summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2018-10-16IB/mlx5: Verify DEVX object typeYishai Hadas
Verify that the input DEVX object type matches the created object. As the obj_id in the firmware is not globally unique the object type must be considered upon checking for a valid object id. Once both the type and the id match we know that the lock was taken on the correct object by the uverbs layer. Fixes: e662e14d801b ("IB/mlx5: Add DEVX support for modify and query commands") Signed-off-by: Yishai Hadas <yishaih@mellanox.com> Reviewed-by: Artemy Kovalyov <artemyko@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-15Merge branch 'nfp-fix-pedit-set-action-offloads'David S. Miller
Jakub Kicinski says: ==================== nfp: fix pedit set action offloads Pieter says: This set fixes set actions when using multiple pedit actions with partial masks and with multiple keys per pedit action. Additionally it fixes set ipv6 pedit action offloads when using it in combination with other header keys. The problem would only trigger if one combines multiple pedit actions of the same type with partial masks, e.g.: $ tc filter add dev netdev protocol ip parent ffff: \ flower indev netdev \ ip_proto tcp \ action pedit ex munge \ ip src set 11.11.11.11 retain 65535 munge \ ip src set 22.22.22.22 retain 4294901760 pipe \ csum ip and tcp pipe \ mirred egress redirect dev netdev ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15nfp: flower: use offsets provided by pedit instead of index for ipv6Pieter Jansen van Vuuren
Previously when populating the set ipv6 address action, we incorrectly made use of pedit's key index to determine which 32bit word should be set. We now calculate which word has been selected based on the offset provided by the pedit action. Fixes: 354b82bb320e ("nfp: add set ipv6 source and destination address") Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15nfp: flower: fix multiple keys per pedit actionPieter Jansen van Vuuren
Previously we only allowed a single header key per pedit action to change the header. This used to result in the last header key in the pedit action to overwrite previous headers. We now keep track of them and allow multiple header keys per pedit action. Fixes: c0b1bd9a8b8a ("nfp: add set ipv4 header action flower offload") Fixes: 354b82bb320e ("nfp: add set ipv6 source and destination address") Fixes: f8b7b0a6b113 ("nfp: add set tcp and udp header action flower offload") Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15nfp: flower: fix pedit set actions for multiple partial masksPieter Jansen van Vuuren
Previously we did not correctly change headers when using multiple pedit actions with partial masks. We now take this into account and no longer just commit the last pedit action. Fixes: c0b1bd9a8b8a ("nfp: add set ipv4 header action flower offload") Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-16RDMA/hns: Add FRMR support for hip08Yixian Liu
This patch adds fast register physical memory region (FRMR) support for hip08. Signed-off-by: Yixian Liu <liuyixian@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-15rxrpc: Fix a missing rxrpc_put_peer() in the error_report handlerDavid Howells
Fix a missing call to rxrpc_put_peer() on the main path through the rxrpc_error_report() function. This manifests itself as a ref leak whenever an ICMP packet or other error comes in. In commit f334430316e7, the hand-off of the ref to a work item was removed and was not replaced with a put. Fixes: f334430316e7 ("rxrpc: Fix error distribution") Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15net: phy: merge phy_start_aneg and phy_start_aneg_privHeiner Kallweit
After commit 9f2959b6b52d ("net: phy: improve handling delayed work") the sync parameter isn't needed any longer in phy_start_aneg_priv(). This allows to merge phy_start_aneg() and phy_start_aneg_priv(). Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15MIPS: dts: Change upper case to lower caseSongjun Wu
All the upper case in unit-address and hex constants are changed to lower case according to the DT conventions. Signed-off-by: Songjun Wu <songjun.wu@linux.intel.com> Signed-off-by: Paul Burton <paul.burton@mips.com> Reviewed-by: Rob Herring <robh@kernel.org> Patchwork: https://patchwork.linux-mips.org/patch/20768/ Cc: yixin.zhu@linux.intel.com Cc: chuanhua.lei@linux.intel.com Cc: hauke.mehrtens@intel.com Cc: devicetree@vger.kernel.org Cc: James Hogan <jhogan@kernel.org> Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Philippe Ombredanne <pombredanne@nexb.com> Cc: Rob Herring <robh+dt@kernel.org> Cc: Kate Stewart <kstewart@linuxfoundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Ralf Baechle <ralf@linux-mips.org>
2018-10-15MIPS: generic: Add Network, SPI and I2C to ocelot_defconfigAlexandre Belloni
Add support for the integrated switch, and the SPI and I2C controller found on MSCC Ocelot. Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com> Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20345/ Cc: James Hogan <jhogan@kernel.org> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-kernel@vger.kernel.org Cc: linux-mips@linux-mips.org
2018-10-15MIPS: Loongson-3: Fix BRIDGE irq delivery problemHuacai Chen
After commit e509bd7da149dc349160 ("genirq: Allow migration of chained interrupts by installing default action") Loongson-3 fails at here: setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction); This is because both chained_action and cascade_irqaction don't have IRQF_SHARED flag. This will cause Loongson-3 resume fails because HPET timer interrupt can't be delivered during S3. So we set the irqchip of the chained irq to loongson_irq_chip which doesn't disable the chained irq in CP0.Status. Cc: stable@vger.kernel.org Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20434/ Cc: Ralf Baechle <ralf@linux-mips.org> Cc: James Hogan <jhogan@kernel.org> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: Huacai Chen <chenhuacai@gmail.com>
2018-10-15MIPS: Loongson-3: Fix CPU UART irq delivery problemHuacai Chen
Masking/unmasking the CPU UART irq in CP0_Status (and redirecting it to other CPUs) may cause interrupts be lost, especially in multi-package machines (Package-0's UART irq cannot be delivered to others). So make mask_loongson_irq() and unmask_loongson_irq() be no-ops. The original problem (UART IRQ may deliver to any core) is also because of masking/unmasking the CPU UART irq in CP0_Status. So it is safe to remove all of the stuff. Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20433/ Cc: Ralf Baechle <ralf@linux-mips.org> Cc: James Hogan <jhogan@kernel.org> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: Huacai Chen <chenhuacai@gmail.com>
2018-10-15MIPS: Remove unused PREF, PREFE & PREFX macrosPaul Burton
asm/asm.h provides PREF(), PREFE() & PREFX() macros which are now entirely unused. Delete the dead code. Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20908/ Cc: linux-mips@linux-mips.org
2018-10-15MIPS: lib: Use kernel_pref & user_pref in memcpy()Paul Burton
memcpy() is the only user of the PREF() & PREFE() macros from asm/asm.h. Switch to using the kernel_pref() & user_pref() macros from asm/asm-eva.h which fit more consistently with other abstractions of EVA vs non-EVA instructions. Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20907/ Cc: linux-mips@linux-mips.org
2018-10-15MIPS: Remove unused CAT macroPaul Burton
asm/asm.h provides a CAT macro which is unused throughout the tree, and if anyone wanted it the generic CONCATENATE macro in linux/kernel.h provides the same functionality. Delete the dead code. Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20905/ Cc: linux-mips@linux-mips.org
2018-10-15MIPS: Add kernel_pref & user_pref helpersPaul Burton
Add kernel_pref & user_pref macros to asm/asm-eva.h, providing an abstraction around EVA & non-EVA pref instructions consistent with the existing macros we have for cache & load/store instructions. Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20906/ Cc: linux-mips@linux-mips.org
2018-10-15MIPS: Remove unused TTABLE macroPaul Burton
asm/asm.h contains a TTABLE macro to generate "text tables" which would appear to be arrays of pointers to strings. It is unused throughout the kernel tree, so delete the dead code. Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20904/ Cc: linux-mips@linux-mips.org
2018-10-15MIPS: Remove unused PIC macrosPaul Burton
asm/asm.h contains CPRESTORE, CPADD & CPLOAD macros that are intended for use with position independent code, but are not used anywhere in the kernel - along with a comment to that effect. Remove the dead code. Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20903/ Cc: linux-mips@linux-mips.org
