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

Pull networking updates from David Millar:
 "Here are some highlights from the 2065 networking commits that
  happened this development cycle:

   1) XDP support for IXGBE (John Fastabend) and thunderx (Sunil Kowuri)

   2) Add a generic XDP driver, so that anyone can test XDP even if they
      lack a networking device whose driver has explicit XDP support
      (me).

   3) Sparc64 now has an eBPF JIT too (me)

   4) Add a BPF program testing framework via BPF_PROG_TEST_RUN (Alexei
      Starovoitov)

   5) Make netfitler network namespace teardown less expensive (Florian
      Westphal)

   6) Add symmetric hashing support to nft_hash (Laura Garcia Liebana)

   7) Implement NAPI and GRO in netvsc driver (Stephen Hemminger)

   8) Support TC flower offload statistics in mlxsw (Arkadi Sharshevsky)

   9) Multiqueue support in stmmac driver (Joao Pinto)

  10) Remove TCP timewait recycling, it never really could possibly work
      well in the real world and timestamp randomization really zaps any
      hint of usability this feature had (Soheil Hassas Yeganeh)

  11) Support level3 vs level4 ECMP route hashing in ipv4 (Nikolay
      Aleksandrov)

  12) Add socket busy poll support to epoll (Sridhar Samudrala)

  13) Netlink extended ACK support (Johannes Berg, Pablo Neira Ayuso,
      and several others)

  14) IPSEC hw offload infrastructure (Steffen Klassert)"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2065 commits)
  tipc: refactor function tipc_sk_recv_stream()
  tipc: refactor function tipc_sk_recvmsg()
  net: thunderx: Optimize page recycling for XDP
  net: thunderx: Support for XDP header adjustment
  net: thunderx: Add support for XDP_TX
  net: thunderx: Add support for XDP_DROP
  net: thunderx: Add basic XDP support
  net: thunderx: Cleanup receive buffer allocation
  net: thunderx: Optimize CQE_TX handling
  net: thunderx: Optimize RBDR descriptor handling
  net: thunderx: Support for page recycling
  ipx: call ipxitf_put() in ioctl error path
  net: sched: add helpers to handle extended actions
  qed*: Fix issues in the ptp filter config implementation.
  qede: Fix concurrency issue in PTP Tx path processing.
  stmmac: Add support for SIMATIC IOT2000 platform
  net: hns: fix ethtool_get_strings overflow in hns driver
  tcp: fix wraparound issue in tcp_lp
  bpf, arm64: fix jit branch offset related to ldimm64
  bpf, arm64: implement jiting of BPF_XADD
  ...

6 files changed, 110 insertions, 14 deletions

diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 8f76b13..d5990eb 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -419,7 +419,7 @@ error_do_abort:
 	call->state = AFS_CALL_COMPLETE;
 	if (ret != -ECONNABORTED) {
 		rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT,
-					-ret, "KSD");
+					ret, "KSD");
 	} else {
 		abort_code = 0;
 		offset = 0;
@@ -478,12 +478,12 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -ENOTCONN:
 			abort_code = RX_CALL_DEAD;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, -ret, "KNC");
+						abort_code, ret, "KNC");
 			goto save_error;
 		case -ENOTSUPP:
 			abort_code = RXGEN_OPCODE;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, -ret, "KIV");
+						abort_code, ret, "KIV");
 			goto save_error;
 		case -ENODATA:
 		case -EBADMSG:
@@ -493,7 +493,7 @@ static void afs_deliver_to_call(struct afs_call *call)
 			if (call->state != AFS_CALL_AWAIT_REPLY)
 				abort_code = RXGEN_SS_UNMARSHAL;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, EBADMSG, "KUM");
+						abort_code, -EBADMSG, "KUM");
 			goto save_error;
 		}
 	}
@@ -754,7 +754,7 @@ void afs_send_empty_reply(struct afs_call *call)
 	case -ENOMEM:
 		_debug("oom");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_USER_ABORT, ENOMEM, "KOO");
+					RX_USER_ABORT, -ENOMEM, "KOO");
 	default:
 		_leave(" [error]");
 		return;
@@ -792,7 +792,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	if (n == -ENOMEM) {
 		_debug("oom");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_USER_ABORT, ENOMEM, "KOO");
+					RX_USER_ABORT, -ENOMEM, "KOO");
 	}
 	_leave(" [error]");
 }
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 34fee9f..d0d11b7 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -37,6 +37,7 @@
 #include <linux/freezer.h>
 #include <linux/namei.h>
 #include <linux/random.h>
+#include <linux/uuid.h>
 #include <linux/xattr.h>
 #include <net/ipv6.h>
 #include "cifsfs.h"
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 0f27816..9bc0b4d 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -35,6 +35,7 @@
 #include <linux/pagevec.h>
 #include <linux/freezer.h>
 #include <linux/namei.h>
+#include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <linux/inet.h>
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 02da648..fb0da09 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -33,6 +33,7 @@
 #include <linux/vfs.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/uaccess.h>
+#include <linux/uuid.h>
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
 #include "smb2pdu.h"
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3412514..5420767 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -42,6 +42,7 @@
 #include <linux/seq_file.h>
 #include <linux/compat.h>
 #include <linux/rculist.h>
+#include <net/busy_poll.h>
 
