April 2021 - Linuxarm - mailweb.openeuler.org

[PATCH v2] PCI/DPC: Check host->native_dpc before enable dpc service
by Yicong Yang 28 Jul '21

28 Jul '21

Per Downstream Port Containment Related Enhancements ECN[1] Table 4-6, Interpretation of _OSC Control Field Returned Value, for bit 7 of _OSC control return value: "Firmware sets this bit to 1 to grant the OS control over PCI Express Downstream Port Containment configuration." "If control of this feature was requested and denied, or was not requested, the firmware returns this bit set to 0." We store bit 7 of _OSC control return value in host->native_dpc, check it before enable the dpc service as the firmware may not grant the control. [1] Downstream Port Containment Related Enhancements ECN, Jan 28, 2019, affecting PCI Firmware Specification, Rev. 3.2 https://members.pcisig.com/wg/PCI-SIG/document/12888 Signed-off-by: Yicong Yang <yangyicong(a)hisilicon.com> --- Change since v1: - use correct reference for _OSC control return value drivers/pci/pcie/portdrv_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index e1fed664..7445d03 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -253,7 +253,8 @@ static int get_port_device_capability(struct pci_dev *dev) */ if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DPC) && pci_aer_available() && - (pcie_ports_dpc_native || (services & PCIE_PORT_SERVICE_AER))) + (pcie_ports_dpc_native || + ((services & PCIE_PORT_SERVICE_AER) && host->native_dpc))) services |= PCIE_PORT_SERVICE_DPC; if (pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM || -- 2.8.1

4 11

[RFC PATCH 0/5] KVM/ARM64 Add support for pinned VMIDs
by Shameer Kolothum 23 Jul '21

23 Jul '21

On an ARM64 system with a SMMUv3 implementation that fully supports Broadcast TLB Maintenance(BTM) feature as part of the Distributed Virtual Memory(DVM) protocol, the CPU TLB invalidate instructions are received by SMMUv3. This is very useful when the SMMUv3 shares the page tables with the CPU(eg: Guest SVA use case). For this to work, the SMMU must use the same VMID that is allocated by KVM to configure the stage 2 translations. At present KVM VMID allocations are recycled on rollover and may change as a result. This will create issues if we have to share the KVM VMID with SMMU. Please see the discussion here, https://lore.kernel.org/linux-iommu/20200522101755.GA3453945@myrica/ This series proposes a way to share the VMID between KVM and IOMMU driver by, 1. Splitting the KVM VMID space into two equal halves based on the command line option "kvm-arm.pinned_vmid_enable". 2. First half of the VMID space follows the normal recycle on rollover policy. 3. Second half of the VMID space doesn't roll over and is used to allocate pinned VMIDs. 4. Provides helper function to retrieve the KVM instance associated with a device(if it is part of a vfio group). 5. Introduces generic interfaces to get/put pinned KVM VMIDs. Open Items: 1. I couldn't figure out a way to determine whether a platform actually fully supports DVM/BTM or not. Not sure we can take a call based on SMMUv3 BTM feature bit alone. Probably we can get it from firmware via IORT? 2. The current splitting of VMID space is only one way to do this and probably not the best. Maybe we can follow the pinned ASID method used in SVA code. Suggestions welcome here. 3. The detach_pasid_table() interface is not very clear to me as the current Qemu prototype is not using that. This requires fixing from my side. This is based on Jean-Philippe's SVA series[1] and Eric's SMMUv3 dual-stage support series[2]. The branch with the whole vSVA + BTM solution is here, https://github.com/hisilicon/kernel-dev/tree/5.10-rc4-2stage-v13-vsva-btm-r… This is lightly tested on a HiSilicon D06 platform with uacce/zip dev test tool, ./zip_sva_per -k tlb Thanks, Shameer 1. https://github.com/Linaro/linux-kernel-uadk/commits/uacce-devel-5.10 2. https://lore.kernel.org/linux-iommu/20201118112151.25412-1-eric.auger@redha… Shameer Kolothum (5): vfio: Add a helper to retrieve kvm instance from a dev KVM: Add generic infrastructure to support pinned VMIDs KVM: ARM64: Add support for pinned VMIDs iommu/arm-smmu-v3: Use pinned VMID for NESTED stage with BTM KVM: arm64: Make sure pinned vmid is released on VM exit arch/arm64/include/asm/kvm_host.h | 2 + arch/arm64/kvm/Kconfig | 1 + arch/arm64/kvm/arm.c | 116 +++++++++++++++++++- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 49 ++++++++- drivers/vfio/vfio.c | 12 ++ include/linux/kvm_host.h | 17 +++ include/linux/vfio.h | 1 + virt/kvm/Kconfig | 2 + virt/kvm/kvm_main.c | 25 +++++ 9 files changed, 220 insertions(+), 5 deletions(-) -- 2.17.1

4 12

[PATCH net] net: hns3: Fixes+Refactors the broken set channel error fallback logic
by Salil Mehta 25 Jun '21

25 Jun '21

The fallback logic of the set channels when set_channel() fails to configure TX Sched/RSS H/W configuration or for the code which brings down/restores client before/therafter is not handled properly. Fix and refactor the code for handling the errors properly and to improve the readibility. Fixes: 3a5a5f06d4d2 ("net: hns3: revert to old channel when setting new channel num fail") Signed-off-by: Salil Mehta <salil.mehta(a)huawei.com> Signed-off-by: Peng Li <lipeng321(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 77 +++++++++++-------- 1 file changed, 47 insertions(+), 30 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index bf4302a5cf95..fbb0f4c9b98e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -4692,24 +4692,60 @@ static int hns3_reset_notify(struct hnae3_handle *handle, static int hns3_change_channels(struct hnae3_handle *handle, u32 new_tqp_num, bool rxfh_configured) { - int ret; + const struct hnae3_ae_ops *ops = handle->ae_algo->ops; + u32 org_tqp_num = handle->kinfo.num_tqps; + struct device *dev = &handle->pdev->dev; + u32 req_tqp_num = new_tqp_num; + bool revert_old_config = false; + int ret, retval = 0; + + /* bring down the client */ + ret = hns3_reset_notify(handle, HNAE3_DOWN_CLIENT); + if (ret) { + dev_err(dev, "client down fail, this should'nt have happened!\n"); + return ret; + } - ret = handle->ae_algo->ops->set_channels(handle, new_tqp_num, - rxfh_configured); + ret = hns3_reset_notify(handle, HNAE3_UNINIT_CLIENT); if (ret) { - dev_err(&handle->pdev->dev, - "Change tqp num(%u) fail.\n", new_tqp_num); + dev_err(dev, "client uninit fail, this should'nt have happened!\n"); return ret; } +revert_old_tpqs_config: + /* update the TX Sched and RSS config in the H/W */ + ret = ops->set_channels(handle, req_tqp_num, rxfh_configured); + if (ret) { + dev_err(dev, "TX Sched/RSS H/W cfg fail(=%d) for %s TPQs\n", + ret, revert_old_config ? "old" : "new"); + goto err_set_channel; + } + + /* restore the client */ ret = hns3_reset_notify(handle, HNAE3_INIT_CLIENT); - if (ret) - return ret; + if (ret) { + dev_err(dev, "failed to initialize the client again\n"); + goto err_set_channel; + } ret = hns3_reset_notify(handle, HNAE3_UP_CLIENT); - if (ret) - hns3_reset_notify(handle, HNAE3_UNINIT_CLIENT); + if (ret) { + dev_err(dev, "Client up fail, this should'nt have happened!\n"); + return ret; + } + + return retval; +err_set_channel: + if (!revert_old_config) { + dev_warn(dev, "Revert TX Sched/RSS H/W config with old TPQs\n"); + req_tqp_num = org_tqp_num; + revert_old_config = true; + retval = ret; + goto revert_old_tpqs_config; + } + dev_err(dev, "Bad, we could'nt revert to old TPQ H/W config\n"); + dev_warn(dev, "Device maybe insane. Reload driver/Reset required!\n"); return ret; } @@ -4720,7 +4756,6 @@ int hns3_set_channels(struct net_device *netdev, struct hnae3_knic_private_info *kinfo = &h->kinfo; bool rxfh_configured = netif_is_rxfh_configured(netdev); u32 new_tqp_num = ch->combined_count; - u16 org_tqp_num; int ret; if (hns3_nic_resetting(netdev)) @@ -4750,28 +4785,10 @@ int hns3_set_channels(struct net_device *netdev, "set channels: tqp_num=%u, rxfh=%d\n", new_tqp_num, rxfh_configured); - ret = hns3_reset_notify(h, HNAE3_DOWN_CLIENT); - if (ret) - return ret; - - ret = hns3_reset_notify(h, HNAE3_UNINIT_CLIENT); - if (ret) - return ret; - - org_tqp_num = h->kinfo.num_tqps; ret = hns3_change_channels(h, new_tqp_num, rxfh_configured); if (ret) { - int ret1; - - netdev_warn(netdev, - "Change channels fail, revert to old value\n"); - ret1 = hns3_change_channels(h, org_tqp_num, rxfh_configured); - if (ret1) { - netdev_err(netdev, - "revert to old channel fail\n"); - return ret1; - } - + netdev_err(netdev, "fail(=%d) to set number of channels to %u\n", ret, + new_tqp_num); return ret; } -- 2.17.1

3 6

[PATCH net-next 0/9] net: hns3: refactor and new features for flow director
by Huazhong Tan 19 Jun '21