2018-10-15MIPS: Remove unused MOVN & MOVZ macrosPaul Burton
We have macros in asm/asm.h to allow for use of the MOVN & MOVZ instructions with compare-and-branch sequences providing compatibility for ISA versions which don't include those instructions. However the macros are unused, and appear to have always been unused. Delete the dead code. Signed-off-by: Paul Burton <paul.burton@mips.com> Patchwork: https://patchwork.linux-mips.org/patch/20909/ Cc: linux-mips@linux-mips.org
2018-10-16RDMA/bnxt_re: Avoid resource leak in case the NQ registration failsSelvin Xavier
In case the NQ alloc/enable fails, free up the already allocated/enabled NQ before reporting failure. Also, track the alloc/enable using proper state checking. Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Wait for delayed work to finish before device removalSelvin Xavier
Delayed work bnxt_re_worker would be still running even after cancel_delayed_work returns. This causes crash as the driver proceeds with device removal. To make sure that the work is finished before returning, use cancel_delayed_work_sync. Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Limit max_pkey to 16 bit valueDevesh Sharma
Some FW versios return pkey values more than 0xFFFF. pkey_tbl_len of ib_port_attr is 16bit value. So restricting max_pkeys to 0xFFFF. Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com> Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Fix qp async event reportingDevesh Sharma
Reports affiliated async event on the qp-async event channel instead of global event channel. Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com> Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Report out of sequence hw countersSelvin Xavier
Expose out of sequence errors received from FW. This counter is a 32 bit counter and driver has to accumulate the counter. Stores the previous value for calculating the difference in the next query. Also, update the HW statistics structure with new fields. Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Expose rx discards and drop countersSelvin Xavier
Expose the RoCE discard and drop counters from the HW statistics context Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Prevent driver crash due to NULL pointer in error message printSomnath Kotur
crsqe->resp would be NULL in case the host command timed out before getting a response from HW. Check for NULL pointer to avoid a potential crash while printing the error message. Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com> Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Drop L2 async events silentlyDevesh Sharma
In some FW versions, RoCE driver also receives an async notification which was directed to L2 driver. RoCE driver does not handle this and print a message to syslog. Drop these notifications silently. Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com> Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Avoid accessing nq->bar_reg_iomem in failure caseSelvin Xavier
In the failure path, nq->bar_reg_iomem gets accessed without initializing. Avoid this by calling the bnxt_qplib_nq_stop_irq only if the initialization is complete. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Fixes: 6e04b1035689 ("RDMA/bnxt_re: Fix broken RoCE driver due to recent L2 driver changes") Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Avoid NULL check after accessing the pointerSelvin Xavier
This is reported by smatch check. rcfw->creq_bar_reg_iomem is accessed in bnxt_qplib_rcfw_stop_irq and this variable check afterwards doesn't make sense. Also, rcfw->creq_bar_reg_iomem will never be NULL. So Removing this check. Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Fixes: 6e04b1035689 ("RDMA/bnxt_re: Fix broken RoCE driver due to recent L2 driver changes") Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Remove the unnecessary version macro definitionSelvin Xavier
Version macro is not required as the driver is not maintaining the version. Removing the references of this macro too. Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Fix recursive lock warning in debug kernelSelvin Xavier
