Add BPF_PROG_GET_FD_BY_ID command to allow user to get a fd
from a bpf_prog's ID.

bpf_prog_inc_not_zero() is added and is called with prog_idr_lock
held.

__bpf_prog_put() is also added which has the 'bool do_idr_lock'
param to decide if the prog_idr_lock should be acquired when
freeing the prog->id.

In the error path of bpf_prog_inc_not_zero(), it may have to
call __bpf_prog_put(map, false) which does not need
to take the prog_idr_lock when freeing the prog->id.

It is currently limited to CAP_SYS_ADMIN which we can
consider to lift it in followup patches.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Acked-by: NAlexei Starovoitov <ast@fb.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch adds BPF_PROG_GET_NEXT_ID and BPF_MAP_GET_NEXT_ID
to allow userspace to iterate all bpf_prog IDs and bpf_map IDs.

The API is trying to be consistent with the existing
BPF_MAP_GET_NEXT_KEY.

It is currently limited to CAP_SYS_ADMIN which we can
consider to lift it in followup patches.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Acked-by: NAlexei Starovoitov <ast@fb.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch generates an unique ID for each created bpf_map.
The approach is similar to the earlier patch for bpf_prog ID.

It is worth to note that the bpf_map's ID and bpf_prog's ID
are in two independent ID spaces and both have the same valid range:
[1, INT_MAX).
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Acked-by: NAlexei Starovoitov <ast@fb.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This patch generates an unique ID for each BPF_PROG_LOAD-ed prog.
It is worth to note that each BPF_PROG_LOAD-ed prog will have
a different ID even they have the same bpf instructions.

The ID is generated by the existing idr_alloc_cyclic().
The ID is ranged from [1, INT_MAX).  It is allocated in cyclic manner,
so an ID will get reused every 2 billion BPF_PROG_LOAD.

The bpf_prog_alloc_id() is done after bpf_prog_select_runtime()
because the jit process may have allocated a new prog.  Hence,
we need to ensure the value of pointer 'prog' will not be changed
any more before storing the prog to the prog_idr.

After bpf_prog_select_runtime(), the prog is read-only.  Hence,
the id is stored in 'struct bpf_prog_aux'.
Signed-off-by: NMartin KaFai Lau <kafai@fb.com>
Acked-by: NAlexei Starovoitov <ast@fb.com>
Acked-by: NDaniel Borkmann <daniel@iogearbox.net>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Implement ndo_set_vf_rate() for mgmt interface to support rate-limiting
of VF traffic using 'ip' command.

Based on the original work of Kumar Sanghvi <kumaras@chelsio.com>
Signed-off-by: NGanesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Using this extension reduces the object size.

$ size drivers/net/ppp/ppp_mppe.o*
   text	   data	    bss	    dec	    hex	filename
   5683	    216	      8	   5907	   1713	drivers/net/ppp/ppp_mppe.o.new
   5808	    216	      8	   6032	   1790	drivers/net/ppp/ppp_mppe.o.old
Signed-off-by: NJoe Perches <joe@perches.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

It's unused, so remove it.
Signed-off-by: NYuval Shaia <yuval.shaia@oracle.com>
Reviewed-by: NFlorian Fainelli <f.fainelli@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Julian Wiedmann says:

====================
s390/net updates

please apply the following qeth updates for net-next.

Aside from some janitorial changes, this adds early setup for virtualized
HiperSockets devices - building upon the code that landed via -net earlier.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

qeth currently supports early setup for OSM and OSN devices.
This patch adds early setup support for z/VM HiperSockets,
since they can only be coupled to L3 networks.

Based on an initial version by Dmitriy Lakhvich.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Similar to how qeth currently does early L2 setup of OSM and OSN
devices, add support for early setup of L3-only devices.
This adds a qeth_l3_devtype that contains all core and l3-specific
sysfs attributes, so that they can be created in one go while probing.

This just adds the infrastructure, exploitation of the support happens
in a subsequent patch.
Signed-off-by: NUrsula Braun <ubraun@linux.vnet.ibm.com>
Reviewed-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Noting the lack of TSO support on every feature change is just silly,
in particular since the requested features might not even affect
NETIF_F_TSO.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

qeth_switch_to_nonpacking_if_needed() contains an open-coded version
of qeth_flush_buffers_on_no_pci(). Extract a single helper instead.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Acked-by: NUrsula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

commit 76b11f8e ("qeth: HiperSockets Network Traffic Analyzer")
missed adding the human-readable translations when adding new RCs.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Acked-by: NUrsula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Bridgeport is a l2-specific feature, and we should write its
capabilities to a debug entry.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

HiperSocket devices don't need the full IPv6 initialization, but we
should still query the supported assists for logging purposes.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Acked-by: NUrsula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

qeth doesn't advertise NETIF_F_SG for L3 IQDs. So trust the stack to
not hand us any nonlinear skbs, and remove an always-true condition.

