kernel/linux.git/include/linux/dynamic_queue_limits.h, branch v6.19.11

dql: annotate data-races around dql->last_obj_cnt

2024-11-01T02:19:36+00:00

dql->last_obj_cnt is read/written from different contexts, without any lock synchronization. Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing. Signed-off-by: Eric Dumazet Reviewed-by: Joe Damato Link: https://patch.msgid.link/20241029191425.2519085-1-edumazet@google.com Signed-off-by: Jakub Kicinski

net: dqs: make struct dql more cache efficient

2024-04-15T18:19:53+00:00

With the previous change, struct dqs->stall_thrs will be in the hot path (at queue side), even if DQS is disabled. The other fields accessed in this function (last_obj_cnt and num_queued) are in the first cache line, let's move this field (stall_thrs) to the very first cache line, since there is a hole there. This does not change the structure size, since it moves an short (2 bytes) to 4-bytes whole in the first cache line. This is the new structure format now: struct dql { unsigned int num_queued; unsigned int last_obj_cnt; ... short unsigned int stall_thrs; /* XXX 2 bytes hole, try to pack */ ... /* --- cacheline 1 boundary (64 bytes) --- */ ... /* Longest stall detected, reported to user */ short unsigned int stall_max; /* XXX 2 bytes hole, try to pack */ }; Also, read the stall_thrs (now in the very first cache line) earlier, together with dql->num_queued (also in the first cache line). Suggested-by: Jakub Kicinski Suggested-by: Eric Dumazet Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240411192241.2498631-5-leitao@debian.org Signed-off-by: Jakub Kicinski

net: dql: Optimize stall information population

2024-04-15T18:19:52+00:00

When Dynamic Queue Limit (DQL) is set, it always populate stall information through dql_queue_stall(). However, this information is only necessary if a stall threshold is set, stored in struct dql->stall_thrs. dql_queue_stall() is cheap, but not free, since it does have memory barriers and so forth. Do not call dql_queue_stall() if there is no stall threshold set, and save some CPU cycles. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240411192241.2498631-4-leitao@debian.org Signed-off-by: Jakub Kicinski

net: dql: Separate queue function responsibilities

2024-04-15T18:19:52+00:00

The dql_queued() function currently handles both queuing object counts and populating bitmaps for reporting stalls. This commit splits the bitmap population into a separate function, allowing for conditional invocation in scenarios where the feature is disabled. This refactor maintains functionality while improving code organization. Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240411192241.2498631-3-leitao@debian.org Signed-off-by: Jakub Kicinski

net: dql: Avoid calling BUG() when WARN() is enough

2024-04-15T18:19:52+00:00

If the dql_queued() function receives an invalid argument, WARN about it and continue, instead of crashing the kernel. This was raised by checkpatch, when I am refactoring this code (see following patch/commit) WARNING: Do not crash the kernel unless it is absolutely unavoidable--use WARN_ON_ONCE() plus recovery code (if feasible) instead of BUG() or variants Signed-off-by: Breno Leitao Link: https://lore.kernel.org/r/20240411192241.2498631-2-leitao@debian.org Signed-off-by: Jakub Kicinski

net: dqs: add NIC stall detector based on BQL

2024-03-08T10:23:26+00:00

softnet_data->time_squeeze is sometimes used as a proxy for host overload or indication of scheduling problems. In practice this statistic is very noisy and has hard to grasp units - e.g. is 10 squeezes a second to be expected, or high? Delaying network (NAPI) processing leads to drops on NIC queues but also RTT bloat, impacting pacing and CA decisions. Stalls are a little hard to detect on the Rx side, because there may simply have not been any packets received in given period of time. Packet timestamps help a little bit, but again we don't know if packets are stale because we're not keeping up or because someone (*cough* cgroups) disabled IRQs for a long time. We can, however, use Tx as a proxy for Rx stalls. Most drivers use combined Rx+Tx NAPIs so if Tx gets starved so will Rx. On the Tx side we know exactly when packets get queued, and completed, so there is no uncertainty. This patch adds stall checks to BQL. Why BQL? Because it's a convenient place to add such checks, already called by most drivers, and it has copious free space in its structures (this patch adds no extra cache references or dirtying to the fast path). The algorithm takes one parameter - max delay AKA stall threshold and increments a counter whenever NAPI got delayed for at least that amount of time. It also records the length of the longest stall. To be precise every time NAPI has not polled for at least stall thrs we check if there were any Tx packets queued between last NAPI run and now - stall_thrs/2. Unlike the classic Tx watchdog this mechanism does not ignore stalls caused by Tx being disabled, or loss of link. I don't think the check is worth the complexity, and stall is a stall, whether due to host overload, flow control, link down... doesn't matter much to the application. We have been running this detector in production at Meta for 2 years, with the threshold of 8ms. It's the lowest value where false positives become rare. There's still a constant stream of reported stalls (especially without the ksoftirqd deferral patches reverted), those who like their stall metrics to be 0 may prefer higher value. Signed-off-by: Jakub Kicinski Signed-off-by: Breno Leitao Signed-off-by: David S. Miller

