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>
Provide user documentation about sockopt prog type and cgroup hooks.
v9:
* add details about setsockopt context and inheritance
v7:
* add description for retval=0 and optlen=-1
v6:
* describe cgroup chaining, add example
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>
sockopt test that verifies chaining behavior.
v9:
* setsockopt chaining example
v7:
* rework the test to verify cgroup getsockopt chaining
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>
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>
Add tests that make sure libbpf section detection works.
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>
Make libbpf aware of new sockopt hooks so it can derive prog type
and hook point from the section names.
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>
Export new prog type and hook points to the libbpf.
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>
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
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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 ab966d7e4f ("net/mlx5e: RX, Recycle buffer of
UMR WQEs") is reverted.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
The PCI API for DMA is deprecated, and PCI_DMA_TODEVICE is just defined
to DMA_TO_DEVICE for backward compatibility. Just use DMA_TO_DEVICE.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
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>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Query XDP_OPTIONS in libbpf to determine if the zero-copy mode is active
or not.
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>
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.
Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Since commit 4bfc0bb2c6 ("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: 4bfc0bb2c6 ("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>
From: Tal Gilboa and Yamin Fridman
Implement net DIM over a generic DIM library, add RDMA DIM
dim.h lib exposes an implementation of the DIM algorithm for
dynamically-tuned interrupt moderation for networking interfaces.
We want a similar functionality for other protocols, which might need to
optimize interrupts differently. Main motivation here is DIM for NVMf
storage protocol.
Current DIM implementation prioritizes reducing interrupt overhead over
latency. Also, in order to reduce DIM's own overhead, the algorithm might
take some time to identify it needs to change profiles. While this is
acceptable for networking, it might not work well on other scenarios.
Here we propose a new structure to DIM. The idea is to allow a slightly
modified functionality without the risk of breaking Net DIM behavior for
netdev. We verified there are no degradations in current DIM behavior with
the modified solution.
Suggested solution:
- Common logic is implemented in lib/dim/dim.c
- Net DIM (existing) logic is implemented in lib/dim/net_dim.c, which uses
the common logic in dim.c
- Any new DIM logic will be implemented in "lib/dim/new_dim.c".
This new implementation will expose modified versions of profiles,
dim_step() and dim_decision().
- DIM API is declared in include/linux/dim.h for all implementations.
Pros for this solution are:
- Zero impact on existing net_dim implementation and usage
- Relatively more code reuse (compared to two separate solutions)
- Increased extensibility
-----BEGIN PGP SIGNATURE-----
iQEzBAABCAAdFiEEGhZs6bAKwk/OTgTpSD+KveBX+j4FAl0SiDAACgkQSD+KveBX
+j4mlQgAoabbtxwIapMg62tKhnlr/3hEEyuEjiQRhzMUb5y5zOIJNRL82Nerv4K3
oD7v76emw/Xb1ErPe4yJJRdkpbpabEAFKbqkM0R7xFPNK33ZbphlU1d9YGgUKp1W
Uieydn5kfubzi6p7R1TC7c2qW1Wr6rE1wnNJyC/sy8zFEP/OEH0NmgPDyOs7ckWI
xaoJ1lhNWMoGN+Qk+fxazd1VtsKdcbc9JvLD2e8ON5qWdnuNiLhawcJVoWzfsCAa
V/Tdff+Rj9bVFsi468u20og4EdV3ceAOTzMnhCYpAtYZHVbVk6MFgh87uQYkTrfY
sW8BDmWKkRdHtzHd3a3yQiVDnz/iuw==
=bAZn
-----END PGP SIGNATURE-----
Merge tag 'blk-dim-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux
Saeed Mamameed says:
====================
Generic DIM
From: Tal Gilboa and Yamin Fridman
Implement net DIM over a generic DIM library, add RDMA DIM
dim.h lib exposes an implementation of the DIM algorithm for
dynamically-tuned interrupt moderation for networking interfaces.
We want a similar functionality for other protocols, which might need to
optimize interrupts differently. Main motivation here is DIM for NVMf
storage protocol.
Current DIM implementation prioritizes reducing interrupt overhead over
latency. Also, in order to reduce DIM's own overhead, the algorithm might
take some time to identify it needs to change profiles. While this is
acceptable for networking, it might not work well on other scenarios.
Here we propose a new structure to DIM. The idea is to allow a slightly
modified functionality without the risk of breaking Net DIM behavior for
netdev. We verified there are no degradations in current DIM behavior with
the modified solution.
Suggested solution:
- Common logic is implemented in lib/dim/dim.c
- Net DIM (existing) logic is implemented in lib/dim/net_dim.c, which uses
the common logic in dim.c
- Any new DIM logic will be implemented in "lib/dim/new_dim.c".
This new implementation will expose modified versions of profiles,
dim_step() and dim_decision().
- DIM API is declared in include/linux/dim.h for all implementations.
Pros for this solution are:
- Zero impact on existing net_dim implementation and usage
- Relatively more code reuse (compared to two separate solutions)
- Increased extensibility
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The QCA8337(N) has a RESETn signal on Pin B42 that
triggers a chip reset if the line is pulled low.
The datasheet says that: "The active low duration
must be greater than 10 ms".
This can hopefully fix some of the issues related
to pin strapping in OpenWrt for the EA8500 which
suffers from detection issues after a SoC reset.
Please note that the qca8k_probe() function does
currently require to read the chip's revision
register for identification purposes.
Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch documents the qca8k's reset-gpios property that
can be used if the QCA8337N ends up in a bad state during
reset.
Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Gateway validation does not need a dst_entry, it only needs the fib
entry to validate the gateway resolution and egress device. So,
convert ip6_nh_lookup_table from ip6_pol_route to fib6_table_lookup
and ip6_route_check_nh to use fib6_lookup over rt6_lookup.
ip6_pol_route is a call to fib6_table_lookup and if successful a call
to fib6_select_path. From there the exception cache is searched for an
entry or a dst_entry is created to return to the caller. The exception
entry is not relevant for gateway validation, so what matters are the
calls to fib6_table_lookup and then fib6_select_path.
Similarly, rt6_lookup can be replaced with a call to fib6_lookup with
RT6_LOOKUP_F_IFACE set in flags. Again, the exception cache search is
not relevant, only the lookup with path selection. The primary difference
in the lookup paths is the use of rt6_select with fib6_lookup versus
rt6_device_match with rt6_lookup. When you remove complexities in the
rt6_select path, e.g.,
1. saddr is not set for gateway validation, so RT6_LOOKUP_F_HAS_SADDR
is not relevant
2. rt6_check_neigh is not called so that removes the RT6_NUD_FAIL_DO_RR
return and round-robin logic.
the code paths are believed to be equivalent for the given use case -
validate the gateway and optionally given the device. Furthermore, it
aligns the validation with onlink code path and the lookup path actually
used for rx and tx.
Adjust the users, ip6_route_check_nh_onlink and ip6_route_check_nh to
handle a fib6_info vs a rt6_info when performing validation checks.
Existing selftests fib-onlink-tests.sh and fib_tests.sh are used to
verify the changes.
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Vladimir Oltean says:
====================
FDB, VLAN and PTP fixes for SJA1105 DSA
This patchset is an assortment of fixes for the net-next version of the
sja1105 DSA driver:
- Avoid a kernel panic when the driver fails to probe or unregisters
- Finish Arnd Bermann's idea of compiling PTP support as part of the
main DSA driver and not separately
- Better handling of initial port-based VLAN as well as VLANs for
dsa_8021q FDB entries
- Fix address learning for the SJA1105 P/Q/R/S family
- Make static FDB entries persistent across switch resets
- Fix reporting of statically-added FDB entries in 'bridge fdb show'
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
The first generation switches don't tell us through the dynamic config
interface whether the dumped FDB entries are static or not (the LOCKEDS
bit from P/Q/R/S).
However, now that we're keeping a mirror of all 'bridge fdb' commands in
the static config, this is an opportunity to compare a dumped FDB entry
to the driver's private database. After all, what makes an entry static
is that *we* added it.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A FDB entry means that "frames that match this VID and DMAC must be
forwarded to this port".
In the case of dsa_8021q however, the VID is not a single one (and
neither two, as my previous patch assumed). The VID can be set either by
the CPU port (1 tx_vid), or by any of the other front-panel port (n-1
rx_vid's).
Fixes: 93647594d8 ("net: dsa: sja1105: Hide the dsa_8021q VLANs from the bridge fdb command")
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The reason why this wasn't tackled earlier is that I had hoped I
understood the user manual wrong. But unfortunately hacks are required
in order to retrieve the static/dynamic nature of FDB entries on SJA1105
P/Q/R/S, since this info is stored in the writeback buffer of the
dynamic config command.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When trying to add support for LOCKEDS (static FDB entries) on SJA1105
P/Q/R/S, at first I didn't remember how the abstraction I created
worked, and actually thought it works by mistake.