With the fact that data_offset < 0 is no longer possible on IQDs,
apply a small cleanup to subsequent code.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Acked-by: NUrsula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

This Assist was never actually implemented in any hardware, so just
remove the leftovers.
Signed-off-by: NJulian Wiedmann <jwi@linux.vnet.ibm.com>
Reviewed-by: NHans Wippel <hwippel@linux.vnet.ibm.com>
Reviewed-by: NThomas Richter <tmricht@linux.vnet.ibm.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jiri Pirko says:

====================
net: introduce trap control action to tc and offload it

This patchset introduces a control action dedicated to indicate
to trap the matched packet to CPU. This is specific action for
HW offloads. Also, the patchset offloads the action to mlxsw driver.

Example usage:
$ tc filter add dev enp3s0np19 parent ffff: protocol ip prio 20 flower skip_sw dst_ip 192.168.10.1 action trap

v1->v2:
- patch 1
  - fix the comment according to Andrew's note
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Just use the previously prepared infrastructure and offload the gact
trap action to ACL.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Use trap/discard flex action to implement trap.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce an ACL trap and put it into ip2me trap group.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The "trap_id" is 9bits long. So far, this was not a problem since we
used only traps with ids that fit into 8bits. But the ACL traps that are
going to be introduced use the 9th bit.

Fixes: eda6500a ("mlxsw: Add PCI bus implementation")
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Introduce a helper called is_tcf_gact_trap which could be used to
tell if the action is gact trap or not.
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

There is need to instruct the HW offloaded path to push certain matched
packets to cpu/kernel for further analysis. So this patch introduces a
new TRAP control action to TC.

For kernel datapath, this action does not make much sense. So with the
same logic as in HW, new TRAP behaves similar to STOLEN. The skb is just
dropped in the datapath (and virtually ejected to an upper level, which
does not exist in case of kernel).
Signed-off-by: NJiri Pirko <jiri@mellanox.com>
Reviewed-by: NYotam Gigi <yotamg@mellanox.com>
Reviewed-by: NAndrew Lunn <andrew@lunn.ch>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The check to see of err is set and the subsequent goto is extraneous
as the next statement is where the goto is jumping to. Remove this
redundant check and goto.

Detected by CoverityScan, CID#1437734 ("Identical code for
different branches")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Acked-by: NYotam Gigi <yotamg@mellanox.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Merge tag 'rxrpc-rewrite-20170606' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs

David Howells says:

====================
rxrpc: Support service upgrade

Here's a set of patches that allow AF_RXRPC to support the AuriStor service
upgrade facility.  This allows the server to change the service ID
requested to an upgraded service if the client requests it upon the
initiation of a connection.

This is used by the AuriStor AFS-compatible servers to implement IPv6
handling and improved facilities by providing improved volume location,
volume, protection, file and cache management services.  Note that certain
parts of the AFS protocol carry hard-coded IPv4 addresses.

The reason AuriStor does it this way is that probing the improved service
ID first will not incur an ABORT or any other response on some servers if
the server is not listening on it - and so one have to employ a timeout.

This is implemented in the server by allowing an AF_RXRPC server to call
bind() twice on a socket to allow it to listen on two service IDs and then
call setsockopt() to instruct the server to upgrade one into the other if
the client requests it (by setting userStatus to 1 on the first DATA packet
on a connection).  If the upgrade occurs, all further operations on that
connection are done with the new service ID.  AF_RXRPC has to handle this
automatically as connections are not exposed to userspace.

Clients can request this facility by setting an RXRPC_UPGRADE_SERVICE
command in the sendmsg() control buffer and then observing the resultant
service ID in the msg_addr returned by recvmsg().  This should only be used
to probe the service.  Clients should then use the returned service ID in
all subsequent communications with that server.  Note that the kernel will
not retain this information should the connection expire from its cache.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Jeff Kirsher says:

====================
1GbE Intel Wired LAN Driver Updates 2017-06-06

This series contains updates and fixes to e1000e and igb.

Matwey V Kornilov fixes an issue where igb_get_phy_id_82575() relies on
the fact that page 0 is already selected, but this is not the case after
igb_read_phy_reg_gs40g()/igb_write_phy_reg_gs40g() were removed in a
previous commit.  This leads to initialization failure and some devices
not working.  To fix the issue, explicitly select page 0 before first
access to PHY registers.

