diff options
493 files changed, 11398 insertions, 2938 deletions
diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml index 29f12d650442..1a5209139e13 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml @@ -223,12 +223,6 @@ allOf: - required: - pwms - - oneOf: - - required: - - interrupts - - required: - - io-backends - - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml index d1a6103fc37a..f3242dc0e7e6 100644 --- a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml +++ b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.yaml @@ -21,7 +21,7 @@ properties: vlogic-supply: true interrupts: - minItems: 1 + maxItems: 1 description: Interrupt mapping for the trigger interrupt from the internal oscillator. diff --git a/Documentation/hwmon/ina238.rst b/Documentation/hwmon/ina238.rst index d1b93cf8627f..9a24da4786a4 100644 --- a/Documentation/hwmon/ina238.rst +++ b/Documentation/hwmon/ina238.rst @@ -65,7 +65,7 @@ Additional sysfs entries for sq52206 ------------------------------------ ======================= ======================================================= -energy1_input Energy measurement (mJ) +energy1_input Energy measurement (uJ) power1_input_highest Peak Power (uW) ======================= ======================================================= diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 1c4bb0cbe5f0..bb87111d5e16 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -853,18 +853,6 @@ attribute-sets: type: nest multi-attr: true nested-attributes: dl-rate-tc-bws - - - name: rate-tc-index - type: u8 - checks: - max: rate-tc-index-max - - - name: rate-tc-bw - type: u32 - doc: | - Specifies the bandwidth share assigned to the Traffic Class. - The bandwidth for the traffic class is determined - in proportion to the sum of the shares of all configured classes. - name: dl-dev-stats subset-of: devlink @@ -1271,12 +1259,20 @@ attribute-sets: type: flag - name: dl-rate-tc-bws - subset-of: devlink + name-prefix: devlink-rate-tc-attr- attributes: - - name: rate-tc-index + name: index + type: u8 + checks: + max: rate-tc-index-max - - name: rate-tc-bw + name: bw + type: u32 + doc: | + Specifies the bandwidth share assigned to the Traffic Class. + The bandwidth for the traffic class is determined + in proportion to the sum of the shares of all configured classes. operations: enum-model: directional diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index c38c03c624f0..1063d5d32fea 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -159,6 +159,26 @@ definitions: name: pse-event-sw-pw-control-error doc: PSE faced an error managing the power control from software - + name: input-xfrm + doc: RSS hash function transformations. + type: flags + enum-name: + name-prefix: rxh-xfrm- + header: linux/ethtool.h + entries: + - + name: sym-xor + doc: >- + XOR the corresponding source and destination fields of each specified + protocol. Both copies of the XOR'ed fields are fed into the RSS and + RXHASH calculation. Note that this XORing reduces the input set + entropy and could be exploited to reduce the RSS queue spread. + - + name: sym-or-xor + doc: >- + Similar to SYM_XOR, except that one copy of the XOR'ed fields is + replaced by an OR of the same fields. + - name: rxfh-fields name-prefix: rxh- enum-name: @@ -1621,6 +1641,7 @@ attribute-sets: - name: input-xfrm type: u32 + enum: input-xfrm - name: start-context type: u32 @@ -2644,12 +2665,65 @@ operations: - header - events - + name: rss-set + doc: Set RSS params. + + attribute-set: rss + + do: + request: + attributes: + - header + - context + - hfunc + - indir + - hkey + - input-xfrm + - flow-hash + - name: rss-ntf doc: | Notification for change in RSS configuration. - For additional contexts only modifications are modified, not creation - or removal of the contexts. + For additional contexts only modifications use this notification, + creation and deletion have dedicated messages. notify: rss-get + - + name: rss-create-act + doc: Create an RSS context. + attribute-set: rss + do: + request: &rss-create-attrs + attributes: + - header + - context + - hfunc + - indir + - hkey + - input-xfrm + reply: *rss-create-attrs + - + name: rss-create-ntf + doc: | + Notification for creation of an additional RSS context. + notify: rss-create-act + - + name: rss-delete-act + doc: Delete an RSS context. + attribute-set: rss + do: + request: + attributes: + - header + - context + - + name: rss-delete-ntf + doc: | + Notification for deletion of an additional RSS context. + attribute-set: rss + event: + attributes: + - header + - context mcast-groups: list: diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml index e983c0c82eb9..b1afc7ab3539 100644 --- a/Documentation/netlink/specs/tc.yaml +++ b/Documentation/netlink/specs/tc.yaml @@ -57,6 +57,23 @@ definitions: - tunoam - tuncrit - + name: dualpi2-drop-overload + type: enum + entries: [overflow, drop] + - + name: dualpi2-drop-early + type: enum + entries: [drop-dequeue, drop-enqueue] + - + name: dualpi2-ecn-mask + type: enum + value-start: 1 + entries: [l4s-ect, cla-ect, any-ect] + - + name: dualpi2-split-gso + type: enum + entries: [no-split-gso, split-gso] + - name: tc-stats type: struct members: @@ -826,6 +843,58 @@ definitions: name: drop-overmemory type: u32 - + name: tc-dualpi2-xstats + type: struct + members: + - + name: prob + type: u32 + doc: Current base PI probability + - + name: delay-c + type: u32 + doc: Current C-queue delay in microseconds + - + name: delay-l + type: u32 + doc: Current L-queue delay in microseconds + - + name: pkts-in-c + type: u32 + doc: Number of packets enqueued in the C-queue + - + name: pkts-in-l + type: u32 + doc: Number of packets enqueued in the L-queue + - + name: maxq + type: u32 + doc: Maximum number of packets seen by the DualPI2 + - + name: ecn-mark + type: u32 + doc: All packets marked with ECN + - + name: step-mark + type: u32 + doc: Only packets marked with ECN due to L-queue step AQM + - + name: credit + type: s32 + doc: Current credit value for WRR + - + name: memory-used + type: u32 + doc: Memory used in bytes by the DualPI2 + - + name: max-memory-used + type: u32 + doc: Maximum memory used in bytes by the DualPI2 + - + name: memory-limit + type: u32 + doc: Memory limit in bytes + - name: tc-fq-pie-xstats type: struct members: @@ -848,7 +917,7 @@ definitions: - name: ecn-mark type: u32 - doc: Packets marked with ecn + doc: Packets marked with ECN - name: new-flow-count type: u32 @@ -991,7 +1060,7 @@ definitions: - name: ecn-mark type: u32 - doc: Packets marked with ecn + doc: Packets marked with ECN - name: tc-red-xstats type: struct @@ -2285,6 +2354,78 @@ attribute-sets: name: quantum type: u32 - + name: dualpi2-attrs + name-prefix: tca-dualpi2- + attributes: + - + name: limit + type: u32 + doc: Limit of total number of packets in queue + - + name: memory-limit + type: u32 + doc: Memory limit of total number of packets in queue + - + name: target + type: u32 + doc: Classic target delay in microseconds + - + name: tupdate + type: u32 + doc: Drop probability update interval time in microseconds + - + name: alpha + type: u32 + doc: Integral gain factor in Hz for PI controller + - + name: beta + type: u32 + doc: Proportional gain factor in Hz for PI controller + - + name: step-thresh-pkts + type: u32 + doc: L4S step marking threshold in packets + - + name: step-thresh-us + type: u32 + doc: L4S Step marking threshold in microseconds + - + name: min-qlen-step + type: u32 + doc: Packets enqueued to the L-queue can apply the step threshold + when the queue length of L-queue is larger than this value. + (0 is recommended) + - + name: coupling + type: u8 + doc: Probability coupling factor between Classic and L4S + (2 is recommended) + - + name: drop-overload + type: u8 + doc: Control the overload strategy (drop to preserve latency or + let the queue overflow) + enum: dualpi2-drop-overload + - + name: drop-early + type: u8 + doc: Decide where the Classic packets are PI-based dropped or marked + enum: dualpi2-drop-early + - + name: c-protection + type: u8 + doc: Classic WRR weight in percentage (from 0 to 100) + - + name: ecn-mask + type: u8 + doc: Configure the L-queue ECN classifier + enum: dualpi2-ecn-mask + - + name: split-gso + type: u8 + doc: Split aggregated skb or not + enum: dualpi2-split-gso + - name: ematch-attrs name-prefix: tca-ematch- attr-max-name: tca-ematch-tree-max @@ -3709,6 +3850,9 @@ sub-messages: value: drr attribute-set: drr-attrs - + value: dualpi2 + attribute-set: dualpi2-attrs + - value: etf attribute-set: etf-attrs - @@ -3876,6 +4020,9 @@ sub-messages: value: codel fixed-header: tc-codel-xstats - + value: dualpi2 + fixed-header: tc-dualpi2-xstats + - value: fq fixed-header: tc-fq-qd-stats - diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 248bc3d93da9..ab20c644af24 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -239,6 +239,9 @@ Userspace to kernel: ``ETHTOOL_MSG_PHY_GET`` get Ethernet PHY information ``ETHTOOL_MSG_TSCONFIG_GET`` get hw timestamping configuration ``ETHTOOL_MSG_TSCONFIG_SET`` set hw timestamping configuration + ``ETHTOOL_MSG_RSS_SET`` set RSS settings + ``ETHTOOL_MSG_RSS_CREATE_ACT`` create an additional RSS context + ``ETHTOOL_MSG_RSS_DELETE_ACT`` delete an additional RSS context ===================================== ================================= Kernel to userspace: @@ -292,6 +295,10 @@ Kernel to userspace: ``ETHTOOL_MSG_TSCONFIG_GET_REPLY`` hw timestamping configuration ``ETHTOOL_MSG_TSCONFIG_SET_REPLY`` new hw timestamping configuration ``ETHTOOL_MSG_PSE_NTF`` PSE events notification + ``ETHTOOL_MSG_RSS_NTF`` RSS settings notification + ``ETHTOOL_MSG_RSS_CREATE_ACT_REPLY`` create an additional RSS context + ``ETHTOOL_MSG_RSS_CREATE_NTF`` additional RSS context created + ``ETHTOOL_MSG_RSS_DELETE_NTF`` additional RSS context deleted ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1989,6 +1996,65 @@ hfunc. Current supported options are symmetric-xor and symmetric-or-xor. ETHTOOL_A_RSS_FLOW_HASH carries per-flow type bitmask of which header fields are included in the hash calculation. +RSS_SET +======= + +Request contents: + +===================================== ====== ============================== + ``ETHTOOL_A_RSS_HEADER`` nested request header + ``ETHTOOL_A_RSS_CONTEXT`` u32 context number + ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func + ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes + ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes + ``ETHTOOL_A_RSS_INPUT_XFRM`` u32 RSS input data transformation + ``ETHTOOL_A_RSS_FLOW_HASH`` nested Header fields included in hash +===================================== ====== ============================== + +``ETHTOOL_A_RSS_INDIR`` is the minimal RSS table the user expects. Kernel and +the device driver may replicate the table if its smaller than smallest table +size supported by the device. For example if user requests ``[0, 1]`` but the +device needs at least 8 entries - the real table in use will end up being +``[0, 1, 0, 1, 0, 1, 0, 1]``. Most devices require the table size to be power +of 2, so tables which size is not a power of 2 will likely be rejected. +Using table of size 0 will reset the indirection table to the default. + +RSS_CREATE_ACT +============== + +Request contents: + +===================================== ====== ============================== + ``ETHTOOL_A_RSS_HEADER`` nested request header + ``ETHTOOL_A_RSS_CONTEXT`` u32 context number + ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func + ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes + ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes + ``ETHTOOL_A_RSS_INPUT_XFRM`` u32 RSS input data transformation +===================================== ====== ============================== + +Kernel response contents: + +===================================== ====== ============================== + ``ETHTOOL_A_RSS_HEADER`` nested request header + ``ETHTOOL_A_RSS_CONTEXT`` u32 context number +===================================== ====== ============================== + +Create an additional RSS context, if ``ETHTOOL_A_RSS_CONTEXT`` is not +specified kernel will allocate one automatically. + +RSS_DELETE_ACT +============== + +Request contents: + +===================================== ====== ============================== + ``ETHTOOL_A_RSS_HEADER`` nested request header + ``ETHTOOL_A_RSS_CONTEXT`` u32 context number +===================================== ====== ============================== + +Delete an additional RSS context. + PLCA_GET_CFG ============ @@ -2440,7 +2506,7 @@ are netlink only. ``ETHTOOL_GPFLAGS`` ``ETHTOOL_MSG_PRIVFLAGS_GET`` ``ETHTOOL_SPFLAGS`` ``ETHTOOL_MSG_PRIVFLAGS_SET`` ``ETHTOOL_GRXFH`` ``ETHTOOL_MSG_RSS_GET`` - ``ETHTOOL_SRXFH`` n/a + ``ETHTOOL_SRXFH`` ``ETHTOOL_MSG_RSS_SET`` ``ETHTOOL_GGRO`` ``ETHTOOL_MSG_FEATURES_GET`` ``ETHTOOL_SGRO`` ``ETHTOOL_MSG_FEATURES_SET`` ``ETHTOOL_GRXRINGS`` n/a @@ -2455,7 +2521,7 @@ are netlink only. ``ETHTOOL_GRXNTUPLE`` n/a ``ETHTOOL_GSSET_INFO`` ``ETHTOOL_MSG_STRSET_GET`` ``ETHTOOL_GRXFHINDIR`` ``ETHTOOL_MSG_RSS_GET`` - ``ETHTOOL_SRXFHINDIR`` n/a + ``ETHTOOL_SRXFHINDIR`` ``ETHTOOL_MSG_RSS_SET`` ``ETHTOOL_GFEATURES`` ``ETHTOOL_MSG_FEATURES_GET`` ``ETHTOOL_SFEATURES`` ``ETHTOOL_MSG_FEATURES_SET`` ``ETHTOOL_GCHANNELS`` ``ETHTOOL_MSG_CHANNELS_GET`` diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst index c69cc89c958e..2d3dc4692d20 100644 --- a/Documentation/networking/net_cachelines/net_device.rst +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -165,7 +165,7 @@ struct sfp_bus* sfp_bus struct lock_class_key* qdisc_tx_busylock bool proto_down unsigned:1 wol_enabled -unsigned:1 threaded napi_poll(napi_enable,dev_set_threaded) +unsigned:1 threaded napi_poll(napi_enable,netif_set_threaded) unsigned_long:1 see_all_hwtstamp_requests unsigned_long:1 change_proto_down unsigned_long:1 netns_immutable diff --git a/Documentation/networking/xdp-rx-metadata.rst b/Documentation/networking/xdp-rx-metadata.rst index a6e0ece18be5..ce96f4c99505 100644 --- a/Documentation/networking/xdp-rx-metadata.rst +++ b/Documentation/networking/xdp-rx-metadata.rst @@ -120,6 +120,39 @@ It is possible to query which kfunc the particular netdev implements via netlink. See ``xdp-rx-metadata-features`` attribute set in ``Documentation/netlink/specs/netdev.yaml``. +Driver Implementation +===================== + +Certain devices may prepend metadata to received packets. However, as of now, +``AF_XDP`` lacks the ability to communicate the size of the ``data_meta`` area +to the consumer. Therefore, it is the responsibility of the driver to copy any +device-reserved metadata out from the metadata area and ensure that +``xdp_buff->data_meta`` is pointing to ``xdp_buff->data`` before presenting the +frame to the XDP program. This is necessary so that, after the XDP program +adjusts the metadata area, the consumer can reliably retrieve the metadata +address using ``METADATA_SIZE`` offset. + +The following diagram shows how custom metadata is positioned relative to the +packet data and how pointers are adjusted for metadata access:: + + |<-- bpf_xdp_adjust_meta(xdp_buff, -METADATA_SIZE) --| + new xdp_buff->data_meta old xdp_buff->data_meta + | | + | xdp_buff->data + | | + +----------+----------------------------------------------------+------+ + | headroom | custom metadata | data | + +----------+----------------------------------------------------+------+ + | | + | xdp_desc->addr + |<------ xsk_umem__get_data() - METADATA_SIZE -------| + +``bpf_xdp_adjust_meta`` ensures that ``METADATA_SIZE`` is aligned to 4 bytes, +does not exceed 252 bytes, and leaves sufficient space for building the +xdp_frame. If these conditions are not met, it returns a negative error. In this +case, the BPF program should not proceed to populate data into the ``data_meta`` +area. + Example ======= diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 43ed57e048a8..544fb11351d9 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -2008,6 +2008,13 @@ If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also be used as a vm ioctl to set the initial tsc frequency of subsequently created vCPUs. +For TSC protected Confidential Computing (CoCo) VMs where TSC frequency +is configured once at VM scope and remains unchanged during VM's +lifetime, the vm ioctl should be used to configure the TSC frequency +and the vcpu ioctl is not supported. + +Example of such CoCo VMs: TDX guests. + 4.56 KVM_GET_TSC_KHZ -------------------- @@ -7230,8 +7237,8 @@ inputs and outputs of the TDVMCALL. Currently the following values of placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info`` field of the union. -* ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to -set up a notification interrupt for vector ``vector``. + * ``TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT``: the guest has requested to + set up a notification interrupt for vector ``vector``. KVM may add support for more values in the future that may cause a userspace exit, even without calls to ``KVM_ENABLE_CAP`` or similar. In this case, diff --git a/Documentation/virt/kvm/review-checklist.rst b/Documentation/virt/kvm/review-checklist.rst index dc01aea4057b..debac54e14e7 100644 --- a/Documentation/virt/kvm/review-checklist.rst +++ b/Documentation/virt/kvm/review-checklist.rst @@ -7,7 +7,7 @@ Review checklist for kvm patches 1. The patch must follow Documentation/process/coding-style.rst and Documentation/process/submitting-patches.rst. -2. Patches should be against kvm.git master branch. +2. Patches should be against kvm.git master or next branches. 3. If the patch introduces or modifies a new userspace API: - the API must be documented in Documentation/virt/kvm/api.rst @@ -18,10 +18,10 @@ Review checklist for kvm patches 5. New features must default to off (userspace should explicitly request them). Performance improvements can and should default to on. -6. New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2 +6. New cpu features should be exposed via KVM_GET_SUPPORTED_CPUID2, + or its equivalent for non-x86 architectures -7. Emulator changes should be accompanied by unit tests for qemu-kvm.git - kvm/test directory. +7. The feature should be testable (see below). 8. Changes should be vendor neutral when possible. Changes to common code are better than duplicating changes to vendor code. @@ -36,6 +36,87 @@ Review checklist for kvm patches 11. New guest visible features must either be documented in a hardware manual or be accompanied by documentation. -12. Features must be robust against reset and kexec - for example, shared - host/guest memory must be unshared to prevent the host from writing to - guest memory that the guest has not reserved for this purpose. +Testing of KVM code +------------------- + +All features contributed to KVM, and in many cases bugfixes too, should be +accompanied by some kind of tests and/or enablement in open source guests +and VMMs. KVM is covered by multiple test suites: + +*Selftests* + These are low level tests that allow granular testing of kernel APIs. + This includes API failure scenarios, invoking APIs after specific + guest instructions, and testing multiple calls to ``KVM_CREATE_VM`` + within a single test. They are included in the kernel tree at + ``tools/testing/selftests/kvm``. + +``kvm-unit-tests`` + A collection of small guests that test CPU and emulated device features + from a guest's perspective. They run under QEMU or ``kvmtool``, and + are generally not KVM-specific: they can be run with any accelerator + that QEMU support or even on bare metal, making it possible to compare + behavior across hypervisors and processor families. + +Functional test suites + Various sets of functional tests exist, such as QEMU's ``tests/functional`` + suite and `avocado-vt <https://avocado-vt.readthedocs.io/en/latest/>`__. + These typically involve running a full operating system in a virtual + machine. + +The best testing approach depends on the feature's complexity and +operation. Here are some examples and guidelines: + +New instructions (no new registers or APIs) + The corresponding CPU features (if applicable) should be made available + in QEMU. If the instructions require emulation support or other code in + KVM, it is worth adding coverage to ``kvm-unit-tests`` or selftests; + the latter can be a better choice if the instructions relate to an API + that already has good selftest coverage. + +New hardware features (new registers, no new APIs) + These should be tested via ``kvm-unit-tests``; this more or less implies + supporting them in QEMU and/or ``kvmtool``. In some cases selftests + can be used instead, similar to the previous case, or specifically to + test corner cases in guest state save/restore. + +Bug fixes and performance improvements + These usually do not introduce new APIs, but it's worth sharing + any benchmarks and tests that will validate your contribution, + ideally in the form of regression tests. Tests and benchmarks + can be included in either ``kvm-unit-tests`` or selftests, depending + on the specifics of your change. Selftests are especially useful for + regression tests because they are included directly in Linux's tree. + +Large scale internal changes + While it's difficult to provide a single policy, you should ensure that + the changed code is covered by either ``kvm-unit-tests`` or selftests. + In some cases the affected code is run for any guests and functional + tests suffice. Explain your testing process in the cover letter, + as that can help identify gaps in existing test suites. + +New APIs + It is important to demonstrate your use case. This can be as simple as + explaining that the feature is already in use on bare metal, or it can be + a proof-of-concept implementation in userspace. The latter need not be + open source, though that is of course preferrable for easier testing. + Selftests should test corner cases of the APIs, and should also cover + basic host and guest operation if no open source VMM uses the feature. + +Bigger features, usually spanning host and guest + These should be supported by Linux guests, with limited exceptions for + Hyper-V features that are testable on Windows guests. It is strongly + suggested that the feature be usable with an open source host VMM, such + as at least one of QEMU or crosvm, and guest firmware. Selftests should + test at least API error cases. Guest operation can be covered by + either selftests of ``kvm-unit-tests`` (this is especially important for + paravirtualized and Windows-only features). Strong selftest coverage + can also be a replacement for implementation in an open source VMM, + but this is generally not recommended. + +Following the above suggestions for testing in selftests and +``kvm-unit-tests`` will make it easier for the maintainers to review +and accept your code. In fact, even before you contribute your changes +upstream it will make it easier for you to develop for KVM. + +Of course, the KVM maintainers reserve the right to require more tests, +though they may also waive the requirement from time to time. diff --git a/MAINTAINERS b/MAINTAINERS index 1bc1698bc5ae..255344c1e413 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5581,6 +5581,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git F: drivers/char/ F: drivers/misc/ F: include/linux/miscdevice.h +F: rust/kernel/miscdevice.rs F: samples/rust/rust_misc_device.rs X: drivers/char/agp/ X: drivers/char/hw_random/ @@ -12200,9 +12201,8 @@ F: drivers/dma/idxd/* F: include/uapi/linux/idxd.h INTEL IN FIELD SCAN (IFS) DEVICE -M: Jithu Joseph <jithu.joseph@intel.com> +M: Tony Luck <tony.luck@intel.com> R: Ashok Raj <ashok.raj.linux@gmail.com> -R: Tony Luck <tony.luck@intel.com> S: Maintained F: drivers/platform/x86/intel/ifs F: include/trace/events/intel_ifs.h @@ -12542,8 +12542,7 @@ T: git https://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi-next.git/ F: drivers/net/wireless/intel/iwlwifi/ INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER -M: Jithu Joseph <jithu.joseph@intel.com> -S: Maintained +S: Orphan W: https://slimbootloader.github.io/security/firmware-update.html F: drivers/platform/x86/intel/wmi/sbl-fw-update.c @@ -17405,6 +17404,7 @@ F: include/linux/ethtool.h F: include/linux/framer/framer-provider.h F: include/linux/framer/framer.h F: include/linux/in.h +F: include/linux/in6.h F: include/linux/indirect_call_wrapper.h F: include/linux/inet.h F: include/linux/inet_diag.h @@ -25923,6 +25923,8 @@ F: fs/hostfs/ USERSPACE COPYIN/COPYOUT (UIOVEC) M: Alexander Viro <viro@zeniv.linux.org.uk> +L: linux-block@vger.kernel.org +L: linux-fsdevel@vger.kernel.org S: Maintained F: include/linux/uio.h F: lib/iov_iter.c @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 16 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 76c2f0da821f..c20bd6f21e60 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2624,7 +2624,7 @@ static bool access_mdcr(struct kvm_vcpu *vcpu, */ if (hpmn > vcpu->kvm->arch.nr_pmu_counters) { hpmn = vcpu->kvm->arch.nr_pmu_counters; - u64_replace_bits(val, hpmn, MDCR_EL2_HPMN); + u64p_replace_bits(&val, hpmn, MDCR_EL2_HPMN); } __vcpu_assign_sys_reg(vcpu, MDCR_EL2, val); diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 6df6dbbe1e7c..ea6c8dc400d2 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -270,6 +270,7 @@ #define H_QUERY_INT_STATE 0x1E4 #define H_POLL_PENDING 0x1D8 #define H_ILLAN_ATTRIBUTES 0x244 +#define H_ADD_LOGICAL_LAN_BUFFERS 0x248 #define H_MODIFY_HEA_QP 0x250 #define H_QUERY_HEA_QP 0x254 #define H_QUERY_HEA 0x258 diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d71ea0f4466f..1c5544401530 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -98,6 +98,7 @@ config RISCV select CLONE_BACKWARDS select COMMON_CLK select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND + select DYNAMIC_FTRACE if FUNCTION_TRACER select EDAC_SUPPORT select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE @@ -162,7 +163,7 @@ config RISCV select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS select HAVE_FUNCTION_GRAPH_FREGS - select HAVE_FUNCTION_TRACER if !XIP_KERNEL + select HAVE_FUNCTION_TRACER if !XIP_KERNEL && HAVE_DYNAMIC_FTRACE select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h index 3b643b9efc07..5acce285e56e 100644 --- a/arch/riscv/include/asm/kvm_aia.h +++ b/arch/riscv/include/asm/kvm_aia.h @@ -87,6 +87,9 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available); extern struct kvm_device_ops kvm_riscv_aia_device_ops; +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu); int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu); @@ -161,7 +164,6 @@ void kvm_riscv_aia_destroy_vm(struct kvm *kvm); int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner, void __iomem **hgei_va, phys_addr_t *hgei_pa); void kvm_riscv_aia_free_hgei(int cpu, int hgei); -void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable); void kvm_riscv_aia_enable(void); void kvm_riscv_aia_disable(void); diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 85cfebc32e4c..bcbf8b1ec115 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -306,6 +306,9 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; } +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} + #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 525e50db24f7..b88a6218b7f2 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -311,8 +311,8 @@ do { \ do { \ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ - __inttype(x) val = (__inttype(x))x; \ - if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \ + __inttype(x) ___val = (__inttype(x))x; \ + if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \ goto label; \ break; \ } \ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 4c6c24380cfd..8d18d6727f0f 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -14,6 +14,18 @@ #include <asm/text-patching.h> #ifdef CONFIG_DYNAMIC_FTRACE +void ftrace_arch_code_modify_prepare(void) + __acquires(&text_mutex) +{ + mutex_lock(&text_mutex); +} + +void ftrace_arch_code_modify_post_process(void) + __releases(&text_mutex) +{ + mutex_unlock(&text_mutex); +} + unsigned long ftrace_call_adjust(unsigned long addr) { if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) @@ -29,10 +41,8 @@ unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) void arch_ftrace_update_code(int command) { - mutex_lock(&text_mutex); command |= FTRACE_MAY_SLEEP; ftrace_modify_all_code(command); - mutex_unlock(&text_mutex); flush_icache_all(); } @@ -149,6 +159,8 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) unsigned int nops[2], offset; int ret; + guard(mutex)(&text_mutex); + ret = ftrace_rec_set_nop_ops(rec); if (ret) return ret; @@ -157,9 +169,7 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) nops[0] = to_auipc_t0(offset); nops[1] = RISCV_INSN_NOP4; - mutex_lock(&text_mutex); ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE); - mutex_unlock(&text_mutex); return ret; } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 9c83848797a7..80230de167de 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -6,6 +6,7 @@ #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/irqflags.h> #include <linux/randomize_kstack.h> #include <linux/sched.h> #include <linux/sched/debug.h> @@ -151,7 +152,9 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ { \ if (user_mode(regs)) { \ irqentry_enter_from_user_mode(regs); \ + local_irq_enable(); \ do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + local_irq_disable(); \ irqentry_exit_to_user_mode(regs); \ } else { \ irqentry_state_t state = irqentry_nmi_enter(regs); \ @@ -173,17 +176,14 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); - local_irq_enable(); handled = riscv_v_first_use_handler(regs); - - local_irq_disable(); - if (!handled) do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, "Oops - illegal instruction"); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); @@ -308,9 +308,11 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) { if (user_mode(regs)) { irqentry_enter_from_user_mode(regs); + local_irq_enable(); handle_break(regs); + local_irq_disable(); irqentry_exit_to_user_mode(regs); } else { irqentry_state_t state = irqentry_nmi_enter(regs); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 93043924fe6c..f760e4fcc052 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -461,7 +461,7 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs) } if (!fp) - SET_RD(insn, regs, val.data_ulong << shift >> shift); + SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift); else if (len == 8) set_f64_rd(insn, regs, val.data_u64); else diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index 19afd1f23537..dad318185660 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -30,28 +30,6 @@ unsigned int kvm_riscv_aia_nr_hgei; unsigned int kvm_riscv_aia_max_ids; DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available); -static int aia_find_hgei(struct kvm_vcpu *owner) -{ - int i, hgei; - unsigned long flags; - struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei); - - raw_spin_lock_irqsave(&hgctrl->lock, flags); - - hgei = -1; - for (i = 1; i <= kvm_riscv_aia_nr_hgei; i++) { - if (hgctrl->owners[i] == owner) { - hgei = i; - break; - } - } - - raw_spin_unlock_irqrestore(&hgctrl->lock, flags); - - put_cpu_ptr(&aia_hgei); - return hgei; -} - static inline unsigned long aia_hvictl_value(bool ext_irq_pending) { unsigned long hvictl; @@ -95,7 +73,6 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) { - int hgei; unsigned long seip; if (!kvm_riscv_aia_available()) @@ -114,11 +91,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip) return false; - hgei = aia_find_hgei(vcpu); - if (hgei > 0) - return !!(ncsr_read(CSR_HGEIP) & BIT(hgei)); - - return false; + return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu); } void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) @@ -164,6 +137,9 @@ void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) csr_write(CSR_HVIPRIO2H, csr->hviprio2h); #endif } + + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu); } void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) @@ -174,6 +150,9 @@ void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) if (!kvm_riscv_aia_available()) return; + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_put(vcpu); + if (kvm_riscv_nacl_available()) { nsh = nacl_shmem(); csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT); @@ -472,22 +451,6 @@ void kvm_riscv_aia_free_hgei(int cpu, int hgei) raw_spin_unlock_irqrestore(&hgctrl->lock, flags); } -void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable) -{ - int hgei; - - if (!kvm_riscv_aia_available()) - return; - - hgei = aia_find_hgei(owner); - if (hgei > 0) { - if (enable) - csr_set(CSR_HGEIE, BIT(hgei)); - else - csr_clear(CSR_HGEIE, BIT(hgei)); - } -} - static irqreturn_t hgei_interrupt(int irq, void *dev_id) { int i; diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c index 29ef9c2133a9..2ff865943ebb 100644 --- a/arch/riscv/kvm/aia_imsic.c +++ b/arch/riscv/kvm/aia_imsic.c @@ -676,6 +676,48 @@ static void imsic_swfile_update(struct kvm_vcpu *vcpu, imsic_swfile_extirq_update(vcpu); } +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + bool ret = false; + + /* + * The IMSIC SW-file directly injects interrupt via hvip so + * only check for interrupt when IMSIC VS-file is being used. + */ + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) + ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + read_unlock_irqrestore(&imsic->vsfile_lock, flags); + + return ret; +} + +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu) +{ + /* + * No need to explicitly clear HGEIE CSR bits because the + * hgei interrupt handler (aka hgei_interrupt()) will always + * clear it for us. + */ +} + +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + + if (!kvm_vcpu_is_blocking(vcpu)) + return; + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) + csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei)); + read_unlock_irqrestore(&imsic->vsfile_lock, flags); +} + void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu) { unsigned long flags; @@ -781,6 +823,9 @@ int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu) * producers to the new IMSIC VS-file. */ + /* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */ + csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei)); + /* Zero-out new IMSIC VS-file */ imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index e0a01af426ff..0462863206ca 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -207,16 +207,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) return kvm_riscv_vcpu_timer_pending(vcpu); } -void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) -{ - kvm_riscv_aia_wakeon_hgei(vcpu, true); -} - -void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) -{ - kvm_riscv_aia_wakeon_hgei(vcpu, false); -} - int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) { return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) && diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c index ff672fa71fcc..85a7262115e1 100644 --- a/arch/riscv/kvm/vcpu_timer.c +++ b/arch/riscv/kvm/vcpu_timer.c @@ -345,8 +345,24 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu) /* * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync() * upon every VM exit so no need to save here. + * + * If VS-timer expires when no VCPU running on a host CPU then + * WFI executed by such host CPU will be effective NOP resulting + * in no power savings. This is because as-per RISC-V Privileged + * specificaiton: "WFI is also required to resume execution for + * locally enabled interrupts pending at any privilege level, + * regardless of the global interrupt enable at each privilege + * level." + * + * To address the above issue, vstimecmp CSR must be set to -1UL + * over here when VCPU is scheduled-out or exits to user space. */ + csr_write(CSR_VSTIMECMP, -1UL); +#if defined(CONFIG_32BIT) + csr_write(CSR_VSTIMECMPH, -1UL); +#endif + /* timer should be enabled for the remaining operations */ if (unlikely(!t->init_done)) return; diff --git a/arch/riscv/tools/relocs_check.sh b/arch/riscv/tools/relocs_check.sh index baeb2e7b2290..742993e6a8cb 100755 --- a/arch/riscv/tools/relocs_check.sh +++ b/arch/riscv/tools/relocs_check.sh @@ -14,7 +14,9 @@ bad_relocs=$( ${srctree}/scripts/relocs_check.sh "$@" | # These relocations are okay # R_RISCV_RELATIVE - grep -F -w -v 'R_RISCV_RELATIVE' + # R_RISCV_NONE + grep -F -w -v 'R_RISCV_RELATIVE +R_RISCV_NONE' ) if [ -z "$bad_relocs" ]; then diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index c7f8313ba449..0c9a35782c83 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -566,7 +566,15 @@ static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target) { memcpy(plt, &bpf_plt, sizeof(*plt)); plt->ret = ret; - plt->target = target; + /* + * (target == NULL) implies that the branch to this PLT entry was + * patched and became a no-op. However, some CPU could have jumped + * to this PLT entry before patching and may be still executing it. + * + * Since the intention in this case is to make the PLT entry a no-op, + * make the target point to the return label instead of NULL. + */ + plt->target = target ?: ret; } /* diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile index db3255b979bd..342d79f0ab6a 100644 --- a/arch/x86/coco/sev/Makefile +++ b/arch/x86/coco/sev/Makefile @@ -5,5 +5,6 @@ obj-y += core.o sev-nmi.o vc-handle.o # Clang 14 and older may fail to respect __no_sanitize_undefined when inlining UBSAN_SANITIZE_sev-nmi.o := n -# GCC may fail to respect __no_sanitize_address when inlining +# GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining KASAN_SANITIZE_sev-nmi.o := n +KCSAN_SANITIZE_sev-nmi.o := n diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 3d1d3547095a..afdbda2dd7b7 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -34,6 +34,7 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> #include <linux/highmem.h> +#include <linux/export.h> void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 31f0d29cbc5e..090f5ac9f492 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -10,6 +10,7 @@ #include <linux/pci.h> #include <linux/irq.h> +#include <linux/export.h> #include <asm/mshyperv.h> static int hv_map_interrupt(union hv_device_id device_id, bool level, @@ -46,7 +47,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level, if (nr_bank < 0) { local_irq_restore(flags); pr_err("%s: unable to generate VP set\n", __func__); - return EINVAL; + return -EINVAL; } intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET; @@ -66,7 +67,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level, if (!hv_result_success(status)) hv_status_err(status, "\n"); - return hv_result(status); + return hv_result_to_errno(status); } static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry) @@ -88,7 +89,10 @@ static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry) status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL); local_irq_restore(flags); - return hv_result(status); + if (!hv_result_success(status)) + hv_status_err(status, "\n"); + + return hv_result_to_errno(status); } #ifdef CONFIG_PCI_MSI @@ -169,13 +173,34 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev) return dev_id; } -static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector, - struct hv_interrupt_entry *entry) +/** + * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor. + * @data: Describes the IRQ + * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL) + * + * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall. + * + * Return: 0 on success, -errno on failure + */ +int hv_map_msi_interrupt(struct irq_data *data, + struct hv_interrupt_entry *out_entry) { - union hv_device_id device_id = hv_build_pci_dev_id(dev); + struct irq_cfg *cfg = irqd_cfg(data); + struct hv_interrupt_entry dummy; + union hv_device_id device_id; + struct msi_desc *msidesc; + struct pci_dev *dev; + int cpu; - return hv_map_interrupt(device_id, false, cpu, vector, entry); + msidesc = irq_data_get_msi_desc(data); + dev = msi_desc_to_pci_dev(msidesc); + device_id = hv_build_pci_dev_id(dev); + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); + + return hv_map_interrupt(device_id, false, cpu, cfg->vector, + out_entry ? out_entry : &dummy); } +EXPORT_SYMBOL_GPL(hv_map_msi_interrupt); static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg) { @@ -188,13 +213,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry); static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { + struct hv_interrupt_entry *stored_entry; + struct irq_cfg *cfg = irqd_cfg(data); struct msi_desc *msidesc; struct pci_dev *dev; - struct hv_interrupt_entry out_entry, *stored_entry; - struct irq_cfg *cfg = irqd_cfg(data); - const cpumask_t *affinity; - int cpu; - u64 status; + int ret; msidesc = irq_data_get_msi_desc(data); dev = msi_desc_to_pci_dev(msidesc); @@ -204,9 +227,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - affinity = irq_data_get_effective_affinity_mask(data); - cpu = cpumask_first_and(affinity, cpu_online_mask); - if (data->chip_data) { /* * This interrupt is already mapped. Let's unmap first. @@ -219,14 +239,12 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) stored_entry = data->chip_data; data->chip_data = NULL; - status = hv_unmap_msi_interrupt(dev, stored_entry); + ret = hv_unmap_msi_interrupt(dev, stored_entry); kfree(stored_entry); - if (status != HV_STATUS_SUCCESS) { - hv_status_debug(status, "failed to unmap\n"); + if (ret) return; - } } stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC); @@ -235,15 +253,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) return; } - status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry); - if (status != HV_STATUS_SUCCESS) { + ret = hv_map_msi_interrupt(data, stored_entry); + if (ret) { kfree(stored_entry); return; } - *stored_entry = out_entry; data->chip_data = stored_entry; - entry_to_msi_msg(&out_entry, msg); + entry_to_msi_msg(data->chip_data, msg); return; } @@ -257,7 +274,6 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd) { struct hv_interrupt_entry old_entry; struct msi_msg msg; - u64 status; if (!irqd->chip_data) { pr_debug("%s: no chip data\n!", __func__); @@ -270,10 +286,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd) kfree(irqd->chip_data); irqd->chip_data = NULL; - status = hv_unmap_msi_interrupt(dev, &old_entry); - - if (status != HV_STATUS_SUCCESS) - hv_status_err(status, "\n"); + (void)hv_unmap_msi_interrupt(dev, &old_entry); } static void hv_msi_free_irq(struct irq_domain *domain, diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index e93a2f488ff7..ade6c665c97e 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/cpu.h> +#include <linux/export.h> #include <asm/svm.h> #include <asm/sev.h> #include <asm/io.h> diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c index 1083dc8646f9..8ccbb7c4fc27 100644 --- a/arch/x86/hyperv/nested.c +++ b/arch/x86/hyperv/nested.c @@ -11,6 +11,7 @@ #include <linux/types.h> +#include <linux/export.h> #include <hyperv/hvhdk.h> #include <asm/mshyperv.h> #include <asm/tlbflush.h> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index e1752ba47e67..abc4659f5809 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -112,12 +112,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) return hv_status; } -/* Hypercall to the L0 hypervisor */ -static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output) -{ - return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output); -} - /* Fast hypercall with 8 bytes of input and no output */ static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1) { @@ -165,13 +159,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) return _hv_do_fast_hypercall8(control, input1); } -static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1) -{ - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED; - - return _hv_do_fast_hypercall8(control, input1); -} - /* Fast hypercall with 16 bytes of input */ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2) { @@ -223,13 +210,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) return _hv_do_fast_hypercall16(control, input1, input2); } -static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2) -{ - u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED; - - return _hv_do_fast_hypercall16(control, input1, input2); -} - extern struct hv_vp_assist_page **hv_vp_assist_page; static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) @@ -262,6 +242,8 @@ static inline void hv_apic_init(void) {} struct irq_domain *hv_create_pci_msi_domain(void); +int hv_map_msi_interrupt(struct irq_data *data, + struct hv_interrupt_entry *out_entry); int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector, struct hv_interrupt_entry *entry); int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index f31ccdeb905b..ec79aacc446f 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -173,7 +173,6 @@ static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char i tdx_clear_unsupported_cpuid(entry); } -#define TDVMCALLINFO_GET_QUOTE BIT(0) #define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT BIT(1) static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, @@ -192,7 +191,6 @@ static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf, caps->cpuid.nent = td_conf->num_cpuid_config; caps->user_tdvmcallinfo_1_r11 = - TDVMCALLINFO_GET_QUOTE | TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT; for (i = 0; i < td_conf->num_cpuid_config; i++) @@ -2271,25 +2269,26 @@ static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd) const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf; struct kvm_tdx_capabilities __user *user_caps; struct kvm_tdx_capabilities *caps = NULL; + u32 nr_user_entries; int ret = 0; /* flags is reserved for future use */ if (cmd->flags) return -EINVAL; - caps = kmalloc(sizeof(*caps) + + caps = kzalloc(sizeof(*caps) + sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config, GFP_KERNEL); if (!caps) return -ENOMEM; user_caps = u64_to_user_ptr(cmd->data); - if (copy_from_user(caps, user_caps, sizeof(*caps))) { + if (get_user(nr_user_entries, &user_caps->cpuid.nent)) { ret = -EFAULT; goto out; } - if (caps->cpuid.nent < td_conf->num_cpuid_config) { + if (nr_user_entries < td_conf->num_cpuid_config) { ret = -E2BIG; goto out; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 357b9e3a6cef..93636f77c42d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6188,6 +6188,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp, u32 user_tsc_khz; r = -EINVAL; + + if (vcpu->arch.guest_tsc_protected) + goto out; + user_tsc_khz = (u32)arg; if (kvm_caps.has_tsc_control && diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 5fa2cca43653..d6b2a665b499 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1526,7 +1526,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports, sched_poll.nr_ports * sizeof(*ports), &e)) { *r = -EFAULT; - return true; + goto out; } for (i = 0; i < sched_poll.nr_ports; i++) { diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index b2b9b89d6967..c611444480b3 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -960,4 +960,5 @@ void blk_unregister_queue(struct gendisk *disk) elevator_set_none(q); blk_debugfs_remove(disk); + kobject_put(&disk->queue_kobj); } diff --git a/drivers/acpi/riscv/cppc.c b/drivers/acpi/riscv/cppc.c index 4cdff387deff..440cf9fb91aa 100644 --- a/drivers/acpi/riscv/cppc.c +++ b/drivers/acpi/riscv/cppc.c @@ -37,10 +37,8 @@ static int __init sbi_cppc_init(void) { if (sbi_spec_version >= sbi_mk_version(2, 0) && sbi_probe_extension(SBI_EXT_CPPC) > 0) { - pr_info("SBI CPPC extension detected\n"); cppc_ext_present = true; } else { - pr_info("SBI CPPC extension NOT detected!!