| Age | Commit message (Collapse) | Author |
|---|
|
XSkFQ refill is pretty generic across the drivers minus FQ descriptor
filling and can easily be unified with one inline callback.
XSk wakeup is usually not, but here, instead of commonly used
"SW interrupts", I picked firing an IPI. In most tests, it showed better
performance; it also provides better control for userspace on which CPU
will handle the xmit, as SW interrupts honor IRQ affinity no matter
which core produces XSk xmit descs (while XDPSQs are associated 1:1
with cores having the same ID).
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add XSk counterparts for preparing XSk &libeth_xdp_buff (adding head and
frags), running the program, and handling the verdict, inc. XDP_PASS.
Shortcuts in comparison with regular Rx: frags and all verdicts except
XDP_REDIRECT are under unlikely() and out of line; no checks for XDP
program presence as it's always true for XSk.
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # optimizations
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Reuse core sending functions to send XSk xmit frames.
Both metadata and no metadata pools/driver are supported. libeth_xdp
also provides generic XSk metadata ops, currently with the checksum
offload only and for cases when HW doesn't require supplying L3/L4
checksum offsets. Drivers are free to pass their own ops.
&libeth_xdp_tx_bulk is not used here as it would be redundant;
pool->tx_descs are accessed directly.
Fake "libeth_xsktmo" is needed to hide implementation details from the
drivers when they want to use the generic ops: the original struct is
defined in the same file where dev->xsk_tx_metadata_ops gets set to
avoid duplication of slowpath; at the same time; XSk xmit functions
use local "fast" copy to inline XMO callbacks.
Tx descriptor filling loop is unrolled by 8.
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # optimizations
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add Xsk counterparts for XDP_TX buffer sending and completion.
The same base structures and functions used from the libeth_xdp core,
with adjustments to that XSk Rx always operates on &xdp_buff_xsk for
both head and frags. And unlike regular Rx, here unlikely() are used
for frags, as the header split gives no benefits for XSk Rx, at
least for now.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
End the XDP section by adding helpers to setup XDP features, flipping
.ndo_xdp_xmit() support at runtime (in case when it's not always on),
and calculating the queue clean/refill threshold.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Running a prog and handling the verdicts, up to napi_gro_receive()
is also pretty generic code not really differing between vendors
(except for Tx descriptor filling and Rx descriptor parsing).
Define a couple inlines to do that. The inline callbacks a driver
needs to pass is mentioned above: Tx descriptor filling for XDP_TX,
populating skb with the descriptor data for XDP_PASS, finalizing
XDPSQs after the polling loop for XDP_TX (kicking the HW to start
sending).
The populate callback passes only &libeth_xdp_buff assuming buff::desc
pointer is enough, plus you can always get the corresponding Rx queue
structure via container_of(buff::rxq). If not, a driver can extend
the buff with more fields directly on the stack without touching
libeth_xdp definitions.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add convenience helpers to build an &xdp_buff. This means: general
initialization before the NAPI loop, adding head, adding frags etc.
libeth_xdp_process_buff() is the same what everybody have in their
drivers:
dma_sync_for_cpu();
if (!frag) {
add_head();
prefetch();
} else {
add_frag();
}
Note that I don't use net_prefetch(), sticking to the original
prefetch(). In none of my tests prefetching 128 bytes yielded better
perf than 64 bytes. That might differ if the headers are huge enough,
but then additional tunneling etc. overhead takes place, you either
way won't win a lot.
&libeth_xdp_stash is for cases when you exit the polling loop without
finishing building the buff. If that happens, you need to store the
buffer in the queue structure until the next loop and then restore it.
It makes no sense to place a whole full &xdp_buff there. Define a
minimal structure, which would store only the fields essential to
restore it.
I was able to pack it into 16 bytes, which is only 8 bytes bigger
than `struct sk_buff *skb` on x64.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
When XDP Tx queues are not interrupt-driven but use lazy cleaning,
i.e. only when there are less than `threshold` free descriptors left,
we also need cleanup timers to avoid &xdp_buff and &xdp_frame stall
for too long, especially with Page Pool (it warns every about inflight
pages every 60 second).
Let's say we sent 256 frames and don't need to send more, but we clean
only when the number of pending items >= 384. In that case, those 256
will stall until 128 more are sent. For this, add simple helpers to
run a timer which will clean the queue regardless, after 1 second of
the last send.
The timer is triggered when finalizing the queue. As long as there is
regular active traffic, the timer doesn't fire.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Unfortunately, it's not always possible to allocate
max(num_rxqs, nr_cpu_ids) even on hi-end NICs.
