- 20 Feb, 2024 5 commits
-
-
Eric Dumazet authored
Last major reorg happened in commit 9115e8cd ("net: reorganize struct sock for better data locality") Since then, many changes have been done. Before SO_PEEK_OFF support is added to TCP, we need to move sk_peek_off to a better location. It is time to make another pass, and add six groups, without explicit alignment. - sock_write_rx (following sk_refcnt) read-write fields in rx path. - sock_read_rx read-mostly fields in rx path. - sock_read_rxtx read-mostly fields in both rx and tx paths. - sock_write_rxtx read-write fields in both rx and tx paths. - sock_write_tx read-write fields in tx paths. - sock_read_tx read-mostly fields in tx paths. Results on TCP_RR benchmarks seem to show a gain (4 to 5 %). It is possible UDP needs a change, because sk_peek_off shares a cache line with sk_receive_queue. If this the case, we can exchange roles of sk->sk_receive and up->reader_queue queues. After this change, we have the following layout: struct sock { struct sock_common __sk_common; /* 0 0x88 */ /* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */ __u8 __cacheline_group_begin__sock_write_rx[0]; /* 0x88 0 */ atomic_t sk_drops; /* 0x88 0x4 */ __s32 sk_peek_off; /* 0x8c 0x4 */ struct sk_buff_head sk_error_queue; /* 0x90 0x18 */ struct sk_buff_head sk_receive_queue; /* 0xa8 0x18 */ /* --- cacheline 3 boundary (192 bytes) --- */ struct { atomic_t rmem_alloc; /* 0xc0 0x4 */ int len; /* 0xc4 0x4 */ struct sk_buff * head; /* 0xc8 0x8 */ struct sk_buff * tail; /* 0xd0 0x8 */ } sk_backlog; /* 0xc0 0x18 */ struct { atomic_t rmem_alloc; /* 0 0x4 */ int len; /* 0x4 0x4 */ struct sk_buff * head; /* 0x8 0x8 */ struct sk_buff * tail; /* 0x10 0x8 */ /* size: 24, cachelines: 1, members: 4 */ /* last cacheline: 24 bytes */ }; __u8 __cacheline_group_end__sock_write_rx[0]; /* 0xd8 0 */ __u8 __cacheline_group_begin__sock_read_rx[0]; /* 0xd8 0 */ rcu * sk_rx_dst; /* 0xd8 0x8 */ int sk_rx_dst_ifindex; /* 0xe0 0x4 */ u32 sk_rx_dst_cookie; /* 0xe4 0x4 */ unsigned int sk_ll_usec; /* 0xe8 0x4 */ unsigned int sk_napi_id; /* 0xec 0x4 */ u16 sk_busy_poll_budget; /* 0xf0 0x2 */ u8 sk_prefer_busy_poll; /* 0xf2 0x1 */ u8 sk_userlocks; /* 0xf3 0x1 */ int sk_rcvbuf; /* 0xf4 0x4 */ rcu * sk_filter; /* 0xf8 0x8 */ /* --- cacheline 4 boundary (256 bytes) --- */ union { rcu * sk_wq; /* 0x100 0x8 */ struct socket_wq * sk_wq_raw; /* 0x100 0x8 */ }; /* 0x100 0x8 */ union { rcu * sk_wq; /* 0 0x8 */ struct socket_wq * sk_wq_raw; /* 0 0x8 */ }; void (*sk_data_ready)(struct sock *); /* 0x108 0x8 */ long sk_rcvtimeo; /* 0x110 0x8 */ int sk_rcvlowat; /* 0x118 0x4 */ __u8 __cacheline_group_end__sock_read_rx[0]; /* 0x11c 0 */ __u8 __cacheline_group_begin__sock_read_rxtx[0]; /* 0x11c 0 */ int sk_err; /* 0x11c 0x4 */ struct socket * sk_socket; /* 0x120 0x8 */ struct mem_cgroup * sk_memcg; /* 0x128 0x8 */ rcu * sk_policy[2]; /* 0x130 0x10 */ /* --- cacheline 5 boundary (320 bytes) --- */ __u8 __cacheline_group_end__sock_read_rxtx[0]; /* 0x140 0 */ __u8 __cacheline_group_begin__sock_write_rxtx[0]; /* 0x140 0 */ socket_lock_t sk_lock; /* 0x140 0x20 */ u32 sk_reserved_mem; /* 0x160 0x4 */ int sk_forward_alloc; /* 0x164 0x4 */ u32 sk_tsflags; /* 0x168 0x4 */ __u8 __cacheline_group_end__sock_write_rxtx[0]; /* 0x16c 0 */ __u8 __cacheline_group_begin__sock_write_tx[0]; /* 0x16c 0 */ int sk_write_pending; /* 0x16c 0x4 */ atomic_t sk_omem_alloc; /* 0x170 0x4 */ int sk_sndbuf; /* 0x174 0x4 */ int sk_wmem_queued; /* 0x178 0x4 */ refcount_t sk_wmem_alloc; /* 0x17c 0x4 */ /* --- cacheline 6 boundary (384 bytes) --- */ unsigned long sk_tsq_flags; /* 0x180 0x8 */ union { struct sk_buff * sk_send_head; /* 0x188 0x8 */ struct rb_root tcp_rtx_queue; /* 0x188 0x8 */ }; /* 0x188 0x8 */ union { struct sk_buff * sk_send_head; /* 0 0x8 */ struct rb_root tcp_rtx_queue; /* 0 0x8 */ }; struct sk_buff_head sk_write_queue; /* 0x190 0x18 */ u32 sk_dst_pending_confirm; /* 0x1a8 0x4 */ u32 sk_pacing_status; /* 0x1ac 0x4 */ struct page_frag sk_frag; /* 0x1b0 0x10 */ /* --- cacheline 7 boundary (448 bytes) --- */ struct timer_list sk_timer; /* 