Arnd Bergmann modifies the driver to avoid a "defined but not used"
warning by removing #ifdefs and using __maybe_unused annotation instead
for new power management functions.

Jake provides most of the changes in the series, all around PTP and
timestamp fixes/updates.  Resolved several race conditions based on
the hardware can only handle one transmit timestamp at a time, so
fix the locking logic, as well as create a statistic for "skipped"
timestamps to help administrators identify issues.

Benjamin Poirier provides 2 changes, first to igb to remove the
second argument to igb_update_stats() since it always passes the
same two arguments.  So instead of having to pass the second argument,
just update the function to the necessary information from the adapter
structure.  Second modifies the e1000e_get_stats64() call to
dev_get_stats() to avoid ethtool garbage being reported.

Konstantin Khlebnikov modifies e1000e to use disable_hardirq(), instead
of disable_irq() for MSIx vectors in e1000_netpoll().
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Replace disable_irq() which waits for threaded irq handlers with
disable_hardirq() which waits only for hardirq part.

Fixes: 31119129 ("e1000: use disable_hardirq() for e1000_netpoll()")
Signed-off-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: NCong Wang <xiyou.wangcong@gmail.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Some statistics passed to ethtool are garbage because e1000e_get_stats64()
doesn't write them, for example: tx_heartbeat_errors. This leaks kernel
memory to userspace and confuses users.

Do like ixgbe and use dev_get_stats() which first zeroes out
rtnl_link_stats64.

Fixes: 5944701d ("net: remove useless memset's in drivers get_stats64")
Reported-by: NStefan Priebe <s.priebe@profihost.ag>
Signed-off-by: NBenjamin Poirier <bpoirier@suse.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Given that all callers of igb_update_stats() pass the same two arguments:
(adapter, &adapter->stats64), the second argument can be removed.
Signed-off-by: NBenjamin Poirier <bpoirier@suse.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The igb driver has logic to handle only one Tx timestamp at a time,
using a state bit lock to avoid multiple requests at once.

It may be possible, if incredibly unlikely, that a Tx timestamp event is
requested but never completes. Since we use an interrupt scheme to
determine when the Tx timestamp occurred we would never clear the state
bit in this case.

Add an igb_ptp_tx_hang() function similar to the already existing
igb_ptp_rx_hang() function. This function runs in the watchdog routine
and makes sure we eventually recover from this case instead of
permanently disabling Tx timestamps.

Note: there is no currently known way to cause this without hacking the
driver code to force it.
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The igb driver can only handle one Tx timestamp request at a time.
This means it is possible for an application timestamp request to be
ignored.

There is no easy way for an administrator to determine if this occurred.
Add a new statistic which tracks this, tx_hwtstamp_skipped.
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The e1000e driver can only handle one Tx timestamp request at a time.
This means it is possible for an application timestamp request to be
ignored.

There is no easy way for an administrator to determine if this occurred.
Add a new statistic which tracks this, tx_hwtstamp_skipped.
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The igb driver uses a state bit lock to avoid handling more than one Tx
timestamp request at once. This is required because hardware is limited
to a single set of registers for Tx timestamps.

The state bit lock is not properly cleaned up during
igb_xmit_frame_ring() if the transmit fails such as due to DMA or TSO
failure. In some hardware this results in blocking timestamps until the
service task times out. In other hardware this results in a permanent
lock of the timestamp bit because we never receive an interrupt
indicating the timestamp occurred, since indeed the packet was never
transmitted.

Fix this by checking for DMA and TSO errors in igb_xmit_frame_ring() and
properly cleaning up after ourselves when these occur.
Reported-by: NReported-by: David Mirabito <davidm@metamako.com>
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

Hardware related to the igb driver has a limitation of only handling one
Tx timestamp at a time. Thus, the driver uses a state bit lock to
enforce that only one timestamp request is honored at a time.

Unfortunately this suffers from a simple race condition. The bit lock is
not cleared until after skb_tstamp_tx() is called notifying the stack of
a new Tx timestamp. Even a well behaved application which sends only one
timestamp request at once and waits for a response might wake up and
send a new packet before the bit lock is cleared. This results in
needlessly dropping some Tx timestamp requests.

We can fix this by unlocking the state bit as soon as we read the
Timestamp register, as this is the first point at which it is safe to
unlock.

To avoid issues with the skb pointer, we'll use a copy of the pointer
and set the global variable in the driver structure to NULL first. This
ensures that the next timestamp request does not modify our local copy
of the skb pointer.

