* Re: [PATCH v2] gso: fix payload length when gso_size is zero
From: Duyck, Alexander H @ 2017-10-06 16:37 UTC (permalink / raw)
To: netdev@vger.kernel.org, alexey.kodanev@oracle.com
Cc: davem@davemloft.net, steffen.klassert@secunet.com
In-Reply-To: <1507305755-14393-1-git-send-email-alexey.kodanev@oracle.com>
On Fri, 2017-10-06 at 19:02 +0300, Alexey Kodanev wrote:
> When gso_size reset to zero for the tail segment in skb_segment(), later
> in ipv6_gso_segment(), __skb_udp_tunnel_segment() and gre_gso_segment()
> we will get incorrect results (payload length, pcsum) for that segment.
> inet_gso_segment() already has a check for gso_size before calculating
> payload.
>
> The issue was found with LTP vxlan & gre tests over ixgbe NIC.
>
> Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer")
> Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
> ---
> v2: also added skb_is_gso to gre_gso_segment() and __skb_udp_tunnel_segment()
>
> net/ipv4/gre_offload.c | 2 +-
> net/ipv4/udp_offload.c | 2 +-
> net/ipv6/ip6_offload.c | 2 +-
> 3 files changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
> index d5cac99..8c72034 100644
> --- a/net/ipv4/gre_offload.c
> +++ b/net/ipv4/gre_offload.c
> @@ -98,7 +98,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
> greh = (struct gre_base_hdr *)skb_transport_header(skb);
> pcsum = (__sum16 *)(greh + 1);
>
> - if (gso_partial) {
> + if (gso_partial && skb_is_gso(skb)) {
> unsigned int partial_adj;
>
> /* Adjust checksum to account for the fact that
> diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
> index 0932c85..6401574 100644
> --- a/net/ipv4/udp_offload.c
> +++ b/net/ipv4/udp_offload.c
> @@ -122,7 +122,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
> * will be using a length value equal to only one MSS sized
> * segment instead of the entire frame.
> */
> - if (gso_partial) {
> + if (gso_partial && skb_is_gso(skb)) {
> uh->len = htons(skb_shinfo(skb)->gso_size +
> SKB_GSO_CB(skb)->data_offset +
> skb->head - (unsigned char *)uh);
> diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
> index cdb3728..4a87f94 100644
> --- a/net/ipv6/ip6_offload.c
> +++ b/net/ipv6/ip6_offload.c
> @@ -105,7 +105,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
>
> for (skb = segs; skb; skb = skb->next) {
> ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
> - if (gso_partial)
> + if (gso_partial && skb_is_gso(skb))
> payload_len = skb_shinfo(skb)->gso_size +
> SKB_GSO_CB(skb)->data_offset +
> skb->head - (unsigned char *)(ipv6h + 1);
^ permalink raw reply
* Re: [PATCH net-next 0/3] tcp: improving RACK cpu performance
From: Yuchung Cheng @ 2017-10-06 16:34 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20171005.212612.1580802624897584218.davem@davemloft.net>
On Thu, Oct 5, 2017 at 9:26 PM, David Miller <davem@davemloft.net> wrote:
>
> From: Yuchung Cheng <ycheng@google.com>
> Date: Wed, 4 Oct 2017 12:59:57 -0700
>
> > This patch set improves the CPU consumption of the RACK TCP loss
> > recovery algorithm, in particular for high-speed networks. Currently,
> > for every ACK in recovery RACK can potentially iterate over all sent
> > packets in the write queue. On large BDP networks with non-trivial
> > losses the RACK write queue walk CPU usage becomes unreasonably high.
> >
> > This patch introduces a new queue in TCP that keeps only skbs sent and
> > not yet (s)acked or marked lost, in time order instead of sequence
> > order. With that, RACK can examine this time-sorted list and only
> > check packets that were sent recently, within the reordering window,
> > per ACK. This is the fastest way without any write queue walks. The
> > number of skbs examined per ACK is reduced by orders of magnitude.
>
> That's a pretty risky way to implement the second SKB list.... but
Agreed. I really appreciate you accepting this change. We tried a few
alternatives but this is the most clean and fastest approach. BBR can
reach 8-10Gbps on 300ms RTT link so both RACK and SACK need to scale
in the era of hundreds MB BDP :-)
> you avoided making sk_buff larger so what can I say :-)
>
> Series applied, thank.
^ permalink raw reply
* Re: [PATCH 0/4] RCU: introduce noref debug
From: Paul E. McKenney @ 2017-10-06 16:34 UTC (permalink / raw)
To: Paolo Abeni
Cc: linux-kernel, Josh Triplett, Steven Rostedt, David S. Miller,
Eric Dumazet, Hannes Frederic Sowa, netdev
In-Reply-To: <1507302609.2793.16.camel@redhat.com>
On Fri, Oct 06, 2017 at 05:10:09PM +0200, Paolo Abeni wrote:
> Hi,
>
> On Fri, 2017-10-06 at 06:34 -0700, Paul E. McKenney wrote:
> > On Fri, Oct 06, 2017 at 02:57:45PM +0200, Paolo Abeni wrote:
> > > The networking subsystem is currently using some kind of long-lived
> > > RCU-protected, references to avoid the overhead of full book-keeping.
> > >
> > > Such references - skb_dst() noref - are stored inside the skbs and can be
> > > moved across relevant slices of the network stack, with the users
> > > being in charge of properly clearing the relevant skb - or properly refcount
> > > the related dst references - before the skb escapes the RCU section.
> > >
> > > We currently don't have any deterministic debug infrastructure to check
> > > the dst noref usages - and the introduction of others noref artifact is
> > > currently under discussion.
> > >
> > > This series tries to tackle the above introducing an RCU debug infrastructure
> > > aimed at spotting incorrect noref pointer usage, in patch one. The
> > > infrastructure is small and must be explicitly enabled via a newly introduced
> > > build option.
> > >
> > > Patch two uses such infrastructure to track dst noref usage in the networking
> > > stack.
> > >
> > > Patch 3 and 4 are bugfixes for small buglet found running this infrastructure
> > > on basic scenarios.
>
> Thank you for the prompt reply!
> >
> > This patchset does not look like it handles rcu_read_lock() nesting.
> > For example, given code like this:
> >
> > void foo(void)
> > {
> > rcu_read_lock();
> > rcu_track_noref(&key2, &noref2, true);
> > do_something();
> > rcu_track_noref(&key2, &noref2, false);
> > rcu_read_unlock();
> > }
> >
> > void bar(void)
> > {
> > rcu_read_lock();
> > rcu_track_noref(&key1, &noref1, true);
> > do_something_more();
> > foo();
> > do_something_else();
> > rcu_track_noref(&key1, &noref1, false);
> > rcu_read_unlock();
> > }
> >
> > void grill(void)
> > {
> > foo();
> > }
> >
> > It looks like foo()'s rcu_read_unlock() will complain about key1.
> > You could remove foo()'s rcu_read_lock() and rcu_read_unlock(), but
> > that will break the call from grill().
>
> Actually the code should cope correctly with your example; when foo()'s
> rcu_read_unlock() is called, 'cache' contains:
>
> { { &key1, &noref1, 1}, // ...
>
> and when the related __rcu_check_noref() is invoked preempt_count() is
> 2 - because the check is called before decreasing the preempt counter.
>
> In the main loop inside __rcu_check_noref() we will hit always the
> 'continue' statement because 'cache->store[i].nesting != nesting', so
> no warn will be triggered.
You are right, it was too early, and my example wasn't correct. How
about this one?
void foo(void (*f)(struct s *sp), struct s **spp)
{
rcu_read_lock();
rcu_track_noref(&key2, &noref2, true);
f(spp);
rcu_track_noref(&key2, &noref2, false);
rcu_read_unlock();
}
void barcb(struct s **spp)
{
*spp = &noref3;
rcu_track_noref(&key3, *spp, true);
}
void bar(void)
{
struct s *sp;
rcu_read_lock();
rcu_track_noref(&key1, &noref1, true);
do_something_more();
foo(barcb, &sp);
do_something_else(sp);
rcu_track_noref(&key3, sp, false);
rcu_track_noref(&key1, &noref1, false);
rcu_read_unlock();
}
void grillcb(struct s **spp)
{
*spp
}
void grill(void)
{
foo();
}
How does the user select the key argument? It looks like someone
can choose to just pass in NULL -- is that the intent, or am I confused
about this as well?
> > Or am I missing something subtle here? Given patch 3/4, I suspect not...
>
> The problem with the code in patch 3/4 is different; currently
> ip_route_input_noref() is basically doing:
>
> rcu_read_lock();
>
> rcu_track_noref(&key1, &noref1, true);
>
> rcu_read_unlock();
>
> So the rcu lock there silence any RCU based check inside
> ip_route_input_noref() but does not really protect the noref dst.
>
> Please let me know if the above clarify the scenario.
OK.
I am also concerned about false negatives when the user invokes
rcu_track_noref(..., false) but then leaks the pointer anyway. Or is
there something you are doing that catches this that I am missing?
Thanx, Paul
^ permalink raw reply
* Re: [PATCH net] bpf: fix liveness marking
From: Edward Cree @ 2017-10-06 16:33 UTC (permalink / raw)
To: Alexei Starovoitov, David S . Miller; +Cc: Daniel Borkmann, netdev, kernel-team
In-Reply-To: <20171005232056.2234669-1-ast@fb.com>
On 06/10/17 00:20, Alexei Starovoitov wrote:
> while processing Rx = Ry instruction the verifier does
> regs[insn->dst_reg] = regs[insn->src_reg]
> which often clears write mark (when Ry doesn't have it)
> that was just set by check_reg_arg(Rx) prior to the assignment.
> That causes mark_reg_read() to keep marking Rx in this block as
> REG_LIVE_READ (since the logic incorrectly misses that it's
> screened by the write) and in many of its parents (until lucky
> write into the same Rx or beginning of the program).
> That causes is_state_visited() logic to miss many pruning opportunities.
Good catch!
> Furthermore mark_reg_read() logic propagates the read mark
> for BPF_REG_FP as well (though it's readonly) which causes
> harmless but unnecssary work during is_state_visited().
Surely it's unnecessary for is_state_visited() to even look at
BPF_REG_FP anyway, so in addition to your change we could make
states_equal just do `for (i = 0; i < BPF_REG_FP; i++)`? That
might save a bit more time.
> Note that do_propagate_liveness() skips FP correctly,
> so do the same in mark_reg_read() as well.
> It saves 0.2 seconds for the test below
>
> program before after
> bpf_lb-DLB_L3.o 2604 2304
> bpf_lb-DLB_L4.o 11159 3723
> bpf_lb-DUNKNOWN.o 1116 1110
> bpf_lxc-DDROP_ALL.o 34566 28004
> bpf_lxc-DUNKNOWN.o 53267 39026
> bpf_netdev.o 17843 16943
> bpf_overlay.o 8672 7929
> time ~11 sec ~4 sec
>
> Fixes: dc503a8ad984 ("bpf/verifier: track liveness for pruning")
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Very nice numbers!
Acked-by: Edward Cree <ecree@solarflare.com>
^ permalink raw reply
* Re: [net-next PATCH 1/3] samples/bpf: xdp_monitor first 8 bytes are not accessible by bpf
From: Alexei Starovoitov @ 2017-10-06 16:13 UTC (permalink / raw)
To: Jesper Dangaard Brouer; +Cc: netdev, Andy Gospodarek, Daniel Borkmann
In-Reply-To: <150727930151.4460.3117254071267380300.stgit@firesoul>
On Fri, Oct 06, 2017 at 10:41:41AM +0200, Jesper Dangaard Brouer wrote:
> The first 8 bytes of the tracepoint context struct are not accessible
> by the bpf code. This is a choice that dates back to the original
> inclusion of this code.
>
> See explaination in:
> commit 98b5c2c65c29 ("perf, bpf: allow bpf programs attach to tracepoints")
>
> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
thank you for fixing it.
Acked-by: Alexei Starovoitov <ast@kernel.org>
^ permalink raw reply
* [net-next V5 PATCH 5/5] samples/bpf: add cpumap sample program xdp_redirect_cpu
From: Jesper Dangaard Brouer @ 2017-10-06 16:13 UTC (permalink / raw)
To: netdev
Cc: jakub.kicinski, Michael S. Tsirkin, pavel.odintsov, Jason Wang,
mchan, John Fastabend, peter.waskiewicz.jr,
Jesper Dangaard Brouer, Daniel Borkmann, Alexei Starovoitov,
Andy Gospodarek
In-Reply-To: <150730632837.22839.11804085686478888137.stgit@firesoul>
This sample program show how to use cpumap and the associated
tracepoints.
It provides command line stats, which shows how the XDP-RX process,
cpumap-enqueue and cpumap kthread dequeue is cooperating on a per CPU
basis. It also utilize the xdp_exception and xdp_redirect_err
transpoints to allow users quickly to identify setup issues.
One issue with ixgbe driver is that the driver reset the link when
loading XDP. This reset the procfs smp_affinity settings. Thus,
after loading the program, these must be reconfigured. The easiest
workaround it to reduce the RX-queue to e.g. two via:
# ethtool --set-channels ixgbe1 combined 2
And then add CPUs above 0 and 1, like:
# xdp_redirect_cpu --dev ixgbe1 --prog 2 --cpu 2 --cpu 3 --cpu 4
Another issue with ixgbe is that the page recycle mechanism is tied to
the RX-ring size. And the default setting of 512 elements is too
small. This is the same issue with regular devmap XDP_REDIRECT.
To overcome this I've been using 1024 rx-ring size:
# ethtool -G ixgbe1 rx 1024 tx 1024
V3:
- whitespace cleanups
- bpf tracepoint cannot access top part of struct
V4:
- report on kthread sched events, according to tracepoint change
- report average bulk enqueue size
V5:
- bpf_map_lookup_elem on cpumap not allowed from bpf_prog
use separate map to mark CPUs not available
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
samples/bpf/Makefile | 4
samples/bpf/xdp_redirect_cpu_kern.c | 609 ++++++++++++++++++++++++++++++++
samples/bpf/xdp_redirect_cpu_user.c | 673 +++++++++++++++++++++++++++++++++++
3 files changed, 1286 insertions(+)
create mode 100644 samples/bpf/xdp_redirect_cpu_kern.c
create mode 100644 samples/bpf/xdp_redirect_cpu_user.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index ebc2ad69b62c..52c4dab2c153 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -39,6 +39,7 @@ hostprogs-y += per_socket_stats_example
hostprogs-y += load_sock_ops
hostprogs-y += xdp_redirect
hostprogs-y += xdp_redirect_map
+hostprogs-y += xdp_redirect_cpu
hostprogs-y += xdp_monitor
hostprogs-y += syscall_tp
@@ -84,6 +85,7 @@ test_map_in_map-objs := bpf_load.o $(LIBBPF) test_map_in_map_user.o
per_socket_stats_example-objs := $(LIBBPF) cookie_uid_helper_example.o
xdp_redirect-objs := bpf_load.o $(LIBBPF) xdp_redirect_user.o
xdp_redirect_map-objs := bpf_load.o $(LIBBPF) xdp_redirect_map_user.o
+xdp_redirect_cpu-objs := bpf_load.o $(LIBBPF) xdp_redirect_cpu_user.o
xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o
syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
@@ -129,6 +131,7 @@ always += tcp_iw_kern.o
always += tcp_clamp_kern.o
always += xdp_redirect_kern.o
always += xdp_redirect_map_kern.o
+always += xdp_redirect_cpu_kern.o
always += xdp_monitor_kern.o
always += syscall_tp_kern.o
@@ -169,6 +172,7 @@ HOSTLOADLIBES_xdp_tx_iptunnel += -lelf
HOSTLOADLIBES_test_map_in_map += -lelf
HOSTLOADLIBES_xdp_redirect += -lelf
HOSTLOADLIBES_xdp_redirect_map += -lelf
+HOSTLOADLIBES_xdp_redirect_cpu += -lelf
HOSTLOADLIBES_xdp_monitor += -lelf
HOSTLOADLIBES_syscall_tp += -lelf
diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
new file mode 100644
index 000000000000..303e9e7161f3
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -0,0 +1,609 @@
+/* XDP redirect to CPUs via cpumap (BPF_MAP_TYPE_CPUMAP)
+ *
+ * GPLv2, Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
+ */
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/if_vlan.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/ipv6.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include <uapi/linux/udp.h>
+
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define MAX_CPUS 12 /* WARNING - sync with _user.c */
+
+/* Special map type that can XDP_REDIRECT frames to another CPU */
+struct bpf_map_def SEC("maps") cpu_map = {
+ .type = BPF_MAP_TYPE_CPUMAP,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = MAX_CPUS,
+};
+
+/* Common stats data record to keep userspace more simple */
+struct datarec {
+ __u64 processed;
+ __u64 dropped;
+ __u64 issue;
+};
+
+/* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
+ * feedback. Redirect TX errors can be caught via a tracepoint.
+ */
+struct bpf_map_def SEC("maps") rx_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 1,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") redirect_err_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 2,
+ /* TODO: have entries for all possible errno's */
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") cpumap_enqueue_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = MAX_CPUS,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") cpumap_kthread_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 1,
+};
+
+/* Set of maps controlling available CPU, and for iterating through
+ * selectable redirect CPUs.