19 Jun '21

This patchset refactor some functions and add some new features for flow director. patch 1~3: refactor large functions patch 4, 7: add traffic class and user-def field support for ethtool patch 5: use asynchronously configuration patch 6: clean up for hns3_del_all_fd_entries() patch 8, 9: add support for queue bonding mode Jian Shen (9): net: hns3: refactor out hclge_add_fd_entry() net: hns3: refactor out hclge_fd_get_tuple() net: hns3: refactor for function hclge_fd_convert_tuple net: hns3: add support for traffic class tuple support for flow director by ethtool net: hns3: refactor flow director configuration net: hns3: refine for hns3_del_all_fd_entries() net: hns3: add support for user-def data of flow director net: hns3: add support for queue bonding mode of flow director net: hns3: add queue bonding mode support for VF drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h | 8 + drivers/net/ethernet/hisilicon/hns3/hnae3.h | 9 +- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 7 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 91 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 14 +- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 13 +- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 2 + .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 21 + .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 1570 ++++++++++++++------ .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 63 + .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 33 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c | 2 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 74 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h | 7 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 17 + 15 files changed, 1450 insertions(+), 481 deletions(-) -- 2.7.4

4 20

Re: [PATCH net v4 1/2] net: sched: fix packet stuck problem for lockless qdisc
by Yunsheng Lin 30 Apr '21

30 Apr '21

On 2021/4/21 17:25, Yunsheng Lin wrote: > On 2021/4/21 16:44, Michal Kubecek wrote: > >> >> I'll try running some tests also on other architectures, including arm64 >> and s390x (to catch potential endinanity issues). I tried debugging nperf in arm64, with the below patch: diff --git a/client/main.c b/client/main.c index 429634d..de1a3ef 100644 --- a/client/main.c +++ b/client/main.c @@ -63,7 +63,10 @@ static int client_init(void) ret = client_set_usr1_handler(); if (ret < 0) return ret; - return ignore_signal(SIGPIPE); + //return ignore_signal(SIGPIPE); + signal(SIGPIPE, SIG_IGN); + + return 0; } static int ctrl_send_start(struct client_config *config) diff --git a/client/worker.c b/client/worker.c index ac026893..d269311 100644 --- a/client/worker.c +++ b/client/worker.c @@ -7,7 +7,7 @@ #include "worker.h" #include "main.h" -#define WORKER_STACK_SIZE 16384 +#define WORKER_STACK_SIZE 131072 struct client_worker_data *workers_data; union sockaddr_any test_addr; It has below error output: ../nperf/nperf -H 127.0.0.1 -l 3 -i 1 --exact -t TCP_STREAM -M 1 server: 127.0.0.1, port 12543 iterations: 1, threads: 1, test length: 3 test: TCP_STREAM, message size: 1048576 run test begin send begin send done: -32 failed to receive server stats *** Iteration 1 failed, quitting. *** Tcpdump has below output: 09:55:12.253341 IP localhost.53080 > localhost.12543: Flags [S], seq 3954442980, win 65495, options [mss 65495,sackOK,TS val 3268837738 ecr 0,nop,wscale 7], length 0 09:55:12.253363 IP localhost.12543 > localhost.53080: Flags [S.], seq 4240541653, ack 3954442981, win 65483, options [mss 65495,sackOK,TS val 3268837738 ecr 3268837738,nop,wscale 7], length 0 09:55:12.253379 IP localhost.53080 > localhost.12543: Flags [.], ack 1, win 512, options [nop,nop,TS val 3268837738 ecr 3268837738], length 0 09:55:12.253412 IP localhost.53080 > localhost.12543: Flags [P.], seq 1:29, ack 1, win 512, options [nop,nop,TS val 3268837738 ecr 3268837738], length 28 09:55:12.253863 IP localhost.12543 > localhost.53080: Flags [P.], seq 1:17, ack 29, win 512, options [nop,nop,TS val 3268837739 ecr 3268837738], length 16 09:55:12.253891 IP localhost.53080 > localhost.12543: Flags [.], ack 17, win 512, options [nop,nop,TS val 3268837739 ecr 3268837739], length 0 09:55:12.254265 IP localhost.12543 > localhost.53080: Flags [F.], seq 17, ack 29, win 512, options [nop,nop,TS val 3268837739 ecr 3268837739], length 0 09:55:12.301992 IP localhost.53080 > localhost.12543: Flags [.], ack 18, win 512, options [nop,nop,TS val 3268837787 ecr 3268837739], length 0 09:55:15.254389 IP localhost.53080 > localhost.12543: Flags [F.], seq 29, ack 18, win 512, options [nop,nop,TS val 3268840739 ecr 3268837739], length 0 09:55:15.254426 IP localhost.12543 > localhost.53080: Flags [.], ack 30, win 512, options [nop,nop,TS val 3268840739 ecr 3268840739], length 0 Any idea what went wrong here? Also, Would you mind running netperf to see if there is similar issue in your system? >> >> Michal >> >> . >> > > > . >

2 3

[RFC PATCH v6 1/4] topology: Represent clusters of CPUs within a die
by Barry Song 30 Apr '21

