aboutsummaryrefslogtreecommitdiff
path: root/Documentation/networking/net_cachelines
AgeCommit message (Collapse)AuthorFilesLines
2024-09-05net: napi: Prevent overflow of napi_defer_hard_irqsJoe Damato1-1/+1
In commit 6f8b12d661d0 ("net: napi: add hard irqs deferral feature") napi_defer_irqs was added to net_device and napi_defer_irqs_count was added to napi_struct, both as type int. This value never goes below zero, so there is not reason for it to be a signed int. Change the type for both from int to u32, and add an overflow check to sysfs to limit the value to S32_MAX. The limit of S32_MAX was chosen because the practical limit before this patch was S32_MAX (anything larger was an overflow) and thus there are no behavioral changes introduced. If the extra bit is needed in the future, the limit can be raised. Before this patch: $ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs' $ cat /sys/class/net/eth4/napi_defer_hard_irqs -2147483647 After this patch: $ sudo bash -c 'echo 2147483649 > /sys/class/net/eth4/napi_defer_hard_irqs' bash: line 0: echo: write error: Numerical result out of range Similarly, /sys/class/net/XXXXX/tx_queue_len is defined as unsigned: include/linux/netdevice.h: unsigned int tx_queue_len; And has an overflow check: dev_change_tx_queue_len(..., unsigned long new_len): if (new_len != (unsigned int)new_len) return -ERANGE; Suggested-by: Jakub Kicinski <[email protected]> Signed-off-by: Joe Damato <[email protected]> Reviewed-by: Eric Dumazet <[email protected]> Link: https://patch.msgid.link/[email protected] Signed-off-by: Jakub Kicinski <[email protected]>
2024-09-03netdev_features: convert NETIF_F_FCOE_MTU to dev->fcoe_mtuAlexander Lobakin1-0/+1
Ability to handle maximum FCoE frames of 2158 bytes can never be changed and thus more of an attribute, not a toggleable feature. Move it from netdev_features_t to "cold" priv flags (bitfield bool) and free yet another feature bit. Signed-off-by: Alexander Lobakin <[email protected]> Signed-off-by: Paolo Abeni <[email protected]>
2024-09-03netdev_features: convert NETIF_F_NETNS_LOCAL to dev->netns_localAlexander Lobakin1-0/+1
"Interface can't change network namespaces" is rather an attribute, not a feature, and it can't be changed via Ethtool. Make it a "cold" private flag instead of a netdev_feature and free one more bit. Signed-off-by: Alexander Lobakin <[email protected]> Signed-off-by: Paolo Abeni <[email protected]>
2024-09-03netdev_features: convert NETIF_F_LLTX to dev->lltxAlexander Lobakin1-0/+1
NETIF_F_LLTX can't be changed via Ethtool and is not a feature, rather an attribute, very similar to IFF_NO_QUEUE (and hot). Free one netdev_features_t bit and make it a "hot" private flag. Signed-off-by: Alexander Lobakin <[email protected]> Signed-off-by: Paolo Abeni <[email protected]>
2024-09-03netdevice: convert private flags > BIT(31) to bitfieldsAlexander Lobakin1-1/+3
Make dev->priv_flags `u32` back and define bits higher than 31 as bitfield booleans as per Jakub's suggestion. This simplifies code which accesses these bits with no optimization loss (testb both before/after), allows to not extend &netdev_priv_flags each time, but also scales better as bits > 63 in the future would only add a new u64 to the structure with no complications, comparing to that extending ::priv_flags would require converting it to a bitmap. Note that I picked `unsigned long :1` to not lose any potential optimizations comparing to `bool :1` etc. Suggested-by: Jakub Kicinski <[email protected]> Signed-off-by: Alexander Lobakin <[email protected]> Signed-off-by: Paolo Abeni <[email protected]>
2024-08-30Documentation: Add missing fields to net_cachelinesJoe Damato1-0/+2
Two fields, page_pools and *irq_moder, were added to struct net_device in commit 083772c9f972 ("net: page_pool: record pools per netdev") and commit f750dfe825b9 ("ethtool: provide customized dim profile management"), respectively. Add both to the net_cachelines documentation, as well. Signed-off-by: Joe Damato <[email protected]> Link: https://patch.msgid.link/[email protected] Signed-off-by: Jakub Kicinski <[email protected]>
2024-03-19net: move dev->state into net_device_read_txrx groupEric Dumazet1-1/+1
dev->state can be read in rx and tx fast paths. netif_running() which needs dev->state is called from - enqueue_to_backlog() [RX path] - __dev_direct_xmit() [TX path] Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables") Signed-off-by: Eric Dumazet <[email protected]> Cc: Coco Li <[email protected]> Reviewed-by: Jiri Pirko <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Paolo Abeni <[email protected]>
2024-02-28Documentations: correct net_cachelines title for struct inet_sockHaiyue Wang1-3/+3
The fast path usage breakdown describes the detail for 'inet_sock', fix the markup title. Signed-off-by: Haiyue Wang <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2024-02-12net-device: move lstats in net_device_read_txrxEric Dumazet1-2/+2