0x1c0 0x28 */ /* XXX last struct has 4 bytes of padding */ unsigned long sk_pacing_rate; /* 0x1e8 0x8 */ atomic_t sk_zckey; /* 0x1f0 0x4 */ atomic_t sk_tskey; /* 0x1f4 0x4 */ __u8 __cacheline_group_end__sock_write_tx[0]; /* 0x1f8 0 */ __u8 __cacheline_group_begin__sock_read_tx[0]; /* 0x1f8 0 */ unsigned long sk_max_pacing_rate; /* 0x1f8 0x8 */ /* --- cacheline 8 boundary (512 bytes) --- */ long sk_sndtimeo; /* 0x200 0x8 */ u32 sk_priority; /* 0x208 0x4 */ u32 sk_mark; /* 0x20c 0x4 */ rcu * sk_dst_cache; /* 0x210 0x8 */ netdev_features_t sk_route_caps; /* 0x218 0x8 */ u16 sk_gso_type; /* 0x220 0x2 */ u16 sk_gso_max_segs; /* 0x222 0x2 */ unsigned int sk_gso_max_size; /* 0x224 0x4 */ gfp_t sk_allocation; /* 0x228 0x4 */ u32 sk_txhash; /* 0x22c 0x4 */ u8 sk_pacing_shift; /* 0x230 0x1 */ bool sk_use_task_frag; /* 0x231 0x1 */ __u8 __cacheline_group_end__sock_read_tx[0]; /* 0x232 0 */ u8 sk_gso_disabled:1; /* 0x232: 0 0x1 */ u8 sk_kern_sock:1; /* 0x232:0x1 0x1 */ u8 sk_no_check_tx:1; /* 0x232:0x2 0x1 */ u8 sk_no_check_rx:1; /* 0x232:0x3 0x1 */ /* XXX 4 bits hole, try to pack */ u8 sk_shutdown; /* 0x233 0x1 */ u16 sk_type; /* 0x234 0x2 */ u16 sk_protocol; /* 0x236 0x2 */ unsigned long sk_lingertime; /* 0x238 0x8 */ /* --- cacheline 9 boundary (576 bytes) --- */ struct proto * sk_prot_creator; /* 0x240 0x8 */ rwlock_t sk_callback_lock; /* 0x248 0x8 */ int sk_err_soft; /* 0x250 0x4 */ u32 sk_ack_backlog; /* 0x254 0x4 */ u32 sk_max_ack_backlog; /* 0x258 0x4 */ kuid_t sk_uid; /* 0x25c 0x4 */ spinlock_t sk_peer_lock; /* 0x260 0x4 */ int sk_bind_phc; /* 0x264 0x4 */ struct pid * sk_peer_pid; /* 0x268 0x8 */ const struct cred * sk_peer_cred; /* 0x270 0x8 */ ktime_t sk_stamp; /* 0x278 0x8 */ /* --- cacheline 10 boundary (640 bytes) --- */ int sk_disconnects; /* 0x280 0x4 */ u8 sk_txrehash; /* 0x284 0x1 */ u8 sk_clockid; /* 0x285 0x1 */ u8 sk_txtime_deadline_mode:1; /* 0x286: 0 0x1 */ u8 sk_txtime_report_errors:1; /* 0x286:0x1 0x1 */ u8 sk_txtime_unused:6; /* 0x286:0x2 0x1 */ /* XXX 1 byte hole, try to pack */ void * sk_user_data; /* 0x288 0x8 */ void * sk_security; /* 0x290 0x8 */ struct sock_cgroup_data sk_cgrp_data; /* 0x298 0x8 */ void (*sk_state_change)(struct sock *); /* 0x2a0 0x8 */ void (*sk_write_space)(struct sock *); /* 0x2a8 0x8 */ void (*sk_error_report)(struct sock *); /* 0x2b0 0x8 */ int (*sk_backlog_rcv)(struct sock *, struct sk_buff *); /* 0x2b8 0x8 */ /* --- cacheline 11 boundary (704 bytes) --- */ void (*sk_destruct)(struct sock *); /* 0x2c0 0x8 */ rcu * sk_reuseport_cb; /* 0x2c8 0x8 */ rcu * sk_bpf_storage; /* 0x2d0 0x8 */ struct callback_head sk_rcu __attribute__((__aligned__(8))); /* 0x2d8 0x10 */ netns_tracker ns_tracker; /* 0x2e8 0x8 */ /* size: 752, cachelines: 12, members: 105 */ /* sum members: 749, holes: 1, sum holes: 1 */ /* sum bitfield members: 12 bits, bit holes: 1, sum bit holes: 4 bits */ /* paddings: 1, sum paddings: 4 */ /* forced alignments: 1 */ /* last cacheline: 48 bytes */ }; Signed-off-by:
Eric Dumazet <edumazet@google.com> Acked-by:
Paolo Abeni <pabeni@redhat.com> Link: https://lore.kernel.org/r/20240216162006.2342759-1-edumazet@google.comSigned-off-by:
-
Colin Ian King authored
The variable len being initialized with a value that is never read, an if statement is initializing it in both paths of the if statement. The initialization is redundant and can be removed. Cleans up clang scan build warning: net/ipv4/tcp_ao.c:512:11: warning: Value stored to 'len' during its initialization is never read [deadcode.DeadStores] Signed-off-by:
Colin Ian King <colin.i.king@gmail.com> Reviewed-by:
Dmitry Safonov <0x7f454c46@gmail.com> Link: https://lore.kernel.org/r/20240216125443.2107244-1-colin.i.king@gmail.comSigned-off-by:
-
Paolo Abeni authored
