Magnus Karlsson [Mon, 16 Nov 2020 11:12:47 +0000 (12:12 +0100)]
i40e: Use batched xsk Tx interfaces to increase performance
Use the new batched xsk interfaces for the Tx path in the i40e driver
to improve performance. On my machine, this yields a throughput
increase of 4% for the l2fwd sample app in xdpsock. If we instead just
look at the Tx part, this patch set increases throughput with above
20% for Tx.
Note that I had to explicitly loop unroll the inner loop to get to
this performance level, by using a pragma. It is honored by both clang
and gcc and should be ignored by versions that do not support
it. Using the -funroll-loops compiler command line switch on the
source file resulted in a loop unrolling on a higher level that
lead to a performance decrease instead of an increase.
Magnus Karlsson [Mon, 16 Nov 2020 11:12:46 +0000 (12:12 +0100)]
xsk: Introduce batched Tx descriptor interfaces
Introduce batched descriptor interfaces in the xsk core code for the
Tx path to be used in the driver to write a code path with higher
performance. This interface will be used by the i40e driver in the
next patch. Though other drivers would likely benefit from this new
interface too.
Note that batching is only implemented for the common case when
there is only one socket bound to the same device and queue id. When
this is not the case, we fall back to the old non-batched version of
the function.
Magnus Karlsson [Mon, 16 Nov 2020 11:12:45 +0000 (12:12 +0100)]
xsk: Introduce padding between more ring pointers
Introduce one cache line worth of padding between the consumer pointer
and the flags field as well as between the flags field and the start
of the descriptors in all the lockless rings. This so that the x86 HW
adjacency prefetcher will not prefetch the adjacent pointer/field when
only one pointer/field is going to be used. This improves throughput
performance for the l2fwd sample app with 1% on my machine with HW
prefetching turned on in the BIOS.
Magnus Karlsson [Mon, 16 Nov 2020 11:12:44 +0000 (12:12 +0100)]
i40e: Remove unnecessary sw_ring access from xsk Tx
Remove the unnecessary access to the software ring for the AF_XDP
zero-copy driver. This was used to record the length of the packet so
that the driver Tx completion code could sum this up to produce the
total bytes sent. This is now performed during the transmission of the
packet, so no need to record this in the software ring.
Magnus Karlsson [Mon, 16 Nov 2020 11:12:43 +0000 (12:12 +0100)]
samples/bpf: Increment Tx stats at sending
Increment the statistics over how many Tx packets have been sent at
the time of sending instead of at the time of completion. This as a
completion event means that the buffer has been sent AND returned to
user space. The packet always gets sent shortly after sendto() is
called. The kernel might, for performance reasons, decide to not
return every single buffer to user space immediately after sending,
for example, only after a batch of packets have been
transmitted. Incrementing the number of packets sent at completion,
will in that case be confusing as if you send a single packet, the
counter might show zero for a while even though the packet has been
transmitted.
Alan Maguire [Sun, 15 Nov 2020 10:46:35 +0000 (10:46 +0000)]
libbpf: bpf__find_by_name[_kind] should use btf__get_nr_types()
When operating on split BTF, btf__find_by_name[_kind] will not
iterate over all types since they use btf->nr_types to show
the number of types to iterate over. For split BTF this is
the number of types _on top of base BTF_, so it will
underestimate the number of types to iterate over, especially
for vmlinux + module BTF, where the latter is much smaller.
Martin KaFai Lau [Mon, 16 Nov 2020 20:01:13 +0000 (12:01 -0800)]
bpf: Fix the irq and nmi check in bpf_sk_storage for tracing usage
The intention of the current check is to avoid using bpf_sk_storage
in irq and nmi. Jakub pointed out that the current check cannot
do that. For example, in_serving_softirq() returns true
if the softirq handling is interrupted by hard irq.
Fixes: 8e4597c627fb ("bpf: Allow using bpf_sk_storage in FENTRY/FEXIT/RAW_TP") Suggested-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20201116200113.2868539-1-kafai@fb.com
selftest/bpf: Fix IPV6FR handling in flow dissector
From second fragment on, IPV6FR program must stop the dissection of IPV6
fragmented packet. This is the same approach used for IPV4 fragmentation.
This fixes the flow keys calculation for the upper-layer protocols.
Note that according to RFC8200, the first fragment packet must include
the upper-layer header.
Jakub Kicinski [Sat, 14 Nov 2020 21:23:01 +0000 (13:23 -0800)]
Merge branch 'ionic-updates'
Shannon Nelson says:
====================
ionic updates
These updates are a bit of code cleaning and a minor
bit of performance tweaking.
v3: convert ionic_lif_quiesce() to void
v2: added void cast on call to ionic_lif_quiesce()
lowered batching threshold
added patch to flatten calls to ionic_lif_rx_mode
added patch to change from_ndo to can_sleep
====================
Shannon Nelson [Thu, 12 Nov 2020 18:22:08 +0000 (10:22 -0800)]
ionic: useful names for booleans
With a few more uses of true and false in function calls, we
need to give them some useful names so we can tell from the
calling point what we're doing.