\n"); cppc_ext_present = false; } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index f2843f814675..1f3f782a04ba 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1173,6 +1173,8 @@ err_name: err_map: kfree(map); err: + if (bus && bus->free_on_exit) + kfree(bus); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(__regmap_init); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 500840e4a74e..8d994cae3b83 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -308,14 +308,13 @@ end_io: static void lo_rw_aio_do_completion(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); - struct loop_device *lo = rq->q->queuedata; if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; if (req_op(rq) == REQ_OP_WRITE) - file_end_write(lo->lo_backing_file); + kiocb_end_write(&cmd->iocb); if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } @@ -391,7 +390,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, } if (rw == ITER_SOURCE) { - file_start_write(lo->lo_backing_file); + kiocb_start_write(&cmd->iocb); ret = file->f_op->write_iter(&cmd->iocb, &iter); } else ret = file->f_op->read_iter(&cmd->iocb, &iter); diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c index 7671bd158545..c1c0a4759c7e 100644 --- a/drivers/bus/fsl-mc/fsl-mc-bus.c +++ b/drivers/bus/fsl-mc/fsl-mc-bus.c @@ -943,6 +943,7 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, struct fsl_mc_obj_desc endpoint_desc = {{ 0 }}; struct dprc_endpoint endpoint1 = {{ 0 }}; struct dprc_endpoint endpoint2 = {{ 0 }}; + struct fsl_mc_bus *mc_bus; int state, err; mc_bus_dev = to_fsl_mc_device(mc_dev->dev.parent); @@ -966,6 +967,8 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, strcpy(endpoint_desc.type, endpoint2.type); endpoint_desc.id = endpoint2.id; endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev); + if (endpoint) + return endpoint; /* * We know that the device has an endpoint because we verified by @@ -973,17 +976,13 @@ struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev, * yet discovered by the fsl-mc bus, thus the lookup returned NULL. * Force a rescan of the devices in this container and retry the lookup. */ - if (!endpoint) { - struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev); - - if (mutex_trylock(&mc_bus->scan_mutex)) { - err = dprc_scan_objects(mc_bus_dev, true); - mutex_unlock(&mc_bus->scan_mutex); - } - - if (err < 0) - return ERR_PTR(err); + mc_bus = to_fsl_mc_bus(mc_bus_dev); + if (mutex_trylock(&mc_bus->scan_mutex)) { + err = dprc_scan_objects(mc_bus_dev, true); + mutex_unlock(&mc_bus->scan_mutex); } + if (err < 0) + return ERR_PTR(err); endpoint = fsl_mc_device_lookup(&endpoint_desc, mc_bus_dev); /* diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c index 09549451dd51..2edc13ca184e 100644 --- a/drivers/clocksource/hyperv_timer.c +++ b/drivers/clocksource/hyperv_timer.c @@ -22,6 +22,7 @@ #include <linux/irq.h> #include <linux/acpi.h> #include <linux/hyperv.h> +#include <linux/export.h> #include <clocksource/hyperv_timer.h> #include <hyperv/hvhdk.h> #include <asm/mshyperv.h> diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 3383a7ce27ff..c83fd14dd7ad 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -1556,21 +1556,27 @@ static int do_insnlist_ioctl(struct comedi_device *dev, } for (i = 0; i < n_insns; ++i) { + unsigned int n = insns[i].n; + if (insns[i].insn & INSN_MASK_WRITE) { if (copy_from_user(data, insns[i].data, - insns[i].n * sizeof(unsigned int))) { + n * sizeof(unsigned int))) { dev_dbg(dev->class_dev, "copy_from_user failed\n"); ret = -EFAULT; goto error; } + if (n < MIN_SAMPLES) { + memset(&data[n], 0, (MIN_SAMPLES - n) * + sizeof(unsigned int)); + } } ret = parse_insn(dev, insns + i, data, file); if (ret < 0) goto error; if (insns[i].insn & INSN_MASK_READ) { if (copy_to_user(insns[i].data, data, - insns[i].n * sizeof(unsigned int))) { + n * sizeof(unsigned int))) { dev_dbg(dev->class_dev, "copy_to_user failed\n"); ret = -EFAULT; @@ -1589,6 +1595,16 @@ error: return i; } +#define MAX_INSNS MAX_SAMPLES +static int check_insnlist_len(struct comedi_device *dev, unsigned int n_insns) +{ + if (n_insns > MAX_INSNS) { + dev_dbg(dev->class_dev, "insnlist length too large\n"); + return -EINVAL; + } + return 0; +} + /* * COMEDI_INSN ioctl * synchronous instruction @@ -1633,6 +1649,10 @@ static int do_insn_ioctl(struct comedi_device *dev, ret = -EFAULT; goto error; } + if (insn->n < MIN_SAMPLES) { + memset(&data[insn->n], 0, + (MIN_SAMPLES - insn->n) * sizeof(unsigned int)); + } } ret = parse_insn(dev, insn, data, file); if (ret < 0) @@ -2239,6 +2259,9 @@ static long comedi_unlocked_ioctl(struct file *file, unsigned int cmd, rc = -EFAULT; break; } + rc = check_insnlist_len(dev, insnlist.n_insns); + if (rc) + break; insns = kcalloc(insnlist.n_insns, sizeof(*insns), GFP_KERNEL); if (!insns) { rc = -ENOMEM; @@ -3142,6 +3165,9 @@ static int compat_insnlist(struct file *file, unsigned long arg) if (copy_from_user(&insnlist32, compat_ptr(arg), sizeof(insnlist32))) return -EFAULT; + rc = check_insnlist_len(dev, insnlist32.n_insns); + if (rc) + return rc; insns = kcalloc(insnlist32.n_insns, sizeof(*insns), GFP_KERNEL); if (!insns) return -ENOMEM; diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c index 376130bfba8a..9e4b7c840a8f 100644 --- a/drivers/comedi/drivers.c +++ b/drivers/comedi/drivers.c @@ -339,10 +339,10 @@ int comedi_dio_insn_config(struct comedi_device *dev, unsigned int *data, unsigned int mask) { - unsigned int chan_mask = 1 << CR_CHAN(insn->chanspec); + unsigned int chan = CR_CHAN(insn->chanspec); - if (!mask) - mask = chan_mask; + if (!mask && chan < 32) + mask = 1U << chan; switch (data[0]) { case INSN_CONFIG_DIO_INPUT: @@ -382,7 +382,7 @@ EXPORT_SYMBOL_GPL(comedi_dio_insn_config); unsigned int comedi_dio_update_state(struct comedi_subdevice *s, unsigned int *data) { - unsigned int chanmask = (s->n_chan < 32) ? ((1 << s->n_chan) - 1) + unsigned int chanmask = (s->n_chan < 32) ? ((1U << s->n_chan) - 1) : 0xffffffff; unsigned int mask = data[0] & chanmask; unsigned int bits = data[1]; @@ -615,6 +615,9 @@ static int insn_rw_emulate_bits(struct comedi_device *dev, unsigned int _data[2]; int ret; + if (insn->n == 0) + return 0; + memset(_data, 0, sizeof(_data)); memset(&_insn, 0, sizeof(_insn)); _insn.insn = INSN_BITS; @@ -625,8 +628,8 @@ static int insn_rw_emulate_bits(struct comedi_device *dev, if (insn->insn == INSN_WRITE) { if (!(s->subdev_flags & SDF_WRITABLE)) return -EINVAL; - _data[0] = 1 << (chan - base_chan); /* mask */ - _data[1] = data[0] ? (1 << (chan - base_chan)) : 0; /* bits */ + _data[0] = 1U << (chan - base_chan); /* mask */ + _data[1] = data[0] ? (1U << (chan - base_chan)) : 0; /* bits */ } ret = s->insn_bits(dev, s, &_insn, _data); @@ -709,7 +712,7 @@ static int __comedi_device_postconfig(struct comedi_device *dev) if (s->type == COMEDI_SUBD_DO) { if (s->n_chan < 32) - s->io_bits = (1 << s->n_chan) - 1; + s->io_bits = (1U << s->n_chan) - 1; else s->io_bits = 0xffffffff; } diff --git a/drivers/comedi/drivers/aio_iiro_16.c b/drivers/comedi/drivers/aio_iiro_16.c index b00fab0b89d4..739cc4db52ac 100644 --- a/drivers/comedi/drivers/aio_iiro_16.c +++ b/drivers/comedi/drivers/aio_iiro_16.c @@ -177,7 +177,8 @@ static int aio_iiro_16_attach(struct comedi_device *dev, * Digital input change of state interrupts are optionally supported * using IRQ 2-7, 10-12, 14, or 15. */ - if ((1 << it->options[1]) & 0xdcfc) { + if (it->options[1] > 0 && it->options[1] < 16 && + (1 << it->options[1]) & 0xdcfc) { ret = request_irq(it->options[1], aio_iiro_16_cos, 0, dev->board_name, dev); if (ret == 0) diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index 9747e6d1f6eb..7984950f0f99 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -792,7 +792,7 @@ static void waveform_detach(struct comedi_device *dev) { struct waveform_private *devpriv = dev->private; - if (devpriv) { + if (devpriv && dev->n_subdevices) { timer_delete_sync(&devpriv->ai_timer); timer_delete_sync(&devpriv->ao_timer); } diff --git a/drivers/comedi/drivers/das16m1.c b/drivers/comedi/drivers/das16m1.c index b8ea737ad3d1..1b638f5b5a4f 100644 --- a/drivers/comedi/drivers/das16m1.c +++ b/drivers/comedi/drivers/das16m1.c @@ -522,7 +522,8 @@ static int das16m1_attach(struct comedi_device *dev, devpriv->extra_iobase = dev->iobase + DAS16M1_8255_IOBASE; /* only irqs 2, 3, 4, 5, 6, 7, 10, 11, 12, 14, and 15 are valid */ - if ((1 << it->options[1]) & 0xdcfc) { + if (it->options[1] >= 2 && it->options[1] <= 15 && + (1 << it->options[1]) & 0xdcfc) { ret = request_irq(it->options[1], das16m1_interrupt, 0, dev->board_name, dev); if (ret == 0) diff --git a/drivers/comedi/drivers/das6402.c b/drivers/comedi/drivers/das6402.c index 68f95330de45..7660487e563c 100644 --- a/drivers/comedi/drivers/das6402.c +++ b/drivers/comedi/drivers/das6402.c @@ -567,7 +567,8 @@ static int das6402_attach(struct comedi_device *dev, das6402_reset(dev); /* IRQs 2,3,5,6,7, 10,11,15 are valid for "enhanced" mode */ - if ((1 << it->options[1]) & 0x8cec) { + if (it->options[1] > 0 && it->options[1] < 16 && + (1 << it->options[1]) & 0x8cec) { ret = request_irq(it->options[1], das6402_interrupt, 0, dev->board_name, dev); if (ret == 0) { diff --git a/drivers/comedi/drivers/pcl812.c b/drivers/comedi/drivers/pcl812.c index 0df639c6a595..abca61a72cf7 100644 --- a/drivers/comedi/drivers/pcl812.c +++ b/drivers/comedi/drivers/pcl812.c @@ -1149,7 +1149,8 @@ static int pcl812_attach(struct comedi_device *dev, struct comedi_devconfig *it) if (IS_ERR(dev->pacer)) return PTR_ERR(dev->pacer); - if ((1 << it->options[1]) & board->irq_bits) { + if (it->options[1] > 0 && it->options[1] < 16 && + (1 << it->options[1]) & board->irq_bits) { ret = request_irq(it->options[1], pcl812_interrupt, 0, dev->board_name, dev); if (ret == 0) diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index 4e1ba35deda9..b19bc60cc627 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -45,7 +45,6 @@ struct psci_cpuidle_domain_state { static DEFINE_PER_CPU_READ_MOSTLY(struct psci_cpuidle_data, psci_cpuidle_data); static DEFINE_PER_CPU(struct psci_cpuidle_domain_state, psci_domain_state); static bool psci_cpuidle_use_syscore; -static bool psci_cpuidle_use_cpuhp; void psci_set_domain_state(struct generic_pm_domain *pd, unsigned int state_idx, u32 state) @@ -124,8 +123,12 @@ static int psci_idle_cpuhp_up(unsigned int cpu) { struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev); - if (pd_dev) - pm_runtime_get_sync(pd_dev); + if (pd_dev) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + pm_runtime_get_sync(pd_dev); + else + dev_pm_genpd_resume(pd_dev); + } return 0; } @@ -135,7 +138,11 @@ static int psci_idle_cpuhp_down(unsigned int cpu) struct device *pd_dev = __this_cpu_read(psci_cpuidle_data.dev); if (pd_dev) { - pm_runtime_put_sync(pd_dev); + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + pm_runtime_put_sync(pd_dev); + else + dev_pm_genpd_suspend(pd_dev); + /* Clear domain state to start fresh at next online. */ psci_clear_domain_state(); } @@ -196,9 +203,6 @@ static void psci_idle_init_cpuhp(void) { int err; - if (!psci_cpuidle_use_cpuhp) - return; - err = cpuhp_setup_state_nocalls(CPUHP_AP_CPU_PM_STARTING, "cpuidle/psci:online", psci_idle_cpuhp_up, @@ -259,10 +263,8 @@ static int psci_dt_cpu_init_topology(struct cpuidle_driver *drv, * s2ram and s2idle. */ drv->states[state_count - 1].enter_s2idle = psci_enter_s2idle_domain_idle_state; - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) drv->states[state_count - 1].enter = psci_enter_domain_idle_state; - psci_cpuidle_use_cpuhp = true; - } return 0; } @@ -339,7 +341,6 @@ static void psci_cpu_deinit_idle(int cpu) dt_idle_detach_cpu(data->dev); psci_cpuidle_use_syscore = false; - psci_cpuidle_use_cpuhp = false; } static int psci_idle_init_cpu(struct device *dev, int cpu) diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index af37477ffd8d..be21e4e2016c 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -314,30 +314,30 @@ static int chcr_compute_partial_hash(struct shash_desc *desc, if (digest_size == SHA1_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA1_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha1_st); + crypto_shash_export_core(desc, &sha1_st); memcpy(result_hash, sha1_st.state, SHA1_DIGEST_SIZE); } else if (digest_size == SHA224_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA256_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha256_st); + crypto_shash_export_core(desc, &sha256_st); memcpy(result_hash, sha256_st.state, SHA256_DIGEST_SIZE); } else if (digest_size == SHA256_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA256_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha256_st); + crypto_shash_export_core(desc, &sha256_st); memcpy(result_hash, sha256_st.state, SHA256_DIGEST_SIZE); } else if (digest_size == SHA384_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA512_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha512_st); + crypto_shash_export_core(desc, &sha512_st); memcpy(result_hash, sha512_st.state, SHA512_DIGEST_SIZE); } else if (digest_size == SHA512_DIGEST_SIZE) { error = crypto_shash_init(desc) ?: crypto_shash_update(desc, iopad, SHA512_BLOCK_SIZE) ?: - crypto_shash_export(desc, (void *)&sha512_st); + crypto_shash_export_core(desc, &sha512_st); memcpy(result_hash, sha512_st.state, SHA512_DIGEST_SIZE); } else { error = -EINVAL; diff --git a/drivers/crypto/intel/qat/qat_common/qat_algs.c b/drivers/crypto/intel/qat/qat_common/qat_algs.c index 3c4bba4a8779..c03a69851114 100644 --- a/drivers/crypto/intel/qat/qat_common/qat_algs.c +++ b/drivers/crypto/intel/qat/qat_common/qat_algs.c @@ -5,11 +5,11 @@ #include <linux/crypto.h> #include <crypto/internal/aead.h> #include <crypto/internal/cipher.h> +#include <crypto/internal/hash.h> #include <crypto/internal/skcipher.h> #include <crypto/aes.h> #include <crypto/sha1.h> #include <crypto/sha2.h> -#include <crypto/hash.h> #include <crypto/hmac.h> #include <crypto/algapi.h> #include <crypto/authenc.h> @@ -154,19 +154,19 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash, switch (ctx->qat_hash_alg) { case ICP_QAT_HW_AUTH_ALGO_SHA1: - if (crypto_shash_export(shash, &ctx->sha1)) + if (crypto_shash_export_core(shash, &ctx->sha1)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha1.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA256: - if (crypto_shash_export(shash, &ctx->sha256)) + if (crypto_shash_export_core(shash, &ctx->sha256)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha256.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA512: - if (crypto_shash_export(shash, &ctx->sha512)) + if (crypto_shash_export_core(shash, &ctx->sha512)) return -EFAULT; for (i = 0; i < digest_size >> 3; i++, hash512_state_out++) *hash512_state_out = cpu_to_be64(ctx->sha512.state[i]); @@ -190,19 +190,19 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash, switch (ctx->qat_hash_alg) { case ICP_QAT_HW_AUTH_ALGO_SHA1: - if (crypto_shash_export(shash, &ctx->sha1)) + if (crypto_shash_export_core(shash, &ctx->sha1)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha1.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA256: - if (crypto_shash_export(shash, &ctx->sha256)) + if (crypto_shash_export_core(shash, &ctx->sha256)) return -EFAULT; for (i = 0; i < digest_size >> 2; i++, hash_state_out++) *hash_state_out = cpu_to_be32(ctx->sha256.state[i]); break; case ICP_QAT_HW_AUTH_ALGO_SHA512: - if (crypto_shash_export(shash, &ctx->sha512)) + if (crypto_shash_export_core(shash, &ctx->sha512)) return -EFAULT; for (i = 0; i < digest_size >> 3; i++, hash512_state_out++) *hash512_state_out = cpu_to_be64(ctx->sha512.state[i]); diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c index 49f09998e5c0..3371e0a76d3c 100644 --- a/drivers/dma/dw-edma/dw-edma-pcie.c +++ b/drivers/dma/dw-edma/dw-edma-pcie.c @@ -161,12 +161,16 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *pid) { struct dw_edma_pcie_data *pdata = (void *)pid->driver_data; - struct dw_edma_pcie_data vsec_data; + struct dw_edma_pcie_data *vsec_data __free(kfree) = NULL; struct device *dev = &pdev->dev; struct dw_edma_chip *chip; int err, nr_irqs; int i, mask; + vsec_data = kmalloc(sizeof(*vsec_data), GFP_KERNEL); + if (!vsec_data) + return -ENOMEM; + /* Enable PCI device */ err = pcim_enable_device(pdev); if (err) { @@ -174,23 +178,23 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return err; } - memcpy(&vsec_data, pdata, sizeof(struct dw_edma_pcie_data)); + memcpy(vsec_data, pdata, sizeof(struct dw_edma_pcie_data)); /* * Tries to find if exists a PCIe Vendor-Specific Extended Capability * for the DMA, if one exists, then reconfigures it. */ - dw_edma_pcie_get_vsec_dma_data(pdev, &vsec_data); + dw_edma_pcie_get_vsec_dma_data(pdev, vsec_data); /* Mapping PCI BAR regions */ - mask = BIT(vsec_data.rg.bar); - for (i = 0; i < vsec_data.wr_ch_cnt; i++) { - mask |= BIT(vsec_data.ll_wr[i].bar); - mask |= BIT(vsec_data.dt_wr[i].bar); + mask = BIT(vsec_data->rg.bar); + for (i = 0; i < vsec_data->wr_ch_cnt; i++) { + mask |= BIT(vsec_data->ll_wr[i].bar); + mask |= BIT(vsec_data->dt_wr[i].bar); } - for (i = 0; i < vsec_data.rd_ch_cnt; i++) { - mask |= BIT(vsec_data.ll_rd[i].bar); - mask |= BIT(vsec_data.dt_rd[i].bar); + for (i = 0; i < vsec_data->rd_ch_cnt; i++) { + mask |= BIT(vsec_data->ll_rd[i].bar); + mask |= BIT(vsec_data->dt_rd[i].bar); } err = pcim_iomap_regions(pdev, mask, pci_name(pdev)); if (err) { @@ -213,7 +217,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, return -ENOMEM; /* IRQs allocation */ - nr_irqs = pci_alloc_irq_vectors(pdev, 1, vsec_data.irqs, + nr_irqs = pci_alloc_irq_vectors(pdev, 1, vsec_data->irqs, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (nr_irqs < 1) { pci_err(pdev, "fail to alloc IRQ vector (number of IRQs=%u)\n", @@ -224,22 +228,22 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, /* Data structure initialization */ chip->dev = dev; - chip->mf = vsec_data.mf; + chip->mf = vsec_data->mf; chip->nr_irqs = nr_irqs; chip->ops = &dw_edma_pcie_plat_ops; - chip->ll_wr_cnt = vsec_data.wr_ch_cnt; - chip->ll_rd_cnt = vsec_data.rd_ch_cnt; + chip->ll_wr_cnt = vsec_data->wr_ch_cnt; + chip->ll_rd_cnt = vsec_data->rd_ch_cnt; - chip->reg_base = pcim_iomap_table(pdev)[vsec_data.rg.bar]; + chip->reg_base = pcim_iomap_table(pdev)[vsec_data->rg.bar]; if (!chip->reg_base) return -ENOMEM; for (i = 0; i < chip->ll_wr_cnt; i++) { struct dw_edma_region *ll_region = &chip->ll_region_wr[i]; struct dw_edma_region *dt_region = &chip->dt_region_wr[i]; - struct dw_edma_block *ll_block = &vsec_data.ll_wr[i]; - struct dw_edma_block *dt_block = &vsec_data.dt_wr[i]; + struct dw_edma_block *ll_block = &vsec_data->ll_wr[i]; + struct dw_edma_block *dt_block = &vsec_data->dt_wr[i]; ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar]; if (!ll_region->vaddr.io) @@ -263,8 +267,8 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, for (i = 0; i < chip->ll_rd_cnt; i++) { struct dw_edma_region *ll_region = &chip->ll_region_rd[i]; struct dw_edma_region *dt_region = &chip->dt_region_rd[i]; - struct dw_edma_block *ll_block = &vsec_data.ll_rd[i]; - struct dw_edma_block *dt_block = &vsec_data.dt_rd[i]; + struct dw_edma_block *ll_block = &vsec_data->ll_rd[i]; + struct dw_edma_block *dt_block = &vsec_data->dt_rd[i]; ll_region->vaddr.io = pcim_iomap_table(pdev)[ll_block->bar]; if (!ll_region->vaddr.io) @@ -298,31 +302,31 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev, pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", chip->mf); pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p)\n", - vsec_data.rg.bar, vsec_data.rg.off, vsec_data.rg.sz, + vsec_data->rg.bar, vsec_data->rg.off, vsec_data->rg.sz, chip->reg_base); for (i = 0; i < chip->ll_wr_cnt; i++) { pci_dbg(pdev, "L. List:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.ll_wr[i].bar, - vsec_data.ll_wr[i].off, chip->ll_region_wr[i].sz, + i, vsec_data->ll_wr[i].bar, + vsec_data->ll_wr[i].off, chip->ll_region_wr[i].sz, chip->ll_region_wr[i].vaddr.io, &chip->ll_region_wr[i].paddr); pci_dbg(pdev, "Data:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.dt_wr[i].bar, - vsec_data.dt_wr[i].off, chip->dt_region_wr[i].sz, + i, vsec_data->dt_wr[i].bar, + vsec_data->dt_wr[i].off, chip->dt_region_wr[i].sz, chip->dt_region_wr[i].vaddr.io, &chip->dt_region_wr[i].paddr); } for (i = 0; i < chip->ll_rd_cnt; i++) { pci_dbg(pdev, "L. List:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.ll_rd[i].bar, - vsec_data.ll_rd[i].off, chip->ll_region_rd[i].sz, + i, vsec_data->ll_rd[i].bar, + vsec_data->ll_rd[i].off, chip->ll_region_rd[i].sz, chip->ll_region_rd[i].vaddr.io, &chip->ll_region_rd[i].paddr); pci_dbg(pdev, "Data:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n", - i, vsec_data.dt_rd[i].bar, - vsec_data.dt_rd[i].off, chip->dt_region_rd[i].sz, + i, vsec_data->dt_rd[i].bar, + vsec_data->dt_rd[i].off, chip->dt_region_rd[i].sz, chip->dt_region_rd[i].vaddr.io, &chip->dt_region_rd[i].paddr); } diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c index 47c8adfdc155..9f0c41ca7770 100644 --- a/drivers/dma/mediatek/mtk-cqdma.c +++ b/drivers/dma/mediatek/mtk-cqdma.c @@ -449,9 +449,9 @@ static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c, return ret; spin_lock_irqsave(&cvc->pc->lock, flags); - spin_lock_irqsave(&cvc->vc.lock, flags); + spin_lock(&cvc->vc.lock); vd = mtk_cqdma_find_active_desc(c, cookie); - spin_unlock_irqrestore(&cvc->vc.lock, flags); + spin_unlock(&cvc->vc.lock); spin_unlock_irqrestore(&cvc->pc->lock, flags); if (vd) { diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c index 0d6324c4e2be..7a2488a0d6a3 100644 --- a/drivers/dma/nbpfaxi.c +++ b/drivers/dma/nbpfaxi.c @@ -1351,7 +1351,7 @@ static int nbpf_probe(struct platform_device *pdev) if (irqs == 1) { eirq = irqbuf[0]; - for (i = 0; i <= num_channels; i++) + for (i = 0; i < num_channels; i++) nbpf->chan[i].irq = irqbuf[0]; } else { eirq = platform_get_irq_byname(pdev, "error"); @@ -1361,16 +1361,15 @@ static int nbpf_probe(struct platform_device *pdev) if (irqs == num_channels + 1) { struct nbpf_channel *chan; - for (i = 0, chan = nbpf->chan; i <= num_channels; + for (i = 0, chan = nbpf->chan; i < num_channels; i++, chan++) { /* Skip the error IRQ */ if (irqbuf[i] == eirq) i++; + if (i >= ARRAY_SIZE(irqbuf)) + return -EINVAL; chan->irq = irqbuf[i]; } - - if (chan != nbpf->chan + num_channels) - return -EINVAL; } else { /* 2 IRQs and more than one channel */ if (irqbuf[0] == eirq) @@ -1378,7 +1377,7 @@ static int nbpf_probe(struct platform_device *pdev) else irq = irqbuf[0]; - for (i = 0; i <= num_channels; i++) + for (i = 0; i < num_channels; i++) nbpf->chan[i].irq = irq; } } diff --git a/drivers/gpio/gpiolib-acpi-quirks.c b/drivers/gpio/gpiolib-acpi-quirks.c index 219667315b2c..c13545dce349 100644 --- a/drivers/gpio/gpiolib-acpi-quirks.c +++ b/drivers/gpio/gpiolib-acpi-quirks.c @@ -331,6 +331,19 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_interrupt = "AMDI0030:00@11", }, }, + { + /* + * Wakeup only works when keyboard backlight is turned off + * https://gitlab.freedesktop.org/drm/amd/-/issues/4169 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Acer Nitro V 15"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_interrupt = "AMDI0030:00@8", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib-devres.c b/drivers/gpio/gpiolib-devres.c index 4d5f83b17624..72422c5db364 100644 --- a/drivers/gpio/gpiolib-devres.c +++ b/drivers/gpio/gpiolib-devres.c @@ -319,7 +319,7 @@ EXPORT_SYMBOL_GPL(devm_gpiod_unhinge); */ void devm_gpiod_put_array(struct device *dev, struct gpio_descs *descs) { - devm_remove_action(dev, devm_gpiod_release_array, descs); + devm_release_action(dev, devm_gpiod_release_array, descs); } EXPORT_SYMBOL_GPL(devm_gpiod_put_array); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 78f8755996f0..aa32df7e2fb2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -5193,6 +5193,8 @@ exit: dev->dev->power.disable_depth--; #endif } + + amdgpu_vram_mgr_clear_reset_blocks(adev); adev->in_suspend = false; if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DEV_D0)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 426834806fbf..6ac0ce361a2d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -427,6 +427,7 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid, { unsigned long flags; ktime_t deadline; + bool ret; if (unlikely(ring->adev->debug_disable_soft_recovery)) return false; @@ -441,12 +442,16 @@ bool amdgpu_ring_soft_recovery(struct amdgpu_ring *ring, unsigned int vmid, dma_fence_set_error(fence, -ENODATA); spin_unlock_irqrestore(fence->lock, flags); - atomic_inc(&ring->adev->gpu_reset_counter); while (!dma_fence_is_signaled(fence) && ktime_to_ns(ktime_sub(deadline, ktime_get())) > 0) ring->funcs->soft_recovery(ring, vmid); - return dma_fence_is_signaled(fence); + ret = dma_fence_is_signaled(fence); + /* increment the counter only if soft reset worked */ + if (ret) + atomic_inc(&ring->adev->gpu_reset_counter); + + return ret; } /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 208b7d1d8a27..450e4bf093b7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -154,6 +154,7 @@ int amdgpu_vram_mgr_reserve_range(struct amdgpu_vram_mgr *mgr, uint64_t start, uint64_t size); int amdgpu_vram_mgr_query_page_status(struct amdgpu_vram_mgr *mgr, uint64_t start); +void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev); bool amdgpu_res_cpu_visible(struct amdgpu_device *adev, struct ttm_resource *res); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index abdc52b0895a..07c936e90d8e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -783,6 +783,23 @@ uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr) } /** + * amdgpu_vram_mgr_clear_reset_blocks - reset clear blocks + * + * @adev: amdgpu device pointer + * + * Reset the cleared drm buddy blocks. + */ +void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev) +{ + struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr; + struct drm_buddy *mm = &mgr->mm; + + mutex_lock(&mgr->lock); + drm_buddy_reset_clear(mm, false); + mutex_unlock(&mgr->lock); +} + +/** * amdgpu_vram_mgr_intersects - test each drm buddy block for intersection * * @man: TTM memory type manager diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 5ee2237d8ee8..bc983ecf3d99 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4640,6 +4640,7 @@ static int gfx_v8_0_kcq_init_queue(struct amdgpu_ring *ring) memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(struct vi_mqd_allocation)); /* reset ring buffer */ ring->wptr = 0; + atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); amdgpu_ring_clear_ring(ring); } return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c index 87058271b00c..2551823382f8 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crtc.c @@ -728,7 +728,16 @@ int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm, * support programmable degamma anywhere. */ is_dcn = dm->adev->dm.dc->caps.color.dpp.dcn_arch; - drm_crtc_enable_color_mgmt(&acrtc->base, is_dcn ? MAX_COLOR_LUT_ENTRIES : 0, + /* Dont't enable DRM CRTC degamma property for DCN401 since the + * pre-blending degamma LUT doesn't apply to cursor, and therefore + * can't work similar to a post-blending degamma LUT as in other hw + * versions. + * TODO: revisit it once KMS plane color API is merged. + */ + drm_crtc_enable_color_mgmt(&acrtc->base, + (is_dcn && + dm->adev->dm.dc->ctx->dce_version != DCN_VERSION_4_01) ? + MAX_COLOR_LUT_ENTRIES : 0, true, MAX_COLOR_LUT_ENTRIES); drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c index a3b8e3d4a429..4b17d2fcd565 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn401/dcn401_clk_mgr.c @@ -1565,7 +1565,7 @@ struct clk_mgr_internal *dcn401_clk_mgr_construct( clk_mgr->base.bw_params = kzalloc(sizeof(*clk_mgr->base.bw_params), GFP_KERNEL); if (!clk_mgr->base.bw_params) { BREAK_TO_DEBUGGER(); - kfree(clk_mgr); + kfree(clk_mgr401); return NULL; } @@ -1576,6 +1576,7 @@ struct clk_mgr_internal *dcn401_clk_mgr_construct( if (!clk_mgr->wm_range_table) { BREAK_TO_DEBUGGER(); kfree(clk_mgr->base.bw_params); + kfree(clk_mgr401); return NULL; } diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index de9c23537465..834b42a4d31f 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1373,7 +1373,7 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, regmap_update_bits(pdata->regmap, SN_HPD_DISABLE_REG, HPD_DISABLE, 0); mutex_unlock(&pdata->comms_mutex); - }; + } drm_bridge_add(&pdata->bridge); diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index dc622c78db9d..ea78c6c8ca7a 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -725,7 +725,7 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset, * monitor doesn't power down exactly after the throw away read. */ if (!aux->is_remote) { - ret = drm_dp_dpcd_probe(aux, DP_LANE0_1_STATUS); + ret = drm_dp_dpcd_probe(aux, DP_TRAINING_PATTERN_SET); if (ret < 0) return ret; } diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 241c855f891f..66aff35f8647 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -405,6 +405,49 @@ drm_get_buddy(struct drm_buddy_block *block) EXPORT_SYMBOL(drm_get_buddy); /** + * drm_buddy_reset_clear - reset blocks clear state + * + * @mm: DRM buddy manager + * @is_clear: blocks clear state + * + * Reset the clear state based on @is_clear value for each block + * in the freelist. + */ +void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear) +{ + u64 root_size, size, start; + unsigned int order; + int i; + + size = mm->size; + for (i = 0; i < mm->n_roots; ++i) { + order = ilog2(size) - ilog2(mm->chunk_size); + start = drm_buddy_block_offset(mm->roots[i]); + __force_merge(mm, start, start + size, order); + + root_size = mm->chunk_size << order; + size -= root_size; + } + + for (i = 0; i <= mm->max_order; ++i) { + struct drm_buddy_block *block; + + list_for_each_entry_reverse(block, &mm->free_list[i], link) { + if (is_clear != drm_buddy_block_is_clear(block)) { + if (is_clear) { + mark_cleared(block); + mm->clear_avail += drm_buddy_block_size(mm, block); + } else { + clear_reset(block); + mm->clear_avail -= drm_buddy_block_size(mm, block); + } + } + } + } +} +EXPORT_SYMBOL(drm_buddy_reset_clear); + +/** * drm_buddy_free_block - free a block * * @mm: DRM buddy manager diff --git a/drivers/gpu/drm/drm_gem_dma_helper.c b/drivers/gpu/drm/drm_gem_dma_helper.c index b7f033d4352a..4f0320df858f 100644 --- a/drivers/gpu/drm/drm_gem_dma_helper.c +++ b/drivers/gpu/drm/drm_gem_dma_helper.c @@ -230,7 +230,7 @@ void drm_gem_dma_free(struct drm_gem_dma_object *dma_obj) if (drm_gem_is_imported(gem_obj)) { if (dma_obj->vaddr) - dma_buf_vunmap_unlocked(gem_obj->dma_buf, &map); + dma_buf_vunmap_unlocked(gem_obj->import_attach->dmabuf, &map); drm_prime_gem_destroy(gem_obj, dma_obj->sgt); } else if (dma_obj->vaddr) { if (dma_obj->map_noncoherent) diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c index 6f72e7a0f427..6ff22e04029e 100644 --- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c +++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c @@ -419,6 +419,7 @@ EXPORT_SYMBOL(drm_gem_fb_vunmap); static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir, unsigned int num_planes) { + struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; int ret; @@ -427,9 +428,10 @@ static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_dat obj = drm_gem_fb_get_obj(fb, num_planes); if (!obj) continue; + import_attach = obj->import_attach; if (!drm_gem_is_imported(obj)) continue; - ret = dma_buf_end_cpu_access(obj->dma_buf, dir); + ret = dma_buf_end_cpu_access(import_attach->dmabuf, dir); if (ret) drm_err(fb->dev, "dma_buf_end_cpu_access(%u, %d) failed: %d\n", ret, num_planes, dir); @@ -452,6 +454,7 @@ static void __drm_gem_fb_end_cpu_access(struct drm_framebuffer *fb, enum dma_dat */ int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direction dir) { + struct dma_buf_attachment *import_attach; struct drm_gem_object *obj; unsigned int i; int ret; @@ -462,9 +465,10 @@ int drm_gem_fb_begin_cpu_access(struct drm_framebuffer *fb, enum dma_data_direct ret = -EINVAL; goto err___drm_gem_fb_end_cpu_access; } + import_attach = obj->import_attach; if (!drm_gem_is_imported(obj)) continue; - ret = dma_buf_begin_cpu_access(obj->dma_buf, dir); + ret = dma_buf_begin_cpu_access(import_attach->dmabuf, dir); if (ret) goto err___drm_gem_fb_end_cpu_access; } diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index aa43265f4f4f..a5dbee6974ab 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -349,7 +349,7 @@ int drm_gem_shmem_vmap_locked(struct drm_gem_shmem_object *shmem, int ret = 0; if (drm_gem_is_imported(obj)) { - ret = dma_buf_vmap(obj->dma_buf, map); + ret = dma_buf_vmap(obj->import_attach->dmabuf, map); } else { pgprot_t prot = PAGE_KERNEL; @@ -409,7 +409,7 @@ void drm_gem_shmem_vunmap_locked(struct drm_gem_shmem_object *shmem, struct drm_gem_object *obj = &shmem->base; if (drm_gem_is_imported(obj)) { - dma_buf_vunmap(obj->dma_buf, map); + dma_buf_vunmap(obj->import_attach->dmabuf, map); } else { dma_resv_assert_held(shmem->base.resv); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index d828502268b8..a0a5d725eab0 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -453,7 +453,13 @@ struct dma_buf *drm_gem_prime_handle_to_dmabuf(struct drm_device *dev, } mutex_lock(&dev->object_name_lock); - /* re-export the original imported/exported object */ + /* re-export the original imported object */ + if (obj->import_attach) { + dmabuf = obj->import_attach->dmabuf; + get_dma_buf(dmabuf); + goto out_have_obj; + } + if (obj->dma_buf) { get_dma_buf(obj->dma_buf); dmabuf = obj->dma_buf; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c index 917ad527c961..40a50c60dfff 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_prime.c @@ -65,7 +65,7 @@ static void etnaviv_gem_prime_release(struct etnaviv_gem_object *etnaviv_obj) struct iosys_map map = IOSYS_MAP_INIT_VADDR(etnaviv_obj->vaddr); if (etnaviv_obj->vaddr) - dma_buf_vunmap_unlocked(etnaviv_obj->base.dma_buf, &map); + dma_buf_vunmap_unlocked(etnaviv_obj->base.import_attach->dmabuf, &map); /* Don't drop the pages for imported dmabuf, as they are not * ours, just free the array we allocated: @@ -82,7 +82,7 @@ static void *etnaviv_gem_prime_vmap_impl(struct etnaviv_gem_object *etnaviv_obj) lockdep_assert_held(&etnaviv_obj->lock); - ret = dma_buf_vmap(etnaviv_obj->base.dma_buf, &map); + ret = dma_buf_vmap(etnaviv_obj->base.import_attach->dmabuf, &map); if (ret) return NULL; return map.vaddr; diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c index 8f6fba4217ec..bc7527542fdc 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c @@ -719,6 +719,39 @@ int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane, return 0; } +void mtk_crtc_plane_disable(struct drm_crtc *crtc, struct drm_plane *plane) +{ +#if IS_REACHABLE(CONFIG_MTK_CMDQ) + struct mtk_crtc *mtk_crtc = to_mtk_crtc(crtc); + struct mtk_plane_state *plane_state = to_mtk_plane_state(plane->state); + int i; + + /* no need to wait for disabling the plane by CPU */ + if (!mtk_crtc->cmdq_client.chan) + return; + + if (!mtk_crtc->enabled) + return; + + /* set pending plane state to disabled */ + for (i = 0; i < mtk_crtc->layer_nr; i++) { + struct drm_plane *mtk_plane = &mtk_crtc->planes[i]; + struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(mtk_plane->state); + + if (mtk_plane->index == plane->index) { + memcpy(mtk_plane_state, plane_state, sizeof(*plane_state)); + break; + } + } + mtk_crtc_update_config(mtk_crtc, false); + + /* wait for planes to be disabled by CMDQ */ + wait_event_timeout(mtk_crtc->cb_blocking_queue, + mtk_crtc->cmdq_vblank_cnt == 0, + msecs_to_jiffies(500)); +#endif +} + void mtk_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane, struct drm_atomic_state *state) { @@ -930,7 +963,8 @@ static int mtk_crtc_init_comp_planes(struct drm_device *drm_dev, mtk_ddp_comp_supported_rotations(comp), mtk_ddp_comp_get_blend_modes(comp), mtk_ddp_comp_get_formats(comp), - mtk_ddp_comp_get_num_formats(comp), i); + mtk_ddp_comp_get_num_formats(comp), + mtk_ddp_comp_is_afbc_supported(comp), i); if (ret) return ret; diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.h b/drivers/gpu/drm/mediatek/mtk_crtc.h index 388e900b6f4d..828f109b83e7 100644 --- a/drivers/gpu/drm/mediatek/mtk_crtc.h +++ b/drivers/gpu/drm/mediatek/mtk_crtc.h @@ -21,6 +21,7 @@ int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int *path, unsigned int num_conn_routes); int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane, struct mtk_plane_state *state); +void mtk_crtc_plane_disable(struct drm_crtc *crtc, struct drm_plane *plane); void mtk_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane, struct drm_atomic_state *plane_state); struct device *mtk_crtc_dma_dev_get(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c index edc6417639e6..ac6620e10262 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c @@ -366,6 +366,7 @@ static const struct mtk_ddp_comp_funcs ddp_ovl = { .get_blend_modes = mtk_ovl_get_blend_modes, .get_formats = mtk_ovl_get_formats, .get_num_formats = mtk_ovl_get_num_formats, + .is_afbc_supported = mtk_ovl_is_afbc_supported, }; static const struct mtk_ddp_comp_funcs ddp_postmask = { diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h index 39720b27f4e9..7289b3dcf22f 100644 --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h @@ -83,6 +83,7 @@ struct mtk_ddp_comp_funcs { u32 (*get_blend_modes)(struct device *dev); const u32 *(*get_formats)(struct device *dev); size_t (*get_num_formats)(struct device *dev); + bool (*is_afbc_supported)(struct device *dev); void (*connect)(struct device *dev, struct device *mmsys_dev, unsigned int next); void (*disconnect)(struct device *dev, struct device *mmsys_dev, unsigned int next); void (*add)(struct device *dev, struct mtk_mutex *mutex); @@ -294,6 +295,14 @@ size_t mtk_ddp_comp_get_num_formats(struct mtk_ddp_comp *comp) return 0; } +static inline bool mtk_ddp_comp_is_afbc_supported(struct mtk_ddp_comp *comp) +{ + if (comp->funcs && comp->funcs->is_afbc_supported) + return comp->funcs->is_afbc_supported(comp->dev); + + return false; +} + static inline bool mtk_ddp_comp_add(struct mtk_ddp_comp *comp, struct mtk_mutex *mutex) { if (comp->funcs && comp->funcs->add) { diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h index 04217a36939c..679d413bf10b 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h +++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h @@ -106,6 +106,7 @@ void mtk_ovl_disable_vblank(struct device *dev); u32 mtk_ovl_get_blend_modes(struct device *dev); const u32 *mtk_ovl_get_formats(struct device *dev); size_t mtk_ovl_get_num_formats(struct device *dev); +bool mtk_ovl_is_afbc_supported(struct device *dev); void mtk_ovl_adaptor_add_comp(struct device *dev, struct mtk_mutex *mutex); void mtk_ovl_adaptor_remove_comp(struct device *dev, struct mtk_mutex *mutex); diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index d0581c4e3c99..e0236353d499 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -236,6 +236,13 @@ size_t mtk_ovl_get_num_formats(struct device *dev) return ovl->data->num_formats; } +bool mtk_ovl_is_afbc_supported(struct device *dev) +{ + struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); + + return ovl->data->supports_afbc; +} + int mtk_ovl_clk_enable(struct device *dev) { struct mtk_disp_ovl *ovl = dev_get_drvdata(dev); diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 6fb85bc6487a..a2fdceadf209 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -1095,7 +1095,6 @@ static const u32 mt8183_output_fmts[] = { }; static const u32 mt8195_dpi_output_fmts[] = { - MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_RGB888_1X24, MEDIA_BUS_FMT_RGB888_2X12_LE, MEDIA_BUS_FMT_RGB888_2X12_BE, @@ -1103,18 +1102,19 @@ static const u32 mt8195_dpi_output_fmts[] = { MEDIA_BUS_FMT_YUYV8_1X16, MEDIA_BUS_FMT_YUYV10_1X20, MEDIA_BUS_FMT_YUYV12_1X24, + MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_YUV8_1X24, MEDIA_BUS_FMT_YUV10_1X30, }; static const u32 mt8195_dp_intf_output_fmts[] = { - MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_RGB888_1X24, MEDIA_BUS_FMT_RGB888_2X12_LE, MEDIA_BUS_FMT_RGB888_2X12_BE, MEDIA_BUS_FMT_RGB101010_1X30, MEDIA_BUS_FMT_YUYV8_1X16, MEDIA_BUS_FMT_YUYV10_1X20, + MEDIA_BUS_FMT_BGR888_1X24, MEDIA_BUS_FMT_YUV8_1X24, MEDIA_BUS_FMT_YUV10_1X30, }; diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c index 655106bbb76d..cbc4f37da8ba 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_plane.c @@ -285,9 +285,14 @@ static void mtk_plane_atomic_disable(struct drm_plane *plane, struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); struct mtk_plane_state *mtk_plane_state = to_mtk_plane_state(new_state); + struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state, + plane); + mtk_plane_state->pending.enable = false; wmb(); /* Make sure the above parameter is set before update */ mtk_plane_state->pending.dirty = true; + + mtk_crtc_plane_disable(old_state->crtc, plane); } static void mtk_plane_atomic_update(struct drm_plane *plane, @@ -321,7 +326,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = { int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, unsigned long possible_crtcs, enum drm_plane_type type, unsigned int supported_rotations, const u32 blend_modes, - const u32 *formats, size_t num_formats, unsigned int plane_idx) + const u32 *formats, size_t num_formats, + bool supports_afbc, unsigned int plane_idx) { int err; @@ -332,7 +338,9 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, err = drm_universal_plane_init(dev, plane, possible_crtcs, &mtk_plane_funcs, formats, - num_formats, modifiers, type, NULL); + num_formats, + supports_afbc ? modifiers : NULL, + type, NULL); if (err) { DRM_ERROR("failed to initialize plane\n"); return err; diff --git a/drivers/gpu/drm/mediatek/mtk_plane.h b/drivers/gpu/drm/mediatek/mtk_plane.h index 3b13b89989c7..95c5fa5295d8 100644 --- a/drivers/gpu/drm/mediatek/mtk_plane.h +++ b/drivers/gpu/drm/mediatek/mtk_plane.h @@ -49,5 +49,6 @@ to_mtk_plane_state(struct drm_plane_state *state) int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane, unsigned long possible_crtcs, enum drm_plane_type type, unsigned int supported_rotations, const u32 blend_modes, - const u32 *formats, size_t num_formats, unsigned int plane_idx); + const u32 *formats, size_t num_formats, + bool supports_afbc, unsigned int plane_idx); #endif diff --git a/drivers/gpu/drm/nouveau/nvif/chan.c b/drivers/gpu/drm/nouveau/nvif/chan.c index baa10227d51a..80c01017d642 100644 --- a/drivers/gpu/drm/nouveau/nvif/chan.c +++ b/drivers/gpu/drm/nouveau/nvif/chan.c @@ -39,6 +39,9 @@ nvif_chan_gpfifo_post(struct nvif_chan *chan) const u32 pbptr = (chan->push.cur - map) + chan->func->gpfifo.post_size; const u32 gpptr = (chan->gpfifo.cur + 1) & chan->gpfifo.max; + if (!chan->func->gpfifo.post) + return 0; + return chan->func->gpfifo.post(chan, gpptr, pbptr); } diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c index 5657106c2f7d..15e2d505550f 100644 --- a/drivers/gpu/drm/panfrost/panfrost_job.c +++ b/drivers/gpu/drm/panfrost/panfrost_job.c @@ -841,7 +841,6 @@ int panfrost_job_init(struct panfrost_device *pfdev) .num_rqs = DRM_SCHED_PRIORITY_COUNT, .credit_limit = 2, .timeout = msecs_to_jiffies(JOB_TIMEOUT_MS), - .timeout_wq = pfdev->reset.wq, .name = "pan_js", .dev = pfdev->dev, }; @@ -879,6 +878,7 @@ int panfrost_job_init(struct panfrost_device *pfdev) pfdev->reset.wq = alloc_ordered_workqueue("panfrost-reset", 0); if (!pfdev->reset.wq) return -ENOMEM; + args.timeout_wq = pfdev->reset.wq; for (j = 0; j < NUM_JOB_SLOTS; j++) { js->queue[j].fence_context = dma_fence_context_alloc(1); diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index bbd39348a7ab..7a3e510327b7 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -26,7 +26,6 @@ * Jerome Glisse */ -#include <linux/console.h> #include <linux/efi.h> #include <linux/pci.h> #include <linux/pm_runtime.h> @@ -1635,11 +1634,9 @@ int radeon_suspend_kms(struct drm_device *dev, bool suspend, pci_set_power_state(pdev, PCI_D3hot); } - if (notify_clients) { - console_lock(); - drm_client_dev_suspend(dev, true); - console_unlock(); - } + if (notify_clients) + drm_client_dev_suspend(dev, false); + return 0; } @@ -1661,17 +1658,11 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool notify_clients) if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; - if (notify_clients) { - console_lock(); - } if (resume) { pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); - if (pci_enable_device(pdev)) { - if (notify_clients) - console_unlock(); + if (pci_enable_device(pdev)) return -1; - } } /* resume AGP if in use */ radeon_agp_resume(rdev); @@ -1747,10 +1738,8 @@ int radeon_resume_kms(struct drm_device *dev, bool resume, bool notify_clients) if ((rdev->pm.pm_method == PM_METHOD_DPM) && rdev->pm.dpm_enabled) radeon_pm_compute_clocks(rdev); - if (notify_clients) { - drm_client_dev_resume(dev, true); - console_unlock(); - } + if (notify_clients) + drm_client_dev_resume(dev, false); return 0; } diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index e671aa241720..ac678de7fe5e 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -355,17 +355,6 @@ void drm_sched_entity_destroy(struct drm_sched_entity *entity) } EXPORT_SYMBOL(drm_sched_entity_destroy); -/* drm_sched_entity_clear_dep - callback to clear the entities dependency */ -static void drm_sched_entity_clear_dep(struct dma_fence *f, - struct dma_fence_cb *cb) -{ - struct drm_sched_entity *entity = - container_of(cb, struct drm_sched_entity, cb); - - entity->dependency = NULL; - dma_fence_put(f); -} - /* * drm_sched_entity_wakeup - callback to clear the entity's dependency and * wake up the scheduler @@ -376,7 +365,8 @@ static void drm_sched_entity_wakeup(struct dma_fence *f, struct drm_sched_entity *entity = container_of(cb, struct drm_sched_entity, cb); - drm_sched_entity_clear_dep(f, cb); + entity->dependency = NULL; + dma_fence_put(f); drm_sched_wakeup(entity->rq->sched); } @@ -429,13 +419,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) fence = dma_fence_get(&s_fence->scheduled); dma_fence_put(entity->dependency); entity->dependency = fence; - if (!dma_fence_add_callback(fence, &entity->cb, - drm_sched_entity_clear_dep)) - return true; - - /* Ignore it when it is already scheduled */ - dma_fence_put(fence); - return false; } if (!dma_fence_add_callback(entity->dependency, &entity->cb, diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c index 1118a0250279..ce49282198cb 100644 --- a/drivers/gpu/drm/virtio/virtgpu_prime.c +++ b/drivers/gpu/drm/virtio/virtgpu_prime.c @@ -204,15 +204,16 @@ static void virtgpu_dma_buf_free_obj(struct drm_gem_object *obj) { struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj); struct virtio_gpu_device *vgdev = obj->dev->dev_private; + struct dma_buf_attachment *attach = obj->import_attach; if (drm_gem_is_imported(obj)) { - struct dma_buf *dmabuf = obj->dma_buf; + struct dma_buf *dmabuf = attach->dmabuf; dma_resv_lock(dmabuf->resv, NULL); virtgpu_dma_buf_unmap(bo); dma_resv_unlock(dmabuf->resv); - dma_buf_detach(dmabuf, obj->import_attach); + dma_buf_detach(dmabuf, attach); dma_buf_put(dmabuf); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index c55382167c1b..e417921af584 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -85,10 +85,10 @@ static int vmw_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map) int ret; if (drm_gem_is_imported(obj)) { - ret = dma_buf_vmap(obj->dma_buf, map); + ret = dma_buf_vmap(obj->import_attach->dmabuf, map); if (!ret) { if (drm_WARN_ON(obj->dev, map->is_iomem)) { - dma_buf_vunmap(obj->dma_buf, map); + dma_buf_vunmap(obj->import_attach->dmabuf, map); return -EIO; } } @@ -102,7 +102,7 @@ static int vmw_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map) static void vmw_gem_vunmap(struct drm_gem_object *obj, struct iosys_map *map) { if (drm_gem_is_imported(obj)) - dma_buf_vunmap(obj->dma_buf, map); + dma_buf_vunmap(obj->import_attach->dmabuf, map); else drm_gem_ttm_vunmap(obj, map); } diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 6c4cb9576fb6..e3517ce2e18c 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -417,6 +417,8 @@ int xe_gt_init_early(struct xe_gt *gt) if (err) return err; + xe_mocs_init_early(gt); + return 0; } @@ -630,17 +632,15 @@ int xe_gt_init(struct xe_gt *gt) if (err) return err; - err = xe_gt_pagefault_init(gt); + err = xe_gt_sysfs_init(gt); if (err) return err; - xe_mocs_init_early(gt); - - err = xe_gt_sysfs_init(gt); + err = gt_fw_domain_init(gt); if (err) return err; - err = gt_fw_domain_init(gt); + err = xe_gt_pagefault_init(gt); if (err) return err; @@ -839,6 +839,9 @@ static int gt_reset(struct xe_gt *gt) goto err_out; } + if (IS_SRIOV_PF(gt_to_xe(gt))) + xe_gt_sriov_pf_stop_prepare(gt); + xe_uc_gucrc_disable(>->uc); xe_uc_stop_prepare(>->uc); xe_gt_pagefault_reset(gt); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c index c08efca6420e..35489fa81825 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c @@ -172,6 +172,25 @@ void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid) pf_clear_vf_scratch_regs(gt, vfid); } +static void pf_cancel_restart(struct xe_gt *gt) +{ + xe_gt_assert(gt, IS_SRIOV_PF(gt_to_xe(gt))); + + if (cancel_work_sync(>->sriov.pf.workers.restart)) + xe_gt_sriov_dbg_verbose(gt, "pending restart canceled!