Mina Almasry says: ==================== Abstract page from net stack This series is a prerequisite to the devmem TCP series. For a full snapshot of the code which includes these changes, feel free to check: https://github.com/mina/linux/commits/tcpdevmem-rfcv5/ Currently these components in the net stack use the struct page directly: 1. Drivers. 2. Page pool. 3. skb_frag_t. To add support for new (non struct page) memory types to the net stack, we must first abstract the current memory type. Originally the plan was to reuse struct page* for the new memory types, and to set the LSB on the page* to indicate it's not really a page. However, for safe compiler type checking we need to introduce a new type. struct netmem is introduced to abstract the underlying memory type. Currently it's a no-op abstraction that is always a struct page underneath. In parallel there is an undergoing effort to add support for devmem to the net stack: https://lore.kernel.org/netdev/20231208005250.2910004-1-almasrymina@google.com/ Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Christian König <christian.koenig@amd.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Yunsheng Lin <linyunsheng@huawei.com> Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com> ==================== Link: https://lore.kernel.org/r/20240214223405.1972973-1-almasrymina@google.comSigned-off-by:
-
Mina Almasry authored
Use struct netmem* instead of page in skb_frag_t. Currently struct netmem* is always a struct page underneath, but the abstraction allows efforts to add support for skb frags not backed by pages. There is unfortunately 1 instance where the skb_frag_t is assumed to be a exactly a bio_vec in kcm. For this case, WARN_ON_ONCE and return error before doing a cast. Add skb[_frag]_fill_netmem_*() and skb_add_rx_frag_netmem() helpers so that the API can be used to create netmem skbs. Signed-off-by:
Mina Almasry <almasrymina@google.com> Acked-by:
-
Mina Almasry authored
Add the netmem_ref type, an abstraction for network memory. To add support for new memory types to the net stack, we must first abstract the current memory type. Currently parts of the net stack use struct page directly: - page_pool - drivers - skb_frag_t Originally the plan was to reuse struct page* for the new memory types, and to set the LSB on the page* to indicate it's not really a page. However, for compiler type checking we need to introduce a new type. netmem_ref is introduced to abstract the underlying memory type. Currently it's a no-op abstraction that is always a struct page underneath. In parallel there is an undergoing effort to add support for devmem to the net stack: https://lore.kernel.org/netdev/20231208005250.2910004-1-almasrymina@google.com/ netmem_ref can be pointers to different underlying memory types, and the low bits are set to indicate the memory type. Helpers are provided to convert netmem pointers to the underlying memory type (currently only struct page). In the devmem series helpers are provided so that calling code can use netmem without worrying about the underlying memory type unless absolutely necessary. Reviewed-by:
Shakeel Butt <shakeelb@google.com> Signed-off-by:
-
- 19 Feb, 2024 11 commits
-
-
Breno Leitao authored
Creation of sysfs entries is expensive, mainly for workloads that constantly creates netdev and netns often. Do not create BQL sysfs entries for devices that don't need, basically those that do not have a real queue, i.e, devices that has NETIF_F_LLTX and IFF_NO_QUEUE, such as `lo` interface. This will remove the /sys/class/net/eth0/queues/tx-X/byte_queue_limits/ directory for these devices. In the example below, eth0 has the `byte_queue_limits` directory but not `lo`. # ls /sys/class/net/lo/queues/tx-0/ traffic_class tx_maxrate tx_timeout xps_cpus xps_rxqs # ls /sys/class/net/eth0/queues/tx-0/byte_queue_limits/ hold_time inflight limit limit_max limit_min This also removes the #ifdefs, since we can also use netdev_uses_bql() to check if the config is enabled. (as suggested by Jakub). Suggested-by:
Breno Leitao <leitao@debian.org> Link: https://lore.kernel.org/r/20240216094154.3263843-1-leitao@debian.orgSigned-off-by:
Jakub Kicinski <kuba@kernel.org>
-
Lorenzo Bianconi authored
Use global percpu page_pool_recycle_stats counter for system page_pool allocator instead of allocating a separate percpu variable for each (also percpu) page pool instance. Reviewed-by:
