Age | Commit message (Collapse) | Author | Files | Lines |
|
Pull dma-mapping updates from Christoph Hellwig:
- optimize DMA sync calls when they are no-ops (Alexander Lobakin)
- fix swiotlb padding for untrusted devices (Michael Kelley)
- add documentation for swiotb (Michael Kelley)
* tag 'dma-mapping-6.10-2024-05-20' of git://git.infradead.org/users/hch/dma-mapping:
dma: fix DMA sync for drivers not calling dma_set_mask*()
xsk: use generic DMA sync shortcut instead of a custom one
page_pool: check for DMA sync shortcut earlier
page_pool: don't use driver-set flags field directly
page_pool: make sure frag API fields don't span between cachelines
iommu/dma: avoid expensive indirect calls for sync operations
dma: avoid redundant calls for sync operations
dma: compile-out DMA sync op calls when not used
iommu/dma: fix zeroing of bounce buffer padding used by untrusted devices
swiotlb: remove alloc_size argument to swiotlb_tbl_map_single()
Documentation/core-api: add swiotlb documentation
|
|
XSk infra's been using its own DMA sync shortcut to try avoiding
redundant function calls. Now that there is a generic one, remove
the custom implementation and rely on the generic helpers.
xsk_buff_dma_sync_for_cpu() doesn't need the second argument anymore,
remove it.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
|
|
__napi_alloc_skb() is napi_alloc_skb() with the added flexibility
of choosing gfp_mask. This is a NAPI function, so GFP_ATOMIC is
implied. The only practical choice the caller has is whether to
set __GFP_NOWARN. But that's a false choice, too, allocation failures
in atomic context will happen, and printing warnings in logs,
effectively for a packet drop, is both too much and very likely
non-actionable.
This leads me to a conclusion that most uses of napi_alloc_skb()
are simply misguided, and should use __GFP_NOWARN in the first
place. We also have a "standard" way of reporting allocation
failures via the queue stat API (qstats::rx-alloc-fail).
The direct motivation for this patch is that one of the drivers
used at Meta calls napi_alloc_skb() (so prior to this patch without
__GFP_NOWARN), and the resulting OOM warning is the top networking
warning in our fleet.
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240327040213.3153864-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Ice and i40e ZC drivers currently set offset of a frag within
skb_shared_info to 0, which is incorrect. xdp_buffs that come from
xsk_buff_pool always have 256 bytes of a headroom, so they need to be
taken into account to retrieve xdp_buff::data via skb_frag_address().
Otherwise, bpf_xdp_frags_increase_tail() would be starting its job from
xdp_buff::data_hard_start which would result in overwriting existing
payload.
Fixes: 1c9ba9c14658 ("i40e: xsk: add RX multi-buffer support")
Fixes: 1bbc04de607b ("ice: xsk: add RX multi-buffer support")
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-8-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
XDP multi-buffer support introduced XDP_FLAGS_HAS_FRAGS flag that is
used by drivers to notify data path whether xdp_buff contains fragments
or not. Data path looks up mentioned flag on first buffer that occupies
the linear part of xdp_buff, so drivers only modify it there. This is
sufficient for SKB and XDP_DRV modes as usually xdp_buff is allocated on
stack or it resides within struct representing driver's queue and
fragments are carried via skb_frag_t structs. IOW, we are dealing with
only one xdp_buff.
ZC mode though relies on list of xdp_buff structs that is carried via
xsk_buff_pool::xskb_list, so ZC data path has to make sure that
fragments do *not* have XDP_FLAGS_HAS_FRAGS set. Otherwise,
xsk_buff_free() could misbehave if it would be executed against xdp_buff
that carries a frag with XDP_FLAGS_HAS_FRAGS flag set. Such scenario can
take place when within supplied XDP program bpf_xdp_adjust_tail() is
used with negative offset that would in turn release the tail fragment
from multi-buffer frame.
Calling xsk_buff_free() on tail fragment with XDP_FLAGS_HAS_FRAGS would
result in releasing all the nodes from xskb_list that were produced by
driver before XDP program execution, which is not what is intended -
only tail fragment should be deleted from xskb_list and then it should
be put onto xsk_buff_pool::free_list. Such multi-buffer frame will never
make it up to user space, so from AF_XDP application POV there would be
no traffic running, however due to free_list getting constantly new
nodes, driver will be able to feed HW Rx queue with recycled buffers.
Bottom line is that instead of traffic being redirected to user space,
it would be continuously dropped.
To fix this, let us clear the mentioned flag on xsk_buff_pool side
during xdp_buff initialization, which is what should have been done
right from the start of XSK multi-buffer support.
Fixes: 1bbc04de607b ("ice: xsk: add RX multi-buffer support")
Fixes: 1c9ba9c14658 ("i40e: xsk: add RX multi-buffer support")
Fixes: 24ea50127ecf ("xsk: support mbuf on ZC RX")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/r/20240124191602.566724-3-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
Refactor the i40e driver to use FIELD_GET() for mask and shift reads,
which reduces lines of code and adds clarity of intent.
This code was generated by the following coccinelle/spatch script and
then manually repaired.