Fix possible recursive lock warning. Its a false warning as the locks are part of two differnt HW Queue data structure - cmdq and creq. Debug kernel is throwing the following warning and stack trace. [ 783.914967] ============================================ [ 783.914970] WARNING: possible recursive locking detected [ 783.914973] 4.19.0-rc2+ #33 Not tainted [ 783.914976] -------------------------------------------- [ 783.914979] swapper/2/0 is trying to acquire lock: [ 783.914982] 000000002aa3949d (&(&hwq->lock)->rlock){..-.}, at: bnxt_qplib_service_creq+0x232/0x350 [bnxt_re] [ 783.914999] but task is already holding lock: [ 783.915002] 00000000be73920d (&(&hwq->lock)->rlock){..-.}, at: bnxt_qplib_service_creq+0x2a/0x350 [bnxt_re] [ 783.915013] other info that might help us debug this: [ 783.915016] Possible unsafe locking scenario: [ 783.915019] CPU0 [ 783.915021] ---- [ 783.915034] lock(&(&hwq->lock)->rlock); [ 783.915035] lock(&(&hwq->lock)->rlock); [ 783.915037] *** DEADLOCK *** [ 783.915038] May be due to missing lock nesting notation [ 783.915039] 1 lock held by swapper/2/0: [ 783.915040] #0: 00000000be73920d (&(&hwq->lock)->rlock){..-.}, at: bnxt_qplib_service_creq+0x2a/0x350 [bnxt_re] [ 783.915044] stack backtrace: [ 783.915046] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 4.19.0-rc2+ #33 [ 783.915047] Hardware name: Dell Inc. PowerEdge R730/0599V5, BIOS 1.0.4 08/28/2014 [ 783.915048] Call Trace: [ 783.915049] <IRQ> [ 783.915054] dump_stack+0x90/0xe3 [ 783.915058] __lock_acquire+0x106c/0x1080 [ 783.915061] ? sched_clock+0x5/0x10 [ 783.915063] lock_acquire+0xbd/0x1a0 [ 783.915065] ? bnxt_qplib_service_creq+0x232/0x350 [bnxt_re] [ 783.915069] _raw_spin_lock_irqsave+0x4a/0x90 [ 783.915071] ? bnxt_qplib_service_creq+0x232/0x350 [bnxt_re] [ 783.915073] bnxt_qplib_service_creq+0x232/0x350 [bnxt_re] [ 783.915078] tasklet_action_common.isra.17+0x197/0x1b0 [ 783.915081] __do_softirq+0xcb/0x3a6 [ 783.915084] irq_exit+0xe9/0x100 [ 783.915085] do_IRQ+0x6a/0x120 [ 783.915087] common_interrupt+0xf/0xf [ 783.915088] </IRQ> Use nested notation for the spin_lock to avoid this warning. Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16RDMA/bnxt_re: Add missing spin lock initializationSelvin Xavier
Add the missing initalization of the cq_lock and qplib.flush_lock. Fixes: 942c9b6ca8de ("RDMA/bnxt_re: Avoid Hard lockup during error CQE processing") Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-16Merge branch 'for-rc' into rdma.git for-nextJason Gunthorpe
From git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git This is required to resolve dependencies of the next series of RDMA patches. The code motion conflicts in drivers/infiniband/core/cache.c were resolved. Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-15hv_netvsc: fix vf serial matching with pci slot infoHaiyang Zhang
The VF device's serial number is saved as a string in PCI slot's kobj name, not the slot->number. This patch corrects the netvsc driver, so the VF device can be successfully paired with synthetic NIC. Fixes: 00d7ddba1143 ("hv_netvsc: pair VF based on serial number") Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com> Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com> Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15Merge branch 'tcp-second-round-for-EDT-conversion'David S. Miller
Eric Dumazet says: ==================== tcp: second round for EDT conversion First round of EDT patches left TCP stack in a non optimal state. - High speed flows suffered from loss of performance, addressed by the first patch of this series. - Second patch brings pacing to the current state of networking, since we now reach ~100 Gbit on a single TCP flow. - Third patch implements a mitigation for scheduling delays, like the one we did in sch_fq in the past. - Fourth patch removes one special case in sch_fq for ACK packets. - Fifth patch removes a serious perfomance cost for TCP internal pacing. We should setup the high resolution timer only if really needed. - Sixth patch fixes a typo in BBR. - Last patch is one minor change in cdg congestion control. Neal Cardwell also has a patch series fixing BBR after EDT adoption. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15tcp: cdg: use tcp high resolution clock cacheEric Dumazet
We store in tcp socket a cache of most recent high resolution clock, there is no need to call local_clock() again, since this cache is good enough. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15tcp_bbr: fix typo in bbr_pacing_margin_percentNeal Cardwell
There was a typo in this parameter name. Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15tcp: optimize tcp internal pacingEric Dumazet