Toke Hoiland-Jorgensen <toke@redhat.com> Signed-off-by:
Lorenzo Bianconi <lorenzo@kernel.org> Reviewed-by:
Alexander Lobakin <aleksander.lobakin@intel.com> Link: https://lore.kernel.org/r/87f572425e98faea3da45f76c3c68815c01a20ee.1708075412.git.lorenzo@kernel.orgSigned-off-by:
-
Alexander Lobakin authored
Now that direct recycling is performed basing on pool->cpuid when set, memory leaks are possible: 1. A pool is destroyed. 2. Alloc cache is emptied (it's done only once). 3. pool->cpuid is still set. 4. napi_pp_put_page() does direct recycling basing on pool->cpuid. 5. Now alloc cache is not empty, but it won't ever be freed. In order to avoid that, rewrite pool->cpuid to -1 when unlinking NAPI to make sure no direct recycling will be possible after emptying the cache. This involves a bit of overhead as pool->cpuid now must be accessed via READ_ONCE() to avoid partial reads. Rename page_pool_unlink_napi() -> page_pool_disable_direct_recycling() to reflect what it actually does and unexport it. Signed-off-by:
-
Frank Li authored
iMX8QM have iommu. Add proerty 'iommus'. Signed-off-by:
Frank Li <Frank.Li@nxp.com> Acked-by:
Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Link: https://lore.kernel.org/r/20240201-8qm_smmu-v2-2-3d12a80201a3@nxp.comSigned-off-by:
-
Kees Cook authored
Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct tc_pedit. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. Link: https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci [1] Signed-off-by:
Kees Cook <keescook@chromium.org> Reviewed-by:
Gustavo A. R. Silva <gustavoars@kernel.org> Acked-by:
Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
David S. Miller authored
Shannon Nelson says: ==================== pds_core: AER handling Add simple handlers for the PCI AER callbacks, and improve the reset handling. ==================== Signed-off-by: -
Shannon Nelson authored
We get the benefit of all the PCI reset locking and recovery if we use the existing pci_reset_function() that will call our local reset handlers. Reviewed-by:
Brett Creeley <brett.creeley@amd.com> Signed-off-by:
Shannon Nelson <shannon.nelson@amd.com> Signed-off-by:
-
Shannon Nelson authored
When the VF is hit with a reset, remove the aux device in the prepare for reset and try to restore it after the reset. The userland mechanics will need to recover and rebuild whatever uses the device afterwards. Reviewed-by:
-
Shannon Nelson authored
Set up the pci_error_handlers error_detected and resume to be useful in handling AER events. Reviewed-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/nextDavid S. Miller authored
-queue Tony Nguyen says: ==================== i40e: Simplify VSI and VEB handling Ivan Vecera says: The series simplifies handling of VSIs and VEBs by introducing for-each iterating macros, 'find' helper functions. Also removes the VEB recursion because the VEBs cannot have sub-VEBs according datasheet and fixes the support for floating VEBs. The series content: Patch 1 - Uses existing helper function for find FDIR VSI instead of loop Patch 2 - Adds and uses macros to iterate VSI and VEB arrays Patch 3 - Adds 2 helper functions to find VSIs and VEBs by their SEID Patch 4 - Fixes broken support for floating VEBs Patch 5 - Removes VEB recursion and simplifies VEB handling ==================== Signed-off-by: -
Jiri Pirko authored
If message contains unknown attribute and user passes "--process-unknown" command line option, _decode() gets called with space arg set to None. In that case, attr_space variable is not initialized used which leads to following trace: Traceback (most recent call last): File "./tools/net/ynl/cli.py", line 77, in <module> main() File "./tools/net/ynl/cli.py", line 68, in main reply = ynl.dump(args.dump, attrs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "tools/net/ynl/lib/ynl.py", line 909, in dump return self._op(method, vals, [], dump=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "tools/net/ynl/lib/ynl.py", line 894, in _op rsp_msg = self._decode(decoded.raw_attrs, op.attr_set.name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "tools/net/ynl/lib/ynl.py", line 