While making one of the conversions, an if() check was inverted to
return early and avoid un-necessary indentation of the remainder of the
function. In some other cases a stack variable was moved inside the
block where it was used while doing cleanups/review.
A couple places were changed to use le16_get_bits() instead of FIELD_GET
with a le16_to_cpu combination.
@get@
constant shift,mask;
metavariable type T;
expression a;
@@
-(((T)(a) & mask) >> shift)
+FIELD_GET(mask, a)
and applied via:
spatch --sp-file field_prep.cocci --in-place --dir \
drivers/net/ethernet/intel/
Cc: Julia Lawall <Julia.Lawall@inria.fr>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Cross-merge networking fixes after downstream PR.
Conflicts:
net/mac80211/rx.c
91535613b609 ("wifi: mac80211: don't drop all unprotected public action frames")
6c02fab72429 ("wifi: mac80211: split ieee80211_drop_unencrypted_mgmt() return value")
Adjacent changes:
drivers/net/ethernet/apm/xgene/xgene_enet_main.c
61471264c018 ("net: ethernet: apm: Convert to platform remove callback returning void")
d2ca43f30611 ("net: xgene: Fix unused xgene_enet_of_match warning for !CONFIG_OF")
net/vmw_vsock/virtio_transport.c
64c99d2d6ada ("vsock/virtio: support to send non-linear skb")
53b08c498515 ("vsock/virtio: initialize the_virtio_vsock before using VQs")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Cited commit introduced a neat way of updating next_to_clean that does
not require boundary checks on each increment. This was done by masking
the new value with (ring length - 1) mask. Problem is that this is
applicable only for power of 2 ring sizes, for every other size this
assumption can not be made. In turn, it leads to cleaning descriptors
out of order as well as splats:
[ 1388.411915] Workqueue: events xp_release_deferred
[ 1388.411919] RIP: 0010:xp_free+0x1a/0x50
[ 1388.411921] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 55 48 8b 57 70 48 8d 47 70 48 89 e5 48 39 d0 74 06 <5d> c3 cc cc cc cc 48 8b 57 60 83 82 b8 00 00 00 01 48 8b 57 60 48
[ 1388.411922] RSP: 0018:ffa0000000a83cb0 EFLAGS: 00000206
[ 1388.411923] RAX: ff11000119aa5030 RBX: 000000000000001d RCX: ff110001129b6e50
[ 1388.411924] RDX: ff11000119aa4fa0 RSI: 0000000055555554 RDI: ff11000119aa4fc0
[ 1388.411925] RBP: ffa0000000a83cb0 R08: 0000000000000000 R09: 0000000000000000
[ 1388.411926] R10: 0000000000000001 R11: 0000000000000000 R12: ff11000115829b80
[ 1388.411927] R13: 000000000000005f R14: 0000000000000000 R15: ff11000119aa4fc0
[ 1388.411928] FS: 0000000000000000(0000) GS:ff11000277e00000(0000) knlGS:0000000000000000
[ 1388.411929] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1388.411930] CR2: 00007f1f564e6c14 CR3: 000000000783c005 CR4: 0000000000771ef0
[ 1388.411931] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1388.411931] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 1388.411932] PKRU: 55555554
[ 1388.411933] Call Trace:
[ 1388.411934] <IRQ>
[ 1388.411935] ? show_regs+0x6e/0x80
[ 1388.411937] ? watchdog_timer_fn+0x1d2/0x240
[ 1388.411939] ? __pfx_watchdog_timer_fn+0x10/0x10
[ 1388.411941] ? __hrtimer_run_queues+0x10e/0x290
[ 1388.411945] ? clockevents_program_event+0xae/0x130
[ 1388.411947] ? hrtimer_interrupt+0x105/0x240
[ 1388.411949] ? __sysvec_apic_timer_interrupt+0x54/0x150
[ 1388.411952] ? sysvec_apic_timer_interrupt+0x7f/0x90
[ 1388.411955] </IRQ>
[ 1388.411955] <TASK>
[ 1388.411956] ? asm_sysvec_apic_timer_interrupt+0x1f/0x30
[ 1388.411958] ? xp_free+0x1a/0x50
[ 1388.411960] i40e_xsk_clean_rx_ring+0x5d/0x100 [i40e]
[ 1388.411968] i40e_clean_rx_ring+0x14c/0x170 [i40e]
[ 1388.411977] i40e_queue_pair_disable+0xda/0x260 [i40e]
[ 1388.411986] i40e_xsk_pool_setup+0x192/0x1d0 [i40e]
[ 1388.411993] i40e_reconfig_rss_queues+0x1f0/0x1450 [i40e]
[ 1388.412002] xp_disable_drv_zc+0x73/0xf0
[ 1388.412004] ? mutex_lock+0x17/0x50
[ 1388.412007] xp_release_deferred+0x2b/0xc0
[ 1388.412010] process_one_work+0x178/0x350
[ 1388.412011] ? __pfx_worker_thread+0x10/0x10
[ 1388.412012] worker_thread+0x2f7/0x420
[ 1388.412014] ? __pfx_worker_thread+0x10/0x10
[ 1388.412015] kthread+0xf8/0x130
[ 1388.412017] ? __pfx_kthread+0x10/0x10
[ 1388.412019] ret_from_fork+0x3d/0x60
[ 1388.412021] ? __pfx_kthread+0x10/0x10
[ 1388.412023] ret_from_fork_asm+0x1b/0x30
[ 1388.412026] </TASK>
It comes from picking wrong ring entries when cleaning xsk buffers
during pool detach.
