When building the erspan header for either v1 or v2, the eth_hdr()
does not point to the right inner packet's eth_hdr,
causing kasan report use-after-free and slab-out-of-bouds read.

The patch fixes the following syzkaller issues:
[1] BUG: KASAN: slab-out-of-bounds in erspan_xmit+0x22d4/0x2430 net/ipv4/ip_gre.c:735
[2] BUG: KASAN: slab-out-of-bounds in erspan_build_header+0x3bf/0x3d0 net/ipv4/ip_gre.c:698
[3] BUG: KASAN: use-after-free in erspan_xmit+0x22d4/0x2430 net/ipv4/ip_gre.c:735
[4] BUG: KASAN: use-after-free in erspan_build_header+0x3bf/0x3d0 net/ipv4/ip_gre.c:698

[2] CPU: 0 PID: 3654 Comm: syzkaller377964 Not tainted 4.15.0-rc9+ #185
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:17 [inline]
 dump_stack+0x194/0x257 lib/dump_stack.c:53
 print_address_description+0x73/0x250 mm/kasan/report.c:252
 kasan_report_error mm/kasan/report.c:351 [inline]
 kasan_report+0x25b/0x340 mm/kasan/report.c:409
 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/report.c:440
 erspan_build_header+0x3bf/0x3d0 net/ipv4/ip_gre.c:698
 erspan_xmit+0x3b8/0x13b0 net/ipv4/ip_gre.c:740
 __netdev_start_xmit include/linux/netdevice.h:4042 [inline]
 netdev_start_xmit include/linux/netdevice.h:4051 [inline]
 packet_direct_xmit+0x315/0x6b0 net/packet/af_packet.c:266
 packet_snd net/packet/af_packet.c:2943 [inline]
 packet_sendmsg+0x3aed/0x60b0 net/packet/af_packet.c:2968
 sock_sendmsg_nosec net/socket.c:638 [inline]
 sock_sendmsg+0xca/0x110 net/socket.c:648
 SYSC_sendto+0x361/0x5c0 net/socket.c:1729
 SyS_sendto+0x40/0x50 net/socket.c:1697
 do_syscall_32_irqs_on arch/x86/entry/common.c:327 [inline]
 do_fast_syscall_32+0x3ee/0xf9d arch/x86/entry/common.c:389
 entry_SYSENTER_compat+0x54/0x63 arch/x86/entry/entry_64_compat.S:129
RIP: 0023:0xf7fcfc79
RSP: 002b:00000000ffc6976c EFLAGS: 00000286 ORIG_RAX: 0000000000000171
RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 0000000020011000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000020008000
RBP: 000000000000001c R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

Fixes: f551c91d ("net: erspan: introduce erspan v2 for ip_gre")
Fixes: 84e54fe0 ("gre: introduce native tunnel support for ERSPAN")
Reported-by: syzbot+9723f2d288e49b492cf0@syzkaller.appspotmail.com
Reported-by: syzbot+f0ddeb2b032a8e1d9098@syzkaller.appspotmail.com
Reported-by: syzbot+f14b3703cd8d7670203f@syzkaller.appspotmail.com
Reported-by: syzbot+eefa384efad8d7997f20@syzkaller.appspotmail.com
Signed-off-by: NWilliam Tu <u9012063@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

All users are now converted to tc_cls_common_offload_init().
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: NSimon Horman <simon.horman@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

cls_bpf now guarantees that only device-bound programs are
allowed with skip_sw.  The drivers no longer pay attention to
flags on filter load, therefore the bpf_offload member can be
removed.  If flags are needed again they should probably be
added to struct tc_cls_common_offload instead.
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: NSimon Horman <simon.horman@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Rename the tc_cls_common_offload_init() helper function to
tc_cls_common_offload_init_deprecated() and add a new implementation
which also takes flags argument.  We will only set extack if flags
indicate that offload is forced (skip_sw) otherwise driver errors
should be ignored, as they don't influence the overall filter
installation.

Note that we need the tc_skip_hw() helper for new version, therefore
it is added later in the file.
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: NSimon Horman <simon.horman@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Propagate extack to cls->destroy callbacks when called from
non-error paths.  On error paths pass NULL to avoid overwriting
the failure message.
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: NSimon Horman <simon.horman@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

TCF_LAYER_LINK and TCF_LAYER_NETWORK returned the same pointer as
skb->data points to the network header.
Use skb_mac_header instead.
Signed-off-by: NWolfgang Bumiller <w.bumiller@proxmox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 513674b5 ("net: reevalulate autoflowlabel setting after
sysctl setting") removed the initialisation of
ipv6_pinfo::autoflowlabel and added a second flag to indicate
whether this field or the net namespace default should be used.