+ */
+struct bpf_map_def SEC("maps") cpus_available = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = MAX_CPUS,
+};
+struct bpf_map_def SEC("maps") cpus_count = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = 1,
+};
+struct bpf_map_def SEC("maps") cpus_iterator = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(u32),
+ .max_entries = 1,
+};
+
+/* Used by trace point */
+struct bpf_map_def SEC("maps") exception_cnt = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(u32),
+ .value_size = sizeof(struct datarec),
+ .max_entries = 1,
+};
+
+/* Helper parse functions */
+
+/* Parse Ethernet layer 2, extract network layer 3 offset and protocol
+ *
+ * Returns false on error and non-supported ether-type
+ */
+struct vlan_hdr {
+ __be16 h_vlan_TCI;
+ __be16 h_vlan_encapsulated_proto;
+};
+
+static __always_inline
+bool parse_eth(struct ethhdr *eth, void *data_end,
+ u16 *eth_proto, u64 *l3_offset)
+{
+ u16 eth_type;
+ u64 offset;
+
+ offset = sizeof(*eth);
+ if ((void *)eth + offset > data_end)
+ return false;
+
+ eth_type = eth->h_proto;
+
+ /* Skip non 802.3 Ethertypes */
+ if (unlikely(ntohs(eth_type) < ETH_P_802_3_MIN))
+ return false;
+
+ /* Handle VLAN tagged packet */
+ if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+ struct vlan_hdr *vlan_hdr;
+
+ vlan_hdr = (void *)eth + offset;
+ offset += sizeof(*vlan_hdr);
+ if ((void *)eth + offset > data_end)
+ return false;
+ eth_type = vlan_hdr->h_vlan_encapsulated_proto;
+ }
+ /* TODO: Handle double VLAN tagged packet */
+
+ *eth_proto = ntohs(eth_type);
+ *l3_offset = offset;
+ return true;
+}
+
+static __always_inline
+u16 get_dest_port_ipv4_udp(struct xdp_md *ctx, u64 nh_off)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct iphdr *iph = data + nh_off;
+ struct udphdr *udph;
+ u16 dport;
+
+ if (iph + 1 > data_end)
+ return 0;
+ if (!(iph->protocol == IPPROTO_UDP))
+ return 0;
+
+ udph = (void *)(iph + 1);
+ if (udph + 1 > data_end)
+ return 0;
+
+ dport = ntohs(udph->dest);
+ return dport;
+}
+
+static __always_inline
+int get_proto_ipv4(struct xdp_md *ctx, u64 nh_off)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct iphdr *iph = data + nh_off;
+
+ if (iph + 1 > data_end)
+ return 0;
+ return iph->protocol;
+}
+
+static __always_inline
+int get_proto_ipv6(struct xdp_md *ctx, u64 nh_off)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ipv6hdr *ip6h = data + nh_off;
+
+ if (ip6h + 1 > data_end)
+ return 0;
+ return ip6h->nexthdr;
+}
+
+SEC("xdp_cpu_map0")
+int xdp_prognum0_no_touch(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct datarec *rec;
+ u32 *cpu_selected;
+ u32 cpu_dest;
+ u32 key = 0;
+
+ /* Only use first entry in cpus_available */
+ cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+ if (!cpu_selected)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_selected;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map1_touch_data")
+int xdp_prognum1_touch_data(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ struct datarec *rec;
+ u32 *cpu_selected;
+ u32 cpu_dest;
+ u16 eth_type;
+ u32 key = 0;
+
+ /* Only use first entry in cpus_available */
+ cpu_selected = bpf_map_lookup_elem(&cpus_available, &key);
+ if (!cpu_selected)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_selected;
+
+ /* Validate packet length is minimum Eth header size */
+ if (eth + 1 > data_end)
+ return XDP_ABORTED;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ /* Read packet data, and use it (drop non 802.3 Ethertypes) */
+ eth_type = eth->h_proto;
+ if (ntohs(eth_type) < ETH_P_802_3_MIN) {
+ rec->dropped++;
+ return XDP_DROP;
+ }
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map2_round_robin")
+int xdp_prognum2_round_robin(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ struct datarec *rec;
+ u32 cpu_dest;
+ u32 *cpu_lookup;
+ u32 key0 = 0;
+
+ u32 *cpu_selected;
+ u32 *cpu_iterator;
+ u32 *cpu_max;
+ u32 cpu_idx;
+
+ cpu_max = bpf_map_lookup_elem(&cpus_count, &key0);
+ if (!cpu_max)
+ return XDP_ABORTED;
+
+ cpu_iterator = bpf_map_lookup_elem(&cpus_iterator, &key0);
+ if (!cpu_iterator)
+ return XDP_ABORTED;
+ cpu_idx = *cpu_iterator;
+
+ *cpu_iterator += 1;
+ if (*cpu_iterator == *cpu_max)
+ *cpu_iterator = 0;
+
+ cpu_selected = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+ if (!cpu_selected)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_selected;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key0);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map3_proto_separate")
+int xdp_prognum3_proto_separate(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ u8 ip_proto = IPPROTO_UDP;
+ struct datarec *rec;
+ u16 eth_proto = 0;
+ u64 l3_offset = 0;
+ u32 cpu_dest = 0;
+ u32 cpu_idx = 0;
+ u32 *cpu_lookup;
+ u32 key = 0;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (!(parse_eth(eth, data_end, ð_proto, &l3_offset)))
+ return XDP_PASS; /* Just skip */
+
+ /* Extract L4 protocol */
+ switch (eth_proto) {
+ case ETH_P_IP:
+ ip_proto = get_proto_ipv4(ctx, l3_offset);
+ break;
+ case ETH_P_IPV6:
+ ip_proto = get_proto_ipv6(ctx, l3_offset);
+ break;
+ case ETH_P_ARP:
+ cpu_idx = 0; /* ARP packet handled on separate CPU */
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ /* Choose CPU based on L4 protocol */
+ switch (ip_proto) {
+ case IPPROTO_ICMP:
+ case IPPROTO_ICMPV6:
+ cpu_idx = 2;
+ break;
+ case IPPROTO_TCP:
+ cpu_idx = 0;
+ break;
+ case IPPROTO_UDP:
+ cpu_idx = 1;
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+ if (!cpu_lookup)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_lookup;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+SEC("xdp_cpu_map4_ddos_filter_pktgen")
+int xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
+{
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ struct ethhdr *eth = data;
+ u8 ip_proto = IPPROTO_UDP;
+ struct datarec *rec;
+ u16 eth_proto = 0;
+ u64 l3_offset = 0;
+ u32 cpu_dest = 0;
+ u32 cpu_idx = 0;
+ u16 dest_port;
+ u32 *cpu_lookup;
+ u32 key = 0;
+
+ /* Count RX packet in map */
+ rec = bpf_map_lookup_elem(&rx_cnt, &key);
+ if (!rec)
+ return XDP_ABORTED;
+ rec->processed++;
+
+ if (!(parse_eth(eth, data_end, ð_proto, &l3_offset)))
+ return XDP_PASS; /* Just skip */
+
+ /* Extract L4 protocol */
+ switch (eth_proto) {
+ case ETH_P_IP:
+ ip_proto = get_proto_ipv4(ctx, l3_offset);
+ break;
+ case ETH_P_IPV6:
+ ip_proto = get_proto_ipv6(ctx, l3_offset);
+ break;
+ case ETH_P_ARP:
+ cpu_idx = 0; /* ARP packet handled on separate CPU */
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ /* Choose CPU based on L4 protocol */
+ switch (ip_proto) {
+ case IPPROTO_ICMP:
+ case IPPROTO_ICMPV6:
+ cpu_idx = 2;
+ break;
+ case IPPROTO_TCP:
+ cpu_idx = 0;
+ break;
+ case IPPROTO_UDP:
+ cpu_idx = 1;
+ /* DDoS filter UDP port 9 (pktgen) */
+ dest_port = get_dest_port_ipv4_udp(ctx, l3_offset);
+ if (dest_port == 9) {
+ if (rec)
+ rec->dropped++;
+ return XDP_DROP;
+ }
+ break;
+ default:
+ cpu_idx = 0;
+ }
+
+ cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+ if (!cpu_lookup)
+ return XDP_ABORTED;
+ cpu_dest = *cpu_lookup;
+
+ if (cpu_dest >= MAX_CPUS) {
+ rec->issue++;
+ return XDP_ABORTED;
+ }
+
+ return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
+
+
+char _license[] SEC("license") = "GPL";
+
+/*** Trace point code ***/
+
+/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_redirect/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct xdp_redirect_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int prog_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12 size:4; signed:0;
+ int ifindex; // offset:16 size:4; signed:1;
+ int err; // offset:20 size:4; signed:1;
+ int to_ifindex; // offset:24 size:4; signed:1;
+ u32 map_id; // offset:28 size:4; signed:0;
+ int map_index; // offset:32 size:4; signed:1;
+}; // offset:36
+
+enum {
+ XDP_REDIRECT_SUCCESS = 0,
+ XDP_REDIRECT_ERROR = 1
+};
+
+static __always_inline
+int xdp_redirect_collect_stat(struct xdp_redirect_ctx *ctx)
+{
+ u32 key = XDP_REDIRECT_ERROR;
+ struct datarec *rec;
+ int err = ctx->err;
+
+ if (!err)
+ key = XDP_REDIRECT_SUCCESS;
+
+ rec = bpf_map_lookup_elem(&redirect_err_cnt, &key);
+ if (!rec)
+ return 0;
+ rec->dropped += 1;
+
+ return 0; /* Indicate event was filtered (no further processing)*/
+ /*
+ * Returning 1 here would allow e.g. a perf-record tracepoint
+ * to see and record these events, but it doesn't work well
+ * in-practice as stopping perf-record also unload this
+ * bpf_prog. Plus, there is additional overhead of doing so.
+ */
+}
+
+SEC("tracepoint/xdp/xdp_redirect_err")
+int trace_xdp_redirect_err(struct xdp_redirect_ctx *ctx)
+{
+ return xdp_redirect_collect_stat(ctx);
+}
+
+SEC("tracepoint/xdp/xdp_redirect_map_err")
+int trace_xdp_redirect_map_err(struct xdp_redirect_ctx *ctx)
+{
+ return xdp_redirect_collect_stat(ctx);
+}
+
+/* Tracepoint format: /sys/kernel/debug/tracing/events/xdp/xdp_exception/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct xdp_exception_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int prog_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12; size:4; signed:0;
+ int ifindex; // offset:16; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_exception")
+int trace_xdp_exception(struct xdp_exception_ctx *ctx)
+{
+ struct datarec *rec;
+ u32 key = 0;
+
+ rec = bpf_map_lookup_elem(&exception_cnt, &key);
+ if (!rec)
+ return 1;
+ rec->dropped += 1;
+
+ return 0;
+}
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_enqueue/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct cpumap_enqueue_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int map_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12; size:4; signed:0;
+ int cpu; // offset:16; size:4; signed:1;
+ unsigned int drops; // offset:20; size:4; signed:0;
+ unsigned int processed; // offset:24; size:4; signed:0;
+ int to_cpu; // offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_enqueue")
+int trace_xdp_cpumap_enqueue(struct cpumap_enqueue_ctx *ctx)
+{
+ u32 to_cpu = ctx->to_cpu;
+ struct datarec *rec;
+
+ if (to_cpu >= MAX_CPUS)
+ return 1;
+
+ rec = bpf_map_lookup_elem(&cpumap_enqueue_cnt, &to_cpu);
+ if (!rec)
+ return 0;
+ rec->processed += ctx->processed;
+ rec->dropped += ctx->drops;
+
+ /* Record bulk events, then userspace can calc average bulk size */
+ if (ctx->processed > 0)
+ rec->issue += 1;
+
+ /* Inception: It's possible to detect overload situations, via
+ * this tracepoint. This can be used for creating a feedback
+ * loop to XDP, which can take appropriate actions to mitigate
+ * this overload situation.
+ */
+ return 0;
+}
+
+/* Tracepoint: /sys/kernel/debug/tracing/events/xdp/xdp_cpumap_kthread/format
+ * Code in: kernel/include/trace/events/xdp.h
+ */
+struct cpumap_kthread_ctx {
+ u64 __pad; // First 8 bytes are not accessible by bpf code
+ int map_id; // offset:8; size:4; signed:1;
+ u32 act; // offset:12; size:4; signed:0;
+ int cpu; // offset:16; size:4; signed:1;
+ unsigned int drops; // offset:20; size:4; signed:0;
+ unsigned int processed; // offset:24; size:4; signed:0;
+ int sched; // offset:28; size:4; signed:1;
+};
+
+SEC("tracepoint/xdp/xdp_cpumap_kthread")
+int trace_xdp_cpumap_kthread(struct cpumap_kthread_ctx *ctx)
+{
+ struct datarec *rec;
+ u32 key = 0;
+
+ rec = bpf_map_lookup_elem(&cpumap_kthread_cnt, &key);
+ if (!rec)
+ return 0;
+ rec->processed += ctx->processed;
+ rec->dropped += ctx->drops;
+
+ /* Count times kthread yielded CPU via schedule call */
+ if (ctx->sched)
+ rec->issue++;
+
+ return 0;
+}
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
new file mode 100644
index 000000000000..fc67837a5c1c
--- /dev/null
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -0,0 +1,673 @@
+/* GPLv2 Copyright(c) 2017 Jesper Dangaard Brouer, Red Hat, Inc.
+ */
+static const char *__doc__ =
+ " XDP redirect with a CPU-map type \"BPF_MAP_TYPE_CPUMAP\"";
+
+#include <errno.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+#include <locale.h>
+#include <sys/resource.h>
+#include <getopt.h>
+#include <net/if.h>
+#include <time.h>
+
+#include <arpa/inet.h>
+#include <linux/if_link.h>
+
+#define MAX_CPUS 12 /* WARNING - sync with _kern.c */
+
+/* How many xdp_progs are defined in _kern.c */
+#define MAX_PROG 5
+
+/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
+ * use bpf/libbpf.h), but cannot as (currently) needed for XDP
+ * attaching to a device via set_link_xdp_fd()
+ */
+#include "libbpf.h"
+#include "bpf_load.h"
+
+#include "bpf_util.h"
+
+static int ifindex = -1;
+static char ifname_buf[IF_NAMESIZE];
+static char *ifname;
+
+static __u32 xdp_flags;
+
+/* Exit return codes */
+#define EXIT_OK 0
+#define EXIT_FAIL 1
+#define EXIT_FAIL_OPTION 2
+#define EXIT_FAIL_XDP 3
+#define EXIT_FAIL_BPF 4
+#define EXIT_FAIL_MEM 5
+
+static const struct option long_options[] = {
+ {"help", no_argument, NULL, 'h' },
+ {"dev", required_argument, NULL, 'd' },
+ {"skb-mode", no_argument, NULL, 'S' },
+ {"debug", no_argument, NULL, 'D' },
+ {"sec", required_argument, NULL, 's' },
+ {"prognum", required_argument, NULL, 'p' },
+ {"qsize", required_argument, NULL, 'q' },
+ {"cpu", required_argument, NULL, 'c' },
+ {"no-separators", no_argument, NULL, 'z' },
+ {0, 0, NULL, 0 }
+};
+
+static void int_exit(int sig)
+{
+ fprintf(stderr,
+ "Interrupted: Removing XDP program on ifindex:%d device:%s\n",
+ ifindex, ifname);
+ if (ifindex > -1)
+ set_link_xdp_fd(ifindex, -1, xdp_flags);
+ exit(EXIT_OK);
+}
+
+static void usage(char *argv[])
+{
+ int i;
+
+ printf("\nDOCUMENTATION:\n%s\n", __doc__);
+ printf("\n");
+ printf(" Usage: %s (options-see-below)\n", argv[0]);
+ printf(" Listing options:\n");
+ for (i = 0; long_options[i].name != 0; i++) {
+ printf(" --%-12s", long_options[i].name);
+ if (long_options[i].flag != NULL)
+ printf(" flag (internal value:%d)",
+ *long_options[i].flag);
+ else
+ printf(" short-option: -%c",
+ long_options[i].val);
+ printf("\n");
+ }
+ printf("\n");
+}
+
+/* gettime returns the current time of day in nanoseconds.
