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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 47 insertions, 32 deletions

diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index d72b2e7..1883d61 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -45,9 +45,10 @@ struct ptr_ring {
 };
 
 /* Note: callers invoking this in a loop must use a compiler barrier,
- * for example cpu_relax().  If ring is ever resized, callers must hold
- * producer_lock - see e.g. ptr_ring_full.  Otherwise, if callers don't hold
- * producer_lock, the next call to __ptr_ring_produce may fail.
+ * for example cpu_relax().
+ *
+ * NB: this is unlike __ptr_ring_empty in that callers must hold producer_lock:
+ * see e.g. ptr_ring_full.
  */
 static inline bool __ptr_ring_full(struct ptr_ring *r)
 {
@@ -113,7 +114,7 @@ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 	/* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
 	smp_wmb();
 
-	r->queue[r->producer++] = ptr;
+	WRITE_ONCE(r->queue[r->producer++], ptr);
 	if (unlikely(r->producer >= r->size))
 		r->producer = 0;
 	return 0;
@@ -169,32 +170,36 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr)
 	return ret;
 }
 
-/* Note: callers invoking this in a loop must use a compiler barrier,
- * for example cpu_relax(). Callers must take consumer_lock
- * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL.
- * If ring is never resized, and if the pointer is merely
- * tested, there's no need to take the lock - see e.g.  __ptr_ring_empty.
- * However, if called outside the lock, and if some other CPU
- * consumes ring entries at the same time, the value returned
- * is not guaranteed to be correct.
- * In this case - to avoid incorrectly detecting the ring
- * as empty - the CPU consuming the ring entries is responsible
- * for either consuming all ring entries until the ring is empty,
- * or synchronizing with some other CPU and causing it to
- * execute __ptr_ring_peek and/or consume the ring enteries
- * after the synchronization point.
- */
 static inline void *__ptr_ring_peek(struct ptr_ring *r)
 {
 	if (likely(r->size))
-		return r->queue[r->consumer_head];
+		return READ_ONCE(r->queue[r->consumer_head]);
 	return NULL;
 }
 
-/* See __ptr_ring_peek above for locking rules. */
+/*
+ * Test ring empty status without taking any locks.
+ *
+ * NB: This is only safe to call if ring is never resized.
+ *
+ * However, if some other CPU consumes ring entries at the same time, the value
+ * returned is not guaranteed to be correct.
+ *
+ * In this case - to avoid incorrectly detecting the ring
+ * as empty - the CPU consuming the ring entries is responsible
+ * for either consuming all ring entries until the ring is empty,
+ * or synchronizing with some other CPU and causing it to
+ * re-test __ptr_ring_empty and/or consume the ring enteries
+ * after the synchronization point.
+ *
+ * Note: callers invoking this in a loop must use a compiler barrier,
+ * for example cpu_relax().
+ */
 static inline bool __ptr_ring_empty(struct ptr_ring *r)
 {
-	return !__ptr_ring_peek(r);
+	if (likely(r->size))
+		return !r->queue[READ_ONCE(r->consumer_head)];
+	return true;
 }
 
 static inline bool ptr_ring_empty(struct ptr_ring *r)
@@ -248,22 +253,28 @@ static inline void __ptr_ring_discard_one(struct ptr_ring *r)
 	/* Fundamentally, what we want to do is update consumer
 	 * index and zero out the entry so producer can reuse it.
 	 * Doing it naively at each consume would be as simple as:
-	 *       r->queue[r->consumer++] = NULL;
-	 *       if (unlikely(r->consumer >= r->size))
-	 *               r->consumer = 0;
+	 *       consumer = r->consumer;
+	 *       r->queue[consumer++] = NULL;
+	 *       if (unlikely(consumer >= r->size))
+	 *               consumer = 0;
+	 *       r->consumer = consumer;
 	 * but that is suboptimal when the ring is full as producer is writing
 	 * out new entries in the same cache line.  Defer these updates until a
 	 * batch of entries has been consumed.
 	 */
-	int head = r->consumer_head++;
+	/* Note: we must keep consumer_head valid at all times for __ptr_ring_empty
+	 * to work correctly.
+	 */
+	int consumer_head = r->consumer_head;
+	int head = consumer_head++;
 
 	/* Once we have processed enough entries invalidate them in
 	 * the ring all at once so producer can reuse their space in the ring.
 	 * We also do this when we reach end of the ring - not mandatory
 	 * but helps keep the implementation simple.
 	 */
-	if (unlikely(r->consumer_head - r->consumer_tail >= r->batch ||
-		     r->consumer_head >= r->size)) {
+	if (unlikely(consumer_head - r->consumer_tail >= r->batch ||
+		     consumer_head >= r->size)) {
 		/* Zero out entries in the reverse order: this way we touch the
 		 * cache line that producer might currently be reading the last;
 		 * producer won't make progress and touch other cache lines
@@ -271,12 +282,14 @@ static inline void __ptr_ring_discard_one(struct ptr_ring *r)
 		 */
 		while (likely(head >= r->consumer_tail))
 			r->queue[head--] = NULL;
-		r->consumer_tail = r->consumer_head;
+		r->consumer_tail = consumer_head;
 	}
-	if (unlikely(r->consumer_head >= r->size)) {
-		r->consumer_head = 0;
+	if (unlikely(consumer_head >= r->size)) {
+		consumer_head = 0;
 		r->consumer_tail = 0;
 	}
+	/* matching READ_ONCE in __ptr_ring_empty for lockless tests */
+	WRITE_ONCE(r->consumer_head, consumer_head);
 }
 
 static inline void *__ptr_ring_consume(struct ptr_ring *r)
@@ -527,7 +540,9 @@ static inline void ptr_ring_unconsume(struct ptr_ring *r, void **batch, int n,
 			goto done;
 		}
 		r->queue[head] = batch[--n];
-		r->consumer_tail = r->consumer_head = head;
+		r->consumer_tail = head;
+		/* matching READ_ONCE in __ptr_ring_empty for lockless tests */
+		WRITE_ONCE(r->consumer_head, head);
 	}
 
 done: