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, 288 insertions, 0 deletions

diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c
new file mode 100644
index 000000000000..4fc6c6cbb4eb
--- /dev/null
+++ b/tools/lib/bpf/ringbuf.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+/*
+ * Ring buffer operations.
+ *
+ * Copyright (C) 2020 Facebook, Inc.
+ */
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE
+#endif
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <unistd.h>
+#include <linux/err.h>
+#include <linux/bpf.h>
+#include <asm/barrier.h>
+#include <sys/mman.h>
+#include <sys/epoll.h>
+#include <tools/libc_compat.h>
+
+#include "libbpf.h"
+#include "libbpf_internal.h"
+#include "bpf.h"
+
+/* make sure libbpf doesn't use kernel-only integer typedefs */
+#pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64
+
+struct ring {
+	ring_buffer_sample_fn sample_cb;
+	void *ctx;
+	void *data;
+	unsigned long *consumer_pos;
+	unsigned long *producer_pos;
+	unsigned long mask;
+	int map_fd;
+};
+
+struct ring_buffer {
+	struct epoll_event *events;
+	struct ring *rings;
+	size_t page_size;
+	int epoll_fd;
+	int ring_cnt;
+};
+
+static void ringbuf_unmap_ring(struct ring_buffer *rb, struct ring *r)
+{
+	if (r->consumer_pos) {
+		munmap(r->consumer_pos, rb->page_size);
+		r->consumer_pos = NULL;
+	}
+	if (r->producer_pos) {
+		munmap(r->producer_pos, rb->page_size + 2 * (r->mask + 1));
+		r->producer_pos = NULL;
+	}
+}
+
+/* Add extra RINGBUF maps to this ring buffer manager */
+int ring_buffer__add(struct ring_buffer *rb, int map_fd,
+		     ring_buffer_sample_fn sample_cb, void *ctx)
+{
+	struct bpf_map_info info;
+	__u32 len = sizeof(info);
+	struct epoll_event *e;
+	struct ring *r;
+	void *tmp;
+	int err;
+
+	memset(&info, 0, sizeof(info));
+
+	err = bpf_obj_get_info_by_fd(map_fd, &info, &len);
+	if (err) {
+		err = -errno;
+		pr_warn("ringbuf: failed to get map info for fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+
+	if (info.type != BPF_MAP_TYPE_RINGBUF) {
+		pr_warn("ringbuf: map fd=%d is not BPF_MAP_TYPE_RINGBUF\n",
+			map_fd);
+		return -EINVAL;
+	}
+
+	tmp = reallocarray(rb->rings, rb->ring_cnt + 1, sizeof(*rb->rings));
+	if (!tmp)
+		return -ENOMEM;
+	rb->rings = tmp;
+
+	tmp = reallocarray(rb->events, rb->ring_cnt + 1, sizeof(*rb->events));
+	if (!tmp)
+		return -ENOMEM;
+	rb->events = tmp;
+
+	r = &rb->rings[rb->ring_cnt];
+	memset(r, 0, sizeof(*r));
+
+	r->map_fd = map_fd;
+	r->sample_cb = sample_cb;
+	r->ctx = ctx;
+	r->mask = info.max_entries - 1;
+
+	/* Map writable consumer page */
+	tmp = mmap(NULL, rb->page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		   map_fd, 0);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		pr_warn("ringbuf: failed to mmap consumer page for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	r->consumer_pos = tmp;
+
+	/* Map read-only producer page and data pages. We map twice as big
+	 * data size to allow simple reading of samples that wrap around the
+	 * end of a ring buffer. See kernel implementation for details.
