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

Pull networking updates from David Miller:

 1) Add VF IPSEC offload support in ixgbe, from Shannon Nelson.

 2) Add zero-copy AF_XDP support to i40e, from Björn Töpel.

 3) All in-tree drivers are converted to {g,s}et_link_ksettings() so we
    can get rid of the {g,s}et_settings ethtool callbacks, from Michal
    Kubecek.

 4) Add software timestamping to veth driver, from Michael Walle.

 5) More work to make packet classifiers and actions lockless, from Vlad
    Buslov.

 6) Support sticky FDB entries in bridge, from Nikolay Aleksandrov.

 7) Add ipv6 version of IP_MULTICAST_ALL sockopt, from Andre Naujoks.

 8) Support batching of XDP buffers in vhost_net, from Jason Wang.

 9) Add flow dissector BPF hook, from Petar Penkov.

10) i40e vf --> generic iavf conversion, from Jesse Brandeburg.

11) Add NLA_REJECT netlink attribute policy type, to signal when users
    provide attributes in situations which don't make sense. From
    Johannes Berg.

12) Switch TCP and fair-queue scheduler over to earliest departure time
    model. From Eric Dumazet.

13) Improve guest receive performance by doing rx busy polling in tx
    path of vhost networking driver, from Tonghao Zhang.

14) Add per-cgroup local storage to bpf

15) Add reference tracking to BPF, from Joe Stringer. The verifier can
    now make sure that references taken to objects are properly released
    by the program.

16) Support in-place encryption in TLS, from Vakul Garg.

17) Add new taprio packet scheduler, from Vinicius Costa Gomes.

18) Lots of selftests additions, too numerous to mention one by one here
    but all of which are very much appreciated.

19) Support offloading of eBPF programs containing BPF to BPF calls in
    nfp driver, frm Quentin Monnet.

20) Move dpaa2_ptp driver out of staging, from Yangbo Lu.

21) Lots of u32 classifier cleanups and simplifications, from Al Viro.

22) Add new strict versions of netlink message parsers, and enable them
    for some situations. From David Ahern.

23) Evict neighbour entries on carrier down, also from David Ahern.

24) Support BPF sk_msg verdict programs with kTLS, from Daniel Borkmann
    and John Fastabend.

25) Add support for filtering route dumps, from David Ahern.

26) New igc Intel driver for 2.5G parts, from Sasha Neftin et al.

27) Allow vxlan enslavement to bridges in mlxsw driver, from Ido
    Schimmel.

28) Add queue and stack map types to eBPF, from Mauricio Vasquez B.

29) Add back byte-queue-limit support to r8169, with all the bug fixes
    in other areas of the driver it works now! From Florian Westphal and
    Heiner Kallweit.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2147 commits)
  tcp: add tcp_reset_xmit_timer() helper
  qed: Fix static checker warning
  Revert "be2net: remove desc field from be_eq_obj"
  Revert "net: simplify sock_poll_wait"
  net: socionext: Reset tx queue in ndo_stop
  net: socionext: Add dummy PHY register read in phy_write()
  net: socionext: Stop PHY before resetting netsec
  net: stmmac: Set OWN bit for jumbo frames
  arm64: dts: stratix10: Support Ethernet Jumbo frame
  tls: Add maintainers
  net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode
  octeontx2-af: Support for NIXLF's UCAST/PROMISC/ALLMULTI modes
  octeontx2-af: Support for setting MAC address
  octeontx2-af: Support for changing RSS algorithm
  octeontx2-af: NIX Rx flowkey configuration for RSS
  octeontx2-af: Install ucast and bcast pkt forwarding rules
  octeontx2-af: Add LMAC channel info to NIXLF_ALLOC response
  octeontx2-af: NPC MCAM and LDATA extract minimal configuration
  octeontx2-af: Enable packet length and csum validation
  octeontx2-af: Support for VTAG strip and capture
  ...