639, in _decode self._rsp_add(rsp, attr_name, None, self._decode_unknown(attr)) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "tools/net/ynl/lib/ynl.py", line 569, in _decode_unknown return self._decode(NlAttrs(attr.raw), None) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "tools/net/ynl/lib/ynl.py", line 630, in _decode search_attrs = SpaceAttrs(attr_space, rsp, outer_attrs) ^^^^^^^^^^ UnboundLocalError: cannot access local variable 'attr_space' where it is not associated with a value Fix this by moving search_attrs assignment under the if statement above it to make sure attr_space is initialized. Fixes: bf8b8323 ("tools/net/ynl: Support sub-messages in nested attribute spaces") Signed-off-by:Jiri Pirko <jiri@nvidia.com> Signed-off-by:
-
- 18 Feb, 2024 3 commits
-
-
Kamal Heib authored
Avoid the following warnings by removing the ena_select_queue() function and rely on the net core to do the queue selection, The issue happen when an skb received from an interface with more queues than ena is forwarded to the ena interface. [ 1176.159959] eth0 selects TX queue 11, but real number of TX queues is 8 [ 1176.863976] eth0 selects TX queue 14, but real number of TX queues is 8 [ 1180.767877] eth0 selects TX queue 14, but real number of TX queues is 8 [ 1188.703742] eth0 selects TX queue 14, but real number of TX queues is 8 Fixes: 1738cd3e ("net: ena: Add a driver for Amazon Elastic Network Adapters (ENA)") Signed-off-by:
Kamal Heib <kheib@redhat.com> Reviewed-by:
Jacob Keller <jacob.e.keller@intel.com> Signed-off-by:
-
Christian Marangi authored
Aquantia AQR813 is the Octal Port variant of the AQR113. Add PHY ID for it to provide support for it. Signed-off-by:
Christian Marangi <ansuelsmth@gmail.com> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
-
Breno Leitao authored
It is impossible to disable BQL individually today, since there is no prompt for the Kconfig entry, so, the BQL is always enabled if SYSFS is enabled. Create a prompt entry for BQL, so, it could be enabled or disabled at build time independently of SYSFS. Signed-off-by:
-
- 17 Feb, 2024 6 commits
-
-
David S. Miller authored
Heiner Kallweit says: ==================== net: phy: add support for the EEE 2 registers This series adds support for the EEE 2 registers. Most relevant and for now the only supported modes are 2500baseT and 5000baseT. ==================== Signed-off-by: -
Heiner Kallweit authored
Add support for handling the EEE advertisement 2 register. For now only 2500baseT and 5000baseT modes are supported. Signed-off-by:
Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by:
-
Heiner Kallweit authored
Add support for reading EEE link partner ability 2 register. Signed-off-by:
-
Heiner Kallweit authored
Add and use genphy_c45_read_eee_cap2(), complementing genphy_c45_read_eee_cap1(). Signed-off-by:
-
Heiner Kallweit authored
As a prerequisite for adding EEE CAP2 register support, complement PHY_EEE_CAP1_FEATURES with PHY_EEE_CAP2_FEATURES. For now only 2500baseT and 5000baseT modes are supported. Signed-off-by:
-
Heiner Kallweit authored
This adds helpers for accessing the EEE CAP2 registers. For now only 2500baseT and 5000baseT modes are supported. Signed-off-by:
-
- 16 Feb, 2024 15 commits
-
-
Ivan Vecera authored
The VEB (virtual embedded switch) as a switch element can be connected according datasheet though its uplink to: - Physical port - Port Virtualizer (not used directly by i40e driver but can be present in MFP mode where the physical port is shared between PFs) - No uplink (aka floating VEB) But VEB uplink cannot be connected to another VEB and any attempt to do so results in: "i40e 0000:02:00.0: couldn't add VEB, err -EIO aq_err I40E_AQ_RC_ENOENT" that indicates "the uplink SEID does not point to valid element". Remove this logic from the driver code this way: 1) For debugfs only allow to build floating VEB (uplink_seid == 0) or main VEB (uplink_seid == mac_seid) 2) Do not recurse in i40e_veb_link_event() as no VEB cannot have sub-VEBs 3) Ditto for