To avoid other people staring at the code and not making much sense out
of it, add some comments at the top of the file.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 8456721dd4 ("net: dsa: sja1105: Add support for
configuring address ageing time"), we started to reset the switch rather
often (each time the bridge core changes the ageing time on a switch
port).
The unfortunate reality is that SJA1105 doesn't have any {cold, warm,
whatever} reset mode in which it accepts a new configuration stream
without flushing the FDB. Instead, in its world, the FDB *is* an
optional part of the static configuration.
So we play its game, and do what we also do for VLANs: for each 'bridge
fdb' command, we add the FDB entry through the dynamic interface, and we
append the in-kernel static config memory with info that we're going to
use later, when the next reset command is going to be issued.
The result is that 'bridge fdb' commands are now persistent (dynamically
learned entries are lost, but that's ok).
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
At the end of the commit 1da7382134 ("net: dsa: sja1105: Add FDB
operations for P/Q/R/S series") message, I said that:
At the moment only FDB entries installed statically through 'bridge fdb'
are visible in the dump callback - the dynamically learned ones are
still under investigation.
It looks like the reason why they were not visible in 'bridge fdb' was
that they were never learned - always flooded.
SJA1105 P/Q/R/S manual says about the MAXADDRP[port] field:
Specify the maximum number of MAC address dynamically learned from
the respective port. It is used to limit the number of learned MAC
addresses per port.
It looks like not providing a value in the static config (aka providing
zeroes) is enough for it to not store the learned addresses in the FDB.
For now we divide the 1024 entry FDB "equally" amongst the 5 ports. This
may be revisited if the situation calls for that - for now I'm happy
that learning works.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 1da7382134 ("net: dsa: sja1105: Add FDB operations for
P/Q/R/S series"), these bits were set in the static config, but
apparently they did not do anything. The reason is that the packing
accessors for them were part of a patch I forgot to send.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In SJA1105 there is no concept of 'default values' per se, everything
needs to be driver-supplied through the static configuration tables.
The issue is that the hardware manual says that 'at least the default
untagging VLAN' is mandatory to be provided through the static config.
But VLAN 0 isn't a very good initial pvid - its use is reserved for
priority-tagged frames, and the layers of the stack that care about
those already make sure that this VLAN is installed, as can be seen in
the message below:
8021q: adding VLAN 0 to HW filter on device swp2
So change the pvid provided through the static configuration to 1, which
matches the bridge core's defaults.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
As Arnd Bergmann pointed out in commit 78fe8a28fb ("net: dsa: sja1105:
fix ptp link error"), there is no point in having PTP support as a
separate loadable kernel module.
So remove the exported symbols and make sja1105.ko contain PTP support
or not based on CONFIG_NET_DSA_SJA1105_PTP.
Signed-off-by: Vladimir Oltean <olteanv@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Marek Vasut says:
====================
net: dsa: microchip: Convert to regmap
This patchset converts KSZ9477 switch driver to regmap.
This was tested with extra patches on KSZ8795. This was also tested
on KSZ9477 on Microchip KSZ9477EVB board, which I now have.
====================
Signed-off-by: Marek Vasut <marex@denx.de>
Regmap provides bit manipulation functions to set/clear bits, use those
insted of reimplementing them.
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The regmap config tables are rather similar for various generations of
the KSZ8xxx/KSZ9xxx switches. Introduce a macro which allows generating
those tables without duplication. Note that $regalign parameter is not
used right now, but will be used in KSZ87xx series switches.
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since the driver now uses regmap , get rid of ad-hoc ksz_io_ops
abstraction, which no longer has any meaning. Moreover, since regmap
has it's own locking, get rid of the register access mutex.
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add basic SPI regmap support into the driver.
Previous patches unconver that ksz_spi_write() is always ever called
with len = 1, 2 or 4. We can thus drop the if (len > SPI_TX_BUF_LEN)
check and we can also drop the allocation of the txbuf which is part
of the driver data and wastes 256 bytes for no reason. Regmap covers
the whole thing now.
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Factor out the code which sends out the register read/write opcodes
to the switch, since the code differs in single bit between read and
write.
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
The indirect function call to dev->dev_ops->get_port_addr() is expensive
especially if called for every single register access, and only returns
the value of PORT_CTRL_ADDR() macro. Use PORT_CTRL_ADDR() macro directly
instead.
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These functions are only used by the KSZ9477 code, move them from
the header into that code. Note that these functions will be soon
replaced by regmap equivalents.
Signed-off-by: Marek Vasut <marex@denx.de>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Tristram Ha <Tristram.Ha@microchip.com>
Cc: Woojung Huh <Woojung.Huh@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stanislav Fomichev