1 files changed, 288 insertions, 0 deletions

diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
new file mode 100644
index 000000000000..12a93fb37449
--- /dev/null
+++ b/kernel/bpf/queue_stack_maps.c
@@ -0,0 +1,288 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * queue_stack_maps.c: BPF queue and stack maps
+ *
+ * Copyright (c) 2018 Politecnico di Torino
+ */
+#include <linux/bpf.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include "percpu_freelist.h"
+
+#define QUEUE_STACK_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+
+struct bpf_queue_stack {
+	struct bpf_map map;
+	raw_spinlock_t lock;
+	u32 head, tail;
+	u32 size; /* max_entries + 1 */
+
+	char elements[0] __aligned(8);
+};
+
+static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map)
+{
+	return container_of(map, struct bpf_queue_stack, map);
+}
+
+static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs)
+{
+	return qs->head == qs->tail;
+}
+
+static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
+{
+	u32 head = qs->head + 1;
+
+	if (unlikely(head >= qs->size))
+		head = 0;
+
+	return head == qs->tail;
+}
+
+/* Called from syscall */
+static int queue_stack_map_alloc_check(union bpf_attr *attr)
+{
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 0 ||
+	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
+		return -EINVAL;
+
+	if (attr->value_size > KMALLOC_MAX_SIZE)
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements.
+		 */
+		return -E2BIG;
+
+	return 0;
+}
+
+static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
+{
+	int ret, numa_node = bpf_map_attr_numa_node(attr);
+	struct bpf_queue_stack *qs;
+	u32 size, value_size;
+	u64 queue_size, cost;
+
+	size = attr->max_entries + 1;
+	value_size = attr->value_size;
+
+	queue_size = sizeof(*qs) + (u64) value_size * size;
+
+	cost = queue_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-E2BIG);
+
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	ret = bpf_map_precharge_memlock(cost);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	qs = bpf_map_area_alloc(queue_size, numa_node);
+	if (!qs)
+		return ERR_PTR(-ENOMEM);
+
+	memset(qs, 0, sizeof(*qs));
+
+	bpf_map_init_from_attr(&qs->map, attr);
+
+	qs->map.pages = cost;
+	qs->size = size;
+
+	raw_spin_lock_init(&qs->lock);
+
+	return &qs->map;
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void queue_stack_map_free(struct bpf_map *map)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+
+	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+	 * so the programs (can be more than one that used this map) were
+	 * disconnected from events. Wait for outstanding critical sections in
+	 * these programs to complete
+	 */
+	synchronize_rcu();
+
+	bpf_map_area_free(qs);
+}
+
+static int __queue_map_get(struct bpf_map *map, void *value, bool delete)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+	unsigned long flags;
+	int err = 0;
+	void *ptr;
+
+	raw_spin_lock_irqsave(&qs->lock, flags);
+
+	if (queue_stack_map_is_empty(qs)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	ptr = &qs->elements[qs->tail * qs->map.value_size];
+	memcpy(value, ptr, qs->map.value_size);
+
+	if (delete) {
+		if (unlikely(++qs->tail >= qs->size))
+			qs->tail = 0;
+	}
+
+out:
+	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	return err;
+}
+
+
+static int __stack_map_get(struct bpf_map *map, void *value, bool delete)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+	unsigned long flags;
+	int err = 0;
+	void *ptr;
+	u32 index;
+
+	raw_spin_lock_irqsave(&qs->lock, flags);
+
+	if (queue_stack_map_is_empty(qs)) {
+		err = -ENOENT;
+		goto out;
+	}
+
+	index = qs->head - 1;
+	if (unlikely(index >= qs->size))
+		index = qs->size - 1;
+
+	ptr = &qs->elements[index * qs->map.value_size];
+	memcpy(value, ptr, qs->map.value_size);
+
+	if (delete)
+		qs->head = index;
+
+out:
+	raw_spin_unlock_irqrestore(&qs->lock, flags);
+	return err;
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_map_peek_elem(struct bpf_map *map, void *value)
+{
+	return __queue_map_get(map, value, false);
+}
+
+/* Called from syscall or from eBPF program */
+static int stack_map_peek_elem(struct bpf_map *map, void *value)
+{
+	return __stack_map_get(map, value, false);
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_map_pop_elem(struct bpf_map *map, void *value)
+{
+	return __queue_map_get(map, value, true);
+}
+
+/* Called from syscall or from eBPF program */
+static int stack_map_pop_elem(struct bpf_map *map, void *value)
+{
+	return __stack_map_get(map, value, true);
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_stack_map_push_elem(struct bpf_map *map, void *value,
+				     u64 flags)
+{
+	struct bpf_queue_stack *qs = bpf_queue_stack(map);
+	unsigned long irq_flags;
+	int err = 0;
+	void *dst;
+
+	/* BPF_EXIST is used to force making room for a new element in case the
+	 * map is full
+	 */
+	bool replace = (flags & BPF_EXIST);
+
+	/* Check supported flags for queue and stack maps */
+	if (flags & BPF_NOEXIST || flags > BPF_EXIST)
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&qs->lock, irq_flags);
+
+	if (queue_stack_map_is_full(qs)) {
+		if (!replace) {
+			err = -E2BIG;
+			goto out;
+		}
+		/* advance tail pointer to overwrite oldest element */
+		if (unlikely(++qs->tail >= qs->size))
+			qs->tail = 0;
+	}
+
+	dst = &qs->elements[qs->head * qs->map.value_size];
+	memcpy(dst, value, qs->map.value_size);
+
+	if (unlikely(++qs->head >= qs->size))
+		qs->head = 0;
+
+out:
+	raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
+	return err;
+}
+
+/* Called from syscall or from eBPF program */
+static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_stack_map_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 flags)
+{
+	return -EINVAL;
+}
+
+/* Called from syscall or from eBPF program */
+static int queue_stack_map_delete_elem(struct bpf_map *map, void *key)
+{
+	return -EINVAL;
+}
+
+/* Called from syscall */
+static int queue_stack_map_get_next_key(struct bpf_map *map, void *key,
+					void *next_key)
+{
+	return -EINVAL;
+}
+
+const struct bpf_map_ops queue_map_ops = {
+	.map_alloc_check = queue_stack_map_alloc_check,
+	.map_alloc = queue_stack_map_alloc,
+	.map_free = queue_stack_map_free,
+	.map_lookup_elem = queue_stack_map_lookup_elem,
+	.map_update_elem = queue_stack_map_update_elem,
+	.map_delete_elem = queue_stack_map_delete_elem,
+	.map_push_elem = queue_stack_map_push_elem,
+	.map_pop_elem = queue_map_pop_elem,
+	.map_peek_elem = queue_map_peek_elem,
+	.map_get_next_key = queue_stack_map_get_next_key,
+};
+
+const struct bpf_map_ops stack_map_ops = {
+	.map_alloc_check = queue_stack_map_alloc_check,
+	.map_alloc = queue_stack_map_alloc,
+	.map_free = queue_stack_map_free,
+	.map_lookup_elem = queue_stack_map_lookup_elem,
+	.map_update_elem = queue_stack_map_update_elem,
+	.map_delete_elem = queue_stack_map_delete_elem,
+	.map_push_elem = queue_stack_map_push_elem,
+	.map_pop_elem = stack_map_pop_elem,
+	.map_peek_elem = stack_map_peek_elem,
+	.map_get_next_key = queue_stack_map_get_next_key,
+};