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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 44 insertions, 73 deletions

diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index b50bb5c76da5..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 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->size || addr >= q->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->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 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 */