\n"); +} + +/** + * xe_gt_sriov_pf_stop_prepare() - Prepare to stop SR-IOV support. + * @gt: the &xe_gt + * + * This function can only be called on the PF. + */ +void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt) +{ + pf_cancel_restart(gt); +} + static void pf_restart(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h index f474509411c0..e2b2ff8132dc 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h @@ -13,6 +13,7 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt); int xe_gt_sriov_pf_init(struct xe_gt *gt); void xe_gt_sriov_pf_init_hw(struct xe_gt *gt); void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid); +void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt); void xe_gt_sriov_pf_restart(struct xe_gt *gt); #else static inline int xe_gt_sriov_pf_init_early(struct xe_gt *gt) @@ -29,6 +30,10 @@ static inline void xe_gt_sriov_pf_init_hw(struct xe_gt *gt) { } +static inline void xe_gt_sriov_pf_stop_prepare(struct xe_gt *gt) +{ +} + static inline void xe_gt_sriov_pf_restart(struct xe_gt *gt) { } diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c index 2420a548cacc..53a44702c04a 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c @@ -2364,6 +2364,21 @@ int xe_gt_sriov_pf_config_restore(struct xe_gt *gt, unsigned int vfid, return err; } +static int pf_push_self_config(struct xe_gt *gt) +{ + int err; + + err = pf_push_full_vf_config(gt, PFID); + if (err) { + xe_gt_sriov_err(gt, "Failed to push self configuration (%pe)\n", + ERR_PTR(err)); + return err; + } + + xe_gt_sriov_dbg_verbose(gt, "self configuration completed\n"); + return 0; +} + static void fini_config(void *arg) { struct xe_gt *gt = arg; @@ -2387,9 +2402,17 @@ static void fini_config(void *arg) int xe_gt_sriov_pf_config_init(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); + int err; xe_gt_assert(gt, IS_SRIOV_PF(xe)); + mutex_lock(xe_gt_sriov_pf_master_mutex(gt)); + err = pf_push_self_config(gt); + mutex_unlock(xe_gt_sriov_pf_master_mutex(gt)); + + if (err) + return err; + return devm_add_action_or_reset(xe->drm.dev, fini_config, gt); } @@ -2407,6 +2430,10 @@ void xe_gt_sriov_pf_config_restart(struct xe_gt *gt) unsigned int n, total_vfs = xe_sriov_pf_get_totalvfs(gt_to_xe(gt)); unsigned int fail = 0, skip = 0; + mutex_lock(xe_gt_sriov_pf_master_mutex(gt)); + pf_push_self_config(gt); + mutex_unlock(xe_gt_sriov_pf_master_mutex(gt)); + for (n = 1; n <= total_vfs; n++) { if (xe_gt_sriov_pf_config_is_empty(gt, n)) skip++; diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 66bc02302c55..07a5161c7d5b 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -1817,8 +1817,8 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, xe_bo_assert_held(bo); /* Use bounce buffer for small access and unaligned access */ - if (len & XE_CACHELINE_MASK || - ((uintptr_t)buf | offset) & XE_CACHELINE_MASK) { + if (!IS_ALIGNED(len, XE_CACHELINE_BYTES) || + !IS_ALIGNED((unsigned long)buf + offset, XE_CACHELINE_BYTES)) { int buf_offset = 0; /* @@ -1848,7 +1848,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, err = xe_migrate_access_memory(m, bo, offset & ~XE_CACHELINE_MASK, (void *)ptr, - sizeof(bounce), 0); + sizeof(bounce), write); if (err) return err; } else { diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c index bc1689db4cd7..7b50c7c1ee21 100644 --- a/drivers/gpu/drm/xe/xe_ring_ops.c +++ b/drivers/gpu/drm/xe/xe_ring_ops.c @@ -110,13 +110,14 @@ static int emit_bb_start(u64 batch_addr, u32 ppgtt_flag, u32 *dw, int i) return i; } -static int emit_flush_invalidate(u32 *dw, int i) +static int emit_flush_invalidate(u32 addr, u32 val, u32 *dw, int i) { dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | - MI_FLUSH_IMM_DW | MI_FLUSH_DW_STORE_INDEX; - dw[i++] = LRC_PPHWSP_FLUSH_INVAL_SCRATCH_ADDR; - dw[i++] = 0; + MI_FLUSH_IMM_DW; + + dw[i++] = addr | MI_FLUSH_DW_USE_GTT; dw[i++] = 0; + dw[i++] = val; return i; } @@ -397,23 +398,20 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job, static void emit_migration_job_gen12(struct xe_sched_job *job, struct xe_lrc *lrc, u32 seqno) { + u32 saddr = xe_lrc_start_seqno_ggtt_addr(lrc); u32 dw[MAX_JOB_SIZE_DW], i = 0; i = emit_copy_timestamp(lrc, dw, i); - i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc), - seqno, dw, i); + i = emit_store_imm_ggtt(saddr, seqno, dw, i); dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */ i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i); - if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) { - /* XXX: Do we need this? Leaving for now. */ - dw[i++] = preparser_disable(true); - i = emit_flush_invalidate(dw, i); - dw[i++] = preparser_disable(false); - } + dw[i++] = preparser_disable(true); + i = emit_flush_invalidate(saddr, seqno, dw, i); + dw[i++] = preparser_disable(false); i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i); diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 1cd188b73b74..57623ca7f350 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -9,7 +9,7 @@ config HYPERV select PARAVIRT select X86_HV_CALLBACK_VECTOR if X86 select OF_EARLY_FLATTREE if OF - select SYSFB if !HYPERV_VTL_MODE + select SYSFB if EFI && !HYPERV_VTL_MODE help Select this option to run Linux as a Hyper-V client operating system. diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 35f26fa1ffe7..7c7c66e0dc3f 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -18,6 +18,7 @@ #include <linux/uio.h> #include <linux/interrupt.h> #include <linux/set_memory.h> +#include <linux/export.h> #include <asm/page.h> #include <asm/mshyperv.h> diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 6e084c207414..65dd299e2944 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/cpu.h> #include <linux/hyperv.h> +#include <linux/export.h> #include <asm/mshyperv.h> #include <linux/sched/isolation.h> diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index be490c598785..1fe3573ae52a 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -519,7 +519,10 @@ void vmbus_set_event(struct vmbus_channel *channel) else WARN_ON_ONCE(1); } else { - hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event); + u64 control = HVCALL_SIGNAL_EVENT; + + control |= hv_nested ? HV_HYPERCALL_NESTED : 0; + hv_do_fast_hypercall8(control, channel->sig_event); } } EXPORT_SYMBOL_GPL(vmbus_set_event); diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 308c8f279df8..b14c5f9e0ef2 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -85,8 +85,10 @@ int hv_post_message(union hv_connection_id connection_id, else status = HV_STATUS_INVALID_PARAMETER; } else { - status = hv_do_hypercall(HVCALL_POST_MESSAGE, - aligned_msg, NULL); + u64 control = HVCALL_POST_MESSAGE; + + control |= hv_nested ? HV_HYPERCALL_NESTED : 0; + status = hv_do_hypercall(control, aligned_msg, NULL); } local_irq_restore(flags); diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c index 7d7ecb6f6137..fbb4eb3901bb 100644 --- a/drivers/hv/hv_proc.c +++ b/drivers/hv/hv_proc.c @@ -6,6 +6,7 @@ #include <linux/slab.h> #include <linux/cpuhotplug.h> #include <linux/minmax.h> +#include <linux/export.h> #include <asm/mshyperv.h> /* diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c index 2575e6d7a71f..6f227a8a5af7 100644 --- a/drivers/hv/mshv_common.c +++ b/drivers/hv/mshv_common.c @@ -13,6 +13,7 @@ #include <linux/mm.h> #include <asm/mshyperv.h> #include <linux/resume_user_mode.h> +#include <linux/export.h> #include "mshv.h" diff --git a/drivers/hv/mshv_root_hv_call.c b/drivers/hv/mshv_root_hv_call.c index a222a16107f6..c9c274f29c3c 100644 --- a/drivers/hv/mshv_root_hv_call.c +++ b/drivers/hv/mshv_root_hv_call.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/export.h> #include <asm/mshyperv.h> #include "mshv_root.h" diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 3c9b02471760..23ce1fb70de1 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/prefetch.h> #include <linux/io.h> +#include <linux/export.h> #include <asm/mshyperv.h> #include "hyperv_vmbus.h" diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 33b524b4eb5e..2ed5a1e89d69 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -2509,7 +2509,7 @@ static int vmbus_acpi_add(struct platform_device *pdev) return 0; } #endif - +#ifndef HYPERVISOR_CALLBACK_VECTOR static int vmbus_set_irq(struct platform_device *pdev) { struct irq_data *data; @@ -2534,6 +2534,7 @@ static int vmbus_set_irq(struct platform_device *pdev) return 0; } +#endif static int vmbus_device_add(struct platform_device *pdev) { @@ -2549,11 +2550,11 @@ static int vmbus_device_add(struct platform_device *pdev) if (ret) return ret; - if (!__is_defined(HYPERVISOR_CALLBACK_VECTOR)) - ret = vmbus_set_irq(pdev); +#ifndef HYPERVISOR_CALLBACK_VECTOR + ret = vmbus_set_irq(pdev); if (ret) return ret; - +#endif for_each_of_range(&parser, &range) { struct resource *res; diff --git a/drivers/hwmon/corsair-cpro.c b/drivers/hwmon/corsair-cpro.c index e1a7f7aa7f80..b7b911f8359c 100644 --- a/drivers/hwmon/corsair-cpro.c +++ b/drivers/hwmon/corsair-cpro.c @@ -89,6 +89,7 @@ struct ccp_device { struct mutex mutex; /* whenever buffer is used, lock before send_usb_cmd */ u8 *cmd_buffer; u8 *buffer; + int buffer_recv_size; /* number of received bytes in buffer */ int target[6]; DECLARE_BITMAP(temp_cnct, NUM_TEMP_SENSORS); DECLARE_BITMAP(fan_cnct, NUM_FANS); @@ -146,6 +147,9 @@ static int send_usb_cmd(struct ccp_device *ccp, u8 command, u8 byte1, u8 byte2, if (!t) return -ETIMEDOUT; + if (ccp->buffer_recv_size != IN_BUFFER_SIZE) + return -EPROTO; + return ccp_get_errno(ccp); } @@ -157,6 +161,7 @@ static int ccp_raw_event(struct hid_device *hdev, struct hid_report *report, u8 spin_lock(&ccp->wait_input_report_lock); if (!completion_done(&ccp->wait_input_report)) { memcpy(ccp->buffer, data, min(IN_BUFFER_SIZE, size)); + ccp->buffer_recv_size = size; complete_all(&ccp->wait_input_report); } spin_unlock(&ccp->wait_input_report_lock); diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c index a4a41742786b..9a5fd16a4ec2 100644 --- a/drivers/hwmon/ina238.c +++ b/drivers/hwmon/ina238.c @@ -97,7 +97,7 @@ * Power (mW) = 0.2 * register value * 20000 / rshunt / 4 * gain * (Specific for SQ52206) * Power (mW) = 0.24 * register value * 20000 / rshunt / 4 * gain - * Energy (mJ) = 16 * 0.24 * register value * 20000 / rshunt / 4 * gain + * Energy (uJ) = 16 * 0.24 * register value * 20000 / rshunt / 4 * gain * 1000 */ #define INA238_CALIBRATION_VALUE 16384 #define INA238_FIXED_SHUNT 20000 @@ -500,9 +500,9 @@ static ssize_t energy1_input_show(struct device *dev, if (ret) return ret; - /* result in mJ */ - energy = div_u64(regval * INA238_FIXED_SHUNT * data->gain * 16 * - data->config->power_calculate_factor, 4 * 100 * data->rshunt); + /* result in uJ */ + energy = div_u64(regval * INA238_FIXED_SHUNT * data->gain * 16 * 10 * + data->config->power_calculate_factor, 4 * data->rshunt); return sysfs_emit(buf, "%llu\n", energy); } diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c index 2bc8cccb01fd..52d4000902d5 100644 --- a/drivers/hwmon/pmbus/ucd9000.c +++ b/drivers/hwmon/pmbus/ucd9000.c @@ -226,15 +226,15 @@ static int ucd9000_gpio_set(struct gpio_chip *gc, unsigned int offset, } if (value) { - if (ret & UCD9000_GPIO_CONFIG_STATUS) + if (ret & UCD9000_GPIO_CONFIG_OUT_VALUE) return 0; - ret |= UCD9000_GPIO_CONFIG_STATUS; + ret |= UCD9000_GPIO_CONFIG_OUT_VALUE; } else { - if (!(ret & UCD9000_GPIO_CONFIG_STATUS)) + if (!(ret & UCD9000_GPIO_CONFIG_OUT_VALUE)) return 0; - ret &= ~UCD9000_GPIO_CONFIG_STATUS; + ret &= ~UCD9000_GPIO_CONFIG_OUT_VALUE; } ret |= UCD9000_GPIO_CONFIG_ENABLE; diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 8b01df3cc8e9..5fcc9f6c33e5 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1472,7 +1472,9 @@ omap_i2c_probe(struct platform_device *pdev) } /* reset ASAP, clearing any IRQs */ - omap_i2c_init(omap); + r = omap_i2c_init(omap); + if (r) + goto err_mux_state_deselect; if (omap->rev < OMAP_I2C_OMAP1_REV_2) r = devm_request_irq(&pdev->dev, omap->irq, omap_i2c_omap1_isr, @@ -1515,12 +1517,13 @@ omap_i2c_probe(struct platform_device *pdev) err_unuse_clocks: omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0); +err_mux_state_deselect: if (omap->mux_state) mux_state_deselect(omap->mux_state); err_put_pm: - pm_runtime_dont_use_autosuspend(omap->dev); pm_runtime_put_sync(omap->dev); err_disable_pm: + pm_runtime_dont_use_autosuspend(omap->dev); pm_runtime_disable(&pdev->dev); return r; diff --git a/drivers/i2c/busses/i2c-stm32.c b/drivers/i2c/busses/i2c-stm32.c index 157c64e27d0b..f84ec056e36d 100644 --- a/drivers/i2c/busses/i2c-stm32.c +++ b/drivers/i2c/busses/i2c-stm32.c @@ -102,7 +102,6 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma, void *dma_async_param) { struct dma_async_tx_descriptor *txdesc; - struct device *chan_dev; int ret; if (rd_wr) { @@ -116,11 +115,10 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma, } dma->dma_len = len; - chan_dev = dma->chan_using->device->dev; - dma->dma_buf = dma_map_single(chan_dev, buf, dma->dma_len, + dma->dma_buf = dma_map_single(dev, buf, dma->dma_len, dma->dma_data_dir); - if (dma_mapping_error(chan_dev, dma->dma_buf)) { + if (dma_mapping_error(dev, dma->dma_buf)) { dev_err(dev, "DMA mapping failed\n"); return -EINVAL; } @@ -150,7 +148,7 @@ int stm32_i2c_prep_dma_xfer(struct device *dev, struct stm32_i2c_dma *dma, return 0; err: - dma_unmap_single(chan_dev, dma->dma_buf, dma->dma_len, + dma_unmap_single(dev, dma->dma_buf, dma->dma_len, dma->dma_data_dir); return ret; } diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c index e4aaeb2262d0..73a7b8894c0d 100644 --- a/drivers/i2c/busses/i2c-stm32f7.c +++ b/drivers/i2c/busses/i2c-stm32f7.c @@ -739,12 +739,13 @@ static void stm32f7_i2c_disable_dma_req(struct stm32f7_i2c_dev *i2c_dev) static void stm32f7_i2c_dma_callback(void *arg) { - struct stm32f7_i2c_dev *i2c_dev = (struct stm32f7_i2c_dev *)arg; + struct stm32f7_i2c_dev *i2c_dev = arg; struct stm32_i2c_dma *dma = i2c_dev->dma; - struct device *dev = dma->chan_using->device->dev; stm32f7_i2c_disable_dma_req(i2c_dev); - dma_unmap_single(dev, dma->dma_buf, dma->dma_len, dma->dma_data_dir); + dmaengine_terminate_async(dma->chan_using); + dma_unmap_single(i2c_dev->dev, dma->dma_buf, dma->dma_len, + dma->dma_data_dir); complete(&dma->dma_complete); } @@ -1510,7 +1511,6 @@ static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev, u16 addr = f7_msg->addr; void __iomem *base = i2c_dev->base; struct device *dev = i2c_dev->dev; - struct stm32_i2c_dma *dma = i2c_dev->dma; /* Bus error */ if (status & STM32F7_I2C_ISR_BERR) { @@ -1551,10 +1551,8 @@ static irqreturn_t stm32f7_i2c_handle_isr_errs(struct stm32f7_i2c_dev *i2c_dev, } /* Disable dma */ - if (i2c_dev->use_dma) { - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); - } + if (i2c_dev->use_dma) + stm32f7_i2c_dma_callback(i2c_dev); i2c_dev->master_mode = false; complete(&i2c_dev->complete); @@ -1600,7 +1598,6 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) { struct stm32f7_i2c_dev *i2c_dev = data; struct stm32f7_i2c_msg *f7_msg = &i2c_dev->f7_msg; - struct stm32_i2c_dma *dma = i2c_dev->dma; void __iomem *base = i2c_dev->base; u32 status, mask; int ret; @@ -1619,10 +1616,8 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) dev_dbg(i2c_dev->dev, "<%s>: Receive NACK (addr %x)\n", __func__, f7_msg->addr); writel_relaxed(STM32F7_I2C_ICR_NACKCF, base + STM32F7_I2C_ICR); - if (i2c_dev->use_dma) { - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); - } + if (i2c_dev->use_dma) + stm32f7_i2c_dma_callback(i2c_dev); f7_msg->result = -ENXIO; } @@ -1640,8 +1635,7 @@ static irqreturn_t stm32f7_i2c_isr_event_thread(int irq, void *data) ret = wait_for_completion_timeout(&i2c_dev->dma->dma_complete, HZ); if (!ret) { dev_dbg(i2c_dev->dev, "<%s>: Timed out\n", __func__); - stm32f7_i2c_disable_dma_req(i2c_dev); - dmaengine_terminate_async(dma->chan_using); + stm32f7_i2c_dma_callback(i2c_dev); f7_msg->result = -ETIMEDOUT; } } diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 12598feaa693..b10a30960e1e 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -877,6 +877,8 @@ static int fxls8962af_buffer_predisable(struct iio_dev *indio_dev) if (ret) return ret; + synchronize_irq(data->irq); + ret = __fxls8962af_fifo_set_mode(data, false); if (data->enable_event) diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 99cb661fabb2..a7961c610ed2 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1353,6 +1353,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) union acpi_object *ont; union acpi_object *elements; acpi_status status; + struct device *parent = indio_dev->dev.parent; int ret = -EINVAL; unsigned int val; int i, j; @@ -1371,7 +1372,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) }; - adev = ACPI_COMPANION(indio_dev->dev.parent); + adev = ACPI_COMPANION(parent); if (!adev) return -ENXIO; @@ -1380,8 +1381,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) if (status == AE_NOT_FOUND) { return -ENXIO; } else if (ACPI_FAILURE(status)) { - dev_warn(&indio_dev->dev, "failed to execute _ONT: %d\n", - status); + dev_warn(parent, "failed to execute _ONT: %d\n", status); return status; } @@ -1457,12 +1457,12 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) } ret = 0; - dev_info(&indio_dev->dev, "computed mount matrix from ACPI\n"); + dev_info(parent, "computed mount matrix from ACPI\n"); out: kfree(buffer.pointer); if (ret) - dev_dbg(&indio_dev->dev, + dev_dbg(parent, "failed to apply ACPI orientation data: %d\n", ret); return ret; diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c index d96bd12dfea6..cabf5511d116 100644 --- a/drivers/iio/adc/ad7380.c +++ b/drivers/iio/adc/ad7380.c @@ -1953,8 +1953,9 @@ static int ad7380_probe(struct spi_device *spi) if (st->chip_info->has_hardware_gain) { device_for_each_child_node_scoped(dev, node) { - unsigned int channel, gain; + unsigned int channel; int gain_idx; + u16 gain; ret = fwnode_property_read_u32(node, "reg", &channel); if (ret) @@ -1966,7 +1967,7 @@ static int ad7380_probe(struct spi_device *spi) "Invalid channel number %i\n", channel); - ret = fwnode_property_read_u32(node, "adi,gain-milli", + ret = fwnode_property_read_u16(node, "adi,gain-milli", &gain); if (ret && ret != -EINVAL) return dev_err_probe(dev, ret, diff --git a/drivers/iio/adc/ad7949.c b/drivers/iio/adc/ad7949.c index edd0c3a35ab7..202561cad401 100644 --- a/drivers/iio/adc/ad7949.c +++ b/drivers/iio/adc/ad7949.c @@ -308,7 +308,6 @@ static void ad7949_disable_reg(void *reg) static int ad7949_spi_probe(struct spi_device *spi) { - u32 spi_ctrl_mask = spi->controller->bits_per_word_mask; struct device *dev = &spi->dev; const struct ad7949_adc_spec *spec; struct ad7949_adc_chip *ad7949_adc; @@ -337,11 +336,11 @@ static int ad7949_spi_probe(struct spi_device *spi) ad7949_adc->resolution = spec->resolution; /* Set SPI bits per word */ - if (spi_ctrl_mask & SPI_BPW_MASK(ad7949_adc->resolution)) { + if (spi_is_bpw_supported(spi, ad7949_adc->resolution)) { spi->bits_per_word = ad7949_adc->resolution; - } else if (spi_ctrl_mask == SPI_BPW_MASK(16)) { + } else if (spi_is_bpw_supported(spi, 16)) { spi->bits_per_word = 16; - } else if (spi_ctrl_mask == SPI_BPW_MASK(8)) { + } else if (spi_is_bpw_supported(spi, 8)) { spi->bits_per_word = 8; } else { dev_err(dev, "unable to find common BPW with spi controller\n"); diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c index 4116c44197b8..2dbaa0b5b3d6 100644 --- a/drivers/iio/adc/adi-axi-adc.c +++ b/drivers/iio/adc/adi-axi-adc.c @@ -445,7 +445,7 @@ static int axi_adc_raw_read(struct iio_backend *back, u32 *val) static int ad7606_bus_reg_read(struct iio_backend *back, u32 reg, u32 *val) { struct adi_axi_adc_state *st = iio_backend_get_priv(back); - int addr; + u32 addr, reg_val; guard(mutex)(&st->lock); @@ -455,7 +455,9 @@ static int ad7606_bus_reg_read(struct iio_backend *back, u32 reg, u32 *val) */ addr = FIELD_PREP(ADI_AXI_REG_ADDRESS_MASK, reg) | ADI_AXI_REG_READ_BIT; axi_adc_raw_write(back, addr); - axi_adc_raw_read(back, val); + axi_adc_raw_read(back, ®_val); + + *val = FIELD_GET(ADI_AXI_REG_VALUE_MASK, reg_val); /* Write 0x0 on the bus to get back to ADC mode */ axi_adc_raw_write(back, 0); diff --git a/drivers/iio/adc/axp20x_adc.c b/drivers/iio/adc/axp20x_adc.c index 71584ffd3632..1b49325ec1ce 100644 --- a/drivers/iio/adc/axp20x_adc.c +++ b/drivers/iio/adc/axp20x_adc.c @@ -187,6 +187,7 @@ static struct iio_map axp717_maps[] = { .consumer_channel = "batt_chrg_i", .adc_channel_label = "batt_chrg_i", }, + { } }; /* diff --git a/drivers/iio/adc/max1363.c b/drivers/iio/adc/max1363.c index a7e9912fb44a..9dd547e62b6c 100644 --- a/drivers/iio/adc/max1363.c +++ b/drivers/iio/adc/max1363.c @@ -511,10 +511,10 @@ static const struct iio_event_spec max1363_events[] = { MAX1363_CHAN_U(1, _s1, 1, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(2, _s2, 2, bits, ev_spec, num_ev_spec), \ MAX1363_CHAN_U(3, _s3, 3, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(0, 1, d0m1, 4, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(2, 3, d2m3, 5, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(1, 0, d1m0, 6, bits, ev_spec, num_ev_spec), \ - MAX1363_CHAN_B(3, 2, d3m2, 7, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, ev_spec, num_ev_spec), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, ev_spec, num_ev_spec), \ IIO_CHAN_SOFT_TIMESTAMP(8) \ } @@ -532,23 +532,23 @@ static const struct iio_chan_spec max1363_channels[] = /* Applies to max1236, max1237 */ static const enum max1363_modes max1236_mode_list[] = { _s0, _s1, _s2, _s3, - s0to1, s0to2, s0to3, + s0to1, s0to2, s2to3, s0to3, d0m1, d2m3, d1m0, d3m2, d0m1to2m3, d1m0to3m2, - s2to3, }; /* Applies to max1238, max1239 */ static const enum max1363_modes max1238_mode_list[] = { _s0, _s1, _s2, _s3, _s4, _s5, _s6, _s7, _s8, _s9, _s10, _s11, s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, + s6to7, s6to8, s6to9, s6to10, s6to11, s0to7, s0to8, s0to9, s0to10, s0to11, d0m1, d2m3, d4m5, d6m7, d8m9, d10m11, d1m0, d3m2, d5m4, d7m6, d9m8, d11m10, - d0m1to2m3, d0m1to4m5, d0m1to6m7, d0m1to8m9, d0m1to10m11, - d1m0to3m2, d1m0to5m4, d1m0to7m6, d1m0to9m8, d1m0to11m10, - s6to7, s6to8, s6to9, s6to10, s6to11, - d6m7to8m9, d6m7to10m11, d7m6to9m8, d7m6to11m10, + d0m1to2m3, d0m1to4m5, d0m1to6m7, d6m7to8m9, + d0m1to8m9, d6m7to10m11, d0m1to10m11, d1m0to3m2, + d1m0to5m4, d1m0to7m6, d7m6to9m8, d1m0to9m8, + d7m6to11m10, d1m0to11m10, }; #define MAX1363_12X_CHANS(bits) { \ @@ -584,16 +584,15 @@ static const struct iio_chan_spec max1238_channels[] = MAX1363_12X_CHANS(12); static const enum max1363_modes max11607_mode_list[] = { _s0, _s1, _s2, _s3, - s0to1, s0to2, s0to3, - s2to3, + s0to1, s0to2, s2to3, + s0to3, d0m1, d2m3, d1m0, d3m2, d0m1to2m3, d1m0to3m2, }; static const enum max1363_modes max11608_mode_list[] = { _s0, _s1, _s2, _s3, _s4, _s5, _s6, _s7, - s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, s0to7, - s6to7, + s0to1, s0to2, s0to3, s0to4, s0to5, s0to6, s6to7, s0to7, d0m1, d2m3, d4m5, d6m7, d1m0, d3m2, d5m4, d7m6, d0m1to2m3, d0m1to4m5, d0m1to6m7, @@ -609,14 +608,14 @@ static const enum max1363_modes max11608_mode_list[] = { MAX1363_CHAN_U(5, _s5, 5, bits, NULL, 0), \ MAX1363_CHAN_U(6, _s6, 6, bits, NULL, 0), \ MAX1363_CHAN_U(7, _s7, 7, bits, NULL, 0), \ - MAX1363_CHAN_B(0, 1, d0m1, 8, bits, NULL, 0), \ - MAX1363_CHAN_B(2, 3, d2m3, 9, bits, NULL, 0), \ - MAX1363_CHAN_B(4, 5, d4m5, 10, bits, NULL, 0), \ - MAX1363_CHAN_B(6, 7, d6m7, 11, bits, NULL, 0), \ - MAX1363_CHAN_B(1, 0, d1m0, 12, bits, NULL, 0), \ - MAX1363_CHAN_B(3, 2, d3m2, 13, bits, NULL, 0), \ - MAX1363_CHAN_B(5, 4, d5m4, 14, bits, NULL, 0), \ - MAX1363_CHAN_B(7, 6, d7m6, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(0, 1, d0m1, 12, bits, NULL, 0), \ + MAX1363_CHAN_B(2, 3, d2m3, 13, bits, NULL, 0), \ + MAX1363_CHAN_B(4, 5, d4m5, 14, bits, NULL, 0), \ + MAX1363_CHAN_B(6, 7, d6m7, 15, bits, NULL, 0), \ + MAX1363_CHAN_B(1, 0, d1m0, 18, bits, NULL, 0), \ + MAX1363_CHAN_B(3, 2, d3m2, 19, bits, NULL, 0), \ + MAX1363_CHAN_B(5, 4, d5m4, 20, bits, NULL, 0), \ + MAX1363_CHAN_B(7, 6, d7m6, 21, bits, NULL, 0), \ IIO_CHAN_SOFT_TIMESTAMP(16) \ } static const struct iio_chan_spec max11602_channels[] = MAX1363_8X_CHANS(8); diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index bd3458965bff..21c04a98b3b6 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -430,10 +430,9 @@ static int stm32_adc_irq_probe(struct platform_device *pdev, return -ENOMEM; } - for (i = 0; i < priv->cfg->num_irqs; i++) { - irq_set_chained_handler(priv->irq[i], stm32_adc_irq_handler); - irq_set_handler_data(priv->irq[i], priv); - } + for (i = 0; i < priv->cfg->num_irqs; i++) + irq_set_chained_handler_and_data(priv->irq[i], + stm32_adc_irq_handler, priv); return 0; } diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 8ce1dccfea4f..dac593be5695 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -154,7 +154,7 @@ static int st_sensors_set_fullscale(struct iio_dev *indio_dev, unsigned int fs) return err; st_accel_set_fullscale_error: - dev_err(&indio_dev->dev, "failed to set new fullscale.\n"); + dev_err(indio_dev->dev.parent, "failed to set new fullscale.\n"); return err; } @@ -231,8 +231,7 @@ int st_sensors_power_enable(struct iio_dev *indio_dev) ARRAY_SIZE(regulator_names), regulator_names); if (err) - return dev_err_probe(&indio_dev->dev, err, - "unable to enable supplies\n"); + return dev_err_probe(parent, err, "unable to enable supplies\n"); return 0; } @@ -241,13 +240,14 @@ EXPORT_SYMBOL_NS(st_sensors_power_enable, "IIO_ST_SENSORS"); static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev, struct st_sensors_platform_data *pdata) { + struct device *parent = indio_dev->dev.parent; struct st_sensor_data *sdata = iio_priv(indio_dev); /* Sensor does not support interrupts */ if (!sdata->sensor_settings->drdy_irq.int1.addr && !sdata->sensor_settings->drdy_irq.int2.addr) { if (pdata->drdy_int_pin) - dev_info(&indio_dev->dev, + dev_info(parent, "DRDY on pin INT%d specified, but sensor does not support interrupts\n", pdata->drdy_int_pin); return 0; @@ -256,29 +256,27 @@ static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev, switch (pdata->drdy_int_pin) { case 1: if (!sdata->sensor_settings->drdy_irq.int1.mask) { - dev_err(&indio_dev->dev, - "DRDY on INT1 not available.\n"); + dev_err(parent, "DRDY on INT1 not available.\n"); return -EINVAL; } sdata->drdy_int_pin = 1; break; case 2: if (!sdata->sensor_settings->drdy_irq.int2.mask) { - dev_err(&indio_dev->dev, - "DRDY on INT2 not available.\n"); + dev_err(parent, "DRDY on INT2 not available.\n"); return -EINVAL; } sdata->drdy_int_pin = 2; break; default: - dev_err(&indio_dev->dev, "DRDY on pdata not valid.\n"); + dev_err(parent, "DRDY on pdata not valid.\n"); return -EINVAL; } if (pdata->open_drain) { if (!sdata->sensor_settings->drdy_irq.int1.addr_od && !sdata->sensor_settings->drdy_irq.int2.addr_od) - dev_err(&indio_dev->dev, + dev_err(parent, "open drain requested but unsupported.\n"); else sdata->int_pin_open_drain = true; @@ -336,6 +334,7 @@ EXPORT_SYMBOL_NS(st_sensors_dev_name_probe, "IIO_ST_SENSORS"); int st_sensors_init_sensor(struct iio_dev *indio_dev, struct st_sensors_platform_data *pdata) { + struct device *parent = indio_dev->dev.parent; struct st_sensor_data *sdata = iio_priv(indio_dev); struct st_sensors_platform_data *of_pdata; int err = 0; @@ -343,7 +342,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, mutex_init(&sdata->odr_lock); /* If OF/DT pdata exists, it will take precedence of anything else */ - of_pdata = st_sensors_dev_probe(indio_dev->dev.parent, pdata); + of_pdata = st_sensors_dev_probe(parent, pdata); if (IS_ERR(of_pdata)) return PTR_ERR(of_pdata); if (of_pdata) @@ -370,7 +369,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, if (err < 0) return err; } else - dev_info(&indio_dev->dev, "Full-scale not possible\n"); + dev_info(parent, "Full-scale not possible\n"); err = st_sensors_set_odr(indio_dev, sdata->odr); if (err < 0) @@ -405,7 +404,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, mask = sdata->sensor_settings->drdy_irq.int2.mask_od; } - dev_info(&indio_dev->dev, + dev_info(parent, "set interrupt line to open drain mode on pin %d\n", sdata->drdy_int_pin); err = st_sensors_write_data_with_mask(indio_dev, addr, @@ -593,21 +592,20 @@ EXPORT_SYMBOL_NS(st_sensors_get_settings_index, "IIO_ST_SENSORS"); int st_sensors_verify_id(struct iio_dev *indio_dev) { struct st_sensor_data *sdata = iio_priv(indio_dev); + struct device *parent = indio_dev->dev.parent; int wai, err; if (sdata->sensor_settings->wai_addr) { err = regmap_read(sdata->regmap, sdata->sensor_settings->wai_addr, &wai); if (err < 0) { - dev_err(&indio_dev->dev, - "failed to read Who-Am-I register.\n"); - return err; + return dev_err_probe(parent, err, + "failed to read Who-Am-I register.\n"); } if (sdata->sensor_settings->wai != wai) { - dev_warn(&indio_dev->dev, - "%s: WhoAmI mismatch (0x%x).\n", - indio_dev->name, wai); + dev_warn(parent, "%s: WhoAmI mismatch (0x%x).\n", + indio_dev->name, wai); } } diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 9d4bf822a15d..8a8ab688d798 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -127,7 +127,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->trig = devm_iio_trigger_alloc(parent, "%s-trigger", indio_dev->name); if (sdata->trig == NULL) { - dev_err(&indio_dev->dev, "failed to allocate iio trigger.\n"); + dev_err(parent, "failed to allocate iio trigger.\n"); return -ENOMEM; } @@ -143,7 +143,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, case IRQF_TRIGGER_FALLING: case IRQF_TRIGGER_LOW: if (!sdata->sensor_settings->drdy_irq.addr_ihl) { - dev_err(&indio_dev->dev, + dev_err(parent, "falling/low specified for IRQ but hardware supports only rising/high: will request rising/high\n"); if (irq_trig == IRQF_TRIGGER_FALLING) irq_trig = IRQF_TRIGGER_RISING; @@ -156,21 +156,19 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.mask_ihl, 1); if (err < 0) return err; - dev_info(&indio_dev->dev, + dev_info(parent, "interrupts on the falling edge or active low level\n"); } break; case IRQF_TRIGGER_RISING: - dev_info(&indio_dev->dev, - "interrupts on the rising edge\n"); + dev_info(parent, "interrupts on the rising edge\n"); break; case IRQF_TRIGGER_HIGH: - dev_info(&indio_dev->dev, - "interrupts active high level\n"); + dev_info(parent, "interrupts active high level\n"); break; default: /* This is the most preferred mode, if possible */ - dev_err(&indio_dev->dev, + dev_err(parent, "unsupported IRQ trigger specified (%lx), enforce rising edge\n", irq_trig); irq_trig = IRQF_TRIGGER_RISING; } @@ -179,7 +177,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, if (irq_trig == IRQF_TRIGGER_FALLING || irq_trig == IRQF_TRIGGER_RISING) { if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) { - dev_err(&indio_dev->dev, + dev_err(parent, "edge IRQ not supported w/o stat register.\n"); return -EOPNOTSUPP; } @@ -214,13 +212,13 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->trig->name, sdata->trig); if (err) { - dev_err(&indio_dev->dev, "failed to request trigger IRQ.\n"); + dev_err(parent, "failed to request trigger IRQ.\n"); return err; } err = devm_iio_trigger_register(parent, sdata->trig); if (err < 0) { - dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); + dev_err(parent, "failed to register iio trigger.\n"); return err; } indio_dev->trig = iio_trigger_get(sdata->trig); diff --git a/drivers/iio/dac/ad3530r.c b/drivers/iio/dac/ad3530r.c index f9752a571aa5..6134613777b8 100644 --- a/drivers/iio/dac/ad3530r.c +++ b/drivers/iio/dac/ad3530r.c @@ -166,7 +166,9 @@ static ssize_t ad3530r_set_dac_powerdown(struct iio_dev *indio_dev, AD3530R_OUTPUT_OPERATING_MODE_0 : AD3530R_OUTPUT_OPERATING_MODE_1; pdmode = powerdown ? st->chan[chan->channel].powerdown_mode : 0; - mask = AD3530R_OP_MODE_CHAN_MSK(chan->channel); + mask = chan->channel < AD3531R_MAX_CHANNELS ? + AD3530R_OP_MODE_CHAN_MSK(chan->channel) : + AD3530R_OP_MODE_CHAN_MSK(chan->channel - 4); val = field_prep(mask, pdmode); ret = regmap_update_bits(st->regmap, reg, mask, val); diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c index c1eb9ef9db08..266e1b29bf91 100644 --- a/drivers/iio/industrialio-backend.c +++ b/drivers/iio/industrialio-backend.c @@ -155,11 +155,14 @@ static ssize_t iio_backend_debugfs_write_reg(struct file *file, ssize_t rc; int ret; + if (count >= sizeof(buf)) + return -ENOSPC; + rc = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, userbuf, count); if (rc < 0) return rc; - buf[count] = '\0'; + buf[rc] = '\0'; ret = sscanf(buf, "%i %i", &back->cached_reg_addr, &val); diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 178e99b111de..5ffda104d4b2 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -411,12 +411,15 @@ static ssize_t iio_debugfs_write_reg(struct file *file, char buf[80]; int ret; + if (count >= sizeof(buf)) + return -EINVAL; + ret = simple_write_to_buffer(buf, sizeof(buf) - 1, ppos, userbuf, count); if (ret < 0) return ret; - buf[count] = '\0'; + buf[ret] = '\0'; ret = sscanf(buf, "%i %i", ®, &val); diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c index 2331e698a65b..4f86b56fee26 100644 --- a/drivers/infiniband/sw/rxe/rxe_verbs.c +++ b/drivers/infiniband/sw/rxe/rxe_verbs.c @@ -65,7 +65,7 @@ static int rxe_query_port(struct ib_device *ibdev, attr->state = ib_get_curr_port_state(ndev); if (attr->state == IB_PORT_ACTIVE) attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP; - else if (dev_get_flags(ndev) & IFF_UP) + else if (netif_get_flags(ndev) & IFF_UP) attr->phys_state = IB_PORT_PHYS_STATE_POLLING; else attr->phys_state = IB_PORT_PHYS_STATE_DISABLED; diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 5d9b7007a730..1d8c579b5433 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -172,12 +172,12 @@ static const struct xpad_device { { 0x046d, 0xca88, "Logitech Compact Controller for Xbox", 0, XTYPE_XBOX }, { 0x046d, 0xca8a, "Logitech Precision Vibration Feedback Wheel", 0, XTYPE_XBOX }, { 0x046d, 0xcaa3, "Logitech DriveFx Racing Wheel", 0, XTYPE_XBOX360 }, + { 0x0502, 0x1305, "Acer NGR200", 0, XTYPE_XBOX360 }, { 0x056e, 0x2004, "Elecom JC-U3613M", 0, XTYPE_XBOX360 }, { 0x05fd, 0x1007, "Mad Catz Controller (unverified)", 0, XTYPE_XBOX }, { 0x05fd, 0x107a, "InterAct 'PowerPad Pro' X-Box pad (Germany)", 0, XTYPE_XBOX }, { 0x05fe, 0x3030, "Chic Controller", 0, XTYPE_XBOX }, { 0x05fe, 0x3031, "Chic Controller", 0, XTYPE_XBOX }, - { 0x0502, 0x1305, "Acer NGR200", 0, XTYPE_XBOX }, { 0x062a, 0x0020, "Logic3 Xbox GamePad", 0, XTYPE_XBOX }, { 0x062a, 0x0033, "Competition Pro Steering Wheel", 0, XTYPE_XBOX }, { 0x06a3, 0x0200, "Saitek Racing Wheel", 0, XTYPE_XBOX }, diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 1a41e59c77f8..3ebf37ddfc18 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -20,7 +20,7 @@ #include "internal.h" -#define ICC_DYN_ID_START 10000 +#define ICC_DYN_ID_START 100000 #define CREATE_TRACE_POINTS #include "trace.h" @@ -819,6 +819,9 @@ static struct icc_node *icc_node_create_nolock(int id) { struct icc_node *node; + if (id >= ICC_DYN_ID_START) + return ERR_PTR(-EINVAL); + /* check if node already exists */ node = node_find(id); if (node) @@ -906,11 +909,36 @@ void icc_node_destroy(int id) return; kfree(node->links); + if (node->id >= ICC_DYN_ID_START) + kfree(node->name); kfree(node); } EXPORT_SYMBOL_GPL(icc_node_destroy); /** + * icc_node_set_name() - set node name + * @node: node + * @provider: node provider + * @name: node name + * + * Return: 0 on success, or -ENOMEM on allocation failure + */ +int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name) +{ + if (node->id >= ICC_DYN_ID_START) { + node->name = kasprintf(GFP_KERNEL, "%s@%s", name, + dev_name(provider->dev)); + if (!node->name) + return -ENOMEM; + } else { + node->name = name; + } + + return 0; +} +EXPORT_SYMBOL_GPL(icc_node_set_name); + +/** * icc_link_nodes() - create link between two nodes * @src_node: source node * @dst_node: destination node @@ -1038,10 +1066,6 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider) node->avg_bw = node->init_avg; node->peak_bw = node->init_peak; - if (node->id >= ICC_DYN_ID_START) - node->name = devm_kasprintf(provider->dev, GFP_KERNEL, "%s@%s", - node->name, dev_name(provider->dev)); - if (node->avg_bw || node->peak_bw) { if (provider->pre_aggregate) provider->pre_aggregate(node); diff --git a/drivers/interconnect/icc-clk.c b/drivers/interconnect/icc-clk.c index 88f311c11020..93c030608d3e 100644 --- a/drivers/interconnect/icc-clk.c +++ b/drivers/interconnect/icc-clk.c @@ -117,6 +117,7 @@ struct icc_provider *icc_clk_register(struct device *dev, node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_master", data[i].name); if (!node->name) { + icc_node_destroy(node->id); ret = -ENOMEM; goto err; } @@ -135,6 +136,7 @@ struct icc_provider *icc_clk_register(struct device *dev, node->name = devm_kasprintf(dev, GFP_KERNEL, "%s_slave", data[i].name); if (!node->name) { + icc_node_destroy(node->id); ret = -ENOMEM; goto err; } diff --git a/drivers/interconnect/qcom/icc-rpmh.c b/drivers/interconnect/qcom/icc-rpmh.c index 41bfc6e7ee1d..001404e91041 100644 --- a/drivers/interconnect/qcom/icc-rpmh.c +++ b/drivers/interconnect/qcom/icc-rpmh.c @@ -293,7 +293,12 @@ int qcom_icc_rpmh_probe(struct platform_device *pdev) goto err_remove_nodes; } - node->name = qn->name; + ret = icc_node_set_name(node, provider, qn->name); + if (ret) { + icc_node_destroy(node->id); + goto err_remove_nodes; + } + node->data = qn; icc_node_add(node, provider); diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index baecbf2533f7..b33f00da1880 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -236,7 +236,12 @@ static int qcom_osm_l3_probe(struct platform_device *pdev) goto err; } - node->name = qnodes[i]->name; + ret = icc_node_set_name(node, provider, qnodes[i]->name); + if (ret) { + icc_node_destroy(node->id); + goto err; + } + /* Cast away const and add it back in qcom_osm_l3_set() */ node->data = (void *)qnodes[i]; icc_node_add(node, provider); diff --git a/drivers/interconnect/qcom/sc7280.c b/drivers/interconnect/qcom/sc7280.c index 346f18d70e9e..905403a3a930 100644 --- a/drivers/interconnect/qcom/sc7280.c +++ b/drivers/interconnect/qcom/sc7280.c @@ -238,6 +238,7 @@ static struct qcom_icc_node xm_pcie3_1 = { .id = SC7280_MASTER_PCIE_1, .channels = 1, .buswidth = 8, + .num_links = 1, .links = { SC7280_SLAVE_ANOC_PCIE_GEM_NOC }, }; diff --git a/drivers/interconnect/samsung/exynos.c b/drivers/interconnect/samsung/exynos.c index 9e041365d909..8e8f56186a36 100644 --- a/drivers/interconnect/samsung/exynos.c +++ b/drivers/interconnect/samsung/exynos.c @@ -134,6 +134,11 @@ static int exynos_generic_icc_probe(struct platform_device *pdev) priv->node = icc_node; icc_node->name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%pOFn", bus_dev->of_node); + if (!icc_node->name) { + icc_node_destroy(pdev->id); + return -ENOMEM; + } + if (of_property_read_u32(bus_dev->of_node, "samsung,data-clock-ratio", &priv->bus_clk_ratio)) priv->bus_clk_ratio = EXYNOS_ICC_DEFAULT_BUS_CLK_RATIO; diff --git a/drivers/iommu/hyperv-iommu.c b/drivers/iommu/hyperv-iommu.c index 761ab647f372..0961ac805944 100644 --- a/drivers/iommu/hyperv-iommu.c +++ b/drivers/iommu/hyperv-iommu.c @@ -193,15 +193,13 @@ struct hyperv_root_ir_data { static void hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) { - u64 status; - u32 vector; - struct irq_cfg *cfg; - int ioapic_id; - const struct cpumask *affinity; - int cpu; - struct hv_interrupt_entry entry; struct hyperv_root_ir_data *data = irq_data->chip_data; + struct hv_interrupt_entry entry; + const struct cpumask *affinity; struct IO_APIC_route_entry e; + struct irq_cfg *cfg; + int cpu, ioapic_id; + u32 vector; cfg = irqd_cfg(irq_data); affinity = irq_data_get_effective_affinity_mask(irq_data); @@ -214,23 +212,16 @@ hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg) && data->entry.ioapic_rte.as_uint64) { entry = data->entry; - status = hv_unmap_ioapic_interrupt(ioapic_id, &entry); - - if (status != HV_STATUS_SUCCESS) - hv_status_debug(status, "failed to unmap\n"); + (void)hv_unmap_ioapic_interrupt(ioapic_id, &entry); data->entry.ioapic_rte.as_uint64 = 0; data->entry.source = 0; /* Invalid source */ } - status = hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu, - vector, &entry); - - if (status != HV_STATUS_SUCCESS) { - hv_status_err(status, "map failed\n"); + if (hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu, + vector, &entry)) return; - } data->entry = entry; @@ -322,10 +313,10 @@ static void hyperv_root_irq_remapping_free(struct irq_domain *domain, data = irq_data->chip_data; e = &data->entry; - if (e->source == HV_DEVICE_TYPE_IOAPIC - && e->ioapic_rte.as_uint64) - hv_unmap_ioapic_interrupt(data->ioapic_id, - &data->entry); + if (e->source == HV_DEVICE_TYPE_IOAPIC && + e->ioapic_rte.as_uint64) + (void)hv_unmap_ioapic_interrupt(data->ioapic_id, + &data->entry); kfree(data); } diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 043b9ec756ff..7f3f47db4c98 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -324,7 +324,7 @@ EXPORT_SYMBOL(memstick_init_req); static int h_memstick_read_dev_id(struct memstick_dev *card, struct memstick_request **mrq) { - struct ms_id_register id_reg; + struct ms_id_register id_reg = {}; if (!(*mrq)) { memstick_init_req(&card->current_mrq, MS_TPC_READ_REG, &id_reg, diff --git a/drivers/misc/amd-sbi/rmi-core.c b/drivers/misc/amd-sbi/rmi-core.c index b653a21a909e..3dec2fc00124 100644 --- a/drivers/misc/amd-sbi/rmi-core.c +++ b/drivers/misc/amd-sbi/rmi-core.c @@ -42,7 +42,6 @@ #define RD_MCA_CMD 0x86 /* CPUID MCAMSR mask & index */ -#define CPUID_MCA_THRD_MASK GENMASK(15, 0) #define CPUID_MCA_THRD_INDEX 32 #define CPUID_MCA_FUNC_MASK GENMASK(31, 0) #define CPUID_EXT_FUNC_INDEX 56 @@ -129,7 +128,7 @@ static int rmi_cpuid_read(struct sbrmi_data *data, goto exit_unlock; } - thread = msg->cpu_in_out << CPUID_MCA_THRD_INDEX & CPUID_MCA_THRD_MASK; + thread = msg->cpu_in_out >> CPUID_MCA_THRD_INDEX; /* Thread > 127, Thread128 CS register, 1'b1 needs to be set to 1 */ if (thread > 127) { @@ -210,7 +209,7 @@ static int rmi_mca_msr_read(struct sbrmi_data *data, goto exit_unlock; } - thread = msg->mcamsr_in_out << CPUID_MCA_THRD_INDEX & CPUID_MCA_THRD_MASK; + thread = msg->mcamsr_in_out >> CPUID_MCA_THRD_INDEX; /* Thread > 127, Thread128 CS register, 1'b1 needs to be set to 1 */ if (thread > 127) { @@ -321,6 +320,10 @@ int rmi_mailbox_xfer(struct sbrmi_data *data, ret = regmap_read(data->regmap, SBRMI_OUTBNDMSG7, &ec); if (ret || ec) goto exit_clear_alert; + + /* Clear the input value before updating the output data */ + msg->mb_in_out = 0; + /* * For a read operation, the initiator (BMC) reads the firmware * response Command Data Out[31:0] from SBRMI::OutBndMsg_inst[4:1] @@ -373,7 +376,8 @@ static int apml_rmi_reg_xfer(struct sbrmi_data *data, mutex_unlock(&data->lock); if (msg.rflag && !ret) - return copy_to_user(arg, &msg, sizeof(struct apml_reg_xfer_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_reg_xfer_msg))) + return -EFAULT; return ret; } @@ -391,7 +395,9 @@ static int apml_mailbox_xfer(struct sbrmi_data *data, struct apml_mbox_msg __use if (ret && ret != -EPROTOTYPE) return ret; - return copy_to_user(arg, &msg, sizeof(struct apml_mbox_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_mbox_msg))) + return -EFAULT; + return ret; } static int apml_cpuid_xfer(struct sbrmi_data *data, struct apml_cpuid_msg __user *arg) @@ -408,7 +414,9 @@ static int apml_cpuid_xfer(struct sbrmi_data *data, struct apml_cpuid_msg __user if (ret && ret != -EPROTOTYPE) return ret; - return copy_to_user(arg, &msg, sizeof(struct apml_cpuid_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_cpuid_msg))) + return -EFAULT; + return ret; } static int apml_mcamsr_xfer(struct sbrmi_data *data, struct apml_mcamsr_msg __user *arg) @@ -425,7 +433,9 @@ static int apml_mcamsr_xfer(struct sbrmi_data *data, struct apml_mcamsr_msg __us if (ret && ret != -EPROTOTYPE) return ret; - return copy_to_user(arg, &msg, sizeof(struct apml_mcamsr_msg)); + if (copy_to_user(arg, &msg, sizeof(struct apml_mcamsr_msg))) + return -EFAULT; + return ret; } static long sbrmi_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index def054ddd256..4fced9b36c80 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -503,7 +503,8 @@ void bcm2835_prepare_dma(struct bcm2835_host *host, struct mmc_data *data) DMA_PREP_INTERRUPT | DMA_CTRL_ACK); if (!desc) { - dma_unmap_sg(dma_chan->device->dev, data->sg, sg_len, dir_data); + dma_unmap_sg(dma_chan->device->dev, data->sg, data->sg_len, + dir_data); return; } diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 13a84b9309e0..e3877a1c72a9 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -913,7 +913,8 @@ static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) { return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_EMMC && (dmi_match(DMI_BIOS_VENDOR, "LENOVO") || - dmi_match(DMI_SYS_VENDOR, "IRBIS")); + dmi_match(DMI_SYS_VENDOR, "IRBIS") || + dmi_match(DMI_SYS_VENDOR, "Positivo Tecnologia SA")); } static bool jsl_broken_hs400es(struct sdhci_pci_slot *slot) diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index 73385ff4c0f3..9e94998e8df7 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -613,7 +613,8 @@ static const struct sdhci_ops sdhci_am654_ops = { static const struct sdhci_pltfm_data sdhci_am654_pdata = { .ops = &sdhci_am654_ops, .