Remove the count_mask logic and use they boundary check when updating
next_to_process (which used to be a next_to_clean).
Fixes: c8a8ca3408dc ("i40e: remove unnecessary memory writes of the next to clean pointer")
Reported-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Tested-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://lore.kernel.org/r/20231018163908.40841-1-maciej.fijalkowski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Similarly as for ice driver [1] there are also circular header
dependencies in i40e driver:
i40e.h -> i40e_virtchnl_pf.h -> i40e.h
Another issue is that i40e header files does not contain their own
dependencies on other header files (both private and standard) so their
inclusion in .c file require to add these deps in certain order to
that .c file to make it compilable.
Fix both issues by removal the mentioned circular dependency, by filling
i40e headers with their dependencies so they can be placed anywhere in
a source code. Additionally remove bunch of includes from i40e.h super
header file that are not necessary and include i40e.h only in .c files
that really require it.
[1] 649c87c6ff52 ("ice: remove circular header dependencies on ice.h")
Signed-off-by: Ivan Vecera <ivecera@redhat.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Set eop bit in TX desc command only for the last descriptor of the
packet and do not set for all preceding descriptors.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-17-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
This patch is inspired from the multi-buffer support in non-zc path for
i40e as well as from the patch to support zc on ice. Each subsequent
frag is added to skb_shared_info of the first frag for possible xdp_prog
use as well to xsk buffer list for accessing the buffers in af_xdp.
For XDP_PASS, new pages are allocated for frags and contents are copied
from memory backed by xsk_buff_pool.
Replace next_to_clean with next_to_process as done in non-zc path and
advance it for every buffer and change the semantics of next_to_clean to
point to the first buffer of a packet. Driver will use next_to_process
in the same way next_to_clean was used previously.
For the non multi-buffer case, next_to_process and next_to_clean will
always be the same since each packet consists of a single buffer.
Signed-off-by: Tirthendu Sarkar <tirthendu.sarkar@intel.com>
Link: https://lore.kernel.org/r/20230719132421.584801-14-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
|
|
Spell "transmission" properly.
Found by searching for keyword "tranm".
Signed-off-by: Yueh-Shun Li <shamrocklee@posteo.net>
Link: https://lore.kernel.org/r/20230622012627.15050-3-shamrocklee@posteo.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
During reallocation of RX buffers, new DMA mappings are created for
those buffers.
steps for reproduction:
while :
do
for ((i=0; i<=8160; i=i+32))
do
ethtool -G enp130s0f0 rx $i tx $i
sleep 0.5
ethtool -g enp130s0f0
done
done
This resulted in crash:
i40e 0000:01:00.1: Unable to allocate memory for the Rx descriptor ring, size=65536
Driver BUG
WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:141 xdp_rxq_info_unreg+0x43/0x50
Call Trace:
i40e_free_rx_resources+0x70/0x80 [i40e]
i40e_set_ringparam+0x27c/0x800 [i40e]
ethnl_set_rings+0x1b2/0x290
genl_family_rcv_msg_doit.isra.15+0x10f/0x150
genl_family_rcv_msg+0xb3/0x160
? rings_fill_reply+0x1a0/0x1a0
genl_rcv_msg+0x47/0x90
? genl_family_rcv_msg+0x160/0x160
netlink_rcv_skb+0x4c/0x120
genl_rcv+0x24/0x40
netlink_unicast+0x196/0x230
netlink_sendmsg+0x204/0x3d0
sock_sendmsg+0x4c/0x50
__sys_sendto+0xee/0x160
? handle_mm_fault+0xbe/0x1e0
? syscall_trace_enter+0x1d3/0x2c0
__x64_sys_sendto+0x24/0x30
do_syscall_64+0x5b/0x1a0
entry_SYSCALL_64_after_hwframe+0x65/0xca
RIP: 0033:0x7f5eac8b035b
Missing register, driver bug
WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:119 xdp_rxq_info_unreg_mem_model+0x69/0x140
Call Trace:
xdp_rxq_info_unreg+0x1e/0x50
i40e_free_rx_resources+0x70/0x80 [i40e]
i40e_set_ringparam+0x27c/0x800 [i40e]
ethnl_set_rings+0x1b2/0x290
genl_family_rcv_msg_doit.isra.15+0x10f/0x150
genl_family_rcv_msg+0xb3/0x160
? rings_fill_reply+0x1a0/0x1a0
genl_rcv_msg+0x47/0x90
? genl_family_rcv_msg+0x160/0x160
netlink_rcv_skb+0x4c/0x120
genl_rcv+0x24/0x40
netlink_unicast+0x196/0x230
netlink_sendmsg+0x204/0x3d0
sock_sendmsg+0x4c/0x50
__sys_sendto+0xee/0x160
? handle_mm_fault+0xbe/0x1e0
? syscall_trace_enter+0x1d3/0x2c0
__x64_sys_sendto+0x24/0x30
do_syscall_64+0x5b/0x1a0
entry_SYSCALL_64_after_hwframe+0x65/0xca
RIP: 0033:0x7f5eac8b035b
This was caused because of new buffers with different RX ring count should
substitute older ones, but those buffers were freed in
i40e_configure_rx_ring and reallocated again with i40e_alloc_rx_bi,
thus kfree on rx_bi caused leak of already mapped DMA.
