is_valid_addr(q, d->addr))
-		return false;
-
-	if (((d->addr + d->len) & q->chunk_mask) != (d->addr & q->chunk_mask) ||
-	    d->options) {
+	if (!xp_validate_desc(umem->pool, d)) {
 		q->invalid_descs++;
 		return false;
 	}
-
 	return true;
 }
 
@@ -250,12 +226,11 @@ static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt)
 	return entries >= cnt;
 }
 
-static inline bool xskq_cons_peek_addr(struct xsk_queue *q, u64 *addr,
-				       struct xdp_umem *umem)
+static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
 {
 	if (q->cached_prod == q->cached_cons)
 		xskq_cons_get_entries(q);
-	return xskq_cons_read_addr(q, addr, umem);
+	return xskq_cons_read_addr_unchecked(q, addr);
 }
 
 static inline bool xskq_cons_peek_desc(struct xsk_queue *q,
@@ -379,11 +354,7 @@ static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q)
 	return q ? q->invalid_descs : 0;
 }
 
-void xskq_set_umem(struct xsk_queue *q, u64 umem_size, u64 chunk_mask);
 struct xsk_queue *xskq_create(u32 nentries, bool umem_queue);
 void xskq_destroy(struct xsk_queue *q_ops);
 
-/* Executed by the core when the entire UMEM gets freed */
-void xsk_reuseq_destroy(struct xdp_umem *umem);
-
 #endif /* _LINUX_XSK_QUEUE_H */