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, - .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_DISABLE_HW_TIMEOUT, }; static const struct sdhci_am654_driver_data sdhci_am654_sr1_drvdata = { @@ -643,7 +644,8 @@ static const struct sdhci_ops sdhci_j721e_8bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = { .ops = &sdhci_j721e_8bit_ops, .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, - .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_DISABLE_HW_TIMEOUT, }; static const struct sdhci_am654_driver_data sdhci_j721e_8bit_drvdata = { @@ -667,7 +669,8 @@ static const struct sdhci_ops sdhci_j721e_4bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = { .ops = &sdhci_j721e_4bit_ops, .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, - .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, + .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | + SDHCI_QUIRK2_DISABLE_HW_TIMEOUT, }; static const struct sdhci_am654_driver_data sdhci_j721e_4bit_drvdata = { diff --git a/drivers/mux/Kconfig b/drivers/mux/Kconfig index 80f015cf6e54..c68132e38138 100644 --- a/drivers/mux/Kconfig +++ b/drivers/mux/Kconfig @@ -48,6 +48,7 @@ config MUX_GPIO config MUX_MMIO tristate "MMIO/Regmap register bitfield-controlled Multiplexer" depends on OF + select REGMAP_MMIO help MMIO/Regmap register bitfield-controlled Multiplexer controller. diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 17c7542be6a5..257333c88710 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1040,7 +1040,7 @@ static int bond_set_dev_addr(struct net_device *bond_dev, slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", bond_dev, slave_dev, slave_dev->addr_len); - err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); + err = netif_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); if (err) return err; @@ -2669,7 +2669,7 @@ static int __bond_release_one(struct net_device *bond_dev, if (unregister) { netdev_lock_ops(slave_dev); - __dev_set_mtu(slave_dev, slave->original_mtu); + __netif_set_mtu(slave_dev, slave->original_mtu); netdev_unlock_ops(slave_dev); } else { dev_set_mtu(slave_dev, slave->original_mtu); @@ -6743,3 +6743,4 @@ module_exit(bonding_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index ea8c807af4d8..3913971125de 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -145,13 +145,16 @@ void can_change_state(struct net_device *dev, struct can_frame *cf, EXPORT_SYMBOL_GPL(can_change_state); /* CAN device restart for bus-off recovery */ -static void can_restart(struct net_device *dev) +static int can_restart(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); struct sk_buff *skb; struct can_frame *cf; int err; + if (!priv->do_set_mode) + return -EOPNOTSUPP; + if (netif_carrier_ok(dev)) netdev_err(dev, "Attempt to restart for bus-off recovery, but carrier is OK?\n"); @@ -173,10 +176,14 @@ static void can_restart(struct net_device *dev) if (err) { netdev_err(dev, "Restart failed, error %pe\n", ERR_PTR(err)); netif_carrier_off(dev); + + return err; } else { netdev_dbg(dev, "Restarted\n"); priv->can_stats.restarts++; } + + return 0; } static void can_restart_work(struct work_struct *work) @@ -201,9 +208,8 @@ int can_restart_now(struct net_device *dev) return -EBUSY; cancel_delayed_work_sync(&priv->restart_work); - can_restart(dev); - return 0; + return can_restart(dev); } /* CAN bus-off diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 13826e8a707b..d9f6ab3efb97 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -285,6 +285,12 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_CAN_RESTART_MS]) { + if (!priv->do_set_mode) { + NL_SET_ERR_MSG(extack, + "Device doesn't support restart from Bus Off"); + return -EOPNOTSUPP; + } + /* Do not allow changing restart delay while running */ if (dev->flags & IFF_UP) return -EBUSY; @@ -292,6 +298,12 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_CAN_RESTART]) { + if (!priv->do_set_mode) { + NL_SET_ERR_MSG(extack, + "Device doesn't support restart from Bus Off"); + return -EOPNOTSUPP; + } + /* Do not allow a restart while not running */ if (!(dev->flags & IFF_UP)) return -EINVAL; diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 678eddb36172..5c8217638dda 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2459,6 +2459,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) skb->data, skb_headlen(skb), DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + dma_addr)) + return -ENOMEM; + desc[frag].addr_lo = lower_32_bits(dma_addr); desc[frag].addr_hi = upper_32_bits(dma_addr); frag++; @@ -2468,6 +2472,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) skb->data, skb_headlen(skb) / 2, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + dma_addr)) + return -ENOMEM; + desc[frag].addr_lo = lower_32_bits(dma_addr); desc[frag].addr_hi = upper_32_bits(dma_addr); frag++; @@ -2478,6 +2486,10 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) skb_headlen(skb) / 2, skb_headlen(skb) / 2, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + dma_addr)) + goto unmap_first_out; + desc[frag].addr_lo = lower_32_bits(dma_addr); desc[frag].addr_hi = upper_32_bits(dma_addr); frag++; @@ -2489,6 +2501,9 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) 0, desc[frag].len_vlan, DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, dma_addr)) + goto unmap_out; + desc[frag].addr_lo = lower_32_bits(dma_addr); desc[frag].addr_hi = upper_32_bits(dma_addr); frag++; @@ -2578,6 +2593,27 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) &adapter->regs->global.watchdog_timer); } return 0; + +unmap_out: + // Unmap the body of the packet with map_page + while (--i) { + frag--; + dma_addr = desc[frag].addr_lo; + dma_addr |= (u64)desc[frag].addr_hi << 32; + dma_unmap_page(&adapter->pdev->dev, dma_addr, + desc[frag].len_vlan, DMA_TO_DEVICE); + } + +unmap_first_out: + // Unmap the header with map_single + while (frag--) { + dma_addr = desc[frag].addr_lo; + dma_addr |= (u64)desc[frag].addr_hi << 32; + dma_unmap_single(&adapter->pdev->dev, dma_addr, + desc[frag].len_vlan, DMA_TO_DEVICE); + } + + return -ENOMEM; } static int send_packet(struct sk_buff *skb, struct et131x_adapter *adapter) diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c index bda3c93e8261..9ab964c536e1 100644 --- a/drivers/net/ethernet/airoha/airoha_npu.c +++ b/drivers/net/ethernet/airoha/airoha_npu.c @@ -179,8 +179,8 @@ static int airoha_npu_run_firmware(struct device *dev, void __iomem *base, } addr = devm_ioremap_resource(dev, res); - if (!addr) { - ret = -ENOMEM; + if (IS_ERR(addr)) { + ret = PTR_ERR(addr); goto out; } diff --git a/drivers/net/ethernet/amd/xgbe/Makefile b/drivers/net/ethernet/amd/xgbe/Makefile index 620785ffbd51..5b0ab6240cf2 100644 --- a/drivers/net/ethernet/amd/xgbe/Makefile +++ b/drivers/net/ethernet/amd/xgbe/Makefile @@ -3,7 +3,7 @@ obj-$(CONFIG_AMD_XGBE) += amd-xgbe.o amd-xgbe-objs := xgbe-main.o xgbe-drv.o xgbe-dev.o \ xgbe-desc.o xgbe-ethtool.o xgbe-mdio.o \ - xgbe-ptp.o \ + xgbe-hwtstamp.o xgbe-ptp.o \ xgbe-i2c.o xgbe-phy-v1.o xgbe-phy-v2.o \ xgbe-platform.o diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index e54e3e36d3f9..009fbc9b11ce 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -223,6 +223,10 @@ #define MAC_TSSR 0x0d20 #define MAC_TXSNR 0x0d30 #define MAC_TXSSR 0x0d34 +#define MAC_TICNR 0x0d58 +#define MAC_TICSNR 0x0d5C +#define MAC_TECNR 0x0d60 +#define MAC_TECSNR 0x0d64 #define MAC_QTFCR_INC 4 #define MAC_MACA_INC 4 @@ -428,6 +432,8 @@ #define MAC_TSCR_SNAPTYPSEL_WIDTH 2 #define MAC_TSCR_TSADDREG_INDEX 5 #define MAC_TSCR_TSADDREG_WIDTH 1 +#define MAC_TSCR_TSUPDT_INDEX 3 +#define MAC_TSCR_TSUPDT_WIDTH 1 #define MAC_TSCR_TSCFUPDT_INDEX 1 #define MAC_TSCR_TSCFUPDT_WIDTH 1 #define MAC_TSCR_TSCTRLSSR_INDEX 9 @@ -456,6 +462,10 @@ #define MAC_TSSR_TXTSC_WIDTH 1 #define MAC_TXSNR_TXTSSTSMIS_INDEX 31 #define MAC_TXSNR_TXTSSTSMIS_WIDTH 1 +#define MAC_TICSNR_TSICSNS_INDEX 8 +#define MAC_TICSNR_TSICSNS_WIDTH 8 +#define MAC_TECSNR_TSECSNS_INDEX 8 +#define MAC_TECSNR_TSECSNS_WIDTH 8 #define MAC_VLANHTR_VLHT_INDEX 0 #define MAC_VLANHTR_VLHT_WIDTH 16 #define MAC_VLANIR_VLTI_INDEX 20 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 9e4e79bfe624..e5391a2eca51 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1558,125 +1558,6 @@ static void xgbe_rx_desc_init(struct xgbe_channel *channel) DBGPR("<--rx_desc_init\n"); } -static void xgbe_update_tstamp_addend(struct xgbe_prv_data *pdata, - unsigned int addend) -{ - unsigned int count = 10000; - - /* Set the addend register value and tell the device */ - XGMAC_IOWRITE(pdata, MAC_TSAR, addend); - XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSADDREG, 1); - - /* Wait for addend update to complete */ - while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSADDREG)) - udelay(5); - - if (!count) - netdev_err(pdata->netdev, - "timed out updating timestamp addend register\n"); -} - -static void xgbe_set_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec, - unsigned int nsec) -{ - unsigned int count = 10000; - - /* Set the time values and tell the device */ - XGMAC_IOWRITE(pdata, MAC_STSUR, sec); - XGMAC_IOWRITE(pdata, MAC_STNUR, nsec); - XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSINIT, 1); - - /* Wait for time update to complete */ - while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSINIT)) - udelay(5); - - if (!count) - netdev_err(pdata->netdev, "timed out initializing timestamp\n"); -} - -static u64 xgbe_get_tstamp_time(struct xgbe_prv_data *pdata) -{ - u64 nsec; - - nsec = XGMAC_IOREAD(pdata, MAC_STSR); - nsec *= NSEC_PER_SEC; - nsec += XGMAC_IOREAD(pdata, MAC_STNR); - - return nsec; -} - -static u64 xgbe_get_tx_tstamp(struct xgbe_prv_data *pdata) -{ - unsigned int tx_snr, tx_ssr; - u64 nsec; - - if (pdata->vdata->tx_tstamp_workaround) { - tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR); - tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR); - } else { - tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR); - tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR); - } - - if (XGMAC_GET_BITS(tx_snr, MAC_TXSNR, TXTSSTSMIS)) - return 0; - - nsec = tx_ssr; - nsec *= NSEC_PER_SEC; - nsec += tx_snr; - - return nsec; -} - -static void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet, - struct xgbe_ring_desc *rdesc) -{ - u64 nsec; - - if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSA) && - !XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSD)) { - nsec = le32_to_cpu(rdesc->desc1); - nsec <<= 32; - nsec |= le32_to_cpu(rdesc->desc0); - if (nsec != 0xffffffffffffffffULL) { - packet->rx_tstamp = nsec; - XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, - RX_TSTAMP, 1); - } - } -} - -static int xgbe_config_tstamp(struct xgbe_prv_data *pdata, - unsigned int mac_tscr) -{ - /* Set one nano-second accuracy */ - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCTRLSSR, 1); - - /* Set fine timestamp update */ - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCFUPDT, 1); - - /* Overwrite earlier timestamps */ - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TXTSSTSM, 1); - - XGMAC_IOWRITE(pdata, MAC_TSCR, mac_tscr); - - /* Exit if timestamping is not enabled */ - if (!XGMAC_GET_BITS(mac_tscr, MAC_TSCR, TSENA)) - return 0; - - /* Initialize time registers */ - XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SSINC, XGBE_TSTAMP_SSINC); - XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SNSINC, XGBE_TSTAMP_SNSINC); - xgbe_update_tstamp_addend(pdata, pdata->tstamp_addend); - xgbe_set_tstamp_time(pdata, 0, 0); - - /* Initialize the timecounter */ - timecounter_init(&pdata->tstamp_tc, &pdata->tstamp_cc, - ktime_to_ns(ktime_get_real())); - - return 0; -} - static void xgbe_tx_start_xmit(struct xgbe_channel *channel, struct xgbe_ring *ring) { @@ -3671,13 +3552,6 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if) hw_if->rx_mmc_int = xgbe_rx_mmc_int; hw_if->read_mmc_stats = xgbe_read_mmc_stats; - /* For PTP config */ - hw_if->config_tstamp = xgbe_config_tstamp; - hw_if->update_tstamp_addend = xgbe_update_tstamp_addend; - hw_if->set_tstamp_time = xgbe_set_tstamp_time; - hw_if->get_tstamp_time = xgbe_get_tstamp_time; - hw_if->get_tx_tstamp = xgbe_get_tx_tstamp; - /* For Data Center Bridging config */ hw_if->config_tc = xgbe_config_tc; hw_if->config_dcb_tc = xgbe_config_dcb_tc; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 65447f9a0a59..2e9b95a94f89 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -448,7 +448,7 @@ static void xgbe_isr_bh_work(struct work_struct *work) if (XGMAC_GET_BITS(mac_tssr, MAC_TSSR, TXTSC)) { /* Read Tx Timestamp to clear interrupt */ pdata->tx_tstamp = - hw_if->get_tx_tstamp(pdata); + xgbe_get_tx_tstamp(pdata); queue_work(pdata->dev_workqueue, &pdata->tx_tstamp_work); } @@ -1371,199 +1371,6 @@ static void xgbe_restart(struct work_struct *work) rtnl_unlock(); } -static void xgbe_tx_tstamp(struct work_struct *work) -{ - struct xgbe_prv_data *pdata = container_of(work, - struct xgbe_prv_data, - tx_tstamp_work); - struct skb_shared_hwtstamps hwtstamps; - u64 nsec; - unsigned long flags; - - spin_lock_irqsave(&pdata->tstamp_lock, flags); - if (!pdata->tx_tstamp_skb) - goto unlock; - - if (pdata->tx_tstamp) { - nsec = timecounter_cyc2time(&pdata->tstamp_tc, - pdata->tx_tstamp); - - memset(&hwtstamps, 0, sizeof(hwtstamps)); - hwtstamps.hwtstamp = ns_to_ktime(nsec); - skb_tstamp_tx(pdata->tx_tstamp_skb, &hwtstamps); - } - - dev_kfree_skb_any(pdata->tx_tstamp_skb); - - pdata->tx_tstamp_skb = NULL; - -unlock: - spin_unlock_irqrestore(&pdata->tstamp_lock, flags); -} - -static int xgbe_get_hwtstamp_settings(struct xgbe_prv_data *pdata, - struct ifreq *ifreq) -{ - if (copy_to_user(ifreq->ifr_data, &pdata->tstamp_config, - sizeof(pdata->tstamp_config))) - return -EFAULT; - - return 0; -} - -static int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, - struct ifreq *ifreq) -{ - struct hwtstamp_config config; - unsigned int mac_tscr; - - if (copy_from_user(&config, ifreq->ifr_data, sizeof(config))) - return -EFAULT; - - mac_tscr = 0; - - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - break; - - case HWTSTAMP_TX_ON: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - default: - return -ERANGE; - } - - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - break; - - case HWTSTAMP_FILTER_NTP_ALL: - case HWTSTAMP_FILTER_ALL: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENALL, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* PTP v2, UDP, any kind of event packet */ - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - fallthrough; /* to PTP v1, UDP, any kind of event packet */ - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* PTP v2, UDP, Sync packet */ - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - fallthrough; /* to PTP v1, UDP, Sync packet */ - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* PTP v2, UDP, Delay_req packet */ - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - fallthrough; /* to PTP v1, UDP, Delay_req packet */ - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* 802.AS1, Ethernet, any kind of event packet */ - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* 802.AS1, Ethernet, Sync packet */ - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* 802.AS1, Ethernet, Delay_req packet */ - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* PTP v2/802.AS1, any layer, any kind of event packet */ - case HWTSTAMP_FILTER_PTP_V2_EVENT: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* PTP v2/802.AS1, any layer, Sync packet */ - case HWTSTAMP_FILTER_PTP_V2_SYNC: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - /* PTP v2/802.AS1, any layer, Delay_req packet */ - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); - XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); - break; - - default: - return -ERANGE; - } - - pdata->hw_if.config_tstamp(pdata, mac_tscr); - - memcpy(&pdata->tstamp_config, &config, sizeof(config)); - - return 0; -} - -static void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata, - struct sk_buff *skb, - struct xgbe_packet_data *packet) -{ - unsigned long flags; - - if (XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, PTP)) { - spin_lock_irqsave(&pdata->tstamp_lock, flags); - if (pdata->tx_tstamp_skb) { - /* Another timestamp in progress, ignore this one */ - XGMAC_SET_BITS(packet->attributes, - TX_PACKET_ATTRIBUTES, PTP, 0); - } else { - pdata->tx_tstamp_skb = skb_get(skb); - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - } - spin_unlock_irqrestore(&pdata->tstamp_lock, flags); - } - - skb_tx_timestamp(skb); -} - static void xgbe_prep_vlan(struct sk_buff *skb, struct xgbe_packet_data *packet) { if (skb_vlan_tag_present(skb)) @@ -1776,6 +1583,9 @@ static int xgbe_open(struct net_device *netdev) INIT_WORK(&pdata->stopdev_work, xgbe_stopdev); INIT_WORK(&pdata->tx_tstamp_work, xgbe_tx_tstamp); + /* Initialize PTP timestamping and clock. */ + xgbe_init_ptp(pdata); + ret = xgbe_alloc_memory(pdata); if (ret) goto err_ptpclk; @@ -2546,12 +2356,8 @@ skip_data: if (XGMAC_GET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, RX_TSTAMP)) { - u64 nsec; - - nsec = timecounter_cyc2time(&pdata->tstamp_tc, - packet->rx_tstamp); hwtstamps = skb_hwtstamps(skb); - hwtstamps->hwtstamp = ns_to_ktime(nsec); + hwtstamps->hwtstamp = ns_to_ktime(packet->rx_tstamp); } if (XGMAC_GET_BITS(packet->attributes, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c b/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c new file mode 100644 index 000000000000..bc52e5ec6420 --- /dev/null +++ b/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c @@ -0,0 +1,401 @@ +// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause) +/* + * Copyright (c) 2014-2025, Advanced Micro Devices, Inc. + * Copyright (c) 2014, Synopsys, Inc. + * All rights reserved + * + * Author: Raju Rangoju <Raju.Rangoju@amd.com> + */ + +#include "xgbe.h" +#include "xgbe-common.h" + +void xgbe_update_tstamp_time(struct xgbe_prv_data *pdata, + unsigned int sec, unsigned int nsec) +{ + int count; + + /* Set the time values and tell the device */ + XGMAC_IOWRITE(pdata, MAC_STSUR, sec); + XGMAC_IOWRITE(pdata, MAC_STNUR, nsec); + + /* issue command to update the system time value */ + XGMAC_IOWRITE(pdata, MAC_TSCR, + XGMAC_IOREAD(pdata, MAC_TSCR) | + (1 << MAC_TSCR_TSUPDT_INDEX)); + + /* Wait for the time adjust/update to complete */ + count = 10000; + while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSUPDT)) + udelay(5); + + if (count < 0) + netdev_err(pdata->netdev, + "timed out updating system timestamp\n"); +} + +void xgbe_update_tstamp_addend(struct xgbe_prv_data *pdata, + unsigned int addend) +{ + unsigned int count = 10000; + + /* Set the addend register value and tell the device */ + XGMAC_IOWRITE(pdata, MAC_TSAR, addend); + XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSADDREG, 1); + + /* Wait for addend update to complete */ + while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSADDREG)) + udelay(5); + + if (!count) + netdev_err(pdata->netdev, + "timed out updating timestamp addend register\n"); +} + +void xgbe_set_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec, + unsigned int nsec) +{ + unsigned int count = 10000; + + /* Set the time values and tell the device */ + XGMAC_IOWRITE(pdata, MAC_STSUR, sec); + XGMAC_IOWRITE(pdata, MAC_STNUR, nsec); + XGMAC_IOWRITE_BITS(pdata, MAC_TSCR, TSINIT, 1); + + /* Wait for time update to complete */ + while (--count && XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSINIT)) + udelay(5); + + if (!count) + netdev_err(pdata->netdev, "timed out initializing timestamp\n"); +} + +u64 xgbe_get_tstamp_time(struct xgbe_prv_data *pdata) +{ + u64 nsec; + + nsec = XGMAC_IOREAD(pdata, MAC_STSR); + nsec *= NSEC_PER_SEC; + nsec += XGMAC_IOREAD(pdata, MAC_STNR); + + return nsec; +} + +u64 xgbe_get_tx_tstamp(struct xgbe_prv_data *pdata) +{ + unsigned int tx_snr, tx_ssr; + u64 nsec; + + if (pdata->vdata->tx_tstamp_workaround) { + tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR); + tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR); + } else { + tx_ssr = XGMAC_IOREAD(pdata, MAC_TXSSR); + tx_snr = XGMAC_IOREAD(pdata, MAC_TXSNR); + } + + if (XGMAC_GET_BITS(tx_snr, MAC_TXSNR, TXTSSTSMIS)) + return 0; + + nsec = tx_ssr; + nsec *= NSEC_PER_SEC; + nsec += tx_snr; + + return nsec; +} + +void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet, + struct xgbe_ring_desc *rdesc) +{ + u64 nsec; + + if (XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSA) && + !XGMAC_GET_BITS_LE(rdesc->desc3, RX_CONTEXT_DESC3, TSD)) { + nsec = le32_to_cpu(rdesc->desc1); + nsec *= NSEC_PER_SEC; + nsec += le32_to_cpu(rdesc->desc0); + if (nsec != 0xffffffffffffffffULL) { + packet->rx_tstamp = nsec; + XGMAC_SET_BITS(packet->attributes, RX_PACKET_ATTRIBUTES, + RX_TSTAMP, 1); + } + } +} + +void xgbe_config_tstamp(struct xgbe_prv_data *pdata, unsigned int mac_tscr) +{ + unsigned int value = 0; + + value = XGMAC_IOREAD(pdata, MAC_TSCR); + value |= mac_tscr; + XGMAC_IOWRITE(pdata, MAC_TSCR, value); +} + +void xgbe_tx_tstamp(struct work_struct *work) +{ + struct xgbe_prv_data *pdata = container_of(work, + struct xgbe_prv_data, + tx_tstamp_work); + struct skb_shared_hwtstamps hwtstamps; + unsigned long flags; + + spin_lock_irqsave(&pdata->tstamp_lock, flags); + if (!pdata->tx_tstamp_skb) + goto unlock; + + if (pdata->tx_tstamp) { + memset(&hwtstamps, 0, sizeof(hwtstamps)); + hwtstamps.hwtstamp = ns_to_ktime(pdata->tx_tstamp); + skb_tstamp_tx(pdata->tx_tstamp_skb, &hwtstamps); + } + + dev_kfree_skb_any(pdata->tx_tstamp_skb); + + pdata->tx_tstamp_skb = NULL; + +unlock: + spin_unlock_irqrestore(&pdata->tstamp_lock, flags); +} + +int xgbe_get_hwtstamp_settings(struct xgbe_prv_data *pdata, struct ifreq *ifreq) +{ + if (copy_to_user(ifreq->ifr_data, &pdata->tstamp_config, + sizeof(pdata->tstamp_config))) + return -EFAULT; + + return 0; +} + +int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, struct ifreq *ifreq) +{ + struct hwtstamp_config config; + unsigned int mac_tscr; + + if (copy_from_user(&config, ifreq->ifr_data, sizeof(config))) + return -EFAULT; + + mac_tscr = 0; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + break; + + case HWTSTAMP_TX_ON: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + + case HWTSTAMP_FILTER_NTP_ALL: + case HWTSTAMP_FILTER_ALL: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENALL, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* PTP v2, UDP, any kind of event packet */ + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); + fallthrough; /* to PTP v1, UDP, any kind of event packet */ + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + /* PTP v2, UDP, Sync packet */ + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); + fallthrough; /* to PTP v1, UDP, Sync packet */ + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* PTP v2, UDP, Delay_req packet */ + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); + fallthrough; /* to PTP v1, UDP, Delay_req packet */ + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* 802.AS1, Ethernet, any kind of event packet */ + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* 802.AS1, Ethernet, Sync packet */ + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* 802.AS1, Ethernet, Delay_req packet */ + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, AV8021ASMEN, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* PTP v2/802.AS1, any layer, any kind of event packet */ + case HWTSTAMP_FILTER_PTP_V2_EVENT: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, SNAPTYPSEL, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* PTP v2/802.AS1, any layer, Sync packet */ + case HWTSTAMP_FILTER_PTP_V2_SYNC: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + /* PTP v2/802.AS1, any layer, Delay_req packet */ + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSVER2ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV4ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSIPV6ENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSMSTRENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSEVNTENA, 1); + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + break; + + default: + return -ERANGE; + } + + xgbe_config_tstamp(pdata, mac_tscr); + + memcpy(&pdata->tstamp_config, &config, sizeof(config)); + + return 0; +} + +void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata, + struct sk_buff *skb, + struct xgbe_packet_data *packet) +{ + unsigned long flags; + + if (XGMAC_GET_BITS(packet->attributes, TX_PACKET_ATTRIBUTES, PTP)) { + spin_lock_irqsave(&pdata->tstamp_lock, flags); + if (pdata->tx_tstamp_skb) { + /* Another timestamp in progress, ignore this one */ + XGMAC_SET_BITS(packet->attributes, + TX_PACKET_ATTRIBUTES, PTP, 0); + } else { + pdata->tx_tstamp_skb = skb_get(skb); + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + } + spin_unlock_irqrestore(&pdata->tstamp_lock, flags); + } + + skb_tx_timestamp(skb); +} + +int xgbe_init_ptp(struct xgbe_prv_data *pdata) +{ + unsigned int mac_tscr = 0; + struct timespec64 now; + u64 dividend; + + /* Register Settings to be done based on the link speed. */ + switch (pdata->phy.speed) { + case SPEED_1000: + XGMAC_IOWRITE(pdata, MAC_TICNR, MAC_TICNR_1G_INITVAL); + XGMAC_IOWRITE(pdata, MAC_TECNR, MAC_TECNR_1G_INITVAL); + break; + case SPEED_2500: + case SPEED_10000: + XGMAC_IOWRITE_BITS(pdata, MAC_TICSNR, TSICSNS, + MAC_TICSNR_10G_INITVAL); + XGMAC_IOWRITE(pdata, MAC_TECNR, MAC_TECNR_10G_INITVAL); + XGMAC_IOWRITE_BITS(pdata, MAC_TECSNR, TSECSNS, + MAC_TECSNR_10G_INITVAL); + break; + case SPEED_UNKNOWN: + default: + break; + } + + /* Enable IEEE1588 PTP clock. */ + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSENA, 1); + + /* Overwrite earlier timestamps */ + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TXTSSTSM, 1); + + /* Set one nano-second accuracy */ + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCTRLSSR, 1); + + /* Set fine timestamp update */ + XGMAC_SET_BITS(mac_tscr, MAC_TSCR, TSCFUPDT, 1); + + xgbe_config_tstamp(pdata, mac_tscr); + + /* Exit if timestamping is not enabled */ + if (!XGMAC_GET_BITS(mac_tscr, MAC_TSCR, TSENA)) + return -EOPNOTSUPP; + + if (pdata->vdata->tstamp_ptp_clock_freq) { + /* Initialize time registers based on + * 125MHz PTP Clock Frequency + */ + XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SSINC, + XGBE_V2_TSTAMP_SSINC); + XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SNSINC, + XGBE_V2_TSTAMP_SNSINC); + } else { + /* Initialize time registers based on + * 50MHz PTP Clock Frequency + */ + XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SSINC, XGBE_TSTAMP_SSINC); + XGMAC_IOWRITE_BITS(pdata, MAC_SSIR, SNSINC, XGBE_TSTAMP_SNSINC); + } + + /* Calculate the addend: + * addend = 2^32 / (PTP ref clock / (PTP clock based on SSINC)) + * = (2^32 * (PTP clock based on SSINC)) / PTP ref clock + */ + if (pdata->vdata->tstamp_ptp_clock_freq) + dividend = XGBE_V2_PTP_ACT_CLK_FREQ; + else + dividend = XGBE_PTP_ACT_CLK_FREQ; + + dividend = (u64)(dividend << 32); + pdata->tstamp_addend = div_u64(dividend, pdata->ptpclk_rate); + + xgbe_update_tstamp_addend(pdata, pdata->tstamp_addend); + + dma_wmb(); + /* initialize system time */ + ktime_get_real_ts64(&now); + + /* lower 32 bits of tv_sec are safe until y2106 */ + xgbe_set_tstamp_time(pdata, (u32)now.tv_sec, now.tv_nsec); + + return 0; +} diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index 097ec5e4f261..e3e1dca9856a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -414,6 +414,7 @@ static struct xgbe_version_data xgbe_v2a = { .tx_max_fifo_size = 229376, .rx_max_fifo_size = 229376, .tx_tstamp_workaround = 1, + .tstamp_ptp_clock_freq = 1, .ecc_support = 1, .i2c_support = 1, .irq_reissue_support = 1, @@ -430,6 +431,7 @@ static struct xgbe_version_data xgbe_v2b = { .tx_max_fifo_size = 65536, .rx_max_fifo_size = 65536, .tx_tstamp_workaround = 1, + .tstamp_ptp_clock_freq = 1, .ecc_support = 1, .i2c_support = 1, .irq_reissue_support = 1, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c index 978c4dd01fa0..3658afc7801d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c @@ -13,18 +13,6 @@ #include "xgbe.h" #include "xgbe-common.h" -static u64 xgbe_cc_read(const struct cyclecounter *cc) -{ - struct xgbe_prv_data *pdata = container_of(cc, - struct xgbe_prv_data, - tstamp_cc); - u64 nsec; - - nsec = pdata->hw_if.get_tstamp_time(pdata); - - return nsec; -} - static int xgbe_adjfine(struct ptp_clock_info *info, long scaled_ppm) { struct xgbe_prv_data *pdata = container_of(info, @@ -37,7 +25,7 @@ static int xgbe_adjfine(struct ptp_clock_info *info, long scaled_ppm) spin_lock_irqsave(&pdata->tstamp_lock, flags); - pdata->hw_if.update_tstamp_addend(pdata, addend); + xgbe_update_tstamp_addend(pdata, addend); spin_unlock_irqrestore(&pdata->tstamp_lock, flags); @@ -49,16 +37,39 @@ static int xgbe_adjtime(struct ptp_clock_info *info, s64 delta) struct xgbe_prv_data *pdata = container_of(info, struct xgbe_prv_data, ptp_clock_info); + unsigned int neg_adjust = 0; + unsigned int sec, nsec; + u32 quotient, reminder; unsigned long flags; + if (delta < 0) { + neg_adjust = 1; + delta = -delta; + } + + quotient = div_u64_rem(delta, 1000000000ULL, &reminder); + sec = quotient; + nsec = reminder; + + /* Negative adjustment for Hw timer register. */ + if (neg_adjust) { + sec = -sec; + if (XGMAC_IOREAD_BITS(pdata, MAC_TSCR, TSCTRLSSR)) + nsec = (1000000000UL - nsec); + else + nsec = (0x80000000UL - nsec); + } + nsec = (neg_adjust << 31) | nsec; + spin_lock_irqsave(&pdata->tstamp_lock, flags); - timecounter_adjtime(&pdata->tstamp_tc, delta); + xgbe_update_tstamp_time(pdata, sec, nsec); spin_unlock_irqrestore(&pdata->tstamp_lock, flags); return 0; } -static int xgbe_gettime(struct ptp_clock_info *info, struct timespec64 *ts) +static int xgbe_gettimex(struct ptp_clock_info *info, struct timespec64 *ts, + struct ptp_system_timestamp *sts) { struct xgbe_prv_data *pdata = container_of(info, struct xgbe_prv_data, @@ -67,9 +78,9 @@ static int xgbe_gettime(struct ptp_clock_info *info, struct timespec64 *ts) u64 nsec; spin_lock_irqsave(&pdata->tstamp_lock, flags); - - nsec = timecounter_read(&pdata->tstamp_tc); - + ptp_read_system_prets(sts); + nsec = xgbe_get_tstamp_time(pdata); + ptp_read_system_postts(sts); spin_unlock_irqrestore(&pdata->tstamp_lock, flags); *ts = ns_to_timespec64(nsec); @@ -84,14 +95,9 @@ static int xgbe_settime(struct ptp_clock_info *info, struct xgbe_prv_data, ptp_clock_info); unsigned long flags; - u64 nsec; - - nsec = timespec64_to_ns(ts); spin_lock_irqsave(&pdata->tstamp_lock, flags); - - timecounter_init(&pdata->tstamp_tc, &pdata->tstamp_cc, nsec); - + xgbe_set_tstamp_time(pdata, ts->tv_sec, ts->tv_nsec); spin_unlock_irqrestore(&pdata->tstamp_lock, flags); return 0; @@ -107,8 +113,6 @@ void xgbe_ptp_register(struct xgbe_prv_data *pdata) { struct ptp_clock_info *info = &pdata->ptp_clock_info; struct ptp_clock *clock; - struct cyclecounter *cc = &pdata->tstamp_cc; - u64 dividend; snprintf(info->name, sizeof(info->name), "%s", netdev_name(pdata->netdev)); @@ -116,7 +120,7 @@ void xgbe_ptp_register(struct xgbe_prv_data *pdata) info->max_adj = pdata->ptpclk_rate; info->adjfine = xgbe_adjfine; info->adjtime = xgbe_adjtime; - info->gettime64 = xgbe_gettime; + info->gettimex64 = xgbe_gettimex; info->settime64 = xgbe_settime; info->enable = xgbe_enable; @@ -128,23 +132,6 @@ void xgbe_ptp_register(struct xgbe_prv_data *pdata) pdata->ptp_clock = clock; - /* Calculate the addend: - * addend = 2^32 / (PTP ref clock / 50Mhz) - * = (2^32 * 50Mhz) / PTP ref clock - */ - dividend = 50000000; - dividend <<= 32; - pdata->tstamp_addend = div_u64(dividend, pdata->ptpclk_rate); - - /* Setup the timecounter */ - cc->read = xgbe_cc_read; - cc->mask = CLOCKSOURCE_MASK(64); - cc->mult = 1; - cc->shift = 0; - - timecounter_init(&pdata->tstamp_tc, &pdata->tstamp_cc, - ktime_to_ns(ktime_get_real())); - /* Disable all timestamping to start */ XGMAC_IOWRITE(pdata, MAC_TSCR, 0); pdata->tstamp_config.tx_type = HWTSTAMP_TX_OFF; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 70169ea23c7f..d7e03e292ec4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -119,6 +119,14 @@ #define XGBE_MSI_BASE_COUNT 4 #define XGBE_MSI_MIN_COUNT (XGBE_MSI_BASE_COUNT + 1) +/* Initial PTP register values based on Link Speed. */ +#define MAC_TICNR_1G_INITVAL 0x10 +#define MAC_TECNR_1G_INITVAL 0x28 + +#define MAC_TICSNR_10G_INITVAL 0x33 +#define MAC_TECNR_10G_INITVAL 0x14 +#define MAC_TECSNR_10G_INITVAL 0xCC + /* PCI clock frequencies */ #define XGBE_V2_DMA_CLOCK_FREQ 500000000 /* 500 MHz */ #define XGBE_V2_PTP_CLOCK_FREQ 125000000 /* 125 MHz */ @@ -128,6 +136,11 @@ */ #define XGBE_TSTAMP_SSINC 20 #define XGBE_TSTAMP_SNSINC 0 +#define XGBE_PTP_ACT_CLK_FREQ 500000000 + +#define XGBE_V2_TSTAMP_SSINC 0xA +#define XGBE_V2_TSTAMP_SNSINC 0 +#define XGBE_V2_PTP_ACT_CLK_FREQ 1000000000 /* Driver PMT macros */ #define XGMAC_DRIVER_CONTEXT 1 @@ -741,14 +754,6 @@ struct xgbe_hw_if { void (*tx_mmc_int)(struct xgbe_prv_data *); void (*read_mmc_stats)(struct xgbe_prv_data *); - /* For Timestamp config */ - int (*config_tstamp)(struct xgbe_prv_data *, unsigned int); - void (*update_tstamp_addend)(struct xgbe_prv_data *, unsigned int); - void (*set_tstamp_time)(struct xgbe_prv_data *, unsigned int sec, - unsigned int nsec); - u64 (*get_tstamp_time)(struct xgbe_prv_data *); - u64 (*get_tx_tstamp)(struct xgbe_prv_data *); - /* For Data Center Bridging config */ void (*config_tc)(struct xgbe_prv_data *); void (*config_dcb_tc)(struct xgbe_prv_data *); @@ -946,6 +951,7 @@ struct xgbe_version_data { unsigned int tx_max_fifo_size; unsigned int rx_max_fifo_size; unsigned int tx_tstamp_workaround; + unsigned int tstamp_ptp_clock_freq; unsigned int ecc_support; unsigned int i2c_support; unsigned int irq_reissue_support; @@ -1131,8 +1137,6 @@ struct xgbe_prv_data { struct ptp_clock_info ptp_clock_info; struct ptp_clock *ptp_clock; struct hwtstamp_config tstamp_config; - struct cyclecounter tstamp_cc; - struct timecounter tstamp_tc; unsigned int tstamp_addend; struct work_struct tx_tstamp_work; struct sk_buff *tx_tstamp_skb; @@ -1277,6 +1281,29 @@ void xgbe_init_tx_coalesce(struct xgbe_prv_data *); void xgbe_restart_dev(struct xgbe_prv_data *pdata); void xgbe_full_restart_dev(struct xgbe_prv_data *pdata); +/* For Timestamp config */ +void xgbe_config_tstamp(struct xgbe_prv_data *pdata, unsigned int mac_tscr); +u64 xgbe_get_tstamp_time(struct xgbe_prv_data *pdata); +u64 xgbe_get_tx_tstamp(struct xgbe_prv_data *pdata); +void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet, + struct xgbe_ring_desc *rdesc); +void xgbe_get_rx_tstamp(struct xgbe_packet_data *packet, + struct xgbe_ring_desc *rdesc); +void xgbe_update_tstamp_addend(struct xgbe_prv_data *pdata, + unsigned int addend); +void xgbe_set_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec, + unsigned int nsec); +void xgbe_tx_tstamp(struct work_struct *work); +int xgbe_get_hwtstamp_settings(struct xgbe_prv_data *pdata, + struct ifreq *ifreq); +int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, + struct ifreq *ifreq); +void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata, + struct sk_buff *skb, + struct xgbe_packet_data *packet); +int xgbe_init_ptp(struct xgbe_prv_data *pdata); +void xgbe_update_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec, + unsigned int nsec); #ifdef CONFIG_DEBUG_FS void xgbe_debugfs_init(struct xgbe_prv_data *); void xgbe_debugfs_exit(struct xgbe_prv_data *); diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index d8e6f23e1432..cbc730c7cff2 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1213,6 +1213,11 @@ static bool ag71xx_fill_rx_buf(struct ag71xx *ag, struct ag71xx_buf *buf, buf->rx.rx_buf = data; buf->rx.dma_addr = dma_map_single(&ag->pdev->dev, data, ag->rx_buf_size, DMA_FROM_DEVICE); + if (dma_mapping_error(&ag->pdev->dev, buf->rx.dma_addr)) { + skb_free_frag(data); + buf->rx.rx_buf = NULL; + return false; + } desc->data = (u32)buf->rx.dma_addr + offset; return true; } @@ -1511,6 +1516,10 @@ static netdev_tx_t ag71xx_hard_start_xmit(struct sk_buff *skb, dma_addr = dma_map_single(&ag->pdev->dev, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(&ag->pdev->dev, dma_addr)) { + netif_dbg(ag, tx_err, ndev, "DMA mapping error\n"); + goto err_drop; + } i = ring->curr & ring_mask; desc = ag71xx_ring_desc(ring, i); diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index ef1a51347351..3a9ad4a9c1cb 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2688,7 +2688,7 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->mii.mdio_write = atl1c_mdio_write; adapter->mii.phy_id_mask = 0x1f; adapter->mii.reg_num_mask = MDIO_CTRL_REG_MASK; - dev_set_threaded(netdev, true); + netif_set_threaded(netdev, true); for (i = 0; i < adapter->rx_queue_count; ++i) netif_napi_add(netdev, &adapter->rrd_ring[i].napi, atl1c_clean_rx); diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c index 4381a4cfd8c6..63f1a8c3a7fb 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c @@ -430,4 +430,5 @@ const struct ethtool_ops bcmasp_ethtool_ops = { .get_ethtool_stats = bcmasp_get_ethtool_stats, .get_sset_count = bcmasp_get_sset_count, .get_ts_info = ethtool_op_get_ts_info, + .nway_reset = phy_ethtool_nway_reset, }; diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index a6ea477bce3c..b9973956c480 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -816,6 +816,9 @@ static void bcmasp_init_tx(struct bcmasp_intf *intf) /* Tx SPB */ tx_spb_ctrl_wl(intf, ((intf->channel + 8) << TX_SPB_CTRL_XF_BID_SHIFT), TX_SPB_CTRL_XF_CTRL2); + + if (intf->parent->tx_chan_offset) + tx_pause_ctrl_wl(intf, (1 << (intf->channel + 8)), TX_PAUSE_MAP_VECTOR); tx_spb_top_wl(intf, 0x1e, TX_SPB_TOP_BLKOUT); tx_spb_dma_wq(intf, intf->tx_spb_dma_addr, TX_SPB_DMA_READ); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index f49400ba9729..cb004fd16252 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1465,10 +1465,10 @@ static void be_tx_timeout(struct net_device *netdev, unsigned int txqueue) ntohs(tcphdr->source)); dev_info(dev, "TCP dest port %d\n", ntohs(tcphdr->dest)); - dev_info(dev, "TCP sequence num %d\n", - ntohs(tcphdr->seq)); - dev_info(dev, "TCP ack_seq %d\n", - ntohs(tcphdr->ack_seq)); + dev_info(dev, "TCP sequence num %u\n", + ntohl(tcphdr->seq)); + dev_info(dev, "TCP ack_seq %u\n", + ntohl(tcphdr->ack_seq)); } else if (ip_hdr(skb)->protocol == IPPROTO_UDP) { udphdr = udp_hdr(skb); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b82f121cadad..0f4efd505332 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4666,12 +4666,19 @@ static int dpaa2_eth_connect_mac(struct dpaa2_eth_priv *priv) return PTR_ERR(dpmac_dev); } - if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) + if (IS_ERR(dpmac_dev)) return 0; + if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) { + err = 0; + goto out_put_device; + } + mac = kzalloc(sizeof(struct dpaa2_mac), GFP_KERNEL); - if (!mac) - return -ENOMEM; + if (!mac) { + err = -ENOMEM; + goto out_put_device; + } mac->mc_dev = dpmac_dev; mac->mc_io = priv->mc_io; @@ -4705,6 +4712,8 @@ err_close_mac: dpaa2_mac_close(mac); err_free_mac: kfree(mac); +out_put_device: + put_device(&dpmac_dev->dev); return err; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index 147a93bf9fa9..4643a3380618 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1448,12 +1448,19 @@ static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv) if (PTR_ERR(dpmac_dev) == -EPROBE_DEFER) return PTR_ERR(dpmac_dev); - if (IS_ERR(dpmac_dev) || dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) + if (IS_ERR(dpmac_dev)) return 0; + if (dpmac_dev->dev.type != &fsl_mc_bus_dpmac_type) { + err = 0; + goto out_put_device; + } + mac = kzalloc(sizeof(*mac), GFP_KERNEL); - if (!mac) - return -ENOMEM; + if (!mac) { + err = -ENOMEM; + goto out_put_device; + } mac->mc_dev = dpmac_dev; mac->mc_io = port_priv->ethsw_data->mc_io; @@ -1483,6 +1490,8 @@ err_close_mac: dpaa2_mac_close(mac); err_free_mac: kfree(mac); +out_put_device: + put_device(&dpmac_dev->dev); return err; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index b481ee8ee478..1383918f8a3f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1045,7 +1045,9 @@ static void fec_enet_bd_init(struct net_device *dev) struct page *page = txq->tx_buf[i].buf_p; if (page) - page_pool_put_page(page->pp, page, 0, false); + page_pool_put_page(pp_page_to_nmdesc(page)->pp, + page, 0, + false); } txq->tx_buf[i].buf_p = NULL; @@ -1586,7 +1588,8 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id, int budget) xdp_return_frame_rx_napi(xdpf); } else { /* recycle pages of XDP_TX frames */ /* The dma_sync_size = 0 as XDP_TX has already synced DMA for_device */ - page_pool_put_page(page->pp, page, 0, true); + page_pool_put_page(pp_page_to_nmdesc(page)->pp, page, + 0, true); } txq->tx_buf[index].buf_p = NULL; @@ -3348,7 +3351,8 @@ static void fec_enet_free_buffers(struct net_device *ndev) } else { struct page *page = txq->tx_buf[i].buf_p; - page_pool_put_page(page->pp, page, 0, false); + page_pool_put_page(pp_page_to_nmdesc(page)->pp, + page, 0, false); } txq->tx_buf[i].buf_p = NULL; diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 53899096e89e..bceaf9b05cb4 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -190,6 +190,9 @@ struct gve_rx_buf_state_dqo { /* The page posted to HW. */ struct gve_rx_slot_page_info page_info; + /* XSK buffer */ + struct xdp_buff *xsk_buff; + /* The DMA address corresponding to `page_info`. */ dma_addr_t addr; @@ -331,7 +334,6 @@ struct gve_rx_ring { /* XDP stuff */ struct xdp_rxq_info xdp_rxq; - struct xdp_rxq_info xsk_rxq; struct xsk_buff_pool *xsk_pool; struct page_frag_cache page_cache; /* Page cache to allocate XDP frames */ }; @@ -400,11 +402,17 @@ enum gve_packet_state { GVE_PACKET_STATE_PENDING_REINJECT_COMPL, /* No valid completion received within the specified timeout. */ GVE_PACKET_STATE_TIMED_OUT_COMPL, + /* XSK pending packet has received a packet/reinjection completion, or + * has timed out. At this point, the pending packet can be counted by + * xsk_tx_complete and freed. + */ + GVE_PACKET_STATE_XSK_COMPLETE, }; enum gve_tx_pending_packet_dqo_type { GVE_TX_PENDING_PACKET_DQO_SKB, - GVE_TX_PENDING_PACKET_DQO_XDP_FRAME + GVE_TX_PENDING_PACKET_DQO_XDP_FRAME, + GVE_TX_PENDING_PACKET_DQO_XSK, }; struct gve_tx_pending_packet_dqo { @@ -441,10 +449,10 @@ struct gve_tx_pending_packet_dqo { /* Identifies the current state of the packet as defined in * `enum gve_packet_state`. */ - u8 state : 2; + u8 state : 3; /* gve_tx_pending_packet_dqo_type */ - u8 type : 1; + u8 type : 2; /* If packet is an outstanding miss completion, then the packet is * freed if the corresponding re-injection completion is not received @@ -513,6 +521,8 @@ struct gve_tx_ring { /* Cached value of `dqo_compl.free_tx_qpl_buf_cnt` */ u32 free_tx_qpl_buf_cnt; }; + + atomic_t xsk_reorder_queue_tail; } dqo_tx; }; @@ -546,6 +556,9 @@ struct gve_tx_ring { /* Last TX ring index fetched by HW */ atomic_t hw_tx_head; + u16 xsk_reorder_queue_head; + u16 xsk_reorder_queue_tail; + /* List to track pending packets which received a miss * completion but not a corresponding reinjection. */ @@ -599,6 +612,8 @@ struct gve_tx_ring { struct gve_tx_pending_packet_dqo *pending_packets; s16 num_pending_packets; + u16 *xsk_reorder_queue; + u32 complq_mask; /* complq size is complq_mask + 1 */ /* QPL fields */ @@ -803,6 +818,7 @@ struct gve_priv { struct gve_tx_queue_config tx_cfg; struct gve_rx_queue_config rx_cfg; + unsigned long *xsk_pools; /* bitmap of RX queues with XSK pools */ u32 num_ntfy_blks; /* split between TX and RX so must be even */ int numa_node; diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c index 6c3c459a1b5e..8f5021e59e0a 100644 --- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c @@ -4,6 +4,7 @@ * Copyright (C) 2015-2024 Google, Inc. */ +#include <net/xdp_sock_drv.h> #include "gve.h" #include "gve_utils.h" @@ -29,6 +30,10 @@ struct gve_rx_buf_state_dqo *gve_alloc_buf_state(struct gve_rx_ring *rx) /* Point buf_state to itself to mark it as allocated */ buf_state->next = buffer_id; + /* Clear the buffer pointers */ + buf_state->page_info.page = NULL; + buf_state->xsk_buff = NULL; + return buf_state; } @@ -286,7 +291,24 @@ int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc) { struct gve_rx_buf_state_dqo *buf_state; - if (rx->dqo.page_pool) { + if (rx->xsk_pool) { + buf_state = gve_alloc_buf_state(rx); + if (unlikely(!buf_state)) + return -ENOMEM; + + buf_state->xsk_buff = xsk_buff_alloc(rx->xsk_pool); + if (unlikely(!buf_state->xsk_buff)) { + xsk_set_rx_need_wakeup(rx->xsk_pool); + gve_free_buf_state(rx, buf_state); + return -ENOMEM; + } + /* Allocated xsk buffer. Clear wakeup in case it was set. */ + xsk_clear_rx_need_wakeup(rx->xsk_pool); + desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states); + desc->buf_addr = + cpu_to_le64(xsk_buff_xdp_get_dma(buf_state->xsk_buff)); + return 0; + } else if (rx->dqo.page_pool) { buf_state = gve_alloc_buf_state(rx); if (WARN_ON_ONCE(!buf_state)) return -ENOMEM; diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h index bb278727f4d9..6eb442096e02 100644 --- a/drivers/net/ethernet/google/gve/gve_dqo.h +++ b/drivers/net/ethernet/google/gve/gve_dqo.h @@ -38,6 +38,7 @@ netdev_features_t gve_features_check_dqo(struct sk_buff *skb, netdev_features_t features); bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean); bool gve_xdp_poll_dqo(struct gve_notify_block *block); +bool gve_xsk_tx_poll_dqo(struct gve_notify_block *block, int budget); int gve_rx_poll_dqo(struct gve_notify_block *block, int budget); int gve_tx_alloc_rings_dqo(struct gve_priv *priv, struct gve_tx_alloc_rings_cfg *cfg); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index be461751ff31..1f411d7c4373 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -4,6 +4,7 @@ * Copyright (C) 2015-2024 Google LLC */ +#include <linux/bitmap.h> #include <linux/bpf.h> #include <linux/cpumask.h> #include <linux/etherdevice.h> @@ -426,6 +427,12 @@ int gve_napi_poll_dqo(struct napi_struct *napi, int budget) if (block->rx) { work_done = gve_rx_poll_dqo(block, budget); + + /* Poll XSK TX as part of RX NAPI. Setup re-poll based on if + * either datapath has more work to do. + */ + if (priv->xdp_prog) + reschedule |= gve_xsk_tx_poll_dqo(block, budget); reschedule |= work_done == budget; } @@ -1158,18 +1165,84 @@ static int gve_reset_recovery(struct gve_priv *priv, bool was_up); static void gve_turndown(struct gve_priv *priv); static void gve_turnup(struct gve_priv *priv); +static void gve_unreg_xsk_pool(struct gve_priv *priv, u16 qid) +{ + struct gve_rx_ring *rx; + + if (!priv->rx) + return; + + rx = &priv->rx[qid]; + rx->xsk_pool = NULL; + if (xdp_rxq_info_is_reg(&rx->xdp_rxq)) + xdp_rxq_info_unreg_mem_model(&rx->xdp_rxq); + + if (!priv->tx) + return; + priv->tx[gve_xdp_tx_queue_id(priv, qid)].xsk_pool = NULL; +} + +static int gve_reg_xsk_pool(struct gve_priv *priv, struct net_device *dev, + struct xsk_buff_pool *pool, u16 qid) +{ + struct gve_rx_ring *rx; + u16 tx_qid; + int err; + + rx = &priv->rx[qid]; + err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, pool); + if (err) { + gve_unreg_xsk_pool(priv, qid); + return err; + } + + rx->xsk_pool = pool; + + tx_qid = gve_xdp_tx_queue_id(priv, qid); + priv->tx[tx_qid].xsk_pool = pool; + + return 0; +} + +static void gve_unreg_xdp_info(struct gve_priv *priv) +{ + int i; + + if (!priv->tx_cfg.num_xdp_queues || !priv->rx) + return; + + for (i = 0; i < priv->rx_cfg.num_queues; i++) { + struct gve_rx_ring *rx = &priv->rx[i]; + + if (xdp_rxq_info_is_reg(&rx->xdp_rxq)) + xdp_rxq_info_unreg(&rx->xdp_rxq); + + gve_unreg_xsk_pool(priv, i); + } +} + +static struct xsk_buff_pool *gve_get_xsk_pool(struct gve_priv *priv, int qid) +{ + if (!test_bit(qid, priv->xsk_pools)) + return NULL; + + return xsk_get_pool_from_qid(priv->dev, qid); +} + static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) { struct napi_struct *napi; struct gve_rx_ring *rx; int err = 0; - int i, j; - u32 tx_qid; + int i; if (!priv->tx_cfg.num_xdp_queues) return 0; for (i = 0; i < priv->rx_cfg.num_queues; i++) { + struct xsk_buff_pool *xsk_pool; + rx = &priv->rx[i]; napi = &priv->ntfy_blocks[rx->ntfy_id].napi; @@ -1177,7 +1250,11 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) napi->napi_id); if (err) goto err; - if (gve_is_qpl(priv)) + + xsk_pool = gve_get_xsk_pool(priv, i); + if (xsk_pool) + err = gve_reg_xsk_pool(priv, dev, xsk_pool, i); + else if (gve_is_qpl(priv)) err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); @@ -1187,60 +1264,14 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev) rx->dqo.page_pool); if (err) goto err; - rx->xsk_pool = xsk_get_pool_from_qid(dev, i); - if (rx->xsk_pool) { - err = xdp_rxq_info_reg(&rx->xsk_rxq, dev, i, - napi->napi_id); - if (err) - goto err; - err = xdp_rxq_info_reg_mem_model(&rx->xsk_rxq, - MEM_TYPE_XSK_BUFF_POOL, NULL); - if (err) - goto err; - xsk_pool_set_rxq_info(rx->xsk_pool, - &rx->xsk_rxq); - } - } - - for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) { - tx_qid = gve_xdp_tx_queue_id(priv, i); - priv->tx[tx_qid].xsk_pool = xsk_get_pool_from_qid(dev, i); } return 0; err: - for (j = i; j >= 0; j--) { - rx = &priv->rx[j]; - if (xdp_rxq_info_is_reg(&rx->xdp_rxq)) - xdp_rxq_info_unreg(&rx->xdp_rxq); - if (xdp_rxq_info_is_reg(&rx->xsk_rxq)) - xdp_rxq_info_unreg(&rx->xsk_rxq); - } + gve_unreg_xdp_info(priv); return err; } -static void gve_unreg_xdp_info(struct gve_priv *priv) -{ - int i, tx_qid; - - if (!priv->tx_cfg.num_xdp_queues || !priv->rx || !priv->tx) - return; - - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - struct gve_rx_ring *rx = &priv->rx[i]; - - xdp_rxq_info_unreg(&rx->xdp_rxq); - if (rx->xsk_pool) { - xdp_rxq_info_unreg(&rx->xsk_rxq); - rx->xsk_pool = NULL; - } - } - - for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) { - tx_qid = gve_xdp_tx_queue_id(priv, i); - priv->tx[tx_qid].xsk_pool = NULL; - } -} static void gve_drain_page_cache(struct gve_priv *priv) { @@ -1555,9 +1586,6 @@ static int gve_xsk_pool_enable(struct net_device *dev, u16 qid) { struct gve_priv *priv = netdev_priv(dev); - struct napi_struct *napi; - struct gve_rx_ring *rx; - int tx_qid; int err; if (qid >= priv->rx_cfg.num_queues) { @@ -1575,34 +1603,31 @@ static int gve_xsk_pool_enable(struct net_device *dev, if (err) return err; + set_bit(qid, priv->xsk_pools); + /* If XDP prog is not installed or interface is down, return. */ if (!priv->xdp_prog || !netif_running(dev)) return 0; - rx = &priv->rx[qid]; - napi = &priv->ntfy_blocks[rx->ntfy_id].napi; - err = xdp_rxq_info_reg(&rx->xsk_rxq, dev, qid, napi->napi_id); - if (err) - goto err; - - err = xdp_rxq_info_reg_mem_model(&rx->xsk_rxq, - MEM_TYPE_XSK_BUFF_POOL, NULL); + err = gve_reg_xsk_pool(priv, dev, pool, qid); if (err) - goto err; - - xsk_pool_set_rxq_info(pool, &rx->xsk_rxq); - rx->xsk_pool = pool; - - tx_qid = gve_xdp_tx_queue_id(priv, qid); - priv->tx[tx_qid].xsk_pool = pool; + goto err_xsk_pool_dma_mapped; + /* Stop and start RDA queues to repost buffers. */ + if (!gve_is_qpl(priv)) { + err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues); + if (err) + goto err_xsk_pool_registered; + } return 0; -err: - if (xdp_rxq_info_is_reg(&rx->xsk_rxq)) - xdp_rxq_info_unreg(&rx->xsk_rxq); +err_xsk_pool_registered: + gve_unreg_xsk_pool(priv, qid); +err_xsk_pool_dma_mapped: + clear_bit(qid, priv->xsk_pools); xsk_pool_dma_unmap(pool, - DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); + DMA_ATTR_SKIP_CPU_SYNC | + DMA_ATTR_WEAK_ORDERING); return err; } @@ -1614,18 +1639,28 @@ static int gve_xsk_pool_disable(struct net_device *dev, struct napi_struct *napi_tx; struct xsk_buff_pool *pool; int tx_qid; + int err; - pool = xsk_get_pool_from_qid(dev, qid); - if (!pool) - return -EINVAL; if (qid >= priv->rx_cfg.num_queues) return -EINVAL; - /* If XDP prog is not installed or interface is down, unmap DMA and - * return. - */ - if (!priv->xdp_prog || !netif_running(dev)) - goto done; + clear_bit(qid, priv->xsk_pools); + + pool = xsk_get_pool_from_qid(dev, qid); + if (pool) + xsk_pool_dma_unmap(pool, + DMA_ATTR_SKIP_CPU_SYNC | + DMA_ATTR_WEAK_ORDERING); + + if (!netif_running(dev) || !priv->tx_cfg.num_xdp_queues) + return 0; + + /* Stop and start RDA queues to repost buffers. */ + if (!gve_is_qpl(priv) && priv->xdp_prog) { + err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues); + if (err) + return err; + } napi_rx = &priv->ntfy_blocks[priv->rx[qid].ntfy_id].napi; napi_disable(napi_rx); /* make sure current rx poll is done */ @@ -1634,22 +1669,19 @@ static int gve_xsk_pool_disable(struct net_device *dev, napi_tx = &priv->ntfy_blocks[priv->tx[tx_qid].ntfy_id].napi; napi_disable(napi_tx); /* make sure current tx poll is done */ - priv->rx[qid].xsk_pool = NULL; - xdp_rxq_info_unreg(&priv->rx[qid].xsk_rxq); - priv->tx[tx_qid].xsk_pool = NULL; + gve_unreg_xsk_pool(priv, qid); smp_mb(); /* Make sure it is visible to the workers on datapath */ napi_enable(napi_rx); - if (gve_rx_work_pending(&priv->rx[qid])) - napi_schedule(napi_rx); - napi_enable(napi_tx); - if (gve_tx_clean_pending(priv, &priv->tx[tx_qid])) - napi_schedule(napi_tx); + if (gve_is_gqi(priv)) { + if (gve_rx_work_pending(&priv->rx[qid])) + napi_schedule(napi_rx); + + if (gve_tx_clean_pending(priv, &priv->tx[tx_qid])) + napi_schedule(napi_tx); + } -done: - xsk_pool_dma_unmap(pool, - DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING); return 0; } @@ -1956,49 +1988,56 @@ static void gve_turnup_and_check_status(struct gve_priv *priv) gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status); } -static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) +static struct gve_notify_block *gve_get_tx_notify_block(struct gve_priv *priv, + unsigned int txqueue) { - struct gve_notify_block *block; - struct gve_tx_ring *tx = NULL; - struct gve_priv *priv; - u32 last_nic_done; - u32 current_time; u32 ntfy_idx; - netdev_info(dev, "Timeout on tx queue, %d", txqueue); - priv = netdev_priv(dev); if (txqueue > priv->tx_cfg.num_queues) - goto reset; + return NULL; ntfy_idx = gve_tx_idx_to_ntfy(priv, txqueue); if (ntfy_idx >= priv->num_ntfy_blks) - goto reset; + return NULL; + + return &priv->ntfy_blocks[ntfy_idx]; +} + +static bool gve_tx_timeout_try_q_kick(struct gve_priv *priv, + unsigned int txqueue) +{ + struct gve_notify_block *block; + u32 current_time; - block = &priv->ntfy_blocks[ntfy_idx]; - tx = block->tx; + block = gve_get_tx_notify_block(priv, txqueue); + + if (!block) + return false; current_time = jiffies_to_msecs(jiffies); - if (tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) - goto reset; + if (block->tx->last_kick_msec + MIN_TX_TIMEOUT_GAP > current_time) + return false; - /* Check to see if there are missed completions, which will allow us to - * kick the queue. - */ - last_nic_done = gve_tx_load_event_counter(priv, tx); - if (last_nic_done - tx->done) { - netdev_info(dev, "Kicking queue %d", txqueue); - iowrite32be(GVE_IRQ_MASK, gve_irq_doorbell(priv, block)); - napi_schedule(&block->napi); - tx->last_kick_msec = current_time; - goto out; - } // Else reset. + netdev_info(priv->dev, "Kicking queue %d", txqueue); + napi_schedule(&block->napi); + block->tx->last_kick_msec = current_time; + return true; +} -reset: - gve_schedule_reset(priv); +static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) +{ + struct gve_notify_block *block; + struct gve_priv *priv; -out: - if (tx) - tx->queue_timeout++; + netdev_info(dev, "Timeout on tx queue, %d", txqueue); + priv = netdev_priv(dev); + + if (!gve_tx_timeout_try_q_kick(priv, txqueue)) + gve_schedule_reset(priv); + + block = gve_get_tx_notify_block(priv, txqueue); + if (block) + block->tx->queue_timeout++; priv->tx_timeo_cnt++; } @@ -2275,6 +2314,7 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv) } else if (priv->queue_format == GVE_DQO_RDA_FORMAT) { xdp_features = NETDEV_XDP_ACT_BASIC; xdp_features |= NETDEV_XDP_ACT_REDIRECT; + xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { xdp_features = 0; } @@ -2370,10 +2410,22 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) priv->ts_config.rx_filter = HWTSTAMP_FILTER_NONE; setup_device: + priv->xsk_pools = bitmap_zalloc(priv->rx_cfg.max_queues, GFP_KERNEL); + if (!priv->xsk_pools) { + err = -ENOMEM; + goto err; + } + gve_set_netdev_xdp_features(priv); err = gve_setup_device_resources(priv); - if (!err) - return 0; + if (err) + goto err_free_xsk_bitmap; + + return 0; + +err_free_xsk_bitmap: + bitmap_free(priv->xsk_pools); + priv->xsk_pools = NULL; err: gve_adminq_free(&priv->pdev->dev, priv); return err; @@ -2383,6 +2435,8 @@ static void gve_teardown_priv_resources(struct gve_priv *priv) { gve_teardown_device_resources(priv); gve_adminq_free(&priv->pdev->dev, priv); + bitmap_free(priv->xsk_pools); + priv->xsk_pools = NULL; } static void gve_trigger_reset(struct gve_priv *priv) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index afaa822b1227..7380c2b7a2d8 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -16,6 +16,7 @@ #include <net/ip6_checksum.h> #include <net/ipv6.h> #include <net/tcp.h> +#include <net/xdp_sock_drv.h> static void gve_rx_free_hdr_bufs(struct gve_priv *priv, struct gve_rx_ring *rx) { @@ -149,6 +150,10 @@ void gve_rx_free_ring_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, gve_free_to_page_pool(rx, bs, false); else gve_free_qpl_page_dqo(bs); + if (gve_buf_state_is_allocated(rx, bs) && bs->xsk_buff) { + xsk_buff_free(bs->xsk_buff); + bs->xsk_buff = NULL; + } } if (rx->dqo.qpl) { @@ -580,8 +585,11 @@ static int gve_xdp_tx_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, int err; xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) + if (unlikely(!xdpf)) { + if (rx->xsk_pool) + xsk_buff_free(xdp); return -ENOSPC; + } tx_qid = gve_xdp_tx_queue_id(priv, rx->q_num); tx = &priv->tx[tx_qid]; @@ -592,6 +600,41 @@ static int gve_xdp_tx_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, return err; } +static void gve_xsk_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, + struct xdp_buff *xdp, struct bpf_prog *xprog, + int xdp_act) +{ + switch (xdp_act) { + case XDP_ABORTED: + case XDP_DROP: + default: + xsk_buff_free(xdp); + break; + case XDP_TX: + if (unlikely(gve_xdp_tx_dqo(priv, rx, xdp))) + goto err; + break; + case XDP_REDIRECT: + if (unlikely(xdp_do_redirect(priv->dev, xdp, xprog))) + goto err; + break; + } + + u64_stats_update_begin(&rx->statss); + if ((u32)xdp_act < GVE_XDP_ACTIONS) + rx->xdp_actions[xdp_act]++; + u64_stats_update_end(&rx->statss); + return; + +err: + u64_stats_update_begin(&rx->statss); + if (xdp_act == XDP_TX) + rx->xdp_tx_errors++; + if (xdp_act == XDP_REDIRECT) + rx->xdp_redirect_errors++; + u64_stats_update_end(&rx->statss); +} + static void gve_xdp_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, struct xdp_buff *xdp, struct bpf_prog *xprog, int xdp_act, @@ -633,6 +676,48 @@ err: return; } +static int gve_rx_xsk_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, + struct gve_rx_buf_state_dqo *buf_state, int buf_len, + struct bpf_prog *xprog) +{ + struct xdp_buff *xdp = buf_state->xsk_buff; + struct gve_priv *priv = rx->gve; + int xdp_act; + + xdp->data_end = xdp->data + buf_len; + xsk_buff_dma_sync_for_cpu(xdp); + + if (xprog) { + xdp_act = bpf_prog_run_xdp(xprog, xdp); + buf_len = xdp->data_end - xdp->data; + if (xdp_act != XDP_PASS) { + gve_xsk_done_dqo(priv, rx, xdp, xprog, xdp_act); + gve_free_buf_state(rx, buf_state); + return 0; + } + } + + /* Copy the data to skb */ + rx->ctx.skb_head = gve_rx_copy_data(priv->dev, napi, + xdp->data, buf_len); + if (unlikely(!rx->ctx.skb_head)) { + xsk_buff_free(xdp); + gve_free_buf_state(rx, buf_state); + return -ENOMEM; + } + rx->ctx.skb_tail = rx->ctx.skb_head; + + /* Free XSK buffer and Buffer state */ + xsk_buff_free(xdp); + gve_free_buf_state(rx, buf_state); + + /* Update Stats */ + u64_stats_update_begin(&rx->statss); + rx->xdp_actions[XDP_PASS]++; + u64_stats_update_end(&rx->statss); + return 0; +} + /* Returns 0 if descriptor is completed successfully. * Returns -EINVAL if descriptor is invalid. * Returns -ENOMEM if data cannot be copied to skb. @@ -671,7 +756,11 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, buf_len = compl_desc->packet_len; hdr_len = compl_desc->header_len; - /* Page might have not been used for a while and was likely last written + xprog = READ_ONCE(priv->xdp_prog); + if (buf_state->xsk_buff) + return gve_rx_xsk_dqo(napi, rx, buf_state, buf_len, xprog); + + /* Page might have not been used for awhile and was likely last written * by a different thread. */ if (rx->dqo.page_pool) { @@ -721,7 +810,6 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, return 0; } - xprog = READ_ONCE(priv->xdp_prog); if (xprog) { struct xdp_buff xdp; void *old_data; diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c index ce5370b741ec..6f1d515673d2 100644 --- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c @@ -13,6 +13,7 @@ #include <linux/tcp.h> #include <linux/slab.h> #include <linux/skbuff.h> +#include <net/xdp_sock_drv.h> /* Returns true if tx_bufs are available. */ static bool gve_has_free_tx_qpl_bufs(struct gve_tx_ring *tx, int count) @@ -241,6 +242,9 @@ static void gve_tx_free_ring_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, tx->dqo.tx_ring = NULL; } + kvfree(tx->dqo.xsk_reorder_queue); + tx->dqo.xsk_reorder_queue = NULL; + kvfree(tx->dqo.pending_packets); tx->dqo.pending_packets = NULL; @@ -345,6 +349,17 @@ static int gve_tx_alloc_ring_dqo(struct gve_priv *priv, tx->dqo.pending_packets[tx->dqo.num_pending_packets - 1].next = -1; atomic_set_release(&tx->dqo_compl.free_pending_packets, -1); + + /* Only alloc xsk pool for XDP queues */ + if (idx >= cfg->qcfg->num_queues && cfg->num_xdp_rings) { + tx->dqo.xsk_reorder_queue = + kvcalloc(tx->dqo.complq_mask + 1, + sizeof(tx->dqo.xsk_reorder_queue[0]), + GFP_KERNEL); + if (!tx->dqo.xsk_reorder_queue) + goto err; + } + tx->dqo_compl.miss_completions.head = -1; tx->dqo_compl.miss_completions.tail = -1; tx->dqo_compl.timed_out_completions.head = -1; @@ -992,6 +1007,38 @@ drop: return 0; } +static void gve_xsk_reorder_queue_push_dqo(struct gve_tx_ring *tx, + u16 completion_tag) +{ + u32 tail = atomic_read(&tx->dqo_tx.xsk_reorder_queue_tail); + + tx->dqo.xsk_reorder_queue[tail] = completion_tag; + tail = (tail + 1) & tx->dqo.complq_mask; + atomic_set_release(&tx->dqo_tx.xsk_reorder_queue_tail, tail); +} + +static struct gve_tx_pending_packet_dqo * +gve_xsk_reorder_queue_head(struct gve_tx_ring *tx) +{ + u32 head = tx->dqo_compl.xsk_reorder_queue_head; + + if (head == tx->dqo_compl.xsk_reorder_queue_tail) { + tx->dqo_compl.xsk_reorder_queue_tail = + atomic_read_acquire(&tx->dqo_tx.xsk_reorder_queue_tail); + + if (head == tx->dqo_compl.xsk_reorder_queue_tail) + return NULL; + } + + return &tx->dqo.pending_packets[tx->dqo.xsk_reorder_queue[head]]; +} + +static void gve_xsk_reorder_queue_pop_dqo(struct gve_tx_ring *tx) +{ + tx->dqo_compl.xsk_reorder_queue_head++; + tx->dqo_compl.xsk_reorder_queue_head &= tx->dqo.complq_mask; +} + /* Transmit a given skb and ring the doorbell. */ netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev) { @@ -1015,6 +1062,62 @@ netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } +static bool gve_xsk_tx_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, + int budget) +{ + struct xsk_buff_pool *pool = tx->xsk_pool; + struct xdp_desc desc; + bool repoll = false; + int sent = 0; + + spin_lock(&tx->dqo_tx.xdp_lock); + for (; sent < budget; sent++) { + struct gve_tx_pending_packet_dqo *pkt; + s16 completion_tag; + dma_addr_t addr; + u32 desc_idx; + + if (unlikely(!gve_has_avail_slots_tx_dqo(tx, 1, 1))) { + repoll = true; + break; + } + + if (!xsk_tx_peek_desc(pool, &desc)) + break; + + pkt = gve_alloc_pending_packet(tx); + pkt->type = GVE_TX_PENDING_PACKET_DQO_XSK; + pkt->num_bufs = 0; + completion_tag = pkt - tx->dqo.pending_packets; + + addr = xsk_buff_raw_get_dma(pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(pool, addr, desc.len); + + desc_idx = tx->dqo_tx.tail; + gve_tx_fill_pkt_desc_dqo(tx, &desc_idx, + true, desc.len, + addr, completion_tag, true, + false); + ++pkt->num_bufs; + gve_tx_update_tail(tx, desc_idx); + tx->dqo_tx.posted_packet_desc_cnt += pkt->num_bufs; + gve_xsk_reorder_queue_push_dqo(tx, completion_tag); + } + + if (sent) { + gve_tx_put_doorbell_dqo(priv, tx->q_resources, tx->dqo_tx.tail); + xsk_tx_release(pool); + } + + spin_unlock(&tx->dqo_tx.xdp_lock); + + u64_stats_update_begin(&tx->statss); + tx->xdp_xsk_sent += sent; + u64_stats_update_end(&tx->statss); + + return (sent == budget) || repoll; +} + static void add_to_list(struct gve_tx_ring *tx, struct gve_index_list *list, struct gve_tx_pending_packet_dqo *pending_packet) { @@ -1152,6 +1255,9 @@ static void gve_handle_packet_completion(struct gve_priv *priv, pending_packet->xdpf = NULL; gve_free_pending_packet(tx, pending_packet); break; + case GVE_TX_PENDING_PACKET_DQO_XSK: + pending_packet->state = GVE_PACKET_STATE_XSK_COMPLETE; + break; default: WARN_ON_ONCE(1); } @@ -1251,8 +1357,34 @@ static void remove_timed_out_completions(struct gve_priv *priv, remove_from_list(tx, &tx->dqo_compl.timed_out_completions, pending_packet); + + /* Need to count XSK packets in xsk_tx_completed. */ + if (pending_packet->type == GVE_TX_PENDING_PACKET_DQO_XSK) + pending_packet->state = GVE_PACKET_STATE_XSK_COMPLETE; + else + gve_free_pending_packet(tx, pending_packet); + } +} + +static void gve_tx_process_xsk_completions(struct gve_tx_ring *tx) +{ + u32 num_xsks = 0; + + while (true) { + struct gve_tx_pending_packet_dqo *pending_packet = + gve_xsk_reorder_queue_head(tx); + + if (!pending_packet || + pending_packet->state != GVE_PACKET_STATE_XSK_COMPLETE) + break; + + num_xsks++; + gve_xsk_reorder_queue_pop_dqo(tx); gve_free_pending_packet(tx, pending_packet); } + + if (num_xsks) + xsk_tx_completed(tx->xsk_pool, num_xsks); } int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, @@ -1333,6 +1465,9 @@ int gve_clean_tx_done_dqo(struct gve_priv *priv, struct gve_tx_ring *tx, remove_miss_completions(priv, tx); remove_timed_out_completions(priv, tx); + if (tx->xsk_pool) + gve_tx_process_xsk_completions(tx); + u64_stats_update_begin(&tx->statss); tx->bytes_done += pkt_compl_bytes + reinject_compl_bytes; tx->pkt_done += pkt_compl_pkts + reinject_compl_pkts; @@ -1365,6 +1500,19 @@ bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean) return compl_desc->generation != tx->dqo_compl.cur_gen_bit; } +bool gve_xsk_tx_poll_dqo(struct gve_notify_block *rx_block, int budget) +{ + struct gve_rx_ring *rx = rx_block->rx; + struct gve_priv *priv = rx->gve; + struct gve_tx_ring *tx; + + tx = &priv->tx[gve_xdp_tx_queue_id(priv, rx->q_num)]; + if (tx->xsk_pool) + return gve_xsk_tx_dqo(priv, tx, budget); + + return 0; +} + bool gve_xdp_poll_dqo(struct gve_notify_block *block) { struct gve_tx_compl_desc *compl_desc; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 52f42fe1d56f..dd3ddb223a92 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -11,6 +11,7 @@ #include <linux/irq.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <linux/iommu.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/skbuff.h> @@ -1039,6 +1040,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring, static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) { u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size; + struct net_device *netdev = ring_to_netdev(ring); + struct hns3_nic_priv *priv = netdev_priv(netdev); struct hns3_tx_spare *tx_spare; struct page *page; dma_addr_t dma; @@ -1080,6 +1083,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) tx_spare->buf = page_address(page); tx_spare->len = PAGE_SIZE << order; ring->tx_spare = tx_spare; + ring->tx_copybreak = priv->tx_copybreak; return; dma_mapping_error: @@ -4874,6 +4878,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv) devm_kfree(&pdev->dev, priv->tqp_vector); } +static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv) +{ +#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024) +#define HNS3_MAX_PACKET_SIZE (64 * 1024) + + struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev); + struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle); + struct hnae3_handle *handle = priv->ae_handle; + + if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) + return; + + if (!(domain && iommu_is_dma_domain(domain))) + return; + + priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE; + priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE; + + if (priv->tx_copybreak < priv->min_tx_copybreak) + priv->tx_copybreak = priv->min_tx_copybreak; + if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size) + handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size; +} + static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, unsigned int ring_type) { @@ -5107,6 +5135,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv) int i, j; int ret; + hns3_update_tx_spare_buf_config(priv); for (i = 0; i < ring_num; i++) { ret = hns3_alloc_ring_memory(&priv->ring[i]); if (ret) { @@ -5313,6 +5342,8 @@ static int hns3_client_init(struct hnae3_handle *handle) priv->ae_handle = handle; priv->tx_timeout_count = 0; priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num; + priv->min_tx_copybreak = 0; + priv->min_tx_spare_buf_size = 0; set_bit(HNS3_NIC_STATE_DOWN, &priv->state); handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index d3bad5d1b888..933e3527ed82 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -596,6 +596,8 @@ struct hns3_nic_priv { struct hns3_enet_coalesce rx_coal; u32 tx_copybreak; u32 rx_copybreak; + u32 min_tx_copybreak; + u32 min_tx_spare_buf_size; }; union l3_hdr_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index d3c71bc1855d..be917e4a8372 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9576,33 +9576,36 @@ static bool hclge_need_enable_vport_vlan_filter(struct hclge_vport *vport) return false; } -int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en) +static int __hclge_enable_vport_vlan_filter(struct hclge_vport *vport, + bool request_en) { - struct hclge_dev *hdev = vport->back; bool need_en; int ret; - mutex_lock(&hdev->vport_lock); - - vport->req_vlan_fltr_en = request_en; - need_en = hclge_need_enable_vport_vlan_filter(vport); - if (need_en == vport->cur_vlan_fltr_en) { - mutex_unlock(&hdev->vport_lock); + if (need_en == vport->cur_vlan_fltr_en) return 0; - } ret = hclge_set_vport_vlan_filter(vport, need_en); - if (ret) { - mutex_unlock(&hdev->vport_lock); + if (ret) return ret; - } vport->cur_vlan_fltr_en = need_en; + return 0; +} + +int hclge_enable_vport_vlan_filter(struct hclge_vport *vport, bool request_en) +{ + struct hclge_dev *hdev = vport->back; + int ret; + + mutex_lock(&hdev->vport_lock); + vport->req_vlan_fltr_en = request_en; + ret = __hclge_enable_vport_vlan_filter(vport, request_en); mutex_unlock(&hdev->vport_lock); - return 0; + return ret; } static int hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) @@ -10623,16 +10626,19 @@ static void hclge_sync_vlan_fltr_state(struct hclge_dev *hdev) &vport->state)) continue; - ret = hclge_enable_vport_vlan_filter(vport, - vport->req_vlan_fltr_en); + mutex_lock(&hdev->vport_lock); + ret = __hclge_enable_vport_vlan_filter(vport, + vport->req_vlan_fltr_en); if (ret) { dev_err(&hdev->pdev->dev, "failed to sync vlan filter state for vport%u, ret = %d\n", vport->vport_id, ret); set_bit(HCLGE_VPORT_STATE_VLAN_FLTR_CHANGE, &vport->state); + mutex_unlock(&hdev->vport_lock); return; } + mutex_unlock(&hdev->vport_lock); } } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index ec581d4b696f..4bd52eab3914 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -497,14 +497,14 @@ int hclge_ptp_init(struct hclge_dev *hdev) if (ret) { dev_err(&hdev->pdev->dev, "failed to init freq, ret = %d\n", ret); - goto out; + goto out_clear_int; } ret = hclge_ptp_set_ts_mode(hdev, &hdev->ptp->ts_cfg); if (ret) { dev_err(&hdev->pdev->dev, "failed to init ts mode, ret = %d\n", ret); - goto out; + goto out_clear_int; } ktime_get_real_ts64(&ts); @@ -512,7 +512,7 @@ int hclge_ptp_init(struct hclge_dev *hdev) if (ret) { dev_err(&hdev->pdev->dev, "failed to init ts time, ret = %d\n", ret); - goto out; + goto out_clear_int; } set_bit(HCLGE_STATE_PTP_EN, &hdev->state); @@ -520,6 +520,9 @@ int hclge_ptp_init(struct hclge_dev *hdev) return 0; +out_clear_int: + clear_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags); + hclge_ptp_int_en(hdev, false); out: hclge_ptp_destroy_clock(hdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 33136a1e02cf..8fcf220a120d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3094,11 +3094,7 @@ static void hclgevf_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) static u32 hclgevf_get_max_channels(struct hclgevf_dev *hdev) { - struct hnae3_handle *nic = &hdev->nic; - struct hnae3_knic_private_info *kinfo = &nic->kinfo; - - return min_t(u32, hdev->rss_size_max, - hdev->num_tqps / kinfo->tc_info.num_tc); + return min(hdev->rss_size_max, hdev->num_tqps); } /** diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 24046fe16634..6f0821f1e798 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -211,98 +211,169 @@ static inline void ibmveth_flush_buffer(void *addr, unsigned long length) static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struct ibmveth_buff_pool *pool) { - u32 i; - u32 count = pool->size - atomic_read(&pool->available); - u32 buffers_added = 0; - struct sk_buff *skb; - unsigned int free_index, index; - u64 correlator; + union ibmveth_buf_desc descs[IBMVETH_MAX_RX_PER_HCALL] = {0}; + u32 remaining = pool->size - atomic_read(&pool->available); + u64 correlators[IBMVETH_MAX_RX_PER_HCALL] = {0}; unsigned long lpar_rc; + u32 buffers_added = 0; + u32 i, filled, batch; + struct vio_dev *vdev; dma_addr_t dma_addr; + struct device *dev; + u32 index; + + vdev = adapter->vdev; + dev = &vdev->dev; mb(); - for (i = 0; i < count; ++i) { - union ibmveth_buf_desc desc; + batch = adapter->rx_buffers_per_hcall; - free_index = pool->consumer_index; - index = pool->free_map[free_index]; - skb = NULL; + while (remaining > 0) { + unsigned int free_index = pool->consumer_index; - if (WARN_ON(index == IBM_VETH_INVALID_MAP)) { - schedule_work(&adapter->work); - goto bad_index_failure; - } + /* Fill a batch of descriptors */ + for (filled = 0; filled < min(remaining, batch); filled++) { + index = pool->free_map[free_index]; + if (WARN_ON(index == IBM_VETH_INVALID_MAP)) { + adapter->replenish_add_buff_failure++; + netdev_info(adapter->netdev, + "Invalid map index %u, reset\n", + index); + schedule_work(&adapter->work); + break; + } + + if (!pool->skbuff[index]) { + struct sk_buff *skb = NULL; - /* are we allocating a new buffer or recycling an old one */ - if (pool->skbuff[index]) - goto reuse; + skb = netdev_alloc_skb(adapter->netdev, + pool->buff_size); + if (!skb) { + adapter->replenish_no_mem++; + adapter->replenish_add_buff_failure++; + break; + } + + dma_addr = dma_map_single(dev, skb->data, + pool->buff_size, + DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + dev_kfree_skb_any(skb); + adapter->replenish_add_buff_failure++; + break; + } - skb = netdev_alloc_skb(adapter->netdev, pool->buff_size); + pool->dma_addr[index] = dma_addr; + pool->skbuff[index] = skb; + } else { + /* re-use case */ + dma_addr = pool->dma_addr[index]; + } - if (!skb) { - netdev_dbg(adapter->netdev, - "replenish: unable to allocate skb\n"); - adapter->replenish_no_mem++; - break; - } + if (rx_flush) { + unsigned int len; - dma_addr = dma_map_single(&adapter->vdev->dev, skb->data, - pool->buff_size, DMA_FROM_DEVICE); + len = adapter->netdev->mtu + IBMVETH_BUFF_OH; + len = min(pool->buff_size, len); + ibmveth_flush_buffer(pool->skbuff[index]->data, + len); + } - if (dma_mapping_error(&adapter->vdev->dev, dma_addr)) - goto failure; + descs[filled].fields.flags_len = IBMVETH_BUF_VALID | + pool->buff_size; + descs[filled].fields.address = dma_addr; - pool->dma_addr[index] = dma_addr; - pool->skbuff[index] = skb; + correlators[filled] = ((u64)pool->index << 32) | index; + *(u64 *)pool->skbuff[index]->data = correlators[filled]; - if (rx_flush) { - unsigned int len = min(pool->buff_size, - adapter->netdev->mtu + - IBMVETH_BUFF_OH); - ibmveth_flush_buffer(skb->data, len); + free_index++; + if (free_index >= pool->size) + free_index = 0; } -reuse: - dma_addr = pool->dma_addr[index]; - desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size; - desc.fields.address = dma_addr; - - correlator = ((u64)pool->index << 32) | index; - *(u64 *)pool->skbuff[index]->data = correlator; - lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, - desc.desc); + if (!filled) + break; + /* single buffer case*/ + if (filled == 1) + lpar_rc = h_add_logical_lan_buffer(vdev->unit_address, + descs[0].desc); + else + /* Multi-buffer hcall */ + lpar_rc = h_add_logical_lan_buffers(vdev->unit_address, + descs[0].desc, + descs[1].desc, + descs[2].desc, + descs[3].desc, + descs[4].desc, + descs[5].desc, + descs[6].desc, + descs[7].desc); if (lpar_rc != H_SUCCESS) { - netdev_warn(adapter->netdev, - "%sadd_logical_lan failed %lu\n", - skb ? "" : "When recycling: ", lpar_rc); - goto failure; + dev_warn_ratelimited(dev, + "RX h_add_logical_lan failed: filled=%u, rc=%lu, batch=%u\n", + filled, lpar_rc, batch); + goto hcall_failure; } - pool->free_map[free_index] = IBM_VETH_INVALID_MAP; - pool->consumer_index++; - if (pool->consumer_index >= pool->size) - pool->consumer_index = 0; + /* Only update pool state after hcall succeeds */ + for (i = 0; i < filled; i++) { + free_index = pool->consumer_index; + pool->free_map[free_index] = IBM_VETH_INVALID_MAP; - buffers_added++; - adapter->replenish_add_buff_success++; - } + pool->consumer_index++; + if (pool->consumer_index >= pool->size) + pool->consumer_index = 0; + } - mb(); - atomic_add(buffers_added, &(pool->available)); - return; + buffers_added += filled; + adapter->replenish_add_buff_success += filled; + remaining -= filled; -failure: + memset(&descs, 0, sizeof(descs)); + memset(&correlators, 0, sizeof(correlators)); + continue; - if (dma_addr && !dma_mapping_error(&adapter->vdev->dev, dma_addr)) - dma_unmap_single(&adapter->vdev->dev, - pool->dma_addr[index], pool->buff_size, - DMA_FROM_DEVICE); - dev_kfree_skb_any(pool->skbuff[index]); - pool->skbuff[index] = NULL; -bad_index_failure: - adapter->replenish_add_buff_failure++; +hcall_failure: + for (i = 0; i < filled; i++) { + index = correlators[i] & 0xffffffffUL; + dma_addr = pool->dma_addr[index]; + + if (pool->skbuff[index]) { + if (dma_addr && + !dma_mapping_error(dev, dma_addr)) + dma_unmap_single(dev, dma_addr, + pool->buff_size, + DMA_FROM_DEVICE); + + dev_kfree_skb_any(pool->skbuff[index]); + pool->skbuff[index] = NULL; + } + } + adapter->replenish_add_buff_failure += filled; + + /* + * If multi rx buffers hcall is no longer supported by FW + * e.g. in the case of Live Parttion Migration + */ + if (batch > 1 && lpar_rc == H_FUNCTION) { + /* + * Instead of retry submit single buffer individually + * here just set the max rx buffer per hcall to 1 + * buffers will be respleshed next time + * when ibmveth_replenish_buffer_pool() is called again + * with single-buffer case + */ + netdev_info(adapter->netdev, + "RX Multi buffers not supported by FW, rc=%lu\n", + lpar_rc); + adapter->rx_buffers_per_hcall = 1; + netdev_info(adapter->netdev, + "Next rx replesh will fall back to single-buffer hcall\n"); + } + break; + } mb(); atomic_add(buffers_added, &(pool->available)); @@ -1783,6 +1854,19 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) netdev->features |= NETIF_F_FRAGLIST; } + if (ret == H_SUCCESS && + (ret_attr & IBMVETH_ILLAN_RX_MULTI_BUFF_SUPPORT)) { + adapter->rx_buffers_per_hcall = IBMVETH_MAX_RX_PER_HCALL; + netdev_dbg(netdev, + "RX Multi-buffer hcall supported by FW, batch set to %u\n", + adapter->rx_buffers_per_hcall); + } else { + adapter->rx_buffers_per_hcall = 1; + netdev_dbg(netdev, + "RX Single-buffer hcall mode, batch set to %u\n", + adapter->rx_buffers_per_hcall); + } + netdev->min_mtu = IBMVETH_MIN_MTU; netdev->max_mtu = ETH_MAX_MTU - IBMVETH_BUFF_OH; diff --git a/drivers/net/ethernet/ibm/ibmveth.h b/drivers/net/ethernet/ibm/ibmveth.h index b0a2460ec9f9..068f99df133e 100644 --- a/drivers/net/ethernet/ibm/ibmveth.h +++ b/drivers/net/ethernet/ibm/ibmveth.h @@ -28,6 +28,7 @@ #define IbmVethMcastRemoveFilter 0x2UL #define IbmVethMcastClearFilterTable 0x3UL +#define IBMVETH_ILLAN_RX_MULTI_BUFF_SUPPORT 0x0000000000040000UL #define IBMVETH_ILLAN_LRG_SR_ENABLED 0x0000000000010000UL #define IBMVETH_ILLAN_LRG_SND_SUPPORT 0x0000000000008000UL #define IBMVETH_ILLAN_PADDED_PKT_CSUM 0x0000000000002000UL @@ -46,6 +47,24 @@ #define h_add_logical_lan_buffer(ua, buf) \ plpar_hcall_norets(H_ADD_LOGICAL_LAN_BUFFER, ua, buf) +static inline long h_add_logical_lan_buffers(unsigned long unit_address, + unsigned long desc1, + unsigned long desc2, + unsigned long desc3, + unsigned long desc4, + unsigned long desc5, + unsigned long desc6, + unsigned long desc7, + unsigned long desc8) +{ + unsigned long retbuf[PLPAR_HCALL9_BUFSIZE]; + + return plpar_hcall9(H_ADD_LOGICAL_LAN_BUFFERS, + retbuf, unit_address, + desc1, desc2, desc3, desc4, + desc5, desc6, desc7, desc8); +} + /* FW allows us to send 6 descriptors but we only use one so mark * the other 5 as unused (0) */ @@ -101,6 +120,7 @@ static inline long h_illan_attributes(unsigned long unit_address, #define IBMVETH_MAX_TX_BUF_SIZE (1024 * 64) #define IBMVETH_MAX_QUEUES 16U #define IBMVETH_DEFAULT_QUEUES 8U +#define IBMVETH_MAX_RX_PER_HCALL 8U static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 }; static int pool_count[] = { 256, 512, 256, 256, 256 }; @@ -151,6 +171,7 @@ struct ibmveth_adapter { int rx_csum; int large_send; bool is_active_trunk; + unsigned int rx_buffers_per_hcall; u64 fw_ipv6_csum_support; u64 fw_ipv4_csum_support; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 92647e137cf8..eec971567aac 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2312,8 +2312,6 @@ static void ibmvnic_tx_scrq_clean_buffer(struct ibmvnic_adapter *adapter, tx_pool->num_buffers - 1 : tx_pool->consumer_index - 1; tx_buff = &tx_pool->tx_buff[index]; - adapter->netdev->stats.tx_packets--; - adapter->netdev->stats.tx_bytes -= tx_buff->skb->len; adapter->tx_stats_buffers[queue_num].batched_packets--; adapter->tx_stats_buffers[queue_num].bytes -= tx_buff->skb->len; @@ -2647,9 +2645,6 @@ tx_err: } out: rcu_read_unlock(); - netdev->stats.tx_dropped += tx_dropped; - netdev->stats.tx_bytes += tx_bytes; - netdev->stats.tx_packets += tx_bpackets + tx_dpackets; adapter->tx_send_failed += tx_send_failed; adapter->tx_map_failed += tx_map_failed; adapter->tx_stats_buffers[queue_num].batched_packets += tx_bpackets; @@ -3452,6 +3447,25 @@ err: return -ret; } +static void ibmvnic_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct ibmvnic_adapter *adapter = netdev_priv(netdev); + int i; + + for (i = 0; i < adapter->req_rx_queues; i++) { + stats->rx_packets += adapter->rx_stats_buffers[i].packets; + stats->rx_bytes += adapter->rx_stats_buffers[i].bytes; + } + + for (i = 0; i < adapter->req_tx_queues; i++) { + stats->tx_packets += adapter->tx_stats_buffers[i].batched_packets; + stats->tx_packets += adapter->tx_stats_buffers[i].direct_packets; + stats->tx_bytes += adapter->tx_stats_buffers[i].bytes; + stats->tx_dropped += adapter->tx_stats_buffers[i].dropped_packets; + } +} + static void ibmvnic_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct ibmvnic_adapter *adapter = netdev_priv(dev); @@ -3567,8 +3581,6 @@ restart_poll: length = skb->len; napi_gro_receive(napi, skb); /* send it up */ - netdev->stats.rx_packets++; - netdev->stats.rx_bytes += length; adapter->rx_stats_buffers[scrq_num].packets++; adapter->rx_stats_buffers[scrq_num].bytes += length; frames_processed++; @@ -3678,6 +3690,7 @@ static const struct net_device_ops ibmvnic_netdev_ops = { .ndo_set_rx_mode = ibmvnic_set_multi, .ndo_set_mac_address = ibmvnic_set_mac, .ndo_validate_addr = eth_validate_addr, + .ndo_get_stats64 = ibmvnic_get_stats64, .ndo_tx_timeout = ibmvnic_tx_timeout, .ndo_change_mtu = ibmvnic_change_mtu, .ndo_features_check = ibmvnic_features_check, diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 8294a7c4f122..ba331899d186 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -638,6 +638,9 @@ /* For checksumming, the sum of all words in the NVM should equal 0xBABA. */ #define NVM_SUM 0xBABA +/* Uninitialized ("empty") checksum word value */ +#define NVM_CHECKSUM_UNINITIALIZED 0xFFFF + /* PBA (printed board assembly) number words */ #define NVM_PBA_OFFSET_0 8 #define NVM_PBA_OFFSET_1 9 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 364378133526..df4e7d781cb1 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -4274,6 +4274,8 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) ret_val = e1000e_update_nvm_checksum(hw); if (ret_val) return ret_val; + } else if (hw->mac.type == e1000_pch_tgp) { + return 0; } } diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c index e609f4df86f4..16369e6d245a 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.c +++ b/drivers/net/ethernet/intel/e1000e/nvm.c @@ -558,6 +558,12 @@ s32 e1000e_validate_nvm_checksum_generic(struct e1000_hw *hw) checksum += nvm_data; } + if (hw->mac.type == e1000_pch_tgp && + nvm_data == NVM_CHECKSUM_UNINITIALIZED) { + e_dbg("Uninitialized NVM Checksum on TGP platform - ignoring\n"); + return 0; + } + if (checksum != (u16)NVM_SUM) { e_dbg("NVM Checksum Invalid\n"); return -E1000_ERR_NVM; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index b232edf68ab1..1a7e9532f8e3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3138,10 +3138,10 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) const u8 *addr = al->list[i].addr; /* Allow to delete VF primary MAC only if it was not set - * administratively by PF or if VF is trusted. + * administratively by PF. */ if (ether_addr_equal(addr, vf->default_lan_addr.addr)) { - if (i40e_can_vf_change_mac(vf)) + if (!vf->pf_set_mac) was_unimac_deleted = true; else continue; @@ -5008,7 +5008,7 @@ int i40e_get_vf_stats(struct net_device *netdev, int vf_id, vf_stats->broadcast = stats->rx_broadcast; vf_stats->multicast = stats->rx_multicast; vf_stats->rx_dropped = stats->rx_discards + stats->rx_discards_other; - vf_stats->tx_dropped = stats->tx_discards; + vf_stats->tx_dropped = stats->tx_errors; return 0; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index aaf70c625655..363c42bf3dcf 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1216,7 +1216,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, unsigned int size) { struct page *buf_page = __netmem_to_page(rx_buffer->netmem); - u32 hr = buf_page->pp->p.offset; + u32 hr = pp_page_to_nmdesc(buf_page)->pp->p.offset; struct sk_buff *skb; void *va; diff --git a/drivers/net/ethernet/intel/ice/devlink/port.c b/drivers/net/ethernet/intel/ice/devlink/port.c index 767419a67fef..63fb36fc4b3d 100644 --- a/drivers/net/ethernet/intel/ice/devlink/port.c +++ b/drivers/net/ethernet/intel/ice/devlink/port.c @@ -30,6 +30,8 @@ static const char *ice_devlink_port_opt_speed_str(u8 speed) return "10"; case ICE_AQC_PORT_OPT_MAX_LANE_25G: return "25"; + case ICE_AQC_PORT_OPT_MAX_LANE_40G: + return "40"; case ICE_AQC_PORT_OPT_MAX_LANE_50G: return "50"; case ICE_AQC_PORT_OPT_MAX_LANE_100G: diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 97f9ebd62d93..39d99c2f7976 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1684,6 +1684,7 @@ struct ice_aqc_get_port_options_elem { #define ICE_AQC_PORT_OPT_MAX_LANE_50G 6 #define ICE_AQC_PORT_OPT_MAX_LANE_100G 7 #define ICE_AQC_PORT_OPT_MAX_LANE_200G 8 +#define ICE_AQC_PORT_OPT_MAX_LANE_40G 9 u8 global_scid[2]; u8 phy_scid[2]; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 1b435e108d3c..b542e1e0f0c9 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -171,6 +171,15 @@ static int ice_set_mac_type(struct ice_hw *hw) case ICE_DEV_ID_E830_XXV_QSFP: case ICE_DEV_ID_E830C_SFP: case ICE_DEV_ID_E830_XXV_SFP: + case ICE_DEV_ID_E835CC_BACKPLANE: + case ICE_DEV_ID_E835CC_QSFP56: + case ICE_DEV_ID_E835CC_SFP: + case ICE_DEV_ID_E835C_BACKPLANE: + case ICE_DEV_ID_E835C_QSFP: + case ICE_DEV_ID_E835C_SFP: + case ICE_DEV_ID_E835_L_BACKPLANE: + case ICE_DEV_ID_E835_L_QSFP: + case ICE_DEV_ID_E835_L_SFP: hw->mac_type = ICE_MAC_E830; break; default: @@ -4307,7 +4316,7 @@ int ice_get_phy_lane_number(struct ice_hw *hw) speed = options[active_idx].max_lane_speed; /* If we don't get speed for this lane, it's unoccupied */ - if (speed > ICE_AQC_PORT_OPT_MAX_LANE_200G) + if (speed > ICE_AQC_PORT_OPT_MAX_LANE_40G) continue; if (hw->pf_id == lport) { diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index 59323c019544..351824dc3c62 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -2301,6 +2301,8 @@ enum ice_ddp_state ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, return ICE_DDP_PKG_ERR; buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL); + if (!buf_copy) + return ICE_DDP_PKG_ERR; state = ice_init_pkg(hw, buf_copy, len); if (!ice_is_init_pkg_successful(state)) { diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h index 34fd604132f5..bd4e66df0372 100644 --- a/drivers/net/ethernet/intel/ice/ice_devids.h +++ b/drivers/net/ethernet/intel/ice/ice_devids.h @@ -6,6 +6,24 @@ /* Device IDs */ #define ICE_DEV_ID_E822_SI_DFLT 0x1888 +/* Intel(R) Ethernet Controller E835-CC for backplane */ +#define ICE_DEV_ID_E835CC_BACKPLANE 0x1248 +/* Intel(R) Ethernet Controller E835-CC for QSFP */ +#define ICE_DEV_ID_E835CC_QSFP56 0x1249 +/* Intel(R) Ethernet Controller E835-CC for SFP */ +#define ICE_DEV_ID_E835CC_SFP 0x124A +/* Intel(R) Ethernet Controller E835-C for backplane */ +#define ICE_DEV_ID_E835C_BACKPLANE 0x1261 +/* Intel(R) Ethernet Controller E835-C for QSFP */ +#define ICE_DEV_ID_E835C_QSFP 0x1262 +/* Intel(R) Ethernet Controller E835-C for SFP */ +#define ICE_DEV_ID_E835C_SFP 0x1263 +/* Intel(R) Ethernet Controller E835-L for backplane */ +#define ICE_DEV_ID_E835_L_BACKPLANE 0x1265 +/* Intel(R) Ethernet Controller E835-L for QSFP */ +#define ICE_DEV_ID_E835_L_QSFP 0x1266 +/* Intel(R) Ethernet Controller E835-L for SFP */ +#define ICE_DEV_ID_E835_L_SFP 0x1267 /* Intel(R) Ethernet Connection E823-L for backplane */ #define ICE_DEV_ID_E823L_BACKPLANE 0x124C /* Intel(R) Ethernet Connection E823-L for SFP */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index e54221fba849..58ed875093cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -667,7 +667,8 @@ static int ice_get_port_topology(struct ice_hw *hw, u8 lport, if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_100G) port_topology->serdes_lane_count = 4; - else if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_50G) + else if (max_speed == ICE_AQC_PORT_OPT_MAX_LANE_50G || + max_speed == ICE_AQC_PORT_OPT_MAX_LANE_40G) port_topology->serdes_lane_count = 2; else port_topology->serdes_lane_count = 1; diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index ed95072ca6e3..363ae79a3620 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -3043,16 +3043,16 @@ ice_disable_fd_swap(struct ice_hw *hw, u8 prof_id) * the ID value used here. */ int -ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], - const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap) +ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, + unsigned long *ptypes, const struct ice_ptype_attributes *attr, + u16 attr_cnt, struct ice_fv_word *es, u16 *masks, bool symm, + bool fd_swap) { - u32 bytes = DIV_ROUND_UP(ICE_FLOW_PTYPE_MAX, BITS_PER_BYTE); DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); struct ice_prof_map *prof; - u8 byte = 0; - u8 prof_id; int status; + u8 prof_id; + u16 ptype; bitmap_zero(ptgs_used, ICE_XLT1_CNT); @@ -3102,57 +3102,35 @@ ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], prof->context = 0; /* build list of ptgs */ - while (bytes && prof->ptg_cnt < ICE_MAX_PTG_PER_PROFILE) { - u8 bit; + for_each_set_bit(ptype, ptypes, ICE_FLOW_PTYPE_MAX) { + u8 ptg; - if (!ptypes[byte]) { - bytes--; - byte++; + /* The package should place all ptypes in a non-zero + * PTG, so the following call should never fail. + */ + if (ice_ptg_find_ptype(hw, blk, ptype, &ptg)) continue; - } - /* Examine 8 bits per byte */ - for_each_set_bit(bit, (unsigned long *)&ptypes[byte], - BITS_PER_BYTE) { - u16 ptype; - u8 ptg; - - ptype = byte * BITS_PER_BYTE + bit; - - /* The package should place all ptypes in a non-zero - * PTG, so the following call should never fail. - */ - if (ice_ptg_find_ptype(hw, blk, ptype, &ptg)) - continue; + /* If PTG is already added, skip and continue */ + if (test_bit(ptg, ptgs_used)) + continue; - /* If PTG is already added, skip and continue */ - if (test_bit(ptg, ptgs_used)) - continue; + set_bit(ptg, ptgs_used); + /* Check to see there are any attributes for this ptype, and + * add them if found. + */ + status = ice_add_prof_attrib(prof, ptg, ptype, attr, attr_cnt); + if (status == -ENOSPC) + break; + if (status) { + /* This is simple a ptype/PTG with no attribute */ + prof->ptg[prof->ptg_cnt] = ptg; + prof->attr[prof->ptg_cnt].flags = 0; + prof->attr[prof->ptg_cnt].mask = 0; - __set_bit(ptg, ptgs_used); - /* Check to see there are any attributes for - * this PTYPE, and add them if found. - */ - status = ice_add_prof_attrib(prof, ptg, ptype, - attr, attr_cnt); - if (status == -ENOSPC) + if (++prof->ptg_cnt >= ICE_MAX_PTG_PER_PROFILE) break; - if (status) { - /* This is simple a PTYPE/PTG with no - * attribute - */ - prof->ptg[prof->ptg_cnt] = ptg; - prof->attr[prof->ptg_cnt].flags = 0; - prof->attr[prof->ptg_cnt].mask = 0; - - if (++prof->ptg_cnt >= - ICE_MAX_PTG_PER_PROFILE) - break; - } } - - bytes--; - byte++; } list_add(&prof->list, &hw->blk[blk].es.prof_map); diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h index 28b0897adf32..ee5d9f9c9d53 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -39,9 +39,10 @@ bool ice_hw_ptype_ena(struct ice_hw *hw, u16 ptype); /* XLT2/VSI group functions */ int -ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, u8 ptypes[], - const struct ice_ptype_attributes *attr, u16 attr_cnt, - struct ice_fv_word *es, u16 *masks, bool symm, bool fd_swap); +ice_add_prof(struct ice_hw *hw, enum ice_block blk, u64 id, + unsigned long *ptypes, const struct ice_ptype_attributes *attr, + u16 attr_cnt, struct ice_fv_word *es, u16 *masks, bool symm, + bool fd_swap); struct ice_prof_map * ice_search_prof_id(struct ice_hw *hw, enum ice_block blk, u64 id); int diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index 278e57686274..6d5c939dc8a5 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -1421,7 +1421,7 @@ ice_flow_add_prof_sync(struct ice_hw *hw, enum ice_block blk, } /* Add a HW profile for this flow profile */ - status = ice_add_prof(hw, blk, prof_id, (u8 *)params->ptypes, + status = ice_add_prof(hw, blk, prof_id, params->ptypes, params->attr, params->attr_cnt, params->es, params->mask, symm, true); if (status) { @@ -1617,7 +1617,7 @@ ice_flow_set_parser_prof(struct ice_hw *hw, u16 dest_vsi, u16 fdir_vsi, break; } - status = ice_add_prof(hw, blk, id, (u8 *)prof->ptypes, + status = ice_add_prof(hw, blk, id, prof->ptypes, params->attr, params->attr_cnt, params->es, params->mask, false, false); if (status) diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index d132eb477551..c8b4fa3efbd4 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -823,6 +823,48 @@ cp_free: } /** + * ice_lag_prepare_vf_reset - helper to adjust vf lag for reset + * @lag: lag struct for interface that owns VF + * + * Context: must be called with the lag_mutex lock held. + * + * Return: active lport value or ICE_LAG_INVALID_PORT if nothing moved. + */ +u8 ice_lag_prepare_vf_reset(struct ice_lag *lag) +{ + u8 pri_prt, act_prt; + + if (lag && lag->bonded && lag->primary && lag->upper_netdev) { + pri_prt = lag->pf->hw.port_info->lport; + act_prt = lag->active_port; + if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT) { + ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); + return act_prt; + } + } + + return ICE_LAG_INVALID_PORT; +} + +/** + * ice_lag_complete_vf_reset - helper for lag after reset + * @lag: lag struct for primary interface + * @act_prt: which port should be active for lag + * + * Context: must be called while holding the lag_mutex. + */ +void ice_lag_complete_vf_reset(struct ice_lag *lag, u8 act_prt) +{ + u8 pri_prt; + + if (lag && lag->bonded && lag->primary && + act_prt != ICE_LAG_INVALID_PORT) { + pri_prt = lag->pf->hw.port_info->lport; + ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + } +} + +/** * ice_lag_info_event - handle NETDEV_BONDING_INFO event * @lag: LAG info struct * @ptr: opaque data pointer diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index bab2c83142a1..69347d9f986b 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -70,4 +70,6 @@ void ice_deinit_lag(struct ice_pf *pf); void ice_lag_rebuild(struct ice_pf *pf); bool ice_lag_is_switchdev_running(struct ice_pf *pf); void ice_lag_move_vf_nodes_cfg(struct ice_lag *lag, u8 src_prt, u8 dst_prt); +u8 ice_lag_prepare_vf_reset(struct ice_lag *lag); +void ice_lag_complete_vf_reset(struct ice_lag *lag, u8 act_prt); #endif /* _ICE_LAG_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index af68869693ed..204e906af591 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5897,6 +5897,15 @@ static const struct pci_device_id ice_pci_tbl[] = { { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_QSFP), }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_SFP), }, { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_QSFP56), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835CC_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835C_SFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_BACKPLANE), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_QSFP), }, + { PCI_VDEVICE(INTEL, ICE_DEV_ID_E835_L_SFP), }, /* required last entry */ {} }; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index c639ce716d32..5ee74f3e82dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -859,16 +859,13 @@ static void ice_notify_vf_reset(struct ice_vf *vf) int ice_reset_vf(struct ice_vf *vf, u32 flags) { struct ice_pf *pf = vf->pf; - struct ice_lag *lag; struct ice_vsi *vsi; - u8 act_prt, pri_prt; struct device *dev; int err = 0; + u8 act_prt; bool rsd; dev = ice_pf_to_dev(pf); - act_prt = ICE_LAG_INVALID_PORT; - pri_prt = pf->hw.port_info->lport; if (flags & ICE_VF_RESET_NOTIFY) ice_notify_vf_reset(vf); @@ -884,16 +881,8 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) else lockdep_assert_held(&vf->cfg_lock); - lag = pf->lag; mutex_lock(&pf->lag_mutex); - if (lag && lag->bonded && lag->primary) { - act_prt = lag->active_port; - if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && - lag->upper_netdev) - ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); - else - act_prt = ICE_LAG_INVALID_PORT; - } + act_prt = ice_lag_prepare_vf_reset(pf->lag); if (ice_is_vf_disabled(vf)) { vsi = ice_get_vf_vsi(vf); @@ -979,9 +968,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) ice_reset_vf_mbx_cnt(vf); out_unlock: - if (lag && lag->bonded && lag->primary && - act_prt != ICE_LAG_INVALID_PORT) - ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + ice_lag_complete_vf_reset(pf->lag, act_prt); mutex_unlock(&pf->lag_mutex); if (flags & ICE_VF_RESET_LOCK) diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 9460b6561b69..05511157c571 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -1996,24 +1996,13 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; struct ice_pf *pf = vf->pf; - struct ice_lag *lag; struct ice_vsi *vsi; - u8 act_prt, pri_prt; int i = -1, q_idx; bool ena_ts; + u8 act_prt; - lag = pf->lag; mutex_lock(&pf->lag_mutex); - act_prt = ICE_LAG_INVALID_PORT; - pri_prt = pf->hw.port_info->lport; - if (lag && lag->bonded && lag->primary) { - act_prt = lag->active_port; - if (act_prt != pri_prt && act_prt != ICE_LAG_INVALID_PORT && - lag->upper_netdev) - ice_lag_move_vf_nodes_cfg(lag, act_prt, pri_prt); - else - act_prt = ICE_LAG_INVALID_PORT; - } + act_prt = ice_lag_prepare_vf_reset(pf->lag); if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) goto error_param; @@ -2141,9 +2130,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } } - if (lag && lag->bonded && lag->primary && - act_prt != ICE_LAG_INVALID_PORT) - ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + ice_lag_complete_vf_reset(pf->lag, act_prt); mutex_unlock(&pf->lag_mutex); /* send the response to the VF */ @@ -2160,9 +2147,7 @@ error_param: vf->vf_id, i); } - if (lag && lag->bonded && lag->primary && - act_prt != ICE_LAG_INVALID_PORT) - ice_lag_move_vf_nodes_cfg(lag, pri_prt, act_prt); + ice_lag_complete_vf_reset(pf->lag, act_prt); mutex_unlock(&pf->lag_mutex); ice_lag_move_new_vf_nodes(vf); diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index 0cf9120d1f97..f4c0eaf9bde3 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -269,6 +269,12 @@ struct idpf_port_stats { struct virtchnl2_vport_stats vport_stats; }; +struct idpf_fsteer_fltr { + struct list_head list; + u32 loc; + u32 q_index; +}; + /** * struct idpf_vport - Handle for netdevices and queue resources * @num_txq: Number of allocated TX queues @@ -400,9 +406,27 @@ struct idpf_rss_data { }; /** + * struct idpf_q_coalesce - User defined coalescing configuration values for + * a single queue. + * @tx_intr_mode: Dynamic TX ITR or not + * @rx_intr_mode: Dynamic RX ITR or not + * @tx_coalesce_usecs: TX interrupt throttling rate + * @rx_coalesce_usecs: RX interrupt throttling rate + * + * Used to restore user coalescing configuration after a reset. + */ +struct idpf_q_coalesce { + u32 tx_intr_mode; + u32 rx_intr_mode; + u32 tx_coalesce_usecs; + u32 rx_coalesce_usecs; +}; + +/** * struct idpf_vport_user_config_data - User defined configuration values for * each vport. * @rss_data: See struct idpf_rss_data + * @q_coalesce: Array of per queue coalescing data * @num_req_tx_qs: Number of user requested TX queues through ethtool * @num_req_rx_qs: Number of user requested RX queues through ethtool * @num_req_txq_desc: Number of user requested TX queue descriptors through @@ -411,17 +435,22 @@ struct idpf_rss_data { * ethtool * @user_flags: User toggled config flags * @mac_filter_list: List of MAC filters + * @num_fsteer_fltrs: number of flow steering filters + * @flow_steer_list: list of flow steering filters * * Used to restore configuration after a reset as the vport will get wiped. */ struct idpf_vport_user_config_data { struct idpf_rss_data rss_data; + struct idpf_q_coalesce *q_coalesce; u16 num_req_tx_qs; u16 num_req_rx_qs; u32 num_req_txq_desc; u32 num_req_rxq_desc; DECLARE_BITMAP(user_flags, __IDPF_USER_FLAGS_NBITS); struct list_head mac_filter_list; + u32 num_fsteer_fltrs; + struct list_head flow_steer_list; }; /** @@ -667,16 +696,16 @@ static inline bool idpf_is_rdma_cap_ena(struct idpf_adapter *adapter) } #define IDPF_CAP_RSS (\ - VIRTCHNL2_CAP_RSS_IPV4_TCP |\ - VIRTCHNL2_CAP_RSS_IPV4_TCP |\ - VIRTCHNL2_CAP_RSS_IPV4_UDP |\ - VIRTCHNL2_CAP_RSS_IPV4_SCTP |\ - VIRTCHNL2_CAP_RSS_IPV4_OTHER |\ - VIRTCHNL2_CAP_RSS_IPV6_TCP |\ - VIRTCHNL2_CAP_RSS_IPV6_TCP |\ - VIRTCHNL2_CAP_RSS_IPV6_UDP |\ - VIRTCHNL2_CAP_RSS_IPV6_SCTP |\ - VIRTCHNL2_CAP_RSS_IPV6_OTHER) + VIRTCHNL2_FLOW_IPV4_TCP |\ + VIRTCHNL2_FLOW_IPV4_TCP |\ + VIRTCHNL2_FLOW_IPV4_UDP |\ + VIRTCHNL2_FLOW_IPV4_SCTP |\ + VIRTCHNL2_FLOW_IPV4_OTHER |\ + VIRTCHNL2_FLOW_IPV6_TCP |\ + VIRTCHNL2_FLOW_IPV6_TCP |\ + VIRTCHNL2_FLOW_IPV6_UDP |\ + VIRTCHNL2_FLOW_IPV6_SCTP |\ + VIRTCHNL2_FLOW_IPV6_OTHER) #define IDPF_CAP_RSC (\ VIRTCHNL2_CAP_RSC_IPV4_TCP |\ @@ -960,4 +989,7 @@ void idpf_idc_issue_reset_event(struct iidc_rdma_core_dev_info *cdev_info); void idpf_idc_vdev_mtu_event(struct iidc_rdma_vport_dev_info *vdev_info, enum iidc_rdma_event_type event_type); +int idpf_add_del_fsteer_filters(struct idpf_adapter *adapter, + struct virtchnl2_flow_rule_add_del *rule, + enum virtchnl2_op opcode); #endif /* !_IDPF_H_ */ diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index eaf7a2606faa..0eb812ac19c2 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -3,6 +3,7 @@ #include "idpf.h" #include "idpf_ptp.h" +#include "idpf_virtchnl.h" /** * idpf_get_rxnfc - command to get RX flow classification rules @@ -13,26 +14,312 @@ * Returns Success if the command is supported. */ static int idpf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, - u32 __always_unused *rule_locs) + u32 *rule_locs) { + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *user_config; + struct idpf_fsteer_fltr *f; struct idpf_vport *vport; + unsigned int cnt = 0; + int err = 0; idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); + user_config = &np->adapter->vport_config[np->vport_idx]->user_config; switch (cmd->cmd) { case ETHTOOL_GRXRINGS: cmd->data = vport->num_rxq; - idpf_vport_ctrl_unlock(netdev); - - return 0; + break; + case ETHTOOL_GRXCLSRLCNT: + cmd->rule_cnt = user_config->num_fsteer_fltrs; + cmd->data = idpf_fsteer_max_rules(vport); + break; + case ETHTOOL_GRXCLSRULE: + err = -EINVAL; + list_for_each_entry(f, &user_config->flow_steer_list, list) + if (f->loc == cmd->fs.location) { + cmd->fs.ring_cookie = f->q_index; + err = 0; + break; + } + break; + case ETHTOOL_GRXCLSRLALL: + cmd->data = idpf_fsteer_max_rules(vport); + list_for_each_entry(f, &user_config->flow_steer_list, list) { + if (cnt == cmd->rule_cnt) { + err = -EMSGSIZE; + break; + } + rule_locs[cnt] = f->loc; + cnt++; + } + if (!err) + cmd->rule_cnt = user_config->num_fsteer_fltrs; + break; default: break; } idpf_vport_ctrl_unlock(netdev); - return -EOPNOTSUPP; + return err; +} + +static void idpf_fsteer_fill_ipv4(struct virtchnl2_proto_hdrs *hdrs, + struct ethtool_rx_flow_spec *fsp) +{ + struct iphdr *iph; + + hdrs->proto_hdr[0].hdr_type = cpu_to_le32(VIRTCHNL2_PROTO_HDR_IPV4); + + iph = (struct iphdr *)hdrs->proto_hdr[0].buffer_spec; + iph->saddr = fsp->h_u.tcp_ip4_spec.ip4src; + iph->daddr = fsp->h_u.tcp_ip4_spec.ip4dst; + + iph = (struct iphdr *)hdrs->proto_hdr[0].buffer_mask; + iph->saddr = fsp->m_u.tcp_ip4_spec.ip4src; + iph->daddr = fsp->m_u.tcp_ip4_spec.ip4dst; +} + +static void idpf_fsteer_fill_udp(struct virtchnl2_proto_hdrs *hdrs, + struct ethtool_rx_flow_spec *fsp, + bool v4) +{ + struct udphdr *udph, *udpm; + + hdrs->proto_hdr[1].hdr_type = cpu_to_le32(VIRTCHNL2_PROTO_HDR_UDP); + + udph = (struct udphdr *)hdrs->proto_hdr[1].buffer_spec; + udpm = (struct udphdr *)hdrs->proto_hdr[1].buffer_mask; + + if (v4) { + udph->source = fsp->h_u.udp_ip4_spec.psrc; + udph->dest = fsp->h_u.udp_ip4_spec.pdst; + udpm->source = fsp->m_u.udp_ip4_spec.psrc; + udpm->dest = fsp->m_u.udp_ip4_spec.pdst; + } else { + udph->source = fsp->h_u.udp_ip6_spec.psrc; + udph->dest = fsp->h_u.udp_ip6_spec.pdst; + udpm->source = fsp->m_u.udp_ip6_spec.psrc; + udpm->dest = fsp->m_u.udp_ip6_spec.pdst; + } +} + +static void idpf_fsteer_fill_tcp(struct virtchnl2_proto_hdrs *hdrs, + struct ethtool_rx_flow_spec *fsp, + bool v4) +{ + struct tcphdr *tcph, *tcpm; + + hdrs->proto_hdr[1].hdr_type = cpu_to_le32(VIRTCHNL2_PROTO_HDR_TCP); + + tcph = (struct tcphdr *)hdrs->proto_hdr[1].buffer_spec; + tcpm = (struct tcphdr *)hdrs->proto_hdr[1].buffer_mask; + + if (v4) { + tcph->source = fsp->h_u.tcp_ip4_spec.psrc; + tcph->dest = fsp->h_u.tcp_ip4_spec.pdst; + tcpm->source = fsp->m_u.tcp_ip4_spec.psrc; + tcpm->dest = fsp->m_u.tcp_ip4_spec.pdst; + } else { + tcph->source = fsp->h_u.tcp_ip6_spec.psrc; + tcph->dest = fsp->h_u.tcp_ip6_spec.pdst; + tcpm->source = fsp->m_u.tcp_ip6_spec.psrc; + tcpm->dest = fsp->m_u.tcp_ip6_spec.pdst; + } +} + +/** + * idpf_add_flow_steer - add a Flow Steering filter + * @netdev: network interface device structure + * @cmd: command to add Flow Steering filter + * + * Return: 0 on success and negative values for failure + */ +static int idpf_add_flow_steer(struct net_device *netdev, + struct ethtool_rxnfc *cmd) +{ + struct idpf_fsteer_fltr *fltr, *parent = NULL, *f; + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *user_config; + struct ethtool_rx_flow_spec *fsp = &cmd->fs; + struct virtchnl2_flow_rule_add_del *rule; + struct idpf_vport_config *vport_config; + struct virtchnl2_rule_action_set *acts; + struct virtchnl2_flow_rule_info *info; + struct virtchnl2_proto_hdrs *hdrs; + struct idpf_vport *vport; + u32 flow_type, q_index; + u16 num_rxq; + int err; + + vport = idpf_netdev_to_vport(netdev); + vport_config = vport->adapter->vport_config[np->vport_idx]; + user_config = &vport_config->user_config; + num_rxq = user_config->num_req_rx_qs; + + flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); + if (flow_type != fsp->flow_type) + return -EINVAL; + + if (!idpf_sideband_action_ena(vport, fsp) || + !idpf_sideband_flow_type_ena(vport, flow_type)) + return -EOPNOTSUPP; + + if (user_config->num_fsteer_fltrs > idpf_fsteer_max_rules(vport)) + return -ENOSPC; + + q_index = fsp->ring_cookie; + if (q_index >= num_rxq) + return -EINVAL; + + rule = kzalloc(struct_size(rule, rule_info, 1), GFP_KERNEL); + if (!rule) + return -ENOMEM; + + rule->vport_id = cpu_to_le32(vport->vport_id); + rule->count = cpu_to_le32(1); + info = &rule->rule_info[0]; + info->rule_id = cpu_to_le32(fsp->location); + + hdrs = &info->rule_cfg.proto_hdrs; + hdrs->tunnel_level = 0; + hdrs->count = cpu_to_le32(2); + + acts = &info->rule_cfg.action_set; + acts->count = cpu_to_le32(1); + acts->actions[0].action_type = cpu_to_le32(VIRTCHNL2_ACTION_QUEUE); + acts->actions[0].act_conf.q_id = cpu_to_le32(q_index); + + switch (flow_type) { + case UDP_V4_FLOW: + idpf_fsteer_fill_ipv4(hdrs, fsp); + idpf_fsteer_fill_udp(hdrs, fsp, true); + break; + case TCP_V4_FLOW: + idpf_fsteer_fill_ipv4(hdrs, fsp); + idpf_fsteer_fill_tcp(hdrs, fsp, true); + break; + default: + err = -EINVAL; + goto out; + } + + err = idpf_add_del_fsteer_filters(vport->adapter, rule, + VIRTCHNL2_OP_ADD_FLOW_RULE); + if (err) + goto out; + + if (info->status != cpu_to_le32(VIRTCHNL2_FLOW_RULE_SUCCESS)) { + err = -EIO; + goto out; + } + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) { + err = -ENOMEM; + goto out; + } + + fltr->loc = fsp->location; + fltr->q_index = q_index; + list_for_each_entry(f, &user_config->flow_steer_list, list) { + if (f->loc >= fltr->loc) + break; + parent = f; + } + + parent ? list_add(&fltr->list, &parent->list) : + list_add(&fltr->list, &user_config->flow_steer_list); + + user_config->num_fsteer_fltrs++; + +out: + kfree(rule); + return err; +} + +/** + * idpf_del_flow_steer - delete a Flow Steering filter + * @netdev: network interface device structure + * @cmd: command to add Flow Steering filter + * + * Return: 0 on success and negative values for failure + */ +static int idpf_del_flow_steer(struct net_device *netdev, + struct ethtool_rxnfc *cmd) +{ + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *user_config; + struct ethtool_rx_flow_spec *fsp = &cmd->fs; + struct virtchnl2_flow_rule_add_del *rule; + struct idpf_vport_config *vport_config; + struct virtchnl2_flow_rule_info *info; + struct idpf_fsteer_fltr *f, *iter; + struct idpf_vport *vport; + int err; + + vport = idpf_netdev_to_vport(netdev); + vport_config = vport->adapter->vport_config[np->vport_idx]; + user_config = &vport_config->user_config; + + if (!idpf_sideband_action_ena(vport, fsp)) + return -EOPNOTSUPP; + + rule = kzalloc(struct_size(rule, rule_info, 1), GFP_KERNEL); + if (!rule) + return -ENOMEM; + + rule->vport_id = cpu_to_le32(vport->vport_id); + rule->count = cpu_to_le32(1); + info = &rule->rule_info[0]; + info->rule_id = cpu_to_le32(fsp->location); + + err = idpf_add_del_fsteer_filters(vport->adapter, rule, + VIRTCHNL2_OP_DEL_FLOW_RULE); + if (err) + goto out; + + if (info->status != cpu_to_le32(VIRTCHNL2_FLOW_RULE_SUCCESS)) { + err = -EIO; + goto out; + } + + list_for_each_entry_safe(f, iter, + &user_config->flow_steer_list, list) { + if (f->loc == fsp->location) { + list_del(&f->list); + kfree(f); + user_config->num_fsteer_fltrs--; + goto out; + } + } + err = -EINVAL; + +out: + kfree(rule); + return err; +} + +static int idpf_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd) +{ + int ret = -EOPNOTSUPP; + + idpf_vport_ctrl_lock(netdev); + switch (cmd->cmd) { + case ETHTOOL_SRXCLSRLINS: + ret = idpf_add_flow_steer(netdev, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + ret = idpf_del_flow_steer(netdev, cmd); + break; + default: + break; + } + + idpf_vport_ctrl_unlock(netdev); + return ret; } /** @@ -1090,12 +1377,14 @@ static int idpf_get_per_q_coalesce(struct net_device *netdev, u32 q_num, /** * __idpf_set_q_coalesce - set ITR values for specific queue * @ec: ethtool structure from user to update ITR settings + * @q_coal: per queue coalesce settings * @qv: queue vector for which itr values has to be set * @is_rxq: is queue type rx * * Returns 0 on success, negative otherwise. */ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec, + struct idpf_q_coalesce *q_coal, struct idpf_q_vector *qv, bool is_rxq) { u32 use_adaptive_coalesce, coalesce_usecs; @@ -1139,20 +1428,25 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec, if (is_rxq) { qv->rx_itr_value = coalesce_usecs; + q_coal->rx_coalesce_usecs = coalesce_usecs; if (use_adaptive_coalesce) { qv->rx_intr_mode = IDPF_ITR_DYNAMIC; + q_coal->rx_intr_mode = IDPF_ITR_DYNAMIC; } else { qv->rx_intr_mode = !IDPF_ITR_DYNAMIC; - idpf_vport_intr_write_itr(qv, qv->rx_itr_value, - false); + q_coal->rx_intr_mode = !IDPF_ITR_DYNAMIC; + idpf_vport_intr_write_itr(qv, coalesce_usecs, false); } } else { qv->tx_itr_value = coalesce_usecs; + q_coal->tx_coalesce_usecs = coalesce_usecs; if (use_adaptive_coalesce) { qv->tx_intr_mode = IDPF_ITR_DYNAMIC; + q_coal->tx_intr_mode = IDPF_ITR_DYNAMIC; } else { qv->tx_intr_mode = !IDPF_ITR_DYNAMIC; - idpf_vport_intr_write_itr(qv, qv->tx_itr_value, true); + q_coal->tx_intr_mode = !IDPF_ITR_DYNAMIC; + idpf_vport_intr_write_itr(qv, coalesce_usecs, true); } } @@ -1165,6 +1459,7 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec, /** * idpf_set_q_coalesce - set ITR values for specific queue * @vport: vport associated to the queue that need updating + * @q_coal: per queue coalesce settings * @ec: coalesce settings to program the device with * @q_num: update ITR/INTRL (coalesce) settings for this queue number/index * @is_rxq: is queue type rx @@ -1172,6 +1467,7 @@ static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec, * Return 0 on success, and negative on failure */ static int idpf_set_q_coalesce(const struct idpf_vport *vport, + struct idpf_q_coalesce *q_coal, const struct ethtool_coalesce *ec, int q_num, bool is_rxq) { @@ -1180,7 +1476,7 @@ static int idpf_set_q_coalesce(const struct idpf_vport *vport, qv = is_rxq ? idpf_find_rxq_vec(vport, q_num) : idpf_find_txq_vec(vport, q_num); - if (qv && __idpf_set_q_coalesce(ec, qv, is_rxq)) + if (qv && __idpf_set_q_coalesce(ec, q_coal, qv, is_rxq)) return -EINVAL; return 0; @@ -1201,9 +1497,13 @@ static int idpf_set_coalesce(struct net_device *netdev, struct netlink_ext_ack *extack) { struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *user_config; + struct idpf_q_coalesce *q_coal; struct idpf_vport *vport; int i, err = 0; + user_config = &np->adapter->vport_config[np->vport_idx]->user_config; + idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); @@ -1211,13 +1511,15 @@ static int idpf_set_coalesce(struct net_device *netdev, goto unlock_mutex; for (i = 0; i < vport->num_txq; i++) { - err = idpf_set_q_coalesce(vport, ec, i, false); + q_coal = &user_config->q_coalesce[i]; + err = idpf_set_q_coalesce(vport, q_coal, ec, i, false); if (err) goto unlock_mutex; } for (i = 0; i < vport->num_rxq; i++) { - err = idpf_set_q_coalesce(vport, ec, i, true); + q_coal = &user_config->q_coalesce[i]; + err = idpf_set_q_coalesce(vport, q_coal, ec, i, true); if (err) goto unlock_mutex; } @@ -1239,20 +1541,25 @@ unlock_mutex: static int idpf_set_per_q_coalesce(struct net_device *netdev, u32 q_num, struct ethtool_coalesce *ec) { + struct idpf_netdev_priv *np = netdev_priv(netdev); + struct idpf_vport_user_config_data *user_config; + struct idpf_q_coalesce *q_coal; struct idpf_vport *vport; int err; idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); + user_config = &np->adapter->vport_config[np->vport_idx]->user_config; + q_coal = &user_config->q_coalesce[q_num]; - err = idpf_set_q_coalesce(vport, ec, q_num, false); + err = idpf_set_q_coalesce(vport, q_coal, ec, q_num, false); if (err) { idpf_vport_ctrl_unlock(netdev); return err; } - err = idpf_set_q_coalesce(vport, ec, q_num, true); + err = idpf_set_q_coalesce(vport, q_coal, ec, q_num, true); idpf_vport_ctrl_unlock(netdev); @@ -1394,6 +1701,7 @@ static const struct ethtool_ops idpf_ethtool_ops = { .get_sset_count = idpf_get_sset_count, .get_channels = idpf_get_channels, .get_rxnfc = idpf_get_rxnfc, + .set_rxnfc = idpf_set_rxnfc, .get_rxfh_key_size = idpf_get_rxfh_key_size, .get_rxfh_indir_size = idpf_get_rxfh_indir_size, .get_rxfh = idpf_get_rxfh, diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 338aa1bab71e..2c2a3e85d693 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -804,6 +804,10 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) if (idpf_is_cap_ena_all(adapter, IDPF_RSS_CAPS, IDPF_CAP_RSS)) dflt_features |= NETIF_F_RXHASH; + if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, + VIRTCHNL2_CAP_FLOW_STEER) && + idpf_vport_is_cap_ena(vport, VIRTCHNL2_VPORT_SIDEBAND_FLOW_STEER)) + dflt_features |= NETIF_F_NTUPLE; if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V4)) csum_offloads |= NETIF_F_IP_CSUM; if (idpf_is_cap_ena_all(adapter, IDPF_CSUM_CAPS, IDPF_CAP_TX_CSUM_L4V6)) @@ -1130,8 +1134,10 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, if (!vport) return vport; + num_max_q = max(max_q->max_txq, max_q->max_rxq); if (!adapter->vport_config[idx]) { struct idpf_vport_config *vport_config; + struct idpf_q_coalesce *q_coal; vport_config = kzalloc(sizeof(*vport_config), GFP_KERNEL); if (!vport_config) { @@ -1140,6 +1146,21 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, return NULL; } + q_coal = kcalloc(num_max_q, sizeof(*q_coal), GFP_KERNEL); + if (!q_coal) { + kfree(vport_config); + kfree(vport); + + return NULL; + } + for (int i = 0; i < num_max_q; i++) { + q_coal[i].tx_intr_mode = IDPF_ITR_DYNAMIC; + q_coal[i].tx_coalesce_usecs = IDPF_ITR_TX_DEF; + q_coal[i].rx_intr_mode = IDPF_ITR_DYNAMIC; + q_coal[i].rx_coalesce_usecs = IDPF_ITR_RX_DEF; + } + vport_config->user_config.q_coalesce = q_coal; + adapter->vport_config[idx] = vport_config; } @@ -1149,7 +1170,6 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, vport->default_vport = adapter->num_alloc_vports < idpf_get_default_vports(adapter); - num_max_q = max(max_q->max_txq, max_q->max_rxq); vport->q_vector_idxs = kcalloc(num_max_q, sizeof(u16), GFP_KERNEL); if (!vport->q_vector_idxs) goto free_vport; @@ -1532,6 +1552,7 @@ void idpf_init_task(struct work_struct *work) spin_lock_init(&vport_config->mac_filter_list_lock); INIT_LIST_HEAD(&vport_config->user_config.mac_filter_list); + INIT_LIST_HEAD(&vport_config->user_config.flow_steer_list); err = idpf_check_supported_desc_ids(vport); if (err) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index b7422be3e967..dfe9126f1f4a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -62,6 +62,7 @@ destroy_wqs: destroy_workqueue(adapter->vc_event_wq); for (i = 0; i < adapter->max_vports; i++) { + kfree(adapter->vport_config[i]->user_config.q_coalesce); kfree(adapter->vport_config[i]); adapter->vport_config[i] = NULL; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c index 4f8725c85332..ee21f2ff0cad 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c @@ -42,6 +42,13 @@ void idpf_ptp_get_features_access(const struct idpf_adapter *adapter) direct, mailbox); + /* Get the cross timestamp */ + direct = VIRTCHNL2_CAP_PTP_GET_CROSS_TIME; + mailbox = VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB; + ptp->get_cross_tstamp_access = idpf_ptp_get_access(adapter, + direct, + mailbox); + /* Set the device clock time */ direct = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME; mailbox = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME; @@ -171,6 +178,127 @@ static int idpf_ptp_read_src_clk_reg(struct idpf_adapter *adapter, u64 *src_clk, return 0; } +#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER) || IS_ENABLED(CONFIG_X86) +/** + * idpf_ptp_get_sync_device_time_direct - Get the cross time stamp values + * directly + * @adapter: Driver specific private structure + * @dev_time: 64bit main timer value + * @sys_time: 64bit system time value + */ +static void idpf_ptp_get_sync_device_time_direct(struct idpf_adapter *adapter, + u64 *dev_time, u64 *sys_time) +{ + u32 dev_time_lo, dev_time_hi, sys_time_lo, sys_time_hi; + struct idpf_ptp *ptp = adapter->ptp; + + spin_lock(&ptp->read_dev_clk_lock); + + idpf_ptp_enable_shtime(adapter); + + dev_time_lo = readl(ptp->dev_clk_regs.dev_clk_ns_l); + dev_time_hi = readl(ptp->dev_clk_regs.dev_clk_ns_h); + + sys_time_lo = readl(ptp->dev_clk_regs.sys_time_ns_l); + sys_time_hi = readl(ptp->dev_clk_regs.sys_time_ns_h); + + spin_unlock(&ptp->read_dev_clk_lock); + + *dev_time = (u64)dev_time_hi << 32 | dev_time_lo; + *sys_time = (u64)sys_time_hi << 32 | sys_time_lo; +} + +/** + * idpf_ptp_get_sync_device_time_mailbox - Get the cross time stamp values + * through mailbox + * @adapter: Driver specific private structure + * @dev_time: 64bit main timer value expressed in nanoseconds + * @sys_time: 64bit system time value expressed in nanoseconds + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_get_sync_device_time_mailbox(struct idpf_adapter *adapter, + u64 *dev_time, u64 *sys_time) +{ + struct idpf_ptp_dev_timers cross_time; + int err; + + err = idpf_ptp_get_cross_time(adapter, &cross_time); + if (err) + return err; + + *dev_time = cross_time.dev_clk_time_ns; + *sys_time = cross_time.sys_time_ns; + + return err; +} + +/** + * idpf_ptp_get_sync_device_time - Get the cross time stamp info + * @device: Current device time + * @system: System counter value read synchronously with device time + * @ctx: Context provided by timekeeping code + * + * The device and the system clocks time read simultaneously. + * + * Return: 0 on success, -errno otherwise. + */ +static int idpf_ptp_get_sync_device_time(ktime_t *device, + struct system_counterval_t *system, + void *ctx) +{ + struct idpf_adapter *adapter = ctx; + u64 ns_time_dev, ns_time_sys; + int err; + + switch (adapter->ptp->get_cross_tstamp_access) { + case IDPF_PTP_NONE: + return -EOPNOTSUPP; + case IDPF_PTP_DIRECT: + idpf_ptp_get_sync_device_time_direct(adapter, &ns_time_dev, + &ns_time_sys); + break; + case IDPF_PTP_MAILBOX: + err = idpf_ptp_get_sync_device_time_mailbox(adapter, + &ns_time_dev, + &ns_time_sys); + if (err) + return err; + break; + default: + return -EOPNOTSUPP; + } + + *device = ns_to_ktime(ns_time_dev); + + system->cs_id = IS_ENABLED(CONFIG_X86) ? CSID_X86_ART + : CSID_ARM_ARCH_COUNTER; + system->cycles = ns_time_sys; + system->use_nsecs = true; + + return 0; +} + +/** + * idpf_ptp_get_crosststamp - Capture a device cross timestamp + * @info: the driver's PTP info structure + * @cts: The memory to fill the cross timestamp info + * + * Capture a cross timestamp between the system time and the device PTP hardware + * clock. + * + * Return: cross timestamp value on success, -errno on failure. + */ +static int idpf_ptp_get_crosststamp(struct ptp_clock_info *info, + struct system_device_crosststamp *cts) +{ + struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info); + + return get_device_system_crosststamp(idpf_ptp_get_sync_device_time, + adapter, NULL, cts); +} +#endif /* CONFIG_ARM_ARCH_TIMER || CONFIG_X86 */ + /** * idpf_ptp_gettimex64 - Get the time of the clock * @info: the driver's PTP info structure @@ -661,6 +789,14 @@ static void idpf_ptp_set_caps(const struct idpf_adapter *adapter) info->verify = idpf_ptp_verify_pin; info->enable = idpf_ptp_gpio_enable; info->do_aux_work = idpf_ptp_do_aux_work; +#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER) + info->getcrosststamp = idpf_ptp_get_crosststamp; +#elif IS_ENABLED(CONFIG_X86) + if (pcie_ptm_enabled(adapter->pdev) && + boot_cpu_has(X86_FEATURE_ART) && + boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) + info->getcrosststamp = idpf_ptp_get_crosststamp; +#endif /* CONFIG_ARM_ARCH_TIMER */ } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h index a876749d6116..785da03e4cf5 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ptp.h +++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h @@ -21,6 +21,8 @@ struct idpf_ptp_cmd { * @dev_clk_ns_h: high part of the device clock register * @phy_clk_ns_l: low part of the PHY clock register * @phy_clk_ns_h: high part of the PHY clock register + * @sys_time_ns_l: low part of the system time register + * @sys_time_ns_h: high part of the system time register * @incval_l: low part of the increment value register * @incval_h: high part of the increment value register * @shadj_l: low part of the shadow adjust register @@ -42,6 +44,10 @@ struct idpf_ptp_dev_clk_regs { void __iomem *phy_clk_ns_l; void __iomem *phy_clk_ns_h; + /* System time */ + void __iomem *sys_time_ns_l; + void __iomem *sys_time_ns_h; + /* Main timer adjustments */ void __iomem *incval_l; void __iomem *incval_h; @@ -162,6 +168,7 @@ struct idpf_ptp_vport_tx_tstamp_caps { * @dev_clk_regs: the set of registers to access the device clock * @caps: PTP capabilities negotiated with the Control Plane * @get_dev_clk_time_access: access type for getting the device clock time + * @get_cross_tstamp_access: access type for the cross timestamping * @set_dev_clk_time_access: access type for setting the device clock time * @adj_dev_clk_time_access: access type for the adjusting the device clock * @tx_tstamp_access: access type for the Tx timestamp value read @@ -182,6 +189,7 @@ struct idpf_ptp { struct idpf_ptp_dev_clk_regs dev_clk_regs; u32 caps; enum idpf_ptp_access get_dev_clk_time_access:2; + enum idpf_ptp_access get_cross_tstamp_access:2; enum idpf_ptp_access set_dev_clk_time_access:2; enum idpf_ptp_access adj_dev_clk_time_access:2; enum idpf_ptp_access tx_tstamp_access:2; @@ -264,6 +272,8 @@ void idpf_ptp_get_features_access(const struct idpf_adapter *adapter); bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq); int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter, struct idpf_ptp_dev_timers *dev_clk_time); +int idpf_ptp_get_cross_time(struct idpf_adapter *adapter, + struct idpf_ptp_dev_timers *cross_time); int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time); int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval); int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta); @@ -305,6 +315,13 @@ idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter, return -EOPNOTSUPP; } +static inline int +idpf_ptp_get_cross_time(struct idpf_adapter *adapter, + struct idpf_ptp_dev_timers *cross_time) +{ + return -EOPNOTSUPP; +} + static inline int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index cef9dfb877e8..66a1b040639d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3276,8 +3276,10 @@ static u32 idpf_rx_hsplit_wa(const struct libeth_fqe *hdr, hdr_page = __netmem_to_page(hdr->netmem); buf_page = __netmem_to_page(buf->netmem); - dst = page_address(hdr_page) + hdr->offset + hdr_page->pp->p.offset; - src = page_address(buf_page) + buf->offset + buf_page->pp->p.offset; + dst = page_address(hdr_page) + hdr->offset + + pp_page_to_nmdesc(hdr_page)->pp->p.offset; + src = page_address(buf_page) + buf->offset + + pp_page_to_nmdesc(buf_page)->pp->p.offset; memcpy(dst, src, LARGEST_ALIGN(copy)); buf->offset += copy; @@ -3296,7 +3298,7 @@ static u32 idpf_rx_hsplit_wa(const struct libeth_fqe *hdr, struct sk_buff *idpf_rx_build_skb(const struct libeth_fqe *buf, u32 size) { struct page *buf_page = __netmem_to_page(buf->netmem); - u32 hr = buf_page->pp->p.offset; + u32 hr = pp_page_to_nmdesc(buf_page)->pp->p.offset; struct sk_buff *skb; void *va; @@ -4355,9 +4357,13 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport) int idpf_vport_intr_alloc(struct idpf_vport *vport) { u16 txqs_per_vector, rxqs_per_vector, bufqs_per_vector; + struct idpf_vport_user_config_data *user_config; struct idpf_q_vector *q_vector; + struct idpf_q_coalesce *q_coal; u32 complqs_per_vector, v_idx; + u16 idx = vport->idx; + user_config = &vport->adapter->vport_config[idx]->user_config; vport->q_vectors = kcalloc(vport->num_q_vectors, sizeof(struct idpf_q_vector), GFP_KERNEL); if (!vport->q_vectors) @@ -4375,14 +4381,15 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport) for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { q_vector = &vport->q_vectors[v_idx]; + q_coal = &user_config->q_coalesce[v_idx]; q_vector->vport = vport; - q_vector->tx_itr_value = IDPF_ITR_TX_DEF; - q_vector->tx_intr_mode = IDPF_ITR_DYNAMIC; + q_vector->tx_itr_value = q_coal->tx_coalesce_usecs; + q_vector->tx_intr_mode = q_coal->tx_intr_mode; q_vector->tx_itr_idx = VIRTCHNL2_ITR_IDX_1; - q_vector->rx_itr_value = IDPF_ITR_RX_DEF; - q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC; + q_vector->rx_itr_value = q_coal->rx_coalesce_usecs; + q_vector->rx_intr_mode = q_coal->rx_intr_mode; q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0; q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx), diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index 0d2199ac5c3e..a028c69f7fdc 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -850,14 +850,14 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter) VIRTCHNL2_CAP_SEG_TX_SINGLE_TUNNEL); caps.rss_caps = - cpu_to_le64(VIRTCHNL2_CAP_RSS_IPV4_TCP | - VIRTCHNL2_CAP_RSS_IPV4_UDP | - VIRTCHNL2_CAP_RSS_IPV4_SCTP | - VIRTCHNL2_CAP_RSS_IPV4_OTHER | - VIRTCHNL2_CAP_RSS_IPV6_TCP | - VIRTCHNL2_CAP_RSS_IPV6_UDP | - VIRTCHNL2_CAP_RSS_IPV6_SCTP | - VIRTCHNL2_CAP_RSS_IPV6_OTHER); + cpu_to_le64(VIRTCHNL2_FLOW_IPV4_TCP | + VIRTCHNL2_FLOW_IPV4_UDP | + VIRTCHNL2_FLOW_IPV4_SCTP | + VIRTCHNL2_FLOW_IPV4_OTHER | + VIRTCHNL2_FLOW_IPV6_TCP | + VIRTCHNL2_FLOW_IPV6_UDP | + VIRTCHNL2_FLOW_IPV6_SCTP | + VIRTCHNL2_FLOW_IPV6_OTHER); caps.hsplit_caps = cpu_to_le32(VIRTCHNL2_CAP_RX_HSPLIT_AT_L4V4 | @@ -1016,6 +1016,41 @@ static int idpf_map_lan_mmio_regs(struct idpf_adapter *adapter) } /** + * idpf_add_del_fsteer_filters - Send virtchnl add/del Flow Steering message + * @adapter: adapter info struct + * @rule: Flow steering rule to add/delete + * @opcode: VIRTCHNL2_OP_ADD_FLOW_RULE to add filter, or + * VIRTCHNL2_OP_DEL_FLOW_RULE to delete. All other values are invalid. + * + * Send ADD/DELETE flow steering virtchnl message and receive the result. + * + * Return: 0 on success, negative on failure. + */ +int idpf_add_del_fsteer_filters(struct idpf_adapter *adapter, + struct virtchnl2_flow_rule_add_del *rule, + enum virtchnl2_op opcode) +{ + int rule_count = le32_to_cpu(rule->count); + struct idpf_vc_xn_params xn_params = {}; + ssize_t reply_sz; + + if (opcode != VIRTCHNL2_OP_ADD_FLOW_RULE && + opcode != VIRTCHNL2_OP_DEL_FLOW_RULE) + return -EINVAL; + + xn_params.vc_op = opcode; + xn_params.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC; + xn_params.async = false; + xn_params.send_buf.iov_base = rule; + xn_params.send_buf.iov_len = struct_size(rule, rule_info, rule_count); + xn_params.recv_buf.iov_base = rule; + xn_params.recv_buf.iov_len = struct_size(rule, rule_info, rule_count); + + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + return reply_sz < 0 ? reply_sz : 0; +} + +/** * idpf_vport_alloc_max_qs - Allocate max queues for a vport * @adapter: Driver specific private structure * @max_q: vport max queue structure @@ -3643,6 +3678,79 @@ bool idpf_is_capability_ena(struct idpf_adapter *adapter, bool all, } /** + * idpf_vport_is_cap_ena - Check if vport capability is enabled + * @vport: Private data struct + * @flag: flag(s) to check + * + * Return: true if the capability is supported, false otherwise + */ +bool idpf_vport_is_cap_ena(struct idpf_vport *vport, u16 flag) +{ + struct virtchnl2_create_vport *vport_msg; + + vport_msg = vport->adapter->vport_params_recvd[vport->idx]; + + return !!(le16_to_cpu(vport_msg->vport_flags) & flag); +} + +/** + * idpf_sideband_flow_type_ena - Check if steering is enabled for flow type + * @vport: Private data struct + * @flow_type: flow type to check (from ethtool.h) + * + * Return: true if sideband filters are allowed for @flow_type, false otherwise + */ +bool idpf_sideband_flow_type_ena(struct idpf_vport *vport, u32 flow_type) +{ + struct virtchnl2_create_vport *vport_msg; + __le64 caps; + + vport_msg = vport->adapter->vport_params_recvd[vport->idx]; + caps = vport_msg->sideband_flow_caps; + + switch (flow_type) { + case TCP_V4_FLOW: + return !!(caps & cpu_to_le64(VIRTCHNL2_FLOW_IPV4_TCP)); + case UDP_V4_FLOW: + return !!(caps & cpu_to_le64(VIRTCHNL2_FLOW_IPV4_UDP)); + default: + return false; + } +} + +/** + * idpf_sideband_action_ena - Check if steering is enabled for action + * @vport: Private data struct + * @fsp: flow spec + * + * Return: true if sideband filters are allowed for @fsp, false otherwise + */ +bool idpf_sideband_action_ena(struct idpf_vport *vport, + struct ethtool_rx_flow_spec *fsp) +{ + struct virtchnl2_create_vport *vport_msg; + unsigned int supp_actions; + + vport_msg = vport->adapter->vport_params_recvd[vport->idx]; + supp_actions = le32_to_cpu(vport_msg->sideband_flow_actions); + + /* Actions Drop/Wake are not supported */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC || + fsp->ring_cookie == RX_CLS_FLOW_WAKE) + return false; + + return !!(supp_actions & VIRTCHNL2_ACTION_QUEUE); +} + +unsigned int idpf_fsteer_max_rules(struct idpf_vport *vport) +{ + struct virtchnl2_create_vport *vport_msg; + + vport_msg = vport->adapter->vport_params_recvd[vport->idx]; + return le32_to_cpu(vport_msg->flow_steer_max_rules); +} + +/** * idpf_get_vport_id: Get vport id * @vport: virtual port structure * diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h index 7bae09483aed..86f30f0db07a 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h @@ -105,6 +105,12 @@ int idpf_get_reg_intr_vecs(struct idpf_vport *vport, int idpf_queue_reg_init(struct idpf_vport *vport); int idpf_vport_queue_ids_init(struct idpf_vport *vport); +bool idpf_vport_is_cap_ena(struct idpf_vport *vport, u16 flag); +bool idpf_sideband_flow_type_ena(struct idpf_vport *vport, u32 flow_type); +bool idpf_sideband_action_ena(struct idpf_vport *vport, + struct ethtool_rx_flow_spec *fsp); +unsigned int idpf_fsteer_max_rules(struct idpf_vport *vport); + int idpf_recv_mb_msg(struct idpf_adapter *adapter); int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op, u16 msg_size, u8 *msg, u16 cookie); diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c index bdcc54a5fb56..4f1fb0cefe51 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c @@ -30,6 +30,7 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter) .send_buf.iov_len = sizeof(send_ptp_caps_msg), .