Fix this by reallocating ZC with rx_bi_zc struct when BPF program loads. Additionally
reallocate back to rx_bi when BPF program unloads.
If BPF program is loaded/unloaded and XSK pools are created, reallocate
RX queues accordingly in XSP_SETUP_XSK_POOL handler.
Fixes: be1222b585fd ("i40e: Separate kernel allocated rx_bi rings from AF_XDP rings")
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Chandan <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Tested-by: Gurucharan <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Similar to how it's done in the ice driver since 'eb087cd82864 ("ice:
propagate xdp_ring onto rx_ring")', read the XDP program once per NAPI
instead of once per descriptor cleaned. I measured an improvement in
throughput of 2% for the AF_XDP xdpsock l2fwd benchmark for zero copy mode
and 1% for copy mode.
Signed-off-by: Ciara Loftus <ciara.loftus@intel.com>
Link: https://lore.kernel.org/r/20220623100852.7867-1-ciara.loftus@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Intel drivers translate actions returned from XDP programs to their own
return codes that have the following mapping:
XDP_REDIRECT -> I40E_XDP_{REDIR,CONSUMED}
XDP_TX -> I40E_XDP_{TX,CONSUMED}
XDP_DROP -> I40E_XDP_CONSUMED
XDP_ABORTED -> I40E_XDP_CONSUMED
XDP_PASS -> I40E_XDP_PASS
Commit b8aef650e549 ("i40e, xsk: Terminate Rx side of NAPI when XSK Rx
queue gets full") introduced new translation
XDP_REDIRECT -> I40E_XDP_EXIT
which is set when XSK RQ gets full and to indicate that driver should
stop further Rx processing. This happens for unsuccessful
xdp_do_redirect() so it is valuable to call trace_xdp_exception() for
this case. In order to avoid I40E_XDP_EXIT -> IXGBE_XDP_CONSUMED
overwrite, XDP_DROP case was moved above which in turn made the
'fallthrough' that is in XDP_ABORTED useless as it became the last label
in the switch statement.
Simply drop this leftover.
Fixes: b8aef650e549 ("i40e, xsk: Terminate Rx side of NAPI when XSK Rx queue gets full")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220421132126.471515-3-maciej.fijalkowski@intel.com
|
|
Currently, when debugging AF_XDP workloads, one can correlate the -ENXIO
return code as the case that XSK is not in the bound state. Returning
same code from ndo_xsk_wakeup can be misleading and simply makes it
harder to follow what is going on.
Change ENXIOs in i40e's ndo_xsk_wakeup() implementation to EINVALs, so
that when probing it is clear that something is wrong on the driver
side, not the xsk_{recv,send}msg.
There is a -ENETDOWN that can happen from both kernel/driver sides
though, but I don't have a correct replacement for this on one of the
sides, so let's keep it that way.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220413153015.453864-10-maciej.fijalkowski@intel.com
|
|
When XSK pool uses need_wakeup feature, correlate -ENOBUFS that was
returned from xdp_do_redirect() with a XSK Rx queue being full. In such
case, terminate the Rx processing that is being done on the current HW
Rx ring and let the user space consume descriptors from XSK Rx queue so
that there is room that driver can use later on.
Introduce new internal return code I40E_XDP_EXIT that will indicate case
described above.
Note that it does not affect Tx processing that is bound to the same
NAPI context, nor the other Rx rings.
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20220413153015.453864-7-maciej.fijalkowski@intel.com
|
|
The 'if (ntu == rx_ring->count)' block in i40e_alloc_rx_buffers_zc()
was previously residing in the loop, but after introducing the
batched interface it is used only to wrap-around the NTU descriptor,
thus no more need to assign 'xdp'.
'cleaned_count' in i40e_clean_rx_irq_zc() was previously being
incremented in the loop, but after commit f12738b6ec06
("i40e: remove unnecessary cleaned_count updates") it gets
assigned only once after it, so the initialization can be dropped.
Fixes: 6aab0bb0c5cd ("i40e: Use the xsk batched rx allocation interface")
Fixes: f12738b6ec06 ("i40e: remove unnecessary cleaned_count updates")
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Daniel Borkmann says:
====================
pull-request: bpf-next 2022-02-09
We've added 126 non-merge commits during the last 16 day(s) which contain
a total of 201 files changed, 4049 insertions(+), 2215 deletions(-).