The getsockopt() handling for this case was not updated, so it
currently returns 0 for all sockets for which IPV6_AUTOFLOWLABEL is
not explicitly enabled.  Fix it to return the effective value, whether
that has been set at the socket or net namespace level.

Fixes: 513674b5 ("net: reevalulate autoflowlabel setting after sysctl ...")
Signed-off-by: NBen Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

use RCU instead of spin_{,unlock}_bh() to protect concurrent read/write on
act_csum configuration, to reduce the effects of contention in the data
path when multiple readers are present.
Signed-off-by: NDavide Caratti <dcaratti@redhat.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Create a wrapper around tc_can_offload() that takes an additional
extack pointer argument in order to output an error message if TC
offload is disabled on the device.

In this way, the error message is handled by the core and can be the
same for all drivers.
Signed-off-by: NQuentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add extack support for hardware offload of classifiers. In order
to achieve this, a pointer to a struct netlink_ext_ack is added to the
struct tc_cls_common_offload that is passed to the callback for setting
up the classifier. Function tc_cls_common_offload_init() is updated to
support initialization of this new attribute.
Signed-off-by: NQuentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds extack handling for the tcf_change_indev function which
is common used by TC classifier implementations.

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: NAlexander Aring <aring@mojatatu.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds extack support for classifier delete callback api. This
prepares to handle extack support inside each specific classifier
implementation.

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: NAlexander Aring <aring@mojatatu.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The tcf_exts_validate function calls the act api change callback. For
preparing extack support for act api, this patch adds the extack as
parameter for this function which is common used in cls implementations.

Furthermore the tcf_exts_validate will call action init callback which
prepares the TC action subsystem for extack support.

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: NAlexander Aring <aring@mojatatu.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds extack support for classifier change callback api. This
prepares to handle extack support inside each specific classifier
implementation.

Cc: David Ahern <dsahern@gmail.com>
Signed-off-by: NAlexander Aring <aring@mojatatu.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch changes some code style issues pointed out by checkpatch
inside the TC cls subsystem.
Signed-off-by: NAlexander Aring <aring@mojatatu.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

A persistent connection may send tiny amount of data (e.g. health-check)
for a long period of time. BBR's windowed min RTT filter may only see
RTT samples from delayed ACKs causing BBR to grossly over-estimate
the path delay depending how much the ACK was delayed at the receiver.

This patch skips RTT samples that are likely coming from delayed ACKs. Note
that it is possible the sender never obtains a valid measure to set the
min RTT. In this case BBR will continue to set cwnd to initial window
which seems fine because the connection is thin stream.
Signed-off-by: NYuchung Cheng <ycheng@google.com>
Acked-by: NNeal Cardwell <ncardwell@google.com>
Acked-by: NSoheil Hassas Yeganeh <soheil@google.com>
Acked-by: NPriyaranjan Jha <priyarjha@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When CONFIG_KASAN is set, we can use relatively large amounts of kernel
stack space:

net/caif/cfctrl.c:555:1: warning: the frame size of 1600 bytes is larger than 1280 bytes [-Wframe-larger-than=]

This adds convenience wrappers around cfpkt_extr_head(), which is responsible
for most of the stack growth. With those wrapper functions, gcc apparently
starts reusing the stack slots for each instance, thus avoiding the
problem.
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch allows deletion of objects via unique handle which can be
listed via '-a' option.
Signed-off-by: NHarsha Sharma <harshasharmaiitr@gmail.com>
Signed-off-by: NPablo Neira Ayuso <pablo@netfilter.org>

The trailing semicolon is an empty statement that does no operation.
It is completely stripped out by the compiler. Removing it since it doesn't do
anything.

Fixes: 5f35227e ("net: Generalize ndo_gso_check to ndo_features_check")
Signed-off-by: NLuis de Bethencourt <luisbg@kernel.org>
Acked-by: NStephen Hemminger <stephen@networkplumber.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce two new attributes to be used for qdisc creation and dumping.
One for ingress block, one for egress block. Introduce a set of ops that
qdisc which supports block sharing would implement.

Passing block indexes in qdisc change is not supported yet and it is
checked and forbidded.

In future, these attributes are to be reused for specifying block
indexes for classes as well. As of this moment however, it is not
supported so a check is in place to forbid it.
Suggested-by: NRoopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

During block bind, we need to check tc offload feature. If it is
disabled yet still the block contains offloaded filters, forbid the
bind. Also forbid to register callback for a block that already
contains offloaded filters, as the play back is not supported now.
For keeping track of offloaded filters there is a new counter
introduced, alongside with couple of helpers called from cls_* code.
These helpers set and clear TCA_CLS_FLAGS_IN_HW flag.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Both are no longer used, so remove them.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Couple of classifiers call netif_keep_dst directly on q->dev. That is
not possible to do directly for shared blocke where multiple qdiscs are
owning the block. So introduce a infrastructure to keep track of the
block owners in list and use this list to implement block variant of
netif_keep_dst.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Allow qdiscs to share filter blocks among them. Each qdisc type has to
use block get/put extended modifications that enable sharing.
Shared blocks are tracked within each net namespace and identified
by u32 index. This index is passed from user during the qdisc creation.
If user passes index that is not used by any other qdisc, new block
is created. If user passes index that is already used, the existing
block will be re-used.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