30 Apr '21

From: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Both ACPI and DT provide the ability to describe additional layers of topology between that of individual cores and higher level constructs such as the level at which the last level cache is shared. In ACPI this can be represented in PPTT as a Processor Hierarchy Node Structure [1] that is the parent of the CPU cores and in turn has a parent Processor Hierarchy Nodes Structure representing a higher level of topology. For example Kunpeng 920 has 6 or 8 clusters in each NUMA node, and each cluster has 4 cpus. All clusters share L3 cache data, but each cluster has local L3 tag. On the other hand, each clusters will share some internal system bus. +-----------------------------------+ +---------+ | +------+ +------+ +---------------------------+ | | | CPU0 | | cpu1 | | +-----------+ | | | +------+ +------+ | | | | | | +----+ L3 | | | | +------+ +------+ cluster | | tag | | | | | CPU2 | | CPU3 | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | | +-----------------------------------+ | | | +------+ +------+ +--------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | | | L3 | | | | +------+ +------+ +----+ tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | L3 | | data | +-----------------------------------+ | | | +------+ +------+ | +-----------+ | | | | | | | | | | | | | +------+ +------+ +----+ L3 | | | | | | tag | | | | +------+ +------+ | | | | | | | | | | ++ +-----------+ | | | +------+ +------+ |---------------------------+ | +-----------------------------------| | | +-----------------------------------| | | | +------+ +------+ +---------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | +----+ L3 | | | | +------+ +------+ | | tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | | +-----------------------------------+ | | | +------+ +------+ +--------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | | | L3 | | | | +------+ +------+ +---+ tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | | +-----------------------------------+ ++ | | +------+ +------+ +--------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | | | L3 | | | | +------+ +------+ +--+ tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | +---------+ +-----------------------------------+ That means the cost to transfer ownership of a cacheline between CPUs within a cluster is lower than between CPUs in different clusters on the same die. Hence, it can make sense to tell the scheduler to use the cache affinity of the cluster to make better decision on thread migration. This patch simply exposes this information to userspace libraries like hwloc by providing cluster_cpus and related sysfs attributes. PoC of HWLOC support at [2]. Note this patch only handle the ACPI case. Special consideration is needed for SMT processors, where it is necessary to move 2 levels up the hierarchy from the leaf nodes (thus skipping the processor core level). Currently the ID provided is the offset of the Processor Hierarchy Nodes Structure within PPTT. Whilst this is unique it is not terribly elegant so alternative suggestions welcome. Note that arm64 / ACPI does not provide any means of identifying a die level in the topology but that may be unrelate to the cluster level. [1] ACPI Specification 6.3 - section 5.2.29.1 processor hierarchy node structure (Type 0) [2] https://github.com/hisilicon/hwloc/tree/linux-cluster Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Signed-off-by: Barry Song <song.bao.hua(a)hisilicon.com> --- -v6: * the topology ABI documents required by Greg is not completed yet. will have a separate patch for that. Documentation/admin-guide/cputopology.rst | 26 +++++++++++-- arch/arm64/kernel/topology.c | 2 + drivers/acpi/pptt.c | 63 +++++++++++++++++++++++++++++++ drivers/base/arch_topology.c | 15 ++++++++ drivers/base/topology.c | 10 +++++ include/linux/acpi.h | 5 +++ include/linux/arch_topology.h | 5 +++ include/linux/topology.h | 6 +++ 8 files changed, 128 insertions(+), 4 deletions(-) diff --git a/Documentation/admin-guide/cputopology.rst b/Documentation/admin-guide/cputopology.rst index b90dafc..f9d3745 100644 --- a/Documentation/admin-guide/cputopology.rst +++ b/Documentation/admin-guide/cputopology.rst @@ -24,6 +24,12 @@ core_id: identifier (rather than the kernel's). The actual value is architecture and platform dependent. +cluster_id: + + the Cluster ID of cpuX. Typically it is the hardware platform's + identifier (rather than the kernel's). The actual value is + architecture and platform dependent. + book_id: the book ID of cpuX. Typically it is the hardware platform's @@ -56,6 +62,14 @@ package_cpus_list: human-readable list of CPUs sharing the same physical_package_id. (deprecated name: "core_siblings_list") +cluster_cpus: + + internal kernel map of CPUs within the same cluster. + +cluster_cpus_list: + + human-readable list of CPUs within the same cluster. + die_cpus: internal kernel map of CPUs within the same die. @@ -96,11 +110,13 @@ these macros in include/asm-XXX/topology.h:: #define topology_physical_package_id(cpu) #define topology_die_id(cpu) + #define topology_cluster_id(cpu) #define topology_core_id(cpu) #define topology_book_id(cpu) #define topology_drawer_id(cpu) #define topology_sibling_cpumask(cpu) #define topology_core_cpumask(cpu) + #define topology_cluster_cpumask(cpu) #define topology_die_cpumask(cpu) #define topology_book_cpumask(cpu) #define topology_drawer_cpumask(cpu) @@ -116,10 +132,12 @@ not defined by include/asm-XXX/topology.h: 1) topology_physical_package_id: -1 2) topology_die_id: -1 -3) topology_core_id: 0 -4) topology_sibling_cpumask: just the given CPU -5) topology_core_cpumask: just the given CPU -6) topology_die_cpumask: just the given CPU +3) topology_cluster_id: -1 +4) topology_core_id: 0 +5) topology_sibling_cpumask: just the given CPU +6) topology_core_cpumask: just the given CPU +7) topology_cluster_cpumask: just the given CPU +8) topology_die_cpumask: just the given CPU For architectures that don't support books (CONFIG_SCHED_BOOK) there are no default definitions for topology_book_id() and topology_book_cpumask(). diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index e08a412..d72eb8d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -103,6 +103,8 @@ int __init parse_acpi_topology(void) cpu_topology[cpu].thread_id = -1; cpu_topology[cpu].core_id = topology_id; } + topology_id = find_acpi_cpu_topology_cluster(cpu); + cpu_topology[cpu].cluster_id = topology_id; topology_id = find_acpi_cpu_topology_package(cpu); cpu_topology[cpu].package_id = topology_id; diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c index 4ae9335..11f8b02 100644 --- a/drivers/acpi/pptt.c +++ b/drivers/acpi/pptt.c @@ -737,6 +737,69 @@ int find_acpi_cpu_topology_package(unsigned int cpu) } /** + * find_acpi_cpu_topology_cluster() - Determine a unique CPU cluster value + * @cpu: Kernel logical CPU number + * + * Determine a topology unique cluster ID for the given CPU/thread. + * This ID can then be used to group peers, which will have matching ids. + * + * The cluster, if present is the level of topology above CPUs. In a + * multi-thread CPU, it will be the level above the CPU, not the thread. + * It may not exist in single CPU systems. In simple multi-CPU systems, + * it may be equal to the package topology level. + * + * Return: -ENOENT if the PPTT doesn't exist, the CPU cannot be found + * or there is no toplogy level above the CPU.. + * Otherwise returns a value which represents the package for this CPU. + */ + +int find_acpi_cpu_topology_cluster(unsigned int cpu) +{ + struct acpi_table_header *table; + acpi_status status; + struct acpi_pptt_processor *cpu_node, *cluster_node; + u32 acpi_cpu_id; + int retval; + int is_thread; + + status = acpi_get_table(ACPI_SIG_PPTT, 0, &table); + if (ACPI_FAILURE(status)) { + acpi_pptt_warn_missing(); + return -ENOENT; + } + + acpi_cpu_id = get_acpi_id_for_cpu(cpu); + cpu_node = acpi_find_processor_node(table, acpi_cpu_id); + if (cpu_node == NULL || !cpu_node->parent) { + retval = -ENOENT; + goto put_table; + } + + is_thread = cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_IS_THREAD; + cluster_node = fetch_pptt_node(table, cpu_node->parent); + if (cluster_node == NULL) { + retval = -ENOENT; + goto put_table; + } + if (is_thread) { + if (!cluster_node->parent) { + retval = -ENOENT; + goto put_table; + } + cluster_node = fetch_pptt_node(table, cluster_node->parent); + if (cluster_node == NULL) { + retval = -ENOENT; + goto put_table; + } + } + retval = ACPI_PTR_DIFF(cluster_node, table); +put_table: + acpi_put_table(table); + + return retval; +} + +/** * find_acpi_cpu_topology_hetero_id() - Get a core architecture tag * @cpu: Kernel logical CPU number * diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index de8587c..ca3b8c1 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -506,6 +506,11 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return core_mask; } +const struct cpumask *cpu_clustergroup_mask(int cpu) +{ + return &cpu_topology[cpu].cluster_sibling; +} + void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; @@ -523,6 +528,11 @@ void update_siblings_masks(unsigned int cpuid) if (cpuid_topo->package_id != cpu_topo->package_id) continue; + if (cpuid_topo->cluster_id == cpu_topo->cluster_id) { + cpumask_set_cpu(cpu, &cpuid_topo->cluster_sibling); + cpumask_set_cpu(cpuid, &cpu_topo->cluster_sibling); + } + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); @@ -541,6 +551,9 @@ static void clear_cpu_topology(int cpu) cpumask_clear(&cpu_topo->llc_sibling); cpumask_set_cpu(cpu, &cpu_topo->llc_sibling); + cpumask_clear(&cpu_topo->cluster_sibling); + cpumask_set_cpu(cpu, &cpu_topo->cluster_sibling); + cpumask_clear(&cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); @@ -556,6 +569,7 @@ void __init reset_cpu_topology(void) cpu_topo->thread_id = -1; cpu_topo->core_id = -1; + cpu_topo->cluster_id = -1; cpu_topo->package_id = -1; cpu_topo->llc_id = -1; @@ -571,6 +585,7 @@ void remove_cpu_topology(unsigned int cpu) cpumask_clear_cpu(cpu, topology_core_cpumask(sibling)); for_each_cpu(sibling, topology_sibling_cpumask(cpu)) cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling)); + for_each_cpu(sibling, topology_llc_cpumask(cpu)) cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling)); diff --git a/drivers/base/topology.c b/drivers/base/topology.c index 4d254fc..7157ac0 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -46,6 +46,9 @@ define_id_show_func(die_id); static DEVICE_ATTR_RO(die_id); +define_id_show_func(cluster_id); +static DEVICE_ATTR_RO(cluster_id); + define_id_show_func(core_id); static DEVICE_ATTR_RO(core_id); @@ -61,6 +64,10 @@ static DEVICE_ATTR_RO(core_siblings); static DEVICE_ATTR_RO(core_siblings_list); +define_siblings_show_func(cluster_cpus, cluster_cpumask); +static DEVICE_ATTR_RO(cluster_cpus); +static DEVICE_ATTR_RO(cluster_cpus_list); + define_siblings_show_func(die_cpus, die_cpumask); static DEVICE_ATTR_RO(die_cpus); static DEVICE_ATTR_RO(die_cpus_list); @@ -88,6 +95,7 @@ static struct attribute *default_attrs[] = { &dev_attr_physical_package_id.attr, &dev_attr_die_id.attr, + &dev_attr_cluster_id.attr, &dev_attr_core_id.attr, &dev_attr_thread_siblings.attr, &dev_attr_thread_siblings_list.attr, @@ -95,6 +103,8 @@ &dev_attr_core_cpus_list.attr, &dev_attr_core_siblings.attr, &dev_attr_core_siblings_list.attr, + &dev_attr_cluster_cpus.attr, + &dev_attr_cluster_cpus_list.attr, &dev_attr_die_cpus.attr, &dev_attr_die_cpus_list.attr, &dev_attr_package_cpus.attr, diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 9f43241..138b779 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1307,6 +1307,7 @@ static inline int lpit_read_residency_count_address(u64 *address) #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); +int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); int find_acpi_cpu_cache_topology(unsigned int cpu, int level); @@ -1319,6 +1320,10 @@ static inline int find_acpi_cpu_topology(unsigned int cpu, int level) { return -EINVAL; } +static inline int find_acpi_cpu_topology_cluster(unsigned int cpu) +{ + return -EINVAL; +} static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 0f6cd6b..987c7ea 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -49,10 +49,12 @@ void topology_set_thermal_pressure(const struct cpumask *cpus, struct cpu_topology { int thread_id; int core_id; + int cluster_id; int package_id; int llc_id; cpumask_t thread_sibling; cpumask_t core_sibling; + cpumask_t cluster_sibling; cpumask_t llc_sibling; }; @@ -60,13 +62,16 @@ struct cpu_topology { extern struct cpu_topology cpu_topology[NR_CPUS]; #define topology_physical_package_id(cpu) (cpu_topology[cpu].package_id) +#define topology_cluster_id(cpu) (cpu_topology[cpu].cluster_id) #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) #define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_cluster_cpumask(cpu) (&cpu_topology[cpu].cluster_sibling) #define topology_llc_cpumask(cpu) (&cpu_topology[cpu].llc_sibling) void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); +const struct cpumask *cpu_clustergroup_mask(int cpu); void update_siblings_masks(unsigned int cpu); void remove_cpu_topology(unsigned int cpuid); void reset_cpu_topology(void); diff --git a/include/linux/topology.h b/include/linux/topology.h index 7634cd7..80d27d7 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -186,6 +186,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif +#ifndef topology_cluster_id +#define topology_cluster_id(cpu) ((void)(cpu), -1) +#endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif @@ -195,6 +198,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif +#ifndef topology_cluster_cpumask +#define topology_cluster_cpumask(cpu) cpumask_of(cpu) +#endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif -- 1.8.3.1

3 2

Re: [PATCH net 0/3] net: hns3: add some fixes for -net
by patchwork-bot+netdevbpf＠kernel.org 30 Apr '21

30 Apr '21

Hello: This series was applied to netdev/net.git (refs/heads/master): On Thu, 29 Apr 2021 16:34:49 +0800 you wrote: > This series adds some fixes for the HNS3 ethernet driver. > > Jian Shen (1): > net: hns3: add check for HNS3_NIC_STATE_INITED in > hns3_reset_notify_up_enet() > > Yufeng Mo (2): > net: hns3: fix incorrect configuration for igu_egu_hw_err > net: hns3: initialize the message content in hclge_get_link_mode() > > [...] Here is the summary with links: - [net,1/3] net: hns3: fix incorrect configuration for igu_egu_hw_err https://git.kernel.org/netdev/net/c/2867298dd49e - [net,2/3] net: hns3: initialize the message content in hclge_get_link_mode() https://git.kernel.org/netdev/net/c/568a54bdf70b - [net,3/3] net: hns3: add check for HNS3_NIC_STATE_INITED in hns3_reset_notify_up_enet() https://git.kernel.org/netdev/net/c/b4047aac4ec1 You are awesome, thank you! -- Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html

1 0

Re: [RFC PATCH v6 3/4] scheduler: scan idle cpu in cluster for tasks within one LLC
by Dietmar Eggemann 29 Apr '21