i40e_veb_rebuild() + simplify the function as we know that the VEB for rebuild can be only the main LAN VEB or some of the floating VEBs 4) In i40e_rebuild() there is no need to check veb->uplink_seid as the possible ones are 0 and MAC SEID 5) In i40e_vsi_release() do not take into account VEBs whose uplink is another VEB as this is not possible 6) Remove veb_idx field from i40e_veb as a VEB cannot have sub-VEBs Tested using i40e debugfs interface: 1) Initial state [root@cnb-03 net-next]# CMD="/sys/kernel/debug/i40e/0000:02:00.0/command" [root@cnb-03 net-next]# echo dump switch > $CMD [root@cnb-03 net-next]# dmesg -c [ 98.440641] i40e 0000:02:00.0: header: 3 reported 3 total [ 98.446053] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 98.452593] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 98.458856] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 2) Add floating VEB [root@cnb-03 net-next]# echo add relay > $CMD [root@cnb-03 net-next]# dmesg -c [ 122.745630] i40e 0000:02:00.0: added relay 162 [root@cnb-03 net-next]# echo dump switch > $CMD [root@cnb-03 net-next]# dmesg -c [ 136.650049] i40e 0000:02:00.0: header: 4 reported 4 total [ 136.655466] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 136.661994] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 136.668264] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 [ 136.674787] i40e 0000:02:00.0: type=17 seid=162 uplink=0 downlink=0 3) Add VMDQ2 VSI to this new VEB [root@cnb-03 net-next]# dmesg -c [ 168.351763] i40e 0000:02:00.0: added VSI 394 to relay 162 [ 168.374652] enp2s0f0np0v0: NIC Link is Up, 40 Gbps Full Duplex, Flow Control: None [root@cnb-03 net-next]# echo dump switch > $CMD [root@cnb-03 net-next]# dmesg -c [ 195.683204] i40e 0000:02:00.0: header: 5 reported 5 total [ 195.688611] i40e 0000:02:00.0: type=19 seid=394 uplink=162 downlink=16 [ 195.695143] i40e 0000:02:00.0: type=17 seid=162 uplink=0 downlink=0 [ 195.701410] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 195.707935] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 195.714201] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 4) Try to delete the VEB [root@cnb-03 net-next]# echo del relay 162 > $CMD [root@cnb-03 net-next]# dmesg -c [ 239.260901] i40e 0000:02:00.0: deleting relay 162 [ 239.265621] i40e 0000:02:00.0: can't remove VEB 162 with 1 VSIs left 5) Do PF reset and check switch status after rebuild [root@cnb-03 net-next]# echo pfr > $CMD [root@cnb-03 net-next]# echo dump switch > $CMD [root@cnb-03 net-next]# dmesg -c ... [ 272.333655] i40e 0000:02:00.0: header: 5 reported 5 total [ 272.339066] i40e 0000:02:00.0: type=19 seid=394 uplink=162 downlink=16 [ 272.345599] i40e 0000:02:00.0: type=17 seid=162 uplink=0 downlink=0 [ 272.351862] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 272.358387] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 272.364654] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 6) Delete VSI and delete VEB [ 297.199116] i40e 0000:02:00.0: deleting VSI 394 [ 299.807580] i40e 0000:02:00.0: deleting relay 162 [ 309.767905] i40e 0000:02:00.0: header: 3 reported 3 total [ 309.773318] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 309.779845] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 309.786111] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 Reviewed-by:
Wojciech Drewek <wojciech.drewek@intel.com> Signed-off-by:
Ivan Vecera <ivecera@redhat.com> Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel) Reviewed-by:
Simon Horman <horms@kernel.org> Signed-off-by:
Tony Nguyen <anthony.l.nguyen@intel.com>
-
Ivan Vecera authored