So far, there was possible only to register a single filter chain
pointer to block->chain[0]. However, when the blocks will get shareable,
we need to allow multiple filter chain pointers registration.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Acked-by: NJamal Hadi Salim <jhs@mojatatu.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Commit 0dfb33a0 ("sch_red: report backlog information") copied
child's backlog into RED's backlog.  Back then RED did not maintain
its own backlog counts.  This has changed after commit 2ccccf5f
("net_sched: update hierarchical backlog too") and commit d7f4f332
("sch_red: update backlog as well").  Copying is no longer necessary.

Tested:

$ tc -s qdisc show dev veth0
qdisc red 1: root refcnt 2 limit 400000b min 30000b max 30000b ecn
 Sent 20942 bytes 221 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 1260b 14p requeues 14
  marked 0 early 0 pdrop 0 other 0
qdisc tbf 2: parent 1: rate 1Kbit burst 15000b lat 3585.0s
 Sent 20942 bytes 221 pkt (dropped 0, overlimits 138 requeues 0)
 backlog 1260b 14p requeues 14

Recently RED offload was added.  We need to make sure drivers don't
depend on resetting the stats.  This means backlog should be treated
like any other statistic:

  total_stat = new_hw_stat - prev_hw_stat;

Adjust mlxsw.
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: NNogah Frankel <nogahf@mellanox.com>
Acked-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

While working on fixing another bug, I ran into the following panic
on arm64 by simply attaching clsact qdisc, adding a filter and running
traffic on ingress to it:

  [...]
  [  178.188591] Unable to handle kernel read from unreadable memory at virtual address 810fb501f000
  [  178.197314] Mem abort info:
  [  178.200121]   ESR = 0x96000004
  [  178.203168]   Exception class = DABT (current EL), IL = 32 bits
  [  178.209095]   SET = 0, FnV = 0
  [  178.212157]   EA = 0, S1PTW = 0
  [  178.215288] Data abort info:
  [  178.218175]   ISV = 0, ISS = 0x00000004
  [  178.222019]   CM = 0, WnR = 0
  [  178.224997] user pgtable: 4k pages, 48-bit VAs, pgd = 0000000023cb3f33
  [  178.231531] [0000810fb501f000] *pgd=0000000000000000
  [  178.236508] Internal error: Oops: 96000004 [#1] SMP
  [...]
  [  178.311855] CPU: 73 PID: 2497 Comm: ping Tainted: G        W        4.15.0-rc7+ #5
  [  178.319413] Hardware name: FOXCONN R2-1221R-A4/C2U4N_MB, BIOS G31FB18A 03/31/2017
  [  178.326887] pstate: 60400005 (nZCv daif +PAN -UAO)
  [  178.331685] pc : __netif_receive_skb_core+0x49c/0xac8
  [  178.336728] lr : __netif_receive_skb+0x28/0x78
  [  178.341161] sp : ffff00002344b750
  [  178.344465] x29: ffff00002344b750 x28: ffff810fbdfd0580
  [  178.349769] x27: 0000000000000000 x26: ffff000009378000
  [...]
  [  178.418715] x1 : 0000000000000054 x0 : 0000000000000000
  [  178.424020] Process ping (pid: 2497, stack limit = 0x000000009f0a3ff4)
  [  178.430537] Call trace:
  [  178.432976]  __netif_receive_skb_core+0x49c/0xac8
  [  178.437670]  __netif_receive_skb+0x28/0x78
  [  178.441757]  process_backlog+0x9c/0x160
  [  178.445584]  net_rx_action+0x2f8/0x3f0
  [...]

Reason is that sch_ingress and sch_clsact are doing mini_qdisc_pair_init()
which sets up miniq pointers to cpu_{b,q}stats from the underlying qdisc.
Problem is that this cannot work since they are actually set up right after
the qdisc ->init() callback in qdisc_create(), so first packet going into
sch_handle_ingress() tries to call mini_qdisc_bstats_cpu_update() and we
therefore panic.

In order to fix this, allocation of {b,q}stats needs to happen before we
call into ->init(). In net-next, there's already such option through commit
d59f5ffa ("net: sched: a dflt qdisc may be used with per cpu stats").
However, the bug needs to be fixed in net still for 4.15. Thus, include
these bits to reduce any merge churn and reuse the static_flags field to
set TCQ_F_CPUSTATS, and remove the allocation from qdisc_create() since
there is no other user left. Prashant Bhole ran into the same issue but
for net-next, thus adding him below as well as co-author. Same issue was
also reported by Sandipan Das when using bcc.