+ * Cost: clock_gettime (ns) => 26ns (CLOCK_MONOTONIC)
+ * clock_gettime (ns) => 9ns (CLOCK_MONOTONIC_COARSE)
+ */
+#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
+static __u64 gettime(void)
+{
+ struct timespec t;
+ int res;
+
+ res = clock_gettime(CLOCK_MONOTONIC, &t);
+ if (res < 0) {
+ fprintf(stderr, "Error with gettimeofday! (%i)\n", res);
+ exit(EXIT_FAIL);
+ }
+ return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
+}
+
+/* Common stats data record shared with _kern.c */
+struct datarec {
+ __u64 processed;
+ __u64 dropped;
+ __u64 issue;
+};
+struct record {
+ __u64 timestamp;
+ struct datarec total;
+ struct datarec *cpu;
+};
+struct stats_record {
+ struct record rx_cnt;
+ struct record redir_err;
+ struct record kthread;
+ struct record exception;
+ struct record enq[MAX_CPUS];
+};
+
+static bool map_collect_percpu(int fd, __u32 key, struct record *rec)
+{
+ /* For percpu maps, userspace gets a value per possible CPU */
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ struct datarec values[nr_cpus];
+ __u64 sum_processed = 0;
+ __u64 sum_dropped = 0;
+ __u64 sum_issue = 0;
+ int i;
+
+ if ((bpf_map_lookup_elem(fd, &key, values)) != 0) {
+ fprintf(stderr,
+ "ERR: bpf_map_lookup_elem failed key:0x%X\n", key);
+ return false;
+ }
+ /* Get time as close as possible to reading map contents */
+ rec->timestamp = gettime();
+
+ /* Record and sum values from each CPU */
+ for (i = 0; i < nr_cpus; i++) {
+ rec->cpu[i].processed = values[i].processed;
+ sum_processed += values[i].processed;
+ rec->cpu[i].dropped = values[i].dropped;
+ sum_dropped += values[i].dropped;
+ rec->cpu[i].issue = values[i].issue;
+ sum_issue += values[i].issue;
+ }
+ rec->total.processed = sum_processed;
+ rec->total.dropped = sum_dropped;
+ rec->total.issue = sum_issue;
+ return true;
+}
+
+static struct datarec *alloc_record_per_cpu(void)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ struct datarec *array;
+ size_t size;
+
+ size = sizeof(struct datarec) * nr_cpus;
+ array = malloc(size);
+ memset(array, 0, size);
+ if (!array) {
+ fprintf(stderr, "Mem alloc error (nr_cpus:%u)\n", nr_cpus);
+ exit(EXIT_FAIL_MEM);
+ }
+ return array;
+}
+
+static struct stats_record *alloc_stats_record(void)
+{
+ struct stats_record *rec;
+ int i;
+
+ rec = malloc(sizeof(*rec));
+ memset(rec, 0, sizeof(*rec));
+ if (!rec) {
+ fprintf(stderr, "Mem alloc error\n");
+ exit(EXIT_FAIL_MEM);
+ }
+ rec->rx_cnt.cpu = alloc_record_per_cpu();
+ rec->redir_err.cpu = alloc_record_per_cpu();
+ rec->kthread.cpu = alloc_record_per_cpu();
+ rec->exception.cpu = alloc_record_per_cpu();
+ for (i = 0; i < MAX_CPUS; i++)
+ rec->enq[i].cpu = alloc_record_per_cpu();
+
+ return rec;
+}
+
+static void free_stats_record(struct stats_record *r)
+{
+ int i;
+
+ for (i = 0; i < MAX_CPUS; i++)
+ free(r->enq[i].cpu);
+ free(r->exception.cpu);
+ free(r->kthread.cpu);
+ free(r->redir_err.cpu);
+ free(r->rx_cnt.cpu);
+ free(r);
+}
+
+static double calc_period(struct record *r, struct record *p)
+{
+ double period_ = 0;
+ __u64 period = 0;
+
+ period = r->timestamp - p->timestamp;
+ if (period > 0)
+ period_ = ((double) period / NANOSEC_PER_SEC);
+
+ return period_;
+}
+
+static __u64 calc_pps(struct datarec *r, struct datarec *p, double period_)
+{
+ __u64 packets = 0;
+ __u64 pps = 0;
+
+ if (period_ > 0) {
+ packets = r->processed - p->processed;
+ pps = packets / period_;
+ }
+ return pps;
+}
+
+static __u64 calc_drop_pps(struct datarec *r, struct datarec *p, double period_)
+{
+ __u64 packets = 0;
+ __u64 pps = 0;
+
+ if (period_ > 0) {
+ packets = r->dropped - p->dropped;
+ pps = packets / period_;
+ }
+ return pps;
+}
+
+static __u64 calc_errs_pps(struct datarec *r,
+ struct datarec *p, double period_)
+{
+ __u64 packets = 0;
+ __u64 pps = 0;
+
+ if (period_ > 0) {
+ packets = r->issue - p->issue;
+ pps = packets / period_;
+ }
+ return pps;
+}
+
+static void stats_print(struct stats_record *stats_rec,
+ struct stats_record *stats_prev,
+ int prog_num)
+{
+ unsigned int nr_cpus = bpf_num_possible_cpus();
+ double pps = 0, drop = 0, err = 0;
+ struct record *rec, *prev;
+ int to_cpu;
+ double t;
+ int i;
+
+ /* Header */
+ printf("Running XDP/eBPF prog_num:%d\n", prog_num);
+ printf("%-15s %-7s %-14s %-11s %-9s\n",
+ "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info");
+
+ /* XDP rx_cnt */
+ {
+ char *fmt_rx = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
+ char *fm2_rx = "%-15s %-7s %'-14.0f %'-11.0f\n";
+ char *errstr = "";
+
+ rec = &stats_rec->rx_cnt;
+ prev = &stats_prev->rx_cnt;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ err = calc_errs_pps(r, p, t);
+ if (err > 0)
+ errstr = "cpu-dest/err";
+ if (pps > 0)
+ printf(fmt_rx, "XDP-RX",
+ i, pps, drop, err, errstr);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ err = calc_errs_pps(&rec->total, &prev->total, t);
+ printf(fm2_rx, "XDP-RX", "total", pps, drop);
+ }
+
+ /* cpumap enqueue stats */
+ for (to_cpu = 0; to_cpu < MAX_CPUS; to_cpu++) {
+ char *fmt = "%-15s %3d:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
+ char *fm2 = "%-15s %3s:%-3d %'-14.0f %'-11.0f %'-10.2f %s\n";
+ char *errstr = "";
+
+ rec = &stats_rec->enq[to_cpu];
+ prev = &stats_prev->enq[to_cpu];
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ err = calc_errs_pps(r, p, t);
+ if (err > 0) {
+ errstr = "bulk-average";
+ err = pps / err; /* calc average bulk size */
+ }
+ if (pps > 0)
+ printf(fmt, "cpumap-enqueue",
+ i, to_cpu, pps, drop, err, errstr);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ if (pps > 0) {
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ err = calc_errs_pps(&rec->total, &prev->total, t);
+ if (err > 0) {
+ errstr = "bulk-average";
+ err = pps / err; /* calc average bulk size */
+ }
+ printf(fm2, "cpumap-enqueue",
+ "sum", to_cpu, pps, drop, err, errstr);
+ }
+ }
+
+ /* cpumap kthread stats */
+ {
+ char *fmt_k = "%-15s %-7d %'-14.0f %'-11.0f %'-10.0f %s\n";
+ char *fm2_k = "%-15s %-7s %'-14.0f %'-11.0f %'-10.0f %s\n";
+ char *errstr = "";
+
+ rec = &stats_rec->kthread;
+ prev = &stats_prev->kthread;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ err = calc_errs_pps(r, p, t);
+ if (err > 0)
+ errstr = "sched";
+ if (pps > 0)
+ printf(fmt_k, "cpumap_kthread",
+ i, pps, drop, err, errstr);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ printf(fm2_k, "cpumap_kthread", "total", pps, drop);
+ }
+
+ /* XDP redirect err tracepoints (very unlikely) */
+ {
+ char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
+ char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
+
+ rec = &stats_rec->redir_err;
+ prev = &stats_prev->redir_err;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ if (pps > 0)
+ printf(fmt_err, "redirect_err", i, pps, drop);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ printf(fm2_err, "redirect_err", "total", pps, drop);
+ }
+
+ /* XDP general exception tracepoints */
+ {
+ char *fmt_err = "%-15s %-7d %'-14.0f %'-11.0f\n";
+ char *fm2_err = "%-15s %-7s %'-14.0f %'-11.0f\n";
+
+ rec = &stats_rec->exception;
+ prev = &stats_prev->exception;
+ t = calc_period(rec, prev);
+ for (i = 0; i < nr_cpus; i++) {
+ struct datarec *r = &rec->cpu[i];
+ struct datarec *p = &prev->cpu[i];
+
+ pps = calc_pps(r, p, t);
+ drop = calc_drop_pps(r, p, t);
+ if (pps > 0)
+ printf(fmt_err, "xdp_exception", i, pps, drop);
+ }
+ pps = calc_pps(&rec->total, &prev->total, t);
+ drop = calc_drop_pps(&rec->total, &prev->total, t);
+ printf(fm2_err, "xdp_exception", "total", pps, drop);
+ }
+
+ printf("\n");
+ fflush(stdout);
+}
+
+static void stats_collect(struct stats_record *rec)
+{
+ int fd, i;
+
+ fd = map_fd[1]; /* map: rx_cnt */
+ map_collect_percpu(fd, 0, &rec->rx_cnt);
+
+ fd = map_fd[2]; /* map: redirect_err_cnt */
+ map_collect_percpu(fd, 1, &rec->redir_err);
+
+ fd = map_fd[3]; /* map: cpumap_enqueue_cnt */
+ for (i = 0; i < MAX_CPUS; i++)
+ map_collect_percpu(fd, i, &rec->enq[i]);
+
+ fd = map_fd[4]; /* map: cpumap_kthread_cnt */
+ map_collect_percpu(fd, 0, &rec->kthread);
+
+ fd = map_fd[8]; /* map: exception_cnt */
+ map_collect_percpu(fd, 0, &rec->exception);
+}
+
+
+/* Pointer swap trick */
+static inline void swap(struct stats_record **a, struct stats_record **b)
+{
+ struct stats_record *tmp;
+
+ tmp = *a;
+ *a = *b;
+ *b = tmp;
+}
+
+static void stats_poll(int interval, bool use_separators, int prog_num)
+{
+ struct stats_record *record, *prev;
+
+ record = alloc_stats_record();
+ prev = alloc_stats_record();
+ stats_collect(record);
+
+ /* Trick to pretty printf with thousands separators use %' */
+ if (use_separators)
+ setlocale(LC_NUMERIC, "en_US");
+
+ while (1) {
+ swap(&prev, &record);
+ stats_collect(record);
+ stats_print(record, prev, prog_num);
+ sleep(interval);
+ }
+
+ free_stats_record(record);
+ free_stats_record(prev);
+}
+
+static int create_cpu_entry(__u32 cpu, __u32 queue_size,
+ __u32 avail_idx, bool new)
+{
+ __u32 curr_cpus_count;
+ __u32 key = 0;
+ int ret;
+
+ /* Add a CPU entry to cpumap, as this allocate a cpu entry in
+ * the kernel for the cpu.
+ */
+ ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0);
+ if (ret) {
+ fprintf(stderr, "Create CPU entry failed\n");
+ exit(EXIT_FAIL_BPF);
+ }
+
+ /* Inform bpf_prog's that a new CPU is available to select
+ * from via some control maps.
+ */
+ /* map_fd[5] = cpus_available */
+ ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0);
+ if (ret) {
+ fprintf(stderr, "Add to avail CPUs failed\n");
+ exit(EXIT_FAIL_BPF);
+ }
+
+ /* When not replacing/updating existing entry, bump the count */
+ /* map_fd[6] = cpus_count */
+ if (new) {
+ ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count);
+ if (ret) {
+ fprintf(stderr, "Failed reading curr cpus_count\n");
+ exit(EXIT_FAIL_BPF);
+ }
+ curr_cpus_count++;
+ ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0);
+ if (ret) {
+ fprintf(stderr, "Failed write curr cpus_count\n");
+ exit(EXIT_FAIL_BPF);
+ }
+ }
+ /* map_fd[7] = cpus_iterator */
+ printf("%s CPU:%u as idx:%u cpus_count:%u\n",
+ new ? "Add-new":"Replace", cpu, avail_idx, curr_cpus_count);
+
+ return 0;
+}
+
+/* CPUs are zero-indexed. Thus, add a special sentinel default value
+ * in map cpus_available to mark CPU index'es not configured
+ */
+static void mark_cpus_unavailable(void)
+{
+ __u32 invalid_cpu = MAX_CPUS;
+ int ret, i;
+
+ for (i = 0; i < MAX_CPUS; i++) {
+ /* map_fd[5] = cpus_available */
+ ret = bpf_map_update_elem(map_fd[5], &i, &invalid_cpu, 0);
+ if (ret) {
+ fprintf(stderr, "Failed marking CPU unavailable\n");
+ exit(EXIT_FAIL_BPF);
+ }
+ }
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ bool use_separators = true;
+ char filename[256];
+ bool debug = false;
+ int added_cpus = 0;
+ int longindex = 0;
+ int interval = 2;
+ int prog_num = 0;
+ int add_cpu = -1;
+ __u32 qsize;
+ int opt;
+
+ /* Notice: choosing he queue size is very important with the
+ * ixgbe driver, because it's driver page recycling trick is
+ * dependend on pages being returned quickly. The number of
+ * out-standing packets in the system must be less-than 2x
+ * RX-ring size.
+ */
+ qsize = 128+64;
+
+ snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
+ return 1;
+ }
+
+ if (load_bpf_file(filename)) {
+ fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf);
+ return EXIT_FAIL;
+ }
+
+ if (!prog_fd[0]) {
+ fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno));
+ return EXIT_FAIL;
+ }
+
+ mark_cpus_unavailable();
+
+ /* Parse commands line args */
+ while ((opt = getopt_long(argc, argv, "hSd:",
+ long_options, &longindex)) != -1) {
+ switch (opt) {
+ case 'd':
+ if (strlen(optarg) >= IF_NAMESIZE) {
+ fprintf(stderr, "ERR: --dev name too long\n");
+ goto error;
+ }
+ ifname = (char *)&ifname_buf;
+ strncpy(ifname, optarg, IF_NAMESIZE);
+ ifindex = if_nametoindex(ifname);
+ if (ifindex == 0) {
+ fprintf(stderr,
+ "ERR: --dev name unknown err(%d):%s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ break;
+ case 's':
+ interval = atoi(optarg);
+ break;
+ case 'S':
+ xdp_flags |= XDP_FLAGS_SKB_MODE;
+ break;
+ case 'D':
+ debug = true;
+ break;
+ case 'z':
+ use_separators = false;
+ break;
+ case 'p':
+ /* Selecting eBPF prog to load */
+ prog_num = atoi(optarg);
+ if (prog_num < 0 || prog_num >= MAX_PROG) {
+ fprintf(stderr,
+ "--prognum too large err(%d):%s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ break;
+ case 'c':
+ /* Add multiple CPUs */
+ add_cpu = strtoul(optarg, NULL, 0);
+ if (add_cpu > MAX_CPUS) {
+ fprintf(stderr,
+ "--cpu nr too large for cpumap err(%d):%s\n",
+ errno, strerror(errno));
+ goto error;
+ }
+ create_cpu_entry(add_cpu, qsize, added_cpus, true);
+ added_cpus++;
+ break;
+ case 'q':
+ qsize = atoi(optarg);
+ break;
+ case 'h':
+ error:
+ default:
+ usage(argv);
+ return EXIT_FAIL_OPTION;
+ }
+ }
+ /* Required option */
+ if (ifindex == -1) {
+ fprintf(stderr, "ERR: required option --dev missing\n");
+ usage(argv);
+ return EXIT_FAIL_OPTION;
+ }
+ /* Required option */
+ if (add_cpu == -1) {
+ fprintf(stderr, "ERR: required option --cpu missing\n");
+ fprintf(stderr, " Specify multiple --cpu option to add more\n");
+ usage(argv);
+ return EXIT_FAIL_OPTION;
+ }
+
+ /* Remove XDP program when program is interrupted */
+ signal(SIGINT, int_exit);
+
+ if (set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) {
+ fprintf(stderr, "link set xdp fd failed\n");
+ return EXIT_FAIL_XDP;
+ }
+
+ if (debug) {
+ printf("Debug-mode reading trace pipe (fix #define DEBUG)\n");
+ read_trace_pipe();
+ }
+
+ stats_poll(interval, use_separators, prog_num);
+ return EXIT_OK;
+}
^ permalink raw reply related
* [net-next V5 PATCH 4/5] bpf: cpumap add tracepoints
From: Jesper Dangaard Brouer @ 2017-10-06 16:12 UTC (permalink / raw)
To: netdev
Cc: jakub.kicinski, Michael S. Tsirkin, pavel.odintsov, Jason Wang,
mchan, John Fastabend, peter.waskiewicz.jr,
Jesper Dangaard Brouer, Daniel Borkmann, Alexei Starovoitov,
Andy Gospodarek
In-Reply-To: <150730632837.22839.11804085686478888137.stgit@firesoul>
This adds two tracepoint to the cpumap. One for the enqueue side
trace_xdp_cpumap_enqueue() and one for the kthread dequeue side
trace_xdp_cpumap_kthread().
To mitigate the tracepoint overhead, these are invoked during the
enqueue/dequeue bulking phases, thus amortizing the cost.
The obvious use-cases are for debugging and monitoring. The
non-intuitive use-case is using these as a feedback loop to know the
system load. One can imagine auto-scaling by reducing, adding or
activating more worker CPUs on demand.
V4: tracepoint remove time_limit info, instead add sched info
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
include/trace/events/xdp.h | 70 ++++++++++++++++++++++++++++++++++++++++++++
kernel/bpf/cpumap.c | 23 +++++++++++---
2 files changed, 88 insertions(+), 5 deletions(-)
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index eb2ece96c1a2..0c8dec61987e 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -150,6 +150,76 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \
err, map, idx)
+TRACE_EVENT(xdp_cpumap_kthread,
+
+ TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
+ int sched),
+
+ TP_ARGS(map_id, processed, drops, sched),
+
+ TP_STRUCT__entry(
+ __field(int, map_id)
+ __field(u32, act)
+ __field(int, cpu)
+ __field(unsigned int, drops)
+ __field(unsigned int, processed)
+ __field(int, sched)
+ ),
+
+ TP_fast_assign(
+ __entry->map_id = map_id;
+ __entry->act = XDP_REDIRECT;
+ __entry->cpu = smp_processor_id();
+ __entry->drops = drops;
+ __entry->processed = processed;
+ __entry->sched = sched;
+ ),
+
+ TP_printk("kthread"
+ " cpu=%d map_id=%d action=%s"
+ " processed=%u drops=%u"
+ " sched=%d",
+ __entry->cpu, __entry->map_id,
+ __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+ __entry->processed, __entry->drops,
+ __entry->sched)
+);
+
+TRACE_EVENT(xdp_cpumap_enqueue,
+
+ TP_PROTO(int map_id, unsigned int processed, unsigned int drops,
+ int to_cpu),
+
+ TP_ARGS(map_id, processed, drops, to_cpu),
+
+ TP_STRUCT__entry(
+ __field(int, map_id)
+ __field(u32, act)
+ __field(int, cpu)
+ __field(unsigned int, drops)
+ __field(unsigned int, processed)
+ __field(int, to_cpu)
+ ),
+
+ TP_fast_assign(
+ __entry->map_id = map_id;
+ __entry->act = XDP_REDIRECT;
+ __entry->cpu = smp_processor_id();
+ __entry->drops = drops;
+ __entry->processed = processed;
+ __entry->to_cpu = to_cpu;
+ ),
+
+ TP_printk("enqueue"
+ " cpu=%d map_id=%d action=%s"
+ " processed=%u drops=%u"
+ " to_cpu=%d",
+ __entry->cpu, __entry->map_id,
+ __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB),
+ __entry->processed, __entry->drops,
+ __entry->to_cpu)
+);
+
#endif /* _TRACE_XDP_H */
#include <trace/define_trace.h>
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 960deeccf245..60410b70094a 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -24,6 +24,7 @@
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/capability.h>
+#include <trace/events/xdp.h>
#include <linux/netdevice.h> /* netif_receive_skb_core */
#include <linux/etherdevice.h> /* eth_type_trans */
@@ -264,14 +265,15 @@ static int cpu_map_kthread_run(void *data)
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
- unsigned int processed = 0, drops = 0;
+ unsigned int processed = 0, drops = 0, sched = 0;
struct xdp_pkt *xdp_pkt;
/* Release CPU reschedule checks */
if (__ptr_ring_empty(rcpu->queue)) {
schedule();
+ sched = 1;
} else {
- cond_resched();
+ sched = cond_resched();
}
/* Process packets in rcpu->queue */
@@ -300,6 +302,9 @@ static int cpu_map_kthread_run(void *data)
if (++processed == 8)
break;
}
+ /* Feedback loop via tracepoint */
+ trace_xdp_cpumap_kthread(rcpu->map_id, processed, drops, sched);
+
local_bh_enable(); /* resched point, may call do_softirq() */
__set_current_state(TASK_INTERRUPTIBLE);
@@ -337,7 +342,10 @@ struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
err = ptr_ring_init(rcpu->queue, qsize, gfp);
if (err)
goto fail;
- rcpu->qsize = qsize;
+
+ rcpu->cpu = cpu;
+ rcpu->map_id = map_id;
+ rcpu->qsize = qsize;
/* Setup kthread */
rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
@@ -564,6 +572,8 @@ const struct bpf_map_ops cpu_map_ops = {
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
struct xdp_bulk_queue *bq)
{
+ unsigned int processed = 0, drops = 0;
+ const int to_cpu = rcpu->cpu;
struct ptr_ring *q;
int i;
@@ -579,13 +589,16 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
err = __ptr_ring_produce(q, xdp_pkt);
if (err) {
- /* Free xdp_pkt */
- page_frag_free(xdp_pkt);
+ drops++;
+ page_frag_free(xdp_pkt); /* Free xdp_pkt */
}
+ processed++;
}
bq->count = 0;
spin_unlock(&q->producer_lock);
+ /* Feedback loop via tracepoints */
+ trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu);
return 0;
}
^ permalink raw reply related
* [net-next V5 PATCH 3/5] bpf: cpumap xdp_buff to skb conversion and allocation
From: Jesper Dangaard Brouer @ 2017-10-06 16:12 UTC (permalink / raw)
To: netdev
Cc: jakub.kicinski, Michael S. Tsirkin, pavel.odintsov, Jason Wang,
mchan, John Fastabend, peter.waskiewicz.jr,
Jesper Dangaard Brouer, Daniel Borkmann, Alexei Starovoitov,
Andy Gospodarek
In-Reply-To: <150730632837.22839.11804085686478888137.stgit@firesoul>
This patch makes cpumap functional, by adding SKB allocation and
invoking the network stack on the dequeuing CPU.
For constructing the SKB on the remote CPU, the xdp_buff in converted
into a struct xdp_pkt, and it mapped into the top headroom of the
packet, to avoid allocating separate mem. For now, struct xdp_pkt is
just a cpumap internal data structure, with info carried between
enqueue to dequeue.
If a driver doesn't have enough headroom it is simply dropped, with
return code -EOVERFLOW. This will be picked up the xdp tracepoint
infrastructure, to allow users to catch this.