The main changes are:
1) Add custom BPF allocator for JITs that pack multiple programs into a huge
page to reduce iTLB pressure, from Song Liu.
2) Add __user tagging support in vmlinux BTF and utilize it from BPF
verifier when generating loads, from Yonghong Song.
3) Add per-socket fast path check guarding from cgroup/BPF overhead when
used by only some sockets, from Pavel Begunkov.
4) Continued libbpf deprecation work of APIs/features and removal of their
usage from samples, selftests, libbpf & bpftool, from Andrii Nakryiko
and various others.
5) Improve BPF instruction set documentation by adding byte swap
instructions and cleaning up load/store section, from Christoph Hellwig.
6) Switch BPF preload infra to light skeleton and remove libbpf dependency
from it, from Alexei Starovoitov.
7) Fix architecture-agnostic macros in libbpf for accessing syscall
arguments from BPF progs for non-x86 architectures,
from Ilya Leoshkevich.
8) Rework port members in struct bpf_sk_lookup and struct bpf_sock to be
of 16-bit field with anonymous zero padding, from Jakub Sitnicki.
9) Add new bpf_copy_from_user_task() helper to read memory from a different
task than current. Add ability to create sleepable BPF iterator progs,
from Kenny Yu.
10) Implement XSK batching for ice's zero-copy driver used by AF_XDP and
utilize TX batching API from XSK buffer pool, from Maciej Fijalkowski.
11) Generate temporary netns names for BPF selftests to avoid naming
collisions, from Hangbin Liu.
12) Implement bpf_core_types_are_compat() with limited recursion for
in-kernel usage, from Matteo Croce.
13) Simplify pahole version detection and finally enable CONFIG_DEBUG_INFO_DWARF5
to be selected with CONFIG_DEBUG_INFO_BTF, from Nathan Chancellor.
14) Misc minor fixes to libbpf and selftests from various folks.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (126 commits)
selftests/bpf: Cover 4-byte load from remote_port in bpf_sk_lookup
bpf: Make remote_port field in struct bpf_sk_lookup 16-bit wide
libbpf: Fix compilation warning due to mismatched printf format
selftests/bpf: Test BPF_KPROBE_SYSCALL macro
libbpf: Add BPF_KPROBE_SYSCALL macro
libbpf: Fix accessing the first syscall argument on s390
libbpf: Fix accessing the first syscall argument on arm64
libbpf: Allow overriding PT_REGS_PARM1{_CORE}_SYSCALL
selftests/bpf: Skip test_bpf_syscall_macro's syscall_arg1 on arm64 and s390
libbpf: Fix accessing syscall arguments on riscv
libbpf: Fix riscv register names
libbpf: Fix accessing syscall arguments on powerpc
selftests/bpf: Use PT_REGS_SYSCALL_REGS in bpf_syscall_macro
libbpf: Add PT_REGS_SYSCALL_REGS macro
selftests/bpf: Fix an endianness issue in bpf_syscall_macro test
bpf: Fix bpf_prog_pack build HPAGE_PMD_SIZE
bpf: Fix leftover header->pages in sparc and powerpc code.
libbpf: Fix signedness bug in btf_dump_array_data()
selftests/bpf: Do not export subtest as standalone test
bpf, x86_64: Fail gracefully on bpf_jit_binary_pack_finalize failures
...
====================
Link: https://lore.kernel.org/r/20220209210050.8425-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
For now, if the XDP prog returns XDP_PASS on XSK, the metadata will
be lost as it doesn't get copied to the skb.
Copy it along with the frame headers. Account its size on skb
allocation, and when copying just treat it as a part of the frame
and do a pull after to "move" it to the "reserved" zone.
net_prefetch() xdp->data_meta and align the copy size to speed-up
memcpy() a little and better match i40e_construct_skb().
Fixes: 0a714186d3c0 ("i40e: add AF_XDP zero-copy Rx support")
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Suggested-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
{__,}napi_alloc_skb() allocates and reserves additional NET_SKB_PAD
+ NET_IP_ALIGN for any skb.
OTOH, i40e_construct_skb_zc() currently allocates and reserves
additional `xdp->data - xdp->data_hard_start`, which is
XDP_PACKET_HEADROOM for XSK frames.
There's no need for that at all as the frame is post-XDP and will
go only to the networking stack core.
Pass the size of the actual data only to __napi_alloc_skb() and
don't reserve anything. This will give enough headroom for stack
processing.
Fixes: 0a714186d3c0 ("i40e: add AF_XDP zero-copy Rx support")
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Move desc_array from the driver to the pool. The reason behind this is
that we can then reuse this array as a temporary storage for descriptors
in all zero-copy drivers that use the batched interface. This will make
it easier to add batching to more drivers.
i40e is the only driver that has a batched Tx zero-copy
implementation, so no need to touch any other driver.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Link: https://lore.kernel.org/bpf/20220125160446.78976-6-maciej.fijalkowski@intel.com
|
|
In non trivial scenarios, the action id alone is not sufficient to
identify the program causing the warning. Before the previous patch,
the generated stack-trace pointed out at least the involved device
driver.
Let's additionally include the program name and id, and the relevant
device name.