29 Apr '21

On 20/04/2021 02:18, Barry Song wrote: [...] > @@ -5786,11 +5786,12 @@ static void record_wakee(struct task_struct *p) > * whatever is irrelevant, spread criteria is apparent partner count exceeds > * socket size. > */ > -static int wake_wide(struct task_struct *p) > +static int wake_wide(struct task_struct *p, int cluster) > { > unsigned int master = current->wakee_flips; > unsigned int slave = p->wakee_flips; > - int factor = __this_cpu_read(sd_llc_size); > + int factor = cluster ? __this_cpu_read(sd_cluster_size) : > + __this_cpu_read(sd_llc_size); I don't see that the wake_wide() change has any effect here. None of the sched domains has SD_BALANCE_WAKE set so a wakeup (WF_TTWU) can never end up in the slow path. Have you seen a diff when running your `lmbench stream` workload in what wake_wide() returns when you use `sd cluster size` instead of `sd llc size` as factor? I guess for you, wakeups are now subdivided into faster (cluster = 4 CPUs) and fast (llc = 24 CPUs) via sis(), not into fast (sis()) and slow (find_idlest_cpu()). > > if (master < slave) > swap(master, slave); [...] > @@ -6745,6 +6748,12 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) > int want_affine = 0; > /* SD_flags and WF_flags share the first nibble */ > int sd_flag = wake_flags & 0xF; > + /* > + * if cpu and prev_cpu share LLC, consider cluster sibling rather > + * than llc. this is typically true while tasks are bound within > + * one numa > + */ > + int cluster = sched_cluster_active() && cpus_share_cache(cpu, prev_cpu, 0); So you changed from scanning cluster before LLC to scan either cluster or LLC. And this is based on whether `this_cpu` and `prev_cpu` are sharing LLC or not. So you only see an effect when running the workload with `numactl -N X ...`. > > if (wake_flags & WF_TTWU) { > record_wakee(p); > @@ -6756,7 +6765,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) > new_cpu = prev_cpu; > } > > - want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr); > + want_affine = !wake_wide(p, cluster) && cpumask_test_cpu(cpu, p->cpus_ptr); > } > > rcu_read_lock(); > @@ -6768,7 +6777,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) > if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && > cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { > if (cpu != prev_cpu) > - new_cpu = wake_affine(tmp, p, cpu, prev_cpu, sync); > + new_cpu = wake_affine(tmp, p, cpu, prev_cpu, sync, cluster); > > sd = NULL; /* Prefer wake_affine over balance flags */ > break; > @@ -6785,7 +6794,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) > new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); > } else if (wake_flags & WF_TTWU) { /* XXX always ? */ > /* Fast path */ > - new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); > + new_cpu = select_idle_sibling(p, prev_cpu, new_cpu, cluster); > > if (want_affine) > current->recent_used_cpu = cpu; [...]

3 4

Re: [PATCH V3 7/7] app/testpmd: remove redundant fwd streams initialization
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 17:01 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V3 7/7] app/testpmd: remove redundant fwd streams > initialization > > The fwd_config_setup() is called after init_fwd_streams(). > The fwd_config_setup() will reinitialize forwarding streams. > This patch removes init_fwd_streams() from init_config(). > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- Agree. Seems redundant. Every fwd setup will call init_fwd_streams() again. Acked-by: Xiaoyun Li <xiaoyun.li(a)intel.com>

1 0

Re: [PATCH V3 6/7] app/testpmd: add forwarding config in start port
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 17:01 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V3 6/7] app/testpmd: add forwarding config in start port > > Most operations in testpmd that need to update the forwarding streams in > testpmd call fwd_config_setup(). In some scenarios, eg, dev_configure is called > again, the forwarding streams may not be updated. As a result, the actual > forwarding streams cannot be queried by "show config fwd" cmd. I don't agree on this. Fwd config should be only changed after the user change something like nb-cores, queue number, eth-peer in non-dcb mode. These are already done in those commands. You should do fwd_config_setup at the end of cmd_config_dcb_parsed(), I agree on this. But doing it in start port seems to do redundant times of fwd_setup. It's not really needed. > > The procedure is as follows: > set nbcore 4 > port stop all > port config 0 dcb vt off 4 pfc on > port start all > show config fwd > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- > app/test-pmd/testpmd.c | 6 ++++++ > 1 file changed, 6 insertions(+) > > diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index > abcbdaa..f8052b6 100644 > --- a/app/test-pmd/testpmd.c > +++ b/app/test-pmd/testpmd.c > @@ -2678,6 +2678,12 @@ start_port(portid_t pid) > } > } > } > + /* > + * In some scenarios, eg, dev_configure is called again, the forwarding > + * streams may not be updated. As a result, the actual forwarding > + * streams cannot be queried by "show config fwd" command. > + */ > + fwd_config_setup(); > > printf("Done\n"); > return 0; > -- > 2.7.4

1 0

Re: [PATCH V3 5/7] app/testpmd: move position of verifying DCB test
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 17:01 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V3 5/7] app/testpmd: move position of verifying DCB test > > Currently, the check for doing DCB test is assigned to start_packet_forwarding(), > which will be called when run "start" cmd. But fwd_config_setup() is used in > many scenarios, such as, "port config all rxq". > > This patch moves the check from start_packet_forwarding() to > fwd_config_setup(). > > Fixes: 7741e4cf16c0 ("app/testpmd: VMDq and DCB updates") > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- > app/test-pmd/config.c | 23 +++++++++++++++++++++-- app/test- > pmd/testpmd.c | 19 ------------------- > 2 files changed, 21 insertions(+), 21 deletions(-) Acked-by: Xiaoyun Li <xiaoyun.li(a)intel.com>

1 0

Re: [PATCH V3 4/7] app/testpmd: add check for support of reporting DCB info
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 17:01 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V3 4/7] app/testpmd: add check for support of reporting DCB > info > > Currently, '.get_dcb_info' must be supported for the port doing DCB test, or all > information in 'rte_eth_dcb_info' are zero. It should be prevented when user run > cmd "port config 0 dcb vt off 4 pfc off". > > This patch adds the check for support of reporting dcb info. > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- > V2->V3 > - fix the abnormal print information > > --- > app/test-pmd/cmdline.c | 9 +++++++++ > 1 file changed, 9 insertions(+) > 2.7.4 Acked-by: Xiaoyun Li <xiaoyun.li(a)intel.com>

1 0

Re: [PATCH V3 3/7] app/testpmd: fix a segment fault when DCB test
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 17:01 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V3 3/7] app/testpmd: fix a segment fault when DCB test > > After DCB mode is configured, if we decrease the number of RX and TX queues, > fwd_config_setup() will be called to setup the DCB forwarding configuration. > And forwarding streams are updated based on new queue numbers in > fwd_config_setup(), but the mapping between the TC and queues obtained by > rte_eth_dev_get_dcb_info() is still old queue numbers (old queue numbers are > greater than new queue numbers). > In this case, the segment fault happens. So rte_eth_dev_configure() should be > called again to update the mapping between the TC and queues before > rte_eth_dev_get_dcb_info(). > > Like: > set nbcore 4 > port stop all > port config 0 dcb vt off 4 pfc on > port start all > port stop all > port config all rxq 8 > port config all txq 8 > > Fixes: 900550de04a7 ("app/testpmd: add dcb support") > Cc: stable(a)dpdk.org > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- > app/test-pmd/config.c | 26 ++++++++++++++++++++++++++ > 1 file changed, 26 insertions(+) > > diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c index > 03ee40c..18b197b 100644 > --- a/app/test-pmd/config.c > +++ b/app/test-pmd/config.c > @@ -2996,7 +2996,33 @@ dcb_fwd_config_setup(void) > uint16_t nb_rx_queue, nb_tx_queue; > uint16_t i, j, k, sm_id = 0; > uint16_t total_tc_num; > + struct rte_port *port; > uint8_t tc = 0; > + portid_t pid; > + int ret; > + > + /* > + * The fwd_config_setup() is called when the port is > RTE_PORT_STARTED When the port is RTE_PORT_STARTED or RTE_PORT_STARTED? Missing an 'or' here. Maybe something like the following will be better? (just a reference, you can put it in a better way) /* * Re-configure ports to get updated mapping between tc and queue in case the queue number of the port is changed. * Skip for started ports since configuring queue number needs to stop ports first. */ > + * RTE_PORT_STOPPED. When a port is RTE_PORT_STARTED, > dev_configure > + * cannot be called. > + * > + * re-configure the device after changing queue numbers of stopped > + * ports, so that the updated mapping between tc and queue can be > + * obtained. > + */ > + for (pid = 0; pid < nb_fwd_ports; pid++) { > + if (port_is_started(pid) == 1) > + continue; > + > + port = &ports[pid]; > + ret = rte_eth_dev_configure(pid, nb_rxq, nb_txq, > + &port->dev_conf); > + if (ret < 0) { > + printf("Failed to re-configure port %d, ret = %d.\n", > + pid, ret); > + return; > + } > + } > > cur_fwd_config.nb_fwd_lcores = (lcoreid_t) nb_fwd_lcores; > cur_fwd_config.nb_fwd_ports = nb_fwd_ports; > -- > 2.7.4