V2: take into account xdp->data_meta
V4:
- Drop busypoll tricks, keeping it more simple.
- Skip RPS and Generic-XDP-recursive-reinjection, suggested by Alexei
V5: correct RCU read protection around __netif_receive_skb_core.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
include/linux/netdevice.h | 1
kernel/bpf/cpumap.c | 150 +++++++++++++++++++++++++++++++++++++++------
net/core/dev.c | 27 ++++++++
3 files changed, 157 insertions(+), 21 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d04424cfffba..0a3dc246f066 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3251,6 +3251,7 @@ int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
int netif_rx(struct sk_buff *skb);
int netif_rx_ni(struct sk_buff *skb);
int netif_receive_skb(struct sk_buff *skb);
+int netif_receive_skb_core(struct sk_buff *skb);
gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
void napi_gro_flush(struct napi_struct *napi, bool flush_old);
struct sk_buff *napi_get_frags(struct napi_struct *napi);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 1499eae96d30..960deeccf245 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -25,6 +25,9 @@
#include <linux/kthread.h>
#include <linux/capability.h>
+#include <linux/netdevice.h> /* netif_receive_skb_core */
+#include <linux/etherdevice.h> /* eth_type_trans */
+
/* General idea: XDP packets getting XDP redirected to another CPU,
* will maximum be stored/queued for one driver ->poll() call. It is
* guaranteed that setting flush bit and flush operation happen on
@@ -169,20 +172,136 @@ static void cpu_map_kthread_stop(struct work_struct *work)
kthread_stop(rcpu->kthread); /* calls put_cpu_map_entry */
}
+/* For now, xdp_pkt is a cpumap internal data structure, with info
+ * carried between enqueue to dequeue. It is mapped into the top
+ * headroom of the packet, to avoid allocating separate mem.
+ */
+struct xdp_pkt {
+ void *data;
+ u16 len;
+ u16 headroom;
+ u16 metasize;
+ struct net_device *dev_rx;
+};
+
+/* Convert xdp_buff to xdp_pkt */
+static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp)
+{
+ struct xdp_pkt *xdp_pkt;
+ int metasize;
+ int headroom;
+
+ /* Assure headroom is available for storing info */
+ headroom = xdp->data - xdp->data_hard_start;
+ metasize = xdp->data - xdp->data_meta;
+ metasize = metasize > 0 ? metasize : 0;
+ if ((headroom - metasize) < sizeof(*xdp_pkt))
+ return NULL;
+
+ /* Store info in top of packet */
+ xdp_pkt = xdp->data_hard_start;
+
+ xdp_pkt->data = xdp->data;
+ xdp_pkt->len = xdp->data_end - xdp->data;
+ xdp_pkt->headroom = headroom - sizeof(*xdp_pkt);
+ xdp_pkt->metasize = metasize;
+
+ return xdp_pkt;
+}
+
+struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_pkt *xdp_pkt)
+{
+ unsigned int frame_size;
+ void *pkt_data_start;
+ struct sk_buff *skb;
+
+ /* build_skb need to place skb_shared_info after SKB end, and
+ * also want to know the memory "truesize". Thus, need to
+ * know the memory frame size backing xdp_buff.
+ *
+ * XDP was designed to have PAGE_SIZE frames, but this
+ * assumption is not longer true with ixgbe and i40e. It
+ * would be preferred to set frame_size to 2048 or 4096
+ * depending on the driver.
+ * frame_size = 2048;
+ * frame_len = frame_size - sizeof(*xdp_pkt);
+ *
+ * Instead, with info avail, skb_shared_info in placed after
+ * packet len. This, unfortunately fakes the truesize.
+ * Another disadvantage of this approach, the skb_shared_info
+ * is not at a fixed memory location, with mixed length
+ * packets, which is bad for cache-line hotness.
+ */
+ frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ pkt_data_start = xdp_pkt->data - xdp_pkt->headroom;
+ skb = build_skb(pkt_data_start, frame_size);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, xdp_pkt->headroom);
+ __skb_put(skb, xdp_pkt->len);
+ if (xdp_pkt->metasize)
+ skb_metadata_set(skb, xdp_pkt->metasize);
+
+ /* Essential SKB info: protocol and skb->dev */
+ skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx);
+
+ /* Optional SKB info, currently missing:
+ * - HW checksum info (skb->ip_summed)
+ * - HW RX hash (skb_set_hash)
+ * - RX ring dev queue index (skb_record_rx_queue)
+ */
+
+ return skb;
+}
+
static int cpu_map_kthread_run(void *data)
{
struct bpf_cpu_map_entry *rcpu = data;
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop()) {
+ unsigned int processed = 0, drops = 0;
struct xdp_pkt *xdp_pkt;
- schedule();
- /* Do work */
- while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) {
- /* For now just "refcnt-free" */
- page_frag_free(xdp_pkt);
+ /* Release CPU reschedule checks */
+ if (__ptr_ring_empty(rcpu->queue)) {
+ schedule();
+ } else {
+ cond_resched();
+ }
+
+ /* Process packets in rcpu->queue */
+ local_bh_disable();
+ /*
+ * The bpf_cpu_map_entry is single consumer, with this
+ * kthread CPU pinned. Lockless access to ptr_ring
+ * consume side valid as no-resize allowed of queue.
+ */
+ while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) {
+ struct sk_buff *skb;
+ int ret;
+
+ skb = cpu_map_build_skb(rcpu, xdp_pkt);
+ if (!skb) {
+ page_frag_free(xdp_pkt);
+ continue;
+ }
+
+ /* Inject into network stack */
+ ret = netif_receive_skb_core(skb);
+ if (ret == NET_RX_DROP)
+ drops++;
+
+ /* Limit BH-disable period */
+ if (++processed == 8)
+ break;
}
+ local_bh_enable(); /* resched point, may call do_softirq() */
+
__set_current_state(TASK_INTERRUPTIBLE);
}
put_cpu_map_entry(rcpu);
@@ -470,13 +589,6 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
return 0;
}
-/* Notice: Will change in later patch */
-struct xdp_pkt {
- void *data;
- u16 len;
- u16 headroom;
-};
-
/* Runs under RCU-read-side, plus in softirq under NAPI protection.
* Thus, safe percpu variable access.
*/
@@ -504,17 +616,13 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
struct xdp_pkt *xdp_pkt;
- int headroom;
- /* For now this is just used as a void pointer to data_hard_start.
- * Followup patch will generalize this.
- */
- xdp_pkt = xdp->data_hard_start;
+ xdp_pkt = convert_to_xdp_pkt(xdp);
+ if (!xdp_pkt)
+ return -EOVERFLOW;
- /* Fake writing into xdp_pkt->data to measure overhead */
- headroom = xdp->data - xdp->data_hard_start;
- if (headroom < sizeof(*xdp_pkt))
- xdp_pkt->data = xdp->data;
+ /* Info needed when constructing SKB on remote CPU */
+ xdp_pkt->dev_rx = dev_rx;
bq_enqueue(rcpu, xdp_pkt);
return 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index 1770097cfd86..bfe316a0918b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4489,6 +4489,33 @@ static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
return ret;
}
+/**
+ * netif_receive_skb_core - special purpose version of netif_receive_skb
+ * @skb: buffer to process
+ *
+ * More direct receive version of netif_receive_skb(). It should
+ * only be used by callers that have a need to skip RPS and Generic XDP.
+ * Caller must also take care of handling if (page_is_)pfmemalloc.
+ *
+ * This function may only be called from softirq context and interrupts
+ * should be enabled.
+ *
+ * Return values (usually ignored):
+ * NET_RX_SUCCESS: no congestion
+ * NET_RX_DROP: packet was dropped
+ */
+int netif_receive_skb_core(struct sk_buff *skb)
+{
+ int ret;
+
+ rcu_read_lock();
+ ret = __netif_receive_skb_core(skb, false);
+ rcu_read_unlock();
+
+ return ret;
+}
+EXPORT_SYMBOL(netif_receive_skb_core);
+
static int __netif_receive_skb(struct sk_buff *skb)
{
int ret;
^ permalink raw reply related
* [net-next V5 PATCH 2/5] bpf: XDP_REDIRECT enable use of cpumap
From: Jesper Dangaard Brouer @ 2017-10-06 16:12 UTC (permalink / raw)
To: netdev
Cc: jakub.kicinski, Michael S. Tsirkin, pavel.odintsov, Jason Wang,
mchan, John Fastabend, peter.waskiewicz.jr,
Jesper Dangaard Brouer, Daniel Borkmann, Alexei Starovoitov,
Andy Gospodarek
In-Reply-To: <150730632837.22839.11804085686478888137.stgit@firesoul>
This patch connects cpumap to the xdp_do_redirect_map infrastructure.
Still no SKB allocation are done yet. The XDP frames are transferred
to the other CPU, but they are simply refcnt decremented on the remote
CPU. This served as a good benchmark for measuring the overhead of
remote refcnt decrement. If driver page recycle cache is not
efficient then this, exposes a bottleneck in the page allocator.
A shout-out to MST's ptr_ring, which is the secret behind is being so
efficient to transfer memory pointers between CPUs, without constantly
bouncing cache-lines between CPUs.
V3: Handle !CONFIG_BPF_SYSCALL pointed out by kbuild test robot.
V4: Make Generic-XDP aware of cpumap type, but don't allow redirect yet,
as implementation require a separate upstream discussion.
V5:
- Fix a maybe-uninitialized pointed out by kbuild test robot.
- Restrict bpf-prog side access to cpumap, open when use-cases appear
- Implement cpu_map_enqueue() as a more simple void pointer enqueue
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
include/linux/bpf.h | 31 +++++++++-
include/trace/events/xdp.h | 10 +++
kernel/bpf/cpumap.c | 22 +++++++
kernel/bpf/verifier.c | 8 ++-
net/core/filter.c | 140 +++++++++++++++++++++++++++++++++++---------
5 files changed, 177 insertions(+), 34 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 252f4bc9eb25..36ec83343c82 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -320,6 +320,13 @@ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
void __dev_map_flush(struct bpf_map *map);
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 index);
+void __cpu_map_flush(struct bpf_map *map);
+struct xdp_buff;
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+ struct net_device *dev_rx);
+
/* Return map's numa specified by userspace */
static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
{
@@ -327,7 +334,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
attr->numa_node : NUMA_NO_NODE;
}
-#else
+#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
@@ -385,6 +392,28 @@ static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
static inline void __dev_map_flush(struct bpf_map *map)
{
}
+
+static inline
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ return NULL;
+}
+
+static inline void __cpu_map_insert_ctx(struct bpf_map *map, u32 index)
+{
+}
+
+static inline void __cpu_map_flush(struct bpf_map *map)
+{
+}
+
+struct xdp_buff;
+static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ return 0;
+}
#endif /* CONFIG_BPF_SYSCALL */
#if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL)
diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
index 4e16c43fba10..eb2ece96c1a2 100644
--- a/include/trace/events/xdp.h
+++ b/include/trace/events/xdp.h
@@ -136,12 +136,18 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
__entry->map_id, __entry->map_index)
);
+#define devmap_ifindex(fwd, map) \
+ (!fwd ? 0 : \
+ (!map ? 0 : \
+ ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \
+ ((struct net_device *)fwd)->ifindex : 0)))
+
#define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \
- trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0, \
+ trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \
0, map, idx)
#define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \
- trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0, \
+ trace_xdp_redirect_map_err(dev, xdp, devmap_ifindex(fwd, map), \
err, map, idx)
#endif /* _TRACE_XDP_H */
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index d3e921620097..1499eae96d30 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -480,7 +480,7 @@ struct xdp_pkt {
/* Runs under RCU-read-side, plus in softirq under NAPI protection.
* Thus, safe percpu variable access.
*/
-int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
+static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
{
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
@@ -500,6 +500,26 @@ int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
return 0;
}
+int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
+ struct net_device *dev_rx)
+{
+ struct xdp_pkt *xdp_pkt;
+ int headroom;
+
+ /* For now this is just used as a void pointer to data_hard_start.
+ * Followup patch will generalize this.
+ */
+ xdp_pkt = xdp->data_hard_start;
+
+ /* Fake writing into xdp_pkt->data to measure overhead */
+ headroom = xdp->data - xdp->data_hard_start;
+ if (headroom < sizeof(*xdp_pkt))
+ xdp_pkt->data = xdp->data;
+
+ bq_enqueue(rcpu, xdp_pkt);
+ return 0;
+}
+
void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit)
{
struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4cf9b72c59a0..34e3ebbc221f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1572,6 +1572,11 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
if (func_id != BPF_FUNC_redirect_map)
goto error;
break;
+ /* Restrict bpf side of cpumap, open when use-cases appear */
+ case BPF_MAP_TYPE_CPUMAP:
+ if (func_id != BPF_FUNC_redirect_map)
+ goto error;
+ break;
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
case BPF_MAP_TYPE_HASH_OF_MAPS:
if (func_id != BPF_FUNC_map_lookup_elem)
@@ -1608,7 +1613,8 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id)
goto error;
break;
case BPF_FUNC_redirect_map:
- if (map->map_type != BPF_MAP_TYPE_DEVMAP)
+ if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+ map->map_type != BPF_MAP_TYPE_CPUMAP)
goto error;
break;
case BPF_FUNC_sk_redirect_map:
diff --git a/net/core/filter.c b/net/core/filter.c
index 9b6e7e84aafd..c02e772309d5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2521,10 +2521,36 @@ static int __bpf_tx_xdp(struct net_device *dev,
err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
if (err)
return err;
- if (map)
+ dev->netdev_ops->ndo_xdp_flush(dev);
+ return 0;
+}
+
+static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
+ struct bpf_map *map,
+ struct xdp_buff *xdp,
+ u32 index)
+{
+ int err;
+
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ struct net_device *dev = fwd;
+
+ if (!dev->netdev_ops->ndo_xdp_xmit)
+ return -EOPNOTSUPP;
+
+ err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp);
+ if (err)
+ return err;
__dev_map_insert_ctx(map, index);
- else
- dev->netdev_ops->ndo_xdp_flush(dev);
+
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ struct bpf_cpu_map_entry *rcpu = fwd;
+
+ err = cpu_map_enqueue(rcpu, xdp, dev_rx);
+ if (err)
+ return err;
+ __cpu_map_insert_ctx(map, index);
+ }
return 0;
}
@@ -2534,11 +2560,33 @@ void xdp_do_flush_map(void)
struct bpf_map *map = ri->map_to_flush;
ri->map_to_flush = NULL;
- if (map)
- __dev_map_flush(map);
+ if (map) {
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ __dev_map_flush(map);
+ break;
+ case BPF_MAP_TYPE_CPUMAP:
+ __cpu_map_flush(map);
+ break;
+ default:
+ break;
+ }
+ }
}
EXPORT_SYMBOL_GPL(xdp_do_flush_map);
+static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
+{
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_DEVMAP:
+ return __dev_map_lookup_elem(map, index);
+ case BPF_MAP_TYPE_CPUMAP:
+ return __cpu_map_lookup_elem(map, index);
+ default:
+ return NULL;
+ }
+}
+
static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
unsigned long aux)
{
@@ -2551,8 +2599,8 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
- struct net_device *fwd = NULL;
u32 index = ri->ifindex;
+ void *fwd = NULL;
int err;
ri->ifindex = 0;
@@ -2565,7 +2613,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
goto err;
}
- fwd = __dev_map_lookup_elem(map, index);
+ fwd = __xdp_map_lookup_elem(map, index);
if (!fwd) {
err = -EINVAL;
goto err;
@@ -2573,7 +2621,7 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
if (ri->map_to_flush && ri->map_to_flush != map)
xdp_do_flush_map();
- err = __bpf_tx_xdp(fwd, map, xdp, index);
+ err = __bpf_tx_xdp_map(dev, fwd, map, xdp, index);
if (unlikely(err))
goto err;
@@ -2615,54 +2663,88 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
}
EXPORT_SYMBOL_GPL(xdp_do_redirect);
-int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
- struct bpf_prog *xdp_prog)
+static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd)
+{
+ unsigned int len;
+
+ if (unlikely(!(fwd->flags & IFF_UP)))
+ return -ENETDOWN;
+
+ len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
+ if (skb->len > len)
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
{
struct redirect_info *ri = this_cpu_ptr(&redirect_info);
unsigned long map_owner = ri->map_owner;
struct bpf_map *map = ri->map;
struct net_device *fwd = NULL;
u32 index = ri->ifindex;
- unsigned int len;
int err = 0;
ri->ifindex = 0;
ri->map = NULL;
ri->map_owner = 0;
- if (map) {
- if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
- err = -EFAULT;
- map = NULL;
- goto err;
- }
- fwd = __dev_map_lookup_elem(map, index);
- } else {
- fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(xdp_map_invalid(xdp_prog, map_owner))) {
+ err = -EFAULT;
+ map = NULL;
+ goto err;
}
+ fwd = __xdp_map_lookup_elem(map, index);
if (unlikely(!fwd)) {
err = -EINVAL;
goto err;
}
- if (unlikely(!(fwd->flags & IFF_UP))) {
- err = -ENETDOWN;
+ if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+ skb->dev = fwd;
+ } else {
+ /* TODO: Handle BPF_MAP_TYPE_CPUMAP */
+ err = -EBADRQC;
goto err;
}
- len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
- if (skb->len > len) {
- err = -EMSGSIZE;
+ _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index);
+ return 0;
+err:
+ _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err);
+ return err;
+}
+
+int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+ u32 index = ri->ifindex;
+ struct net_device *fwd;
+ int err = 0;
+
+ if (ri->map)
+ return xdp_do_generic_redirect_map(dev, skb, xdp_prog);
+
+ ri->ifindex = 0;
+ fwd = dev_get_by_index_rcu(dev_net(dev), index);
+ if (unlikely(!fwd)) {
+ err = -EINVAL;
goto err;
}
+ if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+ goto err;
+
skb->dev = fwd;
- map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index)
- : _trace_xdp_redirect(dev, xdp_prog, index);
+ _trace_xdp_redirect(dev, xdp_prog, index);
return 0;
err:
- map ? _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map, index, err)
- : _trace_xdp_redirect_err(dev, xdp_prog, index, err);
+ _trace_xdp_redirect_err(dev, xdp_prog, index, err);
return err;
}
EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);
^ permalink raw reply related
* [net-next V5 PATCH 1/5] bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP
From: Jesper Dangaard Brouer @ 2017-10-06 16:12 UTC (permalink / raw)
To: netdev
Cc: jakub.kicinski, Michael S. Tsirkin, pavel.odintsov, Jason Wang,
mchan, John Fastabend, peter.waskiewicz.jr,
Jesper Dangaard Brouer, Daniel Borkmann, Alexei Starovoitov,
Andy Gospodarek
In-Reply-To: <150730632837.22839.11804085686478888137.stgit@firesoul>
The 'cpumap' is primary used as a backend map for XDP BPF helper
call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
This patch implement the main part of the map. It is not connected to
the XDP redirect system yet, and no SKB allocation are done yet.