To mitigate this, add simple locking helpers to libeth_xdp.
As long as XDPSQs are not shared, the whole functionality is gated
behind a static lock. Otherwise, each bulk flush locks the queue for
the time of cleaning and filling the descriptors.
As long as this particular queue is not used by more than 1 CPU,
the impact is minimal (runtime check for boolean twice per 16+
descriptors).
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # static key
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Similarly to libeth_tx_complete(), add libeth_xdp_complete_tx() to
handle XDP_TX and xmit buffers. Both use bulk return under the hood.
Also add out of line libeth_tx_complete_any() which handles both
regular and XDP frames (if libeth_xdp is loaded), for example,
to call on queue destroy, where we don't need inlining but
convenience.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Add helpers for implementing .ndo_xdp_xmit().
Same as for XDP_TX, accumulate up to 16 DMA-mapped frames on the stack,
then flush. If DMA mapping is failed for some reason, don't try mapping
further frames, but still flush what was already prepared.
DMA address of a head frame is stored in its headroom, assuming it
has enough of it for an 8 (or 4) byte value.
In addition to @prep and @xmit driver callbacks in XDP_TX, xmit also
needs @finalize to kick the XDPSQ after filling.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Start adding XDP-specific code to libeth, namely handling XDP_TX buffers
(only sending).
The idea is that we accumulate up to 16 buffers on the stack, then,
if either the limit is reached or the polling is finished, flush them
at once with only one XDPSQ cleaning (if needed). The main sending
function will be aware of the sending budget and already have all the
info to send the buffers, so it can't fail.
Drivers need to provide 2 inline callbacks to the main sending function:
for cleaning an XDPSQ and for filling descriptors; the library code
takes care of the rest.
Note that unlike the generic code, multi-buffer support is not wrapped
here with unlikely() to not hurt header split setups.
&libeth_xdp_buff is a simple extension over &xdp_buff which has a direct
pointer to the corresponding Rx descriptor (and, luckily, precisely 1 CL
size and 16-byte alignment on x86_64).
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> # xmit logic
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Expand libeth's Page Pool functionality by adding native XDP support.
This means picking the appropriate headroom and DMA direction.
Also, register all the created &page_pools as XDP memory models.
A driver then can call xdp_rxq_info_attach_page_pool() when registering
its RxQ info.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Back when the libeth Rx core was initially written, devmem was a draft
and netmem_ref didn't exist in the mainline. Now that it's here, make
libeth MP-agnostic before introducing any new code or any new library
users.
When it's known that the created PP/FQ is for header buffers, use faster
"unsafe" underscored netmem <--> virt accessors as netmem_is_net_iov()
is always false in that case, but consumes some cycles (bit test +
true branch).
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Change EXPORT_SYMBOL_NS_GPL(x, "LIBETH") to EXPORT_SYMBOL_GPL(x) +
DEFAULT_SYMBOL_NAMESPACE "LIBETH" to make the code more compact.
Also, explicitly include <linux/export.h> to satisfy new
requirements from scripts/misc-check.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Clean up the existing export namespace code along the same lines of
commit 33def8498fdd ("treewide: Convert macro and uses of __section(foo)
to __section("foo")") and for the same reason, it is not desired for the
namespace argument to be a macro expansion itself.
Scripted using
git grep -l -e MODULE_IMPORT_NS -e EXPORT_SYMBOL_NS | while read file;
do
awk -i inplace '
/^#define EXPORT_SYMBOL_NS/ {
gsub(/__stringify\(ns\)/, "ns");
print;
next;
}
/^#define MODULE_IMPORT_NS/ {
gsub(/__stringify\(ns\)/, "ns");
print;
next;
}
/MODULE_IMPORT_NS/ {
$0 = gensub(/MODULE_IMPORT_NS\(([^)]*)\)/, "MODULE_IMPORT_NS(\"\\1\")", "g");
}
/EXPORT_SYMBOL_NS/ {
if ($0 ~ /(EXPORT_SYMBOL_NS[^(]*)\(([^,]+),/) {
if ($0 !~ /(EXPORT_SYMBOL_NS[^(]*)\(([^,]+), ([^)]+)\)/ &&
$0 !~ /(EXPORT_SYMBOL_NS[^(]*)\(\)/ &&
$0 !~ /^my/) {
getline line;
gsub(/[[:space:]]*\\$/, "");
gsub(/[[:space:]]/, "", line);
$0 = $0 " " line;
}
$0 = gensub(/(EXPORT_SYMBOL_NS[^(]*)\(([^,]+), ([^)]+)\)/,
"\\1(\\2, \"\\3\")", "g");
}
}
{ print }' $file;
done
Requested-by: Masahiro Yamada <masahiroy@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://mail.google.com/mail/u/2/#inbox/FMfcgzQXKWgMmjdFwwdsfgxzKpVHWPlc
Acked-by: Greg KH <gregkh@linuxfoundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2024-07-11 (net/intel)
This series contains updates to most Intel network drivers.