Signed-off-by: Shannon Nelson <snelson@pensando.io> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Shannon Nelson [Thu, 12 Nov 2020 18:22:07 +0000 (10:22 -0800)]
ionic: change set_rx_mode from_ndo to can_sleep
Instead of having two different ways of expressing the same
sleepability concept, using opposite logic, we can rework the
from_ndo to can_sleep for a more consistent usage.
Fixes: 1800eee16676 ("net: ionic: Replace in_interrupt() usage.") Signed-off-by: Shannon Nelson <snelson@pensando.io> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Shannon Nelson [Thu, 12 Nov 2020 18:22:05 +0000 (10:22 -0800)]
ionic: use mc sync for multicast filters
We should be using the multicast sync routines for the multicast
filters. Also, let's just flatten the logic a bit and pull
the small unicast routine back into ionic_set_rx_mode().
Fixes: 1800eee16676 ("net: ionic: Replace in_interrupt() usage.") Signed-off-by: Shannon Nelson <snelson@pensando.io> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Shannon Nelson [Thu, 12 Nov 2020 18:22:04 +0000 (10:22 -0800)]
ionic: batch rx buffer refilling
We don't need to refill the rx descriptors on every napi
if only a few were handled. Waiting until we can batch up
a few together will save us a few Rx cycles.
Signed-off-by: Shannon Nelson <snelson@pensando.io> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Shannon Nelson [Thu, 12 Nov 2020 18:22:03 +0000 (10:22 -0800)]
ionic: add lif quiesce
After the queues are stopped, expressly quiesce the lif.
This assures that even if the queues were in an odd state,
the firmware will close up everything cleanly.
Signed-off-by: Shannon Nelson <snelson@pensando.io> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Shannon Nelson [Thu, 12 Nov 2020 18:22:02 +0000 (10:22 -0800)]
ionic: check for link after netdev registration
Request a link check as soon as the netdev is registered rather
than waiting for the watchdog to go off in order to get the
interface operational a little more quickly.
Signed-off-by: Shannon Nelson <snelson@pensando.io> Reviewed-by: Saeed Mahameed <saeedm@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Lukas Bulwahn [Fri, 13 Nov 2020 13:50:12 +0000 (14:50 +0100)]
ipv6: remove unused function ipv6_skb_idev()
Commit bdb7cc643fc9 ("ipv6: Count interface receive statistics on the
ingress netdev") removed all callees for ipv6_skb_idev(). Hence, since
then, ipv6_skb_idev() is unused and make CC=clang W=1 warns:
net/ipv6/exthdrs.c:909:33:
warning: unused function 'ipv6_skb_idev' [-Wunused-function]
So, remove this unused function and a -Wunused-function warning.
1) Add BTF generation for kernel modules and extend BTF infra in kernel
e.g. support for split BTF loading and validation, from Andrii Nakryiko.
2) Support for pointers beyond pkt_end to recognize LLVM generated patterns
on inlined branch conditions, from Alexei Starovoitov.
3) Implements bpf_local_storage for task_struct for BPF LSM, from KP Singh.
4) Enable FENTRY/FEXIT/RAW_TP tracing program to use the bpf_sk_storage
infra, from Martin KaFai Lau.
5) Add XDP bulk APIs that introduce a defer/flush mechanism to optimize the
XDP_REDIRECT path, from Lorenzo Bianconi.
6) Fix a potential (although rather theoretical) deadlock of hashtab in NMI
context, from Song Liu.
7) Fixes for cross and out-of-tree build of bpftool and runqslower allowing build
for different target archs on same source tree, from Jean-Philippe Brucker.
8) Fix error path in htab_map_alloc() triggered from syzbot, from Eric Dumazet.
9) Move functionality from test_tcpbpf_user into the test_progs framework so it
can run in BPF CI, from Alexander Duyck.
10) Lift hashtab key_size limit to be larger than MAX_BPF_STACK, from Florian Lehner.
Note that for the fix from Song we have seen a sparse report on context
imbalance which requires changes in sparse itself for proper annotation
detection where this is currently being discussed on linux-sparse among
developers [0]. Once we have more clarification/guidance after their fix,
Song will follow-up.
* git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (66 commits)
net: mlx5: Add xdp tx return bulking support
net: mvpp2: Add xdp tx return bulking support
net: mvneta: Add xdp tx return bulking support
net: page_pool: Add bulk support for ptr_ring
net: xdp: Introduce bulking for xdp tx return path
bpf: Expose bpf_d_path helper to sleepable LSM hooks
bpf: Augment the set of sleepable LSM hooks
bpf: selftest: Use bpf_sk_storage in FENTRY/FEXIT/RAW_TP
bpf: Allow using bpf_sk_storage in FENTRY/FEXIT/RAW_TP
bpf: Rename some functions in bpf_sk_storage
bpf: Folding omem_charge() into sk_storage_charge()
selftests/bpf: Add asm tests for pkt vs pkt_end comparison.
selftests/bpf: Add skb_pkt_end test
bpf: Support for pointers beyond pkt_end.
tools/bpf: Always run the *-clean recipes
tools/bpf: Add bootstrap/ to .gitignore
bpf: Fix NULL dereference in bpf_task_storage
tools/bpftool: Fix build slowdown
tools/runqslower: Build bpftool using HOSTCC
tools/runqslower: Enable out-of-tree build
...
====================
Steen Hegelund [Thu, 12 Nov 2020 09:22:50 +0000 (10:22 +0100)]
net: phy: mscc: Add PTP support for 2 more VSC PHYs
Add VSC8572 and VSC8574 in the PTP configuration
as they also support PTP.
The relevant datasheets can be found here:
- VSC8572: https://www.microchip.com/wwwproducts/en/VSC8572
- VSC8574: https://www.microchip.com/wwwproducts/en/VSC8574
Daniel Borkmann [Sat, 14 Nov 2020 01:29:00 +0000 (02:29 +0100)]
Merge branch 'xdp-redirect-bulk'
Lorenzo Bianconi says:
====================
XDP bulk APIs introduce a defer/flush mechanism to return
pages belonging to the same xdp_mem_allocator object
(identified via the mem.id field) in bulk to optimize
I-cache and D-cache since xdp_return_frame is usually
run inside the driver NAPI tx completion loop.
Convert mvneta, mvpp2 and mlx5 drivers to xdp_return_frame_bulk APIs.
More details on benchmarks run on mlx5 can be found here:
https://github.com/xdp-project/xdp-project/blob/master/areas/mem/xdp_bulk_return01.org
Changes since v5:
- do not keep looping over ptr_ring if the cache is full but release leftover
pages running page_pool_return_page
Changes since v3:
- align DEV_MAP_BULK_SIZE to XDP_BULK_QUEUE_SIZE
- refactor page_pool_put_page_bulk to avoid code duplication
Changes since v2:
- move mvneta changes in a dedicated patch
Changes since v1:
- improve comments
- rework xdp_return_frame_bulk routine logic
- move count and xa fields at the beginning of xdp_frame_bulk struct
- invert logic in page_pool_put_page_bulk for loop
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Lorenzo Bianconi [Fri, 13 Nov 2020 11:48:28 +0000 (12:48 +0100)]
net: xdp: Introduce bulking for xdp tx return path
XDP bulk APIs introduce a defer/flush mechanism to return
pages belonging to the same xdp_mem_allocator object
(identified via the mem.id field) in bulk to optimize
I-cache and D-cache since xdp_return_frame is usually run
inside the driver NAPI tx completion loop.
The bulk queue size is set to 16 to be aligned to how
XDP_REDIRECT bulking works. The bulk is flushed when
it is full or when mem.id changes.
xdp_frame_bulk is usually stored/allocated on the function
call-stack to avoid locking penalties.
Current implementation considers only page_pool memory model.
Heiner Kallweit [Wed, 11 Nov 2020 21:56:29 +0000 (22:56 +0100)]
r8169: improve rtl_tx
We can simplify the for() condition and eliminate variable tx_left.
The change also considers that tp->cur_tx may be incremented by a
racing rtl8169_start_xmit().
In addition replace the write to tp->dirty_tx and the following
smp_mb() with an equivalent call to smp_store_mb(). This implicitly
adds a WRITE_ONCE() to the write.
Heiner Kallweit [Wed, 11 Nov 2020 21:14:27 +0000 (22:14 +0100)]
r8169: use READ_ONCE in rtl_tx_slots_avail
tp->dirty_tx and tp->cur_tx may be changed by a racing rtl_tx() or
rtl8169_start_xmit(). Use READ_ONCE() to annotate the races and ensure
that the compiler doesn't use cached values.
Jakub Kicinski [Fri, 13 Nov 2020 23:37:10 +0000 (15:37 -0800)]
Merge branch 'net-ipa-two-fixes'
Alex Elder says:
====================
net: ipa: two fixes
This small series makes two fixes to the IPA code:
- While reviewing something else I found that one of the resource
limits on the SDM845 used the wrong value. The first patch
fixes this. The correct value allocates more resources of this
type for IPA to use, and otherwise does not change behavior.
- When the IPA-resident microcontroller starts up it generates an
event, which triggers an AP interrupt. The event merely
provides some information for logging, which we don't support.
We already ignore the event, and that's harmless. So this
patch explicitly ignores it rather than issuing a warning when
it occurs.
====================
Alex Elder [Thu, 12 Nov 2020 12:20:00 +0000 (06:20 -0600)]
net: ipa: ignore the microcontroller log event
The IPA-resident microcontroller has the ability to log various
activity in an area of IPA shared memory. When the microcontroller
starts it generates an event to the AP to provide information about
the log.
We don't support reading this log, and we can safely ignore the
event. So do that rather than treating the log info event we
receive as "unsupported."
Signed-off-by: Alex Elder <elder@linaro.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Edward Cree [Thu, 12 Nov 2020 15:20:05 +0000 (15:20 +0000)]
sfc: support GRE TSO on EF100
We can treat SKB_GSO_GRE almost exactly the same as UDP tunnels, except
that we don't want to edit the outer UDP len (as there isn't one).
For SKB_GSO_GRE_CSUM, we have to use GSO_PARTIAL as the device doesn't
support offload of non-UDP outer L4 checksums.
Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Acked-by: Martin Habets <mhabets@solarflare.com> Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Edward Cree [Thu, 12 Nov 2020 15:19:47 +0000 (15:19 +0000)]
sfc: correctly support non-partial GSO_UDP_TUNNEL_CSUM on EF100
By asking the HW for the correct edits, we can make UDP tunnel TSO
work without needing GSO_PARTIAL. So don't specify it in our
netdev->gso_partial_features.
However, retain GSO_PARTIAL support, as this will be used for other
protocols later.
Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Acked-by: Martin Habets <mhabets@solarflare.com> Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Edward Cree [Thu, 12 Nov 2020 15:19:26 +0000 (15:19 +0000)]
sfc: extend bitfield macros to 19 fields
Our TSO descriptors got even more fussy.
Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Acked-by: Martin Habets <mhabets@solarflare.com> Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
This series rearranges and consolidates some GSI register
definitions. Its general aim is to make things more
consistent, by:
- Using enumerated types to define the values held in GSI register
fields
- Defining field values in "gsi_reg.h", together with the
definition of the register (and field) that holds them
- Format enumerated type members consistently, with hexidecimal
numeric values, and assignments aligned on the same column
There is one checkpatch "CHECK" warning requesting a blank line; I
ignored that because my intention was to group certain definitions.
====================
Alex Elder [Tue, 10 Nov 2020 21:59:21 +0000 (15:59 -0600)]
net: ipa: move GSI command opcode values into "gsi_reg.h"
The gsi_ch_cmd_opcode, gsi_evt_cmd_opcode, and gsi_generic_cmd_opcode
enumerated types are values that fields in the GSI command registers
can take on. Move their definitions out of "gsi.c" and into "gsi_reg.h",
alongside the definition of registers they are associated with.
Signed-off-by: Alex Elder <elder@linaro.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Alex Elder [Tue, 10 Nov 2020 21:59:20 +0000 (15:59 -0600)]
net: ipa: move GSI error values into "gsi_reg.h"
The gsi_err_code and gsi_err_type enumerated types are values that
fields in the GSI ERROR_LOG register can take on. Move their
definitions out of "gsi.c" and into "gsi_reg.h", alongside the
definition of the ERROR_LOG register offset and field symbols.
Drop the "_ERR" suffix in the names of the gsi_err_code members.
Signed-off-by: Alex Elder <elder@linaro.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Alex Elder [Tue, 10 Nov 2020 21:59:19 +0000 (15:59 -0600)]
net: ipa: move channel type values into "gsi_reg.h"
The gsi_channel_type enumerated type define values used for the
channel type/protocol for event rings and channels. Move its
definition out of "gsi.c" and into "gsi_reg.h", alongside the
definition of the CH_C_CNTXT_0 register offset and its fields.
Add a comment near the definition of the EV_CH_E_CNTXT_0 register
indicating this type is used for its EV_CHTYPE field.
Signed-off-by: Alex Elder <elder@linaro.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Alex Elder [Tue, 10 Nov 2020 21:59:18 +0000 (15:59 -0600)]
net: ipa: use common value for channel type and protocol
The numeric values that represent the event ring channel type are
identical to the values that represent the matching protocol used
for a channel. Use a new gsi_channel_type enumerated type to
represent the values programmed for both cases, using "CHANNEL_TYPE"
in member names in place of "EVT_CHTYPE" and "CHANNEL_PROTOCOL".
Signed-off-by: Alex Elder <elder@linaro.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jakub Kicinski [Fri, 13 Nov 2020 20:03:21 +0000 (12:03 -0800)]
Merge tag 'mac80211-next-for-net-next-2020-11-13' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next
Johannes Berg says:
====================
Some updates:
* injection/radiotap updates for new test capabilities
* remove WDS support - even years ago when we turned
it off by default it was already basically unusable
* support for HE (802.11ax) rates for beacons
* support for some vendor-specific HE rates
* many other small features/cleanups
* tag 'mac80211-next-for-net-next-2020-11-13' of git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next: (21 commits)
nl80211: fix kernel-doc warning in the new SAE attribute
cfg80211: remove WDS code
mac80211: remove WDS-related code
rt2x00: remove WDS code
b43legacy: remove WDS code
b43: remove WDS code
carl9170: remove WDS code
ath9k: remove WDS code
wireless: remove CONFIG_WIRELESS_WDS
mac80211: assure that certain drivers adhere to DONT_REORDER flag
mac80211: don't overwrite QoS TID of injected frames
mac80211: adhere to Tx control flag that prevents frame reordering
mac80211: add radiotap flag to assure frames are not reordered
mac80211: save HE oper info in BSS config for mesh
cfg80211: add support to configure HE MCS for beacon rate
nl80211: fix beacon tx rate mask validation
nl80211/cfg80211: fix potential infinite loop
cfg80211: Add support to calculate and report 4096-QAM HE rates
cfg80211: Add support to configure SAE PWE value to drivers
ieee80211: Add definition for WFA DPP
...
====================
KP Singh [Fri, 13 Nov 2020 00:59:30 +0000 (00:59 +0000)]
bpf: Expose bpf_d_path helper to sleepable LSM hooks
Sleepable hooks are never called from an NMI/interrupt context, so it
is safe to use the bpf_d_path helper in LSM programs attaching to these
hooks.
The helper is not restricted to sleepable programs and merely uses the
list of sleepable hooks as the initial subset of LSM hooks where it can
be used.
KP Singh [Fri, 13 Nov 2020 00:59:29 +0000 (00:59 +0000)]
bpf: Augment the set of sleepable LSM hooks
Update the set of sleepable hooks with the ones that do not trigger
a warning with might_fault() when exercised with the correct kernel
config options enabled, i.e.
DEBUG_ATOMIC_SLEEP=y
LOCKDEP=y
PROVE_LOCKING=y
This means that a sleepable LSM eBPF program can be attached to these
LSM hooks. A new helper method bpf_lsm_is_sleepable_hook is added and
the set is maintained locally in bpf_lsm.c
Merge branch 'bpf: Enable bpf_sk_storage for FENTRY/FEXIT/RAW_TP'
Martin KaFai says:
====================
This set is to allow the FENTRY/FEXIT/RAW_TP tracing program to use
bpf_sk_storage. The first two patches are a cleanup. The last patch is
tests. Patch 3 has the required kernel changes to
enable bpf_sk_storage for FENTRY/FEXIT/RAW_TP.
Please see individual patch for details.
v2:
- Rename some of the function prefix from sk_storage to bpf_sk_storage
- Use prefix check instead of substr check
====================
Martin KaFai Lau [Thu, 12 Nov 2020 21:13:20 +0000 (13:13 -0800)]
bpf: selftest: Use bpf_sk_storage in FENTRY/FEXIT/RAW_TP
This patch tests storing the task's related info into the
bpf_sk_storage by fentry/fexit tracing at listen, accept,
and connect. It also tests the raw_tp at inet_sock_set_state.
A negative test is done by tracing the bpf_sk_storage_free()
and using bpf_sk_storage_get() at the same time. It ensures
this bpf program cannot load.
Martin KaFai Lau [Thu, 12 Nov 2020 21:13:13 +0000 (13:13 -0800)]
bpf: Allow using bpf_sk_storage in FENTRY/FEXIT/RAW_TP
This patch enables the FENTRY/FEXIT/RAW_TP tracing program to use
the bpf_sk_storage_(get|delete) helper, so those tracing programs
can access the sk's bpf_local_storage and the later selftest
will show some examples.
The bpf_sk_storage is currently used in bpf-tcp-cc, tc,
cg sockops...etc which is running either in softirq or
task context.
This patch adds bpf_sk_storage_get_tracing_proto and
bpf_sk_storage_delete_tracing_proto. They will check
in runtime that the helpers can only be called when serving
softirq or running in a task context. That should enable
most common tracing use cases on sk.
During the load time, the new tracing_allowed() function
will ensure the tracing prog using the bpf_sk_storage_(get|delete)
helper is not tracing any bpf_sk_storage*() function itself.
The sk is passed as "void *" when calling into bpf_local_storage.
Martin KaFai Lau [Thu, 12 Nov 2020 21:13:07 +0000 (13:13 -0800)]
bpf: Rename some functions in bpf_sk_storage
Rename some of the functions currently prefixed with sk_storage
to bpf_sk_storage. That will make the next patch have fewer
prefix check and also bring the bpf_sk_storage.c to a more
consistent function naming.
In some cases LLVM uses the knowledge that branch is taken to optimze the code
which causes the verifier to reject valid programs.
Teach the verifier to recognize that
r1 = skb->data;
r1 += 10;
r2 = skb->data_end;
if (r1 > r2) {
here r1 points beyond packet_end and subsequent
if (r1 > r2) // always evaluates to "true".
}
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This patch adds the verifier support to recognize inlined branch conditions.
The LLVM knows that the branch evaluates to the same value, but the verifier
couldn't track it. Hence causing valid programs to be rejected.
The potential LLVM workaround: https://reviews.llvm.org/D87428
can have undesired side effects, since LLVM doesn't know that
skb->data/data_end are being compared. LLVM has to introduce extra boolean
variable and use inline_asm trick to force easier for the verifier assembly.
Instead teach the verifier to recognize that
r1 = skb->data;
r1 += 10;
r2 = skb->data_end;
if (r1 > r2) {
here r1 points beyond packet_end and
subsequent
if (r1 > r2) // always evaluates to "true".
}
Guillaume Nault [Wed, 11 Nov 2020 15:05:35 +0000 (16:05 +0100)]
selftests: set conf.all.rp_filter=0 in bareudp.sh
When working on the rp_filter problem, I didn't realise that disabling
it on the network devices didn't cover all cases: rp_filter could also
be enabled globally in the namespace, in which case it would drop
packets, even if the net device has rp_filter=0.
====================
mlxsw: spectrum: Prepare for XM implementation - prefix insertion and removal
Jiri says:
This is a preparation patchset for follow-up support of boards with
extended mezzanine (XM), which is going to allow extended (scale-wise)
router offload.
XM requires a separate PRM register named XMDR to be used instead of
RALUE to insert/update/remove FIB entries. Therefore, this patchset
extends the previously introduces low-level ops to be able to have
XM-specific FIB entry config implementation.
Currently the existing original RALUE implementation is moved to "basic"
low-level ops.
Unlike legacy router, insertion/update/removal of FIB entries into XM
could be done in bulks up to 4 items in a single PRM register write.
That is why this patchset implements "an op context", that allows the
future XM ops implementation to squash multiple FIB events to single
register write. For that, the way in which the FIB events are processed
by the work queue has to be changed.
The conversion from 1:1 FIB event - work callback call to event queue is
implemented in patch #3.
Patch #4 introduces "an op context" that will allow in future to squash
multiple FIB events into one XMDR register write. Patch #12 converts it
from stack to be allocated per instance.
Existing RALUE manipulations are pushed to ops in patch #10.
Patch #13 is introducing a possibility for low-level implementation to
have per FIB entry private memory.
The rest of the patches are either cosmetics or smaller preparations.
====================
Jiri Pirko [Tue, 10 Nov 2020 09:49:00 +0000 (11:49 +0200)]
mlxsw: spectrum_router: Introduce FIB entry update op
Follow-up patchset introducing XMDR implementation is going to need
to distinguish write and update ops. Therefore introduce "update op"
and call "write op" only when new FIB entry is inserted.
Jiri Pirko [Tue, 10 Nov 2020 09:48:59 +0000 (11:48 +0200)]
mlxsw: spectrum_router: Track FIB entry committed state and skip uncommitted on delete
In case bulking is used, the entry that was previously added may not
be yet committed to the HW as it waits in the queue for bulk send. For
such entries, skip the deletion.
Jiri Pirko [Tue, 10 Nov 2020 09:48:58 +0000 (11:48 +0200)]
mlxsw: spectrum_router: Introduce fib_entry priv for low-level ops
Prepare for the low-level ops that need to store some data alongside
the fib_entry and introduce a per-fib_entry priv for ll ops.
The priv is reference counted as in the follow-up patch it is going
to be saved in pack() function and used later on in commit() even in
case the related fib_entry gets freed in the middle.
Jiri Pirko [Tue, 10 Nov 2020 09:48:57 +0000 (11:48 +0200)]
mlxsw: spectrum_router: Have FIB entry op context allocated for the instance
Get the max size needed for FIB entry op context and allocate it once
for the instance. Use it repeatedly from the scheduled work.
By this, allow to extend the context to hold more data than it is wise
to do when it was on the stack. Make sure to signalize that the context
needs to be initialized in case families of subsequent FIB entries differ.
Jiri Pirko [Tue, 10 Nov 2020 09:48:56 +0000 (11:48 +0200)]
mlxsw: spectrum_router: Prepare work context for possible bulking
For XMDR register it is possible to carry multiple FIB entry
operations in a single write. However the FW does not restrict mixing
the types of operations, make the code easier and indicate the bulking
is ok only in case the bulk contains FIB operations of the same family
and event.
Jiri Pirko [Tue, 10 Nov 2020 09:48:55 +0000 (11:48 +0200)]
mlxsw: spectrum: Push RALUE packing and writing into low-level router ops
With follow-up introduction of XM implementation, XMDR register is
going to be optionally used instead of RALUE register. Push the RALUE
packing helpers and write call into low-level router ops.
Jiri Pirko [Tue, 10 Nov 2020 09:48:53 +0000 (11:48 +0200)]
mlxsw: reg: Allow to pass NULL pointer to mlxsw_reg_ralue_pack4/6()
In preparation for the change that is going to be done in the next
patch, allow to pass NULL pointer to mlxsw_reg_ralue_pack4() and
mlxsw_reg_ralue_pack6() helpers.
Jiri Pirko [Tue, 10 Nov 2020 09:48:49 +0000 (11:48 +0200)]
mlxsw: spectrum: Propagate context from work handler containing RALUE payload
Currently, RALUE payload is defined locally in the function that is
calling the register write. With introduction of alternative register to
RALUE, XMDR, it has to be possible to put multiple FIB entry
operations into single register write.
So in order to prepare for that, have per-work entry operation context
and propagate it all the way down to the functions writing RALUE.
Jiri Pirko [Tue, 10 Nov 2020 09:48:48 +0000 (11:48 +0200)]
mlxsw: spectrum_router: Introduce FIB event queue instead of separate works
Currently, every FIB event is queued-up as a separate work to be
processed. However, that allows to process only one FIB entry per work
callback.
In preparation of future XMDR register bulking of multiple FIB entries,
convert to FIB event queue. Implement this by a list_head, adding new
events to the end of the list in the FIB notify callback. That allows to
process multiple events from the list inside the work callback.
Jiri Pirko [Tue, 10 Nov 2020 09:48:47 +0000 (11:48 +0200)]
mlxsw: spectrum_router: Use RALUE-independent op arg
Since the write/delete of FIB entry is going to be implemented by XMDR
register for XM implementation, introduce RALUE-independent enum for op
so the enum could be used in both RALUE and XMDR.
Jiri Pirko [Tue, 10 Nov 2020 09:48:46 +0000 (11:48 +0200)]
mlxsw: spectrum_router: Pass non-register proto enum to __mlxsw_sp_router_set_abort_trap()
Don't pass RALXX register enum and rather pass enum mlxsw_sp_l3proto
to __mlxsw_sp_router_set_abort_trap(). This is in preparation to fib
entry pack implementation by XMDR register.
Randy Dunlap [Tue, 10 Nov 2020 17:57:46 +0000 (09:57 -0800)]
net: kcov: don't select SKB_EXTENSIONS when there is no NET
Fix kconfig warning when CONFIG_NET is not set/enabled:
WARNING: unmet direct dependencies detected for SKB_EXTENSIONS
Depends on [n]: NET [=n]
Selected by [y]:
- KCOV [=y] && ARCH_HAS_KCOV [=y] && (CC_HAS_SANCOV_TRACE_PC [=y] || GCC_PLUGINS [=n])
Fixes: 6370cc3bbd8a ("net: add kcov handle to skb extensions") Signed-off-by: Randy Dunlap <rdunlap@infradead.org> Cc: Aleksandr Nogikh <nogikh@google.com> Cc: Willem de Bruijn <willemb@google.com> Link: https://lore.kernel.org/r/20201110175746.11437-1-rdunlap@infradead.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Heiner Kallweit [Tue, 10 Nov 2020 19:50:02 +0000 (20:50 +0100)]
usbnet: switch to core handling of rx/tx byte/packet counters
Use netdev->tstats instead of a member of usbnet for storing a pointer
to the per-cpu counters. This allows us to use core functionality for
statistics handling.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Heiner Kallweit [Tue, 10 Nov 2020 19:48:54 +0000 (20:48 +0100)]
qtnfmac: switch to core handling of rx/tx byte/packet counters
Use netdev->tstats instead of a member of qtnf_vif for storing a pointer
to the per-cpu counters. This allows us to use core functionality for
statistics handling.
The driver sets netdev->needs_free_netdev, therefore freeing the per-cpu
counters at the right point in time is a little bit tricky. Best option
seems to be to use the ndo_init/ndo_uninit callbacks.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Acked-by: Kalle Valo <kvalo@codeaurora.org> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Heiner Kallweit [Tue, 10 Nov 2020 19:48:14 +0000 (20:48 +0100)]
qmi_wwan: switch to core handling of rx/tx byte/packet counters
Use netdev->tstats instead of a member of qmimux_priv for storing
a pointer to the per-cpu counters. This allows us to use core
functionality for statistics handling.
Heiner Kallweit [Tue, 10 Nov 2020 19:47:34 +0000 (20:47 +0100)]
IB/hfi1: switch to core handling of rx/tx byte/packet counters
Use netdev->tstats instead of a member of hfi1_ipoib_dev_priv for storing
a pointer to the per-cpu counters. This allows us to use core
functionality for statistics handling.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Acked-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Thierry Reding [Tue, 10 Nov 2020 07:37:57 +0000 (08:37 +0100)]
net: ipconfig: Avoid spurious blank lines in boot log
When dumping the name and NTP servers advertised by DHCP, a blank line
is emitted if either of the lists is empty. This can lead to confusing
issues such as the blank line getting flagged as warning. This happens
because the blank line is the result of pr_cont("\n") and that may see
its level corrupted by some other driver concurrently writing to the
console.
Fix this by making sure that the terminating newline is only emitted
if at least one entry in the lists was printed before.
Andrew Lunn [Tue, 10 Nov 2020 03:02:47 +0000 (04:02 +0100)]
drivers: net: smc911x: Fix cast from pointer to integer of different size
drivers/net/ethernet/smsc/smc911x.c: In function ‘smc911x_hardware_send_pkt’:
drivers/net/ethernet/smsc/smc911x.c:471:11: warning: cast from pointer to integer of different size [-Wpointer-to-int-cast]
471 | cmdA = (((u32)skb->data & 0x3) << 16) |
When built on 64bit targets, the skb->data pointer cannot be cast to a
u32 in a meaningful way. Use uintptr_t instead.
Suggested-by: Nicolas Pitre <nico@fluxnic.net> Signed-off-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Andrew Lunn [Tue, 10 Nov 2020 03:02:45 +0000 (04:02 +0100)]
drivers: net: smc911x: Fix set but unused status because of DBG macro
drivers/net/ethernet/smsc/smc911x.c: In function ‘smc911x_timeout’:
drivers/net/ethernet/smsc/smc911x.c:1251:6: warning: variable ‘status’ set but not used [-Wunused-but-set-variable]
1251 | int status, mask;
The status is read in order to print it via the DBG macro. However,
due to the way DBG is disabled, the compiler never sees it being used.
Change the DBG macro to actually make use of the passed parameters,
and the leave the optimiser to remove the unwanted code inside the
while (0).
Signed-off-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Andrew Lunn [Tue, 10 Nov 2020 03:02:44 +0000 (04:02 +0100)]
drivers: net: smc911x: Work around set but unused status
drivers/net/ethernet/smsc/smc911x.c: In function ‘smc911x_phy_interrupt’:
drivers/net/ethernet/smsc/smc911x.c:976:6: warning: variable ‘status’ set but not used [-Wunused-but-set-variable]
976 | int status;
A comment indicates the status needs to be read from the PHY,
otherwise bad things happen. But due to the macro magic, it is hard to
perform the read without assigning it to a variable. So add
_always_unused attribute to status to tell the compiler we don't
expect to use the value.
Signed-off-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Andrew Lunn [Tue, 10 Nov 2020 03:02:43 +0000 (04:02 +0100)]
drivers: net: smc91x: Fix missing kerneldoc reported by W=1
drivers/net/ethernet/smsc/smc91x.c:2199: warning: Function parameter or member 'dev' not described in 'try_toggle_control_gpio'
drivers/net/ethernet/smsc/smc91x.c:2199: warning: Function parameter or member 'desc' not described in 'try_toggle_control_gpio'
drivers/net/ethernet/smsc/smc91x.c:2199: warning: Function parameter or member 'name' not described in 'try_toggle_control_gpio'
drivers/net/ethernet/smsc/smc91x.c:2199: warning: Function parameter or member 'index' not described in 'try_toggle_control_gpio'
drivers/net/ethernet/smsc/smc91x.c:2199: warning: Function parameter or member 'value' not described in 'try_toggle_control_gpio'
drivers/net/ethernet/smsc/smc91x.c:2199: warning: Function parameter or member 'nsdelay' not described in 'try_toggle_control_gpio'
Document these parameters.
Signed-off-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Andrew Lunn [Tue, 10 Nov 2020 03:02:42 +0000 (04:02 +0100)]
drivers: net: smc91x: Fix set but unused W=1 warning
drivers/net/ethernet/smsc/smc91x.c:706:51: warning: variable ‘pkt_len’ set but not used [-Wunused-but-set-variable]
706 | unsigned int saved_packet, packet_no, tx_status, pkt_len;
The read of the packet length in the descriptor probably needs to be
kept in order to keep the hardware happy. So tell the compiler we
don't expect to use the value by using the __always_unused attribute.
Signed-off-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Linus Torvalds [Thu, 12 Nov 2020 22:02:04 +0000 (14:02 -0800)]
Merge tag 'net-5.10-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Current release - regressions:
- arm64: dts: fsl-ls1028a-kontron-sl28: specify in-band mode for
ENETC
Current release - bugs in new features:
- mptcp: provide rmem[0] limit offset to fix oops
Previous release - regressions:
- IPv6: Set SIT tunnel hard_header_len to zero to fix path MTU
calculations
- lan743x: correctly handle chips with internal PHY
- bpf: Don't rely on GCC __attribute__((optimize)) to disable GCSE
- mlx5e: Fix VXLAN port table synchronization after function reload
Previous release - always broken:
- bpf: Zero-fill re-used per-cpu map element
- fix out-of-order UDP packets when forwarding with UDP GSO fraglists
turned on:
- fix UDP header access on Fast/frag0 UDP GRO
- fix IP header access and skb lookup on Fast/frag0 UDP GRO
- ch_ktls: fix multiple leaks and corner cases in Chelsio TLS offload
- tunnels: Fix off-by-one in lower MTU bounds for ICMP/ICMPv6 replies
- r8169: disable hw csum for short packets on all chip versions
- vrf: Fix fast path output packet handling with async Netfilter
rules"
* tag 'net-5.10-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (65 commits)
lan743x: fix use of uninitialized variable
net: udp: fix IP header access and skb lookup on Fast/frag0 UDP GRO
net: udp: fix UDP header access on Fast/frag0 UDP GRO
devlink: Avoid overwriting port attributes of registered port
vrf: Fix fast path output packet handling with async Netfilter rules
cosa: Add missing kfree in error path of cosa_write
net: switch to the kernel.org patchwork instance
ch_ktls: stop the txq if reaches threshold
ch_ktls: tcb update fails sometimes
ch_ktls/cxgb4: handle partial tag alone SKBs
ch_ktls: don't free skb before sending FIN
ch_ktls: packet handling prior to start marker
ch_ktls: Correction in middle record handling
ch_ktls: missing handling of header alone
ch_ktls: Correction in trimmed_len calculation
cxgb4/ch_ktls: creating skbs causes panic
ch_ktls: Update cheksum information
ch_ktls: Correction in finding correct length
cxgb4/ch_ktls: decrypted bit is not enough
net/x25: Fix null-ptr-deref in x25_connect
...
Linus Torvalds [Thu, 12 Nov 2020 21:49:12 +0000 (13:49 -0800)]
Merge tag 'nfs-for-5.10-2' of git://git.linux-nfs.org/projects/anna/linux-nfs
Pull NFS client bugfixes from Anna Schumaker:
"Stable fixes:
- Fix failure to unregister shrinker
Other fixes:
- Fix unnecessary locking to clear up some contention
- Fix listxattr receive buffer size
- Fix default mount options for nfsroot"
* tag 'nfs-for-5.10-2' of git://git.linux-nfs.org/projects/anna/linux-nfs:
NFS: Remove unnecessary inode lock in nfs_fsync_dir()
NFS: Remove unnecessary inode locking in nfs_llseek_dir()
NFS: Fix listxattr receive buffer size
NFSv4.2: fix failure to unregister shrinker
nfsroot: Default mount option should ask for built-in NFS version
Make $(LIBBPF)-clean and $(LIBBPF_BOOTSTRAP)-clean .PHONY targets, in
case those files exist. And keep consistency within the Makefile by
making the directory dependencies order-only.
projects / mirror_ubuntu-hirsute-kernel.git / log