The main concern in this patch is to ensure the datapath can run
without any locking. This adds complexity to the setup and tear-down
procedure, which assumptions are extra carefully documented in the
code comments.
V2:
- make sure array isn't larger than NR_CPUS
- make sure CPUs added is a valid possible CPU
V3: fix nitpicks from Jakub Kicinski <kubakici@wp.pl>
V5:
- Restrict map allocation to root / CAP_SYS_ADMIN
- WARN_ON_ONCE if queue is not empty on tear-down
- Return -EPERM on memlock limit instead of -ENOMEM
- Error code in __cpu_map_entry_alloc() also handle ptr_ring_cleanup()
- Moved cpu_map_enqueue() to next patch
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
include/linux/bpf_types.h | 1
include/uapi/linux/bpf.h | 1
kernel/bpf/Makefile | 1
kernel/bpf/cpumap.c | 540 ++++++++++++++++++++++++++++++++++++++++
kernel/bpf/syscall.c | 8 +
tools/include/uapi/linux/bpf.h | 1
6 files changed, 551 insertions(+), 1 deletion(-)
create mode 100644 kernel/bpf/cpumap.c
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 6f1a567667b8..814c1081a4a9 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -41,4 +41,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
#ifdef CONFIG_STREAM_PARSER
BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
#endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6d2137b4cf38..03f8e2827a95 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -111,6 +111,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
};
enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 897daa005b23..dba0bd33a43c 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
ifeq ($(CONFIG_NET),y)
obj-$(CONFIG_BPF_SYSCALL) += devmap.o
+obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
ifeq ($(CONFIG_STREAM_PARSER),y)
obj-$(CONFIG_BPF_SYSCALL) += sockmap.o
endif
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
new file mode 100644
index 000000000000..d3e921620097
--- /dev/null
+++ b/kernel/bpf/cpumap.c
@@ -0,0 +1,540 @@
+/* bpf/cpumap.c
+ *
+ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
+ * Released under terms in GPL version 2. See COPYING.
+ */
+
+/* The 'cpumap' is primary used as a backend map for XDP BPF helper
+ * call bpf_redirect_map() and XDP_REDIRECT action, like 'devmap'.
+ *
+ * Unlike devmap which redirect XDP frames out another NIC device,
+ * this map type redirect raw XDP frames to another CPU. The remote
+ * CPU will do SKB-allocation and call the normal network stack.
+ *
+ * This is a scalability and isolation mechanism, that allow
+ * separating the early driver network XDP layer, from the rest of the
+ * netstack, and assigning dedicated CPUs for this stage. This
+ * basically allows for 10G wirespeed pre-filtering via bpf.
+ */
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+
+#include <linux/sched.h>
+#include <linux/workqueue.h>
+#include <linux/kthread.h>
+#include <linux/capability.h>
+
+/* General idea: XDP packets getting XDP redirected to another CPU,
+ * will maximum be stored/queued for one driver ->poll() call. It is
+ * guaranteed that setting flush bit and flush operation happen on
+ * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr()
+ * which queue in bpf_cpu_map_entry contains packets.
+ */
+
+#define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */
+struct xdp_bulk_queue {
+ void *q[CPU_MAP_BULK_SIZE];
+ unsigned int count;
+};
+
+/* Struct for every remote "destination" CPU in map */
+struct bpf_cpu_map_entry {
+ u32 cpu; /* kthread CPU and map index */
+ int map_id; /* Back reference to map */
+ u32 qsize; /* Redundant queue size for map lookup */
+
+ /* XDP can run multiple RX-ring queues, need __percpu enqueue store */
+ struct xdp_bulk_queue __percpu *bulkq;
+
+ /* Queue with potential multi-producers, and single-consumer kthread */
+ struct ptr_ring *queue;
+ struct task_struct *kthread;
+ struct work_struct kthread_stop_wq;
+
+ atomic_t refcnt; /* Control when this struct can be free'ed */
+ struct rcu_head rcu;
+};
+
+struct bpf_cpu_map {
+ struct bpf_map map;
+ /* Below members specific for map type */
+ struct bpf_cpu_map_entry **cpu_map;
+ unsigned long __percpu *flush_needed;
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_bulk_queue *bq);
+
+static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
+{
+ return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
+{
+ struct bpf_cpu_map *cmap;
+ int err = -ENOMEM;
+ u64 cost;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return ERR_PTR(-EPERM);
+
+ /* check sanity of attributes */
+ if (attr->max_entries == 0 || attr->key_size != 4 ||
+ attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+ return ERR_PTR(-EINVAL);
+
+ cmap = kzalloc(sizeof(*cmap), GFP_USER);
+ if (!cmap)
+ return ERR_PTR(-ENOMEM);
+
+ /* mandatory map attributes */
+ cmap->map.map_type = attr->map_type;
+ cmap->map.key_size = attr->key_size;
+ cmap->map.value_size = attr->value_size;
+ cmap->map.max_entries = attr->max_entries;
+ cmap->map.map_flags = attr->map_flags;
+ cmap->map.numa_node = bpf_map_attr_numa_node(attr);
+
+ /* Pre-limit array size based on NR_CPUS, not final CPU check */
+ if (cmap->map.max_entries > NR_CPUS)
+ return ERR_PTR(-E2BIG);
+
+ /* make sure page count doesn't overflow */
+ cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *);
+ cost += cpu_map_bitmap_size(attr) * num_possible_cpus();
+ if (cost >= U32_MAX - PAGE_SIZE)
+ goto free_cmap;
+ cmap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+ /* Notice returns -EPERM on if map size is larger than memlock limit */
+ err = bpf_map_precharge_memlock(cmap->map.pages);
+ if (err)
+ goto free_cmap;
+
+ /* A per cpu bitfield with a bit per possible CPU in map */
+ cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr),
+ __alignof__(unsigned long));
+ if (!cmap->flush_needed)
+ goto free_cmap;
+
+ /* Alloc array for possible remote "destination" CPUs */
+ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries *
+ sizeof(struct bpf_cpu_map_entry *),
+ cmap->map.numa_node);
+ if (!cmap->cpu_map)
+ goto free_cmap;
+
+ return &cmap->map;
+free_cmap:
+ free_percpu(cmap->flush_needed);
+ kfree(cmap);
+ return ERR_PTR(err);
+}
+
+void __cpu_map_queue_destructor(void *ptr)
+{
+ /* The tear-down procedure should have made sure that queue is
+ * empty. See __cpu_map_entry_replace() and work-queue
+ * invoked cpu_map_kthread_stop(). Catch any broken behaviour
+ * gracefully and warn once.
+ */
+ if (WARN_ON_ONCE(ptr))
+ page_frag_free(ptr);
+}
+
+static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+ if (atomic_dec_and_test(&rcpu->refcnt)) {
+ /* The queue should be empty at this point */
+ ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor);
+ kfree(rcpu->queue);
+ kfree(rcpu);
+ }
+}
+
+static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
+{
+ atomic_inc(&rcpu->refcnt);
+}
+
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+ struct bpf_cpu_map_entry *rcpu;
+
+ rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+ synchronize_rcu(); /* wait for flush in __cpu_map_entry_free() */
+ kthread_stop(rcpu->kthread); /* calls put_cpu_map_entry */
+}
+
+static int cpu_map_kthread_run(void *data)
+{
+ struct bpf_cpu_map_entry *rcpu = data;
+
+ set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ struct xdp_pkt *xdp_pkt;
+
+ schedule();
+ /* Do work */
+ while ((xdp_pkt = ptr_ring_consume(rcpu->queue))) {
+ /* For now just "refcnt-free" */
+ page_frag_free(xdp_pkt);
+ }
+ __set_current_state(TASK_INTERRUPTIBLE);
+ }
+ put_cpu_map_entry(rcpu);
+
+ __set_current_state(TASK_RUNNING);
+ return 0;
+}
+
+struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, int map_id)
+{
+ gfp_t gfp = GFP_ATOMIC|__GFP_NOWARN;
+ struct bpf_cpu_map_entry *rcpu;
+ int numa, err;
+
+ /* Have map->numa_node, but choose node of redirect target CPU */
+ numa = cpu_to_node(cpu);
+
+ rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa);
+ if (!rcpu)
+ return NULL;
+
+ /* Alloc percpu bulkq */
+ rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq),
+ sizeof(void *), gfp);
+ if (!rcpu->bulkq)
+ goto fail;
+
+ /* Alloc queue */
+ rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa);
+ if (!rcpu->queue)
+ goto fail;
+
+ err = ptr_ring_init(rcpu->queue, qsize, gfp);
+ if (err)
+ goto fail;
+ rcpu->qsize = qsize;
+
+ /* Setup kthread */
+ rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa,
+ "cpumap/%d/map:%d", cpu, map_id);
+ if (IS_ERR(rcpu->kthread))
+ goto fail;
+
+ /* Make sure kthread runs on a single CPU */
+ kthread_bind(rcpu->kthread, cpu);
+ wake_up_process(rcpu->kthread);
+
+ get_cpu_map_entry(rcpu); /* 1-refcnt for being in cmap->cpu_map[] */
+ get_cpu_map_entry(rcpu); /* 1-refcnt for kthread */
+
+ return rcpu;
+
+fail: /* Hint: free API detect NULL values */
+ free_percpu(rcpu->bulkq);
+ ptr_ring_cleanup(rcpu->queue, NULL);
+ kfree(rcpu->queue);
+ kfree(rcpu);
+ return NULL;
+}
+
+void __cpu_map_entry_free(struct rcu_head *rcu)
+{
+ struct bpf_cpu_map_entry *rcpu;
+ int cpu;
+
+ /* This cpu_map_entry have been disconnected from map and one
+ * RCU graze-period have elapsed. Thus, XDP cannot queue any
+ * new packets and cannot change/set flush_needed that can
+ * find this entry.
+ */
+ rcpu = container_of(rcu, struct bpf_cpu_map_entry, rcu);
+
+ /* Flush remaining packets in percpu bulkq */
+ for_each_online_cpu(cpu) {
+ struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
+
+ /* No concurrent bq_enqueue can run at this point */
+ bq_flush_to_queue(rcpu, bq);
+ }
+ free_percpu(rcpu->bulkq);
+ /* Cannot kthread_stop() here, last put free rcpu resources */
+ put_cpu_map_entry(rcpu);
+}
+
+/* After xchg pointer to bpf_cpu_map_entry, use the call_rcu() to
+ * ensure any driver rcu critical sections have completed, but this
+ * does not guarantee a flush has happened yet. Because driver side
+ * rcu_read_lock/unlock only protects the running XDP program. The
+ * atomic xchg and NULL-ptr check in __cpu_map_flush() makes sure a
+ * pending flush op doesn't fail.
+ *
+ * The bpf_cpu_map_entry is still used by the kthread, and there can
+ * still be pending packets (in queue and percpu bulkq). A refcnt
+ * makes sure to last user (kthread_stop vs. call_rcu) free memory
+ * resources.
+ *
+ * The rcu callback __cpu_map_entry_free flush remaining packets in
+ * percpu bulkq to queue. Due to caller map_delete_elem() disable
+ * preemption, cannot call kthread_stop() to make sure queue is empty.
+ * Instead a work_queue is started for stopping kthread,
+ * cpu_map_kthread_stop, which waits for an RCU graze period before
+ * stopping kthread, emptying the queue.
+ */
+void __cpu_map_entry_replace(struct bpf_cpu_map *cmap,
+ u32 key_cpu, struct bpf_cpu_map_entry *rcpu)
+{
+ struct bpf_cpu_map_entry *old_rcpu;
+
+ old_rcpu = xchg(&cmap->cpu_map[key_cpu], rcpu);
+ if (old_rcpu) {
+ call_rcu(&old_rcpu->rcu, __cpu_map_entry_free);
+ INIT_WORK(&old_rcpu->kthread_stop_wq, cpu_map_kthread_stop);
+ schedule_work(&old_rcpu->kthread_stop_wq);
+ }
+}
+
+int cpu_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ u32 key_cpu = *(u32 *)key;
+
+ if (key_cpu >= map->max_entries)
+ return -EINVAL;
+
+ /* notice caller map_delete_elem() use preempt_disable() */
+ __cpu_map_entry_replace(cmap, key_cpu, NULL);
+ return 0;
+}
+
+int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
+ u64 map_flags)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ struct bpf_cpu_map_entry *rcpu;
+
+ /* Array index key correspond to CPU number */
+ u32 key_cpu = *(u32 *)key;
+ /* Value is the queue size */
+ u32 qsize = *(u32 *)value;
+
+ /* Make sure CPU is a valid possible cpu */
+ if (!cpu_possible(key_cpu))
+ return -ENODEV;
+
+ if (unlikely(map_flags > BPF_EXIST))
+ return -EINVAL;
+ if (unlikely(key_cpu >= cmap->map.max_entries))
+ return -E2BIG;
+ if (unlikely(map_flags == BPF_NOEXIST))
+ return -EEXIST;
+ if (unlikely(qsize > 16384)) /* sanity limit on qsize */
+ return -EOVERFLOW;
+
+ if (qsize == 0) {
+ rcpu = NULL; /* Same as deleting */
+ } else {
+ /* Updating qsize cause re-allocation of bpf_cpu_map_entry */
+ rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
+ if (!rcpu)
+ return -ENOMEM;
+ }
+ rcu_read_lock();
+ __cpu_map_entry_replace(cmap, key_cpu, rcpu);
+ rcu_read_unlock();
+ return 0;
+}
+
+void cpu_map_free(struct bpf_map *map)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ int cpu;
+ u32 i;
+
+ /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+ * so the bpf programs (can be more than one that used this map) were
+ * disconnected from events. Wait for outstanding critical sections in
+ * these programs to complete. The rcu critical section only guarantees
+ * no further "XDP/bpf-side" reads against bpf_cpu_map->cpu_map.
+ * It does __not__ ensure pending flush operations (if any) are
+ * complete.
+ */
+ synchronize_rcu();
+
+ /* To ensure all pending flush operations have completed wait for flush
+ * bitmap to indicate all flush_needed bits to be zero on _all_ cpus.
+ * Because the above synchronize_rcu() ensures the map is disconnected
+ * from the program we can assume no new bits will be set.
+ */
+ for_each_online_cpu(cpu) {
+ unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu);
+
+ while (!bitmap_empty(bitmap, cmap->map.max_entries))
+ cond_resched();
+ }
+
+ /* For cpu_map the remote CPUs can still be using the entries
+ * (struct bpf_cpu_map_entry).
+ */
+ for (i = 0; i < cmap->map.max_entries; i++) {
+ struct bpf_cpu_map_entry *rcpu;
+
+ rcpu = READ_ONCE(cmap->cpu_map[i]);
+ if (!rcpu)
+ continue;
+
+ /* bq flush and cleanup happens after RCU graze-period */
+ __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */
+ }
+ free_percpu(cmap->flush_needed);
+ bpf_map_area_free(cmap->cpu_map);
+ kfree(cmap);
+}
+
+struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ struct bpf_cpu_map_entry *rcpu;
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ rcpu = READ_ONCE(cmap->cpu_map[key]);
+ return rcpu;
+}
+
+static void *cpu_map_lookup_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_cpu_map_entry *rcpu =
+ __cpu_map_lookup_elem(map, *(u32 *)key);
+
+ return rcpu ? &rcpu->qsize : NULL;
+}
+
+static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ u32 index = key ? *(u32 *)key : U32_MAX;
+ u32 *next = next_key;
+
+ if (index >= cmap->map.max_entries) {
+ *next = 0;
+ return 0;
+ }
+
+ if (index == cmap->map.max_entries - 1)
+ return -ENOENT;
+ *next = index + 1;
+ return 0;
+}
+
+const struct bpf_map_ops cpu_map_ops = {
+ .map_alloc = cpu_map_alloc,
+ .map_free = cpu_map_free,
+ .map_delete_elem = cpu_map_delete_elem,
+ .map_update_elem = cpu_map_update_elem,
+ .map_lookup_elem = cpu_map_lookup_elem,
+ .map_get_next_key = cpu_map_get_next_key,
+};
+
+static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
+ struct xdp_bulk_queue *bq)
+{
+ struct ptr_ring *q;
+ int i;
+
+ if (unlikely(!bq->count))
+ return 0;
+
+ q = rcpu->queue;
+ spin_lock(&q->producer_lock);
+
+ for (i = 0; i < bq->count; i++) {
+ void *xdp_pkt = bq->q[i];
+ int err;
+
+ err = __ptr_ring_produce(q, xdp_pkt);
+ if (err) {
+ /* Free xdp_pkt */
+ page_frag_free(xdp_pkt);
+ }
+ }
+ bq->count = 0;
+ spin_unlock(&q->producer_lock);
+
+ return 0;
+}
+
+/* Notice: Will change in later patch */
+struct xdp_pkt {
+ void *data;
+ u16 len;
+ u16 headroom;
+};
+
+/* Runs under RCU-read-side, plus in softirq under NAPI protection.
+ * Thus, safe percpu variable access.
+ */
+int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt)
+{
+ struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
+
+ if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
+ bq_flush_to_queue(rcpu, bq);
+
+ /* Notice, xdp_buff/page MUST be queued here, long enough for
+ * driver to code invoking us to finished, due to driver
+ * (e.g. ixgbe) recycle tricks based on page-refcnt.
+ *
+ * Thus, incoming xdp_pkt is always queued here (else we race
+ * with another CPU on page-refcnt and remaining driver code).
+ * Queue time is very short, as driver will invoke flush
+ * operation, when completing napi->poll call.
+ */
+ bq->q[bq->count++] = xdp_pkt;
+ return 0;
+}
+
+void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+
+ __set_bit(bit, bitmap);
+}
+
+void __cpu_map_flush(struct bpf_map *map)
+{
+ struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map);
+ unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed);
+ u32 bit;
+
+ /* The napi->poll softirq makes sure __cpu_map_insert_ctx()
+ * and __cpu_map_flush() happen on same CPU. Thus, the percpu
+ * bitmap indicate which percpu bulkq have packets.
+ */
+ for_each_set_bit(bit, bitmap, map->max_entries) {
+ struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]);
+ struct xdp_bulk_queue *bq;
+
+ /* This is possible if entry is removed by user space
+ * between xdp redirect and flush op.