Fixes: 46209401 ("net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath")
Reference: https://lists.iovisor.org/pipermail/iovisor-dev/2018-January/001190.htmlReported-by: NSandipan Das <sandipan@linux.vnet.ibm.com>
Co-authored-by: NPrashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Co-authored-by: NJohn Fastabend <john.fastabend@gmail.com>
Signed-off-by: NDaniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Looks like qdisc_lookup_class() never existed in the tree
in the git era.  Remove the prototype from the header.
Signed-off-by: NJakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The hardware processes which are modeled via dpipe commonly use some
internal hardware resources. Such relation can improve the understanding
of hardware limitations. The number of resource's unit consumed per
table's entry are also provided for each table.
Signed-off-by: NArkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for performing driver hot reload.
Signed-off-by: NArkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Add support for hardware resource abstraction over devlink. Each resource
is identified via id, furthermore it contains information regarding its
size and its related sub resources. Each resource can also provide its
current occupancy.

In some cases the sizes of some resources can be changed, yet for those
changes to take place a hot driver reload may be needed. The reload
capability will be introduced in the next patch.
Signed-off-by: NArkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This is a preparation before introducing resources and hot reload support.
Currently there are two global lock where one protects all devlink access,
and the second one protects devlink port access. This patch adds per devlink
instance lock which protects the internal members which are the sb/dpipe/
resource/ports. By introducing this lock the global devlink port lock can
be discarded.
Signed-off-by: NArkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Map all lookup neigh keys to INADDR_ANY for loopback/point-to-point devices
to avoid making an entry for every remote ip the device needs to talk to.

This used the be the old behavior but became broken in a263b309
(ipv4: Make neigh lookups directly in output packet path) and later removed
in 0bb4087c (ipv4: Fix neigh lookup keying over loopback/point-to-point
devices) because it was broken.
Signed-off-by: NJim Westfall <jwestfall@surrealistic.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Since net could be obtained from RCU lists,
and there is a race with net destruction,
the patch converts net::count to refcount_t.

This provides sanity checks for the cases of
incrementing counter of already dead net,
when maybe_get_net() has to used instead
of get_net().

Drivers: allyesconfig and allmodconfig are OK.
Suggested-by: NEric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: NKirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

sendfile() calls can hang endless with using Kernel TLS if a socket error occurs.
Socket error codes must be inverted by Kernel TLS before returning because
they are stored with positive sign. If returned non-inverted they are
interpreted as number of bytes sent, causing endless looping of the
splice mechanic behind sendfile().
Signed-off-by: NRobert Hering <r.hering@avm.de>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

When creating a new radio on the fly, hwsim allows this
to be done with an arbitrary number of channels, but
cfg80211 only supports a limited number of simultaneous
channels, leading to a warning.

Fix this by validating the number - this requires moving
the define for the maximum out to a visible header file.

Reported-by: syzbot+8dd9051ff19940290931@syzkaller.appspotmail.com
Fixes: b59ec8dd ("mac80211_hwsim: fix number of channels in interface combinations")
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>

Add the ability to offload PRIO qdisc by using ndo_setup_tc.
There are three commands for PRIO offloading:
* TC_PRIO_REPLACE: handles set and tune
* TC_PRIO_DESTROY: handles qdisc destroy
* TC_PRIO_STATS: updates the qdiscs counters (given as reference)

Like RED qdisc, the indication of whether PRIO is being offloaded is being
set and updated as part of the dump function. It is so because the driver
could decide to offload or not based on the qdisc parent, which could
change without notifying the qdisc.
Signed-off-by: NNogah Frankel <nogahf@mellanox.com>
Reviewed-by: NYuval Mintz <yuvalm@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Change the name of the stats struct to be generic, so it could be used for
other qdisc offload, that will be added in the next patches.
Signed-off-by: NNogah Frankel <nogahf@mellanox.com>
Reviewed-by: NYuval Mintz <yuvalm@mellanox.com>
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The use of hash-threshold instead of modulo-N makes it trivial to add
support for non-equal-cost multipath.

Instead of dividing the multipath hash function's output space equally
between the nexthops, each nexthop is assigned a region size which is
proportional to its weight.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Before we convert IPv6 to use hash-threshold instead of modulo-N, we
first need each nexthop to store its region boundary in the hash
function's output space.

The boundary is calculated by dividing the output space equally between
the different active nexthops. That is, nexthops that are not dead or
linkdown.

The boundaries are rebalanced whenever a nexthop is added or removed to
a multipath route and whenever a nexthop becomes active or inactive.
Signed-off-by: NIdo Schimmel <idosch@mellanox.com>
Acked-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>