If the user needs additional infos, he can fetch them via a kernel
probe, leveraging the arguments added here.
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/ddb96bb975cbfddb1546cf5da60e77d5100b533c.1638189075.git.pabeni@redhat.com
|
|
Fix the following coccicheck warning:
./drivers/net/ethernet/intel/i40e/i40e_xsk.c:229:35-40: WARNING:
conversion to bool not needed here
./drivers/net/ethernet/intel/ice/ice_xsk.c:399:35-40: WARNING:
conversion to bool not needed here
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Tested-by: Tony Brelinski <tony.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Use the new xsk batched rx allocation interface for the zero-copy data
path. As the array of struct xdp_buff pointers kept by the driver is
really a ring that wraps, the allocation routine is modified to detect
a wrap and in that case call the allocation function twice. The
allocation function cannot deal with wrapped rings, only arrays. As we
now know exactly how many buffers we get and that there is no
wrapping, the allocation function can be simplified even more as all
if-statements in the allocation loop can be removed, improving
performance.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-6-magnus.karlsson@gmail.com
|
|
The Intel drivers all have rcu_read_lock()/rcu_read_unlock() pairs around
XDP program invocations. However, the actual lifetime of the objects
referred by the XDP program invocation is longer, all the way through to
the call to xdp_do_flush(), making the scope of the rcu_read_lock() too
small. This turns out to be harmless because it all happens in a single
NAPI poll cycle (and thus under local_bh_disable()), but it makes the
rcu_read_lock() misleading.
Rather than extend the scope of the rcu_read_lock(), just get rid of it
entirely. With the addition of RCU annotations to the XDP_REDIRECT map
types that take bh execution into account, lockdep even understands this to
be safe, so there's really no reason to keep it around.
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com> # i40e
Cc: Jesse Brandeburg <jesse.brandeburg@intel.com>
Cc: Tony Nguyen <anthony.l.nguyen@intel.com>
Cc: intel-wired-lan@lists.osuosl.org
Link: https://lore.kernel.org/bpf/20210624160609.292325-12-toke@redhat.com
|
|
Add missing exception tracing to XDP when a number of different errors
can occur. The support was only partial. Several errors where not
logged which would confuse the user quite a lot not knowing where and
why the packets disappeared.
Fixes: 74608d17fe29 ("i40e: add support for XDP_TX action")
Fixes: 0a714186d3c0 ("i40e: add AF_XDP zero-copy Rx support")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Conflicts:
MAINTAINERS
- keep Chandrasekar
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
- simple fix + trust the code re-added to param.c in -next is fine
include/linux/bpf.h
- trivial
include/linux/ethtool.h
- trivial, fix kdoc while at it
include/linux/skmsg.h
- move to relevant place in tcp.c, comment re-wrapped
net/core/skmsg.c
- add the sk = sk // sk = NULL around calls
net/tipc/crypto.c
- trivial
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Fix so that single packets are received immediately instead of in
batches of 8. If you sent 1 pps to a system, you received 8 packets
every 8 seconds instead of 1 packet every second. The problem behind
this was that the work_done reporting from the Tx part of the driver
was broken. The work_done reporting in i40e controls not only the
reporting back to the napi logic but also the setting of the interrupt
throttling logic. When Tx or Rx reports that it has more to do,
interrupts are throttled or coalesced and when they both report that
they are done, interrupts are armed right away. If the wrong work_done
value is returned, the logic will start to throttle interrupts in a
situation where it should have just enabled them. This leads to the
undesired batching behavior seen in user-space.
Fix this by returning the correct boolean value from the Tx xsk
zero-copy path. Return true if there is nothing to do or if we got
fewer packets to process than we asked for. Return false if we got as
many packets as the budget since there might be more packets we can
process.
Fixes: 3106c580fb7c ("i40e: Use batched xsk Tx interfaces to increase performance")
Reported-by: Sreedevi Joshi <sreedevi.joshi@intel.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
A bunch of header comments were showing warnings when compiling
with W=1. Fix them all at once. This changes only comments.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Optimize i40e_run_xdp_zc() for the XDP program verdict being
XDP_REDIRECT in the xsk zero-copy path. This path is only used when
having AF_XDP zero-copy on and in that case most packets will be
directed to user space. This provides a little over 100k extra packets
in throughput on my server when running l2fwd in xdpsock.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2021-02-19
This series contains updates to i40e driver only.
Slawomir resolves an issue with the IPv6 extension headers being
processed incorrectly.
Keita Suzuki fixes a memory leak on probe failure.
Mateusz initializes AQ command structures to zero to comply with
spec, fixes FW flow control settings being overwritten and resolves an
issue with adding VLAN filters after enabling FW LLDP. He also adds
an additional check when adding TC filter as the current check doesn't
properly distinguish between IPv4 and IPv6.
Sylwester removes setting disabled bit when syncing filters as this
prevents VFs from completing setup.