This ensures that well behaved applications do not accidentally race
with the unlock bit. Obviously an application which sends multiple Tx
timestamp requests at once will still only timestamp one packet at
a time. Unfortunately there is nothing we can do about this.
Reported-by: NDavid Mirabito <davidm@metamako.com>
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The e1000e driver and related hardware has a limitation on Tx PTP
packets which requires we limit to timestamping a single packet at once.
We do this by verifying that we never request a new Tx timestamp while
we still have a tx_hwtstamp_skb pointer.

Unfortunately the driver suffers from a race condition around this. The
tx_hwtstamp_skb pointer is not set to NULL until after skb_tstamp_tx()
is called. This function notifies the stack and applications of a new
timestamp. Even a well behaved application that only sends a new request
when the first one is finished might be woken up and possibly send
a packet before we can free the timestamp in the driver again. The
result is that we needlessly ignore some Tx timestamp requests in this
corner case.

Fix this by assigning the tx_hwtstamp_skb pointer prior to calling
skb_tstamp_tx() and use a temporary pointer to hold the timestamped skb
until that function finishes. This ensures that the application is not
woken up until the driver is ready to begin timestamping a new packet.

This ensures that well behaved applications do not accidentally race
with condition to skip Tx timestamps. Obviously an application which
sends multiple Tx timestamp requests at once will still only timestamp
one packet at a time. Unfortunately there is nothing we can do about
this.
Reported-by: NDavid Mirabito <davidm@metamako.com>
Signed-off-by: NJacob Keller <jacob.e.keller@intel.com>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The new wake function is only used by the suspend/resume handlers that
are defined in inside of an #ifdef, which can cause this harmless
warning:

drivers/net/ethernet/intel/igb/igb_main.c:7988:13: warning: 'igb_deliver_wake_packet' defined but not used [-Wunused-function]

Removing the #ifdef, instead using a __maybe_unused annotation
simplifies the code and avoids the warning.

Fixes: b90fa876 ("igb: Enable reading of wake up packet")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The functions igb_read_phy_reg_gs40g/igb_write_phy_reg_gs40g (which were
removed in 2a3cdead) explicitly selected the required page at every phy_reg
access. Currently, igb_get_phy_id_82575 relays on the fact that page 0 is
already selected. The assumption is not fulfilled for my Lex 3I380CW
motherboard with integrated dual i211 based gigabit ethernet. This leads to igb
initialization failure and network interfaces are not working:

    igb: Intel(R) Gigabit Ethernet Network Driver - version 5.4.0-k
    igb: Copyright (c) 2007-2014 Intel Corporation.
    igb: probe of 0000:01:00.0 failed with error -2
    igb: probe of 0000:02:00.0 failed with error -2

In order to fix it, we explicitly select page 0 before first access to phy
registers.

See also: https://bugzilla.suse.com/show_bug.cgi?id=1009911
See also: http://www.lex.com.tw/products/pdf/3I380A&3I380CW.pdf

Fixes: 2a3cdead ("igb: Remove GS40G specific defines/functions")
Cc: <stable@vger.kernel.org> # 4.5+
Signed-off-by: NMatwey V Kornilov <matwey@sai.msu.ru>
Tested-by: NAaron Brown <aaron.f.brown@intel.com>
Signed-off-by: NJeff Kirsher <jeffrey.t.kirsher@intel.com>

The u32 variable v is being checked to see if an error return is
less than zero and this check has no effect because it is unsigned.
Fix this by making v and int (this also matches the type of
cb->bus_number which is assigned to the value in v).

Detected by CoverityScan, CID#1440454 ("Unsigned compared against zero")
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

The EPHY may be already enabled by bootloaders which have Ethernet
capability (e.g. current U-Boot). Thus it should be reseted properly
before doing the enabling sequence in the dwmac-sun8i driver, otherwise
the EMAC reset process may fail if no cable is plugged, and then fail
the dwmac-sun8i probing.

Tested on Orange Pi PC, One and Zero. All the boards fail to have
dwmac-sun8i probed with "EMAC reset timeout" without cable plugged
before, and with this fix they're now all able to successfully probe the
EMAC without cable plugged and then use the connection after a cable is
hot-plugged in.

Fixes: 9f93ac8d ("net-next: stmmac: Add dwmac-sun8i")
Signed-off-by: NIcenowy Zheng <icenowy@aosc.io>
Tested-by: NCorentin Labbe <clabbe.montjoie@gmail.com>
Acked-by: NCorentin Labbe <clabbe.montjoie@gmail.com>
Reviewed-by: NCorentin Labbe <clabbe.montjoie@gmail.com>
Acked-by: is not as formal as Signed-off-by:.  It is a record that the acker
Reviewed-by: is similar.
Signed-off-by: NDavid S. Miller <davem@davemloft.net>