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

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

2 files changed, 66 insertions, 27 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 79dae188a987..09ae27b353c1 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5617,16 +5617,26 @@ void perf_output_sample(struct perf_output_handle *handle,
         }
 
         if (sample_type & PERF_SAMPLE_RAW) {
-                if (data->raw) {
-                        u32 raw_size = data->raw->size;
-                        u32 real_size = round_up(raw_size + sizeof(u32),
-                                                 sizeof(u64)) - sizeof(u32);
-                        u64 zero = 0;
-
-                        perf_output_put(handle, real_size);
-                        __output_copy(handle, data->raw->data, raw_size);
-                        if (real_size - raw_size)
-                                __output_copy(handle, &zero, real_size - raw_size);
+                struct perf_raw_record *raw = data->raw;
+
+                if (raw) {
+                        struct perf_raw_frag *frag = &raw->frag;
+
+                        perf_output_put(handle, raw->size);
+                        do {
+                                if (frag->copy) {
+                                        __output_custom(handle, frag->copy,
+                                                        frag->data, frag->size);
+                                } else {
+                                        __output_copy(handle, frag->data,
+                                                      frag->size);
+                                }
+                                if (perf_raw_frag_last(frag))
+                                        break;
+                                frag = frag->next;
+                        } while (1);
+                        if (frag->pad)
+                                __output_skip(handle, NULL, frag->pad);
                 } else {
                         struct {
                                 u32     size;
@@ -5751,14 +5761,28 @@ void perf_prepare_sample(struct perf_event_header *header,
         }
 
         if (sample_type & PERF_SAMPLE_RAW) {
-                int size = sizeof(u32);
-
-                if (data->raw)
-                        size += data->raw->size;
-                else
-                        size += sizeof(u32);
+                struct perf_raw_record *raw = data->raw;
+                int size;
+
+                if (raw) {
+                        struct perf_raw_frag *frag = &raw->frag;
+                        u32 sum = 0;
+
+                        do {
+                                sum += frag->size;
+                                if (perf_raw_frag_last(frag))
+                                        break;
+                                frag = frag->next;
+                        } while (1);
+
+                        size = round_up(sum + sizeof(u32), sizeof(u64));
+                        raw->size = size - sizeof(u32);
+                        frag->pad = raw->size - sum;
+                } else {
+                        size = sizeof(u64);
+                }
 
-                header->size += round_up(size, sizeof(u64));
+                header->size += size;
         }
 
         if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
@@ -7398,7 +7422,7 @@ static struct pmu perf_swevent = {
 static int perf_tp_filter_match(struct perf_event *event,
                                 struct perf_sample_data *data)
 {
-        void *record = data->raw->data;
+        void *record = data->raw->frag.data;
 
         /* only top level events have filters set */
         if (event->parent)
@@ -7454,8 +7478,10 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
         struct perf_event *event;
 
         struct perf_raw_record raw = {
-                .size = entry_size,
-                .data = record,
+                .frag = {
+                        .size = entry_size,
+                        .data = record,
+                },
         };
 
         perf_sample_data_init(&data, 0, 0);
@@ -7596,7 +7622,7 @@ static void perf_event_free_bpf_prog(struct perf_event *event)
         prog = event->tp_event->prog;
         if (prog) {
                 event->tp_event->prog = NULL;
-                bpf_prog_put_rcu(prog);
+                bpf_prog_put(prog);
         }
 }
 
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 05f9f6d626df..486fd78eb8d5 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -123,21 +123,19 @@ static inline unsigned long perf_aux_size(struct ring_buffer *rb)
         return rb->aux_nr_pages << PAGE_SHIFT;
 }
 
-#define DEFINE_OUTPUT_COPY(func_name, memcpy_func)                      \
-static inline unsigned long                                             \
-func_name(struct perf_output_handle *handle,                            \
-          const void *buf, unsigned long len)                           \
+#define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...)        \
 {                                                                       \
         unsigned long size, written;                                    \
                                                                         \
         do {                                                            \
                 size    = min(handle->size, len);                       \
-                written = memcpy_func(handle->addr, buf, size);         \
+                written = memcpy_func(__VA_ARGS__);                     \
                 written = size - written;                               \
                                                                         \
                 len -= written;                                         \
                 handle->addr += written;                                \
-                buf += written;                                         \
+                if (advance_buf)                                        \
+                        buf += written;                                 \
                 handle->size -= written;                                \
                 if (!handle->size) {                                    \
                         struct ring_buffer *rb = handle->rb;            \
@@ -152,6 +150,21 @@ func_name(struct perf_output_handle *handle,				\
         return len;                                                     \
 }
 
+#define DEFINE_OUTPUT_COPY(func_name, memcpy_func)                      \
+static inline unsigned long                                             \
+func_name(struct perf_output_handle *handle,                            \
+          const void *buf, unsigned long len)                           \
+__DEFINE_OUTPUT_COPY_BODY(true, memcpy_func, handle->addr, buf, size)
+
+static inline unsigned long
+__output_custom(struct perf_output_handle *handle, perf_copy_f copy_func,
+                const void *buf, unsigned long len)
+{
+        unsigned long orig_len = len;
+        __DEFINE_OUTPUT_COPY_BODY(false, copy_func, handle->addr, buf,
+                                  orig_len - len, size)
+}
+
 static inline unsigned long
 memcpy_common(void *dst, const void *src, unsigned long n)
 {