Although the i40e supports so-called floating VEB (VEB without an uplink connection to external network), this support is broken. This functionality is currently unused (except debugfs) but it will be used by subsequent series for switchdev mode slow-path. Fix this by following: 1) Handle correctly floating VEB (VEB with uplink_seid == 0) in i40e_reconstitute_veb() and look for owner VSI and create it only for non-floating VEBs and also set bridge mode only for such VEBs as the floating ones are using always VEB mode. 2) Handle correctly floating VEB in i40e_veb_release() and disallow its release when there are some VSIs. This is different from regular VEB that have owner VSI that is connected to VEB's uplink after VEB deletion by FW. 3) Fix i40e_add_veb() to handle 'vsi' that is NULL for floating VEBs. For floating VEB use 0 for downlink SEID and 'true' for 'default_port' parameters as per datasheet. 4) Fix 'add relay' command in i40e_dbg_command_write() to allow to create floating VEB by 'add relay 0 0' or 'add relay' Tested using debugfs: 1) Initial state [root@host net-next]# echo dump switch > $CMD [root@host net-next]# dmesg -c [ 173.701286] i40e 0000:02:00.0: header: 3 reported 3 total [ 173.706701] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 173.713241] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 173.719507] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 2) Add floating VEB [root@host net-next]# CMD="/sys/kernel/debug/i40e/0000:02:00.0/command" [root@host net-next]# echo add relay > $CMD [root@host net-next]# dmesg -c [ 245.551720] i40e 0000:02:00.0: added relay 162 [root@host net-next]# echo dump switch > $CMD [root@host net-next]# dmesg -c [ 276.984371] i40e 0000:02:00.0: header: 4 reported 4 total [ 276.989779] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 276.996302] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 277.002569] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 [ 277.009091] i40e 0000:02:00.0: type=17 seid=162 uplink=0 downlink=0 3) Add VMDQ2 VSI to this new VEB [root@host net-next]# echo add vsi 162 > $CMD [root@host net-next]# dmesg -c [ 332.314030] i40e 0000:02:00.0: added VSI 394 to relay 162 [ 332.337486] enp2s0f0np0v0: NIC Link is Up, 40 Gbps Full Duplex, Flow Control: None [root@host net-next]# echo dump switch > $CMD [root@host net-next]# dmesg -c [ 387.284490] i40e 0000:02:00.0: header: 5 reported 5 total [ 387.289904] i40e 0000:02:00.0: type=19 seid=394 uplink=162 downlink=16 [ 387.296446] i40e 0000:02:00.0: type=17 seid=162 uplink=0 downlink=0 [ 387.302708] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 387.309234] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 387.315500] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 4) Try to delete the VEB [root@host net-next]# echo del relay 162 > $CMD [root@host net-next]# dmesg -c [ 428.749297] i40e 0000:02:00.0: deleting relay 162 [ 428.754011] i40e 0000:02:00.0: can't remove VEB 162 with 1 VSIs left 5) Do PF reset and check switch status after rebuild [root@host net-next]# echo pfr > $CMD [root@host net-next]# echo dump switch > $CMD [root@host net-next]# dmesg -c [ 738.056172] i40e 0000:02:00.0: header: 5 reported 5 total [ 738.061577] i40e 0000:02:00.0: type=19 seid=394 uplink=162 downlink=16 [ 738.068104] i40e 0000:02:00.0: type=17 seid=162 uplink=0 downlink=0 [ 738.074367] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 738.080892] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 738.087160] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 6) Delete VSI and delete VEB [root@host net-next]# echo del vsi 394 > $CMD [root@host net-next]# echo del relay 162 > $CMD [root@host net-next]# echo dump switch > $CMD [root@host net-next]# dmesg -c [ 1233.081126] i40e 0000:02:00.0: deleting VSI 394 [ 1239.345139] i40e 0000:02:00.0: deleting relay 162 [ 1244.886920] i40e 0000:02:00.0: header: 3 reported 3 total [ 1244.892328] i40e 0000:02:00.0: type=19 seid=392 uplink=160 downlink=16 [ 1244.898853] i40e 0000:02:00.0: type=17 seid=160 uplink=2 downlink=0 [ 1244.905119] i40e 0000:02:00.0: type=19 seid=390 uplink=160 downlink=16 Reviewed-by:
-
Ivan Vecera authored
Add two helpers i40e_(veb|vsi)_get_by_seid() to find corresponding VEB or VSI by their SEID value and use these helpers to replace existing open-coded loops. Reviewed-by:
-
Ivan Vecera authored