Norbert cleans up sparse warnings.
v2:
- Fix fixes tag on patch 7
* '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue:
i40e: Fix endianness conversions
i40e: Fix add TC filter for IPv6
i40e: Fix VFs not created
i40e: Fix addition of RX filters after enabling FW LLDP agent
i40e: Fix overwriting flow control settings during driver loading
i40e: Add zero-initialization of AQ command structures
i40e: Fix memory leak in i40e_probe
i40e: Fix flow for IPv6 next header (extension header)
====================
Link: https://lore.kernel.org/r/20210219213606.2567536-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Fixes the following sparse warnings:
i40e_main.c:5953:32: warning: cast from restricted __le16
i40e_main.c:8008:29: warning: incorrect type in assignment (different base types)
i40e_main.c:8008:29: expected unsigned int [assigned] [usertype] ipa
i40e_main.c:8008:29: got restricted __le32 [usertype]
i40e_main.c:8008:29: warning: incorrect type in assignment (different base types)
i40e_main.c:8008:29: expected unsigned int [assigned] [usertype] ipa
i40e_main.c:8008:29: got restricted __le32 [usertype]
i40e_txrx.c:1950:59: warning: incorrect type in initializer (different base types)
i40e_txrx.c:1950:59: expected unsigned short [usertype] vlan_tag
i40e_txrx.c:1950:59: got restricted __le16 [usertype] l2tag1
i40e_txrx.c:1953:40: warning: cast to restricted __le16
i40e_xsk.c:448:38: warning: invalid assignment: |=
i40e_xsk.c:448:38: left side has type restricted __le64
i40e_xsk.c:448:38: right side has type int
Fixes: 2f4b411a3d67 ("i40e: Enable cloud filters via tc-flower")
Fixes: 2a508c64ad27 ("i40e: fix VLAN.TCI == 0 RX HW offload")
Fixes: 3106c580fb7c ("i40e: Use batched xsk Tx interfaces to increase performance")
Fixes: 8f88b3034db3 ("i40e: Add infrastructure for queue channel support")
Signed-off-by: Norbert Ciosek <norbertx.ciosek@intel.com>
Tested-by: Tony Brelinski <tonyx.brelinski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Fold the count decrement into the while-statement.
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Consolidate the actions performed on the packet based on the XDP
program result into a separate function that is easier to read and
maintain. Simplify the i40e_construct_skb_zc function, so that the
input xdp buffer is always freed, regardless of whether the output
skb is successfully created or not. Simplify the behavior of the
i40e_clean_rx_irq_zc function, so that the current packet descriptor
is dropped when function i40_construct_skb_zc returns an error as
opposed to re-processing the same description on the next invocation.
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
For performance reasons, remove the redundant buffer info updates
(*bi = NULL). The buffers ready to be cleaned can easily be tracked
based on the ring next-to-clean variable, which is consistently
updated.
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
For performance reasons, remove the redundant updates of the cleaned_count
variable, as its value can be computed based on the ring next-to-clean
variable, which is consistently updated.
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
For performance reasons, avoid writing the ring next-to-clean pointer
value back to memory on every update, as it is not really necessary.
Instead, simply read it at initialization into a local copy, update
the local copy as necessary and write the local copy back to memory
after the last update.
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Tested-by: Kiran Bhandare <kiranx.bhandare@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Currently, the function i40e_construct_skb_zc only frees the input xdp
buffer when the output skb is successfully built. On error, the
function i40e_clean_rx_irq_zc does not commit anything for the current
packet descriptor and simply exits the packet descriptor processing
loop, with the plan to restart the processing of this descriptor on
the next invocation. Therefore, on error the ring next-to-clean
pointer should not advance, the xdp i.e. *bi buffer should not be
freed and the current buffer info should not be invalidated by setting
*bi to NULL. Therefore, the *bi should only be set to NULL when the
function i40e_construct_skb_zc is successful, otherwise a NULL *bi
will be dereferenced when the work for the current descriptor is
eventually restarted.
Fixes: 3b4f0b66c2b3 ("i40e, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL")
Signed-off-by: Cristian Dumitrescu <cristian.dumitrescu@intel.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/r/20210111181138.49757-1-cristian.dumitrescu@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
On the Rx side, the next_to_use index points to the next item in the
HW ring to be refilled/allocated, and next_to_clean points to the next
item to potentially be processed.
When the HW Rx ring is fully refilled, i.e. no packets has been
processed, the next_to_use will be next_to_clean - 1. When the ring is
fully processed next_to_clean will be equal to next_to_use. The latter
case is where a bug is triggered.
If the next_to_use bits are not cleared, and the "fully processed"
state is entered, a stale descriptor can be processed.
The skb-path correctly clear the status bit for the next_to_use
descriptor, but the AF_XDP zero-copy path did not do that.
This change adds the status bits clearing of the next_to_use
descriptor.
Fixes: 3b4f0b66c2b3 ("i40e, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Alexei Starovoitov says:
====================
pull-request: bpf-next 2020-12-03
The main changes are:
1) Support BTF in kernel modules, from Andrii.
2) Introduce preferred busy-polling, from Björn.
3) bpf_ima_inode_hash() and bpf_bprm_opts_set() helpers, from KP Singh.
4) Memcg-based memory accounting for bpf objects, from Roman.