dev->lstats is notably used from loopback ndo_start_xmit() and other virtual drivers. Per cpu stats updates are dirtying per-cpu data, but the pointer itself is read-only. Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables") Signed-off-by: Eric Dumazet <[email protected]> Cc: Coco Li <[email protected]> Cc: Simon Horman <[email protected]> Reviewed-by: Simon Horman <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2024-02-12tcp: move tp->tcp_usec_ts to tcp_sock_read_txrx groupEric Dumazet1-1/+1
tp->tcp_usec_ts is a read mostly field, used in rx and tx fast paths. Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables") Signed-off-by: Eric Dumazet <[email protected]> Cc: Coco Li <[email protected]> Cc: Wei Wang <[email protected]> Reviewed-by: Simon Horman <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2024-02-12tcp: move tp->scaling_ratio to tcp_sock_read_txrx groupEric Dumazet1-1/+1
tp->scaling_ratio is a read mostly field, used in rx and tx fast paths. Fixes: d5fed5addb2b ("tcp: reorganize tcp_sock fast path variables") Signed-off-by: Eric Dumazet <[email protected]> Cc: Coco Li <[email protected]> Cc: Wei Wang <[email protected]> Reviewed-by: Simon Horman <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2024-01-03net-device: move xdp_prog to net_device_read_rxEric Dumazet1-1/+1
xdp_prog is used in receive path, both from XDP enabled drivers and from netif_elide_gro(). This patch also removes two 4-bytes holes. Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables") Signed-off-by: Eric Dumazet <[email protected]> Cc: Coco Li <[email protected]> Cc: Simon Horman <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jakub Kicinski <[email protected]>
2024-01-02net-device: move gso_partial_features to net_device_read_txEric Dumazet1-1/+1
dev->gso_partial_features is read from tx fast path for GSO packets. Move it to appropriate section to avoid a cache line miss. Fixes: 43a71cd66b9c ("net-device: reorganize net_device fast path variables") Signed-off-by: Eric Dumazet <[email protected]> Cc: Coco Li <[email protected]> Cc: David Ahern <[email protected]> Reviewed-by: Simon Horman <[email protected]> Signed-off-by: David S. Miller <[email protected]>
2023-12-05Documentations: fix net_cachelines documentation build warningCoco Li7-0/+7
Original errors: Documentation/networking/net_cachelines/index.rst:3: WARNING: Explicit markup ends without a blank line; unexpected unindent. Documentation/networking/net_cachelines/inet_connection_sock.rst:3: WARNING: Explicit markup ends without a blank line; unexpected unindent. Documentation/networking/net_cachelines/inet_sock.rst:3: WARNING: Explicit markup ends without a blank line; unexpected unindent. Documentation/networking/net_cachelines/net_device.rst:3: WARNING: Explicit markup ends without a blank line; unexpected unindent. Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst:3: WARNING: Explicit markup ends without a blank line; unexpected unindent. Documentation/networking/net_cachelines/snmp.rst:3: WARNING: Explicit markup ends without a blank line; unexpected unindent. Documentation/networking/net_cachelines/tcp_sock.rst:3: WARNING: Explicit markup ends without a blank line; unexpected unindent. Fixes: 14006f1d8fa2 ("Documentations: Analyze heavily used Networking related structs") Signed-off-by: Coco Li <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jakub Kicinski <[email protected]>
2023-12-02Documentations: Analyze heavily used Networking related structsCoco Li7-0/+731
Analyzed a few structs in the networking stack by looking at variables within them that are used in the TCP/IP fast path. Fast path is defined as TCP path where data is transferred from sender to receiver unidirectionally. It doesn't include phases other than TCP_ESTABLISHED, nor does it look at error paths. We hope to re-organizing variables that span many cachelines whose fast path variables are also spread out, and this document can help future developers keep networking fast path cachelines small. Optimized_cacheline field is computed as (Fastpath_Bytes/L3_cacheline_size_x86), and not the actual organized results (see patches to come for these). Investigation is done on 6.5 Name Struct_Cachelines Cur_fastpath_cache Fastpath_Bytes Optimized_cacheline tcp_sock 42 (2664 Bytes) 12 396 8 net_device 39 (2240 bytes) 12 234 4 inet_sock 15 (960 bytes) 14 922 14 Inet_connection_sock 22 (1368 bytes) 18 1166 18 Netns_ipv4 (sysctls) 12 (768 bytes) 4 77 2 linux_mib 16 (1060) 6 104 2 Note how there isn't much improvement space for inet_sock and Inet_connection_sock because sk and icsk_inet respectively takes up so much of the struct that rest of the variables become a small portion of the struct size. So, we decided to reorganize tcp_sock, net_device, netns_ipv4 Suggested-by: Eric Dumazet <[email protected]> Signed-off-by: Coco Li <[email protected]> Reviewed-by: Eric Dumazet <[email protected]> Reviewed-by: Shakeel Butt <[email protected]> Signed-off-by: David S. Miller <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.