 /*
  * LOCKING:
@@ -224,6 +225,11 @@ struct eventpoll {
 	/* used to optimize loop detection check */
 	int visited;
 	struct list_head visited_list_link;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* used to track busy poll napi_id */
+	unsigned int napi_id;
+#endif
 };
 
 /* Wait structure used by the poll hooks */
@@ -384,6 +390,77 @@ static inline int ep_events_available(struct eventpoll *ep)
 	return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
 }
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static bool ep_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct eventpoll *ep = p;
+
+	return ep_events_available(ep) || busy_loop_timeout(start_time);
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+/*
+ * Busy poll if globally on and supporting sockets found && no events,
+ * busy loop will return if need_resched or ep_events_available.
+ *
+ * we must do our busy polling with irqs enabled
+ */
+static void ep_busy_loop(struct eventpoll *ep, int nonblock)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_id = READ_ONCE(ep->napi_id);
+
+	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
+#endif
+}
+
+static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (ep->napi_id)
+		ep->napi_id = 0;
+#endif
+}
+
+/*
+ * Set epoll busy poll NAPI ID from sk.
+ */
+static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct eventpoll *ep;
+	unsigned int napi_id;
+	struct socket *sock;
+	struct sock *sk;
+	int err;
+
+	if (!net_busy_loop_on())
+		return;
+
+	sock = sock_from_file(epi->ffd.file, &err);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+	ep = epi->ep;
+
+	/* Non-NAPI IDs can be rejected
+	 *	or
+	 * Nothing to do if we already have this ID
+	 */
+	if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
+		return;
+
+	/* record NAPI ID for use in next busy poll */
+	ep->napi_id = napi_id;
+#endif
+}
+
 /**
  * ep_call_nested - Perform a bound (possibly) nested call, by checking
  *                  that the recursion limit is not exceeded, and that
@@ -1022,6 +1099,8 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 
 	spin_lock_irqsave(&ep->lock, flags);
 
+	ep_set_busy_poll_napi_id(epi);
+
 	/*
 	 * If the event mask does not contain any poll(2) event, we consider the
 	 * descriptor to be disabled. This condition is likely the effect of the
@@ -1363,6 +1442,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	/* We have to drop the new item inside our item list to keep track of it */
 	spin_lock_irqsave(&ep->lock, flags);
 
+	/* record NAPI ID of new item if present */
+	ep_set_busy_poll_napi_id(epi);
+
 	/* If the file is already "ready" we drop it inside the ready list */
 	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1637,10 +1719,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	}
 
 fetch_events:
+
+	if (!ep_events_available(ep))
+		ep_busy_loop(ep, timed_out);
+
 	spin_lock_irqsave(&ep->lock, flags);
 
 	if (!ep_events_available(ep)) {
 		/*
+		 * Busy poll timed out.  Drop NAPI ID for now, we can add
+		 * it back in when we have moved a socket with a valid NAPI
+		 * ID onto the ready list.
+		 */
+		ep_reset_busy_poll_napi_id(ep);
+
+		/*
 		 * We don't have any available event to return to the caller.
 		 * We need to sleep here, and we will be wake up by
 		 * ep_poll_callback() when events will become available.
diff --git a/fs/select.c b/fs/select.c
index dd70937..bd4b2cc 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -456,7 +456,7 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 	int retval, i, timed_out = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	rcu_read_lock();
 	retval = max_select_fd(n, fds);
@@ -559,11 +559,11 @@ static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;
@@ -847,7 +847,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 	int timed_out = 0, count = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	/* Optimise the no-wait case */
 	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -900,11 +900,11 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;