1 0

Re: [PATCH V3 2/7] app/testpmd: fix DCB forwarding configuration
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 17:01 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V3 2/7] app/testpmd: fix DCB forwarding configuration > > After DCB mode is configured, the operations of port stop and port start change > the value of the global variable "dcb_test", As a result, the forwarding > configuration from DCB to RSS mode, namely, “dcb_fwd_config_setup()” to > "rss_fwd_config_setup()". > > Currently, the 'dcb_flag' field in struct 'rte_port' indicates whether the port is > configured with DCB. And it is sufficient to have 'dcb_config' > as a global variable to control the DCB test status. So this patch deletes the > "dcb_test". > > In addition, the 'dcb_config' is first set to 1 first in init_port_dcb_config(), but > the function may fail. > So it should be moved to the end. Change this to the following will be better: In addition, setting 'dcb_config' at the end of init_port_dcb_config() in case that ports fail to enter DCB mode. > > Fixes: 900550de04a7 ("app/testpmd: add dcb support") > Fixes: ce8d561418d4 ("app/testpmd: add port configuration settings") > Fixes: 7741e4cf16c0 ("app/testpmd: VMDq and DCB updates") > Cc: stable(a)dpdk.org > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- > app/test-pmd/testpmd.c | 18 ++++-------------- app/test-pmd/testpmd.h | 1 - > 2 files changed, 4 insertions(+), 15 deletions(-) > > diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index > d4be23f..a076b1d 100644 > --- a/app/test-pmd/testpmd.c > +++ b/app/test-pmd/testpmd.c > @@ -246,9 +246,6 @@ uint16_t mb_mempool_cache = DEF_MBUF_CACHE; > /**< Size of mbuf mempool cache. */ > /* current configuration is in DCB or not,0 means it is not in DCB mode */ > uint8_t dcb_config = 0; > > -/* Whether the dcb is in testing status */ -uint8_t dcb_test = 0; > - > /* > * Configurable number of RX/TX queues. > */ > @@ -2167,8 +2164,7 @@ start_packet_forwarding(int with_tx_first) > return; > } > > - > - if(dcb_test) { > + if (dcb_config) { > for (i = 0; i < nb_fwd_ports; i++) { > pt_id = fwd_ports_ids[i]; > port = &ports[pt_id]; > @@ -2476,8 +2472,6 @@ start_port(portid_t pid) > if (port_id_is_invalid(pid, ENABLED_WARN)) > return 0; > > - if(dcb_config) > - dcb_test = 1; > RTE_ETH_FOREACH_DEV(pi) { > if (pid != pi && pid != (portid_t)RTE_PORT_ALL) > continue; > @@ -2717,11 +2711,6 @@ stop_port(portid_t pid) > portid_t peer_pl[RTE_MAX_ETHPORTS]; > int peer_pi; > > - if (dcb_test) { > - dcb_test = 0; > - dcb_config = 0; > - } > - > if (port_id_is_invalid(pid, ENABLED_WARN)) > return; > > @@ -3625,8 +3614,6 @@ init_port_dcb_config(portid_t pid, > rte_port = &ports[pid]; > > memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > - /* Enter DCB configuration status */ > - dcb_config = 1; > > port_conf.rxmode = rte_port->dev_conf.rxmode; > port_conf.txmode = rte_port->dev_conf.txmode; @@ -3694,6 +3681,9 > @@ init_port_dcb_config(portid_t pid, > > rte_port->dcb_flag = 1; > > + /* Enter DCB configuration status */ > + dcb_config = 1; > + > return 0; > } > > diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h index > 9530ec5..432c66d 100644 > --- a/app/test-pmd/testpmd.h > +++ b/app/test-pmd/testpmd.h > @@ -425,7 +425,6 @@ extern uint64_t noisy_lkup_num_reads; extern uint64_t > noisy_lkup_num_reads_writes; > > extern uint8_t dcb_config; > -extern uint8_t dcb_test; > > extern uint32_t mbuf_data_size_n; > extern uint16_t mbuf_data_size[MAX_SEGS_BUFFER_SPLIT]; > -- > 2.7.4

1 0

Re: [PATCH V3 1/7] app/testpmd: fix forward lcores number when DCB test
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 17:01 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V3 1/7] app/testpmd: fix forward lcores number when DCB test > > Currently, 'nb_fwd_lcores' value are both adjusted based on 'nb_fwd_streams' in > rss/simple/icmp_echo_fwd_config_setup. > But the operation is missing in dcb_fwd_config_setup, which may lead to a bad > behavior in which multiple polling threads operate on the same queue. In this > case, the device sends and receives packets, causing unexpected results. The > procedure is as follows: > 1/ run testpmd with "--rxq=8 --txq=8" > 2/ port stop all > 3/ set nbcore 8 > 4/ port config 0 dcb vt off 4 pfc on > 5/ port config all rxq 16 > 6/ port config all txq 16 > 7/ port start all > 8/ set fwd mac > 9/ start > Same as v2 comment. Please check that. > For the DCB forwarding test, each core is assigned to each traffic class and each > core is assigned a multi-stream. > Therefore, 'nb_fwd_lcores' value needs to be adjusted based on 'total_tc_num' > in all forwarding ports. > > Fixes: 900550de04a7 ("app/testpmd: add dcb support") > Fixes: ce8d561418d4 ("app/testpmd: add port configuration settings") > Cc: stable(a)dpdk.org > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- > app/test-pmd/config.c | 19 +++++++++++++++++++ > 1 file changed, 19 insertions(+) > > diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c index > ccb9bd3..03ee40c 100644 > --- a/app/test-pmd/config.c > +++ b/app/test-pmd/config.c > @@ -2961,6 +2961,21 @@ rss_fwd_config_setup(void) > } > } > > +static uint16_t > +get_fwd_port_total_tc_num(void) > +{ > + struct rte_eth_dcb_info dcb_info; > + uint16_t total_tc_num = 0; > + unsigned int i; > + > + for (i = 0; i < nb_fwd_ports; i++) { > + (void)rte_eth_dev_get_dcb_info(fwd_ports_ids[i], &dcb_info); > + total_tc_num += dcb_info.nb_tcs; > + } > + > + return total_tc_num; > +} > + > /** > * For the DCB forwarding test, each core is assigned on each traffic class. > * > @@ -2980,12 +2995,16 @@ dcb_fwd_config_setup(void) > lcoreid_t lc_id; > uint16_t nb_rx_queue, nb_tx_queue; > uint16_t i, j, k, sm_id = 0; > + uint16_t total_tc_num; > uint8_t tc = 0; > > cur_fwd_config.nb_fwd_lcores = (lcoreid_t) nb_fwd_lcores; > cur_fwd_config.nb_fwd_ports = nb_fwd_ports; > cur_fwd_config.nb_fwd_streams = > (streamid_t) (nb_rxq * cur_fwd_config.nb_fwd_ports); > + total_tc_num = get_fwd_port_total_tc_num(); > + if (cur_fwd_config.nb_fwd_lcores > total_tc_num) > + cur_fwd_config.nb_fwd_lcores = total_tc_num; > > /* reinitialize forwarding streams */ > init_fwd_streams(); > -- > 2.7.4

1 0

Re: [PATCH V2 1/7] app/testpmd: fix forward lcores number when DCB test
by Li, Xiaoyun 27 Apr '21

27 Apr '21

> -----Original Message----- > From: Huisong Li <lihuisong(a)huawei.com> > Sent: Tuesday, April 20, 2021 15:32 > To: dev(a)dpdk.org > Cc: Yigit, Ferruh <ferruh.yigit(a)intel.com>; Li, Xiaoyun <xiaoyun.li(a)intel.com>; > linuxarm(a)openeuler.org; lihuisong(a)huawei.com > Subject: [PATCH V2 1/7] app/testpmd: fix forward lcores number when DCB test > > Currently, 'nb_fwd_lcores' value are both adjusted based on 'nb_fwd_streams' in > rss/simple/icmp_echo_fwd_config_setup. > But the operation is missing in dcb_fwd_config_setup, which may lead to a bad > behavior in which multiple polling threads operate on the same queue. This patch is OK. But commit log is redundant and confusing. The above is enough to explain what your patch is doing and can even be more simple. >In this > case, the device sends and receives packets, causing unexpected results. The > procedure is as follows: I don't understand what you're saying here. The commands you're showing is 8 nbcores dealing with 16 queues. So it's one thread dealing with multiple queues which doesn't have issues at all. Please remove the useless and confusing commands. > 1/ run testpmd with "--rxq=8 --txq=8" > 2/ port stop all > 3/ set nbcore 8 > 4/ port config 0 dcb vt off 4 pfc on > 5/ port config all rxq 16 > 6/ port config all txq 16 > 7/ port start all > 8/ set fwd mac > 9/ start > > For the DCB forwarding test, each core is assigned to each traffic class and each > core is assigned a multi-stream. > Therefore, 'nb_fwd_lcores' value needs to be adjusted based on 'total_tc_num' > in all forwarding ports. Please refer to the RSS fwd config fix patch to write your own commit log. Use simple and easy-understanding words to explain yourself. Below is the reference of RSS. commit 017d680a91fcf30da14a6d3a2f96d41f6dda3a0f Author: Pablo de Lara <pablo.de.lara.guarch(a)intel.com> Date: Mon Jun 27 23:35:19 2016 +0100 app/testpmd: limit number of forwarding cores Number of forwarding cores must be equal or less than number of forwarding streams, otherwise two cores would try to use a same queue on a port, which is not allowed. > > Fixes: 900550de04a7 ("app/testpmd: add dcb support") > Fixes: ce8d561418d4 ("app/testpmd: add port configuration settings") > Cc: stable(a)dpdk.org > > Signed-off-by: Huisong Li <lihuisong(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > --- > app/test-pmd/config.c | 19 +++++++++++++++++++ > 1 file changed, 19 insertions(+) > > diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c index > ccb9bd3..03ee40c 100644 > --- a/app/test-pmd/config.c > +++ b/app/test-pmd/config.c > @@ -2961,6 +2961,21 @@ rss_fwd_config_setup(void) > } > } > > +static uint16_t > +get_fwd_port_total_tc_num(void) > +{ > + struct rte_eth_dcb_info dcb_info; > + uint16_t total_tc_num = 0; > + unsigned int i; > + > + for (i = 0; i < nb_fwd_ports; i++) { > + (void)rte_eth_dev_get_dcb_info(fwd_ports_ids[i], &dcb_info); > + total_tc_num += dcb_info.nb_tcs; > + } > + > + return total_tc_num; > +} > + > /** > * For the DCB forwarding test, each core is assigned on each traffic class. > * > @@ -2980,12 +2995,16 @@ dcb_fwd_config_setup(void) > lcoreid_t lc_id; > uint16_t nb_rx_queue, nb_tx_queue; > uint16_t i, j, k, sm_id = 0; > + uint16_t total_tc_num; > uint8_t tc = 0; > > cur_fwd_config.nb_fwd_lcores = (lcoreid_t) nb_fwd_lcores; > cur_fwd_config.nb_fwd_ports = nb_fwd_ports; > cur_fwd_config.nb_fwd_streams = > (streamid_t) (nb_rxq * cur_fwd_config.nb_fwd_ports); > + total_tc_num = get_fwd_port_total_tc_num(); > + if (cur_fwd_config.nb_fwd_lcores > total_tc_num) > + cur_fwd_config.nb_fwd_lcores = total_tc_num; > > /* reinitialize forwarding streams */ > init_fwd_streams(); > -- > 2.7.4