When TCP implements its own pacing (when no fq packet scheduler is used), it is arming high resolution timer after a packet is sent. But in many cases (like TCP_RR kind of workloads), this high resolution timer expires before the application attempts to write the following packet. This overhead also happens when the flow is ACK clocked and cwnd limited instead of being limited by the pacing rate. This leads to extra overhead (high number of IRQ) Now tcp_wstamp_ns is reserved for the pacing timer only (after commit "tcp: do not change tcp_wstamp_ns in tcp_mstamp_refresh"), we can setup the timer only when a packet is about to be sent, and if tcp_wstamp_ns is in the future. This leads to a ~10% performance increase in TCP_RR workloads. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15net_sched: sch_fq: no longer use skb_is_tcp_pure_ack()Eric Dumazet
With the new EDT model, sch_fq no longer has to special case TCP pure acks, since their skb->tstamp will allow them being sent without pacing delay. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15tcp: mitigate scheduling jitter in EDT pacing modelEric Dumazet
In commit fefa569a9d4b ("net_sched: sch_fq: account for schedule/timers drifts") we added a mitigation for scheduling jitter in fq packet scheduler. This patch does the same in TCP stack, now it is using EDT model. Note that this mitigation is valid for both external (fq packet scheduler) or internal TCP pacing. This uses the same strategy than the above commit, allowing a time credit of half the packet currently sent. Consider following case : An skb is sent, after an idle period of 300 usec. The air-time (skb->len/pacing_rate) is 500 usec Instead of setting the pacing timer to now+500 usec, it will use now+min(500/2, 300) -> now+250usec This is like having a token bucket with a depth of half an skb. Tested: tc qdisc replace dev eth0 root pfifo_fast Before netperf -P0 -H remote -- -q 1000000000 # 8000Mbit 540000 262144 262144 10.00 7710.43 After : netperf -P0 -H remote -- -q 1000000000 # 8000 Mbit 540000 262144 262144 10.00 7999.75 # Much closer to 8000Mbit target Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15net: extend sk_pacing_rate to unsigned longEric Dumazet
sk_pacing_rate has beed introduced as a u32 field in 2013, effectively limiting per flow pacing to 34Gbit. We believe it is time to allow TCP to pace high speed flows on 64bit hosts, as we now can reach 100Gbit on one TCP flow. This patch adds no cost for 32bit kernels. The tcpi_pacing_rate and tcpi_max_pacing_rate were already exported as 64bit, so iproute2/ss command require no changes. Unfortunately the SO_MAX_PACING_RATE socket option will stay 32bit and we will need to add a new option to let applications control high pacing rates. State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 1787144 10.246.9.76:49992 10.246.9.77:36741 timer:(on,003ms,0) ino:91863 sk:2 <-> skmem:(r0,rb540000,t66440,tb2363904,f605944,w1822984,o0,bl0,d0) ts sack bbr wscale:8,8 rto:201 rtt:0.057/0.006 mss:1448 rcvmss:536 advmss:1448 cwnd:138 ssthresh:178 bytes_acked:256699822585 segs_out:177279177 segs_in:3916318 data_segs_out:177279175 bbr:(bw:31276.8Mbps,mrtt:0,pacing_gain:1.25,cwnd_gain:2) send 28045.5Mbps lastrcv:73333 pacing_rate 38705.0Mbps delivery_rate 22997.6Mbps busy:73333ms unacked:135 retrans:0/157 rcv_space:14480 notsent:2085120 minrtt:0.013 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15tcp: do not change tcp_wstamp_ns in tcp_mstamp_refreshEric Dumazet
In EDT design, I made the mistake of using tcp_wstamp_ns to store the last tcp_clock_ns() sample and to store the pacing virtual timer. This causes major regressions at high speed flows. Introduce tcp_clock_cache to store last tcp_clock_ns(). This is needed because some arches have slow high-resolution kernel time service. tcp_wstamp_ns is only updated when a packet is sent. Note that we can remove tcp_mstamp in the future since tcp_mstamp is essentially tcp_clock_cache/1000, so the apparent socket size increase is temporary. Fixes: 9799ccb0e984 ("tcp: add tcp_wstamp_ns socket field") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Soheil Hassas Yeganeh <soheil@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15sctp: use the pmtu from the icmp packet to update transport pathmtuXin Long