5) Allow bpf_{s,g}etsockopt from cgroup bind{4,6} hooks, from Stanislav.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (118 commits)
selftests/bpf: Fix invalid use of strncat in test_sockmap
libbpf: Use memcpy instead of strncpy to please GCC
selftests/bpf: Add fentry/fexit/fmod_ret selftest for kernel module
selftests/bpf: Add tp_btf CO-RE reloc test for modules
libbpf: Support attachment of BPF tracing programs to kernel modules
libbpf: Factor out low-level BPF program loading helper
bpf: Allow to specify kernel module BTFs when attaching BPF programs
bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier
selftests/bpf: Add CO-RE relocs selftest relying on kernel module BTF
selftests/bpf: Add support for marking sub-tests as skipped
selftests/bpf: Add bpf_testmod kernel module for testing
libbpf: Add kernel module BTF support for CO-RE relocations
libbpf: Refactor CO-RE relocs to not assume a single BTF object
libbpf: Add internal helper to load BTF data by FD
bpf: Keep module's btf_data_size intact after load
bpf: Fix bpf_put_raw_tracepoint()'s use of __module_address()
selftests/bpf: Add Userspace tests for TCP_WINDOW_CLAMP
bpf: Adds support for setting window clamp
samples/bpf: Fix spelling mistake "recieving" -> "receiving"
bpf: Fix cold build of test_progs-no_alu32
...
====================
Link: https://lore.kernel.org/r/20201204021936.85653-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
|
|
Remove a redundant assignment of the software ring pointer in the i40e
driver. The variable is assigned twice with no use in between, so just
get rid of the first occurrence.
Fixes: 3b4f0b66c2b3 ("i40e, xsk: Migrate to new MEM_TYPE_XSK_BUFF_POOL")
Signed-off-by: Marek Majtyka <marekx.majtyka@intel.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Use the new batched xsk interfaces for the Tx path in the i40e driver
to improve performance. On my machine, this yields a throughput
increase of 4% for the l2fwd sample app in xdpsock. If we instead just
look at the Tx part, this patch set increases throughput with above
20% for Tx.
Note that I had to explicitly loop unroll the inner loop to get to
this performance level, by using a pragma. It is honored by both clang
and gcc and should be ignored by versions that do not support
it. Using the -funroll-loops compiler command line switch on the
source file resulted in a loop unrolling on a higher level that
lead to a performance decrease instead of an increase.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/1605525167-14450-6-git-send-email-magnus.karlsson@gmail.com
|
|
Remove the unnecessary access to the software ring for the AF_XDP
zero-copy driver. This was used to record the length of the packet so
that the driver Tx completion code could sum this up to produce the
total bytes sent. This is now performed during the transmission of the
packet, so no need to record this in the software ring.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/1605525167-14450-3-git-send-email-magnus.karlsson@gmail.com
|
|
The "failure" variable is used without being initialized. It should be
set to false.
Fixes: 8cbf74149903 ("i40e, xsk: move buffer allocation out of the Rx processing loop")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: George Kuruvinakunnel <george.kuruvinakunnel@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Instead of checking in each iteration of the Rx packet processing
loop, move the allocation out of the loop and do it once for each napi
activation.
For AF_XDP the rx_drop benchmark was improved by 6%.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
The software prefetching of HW descriptors has a negative impact on
the performance. Therefore, it is now removed.
Performance for the rx_drop benchmark increased with 2%.
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
|
|
Test for dma_need_sync earlier to increase
performance. xsk_buff_dma_sync_for_cpu() takes an xdp_buff as
parameter and from that the xsk_buff_pool reference is dug out. Perf
shows that this dereference causes a lot of cache misses. But as the
buffer pool is now sent down to the driver at zero-copy initialization
time, we might as well use this pointer directly, instead of going via
the xsk_buff and we can do so already in xsk_buff_dma_sync_for_cpu()
instead of in xp_dma_sync_for_cpu. This gets rid of these cache
misses.
Throughput increases with 3% for the xdpsock l2fwd sample application
on my machine.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-11-git-send-email-magnus.karlsson@intel.com
|
|
Rename the AF_XDP zero-copy driver interface functions to better
reflect what they do after the replacement of umems with buffer
pools in the previous commit. Mostly it is about replacing the
umem name from the function names with xsk_buff and also have
them take the a buffer pool pointer instead of a umem. The
various ring functions have also been renamed in the process so
that they have the same naming convention as the internal
functions in xsk_queue.h. This so that it will be clearer what
they do and also for consistency.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-3-git-send-email-magnus.karlsson@intel.com
|
|
Replace the explicit umem reference passed to the driver in AF_XDP
zero-copy mode with the buffer pool instead. This in preparation for
extending the functionality of the zero-copy mode so that umems can be
shared between queues on the same netdev and also between netdevs. In
this commit, only an umem reference has been added to the buffer pool
struct. But later commits will add other entities to it. These are
going to be entities that are different between different queue ids
and netdevs even though the umem is shared between them.
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/1598603189-32145-2-git-send-email-magnus.karlsson@intel.com
|