1 0

Re: [PATCH] sched/fair: don't use waker's cpu if the waker of sync wake-up is interrupt
by Mike Galbraith 27 Apr '21

27 Apr '21

On Tue, 2021-04-27 at 14:37 +1200, Barry Song wrote: > > To fix this issue, this patch checks the waker of sync wake-up is a task > but not an interrupt. In this case, the waker will schedule out and give > CPU to wakee. That rash "the waker will schedule out" assumption, ie this really really is a synchronous wakeup, may be true in your particular case, but the sync hint is so overused as to be fairly meaningless. We've squabbled with it repeatedly over the years because of that. It really should either become more of a communication of intent than it currently is, or just go away. I'd argue for go away, simply because there is no way for the kernel to know that there isn't more work directly behind any particular wakeup. Take a pipe, does shoving some bits through a pipe mean you have no further use of your CPU? IFF you're doing nothing but playing ping- pong, sure it does, but how many real proggies have zero overlap among its threads of execution? The mere notion of threaded apps having no overlap *to be converted to throughput* is dainbramaged, which should be the death knell of the sync wakeup hint. Threaded apps can't do stuff like, oh, networking, which uses the sync hint heavily, without at least to some extent defeating the purpose of threading if we were to take the hint seriously. Heck, just look at the beauty (gak) of wake_wide(). It was born specifically to combat the pure-evil side of the sync wakeup hint. Bah, 'nuff "Danger Will Robinson, that thing will *eat you*!!" ;-) -Mike

2 4

Re: [RFC PATCH 2/3] vfio/hisilicon: register the driver to vfio
by Alex Williamson 26 Apr '21

26 Apr '21

On Wed, 21 Apr 2021 17:59:02 +0800 liulongfang <liulongfang(a)huawei.com> wrote: > On 2021/4/21 6:04, Alex Williamson wrote: > > On Tue, 20 Apr 2021 09:59:57 -0300 > > Jason Gunthorpe <jgg(a)nvidia.com> wrote: > > > >> On Tue, Apr 20, 2021 at 08:50:12PM +0800, liulongfang wrote: > >>> On 2021/4/19 20:33, Jason Gunthorpe wrote: > >>>> On Mon, Apr 19, 2021 at 08:24:40PM +0800, liulongfang wrote: > >>>> > >>>>>> I'm also confused how this works securely at all, as a general rule a > >>>>>> VFIO PCI driver cannot access the MMIO memory of the function it is > >>>>>> planning to assign to the guest. There is a lot of danger that the > >>>>>> guest could access that MMIO space one way or another. > >>>>> > >>>>> VF's MMIO memory is divided into two parts, one is the guest part, > >>>>> and the other is the live migration part. They do not affect each other, > >>>>> so there is no security problem. > >>>> > >>>> AFAIK there are several scenarios where a guest can access this MMIO > >>>> memory using DMA even if it is not mapped into the guest for CPU > >>>> access. > >>>> > >>> The hardware divides VF's MMIO memory into two parts. The live migration > >>> driver in the host uses the live migration part, and the device driver in > >>> the guest uses the guest part. They obtain the address of VF's MMIO memory > >>> in their respective drivers, although these two parts The memory is > >>> continuous on the hardware device, but due to the needs of the drive function, > >>> they will not perform operations on another part of the memory, and the > >>> device hardware also independently responds to the operation commands of > >>> the two parts. > >> > >> It doesn't matter, the memory is still under the same PCI BDF and VFIO > >> supports scenarios where devices in the same IOMMU group are not > >> isolated from each other. > >> > >> This is why the granual of isolation is a PCI BDF - VFIO directly > >> blocks kernel drivers from attaching to PCI BDFs that are not > >> completely isolated from VFIO BDF. > >> > >> Bypassing this prevention and attaching a kernel driver directly to > >> the same BDF being exposed to the guest breaks that isolation model. > >> > >>> So, I still don't understand what the security risk you are talking about is, > >>> and what do you think the security design should look like? > >>> Can you elaborate on it? > >> > >> Each security domain must have its own PCI BDF. > >> > >> The migration control registers must be on a different VF from the VF > >> being plugged into a guest and the two VFs have to be in different > >> IOMMU groups to ensure they are isolated from each other. > > > > I think that's a solution, I don't know if it's the only solution. > > AIUI, the issue here is that we have a device specific kernel driver > > extending vfio-pci with migration support for this device by using an > > If the two parts of the MMIO region are split into different BAR spaces on > the device, the MMIO region of the business function is still placed in BAR2, > and the MMIO region of the live migration function is moved to BAR4. > Only BAR2 is mapped in the guest. only BAR4 is mapped in the host. > This can solve this security issue. The concern is really the "on the device" part rather than whether the resources are within the same BAR or not. We need to assume that a user driver can generate a DMA targeting any address in the system, including in this case the user driver could generate a DMA targeting this migration BAR. Ideally this would be routed upstream to the IOMMU where it would be blocked for lack of a translation entry. However, because this range resides on the same PCIe requester ID, it's logically more similar to a two-function device where the functions are considered non-isolated and are therefore exposed within the same IOMMU group. We would not allow a kernel driver for one of those functions and a userspace driver for the other. In this case those drivers are strongly related, but we still need to consider to what extent a malicious user driver can interfere with or exploit the kernel side driver. > > MMIO region of the same device. This is susceptible to DMA> manipulation by the user device. Whether that's a security issue or> not depends on how the user can break the device. If the scope is > > limited to breaking their own device, they can do that any number of > > ways and it's not very interesting. If the user can manipulate device > > state in order to trigger an exploit of the host-side kernel driver, > > that's obviously more of a problem. > > > > The other side of this is that if migration support can be implemented > > entirely within the VF using this portion of the device MMIO space, why > > do we need the host kernel to support this rather than implementing it > > in userspace? For example, QEMU could know about this device, > > manipulate the BAR size to expose only the operational portion of MMIO > > to the VM and use the remainder to support migration itself. I'm > > afraid that just like mdev, the vfio migration uAPI is going to be used > > as an excuse to create kernel drivers simply to be able to make use of > > that uAPI. I haven't looked at this driver to know if it has some > > When the accelerator device is designed to support the live migration > function, it is based on the uAPI of the migration region to realize the > live migration function, so the live migration function requires a driver > that connects to this uAPI. > Is this set of interfaces not open to us now? In your model, if both BARs are exposed to userspace and a device specific extension in QEMU claims the migration BAR rather than exposing it to the VM, could that driver mimic the migration region uAPI from userspace? For example, you don't need page pinning to interact with the IOMMU, you don't need resources beyond the scope of the endpoint device itself, and the migration info BAR is safe for userspace to manage? If so, then a kernel-based driver to expose a migration uAPI seems like it's only a risk for the kernel, ie. moving what could be a userspace driver into the kernel for the convenience of re-using a kernel uAPI. Thanks, Alex

2 1

Re: [PATCH V4] ethdev: add queue state when retrieve queue information
by Thomas Monjalon 26 Apr '21

26 Apr '21

16/04/2021 10:46, Lijun Ou: > Currently, upper-layer application could get queue state only > through pointers such as dev->data->tx_queue_state[queue_id], > this is not the recommended way to access it. So this patch > add get queue state when call rte_eth_rx_queue_info_get and > rte_eth_tx_queue_info_get API. > > Note: After add queue_state field, the 'struct rte_eth_rxq_info' size > remains 128B, and the 'struct rte_eth_txq_info' size remains 64B, so > it could be ABI compatible. [...] > --- a/doc/guides/rel_notes/release_21_05.rst > +++ b/doc/guides/rel_notes/release_21_05.rst > @@ -251,6 +251,12 @@ ABI Changes > function was already marked as internal in the API documentation for it, > and was not for use by external applications. > > +* Added new field ``queue_state`` to ``rte_eth_rxq_info`` structure > + to provide indicated rxq queue state. > + > +* Added new field ``queue_state`` to ``rte_eth_txq_info`` structure > + to provide indicated txq queue state. Not sure we should add a note here for additions which do not break ABI compatibility. It may be confusing.

4 6

Re: [PATCH 2/2] Documentation/ABI: Move the topology-related sysfs interface to the right place
by Song Bao Hua (Barry Song) 26 Apr '21