Introduce i40e_for_each_vsi() and i40e_for_each_veb() helper macros and use them to iterate relevant arrays. Replace pattern: for (i = 0; i < pf->num_alloc_vsi; i++) by: i40e_for_each_vsi(pf, i, vsi) and pattern: for (i = 0; i < I40E_MAX_VEB; i++) by i40e_for_each_veb(pf, i, veb) These macros also check if array item pf->vsi[i] or pf->veb[i] are not NULL and skip such items so we can remove redundant checks from loop bodies. Reviewed-by:
-
Ivan Vecera authored
Use existing i40e_find_vsi_by_type() to find a VSI associated with flow director. Reviewed-by:
-
Christian Marangi authored
Add Aquantia AQR113 PHY ID. Aquantia AQR113 is just a chip size variant of the already supported AQR133C where the only difference is the PHY ID and the hw chip size. Signed-off-by:
-
Diogo Ivo authored
Remove the duplicate calls to prueth_emac_stop() and prueth_cleanup_tx_chns() in emac_ndo_stop(). Signed-off-by:
Diogo Ivo <diogo.ivo@siemens.com> Reviewed-by:
Roger Quadros <rogerq@kernel.org> Reviewed-by:
MD Danish Anwar <danishanwar@ti.com> Reviewed-by:
Dan Carpenter <dan.carpenter@linaro.org> Signed-off-by:
-
Geert Uytterhoeven authored
Fix a misspelling of "circuit". Signed-off-by:
Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by:
-
David S. Miller authored
Shannon Nelson says: ==================== ionic: add XDP support This patchset is new support in ionic for XDP processing, including basic XDP on Rx packets, TX and REDIRECT, and frags for jumbo frames. Since ionic has not yet been converted to use the page_pool APIs, this uses the simple MEM_TYPE_PAGE_ORDER0 buffering. There are plans to convert the driver in the near future. v4: - removed "inline" from short utility functions - changed to use "goto err_out" in ionic_xdp_register_rxq_info() - added "continue" to reduce nesting in ionic_xdp_queues_config() - used xdp_prog in ionic_rx_clean() to flag whether or not to sync the rx buffer after calling ionix_xdp_run() - swapped order of XDP_TX and XDP_REDIRECT cases in ionic_xdp_run() to make patch 6 a little cleaner v3: https://lore.kernel.org/netdev/20240210004827.53814-1-shannon.nelson@amd.com/ - removed budget==0 patch, sent it separately to net v2: https://lore.kernel.org/netdev/20240208005725.65134-1-shannon.nelson@amd.com/ - added calls to txq_trans_cond_update() - added a new patch to catch NAPI budget==0 v1: https://lore.kernel.org/netdev/20240130013042.11586-1-shannon.nelson@amd.com/ RFC: https://lore.kernel.org/netdev/20240118192500.58665-1-shannon.nelson@amd.com/ ==================== Signed-off-by:
-
Shannon Nelson authored
Add support for using scatter-gather / frags in XDP in both Rx and Tx paths. Co-developed-by:
-
Shannon Nelson authored
When our ndo_xdp_xmit is called we mark the buffer with XDP_REDIRECT so we know to return it to the XDP stack for cleaning. Co-developed-by:
-
Shannon Nelson authored
The XDP_REDIRECT packets are given to the XDP stack and we drop the use of the related page: it will get freed by the driver that ends up doing the Tx. Because we have some hardware configurations with limited queue resources, we use the existing datapath Tx queues rather than creating and managing a separate set of xdp_tx queues. Co-developed-by:
-
Shannon Nelson authored
The XDP_TX packets get fed back into the Rx queue's partnered Tx queue as an xdp_frame. Co-developed-by:
-
Shannon Nelson authored
If an xdp program is loaded, add headroom at the beginning of the frame to allow for editing and insertions that an XDP program might need room for, and tailroom used later for XDP frame tracking. These are only needed in the first Rx buffer in a packet, not for any trailing frags. Co-developed-by:
-
Shannon Nelson authored
Set up the basics for running Rx packets through XDP programs. Add new queue setup and teardown steps for adding/removing an XDP program, and add the call to run the XDP on a packet. The XDP frame size needs to be the MTU plus standard ethernet header, plus head room for XDP scribblings and tail room for a struct skb_shared_info. Also, at this point, we don't support XDP frags, only a single contiguous Rx buffer. This means that our page splitting is not very useful, so when XDP is in use we need to use the full Rx buffer size and not do sharing. Co-developed-by:
-