Tony removes MODULE_AUTHOR from drivers containing the entry.
Simon Horman corrects a kdoc entry for i40e.
Pawel adds implementation for devlink param "local_forwarding" on ice.
Michal removes unneeded call, and code, for eswitch rebuild for ice.
Sasha removed a no longer used field from igc.
* '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
igc: Remove the internal 'eee_advert' field
ice: remove eswitch rebuild
ice: Add support for devlink local_forwarding param
i40e: correct i40e_addr_to_hkey() name in kdoc
net: intel: Remove MODULE_AUTHORs
====================
Link: https://patch.msgid.link/20240711201932.2019925-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
We are moving away from the Sourceforge email address. Rather than
removing or updating the email for the affected entries, remove the
MODULE_AUTHOR altogether as its usage is incorrect [1].
Link: https://lore.kernel.org/netdev/20200626115236.7f36d379@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com/ [1]
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Acked-by: Alexander Lobakin <aleksander.lobakin@intel.com> # libeth, libie
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Unlike previous generations, idpf requires more buffer types for optimal
performance. This includes: header buffers, short buffers, and
no-overhead buffers (w/o headroom and tailroom, for TCP zerocopy when
the header split is enabled).
Introduce libeth Rx buffer type and calculate page_pool params
accordingly. All the HW-related details like buffer alignment are still
accounted. For the header buffers, pick 256 bytes as in most places in
the kernel (have you ever seen frames with bigger headers?).
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
*-objs suffix is reserved rather for (user-space) host programs while
usually *-y suffix is used for kernel drivers (although *-objs works
for that purpose for now).
Let's correct the old usages of *-objs in Makefiles.
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20240607-next-2024-06-03-intel-next-batch-v3-1-d1470cee3347@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Add a couple intuitive helpers to hide Rx buffer implementation details
in the library and not multiplicate it between drivers. The settings are
sorta optimized for 100G+ NICs, but nothing really HW-specific here.
Use the new page_pool_dev_alloc() to dynamically switch between
split-page and full-page modes depending on MTU, page size, required
headroom etc. For example, on x86_64 with the default driver settings
each page is shared between 2 buffers. Turning on XDP (not in this
series) -> increasing headroom requirement pushes truesize out of 2048
boundary, leading to that each buffer starts getting a full page.
The "ceiling" limit is %PAGE_SIZE, as only order-0 pages are used to
avoid compound overhead. For the above architecture, this means maximum
linear frame size of 3712 w/o XDP.
Not that &libeth_buf_queue is not a complete queue/ring structure for
now, rather a shim, but eventually the libeth-enabled drivers will move
to it, with iavf being the first one.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Not a secret there's a ton of code duplication between two and more Intel
ethernet modules.
Before introducing new changes, which would need to be copied over again,
start decoupling the already existing duplicate functionality into a new
module, which will be shared between several Intel Ethernet drivers.
Add the lookup table which converts 8/10-bit hardware packet type into
a parsed bitfield structure for easy checking packet format parameters,
such as payload level, IP version, etc. This is currently used by i40e,
ice and iavf and it's all the same in all three drivers.
The only difference introduced in this implementation is that instead of
defining a 256 (or 1024 in case of ice) element array, add unlikely()
condition to limit the input to 154 (current maximum non-reserved packet
type). There's no reason to waste 600 (or even 3600) bytes only to not
hurt very unlikely exception packets.
The hash computation function now takes payload level directly as a
pkt_hash_type. There's a couple cases when non-IP ptypes are marked as
L3 payload and in the previous versions their hash level would be 2, not
3. But skb_set_hash() only sees difference between L4 and non-L4, thus
this won't change anything at all.
The module is behind the hidden Kconfig symbol, which the drivers will
select when needed. The exports are behind 'LIBIE' namespace to limit
the scope of the functions.
Not that non-HW-specific symbols will live in yet another module,
libeth. This is done to easily distinguish pretty generic code ready
for reusing by any other vendor and/or for moving the layer up from
the code useful in Intel's 1-100G drivers only.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