26 Apr '21

> -----Original Message----- > From: tiantao (H) > Sent: Monday, April 26, 2021 2:26 PM > To: Song Bao Hua (Barry Song) <song.bao.hua(a)hisilicon.com> > Cc: linuxarm(a)openeuler.org; tiantao (H) <tiantao6(a)hisilicon.com> > Subject: [PATCH 2/2] Documentation/ABI: Move the topology-related sysfs > interface to the right place > > Move the interface that exists under > /sys/devices/system/cpu/cpuX/topology/ to the more logical > Documentation/ABI/ file that can be properly parsed and > displayed to the user space > > Signed-off-by: Tian Tao <tiantao6(a)hisilicon.com> > Signed-off-by: Barry Song <song.bao.hua(a)hisilicon.com> > --- > Documentation/ABI/stable/sysfs-devices-system-cpu | 149 > ++++++++++++++++++++++ > Documentation/admin-guide/cputopology.rst | 104 --------------- > 2 files changed, 149 insertions(+), 104 deletions(-) > > diff --git a/Documentation/ABI/stable/sysfs-devices-system-cpu > b/Documentation/ABI/stable/sysfs-devices-system-cpu > index 33c133e..7d0b23e 100644 > --- a/Documentation/ABI/stable/sysfs-devices-system-cpu > +++ b/Documentation/ABI/stable/sysfs-devices-system-cpu > @@ -1,3 +1,7 @@ > +Export CPU topology info via sysfs. Items (attributes) are similar > +to /proc/cpuinfo output of some architectures. They reside in > +/sys/devices/system/cpu/cpuX/topology/: > + > What: /sys/devices/system/cpu/dscr_default > Date: 13-May-2014 > KernelVersion: v3.15.0 > @@ -23,3 +27,148 @@ Description: Default value for the Data Stream Control > Register (DSCR) on > here). > If set by a process it will be inherited by child processes. > Values: 64 bit unsigned integer (bit field) > + > +What: /sys/devices/system/cpu/cpuX/topology/physical_package_id > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: physical package id of cpuX. Typically corresponds to a > physical > + socket number, but the actual value is architecture and platform > + dependent. > +Values: 64 bit unsigned integer (bit field) > + > +What: /sys/devices/system/cpu/cpuX/topology/die_id > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: the CPU die ID of cpuX. Typically it is the hardware platform's > + identifier (rather than the kernel's). The actual value is > + architecture and platform dependent. > +Values: 64 bit unsigned integer (bit field) > + > +What: /sys/devices/system/cpu/cpuX/topology/core_id > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: the CPU core ID of cpuX. Typically it is the hardware platform's > + identifier (rather than the kernel's). The actual value is > + architecture and platform dependent. > +Values: 64 bit unsigned integer (bit field) > + > +What: /sys/devices/system/cpu/cpuX/topology/book_id > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: the book ID of cpuX. Typically it is the hardware platform's > + identifier (rather than the kernel's). The actual value is > + architecture and platform dependent. > +Values: 64 bit unsigned integer (bit field) > + > +What: /sys/devices/system/cpu/cpuX/topology/drawer_id > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: the drawer ID of cpuX. Typically it is the hardware platform's > + identifier (rather than the kernel's). The actual value is > + architecture and platform dependent. > +Values: 64 bit unsigned integer (bit field) > + > +What: /sys/devices/system/cpu/cpuX/topology/core_cpus > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: internal kernel map of CPUs within the same core. > + (deprecated name: "thread_siblings") > +Values: hexadecimal bitmask. > + > +What: /sys/devices/system/cpu/cpuX/topology/core_cpus_list > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: human-readable list of CPUs within the same core. > + The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > + so the tail of the string will be trimmed while its size is larger > + than PAGE_SIZE. > + (deprecated name: "thread_siblings_list"). > +Values: hexadecimal bitmask. No. this is a list not a mask. > + > +What: /sys/devices/system/cpu/cpuX/topology/package_cpus > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: internal kernel map of the CPUs sharing the same > physical_package_id. > + (deprecated name: "core_siblings"). > +Values: 64 bit unsigned integer (bit field) Id is unsigned integer. Here it is hexadecimal bitmask. > + > +What: /sys/devices/system/cpu/cpuX/topology/package_cpus_list > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: human-readable list of CPUs sharing the same > physical_package_id. > + The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > + so the tail of the string will be trimmed while its size is larger > + than PAGE_SIZE. > + (deprecated name: "core_siblings_list") > +Values: hexadecimal bitmask. As above. > + > +What: /sys/devices/system/cpu/cpuX/topology/die_cpus > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: internal kernel map of CPUs within the same die. > +Values: 64 bit unsigned integer (bit field) As above. > + > +What: /sys/devices/system/cpu/cpuX/topology/die_cpus_list > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: human-readable list of CPUs within the same die. > + The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > + so the tail of the string will be trimmed while its size is larger > + than PAGE_SIZE. > +Values: hexadecimal bitmask. As above. > + > +What: /sys/devices/system/cpu/cpuX/topology/book_siblings > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: internal kernel map of cpuX's hardware threads within the same > + book_id. > +Values: 64 bit unsigned integer (bit field) As above. > + > +What: /sys/devices/system/cpu/cpuX/topology/book_siblings_list > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: human-readable list of cpuX's hardware threads within the same > + book_id. > + The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > + so the tail of the string will be trimmed while its size is larger > + than PAGE_SIZE. For example here we should mark it "available to s390 only" > +Values: hexadecimal bitmask. > + > +What: /sys/devices/system/cpu/cpuX/topology/drawer_siblings > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: internal kernel map of cpuX's hardware threads within the same > + drawer_id. > +Values: 64 bit unsigned integer (bit field) > + > +What: /sys/devices/system/cpu/cpuX/topology/drawer_siblings_list > +Date: 19-Mar-2021 > +KernelVersion: v5.12 > +Contact: > +Description: human-readable list of cpuX's hardware threads within the same > + drawer_id. > + The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > + so the tail of the string will be trimmed while its size is larger > + than PAGE_SIZE. > +Values: hexadecimal bitmask. > + > +Architecture-neutral, drivers/base/topology.c, exports these attributes. > +However, the book and drawer related sysfs files will only be created if > +CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively. > + > +CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390, > +where they reflect the cpu and cache hierarchy. These are not ABIs, better to be in original doc. Better to describe drawer ABI, book ABIs are only available for s390 in the ABI description. > diff --git a/Documentation/admin-guide/cputopology.rst > b/Documentation/admin-guide/cputopology.rst > index 4538d78..4672465 100644 > --- a/Documentation/admin-guide/cputopology.rst > +++ b/Documentation/admin-guide/cputopology.rst > @@ -2,110 +2,6 @@ > How CPU topology info is exported via sysfs > =========================================== > > -Export CPU topology info via sysfs. Items (attributes) are similar > -to /proc/cpuinfo output of some architectures. They reside in > -/sys/devices/system/cpu/cpuX/topology/: > - > -physical_package_id: > - > - physical package id of cpuX. Typically corresponds to a physical > - socket number, but the actual value is architecture and platform > - dependent. > - > -die_id: > - > - the CPU die ID of cpuX. Typically it is the hardware platform's > - identifier (rather than the kernel's). The actual value is > - architecture and platform dependent. > - > -core_id: > - > - the CPU core ID of cpuX. Typically it is the hardware platform's > - identifier (rather than the kernel's). The actual value is > - architecture and platform dependent. > - > -book_id: > - > - the book ID of cpuX. Typically it is the hardware platform's > - identifier (rather than the kernel's). The actual value is > - architecture and platform dependent. > - > -drawer_id: > - > - the drawer ID of cpuX. Typically it is the hardware platform's > - identifier (rather than the kernel's). The actual value is > - architecture and platform dependent. > - > -core_cpus: > - > - internal kernel map of CPUs within the same core. > - (deprecated name: "thread_siblings") > - > -core_cpus_list: > - > - human-readable list of CPUs within the same core. > - The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > - so the tail of the string will be trimmed while its size is larger > - than PAGE_SIZE. > - (deprecated name: "thread_siblings_list"); > - > -package_cpus: > - > - internal kernel map of the CPUs sharing the same physical_package_id. > - (deprecated name: "core_siblings") > - > -package_cpus_list: > - > - human-readable list of CPUs sharing the same physical_package_id. > - The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > - so the tail of the string will be trimmed while its size is larger > - than PAGE_SIZE. > - (deprecated name: "core_siblings_list") > - > -die_cpus: > - > - internal kernel map of CPUs within the same die. > - > -die_cpus_list: > - > - human-readable list of CPUs within the same die. > - The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > - so the tail of the string will be trimmed while its size is larger > - than PAGE_SIZE. > - > -book_siblings: > - > - internal kernel map of cpuX's hardware threads within the same > - book_id. > - > -book_siblings_list: > - > - human-readable list of cpuX's hardware threads within the same > - book_id. > - The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > - so the tail of the string will be trimmed while its size is larger > - than PAGE_SIZE. > - > -drawer_siblings: > - > - internal kernel map of cpuX's hardware threads within the same > - drawer_id. > - > -drawer_siblings_list: > - > - human-readable list of cpuX's hardware threads within the same > - drawer_id. > - The format is like 0-3, 8-11, 14,17. The maximum size is PAGE_SIZE, > - so the tail of the string will be trimmed while its size is larger > - than PAGE_SIZE. > - > -Architecture-neutral, drivers/base/topology.c, exports these attributes. > -However, the book and drawer related sysfs files will only be created if > -CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively. > - > -CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390, > -where they reflect the cpu and cache hierarchy. > - > For an architecture to support this feature, it must define some of > these macros in include/asm-XXX/topology.h:: > > -- > 2.7.4

1 0

[PATCH 0/2] clarify and cleanup CPU and NUMA topology ABIs
by Tian Tao 26 Apr '21

26 Apr '21

patch #1: Move the interface that exists under /sys/devices/system/cpu/cpuX/topology/ to the more logical Documentation/ABI/ file that can be properly parsed and displayed to the user space. patch #2: clarify the overflow issue of sysfs pagebuf, and Move the presence of BUILD_BUG_ON to more sensible place. Tian Tao (2): CPU, NUMA topology ABIs: clarify and cleanup CPU and NUMA topology ABIs cpumask: clarify the overflow issue of sysfs pagebuf Documentation/ABI/stable/sysfs-devices-node | 4 + Documentation/ABI/stable/sysfs-devices-system-cpu | 149 ++++++++++++++++++++++ Documentation/admin-guide/cputopology.rst | 89 ------------- drivers/base/node.c | 3 - include/linux/cpumask.h | 9 +- 5 files changed, 161 insertions(+), 93 deletions(-) -- 2.7.4

1 2

Re: [dpdk-dev] [PATCH V5] ethdev: add queue state when retrieve queue information
by Kinsella, Ray 23 Apr '21