+ */
+ if (unlikely(!rcpu))
+ continue;
+
+ __clear_bit(bit, bitmap);
+
+ /* Flush all frames in bulkq to real queue */
+ bq = this_cpu_ptr(rcpu->bulkq);
+ bq_flush_to_queue(rcpu, bq);
+
+ /* If already running, costs spin_lock_irqsave + smb_mb */
+ wake_up_process(rcpu->kthread);
+ }
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b927da66f653..641bdb0df020 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -593,6 +593,12 @@ static int map_update_elem(union bpf_attr *attr)
if (copy_from_user(value, uvalue, value_size) != 0)
goto free_value;
+ /* Need to create a kthread, thus must support schedule */
+ if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ err = map->ops->map_update_elem(map, key, value, attr->flags);
+ goto out;
+ }
+
/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
* inside bpf map update or delete otherwise deadlocks are possible
*/
@@ -623,7 +629,7 @@ static int map_update_elem(union bpf_attr *attr)
}
__this_cpu_dec(bpf_prog_active);
preempt_enable();
-
+out:
if (!err)
trace_bpf_map_update_elem(map, ufd, key, value);
free_value:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6d2137b4cf38..03f8e2827a95 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -111,6 +111,7 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH_OF_MAPS,
BPF_MAP_TYPE_DEVMAP,
BPF_MAP_TYPE_SOCKMAP,
+ BPF_MAP_TYPE_CPUMAP,
};
enum bpf_prog_type {
^ permalink raw reply related
* [net-next V5 PATCH 0/5] New bpf cpumap type for XDP_REDIRECT
From: Jesper Dangaard Brouer @ 2017-10-06 16:12 UTC (permalink / raw)
To: netdev
Cc: jakub.kicinski, Michael S. Tsirkin, pavel.odintsov, Jason Wang,
mchan, John Fastabend, peter.waskiewicz.jr,
Jesper Dangaard Brouer, Daniel Borkmann, Alexei Starovoitov,
Andy Gospodarek
Introducing a new way to redirect XDP frames. Notice how no driver
changes are necessary given the design of XDP_REDIRECT.
This redirect map type is called 'cpumap', as it allows redirection
XDP frames to remote CPUs. The remote CPU will do the SKB allocation
and start the network stack invocation on that CPU.
This is a scalability and isolation mechanism, that allow separating
the early driver network XDP layer, from the rest of the netstack, and
assigning dedicated CPUs for this stage. The sysadm control/configure
the RX-CPU to NIC-RX queue (as usual) via procfs smp_affinity and how
many queues are configured via ethtool --set-channels. Benchmarks
show that a single CPU can handle approx 11Mpps. Thus, only assigning
two NIC RX-queues (and two CPUs) is sufficient for handling 10Gbit/s
wirespeed smallest packet 14.88Mpps. Reducing the number of queues
have the advantage that more packets being "bulk" available per hard
interrupt[1].
[1] https://www.netdevconf.org/2.1/papers/BusyPollingNextGen.pdf
Use-cases:
1. End-host based pre-filtering for DDoS mitigation. This is fast
enough to allow software to see and filter all packets wirespeed.
Thus, no packets getting silently dropped by hardware.
2. Given NIC HW unevenly distributes packets across RX queue, this
mechanism can be used for redistribution load across CPUs. This
usually happens when HW is unaware of a new protocol. This
resembles RPS (Receive Packet Steering), just faster, but with more
responsibility placed on the BPF program for correct steering.
3. Auto-scaling or power saving via only activating the appropriate
number of remote CPUs for handling the current load. The cpumap
tracepoints can function as a feedback loop for this purpose.
See individual patches for patchset-version changes.
Patchset V5 based on net-next at:
cc71b7b07119 ("net/ipv6: remove unused err variable on icmpv6_push_pending_frames")
---
Jesper Dangaard Brouer (5):
bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP
bpf: XDP_REDIRECT enable use of cpumap
bpf: cpumap xdp_buff to skb conversion and allocation
bpf: cpumap add tracepoints
samples/bpf: add cpumap sample program xdp_redirect_cpu
include/linux/bpf.h | 31 ++
include/linux/bpf_types.h | 1
include/linux/netdevice.h | 1
include/trace/events/xdp.h | 80 ++++
include/uapi/linux/bpf.h | 1
kernel/bpf/Makefile | 1
kernel/bpf/cpumap.c | 681 +++++++++++++++++++++++++++++++++++
kernel/bpf/syscall.c | 8
kernel/bpf/verifier.c | 8
net/core/dev.c | 27 +
net/core/filter.c | 140 ++++++-
samples/bpf/Makefile | 4
samples/bpf/xdp_redirect_cpu_kern.c | 609 +++++++++++++++++++++++++++++++
samples/bpf/xdp_redirect_cpu_user.c | 673 +++++++++++++++++++++++++++++++++++
tools/include/uapi/linux/bpf.h | 1
15 files changed, 2232 insertions(+), 34 deletions(-)
create mode 100644 kernel/bpf/cpumap.c
create mode 100644 samples/bpf/xdp_redirect_cpu_kern.c
create mode 100644 samples/bpf/xdp_redirect_cpu_user.c
^ permalink raw reply
* [PATCH] netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
From: Shmulik Ladkani @ 2017-10-06 16:02 UTC (permalink / raw)
To: Pablo Neira Ayuso, netfilter-devel
Cc: Willem de Bruijn, netdev, Daniel Borkmann, shmulik,
Rafael Buchbinder, Shmulik Ladkani
From: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced
support for attaching an eBPF object by an fd, with the
'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each
IPT_SO_SET_REPLACE call.
However this breaks subsequent iptables calls:
# iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT
# iptables -A INPUT -s 5.6.7.8 -j ACCEPT
iptables: Invalid argument. Run `dmesg' for more information.
That's because iptables works by loading exising rules using
IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with
the replacement set.
However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number
(from the initial "iptables -m bpf" invocation) - so when 2nd invocation
occurs, userspace passes a bogus fd number, which leads to
'bpf_mt_check_v1' to fail.
One suggested solution [1] was to hack iptables userspace, to perform a
"entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new,
process-local fd per every 'xt_bpf_info_v1' entry seen.
However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to
depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects.
This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given
'.fd' and instead perform an in-kernel lookup for the bpf object given
the provided '.path'.
It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named
XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is
expected to provide the path of the pinned object.
Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved.
References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2
[2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Willem de Bruijn <willemb@google.com>
Reported-by: Rafael Buchbinder <rafi@rbk.ms>
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
---
include/uapi/linux/netfilter/xt_bpf.h | 1 +
kernel/bpf/inode.c | 1 +
net/netfilter/xt_bpf.c | 22 ++++++++++++++++++++--
3 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h
index b97725af2ac0..da161b56c79e 100644
--- a/include/uapi/linux/netfilter/xt_bpf.h
+++ b/include/uapi/linux/netfilter/xt_bpf.h
@@ -23,6 +23,7 @@ enum xt_bpf_modes {
XT_BPF_MODE_FD_PINNED,
XT_BPF_MODE_FD_ELF,
};
+#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED
struct xt_bpf_info_v1 {
__u16 mode;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index e833ed914358..be1dde967208 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -363,6 +363,7 @@ int bpf_obj_get_user(const char __user *pathname)
putname(pname);
return ret;
}
+EXPORT_SYMBOL_GPL(bpf_obj_get_user);
static void bpf_evict_inode(struct inode *inode)
{
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 38986a95216c..29123934887b 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -8,6 +8,7 @@
*/
#include <linux/module.h>
+#include <linux/syscalls.h>
#include <linux/skbuff.h>
#include <linux/filter.h>
#include <linux/bpf.h>
@@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret)
return 0;
}
+static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret)
+{
+ mm_segment_t oldfs = get_fs();
+ int retval, fd;
+
+ set_fs(KERNEL_DS);
+ fd = bpf_obj_get_user(path);
+ set_fs(oldfs);
+ if (fd < 0)
+ return fd;
+
+ retval = __bpf_mt_check_fd(fd, ret);
+ sys_close(fd);
+ return retval;
+}
+
static int bpf_mt_check(const struct xt_mtchk_param *par)
{
struct xt_bpf_info *info = par->matchinfo;
@@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par)
return __bpf_mt_check_bytecode(info->bpf_program,
info->bpf_program_num_elem,
&info->filter);
- else if (info->mode == XT_BPF_MODE_FD_PINNED ||
- info->mode == XT_BPF_MODE_FD_ELF)
+ else if (info->mode == XT_BPF_MODE_FD_ELF)
return __bpf_mt_check_fd(info->fd, &info->filter);
+ else if (info->mode == XT_BPF_MODE_PATH_PINNED)
+ return __bpf_mt_check_path(info->path, &info->filter);
else
return -EINVAL;
}
--
2.14.2
^ permalink raw reply related
* Re: [net-next V4 PATCH 1/5] bpf: introduce new bpf cpu map type BPF_MAP_TYPE_CPUMAP
From: Jesper Dangaard Brouer @ 2017-10-06 15:58 UTC (permalink / raw)
To: Daniel Borkmann
Cc: netdev, jakub.kicinski, Michael S. Tsirkin, pavel.odintsov,
Jason Wang, mchan, John Fastabend, peter.waskiewicz.jr,
Daniel Borkmann, Alexei Starovoitov, Andy Gospodarek, brouer
In-Reply-To: <59D798B8.8090101@iogearbox.net>
On Fri, 06 Oct 2017 16:52:40 +0200 Daniel Borkmann <daniel@iogearbox.net> wrote:
> On 10/06/2017 12:50 PM, Jesper Dangaard Brouer wrote:
> > On Thu, 05 Oct 2017 11:40:15 +0200
> > Daniel Borkmann <daniel@iogearbox.net> wrote:
> >> On 10/04/2017 02:03 PM, Jesper Dangaard Brouer wrote:
> >> [...]
> [...]
> >>> + /* Updating qsize cause re-allocation of bpf_cpu_map_entry */
> >>> + rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id);
> >>> + if (!rcpu)
> >>> + return -ENOMEM;
> >>> + }
> >>> + rcu_read_lock();
> >>> + __cpu_map_entry_replace(cmap, key_cpu, rcpu);
> >>> + rcu_read_unlock();
> >>> + return 0;
> >>
> >> You need to update verifier such that this function cannot be called
> >> out of an BPF program,
> >
> > In the example BPF program, I do a lookup into the map, but only to
> > verify that an entry exist (I don't look at the value). I would like
> > to support such usage.
>
> Ok, put comment below.
>
> >> otherwise it would be possible under full RCU
> >> read context, which is explicitly avoided here and also it would otherwise
> >> be allowed for other maps of different type as well, which needs to
> >> be avoided.
> >
> > Sorry, I don't follow this.
>
> What I meant is that check_map_func_compatibility() should check for
> BPF_MAP_TYPE_CPUMAP and only allow func_id of BPF_FUNC_redirect_map
> and BPF_FUNC_map_lookup_elem to be used, which I haven't seen the set
> restricting it to. Some of your later patches do this for the helper
> BPF_FUNC_redirect_map but the important point is that map updates
> wouldn't be done out of the BPF program itself, but rather from user
> space control path given they can't be done under full RCU read lock
> context if I read this correctly (which the programs run in though).
Okay, I choose to restrict bpf_prog side in check_map_func_compatibility()
as you describe. And I changed the user program to keep track of valid
entries via secondary map. We can always add/allow lookup later if users
request this.
I'll send out V5 shortly...
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* [PATCH v2] gso: fix payload length when gso_size is zero
From: Alexey Kodanev @ 2017-10-06 16:02 UTC (permalink / raw)
To: netdev; +Cc: Steffen Klassert, Alexander Duyck, David Miller, Alexey Kodanev
When gso_size reset to zero for the tail segment in skb_segment(), later
in ipv6_gso_segment(), __skb_udp_tunnel_segment() and gre_gso_segment()
we will get incorrect results (payload length, pcsum) for that segment.
inet_gso_segment() already has a check for gso_size before calculating
payload.
The issue was found with LTP vxlan & gre tests over ixgbe NIC.
Fixes: 07b26c9454a2 ("gso: Support partial splitting at the frag_list pointer")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
---
v2: also added skb_is_gso to gre_gso_segment() and __skb_udp_tunnel_segment()
net/ipv4/gre_offload.c | 2 +-
net/ipv4/udp_offload.c | 2 +-
net/ipv6/ip6_offload.c | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index d5cac99..8c72034 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -98,7 +98,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
greh = (struct gre_base_hdr *)skb_transport_header(skb);
pcsum = (__sum16 *)(greh + 1);
- if (gso_partial) {
+ if (gso_partial && skb_is_gso(skb)) {
unsigned int partial_adj;
/* Adjust checksum to account for the fact that
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0932c85..6401574 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -122,7 +122,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
* will be using a length value equal to only one MSS sized
* segment instead of the entire frame.
*/
- if (gso_partial) {
+ if (gso_partial && skb_is_gso(skb)) {
uh->len = htons(skb_shinfo(skb)->gso_size +
SKB_GSO_CB(skb)->data_offset +
skb->head - (unsigned char *)uh);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index cdb3728..4a87f94 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -105,7 +105,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
for (skb = segs; skb; skb = skb->next) {
ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
- if (gso_partial)
+ if (gso_partial && skb_is_gso(skb))
payload_len = skb_shinfo(skb)->gso_size +
SKB_GSO_CB(skb)->data_offset +
skb->head - (unsigned char *)(ipv6h + 1);
--
1.8.3.1
^ permalink raw reply related
* [PATCH iproute2 v2 3/3] ss: add AF_VSOCK support
From: Stefan Hajnoczi @ 2017-10-06 15:48 UTC (permalink / raw)
To: netdev; +Cc: Stephen Hemminger, Jorgen Hansen, Dexuan Cui, Stefan Hajnoczi
In-Reply-To: <20171006154841.10495-1-stefanha@redhat.com>
The AF_VSOCK address family is a host<->guest communications channel
supported by VMware, KVM, and Hyper-V. Initial VMware support was
released in Linux 3.9 in 2013 and transports for other hypervisors were
added later.
AF_VSOCK addresses are <u32 cid, u32 port> tuples. The 32-bit cid
integer is comparable to an IP address. AF_VSOCK ports work like
TCP/UDP ports.
Both SOCK_STREAM and SOCK_DGRAM socket types are available.