Other than asoc pmtu sync from all transports, sctp_assoc_sync_pmtu is also processing transport pmtu_pending by icmp packets. But it's meaningless to use sctp_dst_mtu(t->dst) as new pmtu for a transport. The right pmtu value should come from the icmp packet, and it would be saved into transport->mtu_info in this patch and used later when the pmtu sync happens in sctp_sendmsg_to_asoc or sctp_packet_config. Besides, without this patch, as pmtu can only be updated correctly when receiving a icmp packet and no place is holding sock lock, it will take long time if the sock is busy with sending packets. Note that it doesn't process transport->mtu_info in .release_cb(), as there is no enough information for pmtu update, like for which asoc or transport. It is not worth traversing all asocs to check pmtu_pending. So unlike tcp, sctp does this in tx path, for which mtu_info needs to be atomic_t. Signed-off-by: Xin Long <lucien.xin@gmail.com> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15net: bridge: fix a possible memory leak in __vlan_addLi RongQing
After per-port vlan stats, vlan stats should be released when fail to add vlan Fixes: 9163a0fc1f0c0 ("net: bridge: add support for per-port vlan stats") CC: bridge@lists.linux-foundation.org cc: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> CC: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: Zhang Yu <zhangyu31@baidu.com> Signed-off-by: Li RongQing <lirongqing@baidu.com> Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15rxrpc: Add /proc/net/rxrpc/peers to display peer listDavid Howells
Add /proc/net/rxrpc/peers to display the list of peers currently active. Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15net: fec: don't dump RX FIFO register when not availableFugang Duan
Commit db65f35f50e0 ("net: fec: add support of ethtool get_regs") introduce ethool "--register-dump" interface to dump all FEC registers. But not all silicon implementations of the Freescale FEC hardware module have the FRBR (FIFO Receive Bound Register) and FRSR (FIFO Receive Start Register) register, so we should not be trying to dump them on those that don't. To fix it we create a quirk flag, FEC_QUIRK_HAS_RFREG, and check it before dump those RX FIFO registers. Signed-off-by: Fugang Duan <fugang.duan@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15fore200e: fix missing unlock on error in bsq_audit()Wei Yongjun
Add the missing unlock before return from function bsq_audit() in the error handling case. Fixes: 1d9d8be91788 ("fore200e: check for dma mapping failures") Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15Merge branch 'bnxt_en-Add-support-for-new-57500-chips'David S. Miller
Michael Chan says: ==================== bnxt_en: Add support for new 57500 chips. This patch-set is larger than normal because I wanted a complete series to add basic support for the new 57500 chips. The new chips have the following main differences compared to legacy chips: 1. Requires the PF driver to allocate DMA context memory as a backing store. 2. New NQ (notification queue) for interrupt events. 3. One or more CP rings can be associated with an NQ. 4. 64-bit doorbells. Most other structures and firmware APIs are compatible with legacy devices with some exceptions. For example, ring groups are no longer used and RSS table format has changed. The patch-set includes the usual firmware spec. update, some refactoring and restructuring, and adding the new code to add basic support for the new class of devices. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15bnxt_en: Add PCI ID for BCM57508 device.Michael Chan
Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-15bnxt_en: Add new NAPI poll function for 57500 chips.Michael Chan
Add a new poll function that polls for NQ events. If the NQ event is a CQ notification, we locate the CP ring from the cq_handle and call __bnxt_poll_work() to handle RX/TX events on the CP ring. Add a new has_more_work field in struct bnxt_cp_ring_info to indicate budget has been reached. __bnxt_poll_cqs_done() is called to update or ARM the CP rings if budget has not been reached or not. If budget has been reached, the next bnxt_poll_p5() call will continue to poll from the CQ rings directly. Otherwise, the NQ will be ARMed for the next IRQ. Signed-off-by: Michael Chan <michael.chan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit (git 2.34.1) at 2025-09-23 06:37:30 +0000