+	 * */
+	tmp = mmap(NULL, rb->page_size + 2 * info.max_entries, PROT_READ,
+		   MAP_SHARED, map_fd, rb->page_size);
+	if (tmp == MAP_FAILED) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to mmap data pages for map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+	r->producer_pos = tmp;
+	r->data = tmp + rb->page_size;
+
+	e = &rb->events[rb->ring_cnt];
+	memset(e, 0, sizeof(*e));
+
+	e->events = EPOLLIN;
+	e->data.fd = rb->ring_cnt;
+	if (epoll_ctl(rb->epoll_fd, EPOLL_CTL_ADD, map_fd, e) < 0) {
+		err = -errno;
+		ringbuf_unmap_ring(rb, r);
+		pr_warn("ringbuf: failed to epoll add map fd=%d: %d\n",
+			map_fd, err);
+		return err;
+	}
+
+	rb->ring_cnt++;
+	return 0;
+}
+
+void ring_buffer__free(struct ring_buffer *rb)
+{
+	int i;
+
+	if (!rb)
+		return;
+
+	for (i = 0; i < rb->ring_cnt; ++i)
+		ringbuf_unmap_ring(rb, &rb->rings[i]);
+	if (rb->epoll_fd >= 0)
+		close(rb->epoll_fd);
+
+	free(rb->events);
+	free(rb->rings);
+	free(rb);
+}
+
+struct ring_buffer *
+ring_buffer__new(int map_fd, ring_buffer_sample_fn sample_cb, void *ctx,
+		 const struct ring_buffer_opts *opts)
+{
+	struct ring_buffer *rb;
+	int err;
+
+	if (!OPTS_VALID(opts, ring_buffer_opts))
+		return NULL;
+
+	rb = calloc(1, sizeof(*rb));
+	if (!rb)
+		return NULL;
+
+	rb->page_size = getpagesize();
+
+	rb->epoll_fd = epoll_create1(EPOLL_CLOEXEC);
+	if (rb->epoll_fd < 0) {
+		err = -errno;
+		pr_warn("ringbuf: failed to create epoll instance: %d\n", err);
+		goto err_out;
+	}
+
+	err = ring_buffer__add(rb, map_fd, sample_cb, ctx);
+	if (err)
+		goto err_out;
+
+	return rb;
+
+err_out:
+	ring_buffer__free(rb);
+	return NULL;
+}
+
+static inline int roundup_len(__u32 len)
+{
+	/* clear out top 2 bits (discard and busy, if set) */
+	len <<= 2;
+	len >>= 2;
+	/* add length prefix */
+	len += BPF_RINGBUF_HDR_SZ;
+	/* round up to 8 byte alignment */
+	return (len + 7) / 8 * 8;
+}
+
+static int ringbuf_process_ring(struct ring* r)
+{
+	int *len_ptr, len, err, cnt = 0;
+	unsigned long cons_pos, prod_pos;
+	bool got_new_data;
+	void *sample;
+
+	cons_pos = smp_load_acquire(r->consumer_pos);
+	do {
+		got_new_data = false;
+		prod_pos = smp_load_acquire(r->producer_pos);
+		while (cons_pos < prod_pos) {
+			len_ptr = r->data + (cons_pos & r->mask);
+			len = smp_load_acquire(len_ptr);
+
+			/* sample not committed yet, bail out for now */
+			if (len & BPF_RINGBUF_BUSY_BIT)
+				goto done;
+
+			got_new_data = true;
+			cons_pos += roundup_len(len);
+
+			if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
+				sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
+				err = r->sample_cb(r->ctx, sample, len);
+				if (err) {
+					/* update consumer pos and bail out */
+					smp_store_release(r->consumer_pos,
+							  cons_pos);
+					return err;
+				}
+				cnt++;
+			}
+
+			smp_store_release(r->consumer_pos, cons_pos);
+		}
+	} while (got_new_data);
+done:
+	return cnt;
+}
+
+/* Consume available ring buffer(s) data without event polling.
+ * Returns number of records consumed across all registered ring buffers, or
+ * negative number if any of the callbacks return error.
+ */
+int ring_buffer__consume(struct ring_buffer *rb)
+{
+	int i, err, res = 0;
+
+	for (i = 0; i < rb->ring_cnt; i++) {
+		struct ring *ring = &rb->rings[i];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return err;
+		res += err;
+	}
+	return res;
+}
+
+/* Poll for available data and consume records, if any are available.
+ * Returns number of records consumed, or negative number, if any of the
+ * registered callbacks returned error.
+ */
+int ring_buffer__poll(struct ring_buffer *rb, int timeout_ms)
+{
+	int i, cnt, err, res = 0;
+
+	cnt = epoll_wait(rb->epoll_fd, rb->events, rb->ring_cnt, timeout_ms);
+	for (i = 0; i < cnt; i++) {
+		__u32 ring_id = rb->events[i].data.fd;
+		struct ring *ring = &rb->rings[ring_id];
+
+		err = ringbuf_process_ring(ring);
+		if (err < 0)
+			return err;
+		res += cnt;
+	}
+	return cnt < 0 ? -errno : res;
+}