This patch adds AF_VSOCK support to ss(8) so that sockets can be
observed.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
misc/ss.c | 184 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
man/man8/ss.8 | 8 ++-
2 files changed, 188 insertions(+), 4 deletions(-)
diff --git a/misc/ss.c b/misc/ss.c
index 005e781d..8b563bd4 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -44,6 +44,7 @@
#include <linux/packet_diag.h>
#include <linux/netlink_diag.h>
#include <linux/sctp.h>
+#include <linux/vm_sockets_diag.h>
#define MAGIC_SEQ 123456
@@ -126,6 +127,8 @@ enum {
PACKET_R_DB,
NETLINK_DB,
SCTP_DB,
+ VSOCK_ST_DB,
+ VSOCK_DG_DB,
MAX_DB
};
@@ -134,6 +137,7 @@ enum {
#define ALL_DB ((1<<MAX_DB)-1)
#define INET_L4_DBM ((1<<TCP_DB)|(1<<UDP_DB)|(1<<DCCP_DB)|(1<<SCTP_DB))
#define INET_DBM (INET_L4_DBM | (1<<RAW_DB))
+#define VSOCK_DBM ((1<<VSOCK_ST_DB)|(1<<VSOCK_DG_DB))
enum {
SS_UNKNOWN,
@@ -222,6 +226,14 @@ static const struct filter default_dbs[MAX_DB] = {
.states = SS_CONN,
.families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
},
+ [VSOCK_ST_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_VSOCK),
+ },
+ [VSOCK_DG_DB] = {
+ .states = SS_CONN,
+ .families = FAMILY_MASK(AF_VSOCK),
+ },
};
static const struct filter default_afs[AF_MAX] = {
@@ -245,6 +257,10 @@ static const struct filter default_afs[AF_MAX] = {
.dbs = (1 << NETLINK_DB),
.states = (1 << SS_CLOSE),
},
+ [AF_VSOCK] = {
+ .dbs = VSOCK_DBM,
+ .states = SS_CONN,
+ },
};
static int do_default = 1;
@@ -283,6 +299,8 @@ static void filter_default_dbs(struct filter *f)
filter_db_set(f, PACKET_DG_DB);
filter_db_set(f, NETLINK_DB);
filter_db_set(f, SCTP_DB);
+ filter_db_set(f, VSOCK_ST_DB);
+ filter_db_set(f, VSOCK_DG_DB);
}
static void filter_states_set(struct filter *f, int states)
@@ -791,6 +809,18 @@ static const char *proto_name(int protocol)
return "???";
}
+static const char *vsock_netid_name(int type)
+{
+ switch (type) {
+ case SOCK_STREAM:
+ return "v_str";
+ case SOCK_DGRAM:
+ return "v_dgr";
+ default:
+ return "???";
+ }
+}
+
static void sock_state_print(struct sockstat *s)
{
const char *sock_name;
@@ -823,6 +853,9 @@ static void sock_state_print(struct sockstat *s)
case AF_NETLINK:
sock_name = "nl";
break;
+ case AF_VSOCK:
+ sock_name = vsock_netid_name(s->type);
+ break;
default:
sock_name = "unknown";
}
@@ -1149,6 +1182,8 @@ static int run_ssfilter(struct ssfilter *f, struct sockstat *s)
return s->lport == 0 && s->local.data[0] == 0;
if (s->local.family == AF_NETLINK)
return s->lport < 0;
+ if (s->local.family == AF_VSOCK)
+ return s->lport > 1023;
return is_ephemeral(s->lport);
}
@@ -1524,6 +1559,15 @@ void *parse_devcond(char *name)
return res;
}
+static void vsock_set_inet_prefix(inet_prefix *a, __u32 cid)
+{
+ *a = (inet_prefix){
+ .bytelen = sizeof(cid),
+ .family = AF_VSOCK,
+ };
+ memcpy(a->data, &cid, sizeof(cid));
+}
+
void *parse_hostcond(char *addr, bool is_port)
{
char *port = NULL;
@@ -1598,6 +1642,37 @@ void *parse_hostcond(char *addr, bool is_port)
goto out;
}
+ if (fam == AF_VSOCK || strncmp(addr, "vsock:", 6) == 0) {
+ __u32 cid = ~(__u32)0;
+
+ a.addr.family = AF_VSOCK;
+ if (strncmp(addr, "vsock:", 6) == 0)
+ addr += 6;
+
+ if (is_port)
+ port = addr;
+ else {
+ port = strchr(addr, ':');
+ if (port) {
+ *port = '\0';
+ port++;
+ }
+ }
+
+ if (port && strcmp(port, "*") &&
+ get_u32((__u32 *)&a.port, port, 0))
+ return NULL;
+
+ if (addr[0] && strcmp(addr, "*")) {
+ a.addr.bitlen = 32;
+ if (get_u32(&cid, addr, 0))
+ return NULL;
+ }
+ vsock_set_inet_prefix(&a.addr, cid);
+ fam = AF_VSOCK;
+ goto out;
+ }
+
if (fam == AF_INET || !strncmp(addr, "inet:", 5)) {
fam = AF_INET;
if (!strncmp(addr, "inet:", 5))
@@ -3674,6 +3749,88 @@ static int netlink_show(struct filter *f)
return 0;
}
+static bool vsock_type_skip(struct sockstat *s, struct filter *f)
+{
+ if (s->type == SOCK_STREAM && !(f->dbs & (1 << VSOCK_ST_DB)))
+ return true;
+ if (s->type == SOCK_DGRAM && !(f->dbs & (1 << VSOCK_DG_DB)))
+ return true;
+ return false;
+}
+
+static void vsock_addr_print(inet_prefix *a, __u32 port)
+{
+ char cid_str[sizeof("4294967295")];
+ char port_str[sizeof("4294967295")];
+ __u32 cid;
+
+ memcpy(&cid, a->data, sizeof(cid));
+
+ if (cid == ~(__u32)0)
+ snprintf(cid_str, sizeof(cid_str), "*");
+ else
+ snprintf(cid_str, sizeof(cid_str), "%u", cid);
+
+ if (port == ~(__u32)0)
+ snprintf(port_str, sizeof(port_str), "*");
+ else
+ snprintf(port_str, sizeof(port_str), "%u", port);
+
+ sock_addr_print(cid_str, ":", port_str, NULL);
+}
+
+static void vsock_stats_print(struct sockstat *s, struct filter *f)
+{
+ sock_state_print(s);
+
+ vsock_addr_print(&s->local, s->lport);
+ vsock_addr_print(&s->remote, s->rport);
+
+ proc_ctx_print(s);
+
+ printf("\n");
+}
+
+static int vsock_show_sock(const struct sockaddr_nl *addr,
+ struct nlmsghdr *nlh, void *arg)
+{
+ struct filter *f = (struct filter *)arg;
+ struct vsock_diag_msg *r = NLMSG_DATA(nlh);
+ struct sockstat stat = {
+ .type = r->vdiag_type,
+ .lport = r->vdiag_src_port,
+ .rport = r->vdiag_dst_port,
+ .state = r->vdiag_state,
+ .ino = r->vdiag_ino,
+ };
+
+ vsock_set_inet_prefix(&stat.local, r->vdiag_src_cid);
+ vsock_set_inet_prefix(&stat.remote, r->vdiag_dst_cid);
+
+ if (vsock_type_skip(&stat, f))
+ return 0;
+
+ if (f->f && run_ssfilter(f->f, &stat) == 0)
+ return 0;
+
+ vsock_stats_print(&stat, f);
+
+ return 0;
+}
+
+static int vsock_show(struct filter *f)
+{
+ DIAG_REQUEST(req, struct vsock_diag_req r);
+
+ if (!filter_af_get(f, AF_VSOCK))
+ return 0;
+
+ req.r.sdiag_family = AF_VSOCK;
+ req.r.vdiag_states = f->states;
+
+ return handle_netlink_request(f, &req.nlh, sizeof(req), vsock_show_sock);
+}
+
struct sock_diag_msg {
__u8 sdiag_family;
};
@@ -3694,6 +3851,8 @@ static int generic_show_sock(const struct sockaddr_nl *addr,
return packet_show_sock(addr, nlh, arg);
case AF_NETLINK:
return netlink_show_sock(addr, nlh, arg);
+ case AF_VSOCK:
+ return vsock_show_sock(addr, nlh, arg);
default:
return -1;
}
@@ -3921,14 +4080,15 @@ static void _usage(FILE *dest)
" -d, --dccp display only DCCP sockets\n"
" -w, --raw display only RAW sockets\n"
" -x, --unix display only Unix domain sockets\n"
+" --vsock display only vsock sockets\n"
" -f, --family=FAMILY display sockets of type FAMILY\n"
-" FAMILY := {inet|inet6|link|unix|netlink|help}\n"
+" FAMILY := {inet|inet6|link|unix|netlink|vsock|help}\n"
"\n"
" -K, --kill forcibly close sockets, display what was closed\n"
" -H, --no-header Suppress header line\n"
"\n"
" -A, --query=QUERY, --socket=QUERY\n"
-" QUERY := {all|inet|tcp|udp|raw|unix|unix_dgram|unix_stream|unix_seqpacket|packet|netlink}[,QUERY]\n"
+" QUERY := {all|inet|tcp|udp|raw|unix|unix_dgram|unix_stream|unix_seqpacket|packet|netlink|vsock_stream|vsock_dgram}[,QUERY]\n"
"\n"
" -D, --diag=FILE Dump raw information about TCP sockets to FILE\n"
" -F, --filter=FILE read filter information from FILE\n"
@@ -4001,6 +4161,9 @@ static int scan_state(const char *state)
exit(-1);
}
+/* Values 'v' and 'V' are already used so a non-character is used */
+#define OPT_VSOCK 256
+
static const struct option long_opts[] = {
{ "numeric", 0, 0, 'n' },
{ "resolve", 0, 0, 'r' },
@@ -4017,6 +4180,7 @@ static const struct option long_opts[] = {
{ "udp", 0, 0, 'u' },
{ "raw", 0, 0, 'w' },
{ "unix", 0, 0, 'x' },
+ { "vsock", 0, 0, OPT_VSOCK },
{ "all", 0, 0, 'a' },
{ "listening", 0, 0, 'l' },
{ "ipv4", 0, 0, '4' },
@@ -4102,6 +4266,9 @@ int main(int argc, char *argv[])
case 'x':
filter_af_set(¤t_filter, AF_UNIX);
break;
+ case OPT_VSOCK:
+ filter_af_set(¤t_filter, AF_VSOCK);
+ break;
case 'a':
state_filter = SS_ALL;
break;
@@ -4128,6 +4295,8 @@ int main(int argc, char *argv[])
filter_af_set(¤t_filter, AF_UNIX);
else if (strcmp(optarg, "netlink") == 0)
filter_af_set(¤t_filter, AF_NETLINK);
+ else if (strcmp(optarg, "vsock") == 0)
+ filter_af_set(¤t_filter, AF_VSOCK);
else if (strcmp(optarg, "help") == 0)
help();
else {
@@ -4193,6 +4362,15 @@ int main(int argc, char *argv[])
filter_db_set(¤t_filter, PACKET_DG_DB);
} else if (strcmp(p, "netlink") == 0) {
filter_db_set(¤t_filter, NETLINK_DB);
+ } else if (strcmp(p, "vsock") == 0) {
+ filter_db_set(¤t_filter, VSOCK_ST_DB);
+ filter_db_set(¤t_filter, VSOCK_DG_DB);
+ } else if (strcmp(p, "vsock_stream") == 0 ||
+ strcmp(p, "v_str") == 0) {
+ filter_db_set(¤t_filter, VSOCK_ST_DB);
+ } else if (strcmp(p, "vsock_dgram") == 0 ||
+ strcmp(p, "v_dgr") == 0) {
+ filter_db_set(¤t_filter, VSOCK_DG_DB);
} else {
fprintf(stderr, "ss: \"%s\" is illegal socket table id\n", p);
usage();
@@ -4408,6 +4586,8 @@ int main(int argc, char *argv[])
dccp_show(¤t_filter);
if (current_filter.dbs & (1<<SCTP_DB))
sctp_show(¤t_filter);
+ if (current_filter.dbs & VSOCK_DBM)
+ vsock_show(¤t_filter);
if (show_users || show_proc_ctx || show_sock_ctx)
user_ent_destroy();
diff --git a/man/man8/ss.8 b/man/man8/ss.8
index 3bec97f0..3af509e9 100644
--- a/man/man8/ss.8
+++ b/man/man8/ss.8
@@ -125,14 +125,18 @@ Display Unix domain sockets (alias for -f unix).
.B \-S, \-\-sctp
Display SCTP sockets.
.TP
+.B \-\-vsock
+Display vsock sockets (alias for -f vsock).
+.TP
.B \-f FAMILY, \-\-family=FAMILY
Display sockets of type FAMILY.
-Currently the following families are supported: unix, inet, inet6, link, netlink.
+Currently the following families are supported: unix, inet, inet6, link, netlink, vsock.
.TP
.B \-A QUERY, \-\-query=QUERY, \-\-socket=QUERY
List of socket tables to dump, separated by commas. The following identifiers
are understood: all, inet, tcp, udp, raw, unix, packet, netlink, unix_dgram,
-unix_stream, unix_seqpacket, packet_raw, packet_dgram, dccp, sctp.
+unix_stream, unix_seqpacket, packet_raw, packet_dgram, dccp, sctp,
+vsock_stream, vsock_dgram.
.TP
.B \-D FILE, \-\-diag=FILE
Do not display anything, just dump raw information about TCP sockets to FILE after applying filters. If FILE is - stdout is used.
--
2.13.6
^ permalink raw reply related
* [PATCH iproute2 v2 2/3] include: add <linux/vm_sockets_diag.h>
From: Stefan Hajnoczi @ 2017-10-06 15:48 UTC (permalink / raw)
To: netdev; +Cc: Stephen Hemminger, Jorgen Hansen, Dexuan Cui, Stefan Hajnoczi
In-Reply-To: <20171006154841.10495-1-stefanha@redhat.com>
This new Linux header file defines the sock_diag interface used by
AF_VSOCK. This new header file was merged in net-next in commit
413a4317aca7d6367d57a5971b0c461f03851207 ("VSOCK: add sock_diag
interface").
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
include/linux/vm_sockets_diag.h | 33 +++++++++++++++++++++++++++++++++
1 file changed, 33 insertions(+)
create mode 100644 include/linux/vm_sockets_diag.h
diff --git a/include/linux/vm_sockets_diag.h b/include/linux/vm_sockets_diag.h
new file mode 100644
index 00000000..14cd7dc5
--- /dev/null
+++ b/include/linux/vm_sockets_diag.h
@@ -0,0 +1,33 @@
+/* AF_VSOCK sock_diag(7) interface for querying open sockets */
+
+#ifndef _UAPI__VM_SOCKETS_DIAG_H__
+#define _UAPI__VM_SOCKETS_DIAG_H__
+
+#include <linux/types.h>
+
+/* Request */
+struct vsock_diag_req {
+ __u8 sdiag_family; /* must be AF_VSOCK */
+ __u8 sdiag_protocol; /* must be 0 */
+ __u16 pad; /* must be 0 */
+ __u32 vdiag_states; /* query bitmap (e.g. 1 << TCP_LISTEN) */
+ __u32 vdiag_ino; /* must be 0 (reserved) */
+ __u32 vdiag_show; /* must be 0 (reserved) */
+ __u32 vdiag_cookie[2];
+};
+
+/* Response */
+struct vsock_diag_msg {
+ __u8 vdiag_family; /* AF_VSOCK */
+ __u8 vdiag_type; /* SOCK_STREAM or SOCK_DGRAM */
+ __u8 vdiag_state; /* sk_state (e.g. TCP_LISTEN) */
+ __u8 vdiag_shutdown; /* local RCV_SHUTDOWN | SEND_SHUTDOWN */
+ __u32 vdiag_src_cid;
+ __u32 vdiag_src_port;
+ __u32 vdiag_dst_cid;
+ __u32 vdiag_dst_port;
+ __u32 vdiag_ino;
+ __u32 vdiag_cookie[2];
+};
+
+#endif /* _UAPI__VM_SOCKETS_DIAG_H__ */
--
2.13.6
^ permalink raw reply related
* [PATCH iproute2 v2 1/3] ss: allow AF_FAMILY constants >32
From: Stefan Hajnoczi @ 2017-10-06 15:48 UTC (permalink / raw)
To: netdev; +Cc: Stephen Hemminger, Jorgen Hansen, Dexuan Cui, Stefan Hajnoczi
In-Reply-To: <20171006154841.10495-1-stefanha@redhat.com>
Linux has more than 32 address families defined in <bits/socket.h>. Use
a 64-bit type so all of them can be represented in the filter->families
bitmask.
It's easy to introduce bugs when using (1 << AF_FAMILY) because the
value is 32-bit. This can produce incorrect results from bitmask
operations so introduce the FAMILY_MASK() macro to eliminate these bugs.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
misc/ss.c | 54 ++++++++++++++++++++++++++++--------------------------
1 file changed, 28 insertions(+), 26 deletions(-)
diff --git a/misc/ss.c b/misc/ss.c
index dd8dfaa4..005e781d 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -170,55 +170,57 @@ enum {
struct filter {
int dbs;
int states;
- int families;
+ uint64_t families;
struct ssfilter *f;
bool kill;
};
+#define FAMILY_MASK(family) ((uint64_t)1 << (family))
+
static const struct filter default_dbs[MAX_DB] = {
[TCP_DB] = {
.states = SS_CONN,
- .families = (1 << AF_INET) | (1 << AF_INET6),
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
},
[DCCP_DB] = {
.states = SS_CONN,
- .families = (1 << AF_INET) | (1 << AF_INET6),
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
},
[UDP_DB] = {
.states = (1 << SS_ESTABLISHED),
- .families = (1 << AF_INET) | (1 << AF_INET6),
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
},
[RAW_DB] = {
.states = (1 << SS_ESTABLISHED),
- .families = (1 << AF_INET) | (1 << AF_INET6),
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
},
[UNIX_DG_DB] = {
.states = (1 << SS_CLOSE),
- .families = (1 << AF_UNIX),
+ .families = FAMILY_MASK(AF_UNIX),
},
[UNIX_ST_DB] = {
.states = SS_CONN,
- .families = (1 << AF_UNIX),
+ .families = FAMILY_MASK(AF_UNIX),
},
[UNIX_SQ_DB] = {
.states = SS_CONN,
- .families = (1 << AF_UNIX),
+ .families = FAMILY_MASK(AF_UNIX),
},
[PACKET_DG_DB] = {
.states = (1 << SS_CLOSE),
- .families = (1 << AF_PACKET),
+ .families = FAMILY_MASK(AF_PACKET),
},
[PACKET_R_DB] = {
.states = (1 << SS_CLOSE),
- .families = (1 << AF_PACKET),
+ .families = FAMILY_MASK(AF_PACKET),
},
[NETLINK_DB] = {
.states = (1 << SS_CLOSE),
- .families = (1 << AF_NETLINK),
+ .families = FAMILY_MASK(AF_NETLINK),
},
[SCTP_DB] = {
.states = SS_CONN,
- .families = (1 << AF_INET) | (1 << AF_INET6),
+ .families = FAMILY_MASK(AF_INET) | FAMILY_MASK(AF_INET6),
},
};
@@ -258,14 +260,14 @@ static void filter_db_set(struct filter *f, int db)
static void filter_af_set(struct filter *f, int af)
{
f->states |= default_afs[af].states;
- f->families |= 1 << af;
+ f->families |= FAMILY_MASK(af);
do_default = 0;
preferred_family = af;
}
static int filter_af_get(struct filter *f, int af)
{
- return f->families & (1 << af);
+ return !!(f->families & FAMILY_MASK(af));
}
static void filter_default_dbs(struct filter *f)
@@ -302,7 +304,7 @@ static void filter_merge_defaults(struct filter *f)
f->families |= default_dbs[db].families;
}
for (af = 0; af < AF_MAX; af++) {
- if (!(f->families & (1 << af)))
+ if (!(f->families & FAMILY_MASK(af)))
continue;
if (!(default_afs[af].dbs & f->dbs))
@@ -2608,7 +2610,7 @@ static int show_one_inet_sock(const struct sockaddr_nl *addr,
struct inet_diag_msg *r = NLMSG_DATA(h);
struct sockstat s = {};
- if (!(diag_arg->f->families & (1 << r->idiag_family)))
+ if (!(diag_arg->f->families & FAMILY_MASK(r->idiag_family)))
return 0;
parse_diag_msg(h, &s);
@@ -2802,7 +2804,7 @@ static int tcp_show(struct filter *f)
return -1;
}
- if (f->families & (1<<AF_INET)) {
+ if (f->families & FAMILY_MASK(AF_INET)) {
if ((fp = net_tcp_open()) == NULL)
goto outerr;
@@ -2812,7 +2814,7 @@ static int tcp_show(struct filter *f)
fclose(fp);
}
- if ((f->families & (1<<AF_INET6)) &&
+ if ((f->families & FAMILY_MASK(AF_INET6)) &&
(fp = net_tcp6_open()) != NULL) {
setbuffer(fp, buf, bufsize);
if (generic_record_read(fp, tcp_show_line, f, AF_INET6))
@@ -2911,7 +2913,7 @@ static int udp_show(struct filter *f)
&& inet_show_netlink(f, NULL, IPPROTO_UDP) == 0)
return 0;
- if (f->families&(1<<AF_INET)) {
+ if (f->families&FAMILY_MASK(AF_INET)) {
if ((fp = net_udp_open()) == NULL)
goto outerr;
if (generic_record_read(fp, dgram_show_line, f, AF_INET))
@@ -2919,7 +2921,7 @@ static int udp_show(struct filter *f)
fclose(fp);
}
- if ((f->families&(1<<AF_INET6)) &&
+ if ((f->families&FAMILY_MASK(AF_INET6)) &&
(fp = net_udp6_open()) != NULL) {
if (generic_record_read(fp, dgram_show_line, f, AF_INET6))
goto outerr;
@@ -2951,7 +2953,7 @@ static int raw_show(struct filter *f)
inet_show_netlink(f, NULL, IPPROTO_RAW) == 0)
return 0;
- if (f->families&(1<<AF_INET)) {
+ if (f->families&FAMILY_MASK(AF_INET)) {
if ((fp = net_raw_open()) == NULL)
goto outerr;
if (generic_record_read(fp, dgram_show_line, f, AF_INET))
@@ -2959,7 +2961,7 @@ static int raw_show(struct filter *f)
fclose(fp);
}
- if ((f->families&(1<<AF_INET6)) &&
+ if ((f->families&FAMILY_MASK(AF_INET6)) &&
(fp = net_raw6_open()) != NULL) {
if (generic_record_read(fp, dgram_show_line, f, AF_INET6))
goto outerr;
@@ -3703,13 +3705,13 @@ static int handle_follow_request(struct filter *f)
int groups = 0;
struct rtnl_handle rth;
- if (f->families & (1 << AF_INET) && f->dbs & (1 << TCP_DB))
+ if (f->families & FAMILY_MASK(AF_INET) && f->dbs & (1 << TCP_DB))
groups |= 1 << (SKNLGRP_INET_TCP_DESTROY - 1);
- if (f->families & (1 << AF_INET) && f->dbs & (1 << UDP_DB))
+ if (f->families & FAMILY_MASK(AF_INET) && f->dbs & (1 << UDP_DB))
groups |= 1 << (SKNLGRP_INET_UDP_DESTROY - 1);
- if (f->families & (1 << AF_INET6) && f->dbs & (1 << TCP_DB))
+ if (f->families & FAMILY_MASK(AF_INET6) && f->dbs & (1 << TCP_DB))
groups |= 1 << (SKNLGRP_INET6_TCP_DESTROY - 1);
- if (f->families & (1 << AF_INET6) && f->dbs & (1 << UDP_DB))
+ if (f->families & FAMILY_MASK(AF_INET6) && f->dbs & (1 << UDP_DB))
groups |= 1 << (SKNLGRP_INET6_UDP_DESTROY - 1);
if (groups == 0)
--
2.13.6
^ permalink raw reply related
* [PATCH iproute2 v2 0/3] ss: add AF_VSOCK support
From: Stefan Hajnoczi @ 2017-10-06 15:48 UTC (permalink / raw)
To: netdev; +Cc: Stephen Hemminger, Jorgen Hansen, Dexuan Cui, Stefan Hajnoczi
v2:
* Use uint64_t instead of __u64 for filter->families
* Added reference to net-next commit that merged vsock_diag.ko
This patch series adds AF_VSOCK support to ss(8). AF_VSOCK is a host<->guest
communications channel supported by VMware, KVM (virtio-vsock), and Hyper-V.