locking/seqlock, headers: Untangle the spaghetti monster

2020-08-06T14:13:13+00:00

By using lockdep_assert_*() from seqlock.h, the spaghetti monster attacked. Attack back by reducing seqlock.h dependencies from two key high level headers: - : -Remove - : -Remove - : +Add The price was to add it to sched.h ... Core header fallout, we add direct header dependencies instead of gaining them parasitically from higher level headers: - : +Add - : +Add - : +Add - : +Add - : +Add - : +Add Arch headers fallout: - PARISC: : +Add - SH: : +Add - SPARC: : +Add - SPARC: : +Add , -Remove - X86: : +Add -Remove There's also a bunch of parasitic header dependency fallout in .c files, not listed separately. [ mingo: Extended the changelog, split up & fixed the original patch. ] Co-developed-by: Ingo Molnar Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Link: https://lore.kernel.org/r/20200804133438.GK2674@hirez.programming.kicks-ass.net

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

2017-11-15T19:56:19+00:00

Pull networking updates from David Miller: "Highlights: 1) Maintain the TCP retransmit queue using an rbtree, with 1GB windows at 100Gb this really has become necessary. From Eric Dumazet. 2) Multi-program support for cgroup+bpf, from Alexei Starovoitov. 3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew Lunn. 4) Add meter action support to openvswitch, from Andy Zhou. 5) Add a data meta pointer for BPF accessible packets, from Daniel Borkmann. 6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet. 7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli. 8) More work to move the RTNL mutex down, from Florian Westphal. 9) Add 'bpftool' utility, to help with bpf program introspection. From Jakub Kicinski. 10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper Dangaard Brouer. 11) Support 'blocks' of transformations in the packet scheduler which can span multiple network devices, from Jiri Pirko. 12) TC flower offload support in cxgb4, from Kumar Sanghvi. 13) Priority based stream scheduler for SCTP, from Marcelo Ricardo Leitner. 14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg. 15) Add RED qdisc offloadability, and use it in mlxsw driver. From Nogah Frankel. 16) eBPF based device controller for cgroup v2, from Roman Gushchin. 17) Add some fundamental tracepoints for TCP, from Song Liu. 18) Remove garbage collection from ipv6 route layer, this is a significant accomplishment. From Wei Wang. 19) Add multicast route offload support to mlxsw, from Yotam Gigi" * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits) tcp: highest_sack fix geneve: fix fill_info when link down bpf: fix lockdep splat net: cdc_ncm: GetNtbFormat endian fix openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start netem: remove unnecessary 64 bit modulus netem: use 64 bit divide by rate tcp: Namespace-ify sysctl_tcp_default_congestion_control net: Protect iterations over net::fib_notifier_ops in fib_seq_sum() ipv6: set all.accept_dad to 0 by default uapi: fix linux/tls.h userspace compilation error usbnet: ipheth: prevent TX queue timeouts when device not ready vhost_net: conditionally enable tx polling uapi: fix linux/rxrpc.h userspace compilation errors net: stmmac: fix LPI transitioning for dwmac4 atm: horizon: Fix irq release error net-sysfs: trigger netlink notification on ifalias change via sysfs openvswitch: Using kfree_rcu() to simplify the code openvswitch: Make local function ovs_nsh_key_attr_size() static openvswitch: Fix return value check in ovs_meter_cmd_features() ...

Merge branch 'linus' into locking/core, to resolve conflicts

2017-11-07T09:32:44+00:00

Conflicts: include/linux/compiler-clang.h include/linux/compiler-gcc.h include/linux/compiler-intel.h include/uapi/linux/stddef.h Signed-off-by: Ingo Molnar

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

2017-11-04T00:26:51+00:00

Files removed in 'net-next' had their license header updated in 'net'. We take the remove from 'net-next'. Signed-off-by: David S. Miller