23 Apr '21

On 17/04/2021 04:09, Lijun Ou wrote: > Currently, upper-layer application could get queue state only > through pointers such as dev->data->tx_queue_state[queue_id], > this is not the recommended way to access it. So this patch > add get queue state when call rte_eth_rx_queue_info_get and > rte_eth_tx_queue_info_get API. > > Note: After add queue_state field, the 'struct rte_eth_rxq_info' size > remains 128B, and the 'struct rte_eth_txq_info' size remains 64B, so > it could be ABI compatible. > > Signed-off-by: Chengwen Feng <fengchengwen(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> > Acked-by: Konstantin Ananyev <konstantin.ananyev(a)intel.com> > --- > V4->V5: > - Add acked-by > - add a note to the "New features" section to annouce the new feature. > > V3->V4: > - update libabigail.abignore for removing the CI warnings > > V2->V3: > - rewrite the commit log and delete the part Note > - rewrite tht comments for queue state > - move the queue_state definition locations > > V1->V2: > - move queue state defines to public file > --- > doc/guides/rel_notes/release_21_05.rst | 6 ++++++ > lib/librte_ethdev/ethdev_driver.h | 7 ------- > lib/librte_ethdev/rte_ethdev.c | 3 +++ > lib/librte_ethdev/rte_ethdev.h | 9 +++++++++ > 4 files changed, 18 insertions(+), 7 deletions(-) > > diff --git a/doc/guides/rel_notes/release_21_05.rst b/doc/guides/rel_notes/release_21_05.rst > index 58272e1..1ab3681 100644 > --- a/doc/guides/rel_notes/release_21_05.rst > +++ b/doc/guides/rel_notes/release_21_05.rst > @@ -81,6 +81,12 @@ New Features > representor=[[c#]pf#]sf# sf[0,2-1023] /* 1023 SFs. */ > representor=[c#]pf# c2pf[0,1] /* 2 PFs on controller 2. */ > > +* **Enhanced function for getting rxq/txq info ABI.** > + * Added new field ``queue_state`` to ``rte_eth_rxq_info`` structure to > + provide indicated rxq queue state. > + * Added new field ``queue_state`` to ``rte_eth_txq_info`` structure to > + provide indicated txq queue state. > + > * **Added support for meter PPS profile.** > > Currently meter algorithms only supports bytes per second(BPS). > diff --git a/lib/librte_ethdev/ethdev_driver.h b/lib/librte_ethdev/ethdev_driver.h > index 113129d..40e474a 100644 > --- a/lib/librte_ethdev/ethdev_driver.h > +++ b/lib/librte_ethdev/ethdev_driver.h > @@ -952,13 +952,6 @@ struct eth_dev_ops { > }; > > /** > - * RX/TX queue states > - */ > -#define RTE_ETH_QUEUE_STATE_STOPPED 0 > -#define RTE_ETH_QUEUE_STATE_STARTED 1 > -#define RTE_ETH_QUEUE_STATE_HAIRPIN 2 > - > -/** > * @internal > * Check if the selected Rx queue is hairpin queue. > * > diff --git a/lib/librte_ethdev/rte_ethdev.c b/lib/librte_ethdev/rte_ethdev.c > index c73d263..d5adf4f 100644 > --- a/lib/librte_ethdev/rte_ethdev.c > +++ b/lib/librte_ethdev/rte_ethdev.c > @@ -5038,6 +5038,8 @@ rte_eth_rx_queue_info_get(uint16_t port_id, uint16_t queue_id, > > memset(qinfo, 0, sizeof(*qinfo)); > dev->dev_ops->rxq_info_get(dev, queue_id, qinfo); > + qinfo->queue_state = dev->data->rx_queue_state[queue_id]; > + > return 0; > } > > @@ -5078,6 +5080,7 @@ rte_eth_tx_queue_info_get(uint16_t port_id, uint16_t queue_id, > > memset(qinfo, 0, sizeof(*qinfo)); > dev->dev_ops->txq_info_get(dev, queue_id, qinfo); > + qinfo->queue_state = dev->data->tx_queue_state[queue_id]; > > return 0; > } > diff --git a/lib/librte_ethdev/rte_ethdev.h b/lib/librte_ethdev/rte_ethdev.h > index 3b773b6..a0d01d2 100644 > --- a/lib/librte_ethdev/rte_ethdev.h > +++ b/lib/librte_ethdev/rte_ethdev.h > @@ -1588,6 +1588,13 @@ struct rte_eth_dev_info { > }; > > /** > + * RX/TX queue states > + */ > +#define RTE_ETH_QUEUE_STATE_STOPPED 0 > +#define RTE_ETH_QUEUE_STATE_STARTED 1 > +#define RTE_ETH_QUEUE_STATE_HAIRPIN 2 > + > +/** > * Ethernet device RX queue information structure. > * Used to retrieve information about configured queue. > */ > @@ -1595,6 +1602,7 @@ struct rte_eth_rxq_info { > struct rte_mempool *mp; /**< mempool used by that queue. */ > struct rte_eth_rxconf conf; /**< queue config parameters. */ > uint8_t scattered_rx; /**< scattered packets RX supported. */ > + uint8_t queue_state; /**< one of RTE_ETH_QUEUE_STATE_*. */ Are we sure this is a false positive? - it is being added mid-structure on the rx-side at least. Shouldn't this be appended to the end - unless it is being sneaked into padding between fields. > uint16_t nb_desc; /**< configured number of RXDs. */ > uint16_t rx_buf_size; /**< hardware receive buffer size. */ > } __rte_cache_min_aligned; > @@ -1606,6 +1614,7 @@ struct rte_eth_rxq_info { > struct rte_eth_txq_info { > struct rte_eth_txconf conf; /**< queue config parameters. */ > uint16_t nb_desc; /**< configured number of TXDs. */ > + uint8_t queue_state; /**< one of RTE_ETH_QUEUE_STATE_*. */ > } __rte_cache_min_aligned; > > /* Generic Burst mode flag definition, values can be ORed. */ >

2 2

Re: [PATCH V6] app/test-pmd: support cleanup txq mbufs command
by Ferruh Yigit 21 Apr '21

21 Apr '21

On 4/21/2021 9:45 AM, Lijun Ou wrote: > From: Chengwen Feng <fengchengwen(a)huawei.com> > > This patch supports cleanup txq mbufs command: > port cleanup (port_id) txq (queue_id) (free_cnt) > > Signed-off-by: Chengwen Feng <fengchengwen(a)huawei.com> > Signed-off-by: Lijun Ou <oulijun(a)huawei.com> Reviewed-by: Ferruh Yigit <ferruh.yigit(a)intel.com> Applied to dpdk-next-net/main, thanks.

1 0

Re: [RFC PATCH 2/3] vfio/hisilicon: register the driver to vfio
by Jason Gunthorpe 21 Apr '21

21 Apr '21

On Tue, Apr 20, 2021 at 08:50:12PM +0800, liulongfang wrote: > On 2021/4/19 20:33, Jason Gunthorpe wrote: > > On Mon, Apr 19, 2021 at 08:24:40PM +0800, liulongfang wrote: > > > >>> I'm also confused how this works securely at all, as a general rule a > >>> VFIO PCI driver cannot access the MMIO memory of the function it is > >>> planning to assign to the guest. There is a lot of danger that the > >>> guest could access that MMIO space one way or another. > >> > >> VF's MMIO memory is divided into two parts, one is the guest part, > >> and the other is the live migration part. They do not affect each other, > >> so there is no security problem. > > > > AFAIK there are several scenarios where a guest can access this MMIO > > memory using DMA even if it is not mapped into the guest for CPU > > access. > > > The hardware divides VF's MMIO memory into two parts. The live migration > driver in the host uses the live migration part, and the device driver in > the guest uses the guest part. They obtain the address of VF's MMIO memory > in their respective drivers, although these two parts The memory is > continuous on the hardware device, but due to the needs of the drive function, > they will not perform operations on another part of the memory, and the > device hardware also independently responds to the operation commands of > the two parts. It doesn't matter, the memory is still under the same PCI BDF and VFIO supports scenarios where devices in the same IOMMU group are not isolated from each other. This is why the granual of isolation is a PCI BDF - VFIO directly blocks kernel drivers from attaching to PCI BDFs that are not completely isolated from VFIO BDF. Bypassing this prevention and attaching a kernel driver directly to the same BDF being exposed to the guest breaks that isolation model. > So, I still don't understand what the security risk you are talking about is, > and what do you think the security design should look like? > Can you elaborate on it? Each security domain must have its own PCI BDF. The migration control registers must be on a different VF from the VF being plugged into a guest and the two VFs have to be in different IOMMU groups to ensure they are isolated from each other. Jason

3 3

Re: [PATCH net v4 1/2] net: sched: fix packet stuck problem for lockless qdisc
by Michal Kubecek 21 Apr '21

21 Apr '21

On Wed, Apr 21, 2021 at 04:21:54PM +0800, Yunsheng Lin wrote: > > I tried using below shell to simulate your testcase: > > #!/bin/sh > > for((i=0; i<20; i++)) > do > taskset -c 0-31 netperf -t TCP_STREAM -H 192.168.100.2 -l 30 -- -m 1048576 > done > > And I got a quite stable result: 9413~9416 (10^6bits/sec) for 10G netdev. Perhaps try it without the taskset, in my test, there was only one connection. > > > > https://github.com/mkubecek/nperf > > > > It is still raw and a lot of features are missing but it can be already > > used for multithreaded TCP_STREAM and TCP_RR tests. In particular, the > > output above was with > > > > nperf -H 172.17.1.1 -l 30 -i 20 --exact -t TCP_STREAM -M 1 > > I tried your nperf too, unfortunately it does not seem to work on my > system(arm64), which exits very quickly and output the blow result: > > root@(none):/home# nperf -H 192.168.100.2 -l 30 -i 20 --exact -t TCP_STREAM -M 1 > server: 192.168.100.2, port 12543 > iterations: 20, threads: 1, test length: 30 > test: TCP_STREAM, message size: 1048576 > > 1 4.0 B/s, avg 4.0 B/s, mdev 0.0 B/s ( 0.0%) [...] Did you start nperfd on the other side? (It plays a role similar to netserver for netperf.) Few days ago I noticed that there is something wrong with error handling in case of failed connection but didn't get to fixing it yet. I'll try running some tests also on other architectures, including arm64 and s390x (to catch potential endinanity issues). Michal

1 0