To dump AF_VSOCK sockets:
$ ss --vsock
The vsock_diag.ko module has now been merged in the Linux net-next tree. I
have verified that the <linux/vm_sockets_diag.h> header copy in this patch
series is in sync with Linux net-next. See commit
5820299a271fd3dc9b1733e1e10cd7b983edd028 ("Merge branch 'VSOCK-sock_diag'").
Stefan Hajnoczi (3):
ss: allow AF_FAMILY constants >32
include: add <linux/vm_sockets_diag.h>
ss: add AF_VSOCK support
include/linux/vm_sockets_diag.h | 33 ++++++
misc/ss.c | 238 +++++++++++++++++++++++++++++++++++-----
man/man8/ss.8 | 8 +-
3 files changed, 249 insertions(+), 30 deletions(-)
create mode 100644 include/linux/vm_sockets_diag.h
--
2.13.6
^ permalink raw reply
* Re: [net-next V4 PATCH 2/5] bpf: XDP_REDIRECT enable use of cpumap
From: Jesper Dangaard Brouer @ 2017-10-06 15:45 UTC (permalink / raw)
To: Daniel Borkmann
Cc: netdev, jakub.kicinski, Michael S. Tsirkin, pavel.odintsov,
Jason Wang, mchan, John Fastabend, peter.waskiewicz.jr,
Daniel Borkmann, Alexei Starovoitov, Andy Gospodarek, brouer
In-Reply-To: <20171006131748.75185f65@redhat.com>
On Fri, 6 Oct 2017 13:17:48 +0200
Jesper Dangaard Brouer <brouer@redhat.com> wrote:
> > > +static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index)
> > > +{
> > > + switch (map->map_type) {
> > > + case BPF_MAP_TYPE_DEVMAP:
> > > + return __dev_map_lookup_elem(map, index);
> > > + case BPF_MAP_TYPE_CPUMAP:
> > > + return __cpu_map_lookup_elem(map, index);
> > > + default:
> > > + return NULL;
> > > + }
> >
> > Should we just have a callback and instead of the above use
> > map->ptr_lookup_elem() (or however we name it) ... lot of it
> > is pretty much the same logic as with devmap.
>
> We could extend struct bpf_map *map with such a callback, I was just
> afraid that this would be too invasive.
>
> Performance wise, I don't thinks will hurt too much.
> http://www.cipht.net/2017/10/03/are-jump-tables-always-fastest.html
Looking at the code, I would like to postpone this callback work until
after this patchset is merged. As this work will also touch devmap +
sockmap.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: [PATCH net-next 0/7] nfp: extend match and action for flower offload
From: Tom Herbert @ 2017-10-06 15:34 UTC (permalink / raw)
To: Simon Horman
Cc: David Miller, Jakub Kicinski, Linux Kernel Network Developers,
oss-drivers
In-Reply-To: <1507278086-3102-1-git-send-email-simon.horman@netronome.com>
Simon,
Maybe a bit off topic, but I had the impression netronome would
support BPF so that filters could be programmed for arbitrary
protocols and fields. Is that true? If so, what is the relationship
between that functionality and these patches?
Thanks,
Tom
On Fri, Oct 6, 2017 at 1:21 AM, Simon Horman <simon.horman@netronome.com> wrote:
> Pieter says:
>
> This series extends flower offload match and action capabilities. It
> specifically adds offload capabilities for matching on MPLS, TTL, TOS
> and flow label. Furthermore offload capabilities for action have been
> expanded to include set ethernet, ipv4, ipv6, tcp and udp headers.
>
> Pieter Jansen van Vuuren (7):
> nfp: add mpls match offloading support
> nfp: add IPv4 ttl and tos match offloading support
> nfp: add IPv6 ttl and tos match offloading support
> nfp: add set ethernet header action flower offload
> nfp: add set ipv4 header action flower offload
> nfp: add set ipv6 source and destination address
> nfp: add set tcp and udp header action flower offload
>
> drivers/net/ethernet/netronome/nfp/flower/action.c | 245 +++++++++++++++++++++
> drivers/net/ethernet/netronome/nfp/flower/cmsg.h | 43 ++++
> drivers/net/ethernet/netronome/nfp/flower/match.c | 39 +++-
> .../net/ethernet/netronome/nfp/flower/offload.c | 20 +-
> 4 files changed, 324 insertions(+), 23 deletions(-)
>
> --
> 2.1.4
>
^ permalink raw reply
* [PATCH net-next,3/3] hv_netvsc: Update netvsc Document for TCP hash level setting
From: Haiyang Zhang @ 2017-10-06 15:33 UTC (permalink / raw)
To: davem, netdev; +Cc: haiyangz, kys, sthemmin, olaf, vkuznets, linux-kernel
In-Reply-To: <20171006153359.8400-1-haiyangz@exchange.microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
Update Documentation/networking/netvsc.txt for TCP hash level setting
and related info.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
Documentation/networking/netvsc.txt | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/Documentation/networking/netvsc.txt b/Documentation/networking/netvsc.txt
index 93560fb1170a..92f5b31392fa 100644
--- a/Documentation/networking/netvsc.txt
+++ b/Documentation/networking/netvsc.txt
@@ -19,12 +19,12 @@ Features
Receive Side Scaling
--------------------
- Hyper-V supports receive side scaling. For TCP, packets are
- distributed among available queues based on IP address and port
+ Hyper-V supports receive side scaling. For TCP & UDP, packets can
+ be distributed among available queues based on IP address and port
number.
- For UDP, we can switch UDP hash level between L3 and L4 by ethtool
- command. UDP over IPv4 and v6 can be set differently. The default
+ For TCP & UDP, we can switch hash level between L3 and L4 by ethtool
+ command. TCP/UDP over IPv4 and v6 can be set differently. The default
hash level is L4. We currently only allow switching TX hash level
from within the guests.
--
2.14.1
^ permalink raw reply related
* [PATCH net-next,2/3] hv_netvsc: Add ethtool handler to set and get TCP hash levels
From: Haiyang Zhang @ 2017-10-06 15:33 UTC (permalink / raw)
To: davem, netdev; +Cc: haiyangz, kys, sthemmin, olaf, vkuznets, linux-kernel
In-Reply-To: <20171006153359.8400-1-haiyangz@exchange.microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
The patch supports the options to switch TCP hash level between
L3 and L4 by ethtool command. TCP over IPv4 and v6 can be set
differently. The default hash level is L4. We currently only
allow switching TX hash level from within the guests.
For example, for TCP over IPv4 on eth0:
To include TCP port numbers in hashing:
ethtool -N eth0 rx-flow-hash tcp4 sdfn
To exclude TCP port numbers in hashing:
ethtool -N eth0 rx-flow-hash tcp4 sd
To show TCP hash level:
ethtool -n eth0 rx-flow-hash tcp4
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
drivers/net/hyperv/netvsc_drv.c | 25 ++++++++++++++++++++++++-
1 file changed, 24 insertions(+), 1 deletion(-)
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 9bc7dbab9506..44746de3dd4c 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1264,8 +1264,15 @@ netvsc_get_rss_hash_opts(struct net_device_context *ndc,
switch (info->flow_type) {
case TCP_V4_FLOW:
+ if (ndc->l4_hash & HV_TCP4_L4HASH)
+ info->data |= l4_flag;
+
+ break;
+
case TCP_V6_FLOW:
- info->data |= l4_flag;
+ if (ndc->l4_hash & HV_TCP6_L4HASH)
+ info->data |= l4_flag;
+
break;
case UDP_V4_FLOW:
@@ -1318,6 +1325,14 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
if (info->data == (RXH_IP_SRC | RXH_IP_DST |
RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
switch (info->flow_type) {
+ case TCP_V4_FLOW:
+ ndc->l4_hash |= HV_TCP4_L4HASH;
+ break;
+
+ case TCP_V6_FLOW:
+ ndc->l4_hash |= HV_TCP6_L4HASH;
+ break;
+
case UDP_V4_FLOW:
ndc->l4_hash |= HV_UDP4_L4HASH;
break;
@@ -1335,6 +1350,14 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
if (info->data == (RXH_IP_SRC | RXH_IP_DST)) {
switch (info->flow_type) {
+ case TCP_V4_FLOW:
+ ndc->l4_hash &= ~HV_TCP4_L4HASH;
+ break;
+
+ case TCP_V6_FLOW:
+ ndc->l4_hash &= ~HV_TCP6_L4HASH;
+ break;
+
case UDP_V4_FLOW:
ndc->l4_hash &= ~HV_UDP4_L4HASH;
break;
--
2.14.1
^ permalink raw reply related
* [PATCH net-next,1/3] hv_netvsc: Change the hash level variable to bit flags
From: Haiyang Zhang @ 2017-10-06 15:33 UTC (permalink / raw)
To: davem, netdev; +Cc: haiyangz, kys, sthemmin, olaf, vkuznets, linux-kernel
In-Reply-To: <20171006153359.8400-1-haiyangz@exchange.microsoft.com>
From: Haiyang Zhang <haiyangz@microsoft.com>
This simplifies the logic and make it easier to add more
options.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
drivers/net/hyperv/hyperv_net.h | 11 +++++--
drivers/net/hyperv/netvsc_drv.c | 73 ++++++++++++++++++++++++++++-------------
2 files changed, 59 insertions(+), 25 deletions(-)
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 6f550e15a41c..a81335e8ebe8 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -704,6 +704,14 @@ struct netvsc_reconfig {
u32 event;
};
+/* L4 hash bits for different protocols */
+#define HV_TCP4_L4HASH 1
+#define HV_TCP6_L4HASH 2
+#define HV_UDP4_L4HASH 4
+#define HV_UDP6_L4HASH 8
+#define HV_DEFAULT_L4HASH (HV_TCP4_L4HASH | HV_TCP6_L4HASH | HV_UDP4_L4HASH | \
+ HV_UDP6_L4HASH)
+
/* The context of the netvsc device */
struct net_device_context {
/* point back to our device context */
@@ -726,10 +734,9 @@ struct net_device_context {
u32 tx_send_table[VRSS_SEND_TAB_SIZE];
/* Ethtool settings */
- bool udp4_l4_hash;
- bool udp6_l4_hash;
u8 duplex;
u32 speed;
+ u32 l4_hash; /* L4 hash settings */
struct netvsc_ethtool_stats eth_stats;
/* State to manage the associated VF interface. */
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index dfb986421ec6..9bc7dbab9506 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -203,7 +203,7 @@ static inline u32 netvsc_get_hash(
const struct net_device_context *ndc)
{
struct flow_keys flow;
- u32 hash;
+ u32 hash, pkt_proto = 0;
static u32 hashrnd __read_mostly;
net_get_random_once(&hashrnd, sizeof(hashrnd));
@@ -211,11 +211,25 @@ static inline u32 netvsc_get_hash(
if (!skb_flow_dissect_flow_keys(skb, &flow, 0))
return 0;
- if (flow.basic.ip_proto == IPPROTO_TCP ||
- (flow.basic.ip_proto == IPPROTO_UDP &&
- ((flow.basic.n_proto == htons(ETH_P_IP) && ndc->udp4_l4_hash) ||
- (flow.basic.n_proto == htons(ETH_P_IPV6) &&
- ndc->udp6_l4_hash)))) {
+ switch (flow.basic.ip_proto) {
+ case IPPROTO_TCP:
+ if (flow.basic.n_proto == htons(ETH_P_IP))
+ pkt_proto = HV_TCP4_L4HASH;
+ else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+ pkt_proto = HV_TCP6_L4HASH;
+
+ break;
+
+ case IPPROTO_UDP:
+ if (flow.basic.n_proto == htons(ETH_P_IP))
+ pkt_proto = HV_UDP4_L4HASH;
+ else if (flow.basic.n_proto == htons(ETH_P_IPV6))
+ pkt_proto = HV_UDP6_L4HASH;
+
+ break;
+ }
+
+ if (pkt_proto & ndc->l4_hash) {
return skb_get_hash(skb);
} else {
if (flow.basic.n_proto == htons(ETH_P_IP))
@@ -898,8 +912,7 @@ static void netvsc_init_settings(struct net_device *dev)
{
struct net_device_context *ndc = netdev_priv(dev);
- ndc->udp4_l4_hash = true;
- ndc->udp6_l4_hash = true;
+ ndc->l4_hash = HV_DEFAULT_L4HASH;
ndc->speed = SPEED_UNKNOWN;
ndc->duplex = DUPLEX_FULL;
@@ -1245,23 +1258,25 @@ static int
netvsc_get_rss_hash_opts(struct net_device_context *ndc,
struct ethtool_rxnfc *info)
{
+ const u32 l4_flag = RXH_L4_B_0_1 | RXH_L4_B_2_3;
+
info->data = RXH_IP_SRC | RXH_IP_DST;
switch (info->flow_type) {
case TCP_V4_FLOW:
case TCP_V6_FLOW:
- info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ info->data |= l4_flag;
break;
case UDP_V4_FLOW:
- if (ndc->udp4_l4_hash)
- info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ if (ndc->l4_hash & HV_UDP4_L4HASH)
+ info->data |= l4_flag;
break;
case UDP_V6_FLOW:
- if (ndc->udp6_l4_hash)
- info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+ if (ndc->l4_hash & HV_UDP6_L4HASH)
+ info->data |= l4_flag;
break;
@@ -1302,23 +1317,35 @@ static int netvsc_set_rss_hash_opts(struct net_device_context *ndc,
{
if (info->data == (RXH_IP_SRC | RXH_IP_DST |
RXH_L4_B_0_1 | RXH_L4_B_2_3)) {
- if (info->flow_type == UDP_V4_FLOW)
- ndc->udp4_l4_hash = true;
- else if (info->flow_type == UDP_V6_FLOW)
- ndc->udp6_l4_hash = true;
- else
+ switch (info->flow_type) {
+ case UDP_V4_FLOW:
+ ndc->l4_hash |= HV_UDP4_L4HASH;
+ break;
+
+ case UDP_V6_FLOW:
+ ndc->l4_hash |= HV_UDP6_L4HASH;
+ break;
+
+ default:
return -EOPNOTSUPP;
+ }
return 0;
}
if (info->data == (RXH_IP_SRC | RXH_IP_DST)) {
- if (info->flow_type == UDP_V4_FLOW)
- ndc->udp4_l4_hash = false;
- else if (info->flow_type == UDP_V6_FLOW)
- ndc->udp6_l4_hash = false;
- else
+ switch (info->flow_type) {
+ case UDP_V4_FLOW:
+ ndc->l4_hash &= ~HV_UDP4_L4HASH;
+ break;
+
+ case UDP_V6_FLOW:
+ ndc->l4_hash &= ~HV_UDP6_L4HASH;
+ break;
+
+ default:
return -EOPNOTSUPP;
+ }
return 0;
}
--
2.14.1
^ permalink raw reply related
* [PATCH net-next,0/3] hv_netvsc: support changing TCP hash level
From: Haiyang Zhang @ 2017-10-06 15:33 UTC (permalink / raw)
To: davem, netdev; +Cc: haiyangz, kys, sthemmin, olaf, vkuznets, linux-kernel
From: Haiyang Zhang <haiyangz@microsoft.com>
The patch set simplifies the existing hash level switching code for
UDP. It also adds the support for changing TCP hash level. So users
can switch between L3 an L4 hash levels for TCP and UDP.
Haiyang Zhang (3):
hv_netvsc: Change the hash level variable to bit flags
hv_netvsc: Add ethtool handler to set and get TCP hash levels
hv_netvsc: Update netvsc Document for TCP hash level setting
Documentation/networking/netvsc.txt | 8 ++--
drivers/net/hyperv/hyperv_net.h | 11 ++++-
drivers/net/hyperv/netvsc_drv.c | 96 ++++++++++++++++++++++++++++---------
3 files changed, 86 insertions(+), 29 deletions(-)
--
2.14.1
^ permalink raw reply
* Re: [PATCH 4/4] tcp: avoid noref dst leak on input path
From: Eric Dumazet @ 2017-10-06 15:32 UTC (permalink / raw)
To: Paolo Abeni
Cc: Eric Dumazet, LKML, Paul E. McKenney, Josh Triplett,
Steven Rostedt, David S. Miller, Hannes Frederic Sowa, netdev
In-Reply-To: <1507303300.2793.25.camel@redhat.com>
On Fri, Oct 6, 2017 at 8:21 AM, Paolo Abeni <pabeni@redhat.com> wrote:
> Hi,
>
> On Fri, 2017-10-06 at 07:37 -0700, Eric Dumazet wrote:
>> On Fri, 2017-10-06 at 14:57 +0200, Paolo Abeni wrote:
>> > Enabling CONFIG_RCU_NOREF_DEBUG gives the following splat when
>> > processing tcp packets:
>> >
>> > to-be-untracked noref entity ffff942cb71ea300 not found in cache
>> > ------------[ cut here ]------------
>> > WARNING: CPU: 24 PID: 178 at kernel/rcu/noref_debug.c:54 rcu_track_noref+0xa4/0xf0
>> > Modules linked in: intel_rapl sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc aesni_intel crypto_simd glue_helper cryptd iTCO_wdt ipmi_ssif mei_me iTCO_vendor_support mei dcdbas lpc_ich ipmi_si mxm_wmi sg pcspkr ipmi_devintf ipmi_msghandler acpi_power_meter shpchp wmi nfsd auth_rpcgss nfs_acl lockd grace sunrpc ip_tables xfs libcrc32c sd_mod mgag200 drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm igb drm ixgbe mdio crc32c_intel ahci ptp i2c_algo_bit libahci pps_core i2c_core libata dca dm_mirror dm_region_hash dm_log dm_mod
>> > CPU: 24 PID: 178 Comm: ksoftirqd/24 Not tainted 4.14.0-rc1.noref_route+ #1610
>> > Hardware name: Dell Inc. PowerEdge R730/072T6D, BIOS 2.4.3 01/17/2017
>> > task: ffff940e48300000 task.stack: ffffaec406a20000
>> > RIP: 0010:rcu_track_noref+0xa4/0xf0
>> > RSP: 0018:ffffaec406a238e0 EFLAGS: 00010246
>> > RAX: 0000000000000040 RBX: 0000000000000000 RCX: 0000000000000002
>> > RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000292
>> > RBP: ffffaec406a238e0 R08: 0000000000000000 R09: 0000000000000000
> Thank you for the feedback.
>
> I most probably messed-up while extracting the info from dmsg, as this
> issue gives a couple of splats almost concurrently. Please let me re-do
> the test and post a more resonable dmsg.
>
> The problem with the current code is that in the tcp_rcv_established()
> -> tcp_queue_rcv() path, the skb_dst() is not cleared.
>
In any case, I would rather put one skb_dst_drop() right after the
last possible use of skb dst in TCP stack,
probably after sk_rx_dst_set() call.
Trying to move it in multiple places has been error prone, even if
current code is not buggy.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox