Adds support for fq's Earliest Departure Time to HBM (Host Bandwidth
Manager). Includes a new BPF program supporting EDT, and also updates
corresponding programs.
It will drop packets with an EDT of more than 500us in the future
unless the packet belongs to a flow with less than 2 packets in flight.
This is done so each flow has at least 2 packets in flight, so they
will not starve, and also to help prevent delayed ACK timeouts.
It will also work with ECN enabled traffic, where the packets will be
CE marked if their EDT is more than 50us in the future.
The table below shows some performance numbers. The flows are back to
back RPCS. One server sending to another, either 2 or 4 flows.
One flow is a 10KB RPC, the rest are 1MB RPCs. When there are more
than one flow of a given RPC size, the numbers represent averages.
The rate limit applies to all flows (they are in the same cgroup).
Tests ending with "-edt" ran with the new BPF program supporting EDT.
Tests ending with "-hbt" ran on top HBT qdisc with the specified rate
(i.e. no HBM). The other tests ran with the HBM BPF program included
in the HBM patch-set.
EDT has limited value when using DCTCP, but it helps in many cases when
using Cubic. It usually achieves larger link utilization and lower
99% latencies for the 1MB RPCs.
HBM ends up queueing a lot of packets with its default parameter values,
reducing the goodput of the 10KB RPCs and increasing their latency. Also,
the RTTs seen by the flows are quite large.
At the head of function, it directly access 'attr' without checking
if it's NULL pointer. This patch moves the values assignment after
validating 'attr' and 'attr->file'.
Signed-off-by: Leo Yan <leo.yan@linaro.org> Acked-by: Yonghong Song <yhs@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
GCC8 started emitting warning about using strncpy with number of bytes
exactly equal destination size, which is generally unsafe, as can lead
to non-zero terminated string being copied. Use IFNAMSIZ - 1 as number
of bytes to ensure name is always zero-terminated.
Signed-off-by: Andrii Nakryiko <andriin@fb.com> Cc: Magnus Karlsson <magnus.karlsson@intel.com> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Magnus Karlsson <magnus.karlsson@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Daniel Borkmann [Fri, 28 Jun 2019 23:31:10 +0000 (01:31 +0200)]
Merge branch 'bpf-lookup-devmap'
Toke Høiland-Jørgensen says:
====================
When using the bpf_redirect_map() helper to redirect packets from XDP, the eBPF
program cannot currently know whether the redirect will succeed, which makes it
impossible to gracefully handle errors. To properly fix this will probably
require deeper changes to the way TX resources are allocated, but one thing that
is fairly straight forward to fix is to allow lookups into devmaps, so programs
can at least know when a redirect is *guaranteed* to fail because there is no
entry in the map. Currently, programs work around this by keeping a shadow map
of another type which indicates whether a map index is valid.
This series contains two changes that are complementary ways to fix this issue:
- Moving the map lookup into the bpf_redirect_map() helper (and caching the
result), so the helper can return an error if no value is found in the map.
This includes a refactoring of the devmap and cpumap code to not care about
the index on enqueue.
- Allowing regular lookups into devmaps from eBPF programs, using the read-only
flag to make sure they don't change the values.
The performance impact of the series is negligible, in the sense that I cannot
measure it because the variance between test runs is higher than the difference
pre/post series.
Changelog:
v6:
- Factor out list handling in maps to a helper in list.h (new patch 1)
- Rename variables in struct bpf_redirect_info (new patch 3 + patch 4)
- Explain why we are clearing out the map in the info struct on lookup failure
- Remove unneeded check for forwarding target in tracepoint macro
v5:
- Rebase on latest bpf-next.
- Update documentation for bpf_redirect_map() with the new meaning of flags.
v4:
- Fix a few nits from Andrii
- Lose the #defines in bpf.h and just compare the flags argument directly to
XDP_TX in bpf_xdp_redirect_map().
v3:
- Adopt Jonathan's idea of using the lower two bits of the flag value as the
return code.
- Always do the lookup, and cache the result for use in xdp_do_redirect(); to
achieve this, refactor the devmap and cpumap code to get rid the bitmap for
selecting which devices to flush.
v2:
- For patch 1, make it clear that the change works for any map type.
- For patch 2, just use the new BPF_F_RDONLY_PROG flag to make the return
value read-only.
====================
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
We don't currently allow lookups into a devmap from eBPF, because the map
lookup returns a pointer directly to the dev->ifindex, which shouldn't be
modifiable from eBPF.
However, being able to do lookups in devmaps is useful to know (e.g.)
whether forwarding to a specific interface is enabled. Currently, programs
work around this by keeping a shadow map of another type which indicates
whether a map index is valid.
Since we now have a flag to make maps read-only from the eBPF side, we can
simply lift the lookup restriction if we make sure this flag is always set.
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
bpf_xdp_redirect_map: Perform map lookup in eBPF helper
The bpf_redirect_map() helper used by XDP programs doesn't return any
indication of whether it can successfully redirect to the map index it was
given. Instead, BPF programs have to track this themselves, leading to
programs using duplicate maps to track which entries are populated in the
devmap.
This patch fixes this by moving the map lookup into the bpf_redirect_map()
helper, which makes it possible to return failure to the eBPF program. The
lower bits of the flags argument is used as the return code, which means
that existing users who pass a '0' flag argument will get XDP_ABORTED.
With this, a BPF program can check the return code from the helper call and
react by, for instance, substituting a different redirect. This works for
any type of map used for redirect.
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
devmap: Rename ifindex member in bpf_redirect_info
The bpf_redirect_info struct has an 'ifindex' member which was named back
when the redirects could only target egress interfaces. Now that we can
also redirect to sockets and CPUs, this is a bit misleading, so rename the
member to tgt_index.
Reorder the struct members so we can have 'tgt_index' and 'tgt_value' next
to each other in a subsequent patch.
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
The socket map uses a linked list instead of a bitmap to keep track of
which entries to flush. Do the same for devmap and cpumap, as this means we
don't have to care about the map index when enqueueing things into the
map (and so we can cache the map lookup).
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jonathan Lemon <jonathan.lemon@gmail.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
xskmap: Move non-standard list manipulation to helper
Add a helper in list.h for the non-standard way of clearing a list that is
used in xskmap. This makes it easier to reuse it in the other map types,
and also makes sure this usage is not forgotten in any list refactorings in
the future.
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
selftests/bpf: fix -Wstrict-aliasing in test_sockopt_sk.c
Let's use union with u8[4] and u32 members for sockopt buffer,
that should fix any possible aliasing issues.
test_sockopt_sk.c: In function ‘getsetsockopt’:
test_sockopt_sk.c:115:2: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
if (*(__u32 *)buf != 0x55AA*2) {
^~
test_sockopt_sk.c:116:3: warning: dereferencing type-punned pointer will break strict-aliasing rules [-Wstrict-aliasing]
log_err("Unexpected getsockopt(SO_SNDBUF) 0x%x != 0x55AA*2",
^~~~~~~
Fixes: 8a027dc0d8f5 ("selftests/bpf: add sockopt test that exercises sk helpers") Reported-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Stanislav Fomichev <sdf@google.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
====================
This series implements two new per-cgroup hooks: getsockopt and
setsockopt along with a new sockopt program type. The idea is pretty
similar to recently introduced cgroup sysctl hooks, but
implementation is simpler (no need to convert to/from strings).
What this can be applied to:
* move business logic of what tos/priority/etc can be set by
containers (either pass or reject)
* handle existing options (or introduce new ones) differently by
propagating some information in cgroup/socket local storage
Compared to a simple syscall/{g,s}etsockopt tracepoint, those
hooks are context aware. Meaning, they can access underlying socket
and use cgroup and socket local storage.
v9:
* allow overwriting setsocktop arguments (Alexei Starovoitov)
(see individual changes for more changelog details)
====================
Support sockopt prog type and cgroup hooks in the bpftool.
Cc: Andrii Nakryiko <andriin@fb.com> Cc: Martin Lau <kafai@fb.com> Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
selftests/bpf: add sockopt test that exercises sk helpers
socktop test that introduces new SOL_CUSTOM sockopt level and
stores whatever users sets in sk storage. Whenever getsockopt
is called, the original value is retrieved.
v9:
* SO_SNDBUF example to override user-supplied buffer
v7:
* use retval=0 and optlen-1
v6:
* test 'ret=1' use-case as well (Alexei Starovoitov)
v4:
* don't call bpf_sk_fullsock helper
v3:
* drop (__u8 *)(long) casts for optval{,_end}
v2:
* new test
Cc: Andrii Nakryiko <andriin@fb.com> Cc: Martin Lau <kafai@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add sockopt selftests:
* require proper expected_attach_type
* enforce context field read/write access
* test bpf_sockopt_handled handler
* test EPERM
* test limiting optlen from getsockopt
* test out-of-bounds access
v9:
* add tests for setsockopt argument mangling
v7:
* remove return 2; test retval=0 and optlen=-1
v3:
* use DW for optval{,_end} loads
v2:
* use return code 2 for kernel bypass
Cc: Andrii Nakryiko <andriin@fb.com> Cc: Martin Lau <kafai@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Implement new BPF_PROG_TYPE_CGROUP_SOCKOPT program type and
BPF_CGROUP_{G,S}ETSOCKOPT cgroup hooks.
BPF_CGROUP_SETSOCKOPT can modify user setsockopt arguments before
passing them down to the kernel or bypass kernel completely.
BPF_CGROUP_GETSOCKOPT can can inspect/modify getsockopt arguments that
kernel returns.
Both hooks reuse existing PTR_TO_PACKET{,_END} infrastructure.
The buffer memory is pre-allocated (because I don't think there is
a precedent for working with __user memory from bpf). This might be
slow to do for each {s,g}etsockopt call, that's why I've added
__cgroup_bpf_prog_array_is_empty that exits early if there is nothing
attached to a cgroup. Note, however, that there is a race between
__cgroup_bpf_prog_array_is_empty and BPF_PROG_RUN_ARRAY where cgroup
program layout might have changed; this should not be a problem
because in general there is a race between multiple calls to
{s,g}etsocktop and user adding/removing bpf progs from a cgroup.
The return code of the BPF program is handled as follows:
* 0: EPERM
* 1: success, continue with next BPF program in the cgroup chain
v9:
* allow overwriting setsockopt arguments (Alexei Starovoitov):
* use set_fs (same as kernel_setsockopt)
* buffer is always kzalloc'd (no small on-stack buffer)
v8:
* use s32 for optlen (Andrii Nakryiko)
v7:
* return only 0 or 1 (Alexei Starovoitov)
* always run all progs (Alexei Starovoitov)
* use optval=0 as kernel bypass in setsockopt (Alexei Starovoitov)
(decided to use optval=-1 instead, optval=0 might be a valid input)
* call getsockopt hook after kernel handlers (Alexei Starovoitov)
v6:
* rework cgroup chaining; stop as soon as bpf program returns
0 or 2; see patch with the documentation for the details
* drop Andrii's and Martin's Acked-by (not sure they are comfortable
with the new state of things)
v5:
* skip copy_to_user() and put_user() when ret == 0 (Martin Lau)
v4:
* don't export bpf_sk_fullsock helper (Martin Lau)
* size != sizeof(__u64) for uapi pointers (Martin Lau)
* offsetof instead of bpf_ctx_range when checking ctx access (Martin Lau)
v3:
* typos in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY comments (Andrii Nakryiko)
* reverse christmas tree in BPF_PROG_CGROUP_SOCKOPT_RUN_ARRAY (Andrii
Nakryiko)
* use __bpf_md_ptr instead of __u32 for optval{,_end} (Martin Lau)
* use BPF_FIELD_SIZEOF() for consistency (Martin Lau)
* new CG_SOCKOPT_ACCESS macro to wrap repeated parts
v2:
* moved bpf_sockopt_kern fields around to remove a hole (Martin Lau)
* aligned bpf_sockopt_kern->buf to 8 bytes (Martin Lau)
* bpf_prog_array_is_empty instead of bpf_prog_array_length (Martin Lau)
* added [0,2] return code check to verifier (Martin Lau)
* dropped unused buf[64] from the stack (Martin Lau)
* use PTR_TO_SOCKET for bpf_sockopt->sk (Martin Lau)
* dropped bpf_target_off from ctx rewrites (Martin Lau)
* use return code for kernel bypass (Martin Lau & Andrii Nakryiko)
Cc: Andrii Nakryiko <andriin@fb.com> Cc: Martin Lau <kafai@fb.com> Signed-off-by: Stanislav Fomichev <sdf@google.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Daniel Borkmann [Thu, 27 Jun 2019 20:53:29 +0000 (22:53 +0200)]
Merge branch 'bpf-af-xdp-mlx5e'
Tariq Toukan says:
====================
This series contains improvements to the AF_XDP kernel infrastructure
and AF_XDP support in mlx5e. The infrastructure improvements are
required for mlx5e, but also some of them benefit to all drivers, and
some can be useful for other drivers that want to implement AF_XDP.
The performance testing was performed on a machine with the following
configuration:
- 24 cores of Intel Xeon E5-2620 v3 @ 2.40 GHz
- Mellanox ConnectX-5 Ex with 100 Gbit/s link
The results with retpoline disabled, single stream:
txonly: 33.3 Mpps (21.5 Mpps with queue and app pinned to the same CPU)
rxdrop: 12.2 Mpps
l2fwd: 9.4 Mpps
The results with retpoline enabled, single stream:
txonly: 21.3 Mpps (14.1 Mpps with queue and app pinned to the same CPU)
rxdrop: 9.9 Mpps
l2fwd: 6.8 Mpps
v2 changes:
Added patches for mlx5e and addressed the comments for v1. Rebased for
bpf-next.
v3 changes:
Rebased for the newer bpf-next, resolved conflicts in libbpf. Addressed
Björn's comments for coding style. Fixed a bug in error handling flow in
mlx5e_open_xsk.
v4 changes:
UAPI is not changed, XSK RX queues are exposed to the kernel. The lower
half of the available amount of RX queues are regular queues, and the
upper half are XSK RX queues. The patch "xsk: Extend channels to support
combined XSK/non-XSK traffic" was dropped. The final patch was reworked
accordingly.
Added "net/mlx5e: Attach/detach XDP program safely", as the changes
introduced in the XSK patch base on the stuff from this one.
Added "libbpf: Support drivers with non-combined channels", which aligns
the condition in libbpf with the condition in the kernel.
Rebased over the newer bpf-next.
v5 changes:
In v4, ethtool reports the number of channels as 'combined' and the
number of XSK RX queues as 'rx' for mlx5e. It was changed, so that 'rx'
is 0, and 'combined' reports the double amount of channels if there is
an active UMEM - to make libbpf happy.
The patch for libbpf was dropped. Although it's still useful and fixes
things, it raises some disagreement, so I'm dropping it - it's no longer
useful for mlx5e anymore after the change above.
v6 changes:
As Maxim is out of office, I rebased the series on behalf of him,
solved some conflicts, and re-spinned.
====================
Acked-by: Björn Töpel <bjorn.topel@intel.com> Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
This commit adds support for AF_XDP zero-copy RX and TX.
We create a dedicated XSK RQ inside the channel, it means that two
RQs are running simultaneously: one for non-XSK traffic and the other
for XSK traffic. The regular and XSK RQs use a single ID namespace split
into two halves: the lower half is regular RQs, and the upper half is
XSK RQs. When any zero-copy AF_XDP socket is active, changing the number
of channels is not allowed, because it would break to mapping between
XSK RQ IDs and channels.
XSK requires different page allocation and release routines. Such
functions as mlx5e_{alloc,free}_rx_mpwqe and mlx5e_{get,put}_rx_frag are
generic enough to be used for both regular and XSK RQs, and they use the
mlx5e_page_{alloc,release} wrappers around the real allocation
functions. Function pointers are not used to avoid losing the
performance with retpolines. Wherever it's certain that the regular
(non-XSK) page release function should be used, it's called directly.
Only the stats that could be meaningful for XSK are exposed to the
userspace. Those that don't take part in the XSK flow are not
considered.
Note that we don't wait for WQEs on the XSK RQ (unlike the regular RQ),
because the newer xdpsock sample doesn't provide any Fill Ring entries
at the setup stage.
We create a dedicated XSK SQ in the channel. This separation has its
advantages:
1. When the UMEM is closed, the XSK SQ can also be closed and stop
receiving completions. If an existing SQ was used for XSK, it would
continue receiving completions for the packets of the closed socket. If
a new UMEM was opened at that point, it would start getting completions
that don't belong to it.
2. Calculating statistics separately.
When the userspace kicks the TX, the driver triggers a hardware
interrupt by posting a NOP to a dedicated XSK ICO (internal control
operations) SQ, in order to trigger NAPI on the right CPU core. This XSK
ICO SQ is protected by a spinlock, as the userspace application may kick
the TX from any core.
Store the pointers to the UMEMs in the net device private context,
independently from the kernel. This way the driver can distinguish
between the zero-copy and non-zero-copy UMEMs. The kernel function
xdp_get_umem_from_qid does not care about this difference, but the
driver is only interested in zero-copy UMEMs, particularly, on the
cleanup it determines whether to close the XSK RQ and SQ or not by
looking at the presence of the UMEM. Use state_lock to protect the
access to this area of UMEM pointers.
LRO isn't compatible with XDP, but there may be active UMEMs while
XDP is off. If this is the case, don't allow LRO to ensure XDP can
be reenabled at any time.
The validation of XSK parameters typically happens when XSK queues
open. However, when the interface is down or the XDP program isn't
set, it's still possible to have active AF_XDP sockets and even to
open new, but the XSK queues will be closed. To cover these cases,
perform the validation also in these flows:
1. A new UMEM is registered, but the XSK queues aren't going to be
created due to missing XDP program or interface being down.
2. MTU changes while there are UMEMs registered.
Having this early check prevents mlx5e_open_channels from failing
at a later stage, where recovery is impossible and the application
has no chance to handle the error, because it got the successful
return value for an MTU change or XSK open operation.
The performance testing was performed on a machine with the following
configuration:
- 24 cores of Intel Xeon E5-2620 v3 @ 2.40 GHz
- Mellanox ConnectX-5 Ex with 100 Gbit/s link
The results with retpoline disabled, single stream:
txonly: 33.3 Mpps (21.5 Mpps with queue and app pinned to the same CPU)
rxdrop: 12.2 Mpps
l2fwd: 9.4 Mpps
The results with retpoline enabled, single stream:
txonly: 21.3 Mpps (14.1 Mpps with queue and app pinned to the same CPU)
rxdrop: 9.9 Mpps
l2fwd: 6.8 Mpps
net/mlx5e: Move queue param structs to en/params.h
structs mlx5e_{rq,sq,cq,channel}_param are going to be used in the
upcoming XSK RX and TX patches. Move them to a header file to make
them accessible from other C files.
net/mlx5e: Encapsulate open/close queues into a function
Create new functions mlx5e_{open,close}_queues to encapsulate opening
and closing RQs and SQs, and call the new functions from
mlx5e_{open,close}_channel. It simplifies the existing functions a bit
and prepares them for the upcoming AF_XDP changes.
net/mlx5e: Consider XSK in XDP MTU limit calculation
Use the existing mlx5e_get_linear_rq_headroom function to calculate the
headroom for mlx5e_xdp_max_mtu. This function takes the XSK headroom
into consideration, which will be used in the following patches.
When an XDP program returns XDP_TX, and the RQ is XSK-enabled, it
requires careful handling, because convert_to_xdp_frame creates a new
page and copies the data there, while our driver expects the xdp_frame
to point to the same memory as the xdp_buff. Handle this case
separately: map the page, and in the end unmap it and call
xdp_return_frame.
net/mlx5e: Share the XDP SQ for XDP_TX between RQs
Put the XDP SQ that is used for XDP_TX into the channel. It used to be a
part of the RQ, but with introduction of AF_XDP there will be one more
RQ that could share the same XDP SQ. This patch is a preparation for
that change.
Separate XDP_TX statistics per RQ were implemented in one of the previous
patches.
Currently, struct mlx5e_xdp_info has some issues that have to be cleaned
up before the upcoming AF_XDP support makes things too complicated and
messy. This structure is used both when sending the packet and on
completion. Moreover, the cleanup procedure on completion depends on the
origin of the packet (XDP_REDIRECT, XDP_TX). Adding AF_XDP support will
add new flows that use this structure even differently. To avoid
overcomplicating the code, this commit refactors the usage of this
structure in the following ways:
1. struct mlx5e_xdp_info is split into two different structures. One is
struct mlx5e_xdp_xmit_data, a transient structure that doesn't need to
be stored and is only used while sending the packet. The other is still
struct mlx5e_xdp_info that is stored in a FIFO and contains the fields
needed on completion.
2. The fields of struct mlx5e_xdp_info that are used in different flows
are put into a union. A special enum indicates the cleanup mode and
helps choose the right union member. This approach is clear and
explicit. Although it could be possible to "guess" the mode by looking
at the values of the fields and at the XDP SQ type, it wouldn't be that
clear and extendable and would require looking through the whole chain
to understand what's going on.
For the reference, there are the fields of struct mlx5e_xdp_info that
are used in different flows (including AF_XDP ones):
Packet origin | Fields used on completion | Cleanup steps
-----------------------+---------------------------+------------------
XDP_REDIRECT, | xdpf, dma_addr | DMA unmap and
XDP_TX from XSK RQ | | xdp_return_frame.
-----------------------+---------------------------+------------------
XDP_TX from regular RQ | di | Recycle page.
-----------------------+---------------------------+------------------
AF_XDP TX | (none) | Increment the
| | producer index in
| | Completion Ring.
On send, the same set of mlx5e_xdp_xmit_data fields is used in all
flows: DMA and virtual addresses and length.
net/mlx5e: Allow ICO SQ to be used by multiple RQs
Prepare to creation of the XSK RQ, which will require posting UMRs, too.
The same ICO SQ will be used for both RQs and also to trigger interrupts
by posting NOPs. UMR WQEs can't be reused any more. Optimization
introduced in commit ab966d7e4ff98 ("net/mlx5e: RX, Recycle buffer of
UMR WQEs") is reverted.
net/mlx5e: Calculate linear RX frag size considering XSK
Additional conditions introduced:
- XSK implies XDP.
- Headroom includes the XSK headroom if it exists.
- No space is reserved for struct shared_skb_info in XSK mode.
- Fragment size smaller than the XSK chunk size is not allowed.
A new auxiliary function mlx5e_get_linear_rq_headroom with the support
for XSK is introduced. Use this function in the implementation of
mlx5e_get_rq_headroom. Change headroom to u32 to match the headroom
field in struct xdp_umem.
xsk: Return the whole xdp_desc from xsk_umem_consume_tx
Some drivers want to access the data transmitted in order to implement
acceleration features of the NICs. It is also useful in AF_XDP TX flow.
Change the xsk_umem_consume_tx API to return the whole xdp_desc, that
contains the data pointer, length and DMA address, instead of only the
latter two. Adapt the implementation of i40e and ixgbe to this change.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Acked-by: Saeed Mahameed <saeedm@mellanox.com> Cc: Björn Töpel <bjorn.topel@intel.com> Cc: Magnus Karlsson <magnus.karlsson@intel.com> Acked-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
xsk: Change the default frame size to 4096 and allow controlling it
The typical XDP memory scheme is one packet per page. Change the AF_XDP
frame size in libbpf to 4096, which is the page size on x86, to allow
libbpf to be used with the drivers with the packet-per-page scheme.
Add a command line option -f to xdpsock to allow to specify a custom
frame size.
Make it possible for the application to determine whether the AF_XDP
socket is running in zero-copy mode. To achieve this, add a new
getsockopt option XDP_OPTIONS that returns flags. The only flag
supported for now is the zero-copy mode indicator.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Acked-by: Saeed Mahameed <saeedm@mellanox.com> Acked-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Add a function that checks whether the Fill Ring has the specified
amount of descriptors available. It will be useful for mlx5e that wants
to check in advance, whether it can allocate a bulk of RX descriptors,
to get the best performance.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com> Signed-off-by: Tariq Toukan <tariqt@mellanox.com> Acked-by: Saeed Mahameed <saeedm@mellanox.com> Acked-by: Björn Töpel <bjorn.topel@intel.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
When an XDP program is set, a full reopen of all channels happens in two
cases:
1. When there was no program set, and a new one is being set.
2. When there was a program set, but it's being unset.
The full reopen is necessary, because the channel parameters may change
if XDP is enabled or disabled. However, it's performed in an unsafe way:
if the new channels fail to open, the old ones are already closed, and
the interface goes down. Use the safe way to switch channels instead.
The same way is already used for other configuration changes.
Roman Gushchin [Tue, 25 Jun 2019 21:38:58 +0000 (14:38 -0700)]
bpf: fix cgroup bpf release synchronization
Since commit 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf
from cgroup itself"), cgroup_bpf release occurs asynchronously
(from a worker context), and before the release of the cgroup itself.
This introduced a previously non-existing race between the release
and update paths. E.g. if a leaf's cgroup_bpf is released and a new
bpf program is attached to the one of ancestor cgroups at the same
time. The race may result in double-free and other memory corruptions.
To fix the problem, let's protect the body of cgroup_bpf_release()
with cgroup_mutex, as it was effectively previously, when all this
code was called from the cgroup release path with cgroup mutex held.
Also let's skip cgroups, which have no chances to invoke a bpf
program, on the update path. If the cgroup bpf refcnt reached 0,
it means that the cgroup is offline (no attached processes), and
there are no associated sockets left. It means there is no point
in updating effective progs array! And it can lead to a leak,
if it happens after the release. So, let's skip such cgroups.
Big thanks for Tejun Heo for discovering and debugging of this problem!
Fixes: 4bfc0bb2c60e ("bpf: decouple the lifetime of cgroup_bpf from cgroup itself") Reported-by: Tejun Heo <tj@kernel.org> Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
YueHaibing [Tue, 25 Jun 2019 02:31:37 +0000 (10:31 +0800)]
xdp: Make __mem_id_disconnect static
Fix sparse warning:
net/core/xdp.c:88:6: warning:
symbol '__mem_id_disconnect' was not declared. Should it be static?
Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: YueHaibing <yuehaibing@huawei.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Daniel T. Lee [Tue, 25 Jun 2019 00:55:36 +0000 (09:55 +0900)]
samples: bpf: make the use of xdp samples consistent
Currently, each xdp samples are inconsistent in the use.
Most of the samples fetch the interface with it's name.
(ex. xdp1, xdp2skb, xdp_redirect_cpu, xdp_sample_pkts, etc.)
But some of the xdp samples are fetching the interface with
ifindex by command argument.
This commit enables xdp samples to fetch interface with it's name
without changing the original index interface fetching.
(<ifname|ifindex> fetching in the same way as xdp_sample_pkts_user.c does.)
Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com> Acked-by: Toke Høiland-Jørgensen <toke@redhat.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Yonghong Song [Wed, 26 Jun 2019 00:35:03 +0000 (17:35 -0700)]
bpf: fix compiler warning with CONFIG_MODULES=n
With CONFIG_MODULES=n, the following compiler warning occurs:
/data/users/yhs/work/net-next/kernel/trace/bpf_trace.c:605:13: warning:
‘do_bpf_send_signal’ defined but not used [-Wunused-function]
static void do_bpf_send_signal(struct irq_work *entry)
The __init function send_signal_irq_work_init(), which calls
do_bpf_send_signal(), is defined under CONFIG_MODULES. Hence,
when CONFIG_MODULES=n, nobody calls static function do_bpf_send_signal(),
hence the warning.
The init function send_signal_irq_work_init() should work without
CONFIG_MODULES. Moving it out of CONFIG_MODULES
code section fixed the compiler warning, and also make bpf_send_signal()
helper work without CONFIG_MODULES.
Fixes: 8b401f9ed244 ("bpf: implement bpf_send_signal() helper") Reported-By: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Yonghong Song <yhs@fb.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Toshiaki Makita [Thu, 13 Jun 2019 09:39:59 +0000 (18:39 +0900)]
veth: Support bulk XDP_TX
XDP_TX is similar to XDP_REDIRECT as it essentially redirects packets to
the device itself. XDP_REDIRECT has bulk transmit mechanism to avoid the
heavy cost of indirect call but it also reduces lock acquisition on the
destination device that needs locks like veth and tun.
XDP_TX does not use indirect calls but drivers which require locks can
benefit from the bulk transmit for XDP_TX as well.
This patch introduces bulk transmit mechanism in veth using bulk queue
on stack, and improves XDP_TX performance by about 9%.
Here are single-core/single-flow XDP_TX test results. CPU consumptions
are taken from "perf report --no-child".
- Before:
7.26 Mpps
_raw_spin_lock 7.83%
veth_xdp_xmit 12.23%
- After:
7.94 Mpps
_raw_spin_lock 1.08%
veth_xdp_xmit 6.10%
v2:
- Use stack for bulk queue instead of a global variable.
There are several spelling mistakes in pr_warning messages. Fix these.
Signed-off-by: Colin Ian King <colin.king@canonical.com> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Michal Rostecki [Tue, 18 Jun 2019 18:13:18 +0000 (20:13 +0200)]
samples: bpf: Remove bpf_debug macro in favor of bpf_printk
ibumad example was implementing the bpf_debug macro which is exactly the
same as the bpf_printk macro available in bpf_helpers.h. This change
makes use of bpf_printk instead of bpf_debug.
Signed-off-by: Michal Rostecki <mrostecki@opensuse.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
====================
ipv6: avoid taking refcnt on dst during route lookup
Ipv6 route lookup code always grabs refcnt on the dst for the caller.
But for certain cases, grabbing refcnt is not always necessary if the
call path is rcu protected and the caller does not cache the dst.
Another issue in the route lookup logic is:
When there are multiple custom rules, we have to do the lookup into
each table associated to each rule individually. And when we can't
find the route in one table, we grab and release refcnt on
net->ipv6.ip6_null_entry before going to the next table.
This operation is completely redundant, and causes false issue because
net->ipv6.ip6_null_entry is a shared object.
This patch set introduces a new flag RT6_LOOKUP_F_DST_NOREF for route
lookup callers to set, to avoid any manipulation on the dst refcnt. And
it converts the major input and output path to use it.
The performance gain is noticable.
I ran synflood tests between 2 hosts under the same switch. Both hosts
have 20G mlx NIC, and 8 tx/rx queues.
Sender sends pure SYN flood with random src IPs and ports using trafgen.
Receiver has a simple TCP listener on the target port.
Both hosts have multiple custom rules:
- For incoming packets, only local table is traversed.
- For outgoing packets, 3 tables are traversed to find the route.
The packet processing rate on the receiver is as follows:
- Before the fix: 3.78Mpps
- After the fix: 5.50Mpps
v2->v3:
- Handled fib6_rule_lookup() when CONFIG_IPV6_MULTIPLE_TABLES is not
configured in patch 03 (suggested by David Ahern)
- Removed the renaming of l3mdev_link_scope_lookup() in patch 05
(suggested by David Ahern)
- Moved definition of ip6_route_output_flags() from an inline function
in /net/ipv6/route.c to net/ipv6/route.c in order to address kbuild
error in patch 05
v1->v2:
- Added a helper ip6_rt_put_flags() in patch 3 suggested by David Miller
====================
Reviewed-by: David Ahern <dsahern@gmail.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Wei Wang [Fri, 21 Jun 2019 00:36:41 +0000 (17:36 -0700)]
ipv6: convert major tx path to use RT6_LOOKUP_F_DST_NOREF
For tx path, in most cases, we still have to take refcnt on the dst
cause the caller is caching the dst somewhere. But it still is
beneficial to make use of RT6_LOOKUP_F_DST_NOREF flag while doing the
route lookup. It is cause this flag prevents manipulating refcnt on
net->ipv6.ip6_null_entry when doing fib6_rule_lookup() to traverse each
routing table. The null_entry is a shared object and constant updates on
it cause false sharing.
We converted the current major lookup function ip6_route_output_flags()
to make use of RT6_LOOKUP_F_DST_NOREF.
Together with the change in the rx path, we see noticable performance
boost:
I ran synflood tests between 2 hosts under the same switch. Both hosts
have 20G mlx NIC, and 8 tx/rx queues.
Sender sends pure SYN flood with random src IPs and ports using trafgen.
Receiver has a simple TCP listener on the target port.
Both hosts have multiple custom rules:
- For incoming packets, only local table is traversed.
- For outgoing packets, 3 tables are traversed to find the route.
The packet processing rate on the receiver is as follows:
- Before the fix: 3.78Mpps
- After the fix: 5.50Mpps
Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Wei Wang [Fri, 21 Jun 2019 00:36:40 +0000 (17:36 -0700)]
ipv6: convert rx data path to not take refcnt on dst
ip6_route_input() is the key function to do the route lookup in the
rx data path. All the callers to this function are already holding rcu
lock. So it is fairly easy to convert it to not take refcnt on the dst:
We pass in flag RT6_LOOKUP_F_DST_NOREF and do skb_dst_set_noref().
This saves a few atomic inc or dec operations and should boost
performance overall.
This also makes the logic more aligned with v4.
Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Mahesh Bandewar <maheshb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Wei Wang [Fri, 21 Jun 2019 00:36:39 +0000 (17:36 -0700)]
ipv6: honor RT6_LOOKUP_F_DST_NOREF in rule lookup logic
This patch specifically converts the rule lookup logic to honor this
flag and not release refcnt when traversing each rule and calling
lookup() on each routing table.
Similar to previous patch, we also need some special handling of dst
entries in uncached list because there is always 1 refcnt taken for them
even if RT6_LOOKUP_F_DST_NOREF flag is set.
Signed-off-by: Wei Wang <weiwan@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Wei Wang [Fri, 21 Jun 2019 00:36:38 +0000 (17:36 -0700)]
ipv6: initialize rt6->rt6i_uncached in all pre-allocated dst entries
Initialize rt6->rt6i_uncached on the following pre-allocated dsts:
net->ipv6.ip6_null_entry
net->ipv6.ip6_prohibit_entry
net->ipv6.ip6_blk_hole_entry
This is a preparation patch for later commits to be able to distinguish
dst entries in uncached list by doing:
!list_empty(rt6->rt6i_uncached)
Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Mahesh Bandewar <maheshb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Wei Wang [Fri, 21 Jun 2019 00:36:37 +0000 (17:36 -0700)]
ipv6: introduce RT6_LOOKUP_F_DST_NOREF flag in ip6_pol_route()
This new flag is to instruct the route lookup function to not take
refcnt on the dst entry. The user which does route lookup with this flag
must properly use rcu protection.
ip6_pol_route() is the major route lookup function for both tx and rx
path.
In this function:
Do not take refcnt on dst if RT6_LOOKUP_F_DST_NOREF flag is set, and
directly return the route entry. The caller should be holding rcu lock
when using this flag, and decide whether to take refcnt or not.
One note on the dst cache in the uncached_list:
As uncached_list does not consume refcnt, one refcnt is always returned
back to the caller even if RT6_LOOKUP_F_DST_NOREF flag is set.
Uncached dst is only possible in the output path. So in such call path,
caller MUST check if the dst is in the uncached_list before assuming
that there is no refcnt taken on the returned dst.
Signed-off-by: Wei Wang <weiwan@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Mahesh Bandewar <maheshb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Russell King [Fri, 21 Jun 2019 14:59:09 +0000 (15:59 +0100)]
doc: phy: document some PHY_INTERFACE_MODE_xxx settings
There seems to be some confusion surrounding three PHY interface modes,
specifically 1000BASE-X, 2500BASE-X and SGMII. Add some documentation
to phylib detailing precisely what these interface modes refer to.
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
Qian Cai [Thu, 20 Jun 2019 14:52:40 +0000 (10:52 -0400)]
inet: fix compilation warnings in fqdir_pre_exit()
The linux-next commit "inet: fix various use-after-free in defrags
units" [1] introduced compilation warnings,
./include/net/inet_frag.h:117:1: warning: 'inline' is not at beginning
of declaration [-Wold-style-declaration]
static void inline fqdir_pre_exit(struct fqdir *fqdir)
^~~~~~
In file included from ./include/net/netns/ipv4.h:10,
from ./include/net/net_namespace.h:20,
from ./include/linux/netdevice.h:38,
from ./include/linux/icmpv6.h:13,
from ./include/linux/ipv6.h:86,
from ./include/net/ipv6.h:12,
from ./include/rdma/ib_verbs.h:51,
from ./include/linux/mlx5/device.h:37,
from ./include/linux/mlx5/driver.h:51,
from
drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c:37:
Rasmus Villemoes [Thu, 20 Jun 2019 13:50:42 +0000 (13:50 +0000)]
net: dsa: mv88e6xxx: introduce helpers for handling chip->reg_lock
This is a no-op that simply moves all locking and unlocking of
->reg_lock into trivial helpers. I did that to be able to easily add
some ad hoc instrumentation to those helpers to get some information
on contention and hold times of the mutex. Perhaps others want to do
something similar at some point, so this frees them from doing the
'sed -i' yoga, and have a much smaller 'git diff' while fiddling.
Signed-off-by: Rasmus Villemoes <rasmus.villemoes@prevas.dk> Reviewed-by: Vivien Didelot <vivien.didelot@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Sameeh Jubran [Sun, 23 Jun 2019 07:11:10 +0000 (10:11 +0300)]
net: ena: Fix bug where ring allocation backoff stopped too late
The current code of create_queues_with_size_backoff() allows the ring size
to become as small as ENA_MIN_RING_SIZE/2. This is a bug since we don't
want the queue ring to be smaller than ENA_MIN_RING_SIZE
In this commit we change the loop's termination condition to look at the
queue size of the next iteration instead of that of the current one,
so that the minimal queue size again becomes ENA_MIN_RING_SIZE.
Fixes: eece4d2ab9d2 ("net: ena: add ethtool function for changing io queue sizes") Signed-off-by: Arthur Kiyanovski <akiyano@amazon.com> Signed-off-by: Sameeh Jubran <sameehj@amazon.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Colin Ian King [Thu, 20 Jun 2019 13:27:51 +0000 (14:27 +0100)]
hinic: fix dereference of pointer hwdev before it is null checked
Currently pointer hwdev is dereferenced when assigning hwif before
hwdev is null checked. Fix this by only derefencing hwdev after the
null check.
Addresses-Coverity: ("Dereference before null check") Fixes: 4fdc51bb4e92 ("hinic: add support for rss parameters with ethtool") Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: David S. Miller <davem@davemloft.net>
====================
net: mediatek: Add MT7621 TRGMII mode support
Like many other mediatek SOCs, the MT7621 SOC and the internal MT7530
switch both supports TRGMII mode. MT7621 TRGMII speed is fix 1200MBit.
v1->v2:
- Fix breakage on non MT7621 SOC
- Support 25MHz and 40MHz XTAL as MT7530 clocksource
====================
Tested-by: "Frank Wunderlich" <frank-w@public-files.de> Acked-by: Sean Wang <sean.wang@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: René van Dorst <opensource@vdorst.com> Tested-by: Frank Wunderlich <frank-w@public-files.de> Signed-off-by: David S. Miller <davem@davemloft.net>
Li RongQing [Thu, 20 Jun 2019 11:24:40 +0000 (19:24 +0800)]
netns: restore ops before calling ops_exit_list
ops has been iterated to first element when call pre_exit, and
it needs to restore from save_ops, not save ops to save_ops
Fixes: d7d99872c144 ("netns: add pre_exit method to struct pernet_operations") Signed-off-by: Li RongQing <lirongqing@baidu.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
fjes: no need to check return value of debugfs_create functions
When calling debugfs functions, there is no need to ever check the
return value. The function can work or not, but the code logic should
never do something different based on this.
Cc: "David S. Miller" <davem@davemloft.net> Cc: Yangtao Li <tiny.windzz@gmail.com> Cc: netdev@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Ard Biesheuvel [Wed, 19 Jun 2019 21:46:28 +0000 (23:46 +0200)]
net: fastopen: robustness and endianness fixes for SipHash
Some changes to the TCP fastopen code to make it more robust
against future changes in the choice of key/cookie size, etc.
- Instead of keeping the SipHash key in an untyped u8[] buffer
and casting it to the right type upon use, use the correct
type directly. This ensures that the key will appear at the
correct alignment if we ever change the way these data
structures are allocated. (Currently, they are only allocated
via kmalloc so they always appear at the correct alignment)
- Use DIV_ROUND_UP when sizing the u64[] array to hold the
cookie, so it is always of sufficient size, even if
TCP_FASTOPEN_COOKIE_MAX is no longer a multiple of 8.
- Drop the 'len' parameter from the tcp_fastopen_reset_cipher()
function, which is no longer used.
- Add endian swabbing when setting the keys and calculating the hash,
to ensure that cookie values are the same for a given key and
source/destination address pair regardless of the endianness of
the server.
Note that none of these are functional changes wrt the current
state of the code, with the exception of the swabbing, which only
affects big endian systems.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: David S. Miller <davem@davemloft.net>
1) Fix leak of unqueued fragments in ipv6 nf_defrag, from Guillaume
Nault.
2) Don't access the DDM interface unless the transceiver implements it
in bnx2x, from Mauro S. M. Rodrigues.
3) Don't double fetch 'len' from userspace in sock_getsockopt(), from
JingYi Hou.
4) Sign extension overflow in lio_core, from Colin Ian King.
5) Various netem bug fixes wrt. corrupted packets from Jakub Kicinski.
6) Fix epollout hang in hvsock, from Sunil Muthuswamy.
7) Fix regression in default fib6_type, from David Ahern.
8) Handle memory limits in tcp_fragment more appropriately, from Eric
Dumazet.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (24 commits)
tcp: refine memory limit test in tcp_fragment()
inet: clear num_timeout reqsk_alloc()
net: mvpp2: debugfs: Add pmap to fs dump
ipv6: Default fib6_type to RTN_UNICAST when not set
net: hns3: Fix inconsistent indenting
net/af_iucv: always register net_device notifier
net/af_iucv: build proper skbs for HiperTransport
net/af_iucv: remove GFP_DMA restriction for HiperTransport
net: dsa: mv88e6xxx: fix shift of FID bits in mv88e6185_g1_vtu_loadpurge()
hvsock: fix epollout hang from race condition
net/udp_gso: Allow TX timestamp with UDP GSO
net: netem: fix use after free and double free with packet corruption
net: netem: fix backlog accounting for corrupted GSO frames
net: lio_core: fix potential sign-extension overflow on large shift
tipc: pass tunnel dev as NULL to udp_tunnel(6)_xmit_skb
ip6_tunnel: allow not to count pkts on tstats by passing dev as NULL
ip_tunnel: allow not to count pkts on tstats by setting skb's dev to NULL
tun: wake up waitqueues after IFF_UP is set
net: remove duplicate fetch in sock_getsockopt
tipc: fix issues with early FAILOVER_MSG from peer
...
====================
PCI: let pci_disable_link_state propagate errors
Drivers like r8169 rely on pci_disable_link_state() having disabled
certain ASPM link states. If OS can't control ASPM then
pci_disable_link_state() turns into a no-op w/o informing the caller.
The driver therefore may falsely assume the respective ASPM link
states are disabled. Let pci_disable_link_state() propagate errors
to the caller, enabling the caller to react accordingly.
I'd propose to let this series go through the netdev tree if the PCI
core extension is acked by the PCI people.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 18 Jun 2019 21:14:50 +0000 (23:14 +0200)]
r8169: don't activate ASPM in chip if OS can't control ASPM
Certain chip version / board combinations have massive problems if
ASPM is active. If BIOS enables ASPM and doesn't let OS control it,
then we may have a problem with the current code. Therefore check the
return code of pci_disable_link_state() and don't enable ASPM in the
network chip if OS can't control ASPM.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Heiner Kallweit [Tue, 18 Jun 2019 21:13:48 +0000 (23:13 +0200)]
PCI: let pci_disable_link_state propagate errors
Drivers may rely on pci_disable_link_state() having disabled certain
ASPM link states. If OS can't control ASPM then pci_disable_link_state()
turns into a no-op w/o informing the caller. The driver therefore may
falsely assume the respective ASPM link states are disabled.
Let pci_disable_link_state() propagate errors to the caller, enabling
the caller to react accordingly.
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Acked-by: Bjorn Helgaas <bhelgaas@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Fri, 21 Jun 2019 13:09:55 +0000 (06:09 -0700)]
tcp: refine memory limit test in tcp_fragment()
tcp_fragment() might be called for skbs in the write queue.
Memory limits might have been exceeded because tcp_sendmsg() only
checks limits at full skb (64KB) boundaries.
Therefore, we need to make sure tcp_fragment() wont punish applications
that might have setup very low SO_SNDBUF values.
Fixes: f070ef2ac667 ("tcp: tcp_fragment() should apply sane memory limits") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Christoph Paasch <cpaasch@apple.com> Tested-by: Christoph Paasch <cpaasch@apple.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Linus Torvalds [Fri, 21 Jun 2019 21:47:09 +0000 (14:47 -0700)]
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma fixes from Doug Ledford:
"This is probably our last -rc pull request. We don't have anything
else outstanding at the moment anyway, and with the summer months on
us and people taking trips, I expect the next weeks leading up to the
merge window to be pretty calm and sedate.
This has two simple, no brainer fixes for the EFA driver.
Then it has ten not quite so simple fixes for the hfi1 driver. The
problem with them is that they aren't simply one liner typo fixes.
They're still fixes, but they're more complex issues like livelock
under heavy load where the answer was to change work queue usage and
spinlock usage to resolve the problem, or issues with orphaned
requests during certain types of failures like link down which
required some more complex work to fix too. They all look like
legitimate fixes to me, they just aren't small like I wish they were.
Summary:
- 2 minor EFA fixes
- 10 hfi1 fixes related to scaling issues"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
RDMA/efa: Handle mmap insertions overflow
RDMA/efa: Fix success return value in case of error
IB/hfi1: Handle port down properly in pio
IB/hfi1: Handle wakeup of orphaned QPs for pio
IB/hfi1: Wakeup QPs orphaned on wait list after flush
IB/hfi1: Use aborts to trigger RC throttling
IB/hfi1: Create inline to get extended headers
IB/hfi1: Silence txreq allocation warnings
IB/hfi1: Avoid hardlockup with flushlist_lock
IB/hfi1: Correct tid qp rcd to match verbs context
IB/hfi1: Close PSM sdma_progress sleep window
IB/hfi1: Validate fault injection opcode user input
Linus Torvalds [Fri, 21 Jun 2019 20:45:41 +0000 (13:45 -0700)]
Merge tag 'nfs-for-5.2-3' of git://git.linux-nfs.org/projects/anna/linux-nfs
Pull more NFS client fixes from Anna Schumaker:
"These are mostly refcounting issues that people have found recently.
The revert fixes a suspend recovery performance issue.
- SUNRPC: Fix a credential refcount leak
- Revert "SUNRPC: Declare RPC timers as TIMER_DEFERRABLE"
- SUNRPC: Fix xps refcount imbalance on the error path
- NFS4: Only set creation opendata if O_CREAT"
* tag 'nfs-for-5.2-3' of git://git.linux-nfs.org/projects/anna/linux-nfs:
SUNRPC: Fix a credential refcount leak
Revert "SUNRPC: Declare RPC timers as TIMER_DEFERRABLE"
net :sunrpc :clnt :Fix xps refcount imbalance on the error path
NFS4: Only set creation opendata if O_CREAT
Andy Lutomirski [Fri, 21 Jun 2019 15:43:04 +0000 (08:43 -0700)]
x86/vdso: Prevent segfaults due to hoisted vclock reads
GCC 5.5.0 sometimes cleverly hoists reads of the pvclock and/or hvclock
pages before the vclock mode checks. This creates a path through
vclock_gettime() in which no vclock is enabled at all (due to disabled
TSC on old CPUs, for example) but the pvclock or hvclock page
nevertheless read. This will segfault on bare metal.
This fixes commit 459e3a21535a ("gcc-9: properly declare the
{pv,hv}clock_page storage") in the sense that, before that commit, GCC
didn't seem to generate the offending code. There was nothing wrong
with that commit per se, and -stable maintainers should backport this to
all supported kernels regardless of whether the offending commit was
present, since the same crash could just as easily be triggered by the
phase of the moon.
On GCC 9.1.1, this doesn't seem to affect the generated code at all, so
I'm not too concerned about performance regressions from this fix.
Trond Myklebust [Thu, 20 Jun 2019 14:47:40 +0000 (10:47 -0400)]
SUNRPC: Fix a credential refcount leak
All callers of __rpc_clone_client() pass in a value for args->cred,
meaning that the credential gets assigned and referenced in
the call to rpc_new_client().
Reported-by: Ido Schimmel <idosch@idosch.org> Fixes: 79caa5fad47c ("SUNRPC: Cache cred of process creating the rpc_client") Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com> Tested-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Anna Schumaker [Tue, 18 Jun 2019 18:57:33 +0000 (14:57 -0400)]
Revert "SUNRPC: Declare RPC timers as TIMER_DEFERRABLE"
Jon Hunter reports:
"I have been noticing intermittent failures with a system suspend test on
some of our machines that have a NFS mounted root file-system. Bisecting
this issue points to your commit 431235818bc3 ("SUNRPC: Declare RPC
timers as TIMER_DEFERRABLE") and reverting this on top of v5.2-rc3 does
appear to resolve the problem.
The cause of the suspend failure appears to be a long delay observed
sometimes when resuming from suspend, and this is causing our test to
timeout."
We can end up in nfs4_opendata_alloc during task exit, in which case
current->fs has already been cleaned up. This leads to a crash in
current_umask().
Fix this by only setting creation opendata if we are actually doing an open
with O_CREAT. We can drop the check for NULL nfs4_open_createattrs, since
O_CREAT will never be set for the recovery path.
Suggested-by: Trond Myklebust <trondmy@hammerspace.com> Signed-off-by: Benjamin Coddington <bcodding@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Linus Torvalds [Fri, 21 Jun 2019 18:03:33 +0000 (11:03 -0700)]
Merge tag 'drm-fixes-2019-06-21' of git://anongit.freedesktop.org/drm/drm
Pull drm fixes from Dave Airlie:
"Just catching up on the week since back from holidays, everything
seems quite sane.
core:
- copy_to_user fix for really legacy codepaths.
vmwgfx:
- two dma fixes
- one virt hw interaction fix
i915:
- modesetting fix
- gvt fix
panfrost:
- BO unmapping fix
imx:
- image converter fixes"
* tag 'drm-fixes-2019-06-21' of git://anongit.freedesktop.org/drm/drm:
drm/i915: Don't clobber M/N values during fastset check
drm: return -EFAULT if copy_to_user() fails
drm/panfrost: Make sure a BO is only unmapped when appropriate
drm/i915/gvt: ignore unexpected pvinfo write
gpu: ipu-v3: image-convert: Fix image downsize coefficients
gpu: ipu-v3: image-convert: Fix input bytesperline for packed formats
gpu: ipu-v3: image-convert: Fix input bytesperline width/height align
drm/vmwgfx: fix a warning due to missing dma_parms
drm/vmwgfx: Honor the sg list segment size limitation
drm/vmwgfx: Use the backdoor port if the HB port is not available
Linus Torvalds [Fri, 21 Jun 2019 17:20:19 +0000 (10:20 -0700)]
Merge tag 'staging-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging
Pull staging/IIO/counter fixes from Greg KH:
"Here are some small driver bugfixes for some staging/iio/counter
drivers.
Staging and IIO have been lumped together for a while, as those
subsystems cross the areas a log, and counter is used by IIO, so
that's why they are all in one pull request here.
These are small fixes for reported issues in some iio drivers, the
erofs filesystem, and a build issue for counter code.
All have been in linux-next with no reported issues"
* tag 'staging-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging:
staging: erofs: add requirements field in superblock
counter/ftm-quaddec: Add missing dependencies in Kconfig
staging: iio: adt7316: Fix build errors when GPIOLIB is not set
iio: temperature: mlx90632 Relax the compatibility check
iio: imu: st_lsm6dsx: fix PM support for st_lsm6dsx i2c controller
staging:iio:ad7150: fix threshold mode config bit
All of these have been in linux-next with no reported issues"
* tag 'char-misc-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
habanalabs: use u64_to_user_ptr() for reading user pointers
doc: fix documentation about UIO_MEM_LOGICAL using
MAINTAINERS / Documentation: Thorsten Scherer is the successor of Gavin Schenk
docs: fb: Add TER16x32 to the available font names
MAINTAINERS: fpga: hand off maintainership to Moritz
thunderbolt: Implement CIO reset correctly for Titan Ridge
binder: fix possible UAF when freeing buffer
thunderbolt: Make sure device runtime resume completes before taking domain lock
soundwire: intel: set dai min and max channels correctly
soundwire: stream: fix bad unlock balance
soundwire: stream: fix out of boundary access on port properties
Linus Torvalds [Fri, 21 Jun 2019 17:16:41 +0000 (10:16 -0700)]
Merge tag 'usb-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb
Pull USB fixes from Greg KH:
"Here are four small USB fixes for 5.2-rc6.
They include two xhci bugfixes, a chipidea fix, and a small dwc2 fix.
Nothing major, just nice things to get resolved for reported issues.
All have been in linux-next with no reported issues"
* tag 'usb-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
xhci: detect USB 3.2 capable host controllers correctly
usb: xhci: Don't try to recover an endpoint if port is in error state.
usb: dwc2: Use generic PHY width in params setup
usb: chipidea: udc: workaround for endpoint conflict issue
Linus Torvalds [Fri, 21 Jun 2019 16:58:42 +0000 (09:58 -0700)]
Merge tag 'spdx-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/spdx
Pull still more SPDX updates from Greg KH:
"Another round of SPDX updates for 5.2-rc6
Here is what I am guessing is going to be the last "big" SPDX update
for 5.2. It contains all of the remaining GPLv2 and GPLv2+ updates
that were "easy" to determine by pattern matching. The ones after this
are going to be a bit more difficult and the people on the spdx list
will be discussing them on a case-by-case basis now.
Another 5000+ files are fixed up, so our overall totals are:
Files checked: 64545
Files with SPDX: 45529
Compared to the 5.1 kernel which was:
Files checked: 63848
Files with SPDX: 22576
This is a huge improvement.
Also, we deleted another 20000 lines of boilerplate license crud,
always nice to see in a diffstat"
* tag 'spdx-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/spdx: (65 commits)
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 507
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 506
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 505
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 504
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 503
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 502
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 501
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 500
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 499
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 498
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 497
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 496
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 495
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 491
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 490
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 489
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 488
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 487
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 486
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 485
...
Linus Torvalds [Fri, 21 Jun 2019 16:51:44 +0000 (09:51 -0700)]
Merge tag '5.2-rc5-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6
Pull cifs fixes from Steve French:
"Four small SMB3 fixes, all for stable"
* tag '5.2-rc5-smb3-fixes' of git://git.samba.org/sfrench/cifs-2.6:
cifs: fix GlobalMid_Lock bug in cifs_reconnect
SMB3: retry on STATUS_INSUFFICIENT_RESOURCES instead of failing write
cifs: add spinlock for the openFileList to cifsInodeInfo
cifs: fix panic in smb2_reconnect
Dave Airlie [Fri, 21 Jun 2019 01:44:20 +0000 (11:44 +1000)]
Merge tag 'imx-drm-fixes-2019-06-20' of git://git.pengutronix.de/git/pza/linux into drm-fixes
drm/imx: ipu-v3 image converter fixes
This series fixes input buffer alignment and downsizer configuration
to adhere to IPU mem2mem CSC/scaler hardware restrictions in certain
downscaling ratios.
Dave Airlie [Fri, 21 Jun 2019 01:26:59 +0000 (11:26 +1000)]
Merge branch 'vmwgfx-fixes-5.2' of git://people.freedesktop.org/~thomash/linux into drm-fixes
A couple of fixes for vmwgfx. Two fixes for a DMA sg-list debug warning
message. These are not cc'd stable since there is no evidence of actual
breakage.
On fix for the high-bandwidth backdoor port which is cc'd stable due to
upcoming hardware, on which the code would otherwise break.
ARM: 8867/1: vdso: pass --be8 to linker if necessary
The commit fe00e50b2db8 ("ARM: 8858/1: vdso: use $(LD) instead of $(CC)
to link VDSO") removed the passing of CFLAGS, since ld doesn't take
those directly. However, prior, big-endian ARM was relying on gcc to
translate its -mbe8 option into ld's --be8 option. Lacking this, ld
generated be32 code, making the VDSO generate SIGILL when called by
userspace.
This commit passes --be8 if CONFIG_CPU_ENDIAN_BE8 is enabled.
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Linus Torvalds [Thu, 20 Jun 2019 21:19:34 +0000 (14:19 -0700)]
Merge tag 'ovl-fixes-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs
Pull overlayfs fixes from Miklos Szeredi:
"Fix two regressions in this cycle, and a couple of older bugs"
* tag 'ovl-fixes-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
ovl: make i_ino consistent with st_ino in more cases
ovl: fix typo in MODULE_PARM_DESC
ovl: fix bogus -Wmaybe-unitialized warning
ovl: don't fail with disconnected lower NFS
ovl: fix wrong flags check in FS_IOC_FS[SG]ETXATTR ioctls
Linus Torvalds [Thu, 20 Jun 2019 21:16:16 +0000 (14:16 -0700)]
Merge tag 'fuse-fixes-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse
Pull fuse fix from Miklos Szeredi:
"Just a single revert, fixing a regression in -rc1"
* tag 'fuse-fixes-5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:
Revert "fuse: require /dev/fuse reads to have enough buffer capacity"
Linus Torvalds [Thu, 20 Jun 2019 20:50:37 +0000 (13:50 -0700)]
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm fixes from Paolo Bonzini:
"Fixes for ARM and x86, plus selftest patches and nicer structs for
nested state save/restore"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: nVMX: reorganize initial steps of vmx_set_nested_state
KVM: arm/arm64: Fix emulated ptimer irq injection
tests: kvm: Check for a kernel warning
kvm: tests: Sort tests in the Makefile alphabetically
KVM: x86/mmu: Allocate PAE root array when using SVM's 32-bit NPT
KVM: x86: Modify struct kvm_nested_state to have explicit fields for data
KVM: fix typo in documentation
KVM: nVMX: use correct clean fields when copying from eVMCS
KVM: arm/arm64: vgic: Fix kvm_device leak in vgic_its_destroy
KVM: arm64: Filter out invalid core register IDs in KVM_GET_REG_LIST
KVM: arm64: Implement vq_present() as a macro
Linus Torvalds [Thu, 20 Jun 2019 19:04:57 +0000 (12:04 -0700)]
Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 fixes from Will Deacon:
"This is mainly a couple of email address updates to MAINTAINERS, but
we've also fixed a UAPI build issue with musl libc and an accidental
double-initialisation of our pgd_cache due to a naming conflict with a
weak symbol.
There are a couple of outstanding issues that have been reported, but
it doesn't look like they're new and we're still a long way off from
fully debugging them.
Summary:
- Fix use of #include in UAPI headers for compatability with musl libc
- Update email addresses in MAINTAINERS
- Fix initialisation of pgd_cache due to name collision with weak symbol"
* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
arm64/mm: don't initialize pgd_cache twice
MAINTAINERS: Update my email address
arm64/sve: <uapi/asm/ptrace.h> should not depend on <uapi/linux/prctl.h>
arm64: ssbd: explicitly depend on <linux/prctl.h>
MAINTAINERS: Update my email address to use @kernel.org
Linus Torvalds [Thu, 20 Jun 2019 19:03:41 +0000 (12:03 -0700)]
Merge tag 's390-5.2-5' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux
Pull s390 fixes from Heiko Carstens:
- Disable address-of-packed-member warning in s390 specific boot code
to get rid of a gcc9 warning which otherwise is already disabled for
the whole kernel.
- Fix yet another compiler error seen with CONFIG_OPTIMIZE_INLINING
enabled.
- Fix memory leak in vfio-ccw code on module exit.
* tag 's390-5.2-5' of git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux:
vfio-ccw: Destroy kmem cache region on module exit
s390/ctl_reg: mark __ctl_set_bit and __ctl_clear_bit as __always_inline
s390/boot: disable address-of-packed-member warning
Linus Torvalds [Thu, 20 Jun 2019 17:12:53 +0000 (10:12 -0700)]
Merge tag 'for_v5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs
Pull two misc vfs fixes from Jan Kara:
"One small quota fix fixing spurious EDQUOT errors and one fanotify fix
fixing a bug in the new fanotify FID reporting code"
* tag 'for_v5.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/jack/linux-fs:
fanotify: update connector fsid cache on add mark
quota: fix a problem about transfer quota
Linus Torvalds [Thu, 20 Jun 2019 17:08:38 +0000 (10:08 -0700)]
Merge tag 'mmc-v5.2-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc
Pull MMC fixes from Ulf Hansson:
"Here's quite a few MMC fixes intended for v5.2-rc6. This time it also
contains fixes for a WiFi driver, which device is attached to the SDIO
interface. Patches for the WiFi driver have been acked by the
corresponding maintainers.
Summary:
MMC core:
- Make switch to eMMC HS400 more robust for some controllers
- Add two SDIO func API to manage re-tuning constraints
- Prevent processing SDIO IRQs when the card is suspended
MMC host:
- sdhi: Disallow broken HS400 for M3-W ES1.2, RZ/G2M and V3H
- mtk-sd: Fixup support for SDIO IRQs
- sdhci-pci-o2micro: Fixup support for tuning
Wireless BRCMFMAC (SDIO):
- Deal with expected transmission errors related to the idle states
(handled by the Always-On-Subsystem or AOS) on the SDIO-based WiFi
on rk3288-veyron-minnie, rk3288-veyron-speedy and
rk3288-veyron-mickey"
* tag 'mmc-v5.2-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc:
mmc: core: Prevent processing SDIO IRQs when the card is suspended
mmc: sdhci: sdhci-pci-o2micro: Correctly set bus width when tuning
brcmfmac: sdio: Don't tune while the card is off
mmc: core: Add sdio_retune_hold_now() and sdio_retune_release()
brcmfmac: sdio: Disable auto-tuning around commands expected to fail
mmc: core: API to temporarily disable retuning for SDIO CRC errors
Revert "brcmfmac: disable command decode in sdio_aos"
mmc: mediatek: fix SDIO IRQ detection issue
mmc: mediatek: fix SDIO IRQ interrupt handle flow
mmc: core: complete HS400 before checking status
mmc: sdhi: disallow HS400 for M3-W ES1.2, RZ/G2M, and V3H
projects / mirror_ubuntu-kernels.git / log