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, }; + struct virtchnl2_ptp_cross_time_reg_offsets cross_tstamp_offsets; struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets; struct virtchnl2_ptp_clk_reg_offsets clock_offsets; struct idpf_ptp_secondary_mbx *scnd_mbx; @@ -71,7 +72,7 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter) access_type = ptp->get_dev_clk_time_access; if (access_type != IDPF_PTP_DIRECT) - goto discipline_clock; + goto cross_tstamp; clock_offsets = recv_ptp_caps_msg->clk_offsets; @@ -90,6 +91,22 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter) temp_offset = le32_to_cpu(clock_offsets.cmd_sync_trigger); ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset); +cross_tstamp: + access_type = ptp->get_cross_tstamp_access; + if (access_type != IDPF_PTP_DIRECT) + goto discipline_clock; + + cross_tstamp_offsets = recv_ptp_caps_msg->cross_time_offsets; + + temp_offset = le32_to_cpu(cross_tstamp_offsets.sys_time_ns_l); + ptp->dev_clk_regs.sys_time_ns_l = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(cross_tstamp_offsets.sys_time_ns_h); + ptp->dev_clk_regs.sys_time_ns_h = idpf_get_reg_addr(adapter, + temp_offset); + temp_offset = le32_to_cpu(cross_tstamp_offsets.cmd_sync_trigger); + ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset); + discipline_clock: access_type = ptp->adj_dev_clk_time_access; if (access_type != IDPF_PTP_DIRECT) @@ -163,6 +180,42 @@ int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter, } /** + * idpf_ptp_get_cross_time - Send virtchnl get cross time message + * @adapter: Driver specific private structure + * @cross_time: Pointer to the device clock structure where the value is set + * + * Send virtchnl get cross time message to get the time of the clock and the + * system time. + * + * Return: 0 on success, -errno otherwise. + */ +int idpf_ptp_get_cross_time(struct idpf_adapter *adapter, + struct idpf_ptp_dev_timers *cross_time) +{ + struct virtchnl2_ptp_get_cross_time cross_time_msg; + struct idpf_vc_xn_params xn_params = { + .vc_op = VIRTCHNL2_OP_PTP_GET_CROSS_TIME, + .send_buf.iov_base = &cross_time_msg, + .send_buf.iov_len = sizeof(cross_time_msg), + .recv_buf.iov_base = &cross_time_msg, + .recv_buf.iov_len = sizeof(cross_time_msg), + .timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC, + }; + int reply_sz; + + reply_sz = idpf_vc_xn_exec(adapter, &xn_params); + if (reply_sz < 0) + return reply_sz; + if (reply_sz != sizeof(cross_time_msg)) + return -EIO; + + cross_time->dev_clk_time_ns = le64_to_cpu(cross_time_msg.dev_time_ns); + cross_time->sys_time_ns = le64_to_cpu(cross_time_msg.sys_time_ns); + + return 0; +} + +/** * idpf_ptp_set_dev_clk_time - Send virtchnl set device time message * @adapter: Driver specific private structure * @time: New time value diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h index 48d3cc9236a4..02ae447cc24a 100644 --- a/drivers/net/ethernet/intel/idpf/virtchnl2.h +++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h @@ -80,6 +80,10 @@ enum virtchnl2_op { VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME = 547, VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS = 548, VIRTCHNL2_OP_GET_LAN_MEMORY_REGIONS = 549, + /* Opcode 550 is reserved */ + VIRTCHNL2_OP_ADD_FLOW_RULE = 551, + VIRTCHNL2_OP_GET_FLOW_RULE = 552, + VIRTCHNL2_OP_DEL_FLOW_RULE = 553, }; /** @@ -153,22 +157,22 @@ enum virtchnl2_cap_seg { VIRTCHNL2_CAP_SEG_TX_DOUBLE_TUNNEL = BIT(8), }; -/* Receive Side Scaling Flow type capability flags */ -enum virtchnl2_cap_rss { - VIRTCHNL2_CAP_RSS_IPV4_TCP = BIT(0), - VIRTCHNL2_CAP_RSS_IPV4_UDP = BIT(1), - VIRTCHNL2_CAP_RSS_IPV4_SCTP = BIT(2), - VIRTCHNL2_CAP_RSS_IPV4_OTHER = BIT(3), - VIRTCHNL2_CAP_RSS_IPV6_TCP = BIT(4), - VIRTCHNL2_CAP_RSS_IPV6_UDP = BIT(5), - VIRTCHNL2_CAP_RSS_IPV6_SCTP = BIT(6), - VIRTCHNL2_CAP_RSS_IPV6_OTHER = BIT(7), - VIRTCHNL2_CAP_RSS_IPV4_AH = BIT(8), - VIRTCHNL2_CAP_RSS_IPV4_ESP = BIT(9), - VIRTCHNL2_CAP_RSS_IPV4_AH_ESP = BIT(10), - VIRTCHNL2_CAP_RSS_IPV6_AH = BIT(11), - VIRTCHNL2_CAP_RSS_IPV6_ESP = BIT(12), - VIRTCHNL2_CAP_RSS_IPV6_AH_ESP = BIT(13), +/* Receive Side Scaling and Flow Steering Flow type capability flags */ +enum virtchnl2_flow_types { + VIRTCHNL2_FLOW_IPV4_TCP = BIT(0), + VIRTCHNL2_FLOW_IPV4_UDP = BIT(1), + VIRTCHNL2_FLOW_IPV4_SCTP = BIT(2), + VIRTCHNL2_FLOW_IPV4_OTHER = BIT(3), + VIRTCHNL2_FLOW_IPV6_TCP = BIT(4), + VIRTCHNL2_FLOW_IPV6_UDP = BIT(5), + VIRTCHNL2_FLOW_IPV6_SCTP = BIT(6), + VIRTCHNL2_FLOW_IPV6_OTHER = BIT(7), + VIRTCHNL2_FLOW_IPV4_AH = BIT(8), + VIRTCHNL2_FLOW_IPV4_ESP = BIT(9), + VIRTCHNL2_FLOW_IPV4_AH_ESP = BIT(10), + VIRTCHNL2_FLOW_IPV6_AH = BIT(11), + VIRTCHNL2_FLOW_IPV6_ESP = BIT(12), + VIRTCHNL2_FLOW_IPV6_AH_ESP = BIT(13), }; /* Header split capability flags */ @@ -194,8 +198,9 @@ enum virtchnl2_cap_other { VIRTCHNL2_CAP_RDMA = BIT_ULL(0), VIRTCHNL2_CAP_SRIOV = BIT_ULL(1), VIRTCHNL2_CAP_MACFILTER = BIT_ULL(2), - VIRTCHNL2_CAP_FLOW_DIRECTOR = BIT_ULL(3), - /* Queue based scheduling using split queue model */ + /* Other capability 3 is available + * Queue based scheduling using split queue model + */ VIRTCHNL2_CAP_SPLITQ_QSCHED = BIT_ULL(4), VIRTCHNL2_CAP_CRC = BIT_ULL(5), VIRTCHNL2_CAP_ADQ = BIT_ULL(6), @@ -209,17 +214,37 @@ enum virtchnl2_cap_other { /* EDT: Earliest Departure Time capability used for Timing Wheel */ VIRTCHNL2_CAP_EDT = BIT_ULL(14), VIRTCHNL2_CAP_ADV_RSS = BIT_ULL(15), - VIRTCHNL2_CAP_FDIR = BIT_ULL(16), + /* Other capability 16 is available */ VIRTCHNL2_CAP_RX_FLEX_DESC = BIT_ULL(17), VIRTCHNL2_CAP_PTYPE = BIT_ULL(18), VIRTCHNL2_CAP_LOOPBACK = BIT_ULL(19), - /* Other capability 20-21 is reserved */ + /* Other capability 20 is reserved */ + VIRTCHNL2_CAP_FLOW_STEER = BIT_ULL(21), VIRTCHNL2_CAP_LAN_MEMORY_REGIONS = BIT_ULL(22), /* this must be the last capability */ VIRTCHNL2_CAP_OEM = BIT_ULL(63), }; +/** + * enum virtchnl2_action_types - Available actions for sideband flow steering + * @VIRTCHNL2_ACTION_DROP: Drop the packet + * @VIRTCHNL2_ACTION_PASSTHRU: Forward the packet to the next classifier/stage + * @VIRTCHNL2_ACTION_QUEUE: Forward the packet to a receive queue + * @VIRTCHNL2_ACTION_Q_GROUP: Forward the packet to a receive queue group + * @VIRTCHNL2_ACTION_MARK: Mark the packet with specific marker value + * @VIRTCHNL2_ACTION_COUNT: Increment the corresponding counter + */ + +enum virtchnl2_action_types { + VIRTCHNL2_ACTION_DROP = BIT(0), + VIRTCHNL2_ACTION_PASSTHRU = BIT(1), + VIRTCHNL2_ACTION_QUEUE = BIT(2), + VIRTCHNL2_ACTION_Q_GROUP = BIT(3), + VIRTCHNL2_ACTION_MARK = BIT(4), + VIRTCHNL2_ACTION_COUNT = BIT(5), +}; + /* underlying device type */ enum virtchl2_device_type { VIRTCHNL2_MEV_DEVICE = 0, @@ -461,7 +486,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_version_info); * @seg_caps: See enum virtchnl2_cap_seg. * @hsplit_caps: See enum virtchnl2_cap_rx_hsplit_at. * @rsc_caps: See enum virtchnl2_cap_rsc. - * @rss_caps: See enum virtchnl2_cap_rss. + * @rss_caps: See enum virtchnl2_flow_types. * @other_caps: See enum virtchnl2_cap_other. * @mailbox_dyn_ctl: DYN_CTL register offset and vector id for mailbox * provided by CP. @@ -578,11 +603,17 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks); /** * enum virtchnl2_vport_flags - Vport flags that indicate vport capabilities. * @VIRTCHNL2_VPORT_UPLINK_PORT: Representatives of underlying physical ports + * @VIRTCHNL2_VPORT_INLINE_FLOW_STEER: Inline flow steering enabled + * @VIRTCHNL2_VPORT_INLINE_FLOW_STEER_RXQ: Inline flow steering enabled + * with explicit Rx queue action + * @VIRTCHNL2_VPORT_SIDEBAND_FLOW_STEER: Sideband flow steering enabled * @VIRTCHNL2_VPORT_ENABLE_RDMA: RDMA is enabled for this vport */ enum virtchnl2_vport_flags { - VIRTCHNL2_VPORT_UPLINK_PORT = BIT(0), - /* VIRTCHNL2_VPORT_* bits [1:3] rsvd */ + VIRTCHNL2_VPORT_UPLINK_PORT = BIT(0), + VIRTCHNL2_VPORT_INLINE_FLOW_STEER = BIT(1), + VIRTCHNL2_VPORT_INLINE_FLOW_STEER_RXQ = BIT(2), + VIRTCHNL2_VPORT_SIDEBAND_FLOW_STEER = BIT(3), VIRTCHNL2_VPORT_ENABLE_RDMA = BIT(4), }; @@ -608,6 +639,14 @@ enum virtchnl2_vport_flags { * @rx_desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions. * @tx_desc_ids: See VIRTCHNL2_TX_DESC_IDS definitions. * @pad1: Padding. + * @inline_flow_caps: Bit mask of supported inline-flow-steering + * flow types (See enum virtchnl2_flow_types) + * @sideband_flow_caps: Bit mask of supported sideband-flow-steering + * flow types (See enum virtchnl2_flow_types) + * @sideband_flow_actions: Bit mask of supported action types + * for sideband flow steering (See enum virtchnl2_action_types) + * @flow_steer_max_rules: Max rules allowed for inline and sideband + * flow steering combined * @rss_algorithm: RSS algorithm. * @rss_key_size: RSS key size. * @rss_lut_size: RSS LUT size. @@ -640,7 +679,11 @@ struct virtchnl2_create_vport { __le16 vport_flags; __le64 rx_desc_ids; __le64 tx_desc_ids; - u8 pad1[72]; + u8 pad1[48]; + __le64 inline_flow_caps; + __le64 sideband_flow_caps; + __le32 sideband_flow_actions; + __le32 flow_steer_max_rules; __le32 rss_algorithm; __le16 rss_key_size; __le16 rss_lut_size; @@ -1615,4 +1658,156 @@ struct virtchnl2_get_lan_memory_regions { }; VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_get_lan_memory_regions); +#define VIRTCHNL2_MAX_NUM_PROTO_HDRS 4 +#define VIRTCHNL2_MAX_SIZE_RAW_PACKET 256 +#define VIRTCHNL2_MAX_NUM_ACTIONS 8 + +/** + * struct virtchnl2_proto_hdr - represent one protocol header + * @hdr_type: See enum virtchnl2_proto_hdr_type + * @pad: padding + * @buffer_spec: binary buffer based on header type. + * @buffer_mask: mask applied on buffer_spec. + * + * Structure to hold protocol headers based on hdr_type + */ +struct virtchnl2_proto_hdr { + __le32 hdr_type; + u8 pad[4]; + u8 buffer_spec[64]; + u8 buffer_mask[64]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(136, virtchnl2_proto_hdr); + +/** + * struct virtchnl2_proto_hdrs - struct to represent match criteria + * @tunnel_level: specify where protocol header(s) start from. + * must be 0 when sending a raw packet request. + * 0 - from the outer layer + * 1 - from the first inner layer + * 2 - from the second inner layer + * @pad: Padding bytes + * @count: total number of protocol headers in proto_hdr. 0 for raw packet. + * @proto_hdr: Array of protocol headers + * @raw: struct holding raw packet buffer when count is 0 + */ +struct virtchnl2_proto_hdrs { + u8 tunnel_level; + u8 pad[3]; + __le32 count; + union { + struct virtchnl2_proto_hdr + proto_hdr[VIRTCHNL2_MAX_NUM_PROTO_HDRS]; + struct { + __le16 pkt_len; + u8 spec[VIRTCHNL2_MAX_SIZE_RAW_PACKET]; + u8 mask[VIRTCHNL2_MAX_SIZE_RAW_PACKET]; + } raw; + }; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(552, virtchnl2_proto_hdrs); + +/** + * struct virtchnl2_rule_action - struct representing single action for a flow + * @action_type: see enum virtchnl2_action_types + * @act_conf: union representing action depending on action_type. + * @act_conf.q_id: queue id to redirect the packets to. + * @act_conf.q_grp_id: queue group id to redirect the packets to. + * @act_conf.ctr_id: used for count action. If input value 0xFFFFFFFF control + * plane assigns a new counter and returns the counter ID to + * the driver. If input value is not 0xFFFFFFFF then it must + * be an existing counter given to the driver for an earlier + * flow. Then this flow will share the counter. + * @act_conf.mark_id: Value used to mark the packets. Used for mark action. + * @act_conf.reserved: Reserved for future use. + */ +struct virtchnl2_rule_action { + __le32 action_type; + union { + __le32 q_id; + __le32 q_grp_id; + __le32 ctr_id; + __le32 mark_id; + u8 reserved[8]; + } act_conf; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(12, virtchnl2_rule_action); + +/** + * struct virtchnl2_rule_action_set - struct representing multiple actions + * @count: number of valid actions in the action set of a rule + * @actions: array of struct virtchnl2_rule_action + */ +struct virtchnl2_rule_action_set { + /* action count must be less than VIRTCHNL2_MAX_NUM_ACTIONS */ + __le32 count; + struct virtchnl2_rule_action actions[VIRTCHNL2_MAX_NUM_ACTIONS]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(100, virtchnl2_rule_action_set); + +/** + * struct virtchnl2_flow_rule - represent one flow steering rule + * @proto_hdrs: array of protocol header buffers representing match criteria + * @action_set: series of actions to be applied for given rule + * @priority: rule priority. + * @pad: padding for future extensions. + */ +struct virtchnl2_flow_rule { + struct virtchnl2_proto_hdrs proto_hdrs; + struct virtchnl2_rule_action_set action_set; + __le32 priority; + u8 pad[8]; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(664, virtchnl2_flow_rule); + +enum virtchnl2_flow_rule_status { + VIRTCHNL2_FLOW_RULE_SUCCESS = 1, + VIRTCHNL2_FLOW_RULE_NORESOURCE = 2, + VIRTCHNL2_FLOW_RULE_EXIST = 3, + VIRTCHNL2_FLOW_RULE_TIMEOUT = 4, + VIRTCHNL2_FLOW_RULE_FLOW_TYPE_NOT_SUPPORTED = 5, + VIRTCHNL2_FLOW_RULE_MATCH_KEY_NOT_SUPPORTED = 6, + VIRTCHNL2_FLOW_RULE_ACTION_NOT_SUPPORTED = 7, + VIRTCHNL2_FLOW_RULE_ACTION_COMBINATION_INVALID = 8, + VIRTCHNL2_FLOW_RULE_ACTION_DATA_INVALID = 9, + VIRTCHNL2_FLOW_RULE_NOT_ADDED = 10, +}; + +/** + * struct virtchnl2_flow_rule_info: structure representing single flow rule + * @rule_id: rule_id associated with the flow_rule. + * @rule_cfg: structure representing rule. + * @status: status of rule programming. See enum virtchnl2_flow_rule_status. + */ +struct virtchnl2_flow_rule_info { + __le32 rule_id; + struct virtchnl2_flow_rule rule_cfg; + __le32 status; +}; +VIRTCHNL2_CHECK_STRUCT_LEN(672, virtchnl2_flow_rule_info); + +/** + * struct virtchnl2_flow_rule_add_del - add/delete a flow steering rule + * @vport_id: vport id for which the rule is to be added or deleted. + * @count: Indicates number of rules to be added or deleted. + * @rule_info: Array of flow rules to be added or deleted. + * + * For VIRTCHNL2_OP_FLOW_RULE_ADD, rule_info contains list of rules to be + * added. If rule_id is 0xFFFFFFFF, then the rule is programmed and not cached. + * + * For VIRTCHNL2_OP_FLOW_RULE_DEL, there are two possibilities. The structure + * can contain either array of rule_ids or array of match keys to be deleted. + * When match keys are used the corresponding rule_ids must be 0xFFFFFFFF. + * + * status member of each rule indicates the result. Maximum of 6 rules can be + * added or deleted using this method. Driver has to retry in case of any + * failure of ADD or DEL opcode. CP doesn't retry in case of failure. + */ +struct virtchnl2_flow_rule_add_del { + __le32 vport_id; + __le32 count; + struct virtchnl2_flow_rule_info rule_info[] __counted_by_le(count); +}; +VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_flow_rule_add_del); + #endif /* _VIRTCHNL_2_H_ */ diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index ba9c3fee6da7..da8e1fd47301 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -154,7 +154,6 @@ struct igbvf_ring { /* board specific private data structure */ struct igbvf_adapter { struct timer_list watchdog_timer; - struct timer_list blink_timer; struct work_struct reset_task; struct work_struct watchdog_task; @@ -162,10 +161,7 @@ struct igbvf_adapter { const struct igbvf_info *ei; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - u32 bd_number; u32 rx_buffer_len; - u32 polling_interval; - u16 mng_vlan_id; u16 link_speed; u16 link_duplex; @@ -183,9 +179,6 @@ struct igbvf_adapter { unsigned int restart_queue; u32 txd_cmd; - u32 tx_int_delay; - u32 tx_abs_int_delay; - unsigned int total_tx_bytes; unsigned int total_tx_packets; unsigned int total_rx_bytes; @@ -193,23 +186,15 @@ struct igbvf_adapter { /* Tx stats */ u32 tx_timeout_count; - u32 tx_fifo_head; - u32 tx_head_addr; - u32 tx_fifo_size; - u32 tx_dma_failed; /* Rx */ struct igbvf_ring *rx_ring; - u32 rx_int_delay; - u32 rx_abs_int_delay; - /* Rx stats */ u64 hw_csum_err; u64 hw_csum_good; u64 rx_hdr_split; u32 alloc_rx_buff_failed; - u32 rx_dma_failed; unsigned int rx_ps_hdr_size; u32 max_frame_size; @@ -229,24 +214,14 @@ struct igbvf_adapter { struct e1000_vf_stats stats; u64 zero_base; - struct igbvf_ring test_tx_ring; - struct igbvf_ring test_rx_ring; - u32 test_icr; - u32 msg_enable; struct msix_entry *msix_entries; - int int_mode; u32 eims_enable_mask; u32 eims_other; - u32 eeprom_wol; u32 wol; u32 pba; - bool fc_autoneg; - - unsigned long led_status; - unsigned int flags; unsigned long last_reset; }; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index aed9162afd38..61dfcd8cb370 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1629,10 +1629,6 @@ static int igbvf_sw_init(struct igbvf_adapter *adapter) adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; - adapter->tx_int_delay = 8; - adapter->tx_abs_int_delay = 32; - adapter->rx_int_delay = 0; - adapter->rx_abs_int_delay = 8; adapter->requested_itr = 3; adapter->current_itr = IGBVF_START_ITR; @@ -2708,7 +2704,6 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct igbvf_adapter *adapter; struct e1000_hw *hw; const struct igbvf_info *ei = igbvf_info_tbl[ent->driver_data]; - static int cards_found; int err; err = pci_enable_device_mem(pdev); @@ -2780,8 +2775,6 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->watchdog_timeo = 5 * HZ; strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); - adapter->bd_number = cards_found++; - netdev->hw_features = NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 97b1a2c820ee..266bfcf2a28f 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -406,10 +406,6 @@ extern char igc_driver_name[]; #define IGC_FLAG_RSS_FIELD_IPV4_UDP BIT(6) #define IGC_FLAG_RSS_FIELD_IPV6_UDP BIT(7) -#define IGC_MRQC_ENABLE_RSS_MQ 0x00000002 -#define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000 -#define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 - /* RX-desc Write-Back format RSS Type's */ enum igc_rss_type_num { IGC_RSS_TYPE_NO_HASH = 0, @@ -635,6 +631,7 @@ enum igc_filter_match_flags { IGC_FILTER_FLAG_DST_MAC_ADDR = BIT(3), IGC_FILTER_FLAG_USER_DATA = BIT(4), IGC_FILTER_FLAG_VLAN_ETYPE = BIT(5), + IGC_FILTER_FLAG_DEFAULT_QUEUE = BIT(6), }; struct igc_nfc_filter { @@ -662,10 +659,14 @@ struct igc_nfc_rule { bool flex; }; -/* IGC supports a total of 32 NFC rules: 16 MAC address based, 8 VLAN priority - * based, 8 ethertype based and 32 Flex filter based rules. +/* IGC supports a total of 65 NFC rules, listed below in order of priority: + * - 16 MAC address based filtering rules (highest priority) + * - 8 ethertype based filtering rules + * - 32 Flex filter based filtering rules + * - 8 VLAN priority based filtering rules + * - 1 default queue rule (lowest priority) */ -#define IGC_MAX_RXNFC_RULES 64 +#define IGC_MAX_RXNFC_RULES 65 struct igc_flex_filter { u8 index; diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 86b346687196..498ba1522ca4 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -383,11 +383,15 @@ #define IGC_RXDEXT_STATERR_IPE 0x40000000 #define IGC_RXDEXT_STATERR_RXE 0x80000000 +#define IGC_MRQC_ENABLE_RSS_MQ 0x00000002 #define IGC_MRQC_RSS_FIELD_IPV4_TCP 0x00010000 #define IGC_MRQC_RSS_FIELD_IPV4 0x00020000 #define IGC_MRQC_RSS_FIELD_IPV6_TCP_EX 0x00040000 #define IGC_MRQC_RSS_FIELD_IPV6 0x00100000 #define IGC_MRQC_RSS_FIELD_IPV6_TCP 0x00200000 +#define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000 +#define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 +#define IGC_MRQC_DEFAULT_QUEUE_MASK GENMASK(5, 3) /* Header split receive */ #define IGC_RFCTL_IPV6_EX_DIS 0x00010000 diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index a7f397b58cd6..ecb35b693ce5 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1283,6 +1283,24 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, rule->flex = true; else rule->flex = false; + + /* The wildcard rule is only applied if: + * a) None of the other filtering rules match (match_flags is zero) + * b) The flow type is ETHER_FLOW only (no additional fields set) + * c) Mask for Source MAC address is not specified (all zeros) + * d) Mask for Destination MAC address is not specified (all zeros) + * e) Mask for L2 EtherType is not specified (zero) + * + * If all these conditions are met, the rule is treated as a wildcard + * rule. Default queue feature will be used, so that all packets that do + * not match any other rule will be routed to the default queue. + */ + if (!rule->filter.match_flags && + fsp->flow_type == ETHER_FLOW && + is_zero_ether_addr(fsp->m_u.ether_spec.h_source) && + is_zero_ether_addr(fsp->m_u.ether_spec.h_dest) && + !fsp->m_u.ether_spec.h_proto) + rule->filter.match_flags = IGC_FILTER_FLAG_DEFAULT_QUEUE; } /** diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 32ea4fdd3e2b..458e5eaa92e5 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3874,6 +3874,22 @@ static void igc_del_flex_filter(struct igc_adapter *adapter, wr32(IGC_WUFC, wufc); } +static void igc_set_default_queue_filter(struct igc_adapter *adapter, u32 queue) +{ + struct igc_hw *hw = &adapter->hw; + u32 mrqc = rd32(IGC_MRQC); + + mrqc &= ~IGC_MRQC_DEFAULT_QUEUE_MASK; + mrqc |= FIELD_PREP(IGC_MRQC_DEFAULT_QUEUE_MASK, queue); + wr32(IGC_MRQC, mrqc); +} + +static void igc_reset_default_queue_filter(struct igc_adapter *adapter) +{ + /* Reset the default queue to its default value which is Queue 0 */ + igc_set_default_queue_filter(adapter, 0); +} + static int igc_enable_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule) { @@ -3912,6 +3928,9 @@ static int igc_enable_nfc_rule(struct igc_adapter *adapter, return err; } + if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE) + igc_set_default_queue_filter(adapter, rule->action); + return 0; } @@ -3939,6 +3958,9 @@ static void igc_disable_nfc_rule(struct igc_adapter *adapter, if (rule->filter.match_flags & IGC_FILTER_FLAG_DST_MAC_ADDR) igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, rule->filter.dst_addr); + + if (rule->filter.match_flags & IGC_FILTER_FLAG_DEFAULT_QUEUE) + igc_reset_default_queue_filter(adapter); } /** diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 4384e892f967..3a379e6a3a2a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -346,7 +346,6 @@ struct ixgbevf_adapter { int num_rx_queues; struct ixgbevf_ring *rx_ring[MAX_TX_QUEUES]; /* One per active queue */ u64 hw_csum_rx_error; - u64 hw_rx_no_dma_resources; int num_msix_vectors; u64 alloc_rx_page_failed; u64 alloc_rx_buff_failed; @@ -363,8 +362,6 @@ struct ixgbevf_adapter { /* structs defined in ixgbe_vf.h */ struct ixgbe_hw hw; u16 msg_enable; - /* Interrupt Throttle Rate */ - u32 eitr_param; struct ixgbevf_hw_stats stats; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 846ee2b9edf1..ab5838865c3f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1704,9 +1704,11 @@ unsigned long cgx_get_lmac_bmap(void *cgxd) static int cgx_lmac_init(struct cgx *cgx) { + u8 max_dmac_filters; struct lmac *lmac; u64 lmac_list; int i, err; + int filter; /* lmac_list specifies which lmacs are enabled * when bit n is set to 1, LMAC[n] is enabled @@ -1745,6 +1747,8 @@ static int cgx_lmac_init(struct cgx *cgx) cgx->mac_ops->dmac_filter_count / cgx->lmac_count; + max_dmac_filters = lmac->mac_to_index_bmap.max; + err = rvu_alloc_bitmap(&lmac->mac_to_index_bmap); if (err) goto err_name_free; @@ -1774,6 +1778,15 @@ static int cgx_lmac_init(struct cgx *cgx) set_bit(lmac->lmac_id, &cgx->lmac_bmap); cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true); lmac->lmac_type = cgx->mac_ops->get_lmac_type(cgx, lmac->lmac_id); + + /* Disable stale DMAC filters for sane state */ + for (filter = 0; filter < max_dmac_filters; filter++) + cgx_lmac_addr_del(cgx->cgx_id, lmac->lmac_id, filter); + + /* As cgx_lmac_addr_del does not clear entry for index 0 + * so it needs to be done explicitly + */ + cgx_lmac_addr_reset(cgx->cgx_id, lmac->lmac_id); } /* Start X2P reset on given MAC block */ @@ -1951,6 +1964,12 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_disable_device; } + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); + if (err) { + dev_err(dev, "DMA mask config failed, abort\n"); + goto err_release_regions; + } + /* MAP configuration registers */ cgx->reg_base = pcim_iomap(pdev, PCI_CFG_REG_BAR_NUM, 0); if (!cgx->reg_base) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 0bc0dc79868b..933073cd2280 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -664,7 +664,12 @@ struct cgx_lmac_fwdata_s { /* Only applicable if SFP/QSFP slot is present */ struct sfp_eeprom_s sfp_eeprom; struct phy_s phy; -#define LMAC_FWDATA_RESERVED_MEM 1021 + u32 lmac_type; + u32 portm_idx; + u64 mgmt_port:1; + u64 advertised_an:1; + u64 port; +#define LMAC_FWDATA_RESERVED_MEM 1018 u64 reserved[LMAC_FWDATA_RESERVED_MEM]; }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index 890a1a5df2de..3303c475414a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -682,16 +682,19 @@ int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu, struct cgx_mac_addr_set_or_get *rsp) { int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); + struct rvu_pfvf *pfvf; u8 cgx_id, lmac_id; - if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) - return -EPERM; + if (!is_pf_cgxmapped(rvu, pf)) + return LMAC_AF_ERR_PF_NOT_MAPPED; if (rvu_npc_exact_has_match_table(rvu)) return rvu_npc_exact_mac_addr_set(rvu, req, rsp); rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + pfvf = &rvu->pf[pf]; + ether_addr_copy(pfvf->mac_addr, req->mac_addr); cgx_lmac_addr_set(cgx_id, lmac_id, req->mac_addr); return 0; @@ -769,20 +772,12 @@ int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req, struct cgx_mac_addr_set_or_get *rsp) { - int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc); - u8 cgx_id, lmac_id; - int rc = 0; - u64 cfg; + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); - if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) - return -EPERM; - - rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id); + if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, req->hdr.pcifunc))) + return LMAC_AF_ERR_PF_NOT_MAPPED; - rsp->hdr.rc = rc; - cfg = cgx_lmac_addr_get(cgx_id, lmac_id); - /* copy 48 bit mac address to req->mac_addr */ - u64_to_ether_addr(cfg, rsp->mac_addr); + ether_addr_copy(rsp->mac_addr, pfvf->mac_addr); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 0c20642f81b9..8375f18c8e07 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -867,6 +867,71 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) RVU_DEBUG_SEQ_FOPS(rvu_pf_cgx_map, rvu_pf_cgx_map_display, NULL); +static int rvu_dbg_rvu_fwdata_display(struct seq_file *s, void *unused) +{ + struct rvu *rvu = s->private; + struct rvu_fwdata *fwdata; + u8 mac[ETH_ALEN]; + int count = 0, i; + + if (!rvu->fwdata) + return -EAGAIN; + + fwdata = rvu->fwdata; + seq_puts(s, "\nRVU Firmware Data:\n"); + seq_puts(s, "\n\t\tPTP INFORMATION\n"); + seq_puts(s, "\t\t===============\n"); + seq_printf(s, "\t\texternal clockrate \t :%x\n", + fwdata->ptp_ext_clk_rate); + seq_printf(s, "\t\texternal timestamp \t :%x\n", + fwdata->ptp_ext_tstamp); + seq_puts(s, "\n"); + + seq_puts(s, "\n\t\tSDP CHANNEL INFORMATION\n"); + seq_puts(s, "\t\t=======================\n"); + seq_printf(s, "\t\tValid \t\t\t :%x\n", fwdata->channel_data.valid); + seq_printf(s, "\t\tNode ID \t\t :%x\n", + fwdata->channel_data.info.node_id); + seq_printf(s, "\t\tNumber of VFs \t\t :%x\n", + fwdata->channel_data.info.max_vfs); + seq_printf(s, "\t\tNumber of PF-Rings \t :%x\n", + fwdata->channel_data.info.num_pf_rings); + seq_printf(s, "\t\tPF SRN \t\t\t :%x\n", + fwdata->channel_data.info.pf_srn); + seq_puts(s, "\n"); + + seq_puts(s, "\n\t\tPF-INDEX MACADDRESS\n"); + seq_puts(s, "\t\t====================\n"); + for (i = 0; i < PF_MACNUM_MAX; i++) { + u64_to_ether_addr(fwdata->pf_macs[i], mac); + if (!is_zero_ether_addr(mac)) { + seq_printf(s, "\t\t %d %pM\n", i, mac); + count++; + } + } + + if (!count) + seq_puts(s, "\t\tNo valid address found\n"); + + seq_puts(s, "\n\t\tVF-INDEX MACADDRESS\n"); + seq_puts(s, "\t\t====================\n"); + count = 0; + for (i = 0; i < VF_MACNUM_MAX; i++) { + u64_to_ether_addr(fwdata->vf_macs[i], mac); + if (!is_zero_ether_addr(mac)) { + seq_printf(s, "\t\t %d %pM\n", i, mac); + count++; + } + } + + if (!count) + seq_puts(s, "\t\tNo valid address found\n"); + + return 0; +} + +RVU_DEBUG_SEQ_FOPS(rvu_fwdata, rvu_fwdata_display, NULL); + static bool rvu_dbg_is_valid_lf(struct rvu *rvu, int blkaddr, int lf, u16 *pcifunc) { @@ -2923,6 +2988,97 @@ static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *s, void *unused) RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL); +static int cgx_print_fwdata(struct seq_file *s, int lmac_id) +{ + struct cgx_lmac_fwdata_s *fwdata; + void *cgxd = s->private; + struct phy_s *phy; + struct rvu *rvu; + int cgx_id, i; + + rvu = pci_get_drvdata(pci_get_device(PCI_VENDOR_ID_CAVIUM, + PCI_DEVID_OCTEONTX2_RVU_AF, NULL)); + if (!rvu) + return -ENODEV; + + if (!rvu->fwdata) + return -EAGAIN; + + cgx_id = cgx_get_cgxid(cgxd); + + if (rvu->hw->lmac_per_cgx == CGX_LMACS_USX) + fwdata = &rvu->fwdata->cgx_fw_data_usx[cgx_id][lmac_id]; + else + fwdata = &rvu->fwdata->cgx_fw_data[cgx_id][lmac_id]; + + seq_puts(s, "\nFIRMWARE SHARED:\n"); + seq_puts(s, "\t\tSUPPORTED LINK INFORMATION\t\t\n"); + seq_puts(s, "\t\t==========================\n"); + seq_printf(s, "\t\t Link modes \t\t :%llx\n", + fwdata->supported_link_modes); + seq_printf(s, "\t\t Autoneg \t\t :%llx\n", fwdata->supported_an); + seq_printf(s, "\t\t FEC \t\t\t :%llx\n", fwdata->supported_fec); + seq_puts(s, "\n"); + + seq_puts(s, "\t\tADVERTISED LINK INFORMATION\t\t\n"); + seq_puts(s, "\t\t==========================\n"); + seq_printf(s, "\t\t Link modes \t\t :%llx\n", + (u64)fwdata->advertised_link_modes); + seq_printf(s, "\t\t Autoneg \t\t :%x\n", fwdata->advertised_an); + seq_printf(s, "\t\t FEC \t\t\t :%llx\n", fwdata->advertised_fec); + seq_puts(s, "\n"); + + seq_puts(s, "\t\tLMAC CONFIG\t\t\n"); + seq_puts(s, "\t\t============\n"); + seq_printf(s, "\t\t rw_valid \t\t :%x\n", fwdata->rw_valid); + seq_printf(s, "\t\t lmac_type \t\t :%x\n", fwdata->lmac_type); + seq_printf(s, "\t\t portm_idx \t\t :%x\n", fwdata->portm_idx); + seq_printf(s, "\t\t mgmt_port \t\t :%x\n", fwdata->mgmt_port); + seq_printf(s, "\t\t Link modes own \t :%llx\n", + (u64)fwdata->advertised_link_modes_own); + seq_puts(s, "\n"); + + seq_puts(s, "\n\t\tEEPROM DATA\n"); + seq_puts(s, "\t\t===========\n"); + seq_printf(s, "\t\t sff_id \t\t :%x\n", fwdata->sfp_eeprom.sff_id); + seq_puts(s, "\t\t data \t\t\t :\n"); + seq_puts(s, "\t\t"); + for (i = 0; i < SFP_EEPROM_SIZE; i++) { + seq_printf(s, "%x", fwdata->sfp_eeprom.buf[i]); + if ((i + 1) % 16 == 0) { + seq_puts(s, "\n"); + seq_puts(s, "\t\t"); + } + } + seq_puts(s, "\n"); + + phy = &fwdata->phy; + seq_puts(s, "\n\t\tPHY INFORMATION\n"); + seq_puts(s, "\t\t===============\n"); + seq_printf(s, "\t\t Mod type configurable \t\t :%x\n", + phy->misc.can_change_mod_type); + seq_printf(s, "\t\t Mod type \t\t\t :%x\n", phy->misc.mod_type); + seq_printf(s, "\t\t Support FEC \t\t\t :%x\n", phy->misc.has_fec_stats); + seq_printf(s, "\t\t RSFEC corrected words \t\t :%x\n", + phy->fec_stats.rsfec_corr_cws); + seq_printf(s, "\t\t RSFEC uncorrected words \t :%x\n", + phy->fec_stats.rsfec_uncorr_cws); + seq_printf(s, "\t\t BRFEC corrected words \t\t :%x\n", + phy->fec_stats.brfec_corr_blks); + seq_printf(s, "\t\t BRFEC uncorrected words \t :%x\n", + phy->fec_stats.brfec_uncorr_blks); + seq_puts(s, "\n"); + + return 0; +} + +static int rvu_dbg_cgx_fwdata_display(struct seq_file *s, void *unused) +{ + return cgx_print_fwdata(s, rvu_dbg_derive_lmacid(s)); +} + +RVU_DEBUG_SEQ_FOPS(cgx_fwdata, cgx_fwdata_display, NULL); + static void rvu_dbg_cgx_init(struct rvu *rvu) { struct mac_ops *mac_ops; @@ -2962,6 +3118,9 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) debugfs_create_file_aux_num("mac_filter", 0600, rvu->rvu_dbg.lmac, cgx, lmac_id, &rvu_dbg_cgx_dmac_flt_fops); + debugfs_create_file("fwdata", 0600, + rvu->rvu_dbg.lmac, cgx, + &rvu_dbg_cgx_fwdata_fops); } } } @@ -3808,6 +3967,9 @@ void rvu_dbg_init(struct rvu *rvu) debugfs_create_file("lmtst_map_table", 0444, rvu->rvu_dbg.root, rvu, &rvu_dbg_lmtst_map_table_fops); + debugfs_create_file("rvu_fwdata", 0444, rvu->rvu_dbg.root, rvu, + &rvu_dbg_rvu_fwdata_fops); + if (!cgx_get_cgxcnt_max()) goto create; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 99ace381cc78..625bb5a05344 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -1571,7 +1571,7 @@ handle_xdp_verdict: cq->pool_ptrs++; if (xsk_buff) { xsk_buff_free(xsk_buff); - } else if (page->pp) { + } else if (pp_page_to_nmdesc(page)->pp) { page_pool_recycle_direct(pool->page_pool, page); } else { otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 11ee7e1829bf..5a5fcde76dc0 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -4967,7 +4967,7 @@ void mtk_eth_set_dma_device(struct mtk_eth *eth, struct device *dma_dev) list_add_tail(&dev->close_list, &dev_list); } - dev_close_many(&dev_list, false); + netif_close_many(&dev_list, false); eth->dma_dev = dma_dev; @@ -5610,3 +5610,4 @@ module_platform_driver(mtk_driver); MODULE_LICENSE("GPL"); MODULE_AUTHOR("John Crispin <blogic@openwrt.org>"); MODULE_DESCRIPTION("Ethernet driver for MediaTek SoC"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c index 8498b35ec7a6..fa6b21603416 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c @@ -247,8 +247,10 @@ mtk_wed_get_memory_region(struct mtk_wed_hw *hw, const char *name, region->phy_addr = res.start; region->size = resource_size(&res); region->addr = devm_ioremap_resource(hw->dev, &res); + if (IS_ERR(region->addr)) + return PTR_ERR(region->addr); - return !region->addr ? -EINVAL : 0; + return 0; } static int diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index b33285d755b9..92a16ddb7d86 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -460,9 +460,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv, truesize += frag_info->frag_stride; if (frag_info->frag_stride == PAGE_SIZE / 2) { + struct netmem_desc *desc = pp_page_to_nmdesc(page); + frags->page_offset ^= PAGE_SIZE / 2; release = page_count(page) != 1 || - atomic_long_read(&page->pp_ref_count) != 1 || + atomic_long_read(&desc->pp_ref_count) != 1 || page_is_pfmemalloc(page) || page_to_nid(page) != numa_mem_id(); } else if (!priv->rx_headroom) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index b1aeea7c4a91..e395ef5f356e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1947,8 +1947,8 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, err = mlx5_cmd_invoke(dev, inb, outb, out, out_size, callback, context, pages_queue, token, force_polling); - if (callback) - return err; + if (callback && !err) + return 0; if (err > 0) /* Failed in FW, command didn't execute */ err = deliv_status_to_err(err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index b6340e9453c0..99295eaf2f02 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -84,9 +84,10 @@ struct page_pool; #define MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE (9) #define MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (PAGE_SIZE >> MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE) #define MLX5E_SHAMPO_LOG_WQ_HEADER_PER_PAGE (PAGE_SHIFT - MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE) -#define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE (64) -#define MLX5E_SHAMPO_WQ_RESRV_SIZE (64 * 1024) -#define MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE (4096) +#define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE_SHIFT (6) +#define MLX5E_SHAMPO_WQ_RESRV_SIZE_BASE_SHIFT (12) +#define MLX5E_SHAMPO_WQ_LOG_RESRV_SIZE (16) +#define MLX5E_SHAMPO_WQ_RESRV_SIZE BIT(MLX5E_SHAMPO_WQ_LOG_RESRV_SIZE) #define MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev) \ (6 + MLX5_CAP_GEN(mdev, cache_line_128byte)) /* HW restriction */ @@ -629,14 +630,13 @@ struct mlx5e_dma_info { }; struct mlx5e_shampo_hd { - u32 mkey; struct mlx5e_frag_page *pages; u32 hd_per_wq; u16 hd_per_wqe; unsigned long *bitmap; u16 pi; u16 ci; - __be32 key; + __be32 mkey_be; }; struct mlx5e_hw_gro_data { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index fc945bce933a..3cca06a74cf9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -414,25 +414,10 @@ u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5_core_dev *mdev, return params->log_rq_mtu_frames - log_pkts_per_wqe; } -u8 mlx5e_shampo_get_log_hd_entry_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) +static u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5e_params *params) { - return order_base_2(DIV_ROUND_UP(MLX5E_RX_MAX_HEAD, MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE)); -} - -u8 mlx5e_shampo_get_log_rsrv_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) -{ - return order_base_2(MLX5E_SHAMPO_WQ_RESRV_SIZE / MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE); -} - -u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) -{ - u32 resrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * - MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE; - - return order_base_2(DIV_ROUND_UP(resrv_size, params->sw_mtu)); + return order_base_2(DIV_ROUND_UP(MLX5E_SHAMPO_WQ_RESRV_SIZE, + params->sw_mtu)); } u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, @@ -834,13 +819,12 @@ static u32 mlx5e_shampo_get_log_cq_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { - int rsrv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * - MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE; u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk)); - int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); + int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(params)); int wq_size = BIT(mlx5e_mpwqe_get_log_rq_size(mdev, params, xsk)); int wqe_size = BIT(log_stride_sz) * num_strides; + int rsrv_size = MLX5E_SHAMPO_WQ_RESRV_SIZE; /* +1 is for the case that the pkt_per_rsrv dont consume the reservation * so we get a filler cqe for the rest of the reservation. @@ -932,12 +916,14 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev, MLX5_SET(wq, wq, shampo_enable, true); MLX5_SET(wq, wq, log_reservation_size, - mlx5e_shampo_get_log_rsrv_size(mdev, params)); + MLX5E_SHAMPO_WQ_LOG_RESRV_SIZE - + MLX5E_SHAMPO_WQ_RESRV_SIZE_BASE_SHIFT); MLX5_SET(wq, wq, log_max_num_of_packets_per_reservation, - mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); + mlx5e_shampo_get_log_pkt_per_rsrv(params)); MLX5_SET(wq, wq, log_headers_entry_size, - mlx5e_shampo_get_log_hd_entry_size(mdev, params)); + MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE - + MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE_SHIFT); lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_SHAMPO_TIMEOUT); @@ -1048,18 +1034,17 @@ u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param) { - int resv_size = BIT(mlx5e_shampo_get_log_rsrv_size(mdev, params)) * - MLX5E_SHAMPO_WQ_BASE_RESRV_SIZE; u16 num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, NULL)); - int pkt_per_resv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(mdev, params)); u8 log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL); + int pkt_per_rsrv = BIT(mlx5e_shampo_get_log_pkt_per_rsrv(params)); int wqe_size = BIT(log_stride_sz) * num_strides; + int rsrv_size = MLX5E_SHAMPO_WQ_RESRV_SIZE; u32 hd_per_wqe; /* Assumption: hd_per_wqe % 8 == 0. */ - hd_per_wqe = (wqe_size / resv_size) * pkt_per_resv; - mlx5_core_dbg(mdev, "%s hd_per_wqe = %d rsrv_size = %d wqe_size = %d pkt_per_resv = %d\n", - __func__, hd_per_wqe, resv_size, wqe_size, pkt_per_resv); + hd_per_wqe = (wqe_size / rsrv_size) * pkt_per_rsrv; + mlx5_core_dbg(mdev, "%s hd_per_wqe = %d rsrv_size = %d wqe_size = %d pkt_per_rsrv = %d\n", + __func__, hd_per_wqe, rsrv_size, wqe_size, pkt_per_rsrv); return hd_per_wqe; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index bd5877acc5b1..488ccdbc1e2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -95,12 +95,6 @@ bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); -u8 mlx5e_shampo_get_log_hd_entry_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); -u8 mlx5e_shampo_get_log_rsrv_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); -u8 mlx5e_shampo_get_log_pkt_per_rsrv(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); u32 mlx5e_shampo_hd_per_wqe(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_rq_param *rq_param); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index f0744a45db92..4e461cb03b83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -374,7 +374,7 @@ void mlx5e_reactivate_qos_sq(struct mlx5e_priv *priv, u16 qid, struct netdev_que void mlx5e_reset_qdisc(struct net_device *dev, u16 qid) { struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, qid); - struct Qdisc *qdisc = dev_queue->qdisc_sleeping; + struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); if (!qdisc) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 6501252359b0..5dc04bbfc71b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -322,14 +322,24 @@ mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i) } static inline void -mlx5e_dma_push(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size, - enum mlx5e_dma_map_type map_type) +mlx5e_dma_push_single(struct mlx5e_txqsq *sq, dma_addr_t addr, u32 size) { struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++); dma->addr = addr; dma->size = size; - dma->type = map_type; + dma->type = MLX5E_DMA_MAP_SINGLE; +} + +static inline void +mlx5e_dma_push_netmem(struct mlx5e_txqsq *sq, netmem_ref netmem, + dma_addr_t addr, u32 size) +{ + struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++); + + netmem_dma_unmap_addr_set(netmem, dma, addr, addr); + dma->size = size; + dma->type = MLX5E_DMA_MAP_PAGE; } static inline diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 5ce1b463b7a8..5d51600935a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -710,7 +710,8 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, /* No need to check page_pool_page_is_pp() as we * know this is a page_pool page. */ - page_pool_recycle_direct(page->pp, page); + page_pool_recycle_direct(pp_page_to_nmdesc(page)->pp, + page); } while (++n < num); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 820debf3fbbf..ef7322d381af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -42,8 +42,7 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) if (MLX5_CAP_IPSEC(mdev, ipsec_full_offload) && (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS || - (mdev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS && - is_mdev_legacy_mode(mdev)))) { + is_mdev_legacy_mode(mdev))) { if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_esp_trasport) && MLX5_CAP_FLOWTABLE_NIC_RX(mdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 3db31cc10719..08f06984407b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -744,7 +744,7 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn) dseg->addr = cpu_to_be64(dma_addr); dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(fsz); - mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); + mlx5e_dma_push_netmem(sq, skb_frag_netmem(frag), dma_addr, fsz); tx_fill_wi(sq, pi, MLX5E_KTLS_DUMP_WQEBBS, fsz, skb_frag_page(frag)); sq->pc += MLX5E_KTLS_DUMP_WQEBBS; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bd481f3384d0..33bdb7f1e03f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -546,18 +546,26 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq } static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev, - u16 hd_per_wq, u32 *umr_mkey) + u16 hd_per_wq, __be32 *umr_mkey) { u32 max_ksm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size)); + u32 mkey; + int err; if (max_ksm_size < hd_per_wq) { mlx5_core_err(mdev, "max ksm list size 0x%x is smaller than shampo header buffer list size 0x%x\n", max_ksm_size, hd_per_wq); return -EINVAL; } - return mlx5e_create_umr_ksm_mkey(mdev, hd_per_wq, - MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE, - umr_mkey); + + err = mlx5e_create_umr_ksm_mkey(mdev, hd_per_wq, + MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE, + &mkey); + if (err) + return err; + + *umr_mkey = cpu_to_be32(mkey); + return 0; } static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) @@ -783,11 +791,10 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, goto err_shampo_hd_info_alloc; err = mlx5e_create_rq_hd_umr_mkey(mdev, hd_per_wq, - &rq->mpwqe.shampo->mkey); + &rq->mpwqe.shampo->mkey_be); if (err) goto err_umr_mkey; - rq->mpwqe.shampo->key = cpu_to_be32(rq->mpwqe.shampo->mkey); rq->mpwqe.shampo->hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rqp); wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz)); @@ -832,7 +839,7 @@ static int mlx5_rq_shampo_alloc(struct mlx5_core_dev *mdev, err_hw_gro_data: page_pool_destroy(rq->hd_page_pool); err_hds_page_pool: - mlx5_core_destroy_mkey(mdev, rq->mpwqe.shampo->mkey); + mlx5_core_destroy_mkey(mdev, be32_to_cpu(rq->mpwqe.shampo->mkey_be)); err_umr_mkey: mlx5e_rq_shampo_hd_info_free(rq); err_shampo_hd_info_alloc: @@ -849,7 +856,8 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq) if (rq->hd_page_pool != rq->page_pool) page_pool_destroy(rq->hd_page_pool); mlx5e_rq_shampo_hd_info_free(rq); - mlx5_core_destroy_mkey(rq->mdev, rq->mpwqe.shampo->mkey); + mlx5_core_destroy_mkey(rq->mdev, + be32_to_cpu(rq->mpwqe.shampo->mkey_be)); kvfree(rq->mpwqe.shampo); } @@ -1122,7 +1130,8 @@ int mlx5e_create_rq(struct mlx5e_rq *rq, struct mlx5e_rq_param *param, u16 q_cou if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) { MLX5_SET(wq, wq, log_headers_buffer_entry_num, order_base_2(rq->mpwqe.shampo->hd_per_wq)); - MLX5_SET(wq, wq, headers_mkey, rq->mpwqe.shampo->mkey); + MLX5_SET(wq, wq, headers_mkey, + be32_to_cpu(rq->mpwqe.shampo->mkey_be)); } mlx5_fill_page_frag_array(&rq->wq_ctrl.buf, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index a4896e89fa35..218b1a09534c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -676,7 +676,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq, wqe_bbs = MLX5E_KSM_UMR_WQEBBS(ksm_entries); pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs); umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi); - build_ksm_umr(sq, umr_wqe, shampo->key, index, ksm_entries); + build_ksm_umr(sq, umr_wqe, shampo->mkey_be, index, ksm_entries); WARN_ON_ONCE(ksm_entries & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)); while (i < ksm_entries) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fef418e1ed1a..32c07a8b03d1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -5446,7 +5446,7 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) goto err_action_counter; } - err = dev_get_port_parent_id(priv->netdev, &ppid, false); + err = netif_get_port_parent_id(priv->netdev, &ppid, false); if (!err) { memcpy(&key, &ppid.id, sizeof(key)); mlx5_esw_offloads_devcom_init(esw, key); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index e6a301ba3254..319061d31602 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -196,7 +196,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(headlen); - mlx5e_dma_push(sq, dma_addr, headlen, MLX5E_DMA_MAP_SINGLE); + mlx5e_dma_push_single(sq, dma_addr, headlen); num_dma++; dseg++; } @@ -214,7 +214,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, dseg->lkey = sq->mkey_be; dseg->byte_count = cpu_to_be32(fsz); - mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE); + mlx5e_dma_push_netmem(sq, skb_frag_netmem(frag), dma_addr, fsz); num_dma++; dseg++; } @@ -616,7 +616,7 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, sq->stats->xmit_more += xmit_more; - mlx5e_dma_push(sq, txd.dma_addr, txd.len, MLX5E_DMA_MAP_SINGLE); + mlx5e_dma_push_single(sq, txd.dma_addr, txd.len); mlx5e_skb_fifo_push(&sq->db.skb_fifo, skb); mlx5e_tx_mpwqe_add_dseg(sq, &txd); mlx5e_tx_skb_update_ts_flags(skb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index e1cef8dd3b4d..91d863c8c152 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -1405,9 +1405,10 @@ esw_qos_move_node(struct mlx5_esw_sched_node *curr_node) new_node = __esw_qos_alloc_node(curr_node->esw, curr_node->ix, curr_node->type, NULL); - if (!IS_ERR(new_node)) - esw_qos_nodes_set_parent(&curr_node->children, new_node); + if (!new_node) + return ERR_PTR(-ENOMEM); + esw_qos_nodes_set_parent(&curr_node->children, new_node); return new_node; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index d59fdcb29cb8..b0b8ef3ec3c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -827,7 +827,7 @@ void mlx5_esw_vport_vhca_id_clear(struct mlx5_eswitch *esw, u16 vport_num); int mlx5_eswitch_vhca_id_to_vport(struct mlx5_eswitch *esw, u16 vhca_id, u16 *vport_num); /** - * mlx5_esw_event_info - Indicates eswitch mode changed/changing. + * struct mlx5_esw_event_info - Indicates eswitch mode changed/changing. * * @new_mode: New mode of eswitch. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0e3a977d5332..bee906661282 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1182,19 +1182,19 @@ static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw, static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_core_dev *peer_dev) { + struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch; struct mlx5_flow_destination dest = {}; struct mlx5_flow_act flow_act = {0}; struct mlx5_flow_handle **flows; - /* total vports is the same for both e-switches */ - int nvports = esw->total_vports; struct mlx5_flow_handle *flow; + struct mlx5_vport *peer_vport; struct mlx5_flow_spec *spec; - struct mlx5_vport *vport; int err, pfindex; unsigned long i; void *misc; - if (!MLX5_VPORT_MANAGER(esw->dev) && !mlx5_core_is_ecpf_esw_manager(esw->dev)) + if (!MLX5_VPORT_MANAGER(peer_dev) && + !mlx5_core_is_ecpf_esw_manager(peer_dev)) return 0; spec = kvzalloc(sizeof(*spec), GFP_KERNEL); @@ -1203,7 +1203,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, peer_miss_rules_setup(esw, peer_dev, spec, &dest); - flows = kvcalloc(nvports, sizeof(*flows), GFP_KERNEL); + flows = kvcalloc(peer_esw->total_vports, sizeof(*flows), GFP_KERNEL); if (!flows) { err = -ENOMEM; goto alloc_flows_err; @@ -1213,10 +1213,10 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, - spec, MLX5_VPORT_PF); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + esw_set_peer_miss_rule_source_port(esw, peer_esw, spec, + MLX5_VPORT_PF); flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1224,11 +1224,11 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_pf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF); flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1236,13 +1236,14 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_ecpf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } - mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) { + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { esw_set_peer_miss_rule_source_port(esw, - peer_dev->priv.eswitch, - spec, vport->vport); + peer_esw, + spec, peer_vport->vport); flow = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(esw), spec, &flow_act, &dest, 1); @@ -1250,22 +1251,22 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, err = PTR_ERR(flow); goto add_vf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } - if (mlx5_core_ec_sriov_enabled(esw->dev)) { - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - if (i >= mlx5_core_max_ec_vfs(peer_dev)) - break; - esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch, - spec, vport->vport); + if (mlx5_core_ec_sriov_enabled(peer_dev)) { + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) { + esw_set_peer_miss_rule_source_port(esw, peer_esw, + spec, + peer_vport->vport); flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); goto add_ec_vf_flow_err; } - flows[vport->index] = flow; + flows[peer_vport->index] = flow; } } @@ -1282,25 +1283,27 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, return 0; add_ec_vf_flow_err: - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - if (!flows[vport->index]) + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) { + if (!flows[peer_vport->index]) continue; - mlx5_del_flow_rules(flows[vport->index]); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_vf_flow_err: - mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) { - if (!flows[vport->index]) + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) { + if (!flows[peer_vport->index]) continue; - mlx5_del_flow_rules(flows[vport->index]); + mlx5_del_flow_rules(flows[peer_vport->index]); } - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_ecpf_flow_err: - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + mlx5_del_flow_rules(flows[peer_vport->index]); } add_pf_flow_err: esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err); @@ -1313,37 +1316,34 @@ alloc_flows_err: static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw, struct mlx5_core_dev *peer_dev) { + struct mlx5_eswitch *peer_esw = peer_dev->priv.eswitch; u16 peer_index = mlx5_get_dev_index(peer_dev); struct mlx5_flow_handle **flows; - struct mlx5_vport *vport; + struct mlx5_vport *peer_vport; unsigned long i; flows = esw->fdb_table.offloads.peer_miss_rules[peer_index]; if (!flows) return; - if (mlx5_core_ec_sriov_enabled(esw->dev)) { - mlx5_esw_for_each_ec_vf_vport(esw, i, vport, mlx5_core_max_ec_vfs(esw->dev)) { - /* The flow for a particular vport could be NULL if the other ECPF - * has fewer or no VFs enabled - */ - if (!flows[vport->index]) - continue; - mlx5_del_flow_rules(flows[vport->index]); - } + if (mlx5_core_ec_sriov_enabled(peer_dev)) { + mlx5_esw_for_each_ec_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_ec_vfs(peer_dev)) + mlx5_del_flow_rules(flows[peer_vport->index]); } - mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) - mlx5_del_flow_rules(flows[vport->index]); + mlx5_esw_for_each_vf_vport(peer_esw, i, peer_vport, + mlx5_core_max_vfs(peer_dev)) + mlx5_del_flow_rules(flows[peer_vport->index]); - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_ecpf_vport_exists(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_ECPF); + mlx5_del_flow_rules(flows[peer_vport->index]); } - if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - mlx5_del_flow_rules(flows[vport->index]); + if (mlx5_core_is_ecpf_esw_manager(peer_dev)) { + peer_vport = mlx5_eswitch_get_vport(peer_esw, MLX5_VPORT_PF); + mlx5_del_flow_rules(flows[peer_vport->index]); } kvfree(flows); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c index d45e1145d197..c6436c3a7a83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c @@ -727,8 +727,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd, u32 *s_ipv6, *d_ipv6; if (HWS_IS_FLD_SET_SZ(match_param, outer_headers.l4_type, 0x2) || - HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c2, 0xe) || - HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c4, 0x4)) { + HWS_IS_FLD_SET_SZ(match_param, outer_headers.l4_type_ext, 0x4) || + HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c6, 0xa) || + HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_d4, 0x4)) { mlx5hws_err(cd->ctx, "Unsupported outer parameters set\n"); return -EINVAL; } @@ -903,8 +904,9 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd, u32 *s_ipv6, *d_ipv6; if (HWS_IS_FLD_SET_SZ(match_param, inner_headers.l4_type, 0x2) || - HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c2, 0xe) || - HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c4, 0x4)) { + HWS_IS_FLD_SET_SZ(match_param, inner_headers.l4_type_ext, 0x4) || + HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c6, 0xa) || + HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_d4, 0x4)) { mlx5hws_err(cd->ctx, "Unsupported inner parameters set\n"); return -EINVAL; } @@ -1279,7 +1281,8 @@ hws_definer_conv_misc2(struct mlx5hws_definer_conv_data *cd, struct mlx5hws_definer_fc *curr_fc; if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1a0, 0x8) || - HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1b8, 0x8) || + HWS_IS_FLD_SET_SZ(match_param, + misc_parameters_2.ipsec_next_header, 0x8) || HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1c0, 0x40) || HWS_IS_FLD_SET(match_param, misc_parameters_2.macsec_syndrome) || HWS_IS_FLD_SET(match_param, misc_parameters_2.ipsec_syndrome)) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 058dcabfaa2e..a2e97b712a3d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -156,7 +156,7 @@ static int mlxsw_pci_napi_devs_init(struct mlxsw_pci *mlxsw_pci) } strscpy(mlxsw_pci->napi_dev_rx->name, "mlxsw_rx", sizeof(mlxsw_pci->napi_dev_rx->name)); - dev_set_threaded(mlxsw_pci->napi_dev_rx, true); + netif_set_threaded(mlxsw_pci->napi_dev_rx, true); return 0; diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index d6c0699bc8cf..43f034e180c4 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -8,6 +8,7 @@ #include <linux/version.h> #include <linux/msi.h> #include <linux/irqdomain.h> +#include <linux/export.h> #include <net/mana/mana.h> #include <net/mana/hw_channel.h> diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a7973651ae51..550843e2164b 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -10,6 +10,7 @@ #include <linux/filter.h> #include <linux/mm.h> #include <linux/pci.h> +#include <linux/export.h> #include <net/checksum.h> #include <net/ip6_checksum.h> diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index c9f4976a3527..4e79bf88688a 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -3075,7 +3075,7 @@ static int ravb_probe(struct platform_device *pdev) if (info->coalesce_irqs) { netdev_sw_irq_coalesce_default_on(ndev); if (num_present_cpus() == 1) - dev_set_threaded(ndev, true); + netif_set_threaded(ndev, true); } /* Network device register */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c index 9a774046455b..df4ca897a60c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-renesas-gbeth.c @@ -136,6 +136,7 @@ static struct platform_driver renesas_gbeth_driver = { .probe = renesas_gbeth_probe, .driver = { .name = "renesas-gbeth", + .pm = &stmmac_pltfr_pm_ops, .of_match_table = renesas_gbeth_match, }, }; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index ddfd1c02a885..da53eb04b0a4 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -288,8 +288,12 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac) int i; addr = lower_32_bits(prueth->msmcram.pa); - if (slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + if (slice) { + if (prueth->pdata.banked_ms_ram) + addr += MSMC_RAM_BANK_SIZE; + else + addr += PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE; + } if (addr % SZ_64K) { dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n"); @@ -297,43 +301,66 @@ static int prueth_fw_offload_buffer_setup(struct prueth_emac *emac) } bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; - /* workaround for f/w bug. bpool 0 needs to be initialized */ - for (i = 0; i < PRUETH_NUM_BUF_POOLS; i++) { + + /* Configure buffer pools for forwarding buffers + * - used by firmware to store packets to be forwarded to other port + * - 8 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) { writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len); - addr += PRUETH_EMAC_BUF_POOL_SIZE; + writel(PRUETH_SW_FWD_BUF_POOL_SIZE, &bpool_cfg[i].len); + addr += PRUETH_SW_FWD_BUF_POOL_SIZE; } - if (!slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; - else - addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; - - for (i = PRUETH_NUM_BUF_POOLS; - i < 2 * PRUETH_SW_NUM_BUF_POOLS_HOST + PRUETH_NUM_BUF_POOLS; - i++) { - /* The driver only uses first 4 queues per PRU so only initialize them */ - if (i % PRUETH_SW_NUM_BUF_POOLS_HOST < PRUETH_SW_NUM_BUF_POOLS_PER_PRU) { - writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_SW_BUF_POOL_SIZE_HOST, &bpool_cfg[i].len); - addr += PRUETH_SW_BUF_POOL_SIZE_HOST; + /* Configure buffer pools for Local Injection buffers + * - used by firmware to store packets received from host core + * - 16 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) { + int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; + + /* The driver only uses first 4 queues per PRU, + * so only initialize buffer for them + */ + if ((i % PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE) + < PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) { + writel(addr, &bpool_cfg[cfg_idx].addr); + writel(PRUETH_SW_LI_BUF_POOL_SIZE, + &bpool_cfg[cfg_idx].len); + addr += PRUETH_SW_LI_BUF_POOL_SIZE; } else { - writel(0, &bpool_cfg[i].addr); - writel(0, &bpool_cfg[i].len); + writel(0, &bpool_cfg[cfg_idx].addr); + writel(0, &bpool_cfg[cfg_idx].len); } } - if (!slice) - addr += PRUETH_SW_NUM_BUF_POOLS_HOST * PRUETH_SW_BUF_POOL_SIZE_HOST; - else - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + /* Express RX buffer queue + * - used by firmware to store express packets to be transmitted + * to the host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; + for (i = 0; i < 3; i++) + writel(addr, &rxq_ctx->start[i]); + + addr += PRUETH_SW_HOST_EXP_BUF_POOL_SIZE; + writel(addr, &rxq_ctx->end); + /* Pre-emptible RX buffer queue + * - used by firmware to store preemptible packets to be transmitted + * to the host core + */ rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]); - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; - writel(addr - SZ_2K, &rxq_ctx->end); + addr += PRUETH_SW_HOST_PRE_BUF_POOL_SIZE; + writel(addr, &rxq_ctx->end); + + /* Set pointer for default dropped packet write + * - used by firmware to temporarily store packet to be dropped + */ + rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET; + writel(addr, &rxq_ctx->start[0]); return 0; } @@ -347,13 +374,13 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) u32 addr; int i; - /* Layout to have 64KB aligned buffer pool - * |BPOOL0|BPOOL1|RX_CTX0|RX_CTX1| - */ - addr = lower_32_bits(prueth->msmcram.pa); - if (slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; + if (slice) { + if (prueth->pdata.banked_ms_ram) + addr += MSMC_RAM_BANK_SIZE; + else + addr += PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE; + } if (addr % SZ_64K) { dev_warn(prueth->dev, "buffer pool needs to be 64KB aligned\n"); @@ -361,39 +388,66 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac) } bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; - /* workaround for f/w bug. bpool 0 needs to be initilalized */ - writel(addr, &bpool_cfg[0].addr); - writel(0, &bpool_cfg[0].len); - for (i = PRUETH_EMAC_BUF_POOL_START; - i < PRUETH_EMAC_BUF_POOL_START + PRUETH_NUM_BUF_POOLS; - i++) { - writel(addr, &bpool_cfg[i].addr); - writel(PRUETH_EMAC_BUF_POOL_SIZE, &bpool_cfg[i].len); - addr += PRUETH_EMAC_BUF_POOL_SIZE; + /* Configure buffer pools for forwarding buffers + * - in mac mode - no forwarding so initialize all pools to 0 + * - 8 total pools per slice + */ + for (i = 0; i < PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; i++) { + writel(0, &bpool_cfg[i].addr); + writel(0, &bpool_cfg[i].len); } - if (!slice) - addr += PRUETH_NUM_BUF_POOLS * PRUETH_EMAC_BUF_POOL_SIZE; - else - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE * 2; + /* Configure buffer pools for Local Injection buffers + * - used by firmware to store packets received from host core + * - 16 total pools per slice + */ + bpool_cfg = emac->dram.va + BUFFER_POOL_0_ADDR_OFFSET; + for (i = 0; i < PRUETH_NUM_LI_BUF_POOLS_PER_SLICE; i++) { + int cfg_idx = i + PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE; + + /* In EMAC mode, only first 4 buffers are used, + * as 1 slice needs to handle only 1 port + */ + if (i < PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE) { + writel(addr, &bpool_cfg[cfg_idx].addr); + writel(PRUETH_EMAC_LI_BUF_POOL_SIZE, + &bpool_cfg[cfg_idx].len); + addr += PRUETH_EMAC_LI_BUF_POOL_SIZE; + } else { + writel(0, &bpool_cfg[cfg_idx].addr); + writel(0, &bpool_cfg[cfg_idx].len); + } + } - /* Pre-emptible RX buffer queue */ - rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; + /* Express RX buffer queue + * - used by firmware to store express packets to be transmitted + * to host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]); - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + addr += PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE; writel(addr, &rxq_ctx->end); - /* Express RX buffer queue */ - rxq_ctx = emac->dram.va + HOST_RX_Q_EXP_CONTEXT_OFFSET; + /* Pre-emptible RX buffer queue + * - used by firmware to store preemptible packets to be transmitted + * to host core + */ + rxq_ctx = emac->dram.va + HOST_RX_Q_PRE_CONTEXT_OFFSET; for (i = 0; i < 3; i++) writel(addr, &rxq_ctx->start[i]); - addr += PRUETH_EMAC_RX_CTX_BUF_SIZE; + addr += PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE; writel(addr, &rxq_ctx->end); + /* Set pointer for default dropped packet write + * - used by firmware to temporarily store packet to be dropped + */ + rxq_ctx = emac->dram.va + DEFAULT_MSMC_Q_OFFSET; + writel(addr, &rxq_ctx->start[0]); + return 0; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index c884e9fa099e..60d69744ffae 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -26,21 +26,71 @@ struct icssg_flow_cfg { #define PRUETH_MAX_RX_FLOWS 1 /* excluding default flow */ #define PRUETH_RX_FLOW_DATA 0 -#define PRUETH_EMAC_BUF_POOL_SIZE SZ_8K -#define PRUETH_EMAC_POOLS_PER_SLICE 24 -#define PRUETH_EMAC_BUF_POOL_START 8 -#define PRUETH_NUM_BUF_POOLS 8 -#define PRUETH_EMAC_RX_CTX_BUF_SIZE SZ_16K /* per slice */ -#define MSMC_RAM_SIZE \ - (2 * (PRUETH_EMAC_BUF_POOL_SIZE * PRUETH_NUM_BUF_POOLS + \ - PRUETH_EMAC_RX_CTX_BUF_SIZE * 2)) - -#define PRUETH_SW_BUF_POOL_SIZE_HOST SZ_4K -#define PRUETH_SW_NUM_BUF_POOLS_HOST 8 -#define PRUETH_SW_NUM_BUF_POOLS_PER_PRU 4 -#define MSMC_RAM_SIZE_SWITCH_MODE \ - (MSMC_RAM_SIZE + \ - (2 * PRUETH_SW_BUF_POOL_SIZE_HOST * PRUETH_SW_NUM_BUF_POOLS_HOST)) +/* Defines for forwarding path buffer pools: + * - used by firmware to store packets to be forwarded to other port + * - 8 total pools per slice + * - only used in switch mode (as no forwarding in mac mode) + */ +#define PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE 8 +#define PRUETH_SW_FWD_BUF_POOL_SIZE (SZ_8K) + +/* Defines for local injection path buffer pools: + * - used by firmware to store packets received from host core + * - 16 total pools per slice + * - 8 pools per port per slice and each slice handles both ports + * - only 4 out of 8 pools used per port (as only 4 real QoS levels in ICSSG) + * - switch mode: 8 total pools used + * - mac mode: 4 total pools used + */ +#define PRUETH_NUM_LI_BUF_POOLS_PER_SLICE 16 +#define PRUETH_NUM_LI_BUF_POOLS_PER_PORT_PER_SLICE 8 +#define PRUETH_SW_LI_BUF_POOL_SIZE SZ_4K +#define PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE 8 +#define PRUETH_SW_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE 4 +#define PRUETH_EMAC_LI_BUF_POOL_SIZE SZ_8K +#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE 4 +#define PRUETH_EMAC_USED_LI_BUF_POOLS_PER_PORT_PER_SLICE 4 + +/* Defines for host egress path - express and preemptible buffers + * - used by firmware to store express and preemptible packets + * to be transmitted to host core + * - used by both mac/switch modes + */ +#define PRUETH_SW_HOST_EXP_BUF_POOL_SIZE SZ_16K +#define PRUETH_SW_HOST_PRE_BUF_POOL_SIZE (SZ_16K - SZ_2K) +#define PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE PRUETH_SW_HOST_EXP_BUF_POOL_SIZE +#define PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE PRUETH_SW_HOST_PRE_BUF_POOL_SIZE + +/* Buffer used by firmware to temporarily store packet to be dropped */ +#define PRUETH_SW_DROP_PKT_BUF_SIZE SZ_2K +#define PRUETH_EMAC_DROP_PKT_BUF_SIZE PRUETH_SW_DROP_PKT_BUF_SIZE + +/* Total switch mode memory usage for buffers per slice */ +#define PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE \ + (PRUETH_SW_FWD_BUF_POOL_SIZE * PRUETH_NUM_FWD_BUF_POOLS_PER_SLICE + \ + PRUETH_SW_LI_BUF_POOL_SIZE * PRUETH_SW_USED_LI_BUF_POOLS_PER_SLICE + \ + PRUETH_SW_HOST_EXP_BUF_POOL_SIZE + \ + PRUETH_SW_HOST_PRE_BUF_POOL_SIZE + \ + PRUETH_SW_DROP_PKT_BUF_SIZE) + +/* Total switch mode memory usage for all buffers */ +#define PRUETH_SW_TOTAL_BUF_SIZE \ + (2 * PRUETH_SW_TOTAL_BUF_SIZE_PER_SLICE) + +/* Total mac mode memory usage for buffers per slice */ +#define PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE \ + (PRUETH_EMAC_LI_BUF_POOL_SIZE * \ + PRUETH_EMAC_USED_LI_BUF_POOLS_PER_SLICE + \ + PRUETH_EMAC_HOST_EXP_BUF_POOL_SIZE + \ + PRUETH_EMAC_HOST_PRE_BUF_POOL_SIZE + \ + PRUETH_EMAC_DROP_PKT_BUF_SIZE) + +/* Total mac mode memory usage for all buffers */ +#define PRUETH_EMAC_TOTAL_BUF_SIZE \ + (2 * PRUETH_EMAC_TOTAL_BUF_SIZE_PER_SLICE) + +/* Size of 1 bank of MSMC/OC_SRAM memory */ +#define MSMC_RAM_BANK_SIZE SZ_256K #define PRUETH_SWITCH_FDB_MASK ((SIZE_OF_FDB / NUMBER_OF_FDB_BUCKET_ENTRIES) - 1) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 2aa812cbab92..2b973d6e2341 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1814,10 +1814,15 @@ static int prueth_probe(struct platform_device *pdev) goto put_mem; } - msmc_ram_size = MSMC_RAM_SIZE; prueth->is_switchmode_supported = prueth->pdata.switch_mode; - if (prueth->is_switchmode_supported) - msmc_ram_size = MSMC_RAM_SIZE_SWITCH_MODE; + if (prueth->pdata.banked_ms_ram) { + /* Reserve 2 MSMC RAM banks for buffers to avoid arbitration */ + msmc_ram_size = (2 * MSMC_RAM_BANK_SIZE); + } else { + msmc_ram_size = PRUETH_EMAC_TOTAL_BUF_SIZE; + if (prueth->is_switchmode_supported) + msmc_ram_size = PRUETH_SW_TOTAL_BUF_SIZE; + } /* NOTE: FW bug needs buffer base to be 64KB aligned */ prueth->msmcram.va = @@ -1985,7 +1990,8 @@ put_iep0: free_pool: gen_pool_free(prueth->sram_pool, - (unsigned long)prueth->msmcram.va, msmc_ram_size); + (unsigned long)prueth->msmcram.va, + prueth->msmcram.size); put_mem: pruss_release_mem_region(prueth->pruss, &prueth->shram); @@ -2037,8 +2043,8 @@ static void prueth_remove(struct platform_device *pdev) icss_iep_put(prueth->iep0); gen_pool_free(prueth->sram_pool, - (unsigned long)prueth->msmcram.va, - MSMC_RAM_SIZE); + (unsigned long)prueth->msmcram.va, + prueth->msmcram.size); pruss_release_mem_region(prueth->pruss, &prueth->shram); @@ -2055,12 +2061,14 @@ static const struct prueth_pdata am654_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, .quirk_10m_link_issue = 1, .switch_mode = 1, + .banked_ms_ram = 0, }; static const struct prueth_pdata am64x_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_RING, .quirk_10m_link_issue = 1, .switch_mode = 1, + .banked_ms_ram = 1, }; static const struct of_device_id prueth_dt_match[] = { diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 9ca2e7fdefbd..ca8a22a4a5da 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -252,11 +252,13 @@ struct prueth_emac { * @fdqring_mode: Free desc queue mode * @quirk_10m_link_issue: 10M link detect errata * @switch_mode: switch firmware support + * @banked_ms_ram: banked memory support */ struct prueth_pdata { enum k3_ring_mode fdqring_mode; u32 quirk_10m_link_issue:1; u32 switch_mode:1; + u32 banked_ms_ram:1; }; struct icssg_firmwares { diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index ff5f41bf499e..5e225310c9de 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -367,7 +367,7 @@ static irqreturn_t prueth_rx_mgm_ts_thread_sr1(int irq, void *dev_id) return IRQ_NONE; prueth_tx_ts_sr1(emac, (void *)page_address(page)); - page_pool_recycle_direct(page->pp, page); + page_pool_recycle_direct(pp_page_to_nmdesc(page)->pp, page); return IRQ_HANDLED; } @@ -392,7 +392,7 @@ static irqreturn_t prueth_rx_mgm_rsp_thread(int irq, void *dev_id) complete(&emac->cmd_complete); } - page_pool_recycle_direct(page->pp, page); + page_pool_recycle_direct(pp_page_to_nmdesc(page)->pp, page); return IRQ_HANDLED; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h index 490a9cc06fb0..7e053b8af3ec 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_switch_map.h +++ b/drivers/net/ethernet/ti/icssg/icssg_switch_map.h @@ -180,6 +180,9 @@ /* Used to notify the FW of the current link speed */ #define PORT_LINK_SPEED_OFFSET 0x00A8 +/* 2k memory pointer reserved for default writes by PRU0*/ +#define DEFAULT_MSMC_Q_OFFSET 0x00AC + /* TAS gate mask for windows list0 */ #define TAS_GATE_MASK_LIST0 0x0100 diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 0ed2fd833a5d..660f3db11766 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -784,9 +784,9 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_PRE_CHANGEADDR: prechaddr_info = ptr; list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - err = dev_pre_changeaddr_notify(ipvlan->dev, - prechaddr_info->dev_addr, - extack); + err = netif_pre_changeaddr_notify(ipvlan->dev, + prechaddr_info->dev_addr, + extack); if (err) return notifier_from_errno(err); } @@ -1094,3 +1094,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>"); MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs"); MODULE_ALIAS_RTNL_LINK("ipvlan"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 01c7edb28d96..2672d071b325 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -314,6 +314,8 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev) &nsim_dev->fw_update_status); debugfs_create_u32("fw_update_overwrite_mask", 0600, nsim_dev->ddir, &nsim_dev->fw_update_overwrite_mask); + debugfs_create_u32("fw_update_flash_chunk_time_ms", 0600, nsim_dev->ddir, + &nsim_dev->fw_update_flash_chunk_time_ms); debugfs_create_u32("max_macs", 0600, nsim_dev->ddir, &nsim_dev->max_macs); debugfs_create_bool("test1", 0600, nsim_dev->ddir, @@ -1015,9 +1017,9 @@ static int nsim_dev_info_get(struct devlink *devlink, DEVLINK_INFO_VERSION_TYPE_COMPONENT); } -#define NSIM_DEV_FLASH_SIZE 500000 +#define NSIM_DEV_FLASH_SIZE 50000 #define NSIM_DEV_FLASH_CHUNK_SIZE 1000 -#define NSIM_DEV_FLASH_CHUNK_TIME_MS 10 +#define NSIM_DEV_FLASH_CHUNK_TIME_MS_DEFAULT 100 static int nsim_dev_flash_update(struct devlink *devlink, struct devlink_flash_update_params *params, @@ -1041,7 +1043,7 @@ static int nsim_dev_flash_update(struct devlink *devlink, params->component, i * NSIM_DEV_FLASH_CHUNK_SIZE, NSIM_DEV_FLASH_SIZE); - msleep(NSIM_DEV_FLASH_CHUNK_TIME_MS); + msleep(nsim_dev->fw_update_flash_chunk_time_ms ?: 1); } if (nsim_dev->fw_update_status) { @@ -1585,6 +1587,7 @@ int nsim_drv_probe(struct nsim_bus_dev *nsim_bus_dev) INIT_LIST_HEAD(&nsim_dev->port_list); nsim_dev->fw_update_status = true; nsim_dev->fw_update_overwrite_mask = 0; + nsim_dev->fw_update_flash_chunk_time_ms = NSIM_DEV_FLASH_CHUNK_TIME_MS_DEFAULT; nsim_dev->max_macs = NSIM_DEV_MAX_MACS_DEFAULT; nsim_dev->test1 = NSIM_DEV_TEST1_DEFAULT; spin_lock_init(&nsim_dev->fa_cookie_lock); diff --git a/drivers/net/netdevsim/hwstats.c b/drivers/net/netdevsim/hwstats.c index 66b3215db3ac..1abe48e35ca3 100644 --- a/drivers/net/netdevsim/hwstats.c +++ b/drivers/net/netdevsim/hwstats.c @@ -220,7 +220,6 @@ nsim_dev_hwstats_enable_ifindex(struct nsim_dev_hwstats *hwstats, struct nsim_dev_hwstats_netdev *hwsdev; struct nsim_dev *nsim_dev; struct net_device *netdev; - bool notify = false; struct net *net; int err = 0; @@ -251,11 +250,9 @@ nsim_dev_hwstats_enable_ifindex(struct nsim_dev_hwstats *hwstats, if (netdev_offload_xstats_enabled(netdev, type)) { nsim_dev_hwsdev_enable(hwsdev, NULL); - notify = true; + rtnl_offload_xstats_notify(netdev); } - if (notify) - rtnl_offload_xstats_notify(netdev); rtnl_unlock(); return err; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 611e7f65291c..39fe28af48b9 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -387,15 +387,34 @@ static int nsim_get_iflink(const struct net_device *dev) static int nsim_rcv(struct nsim_rq *rq, int budget) { struct net_device *dev = rq->napi.dev; + struct bpf_prog *xdp_prog; + struct netdevsim *ns; struct sk_buff *skb; unsigned int skblen; int i, ret; + ns = netdev_priv(dev); + xdp_prog = READ_ONCE(ns->xdp.prog); + for (i = 0; i < budget; i++) { if (skb_queue_empty(&rq->skb_queue)) break; skb = skb_dequeue(&rq->skb_queue); + + if (xdp_prog) { + /* skb might be freed directly by XDP, save the len */ + skblen = skb->len; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + skb_checksum_help(skb); + ret = do_xdp_generic(xdp_prog, &skb); + if (ret != XDP_PASS) { + dev_dstats_rx_add(dev, skblen); + continue; + } + } + /* skb might be discard at netif_receive_skb, save the len */ skblen = skb->len; skb_mark_napi_id(skb, &rq->napi); @@ -898,7 +917,8 @@ nsim_pp_hold_write(struct file *file, const char __user *data, if (!ns->page) ret = -ENOMEM; } else { - page_pool_put_full_page(ns->page->pp, ns->page, false); + page_pool_put_full_page(pp_page_to_nmdesc(ns->page)->pp, + ns->page, false); ns->page = NULL; } @@ -936,7 +956,7 @@ static void nsim_setup(struct net_device *dev) NETIF_F_TSO; dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; dev->max_mtu = ETH_MAX_MTU; - dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD; + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_HW_OFFLOAD; } static int nsim_queue_init(struct netdevsim *ns) @@ -1126,7 +1146,8 @@ void nsim_destroy(struct netdevsim *ns) /* Put this intentionally late to exercise the orphaning path */ if (ns->page) { - page_pool_put_full_page(ns->page->pp, ns->page, false); + page_pool_put_full_page(pp_page_to_nmdesc(ns->page)->pp, + ns->page, false); ns->page = NULL; } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 8eeeb9256077..bddd24c1389d 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -317,6 +317,7 @@ struct nsim_dev { struct list_head port_list; bool fw_update_status; u32 fw_update_overwrite_mask; + u32 fw_update_flash_chunk_time_ms; u32 max_macs; bool test1; bool dont_allow_reload; diff --git a/drivers/net/pcs/pcs-xpcs-plat.c b/drivers/net/pcs/pcs-xpcs-plat.c index 137d91038fb4..9e1ccc319a1d 100644 --- a/drivers/net/pcs/pcs-xpcs-plat.c +++ b/drivers/net/pcs/pcs-xpcs-plat.c @@ -66,7 +66,7 @@ static int xpcs_mmio_read_reg_indirect(struct dw_xpcs_plat *pxpcs, switch (pxpcs->reg_width) { case 4: writel(page, pxpcs->reg_base + (DW_VR_CSR_VIEWPORT << 2)); - ret = readl(pxpcs->reg_base + (ofs << 2)); + ret = readl(pxpcs->reg_base + (ofs << 2)) & 0xffff; break; default: writew(page, pxpcs->reg_base + (DW_VR_CSR_VIEWPORT << 1)); @@ -124,7 +124,7 @@ static int xpcs_mmio_read_reg_direct(struct dw_xpcs_plat *pxpcs, switch (pxpcs->reg_width) { case 4: - ret = readl(pxpcs->reg_base + (csr << 2)); + ret = readl(pxpcs->reg_base + (csr << 2)) & 0xffff; break; default: ret = readw(pxpcs->reg_base + (csr << 1)); diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 6d10ef7e9a8a..04e84ebb646c 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -124,6 +124,7 @@ struct qca807x_priv { bool dac_full_amplitude; bool dac_full_bias_current; bool dac_disable_bias_current_tweak; + struct qcom_phy_hw_stats hw_stats; }; static int qca807x_cable_test_start(struct phy_device *phydev) @@ -768,6 +769,10 @@ static int qca807x_config_init(struct phy_device *phydev) return ret; } + ret = qcom_phy_counter_config(phydev); + if (ret) + return ret; + control_dac = phy_read_mmd(phydev, MDIO_MMD_AN, QCA807X_MMD7_1000BASE_T_POWER_SAVE_PER_CABLE_LENGTH); control_dac &= ~QCA807X_CONTROL_DAC_MASK; @@ -782,6 +787,22 @@ static int qca807x_config_init(struct phy_device *phydev) control_dac); } +static int qca807x_update_stats(struct phy_device *phydev) +{ + struct qca807x_priv *priv = phydev->priv; + + return qcom_phy_update_stats(phydev, &priv->hw_stats); +} + +static void qca807x_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats) +{ + struct qca807x_priv *priv = phydev->priv; + + qcom_phy_get_stats(stats, priv->hw_stats); +} + static struct phy_driver qca807x_drivers[] = { { PHY_ID_MATCH_EXACT(PHY_ID_QCA8072), @@ -800,6 +821,10 @@ static struct phy_driver qca807x_drivers[] = { .suspend = genphy_suspend, .cable_test_start = qca807x_cable_test_start, .cable_test_get_status = qca808x_cable_test_get_status, + .update_stats = qca807x_update_stats, + .get_phy_stats = qca807x_get_phy_stats, + .set_wol = at8031_set_wol, + .get_wol = at803x_get_wol, }, { PHY_ID_MATCH_EXACT(PHY_ID_QCA8075), @@ -823,6 +848,10 @@ static struct phy_driver qca807x_drivers[] = { .led_hw_is_supported = qca807x_led_hw_is_supported, .led_hw_control_set = qca807x_led_hw_control_set, .led_hw_control_get = qca807x_led_hw_control_get, + .update_stats = qca807x_update_stats, + .get_phy_stats = qca807x_get_phy_stats, + .set_wol = at8031_set_wol, + .get_wol = at803x_get_wol, }, }; module_phy_driver(qca807x_drivers); diff --git a/drivers/net/phy/qcom/qca808x.c b/drivers/net/phy/qcom/qca808x.c index 6de16c0eaa08..8eb51b1a006c 100644 --- a/drivers/net/phy/qcom/qca808x.c +++ b/drivers/net/phy/qcom/qca808x.c @@ -93,6 +93,7 @@ MODULE_LICENSE("GPL"); struct qca808x_priv { int led_polarity_mode; + struct qcom_phy_hw_stats hw_stats; }; static int qca808x_phy_fast_retrain_config(struct phy_device *phydev) @@ -243,6 +244,10 @@ static int qca808x_config_init(struct phy_device *phydev) qca808x_fill_possible_interfaces(phydev); + ret = qcom_phy_counter_config(phydev); + if (ret) + return ret; + /* Configure adc threshold as 100mv for the link 10M */ return at803x_debug_reg_mask(phydev, QCA808X_PHY_DEBUG_ADC_THRESHOLD, QCA808X_ADC_THRESHOLD_MASK, @@ -622,6 +627,22 @@ static int qca808x_led_polarity_set(struct phy_device *phydev, int index, active_low ? 0 : QCA808X_LED_ACTIVE_HIGH); } +static int qca808x_update_stats(struct phy_device *phydev) +{ + struct qca808x_priv *priv = phydev->priv; + + return qcom_phy_update_stats(phydev, &priv->hw_stats); +} + +static void qca808x_get_phy_stats(struct phy_device *phydev, + struct ethtool_eth_phy_stats *eth_stats, + struct ethtool_phy_stats *stats) +{ + struct qca808x_priv *priv = phydev->priv; + + qcom_phy_get_stats(stats, priv->hw_stats); +} + static struct phy_driver qca808x_driver[] = { { /* Qualcomm QCA8081 */ @@ -651,6 +672,8 @@ static struct phy_driver qca808x_driver[] = { .led_hw_control_set = qca808x_led_hw_control_set, .led_hw_control_get = qca808x_led_hw_control_get, .led_polarity_set = qca808x_led_polarity_set, + .update_stats = qca808x_update_stats, + .get_phy_stats = qca808x_get_phy_stats, }, }; module_phy_driver(qca808x_driver); diff --git a/drivers/net/phy/qcom/qcom-phy-lib.c b/drivers/net/phy/qcom/qcom-phy-lib.c index af7d0d8e81be..965c2bb99a9b 100644 --- a/drivers/net/phy/qcom/qcom-phy-lib.c +++ b/drivers/net/phy/qcom/qcom-phy-lib.c @@ -699,3 +699,78 @@ int qca808x_led_reg_blink_set(struct phy_device *phydev, u16 reg, return 0; } EXPORT_SYMBOL_GPL(qca808x_led_reg_blink_set); + +/* Enable CRC checking for both received and transmitted frames to ensure + * accurate counter recording. The hardware supports a 32-bit counter, + * configure the counter to clear after it is read to facilitate the + * implementation of a 64-bit software counter + */ +int qcom_phy_counter_config(struct phy_device *phydev) +{ + return phy_set_bits_mmd(phydev, MDIO_MMD_AN, QCA808X_MMD7_CNT_CTRL, + QCA808X_MMD7_CNT_CTRL_CRC_CHECK_EN | + QCA808X_MMD7_CNT_CTRL_READ_CLEAR_EN); +} +EXPORT_SYMBOL_GPL(qcom_phy_counter_config); + +int qcom_phy_update_stats(struct phy_device *phydev, + struct qcom_phy_hw_stats *hw_stats) +{ + int ret; + u32 cnt; + + /* PHY 32-bit counter for RX packets. */ + ret = phy_read_mmd(phydev, MDIO_MMD_AN, QCA808X_MMD7_CNT_RX_PKT_15_0); + if (ret < 0) + return ret; + + cnt = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_AN, QCA808X_MMD7_CNT_RX_PKT_31_16); + if (ret < 0) + return ret; + + cnt |= ret << 16; + hw_stats->rx_pkts += cnt; + + /* PHY 16-bit counter for RX CRC error packets. */ + ret = phy_read_mmd(phydev, MDIO_MMD_AN, QCA808X_MMD7_CNT_RX_ERR_PKT); + if (ret < 0) + return ret; + + hw_stats->rx_err_pkts += ret; + + /* PHY 32-bit counter for TX packets. */ + ret = phy_read_mmd(phydev, MDIO_MMD_AN, QCA808X_MMD7_CNT_TX_PKT_15_0); + if (ret < 0) + return ret; + + cnt = ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_AN, QCA808X_MMD7_CNT_TX_PKT_31_16); + if (ret < 0) + return ret; + + cnt |= ret << 16; + hw_stats->tx_pkts += cnt; + + /* PHY 16-bit counter for TX CRC error packets. */ + ret = phy_read_mmd(phydev, MDIO_MMD_AN, QCA808X_MMD7_CNT_TX_ERR_PKT); + if (ret < 0) + return ret; + + hw_stats->tx_err_pkts += ret; + + return 0; +} +EXPORT_SYMBOL_GPL(qcom_phy_update_stats); + +void qcom_phy_get_stats(struct ethtool_phy_stats *stats, + struct qcom_phy_hw_stats hw_stats) +{ + stats->tx_packets = hw_stats.tx_pkts; + stats->tx_errors = hw_stats.tx_err_pkts; + stats->rx_packets = hw_stats.rx_pkts; + stats->rx_errors = hw_stats.rx_err_pkts; +} +EXPORT_SYMBOL_GPL(qcom_phy_get_stats); diff --git a/drivers/net/phy/qcom/qcom.h b/drivers/net/phy/qcom/qcom.h index 7f7151c8baca..5071e7149a11 100644 --- a/drivers/net/phy/qcom/qcom.h +++ b/drivers/net/phy/qcom/qcom.h @@ -195,6 +195,17 @@ #define AT803X_MIN_DOWNSHIFT 2 #define AT803X_MAX_DOWNSHIFT 9 +#define QCA808X_MMD7_CNT_CTRL 0x8029 +#define QCA808X_MMD7_CNT_CTRL_READ_CLEAR_EN BIT(1) +#define QCA808X_MMD7_CNT_CTRL_CRC_CHECK_EN BIT(0) + +#define QCA808X_MMD7_CNT_RX_PKT_31_16 0x802a +#define QCA808X_MMD7_CNT_RX_PKT_15_0 0x802b +#define QCA808X_MMD7_CNT_RX_ERR_PKT 0x802c +#define QCA808X_MMD7_CNT_TX_PKT_31_16 0x802d +#define QCA808X_MMD7_CNT_TX_PKT_15_0 0x802e +#define QCA808X_MMD7_CNT_TX_ERR_PKT 0x802f + enum stat_access_type { PHY, MMD @@ -212,6 +223,13 @@ struct at803x_ss_mask { u8 speed_shift; }; +struct qcom_phy_hw_stats { + u64 rx_pkts; + u64 rx_err_pkts; + u64 tx_pkts; + u64 tx_err_pkts; +}; + int at803x_debug_reg_read(struct phy_device *phydev, u16 reg); int at803x_debug_reg_mask(struct phy_device *phydev, u16 reg, u16 clear, u16 set); @@ -246,3 +264,8 @@ int qca808x_led_reg_brightness_set(struct phy_device *phydev, int qca808x_led_reg_blink_set(struct phy_device *phydev, u16 reg, unsigned long *delay_on, unsigned long *delay_off); +int qcom_phy_counter_config(struct phy_device *phydev); +int qcom_phy_update_stats(struct phy_device *phydev, + struct qcom_phy_hw_stats *hw_stats); +void qcom_phy_get_stats(struct ethtool_phy_stats *stats, + struct qcom_phy_hw_stats hw_stats); diff --git a/drivers/net/tap.c b/drivers/net/tap.c index d82eb7276a8b..1197f245e873 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -1000,8 +1000,8 @@ static long tap_ioctl(struct file *file, unsigned int cmd, return -ENOLINK; } ret = 0; - dev_get_mac_address((struct sockaddr *)&ss, dev_net(tap->dev), - tap->dev->name); + netif_get_mac_address((struct sockaddr *)&ss, dev_net(tap->dev), + tap->dev->name); if (copy_to_user(&ifr->ifr_name, tap->dev->name, IFNAMSIZ) || copy_to_user(&ifr->ifr_hwaddr, &ss, sizeof(ifr->ifr_hwaddr))) ret = -EFAULT; @@ -1282,3 +1282,4 @@ MODULE_DESCRIPTION("Common library for drivers implementing the TAP interface"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>"); MODULE_LICENSE("GPL"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 49bcd12a4ac8..cc6c50180663 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1002,8 +1002,8 @@ static unsigned int run_ebpf_filter(struct tun_struct *tun, /* Net device start xmit */ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { + enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct tun_struct *tun = netdev_priv(dev); - enum skb_drop_reason drop_reason; int txq = skb->queue_mapping; struct netdev_queue *queue; struct tun_file *tfile; @@ -1032,10 +1032,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) } if (tfile->socket.sk->sk_filter && - sk_filter(tfile->socket.sk, skb)) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + sk_filter_reason(tfile->socket.sk, skb, &drop_reason)) goto drop; - } len = run_ebpf_filter(tun, skb, len); if (len == 0) { @@ -3225,7 +3223,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, case SIOCGIFHWADDR: /* Get hw address */ - dev_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name); + netif_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name); if (copy_to_user(argp, &ifr, ifreq_len)) ret = -EFAULT; break; @@ -3734,3 +3732,4 @@ MODULE_AUTHOR(DRV_COPYRIGHT); MODULE_LICENSE("GPL"); MODULE_ALIAS_MISCDEV(TUN_MINOR); MODULE_ALIAS("devname:net/tun"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 34e82f1e37d9..ea0e5e276cd6 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -892,6 +892,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ } } + if (ctx->func_desc) + ctx->filtering_supported = !!(ctx->func_desc->bmNetworkCapabilities + & USB_CDC_NCM_NCAP_ETH_FILTER); + iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber; /* Device-specific flags */ @@ -1898,6 +1902,14 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb) } } +static void cdc_ncm_update_filter(struct usbnet *dev) +{ + struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0]; + + if (ctx->filtering_supported) + usbnet_cdc_update_filter(dev); +} + static const struct driver_info cdc_ncm_info = { .description = "CDC NCM (NO ZLP)", .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET @@ -1908,7 +1920,7 @@ static const struct driver_info cdc_ncm_info = { .status = cdc_ncm_status, .rx_fixup = cdc_ncm_rx_fixup, .tx_fixup = cdc_ncm_tx_fixup, - .set_rx_mode = usbnet_cdc_update_filter, + .set_rx_mode = cdc_ncm_update_filter, }; /* Same as cdc_ncm_info, but with FLAG_SEND_ZLP */ @@ -1922,7 +1934,7 @@ static const struct driver_info cdc_ncm_zlp_info = { .status = cdc_ncm_status, .rx_fixup = cdc_ncm_rx_fixup, .tx_fixup = cdc_ncm_tx_fixup, - .set_rx_mode = usbnet_cdc_update_filter, + .set_rx_mode = cdc_ncm_update_filter, }; /* Same as cdc_ncm_info, but with FLAG_SEND_ZLP */ @@ -1964,7 +1976,7 @@ static const struct driver_info wwan_info = { .status = cdc_ncm_status, .rx_fixup = cdc_ncm_rx_fixup, .tx_fixup = cdc_ncm_tx_fixup, - .set_rx_mode = usbnet_cdc_update_filter, + .set_rx_mode = cdc_ncm_update_filter, }; /* Same as wwan_info, but with FLAG_NOARP */ @@ -1978,7 +1990,7 @@ static const struct driver_info wwan_noarp_info = { .status = cdc_ncm_status, .rx_fixup = cdc_ncm_rx_fixup, .tx_fixup = cdc_ncm_tx_fixup, - .set_rx_mode = usbnet_cdc_update_filter, + .set_rx_mode = cdc_ncm_update_filter, }; static const struct usb_device_id cdc_devs[] = { diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 8e82184be5e7..de733e0488bf 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -63,6 +63,9 @@ struct smsc95xx_priv { u32 hash_hi; u32 hash_lo; u32 wolopts; + bool pause_rx; + bool pause_tx; + bool pause_autoneg; spinlock_t mac_cr_lock; u8 features; u8 suspend_flags; @@ -537,16 +540,23 @@ static void smsc95xx_set_multicast(struct net_device *netdev) static int smsc95xx_phy_update_flowcontrol(struct usbnet *dev) { - u32 flow = 0, afc_cfg; struct smsc95xx_priv *pdata = dev->driver_priv; - bool tx_pause, rx_pause; + u32 flow = 0, afc_cfg; int ret = smsc95xx_read_reg(dev, AFC_CFG, &afc_cfg); if (ret < 0) return ret; if (pdata->phydev->duplex == DUPLEX_FULL) { - phy_get_pause(pdata->phydev, &tx_pause, &rx_pause); + bool tx_pause, rx_pause; + + if (pdata->phydev->autoneg == AUTONEG_ENABLE && + pdata->pause_autoneg) { + phy_get_pause(pdata->phydev, &tx_pause, &rx_pause); + } else { + tx_pause = pdata->pause_tx; + rx_pause = pdata->pause_rx; + } if (rx_pause) flow = 0xFFFF0002; @@ -772,6 +782,55 @@ static int smsc95xx_ethtool_get_sset_count(struct net_device *ndev, int sset) } } +static void smsc95xx_get_pauseparam(struct net_device *ndev, + struct ethtool_pauseparam *pause) +{ + struct smsc95xx_priv *pdata; + struct usbnet *dev; + + dev = netdev_priv(ndev); + pdata = dev->driver_priv; + + pause->autoneg = pdata->pause_autoneg; + pause->rx_pause = pdata->pause_rx; + pause->tx_pause = pdata->pause_tx; +} + +static int smsc95xx_set_pauseparam(struct net_device *ndev, + struct ethtool_pauseparam *pause) +{ + bool pause_autoneg_rx, pause_autoneg_tx; + struct smsc95xx_priv *pdata; + struct phy_device *phydev; + struct usbnet *dev; + + dev = netdev_priv(ndev); + pdata = dev->driver_priv; + phydev = ndev->phydev; + + if (!phydev) + return -ENODEV; + + pdata->pause_rx = pause->rx_pause; + pdata->pause_tx = pause->tx_pause; + pdata->pause_autoneg = pause->autoneg; + + if (pause->autoneg) { + pause_autoneg_rx = pause->rx_pause; + pause_autoneg_tx = pause->tx_pause; + } else { + pause_autoneg_rx = false; + pause_autoneg_tx = false; + } + + phy_set_asym_pause(ndev->phydev, pause_autoneg_rx, pause_autoneg_tx); + if (phydev->link && (!pause->autoneg || + phydev->autoneg == AUTONEG_DISABLE)) + smsc95xx_mac_update_fullduplex(dev); + + return 0; +} + static const struct ethtool_ops smsc95xx_ethtool_ops = { .get_link = smsc95xx_get_link, .nway_reset = phy_ethtool_nway_reset, @@ -791,6 +850,8 @@ static const struct ethtool_ops smsc95xx_ethtool_ops = { .self_test = net_selftest, .get_strings = smsc95xx_ethtool_get_strings, .get_sset_count = smsc95xx_ethtool_get_sset_count, + .get_pauseparam = smsc95xx_get_pauseparam, + .set_pauseparam = smsc95xx_set_pauseparam, }; static int smsc95xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) @@ -1227,6 +1288,11 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; + pdata->pause_tx = true; + pdata->pause_rx = true; + pdata->pause_autoneg = true; + phy_support_asym_pause(pdata->phydev); + ret = phy_connect_direct(dev->net, pdata->phydev, &smsc95xx_handle_link_change, PHY_INTERFACE_MODE_MII); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 6a3cca104af9..921c05bc73e3 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1759,7 +1759,6 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->hard_mtu = net->mtu + net->hard_header_len; net->min_mtu = 0; net->max_mtu = ETH_MAX_MTU; - net->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; net->netdev_ops = &usbnet_netdev_ops; net->watchdog_timeo = TX_TIMEOUT_JIFFIES; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index bcde95cb2a2e..f32be2e301f2 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -4041,7 +4041,7 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_VXLAN_ID], "Cannot change VNI"); return -EOPNOTSUPP; } - conf->vni = cpu_to_be32(nla_get_u32(data[IFLA_VXLAN_ID])); + conf->vni = vni; } if (data[IFLA_VXLAN_GROUP]) { diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 4a529f1f9bea..5afec5a865f4 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -366,7 +366,7 @@ static int wg_newlink(struct net_device *dev, if (ret < 0) goto err_free_handshake_queue; - dev_set_threaded(dev, true); + netif_set_threaded(dev, true); ret = register_netdevice(dev); if (ret < 0) goto err_uninit_ratelimiter; diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c index d51f2e5a79a4..0ee68d3dad12 100644 --- a/drivers/net/wireless/ath/ath10k/snoc.c +++ b/drivers/net/wireless/ath/ath10k/snoc.c @@ -936,7 +936,7 @@ static int ath10k_snoc_hif_start(struct ath10k *ar) bitmap_clear(ar_snoc->pending_ce_irqs, 0, CE_COUNT_MAX); - dev_set_threaded(ar->napi_dev, true); + netif_set_threaded(ar->napi_dev, true); ath10k_core_napi_enable(ar); /* IRQs are left enabled when we restart due to a firmware crash */ if (!test_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags)) diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 2912568612bc..8dd5c29fb75b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -1810,7 +1810,8 @@ static inline void mt76_put_page_pool_buf(void *buf, bool allow_direct) { struct page *page = virt_to_head_page(buf); - page_pool_put_full_page(page->pp, page, allow_direct); + page_pool_put_full_page(pp_page_to_nmdesc(page)->pp, page, + allow_direct); } static inline void * diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7493e5aa984c..895fb163d48e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -381,12 +381,12 @@ static void nvme_log_err_passthru(struct request *req) nr->status & NVME_SC_MASK, /* Status Code */ nr->status & NVME_STATUS_MORE ? "MORE " : "", nr->status & NVME_STATUS_DNR ? "DNR " : "", - nr->cmd->common.cdw10, - nr->cmd->common.cdw11, - nr->cmd->common.cdw12, - nr->cmd->common.cdw13, - nr->cmd->common.cdw14, - nr->cmd->common.cdw15); + le32_to_cpu(nr->cmd->common.cdw10), + le32_to_cpu(nr->cmd->common.cdw11), + le32_to_cpu(nr->cmd->common.cdw12), + le32_to_cpu(nr->cmd->common.cdw13), + le32_to_cpu(nr->cmd->common.cdw14), + le32_to_cpu(nr->cmd->common.cdw15)); } enum nvme_disposition { @@ -764,6 +764,10 @@ blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl, !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) && !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH)) return BLK_STS_RESOURCE; + + if (!(rq->rq_flags & RQF_DONTPREP)) + nvme_clear_nvme_request(rq); + return nvme_host_path_error(rq); } EXPORT_SYMBOL_GPL(nvme_fail_nonready_command); @@ -3537,15 +3541,6 @@ static int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret) goto out_free; } - - if (le16_to_cpu(id->awupf) != ctrl->subsys->awupf) { - dev_err_ratelimited(ctrl->device, - "inconsistent AWUPF, controller not added (%u/%u).\n", - le16_to_cpu(id->awupf), ctrl->subsys->awupf); - ret = -EINVAL; - goto out_free; - } - memcpy(ctrl->subsys->firmware_rev, id->fr, sizeof(ctrl->subsys->firmware_rev)); @@ -4077,7 +4072,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns) return; } } - list_add(&ns->list, &ns->ctrl->namespaces); + list_add_rcu(&ns->list, &ns->ctrl->namespaces); } static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 688033b88d38..470bf37e5a63 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1928,10 +1928,10 @@ static void nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port, struct sock *sk = queue->sock->sk; /* Restore the default callbacks before starting upcall */ - read_lock_bh(&sk->sk_callback_lock); + write_lock_bh(&sk->sk_callback_lock); sk->sk_user_data = NULL; sk->sk_data_ready = port->data_ready; - read_unlock_bh(&sk->sk_callback_lock); + write_unlock_bh(&sk->sk_callback_lock); if (!nvmet_tcp_try_peek_pdu(queue)) { if (!nvmet_tcp_tls_handshake(queue)) return; diff --git a/drivers/nvmem/imx-ocotp-ele.c b/drivers/nvmem/imx-ocotp-ele.c index ca6dd71d8a2e..7807ec0e2d18 100644 --- a/drivers/nvmem/imx-ocotp-ele.c +++ b/drivers/nvmem/imx-ocotp-ele.c @@ -12,6 +12,7 @@ #include <linux/of.h> #include <linux/platform_device.h> #include <linux/slab.h> +#include <linux/if_ether.h> /* ETH_ALEN */ enum fuse_type { FUSE_FSB = BIT(0), @@ -118,9 +119,11 @@ static int imx_ocotp_cell_pp(void *context, const char *id, int index, int i; /* Deal with some post processing of nvmem cell data */ - if (id && !strcmp(id, "mac-address")) + if (id && !strcmp(id, "mac-address")) { + bytes = min(bytes, ETH_ALEN); for (i = 0; i < bytes / 2; i++) swap(buf[i], buf[bytes - i - 1]); + } return 0; } diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index 79dd4fda0329..7bf7656d4f96 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -23,6 +23,7 @@ #include <linux/platform_device.h> #include <linux/slab.h> #include <linux/delay.h> +#include <linux/if_ether.h> /* ETH_ALEN */ #define IMX_OCOTP_OFFSET_B0W0 0x400 /* Offset from base address of the * OTP Bank0 Word0 @@ -227,9 +228,11 @@ static int imx_ocotp_cell_pp(void *context, const char *id, int index, int i; /* Deal with some post processing of nvmem cell data */ - if (id && !strcmp(id, "mac-address")) + if (id && !strcmp(id, "mac-address")) { + bytes = min(bytes, ETH_ALEN); for (i = 0; i < bytes / 2; i++) swap(buf[i], buf[bytes - i - 1]); + } return 0; } diff --git a/drivers/nvmem/layouts/u-boot-env.c b/drivers/nvmem/layouts/u-boot-env.c index 436426d4e8f9..8571aac56295 100644 --- a/drivers/nvmem/layouts/u-boot-env.c +++ b/drivers/nvmem/layouts/u-boot-env.c @@ -92,7 +92,7 @@ int u_boot_env_parse(struct device *dev, struct nvmem_device *nvmem, size_t crc32_data_offset; size_t crc32_data_len; size_t crc32_offset; - __le32 *crc32_addr; + uint32_t *crc32_addr; size_t data_offset; size_t data_len; size_t dev_size; @@ -143,8 +143,8 @@ int u_boot_env_parse(struct device *dev, struct nvmem_device *nvmem, goto err_kfree; } - crc32_addr = (__le32 *)(buf + crc32_offset); - crc32 = le32_to_cpu(*crc32_addr); + crc32_addr = (uint32_t *)(buf + crc32_offset); + crc32 = *crc32_addr; crc32_data_len = dev_size - crc32_data_offset; data_len = dev_size - data_offset; diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c index cc96be450360..28b3e93d31c0 100644 --- a/drivers/pci/controller/pci-hyperv-intf.c +++ b/drivers/pci/controller/pci-hyperv-intf.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/hyperv.h> +#include <linux/export.h> struct hyperv_pci_block_ops hvpci_block_ops; EXPORT_SYMBOL_GPL(hvpci_block_ops); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ebe39218479a..d2b7e8ea710b 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -599,7 +599,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) #define hv_msi_prepare pci_msi_prepare /** - * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current + * hv_irq_retarget_interrupt() - "Unmask" the IRQ by setting its current * affinity. * @data: Describes the IRQ * @@ -608,7 +608,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) * is built out of this PCI bus's instance GUID and the function * number of the device. */ -static void hv_arch_irq_unmask(struct irq_data *data) +static void hv_irq_retarget_interrupt(struct irq_data *data) { struct msi_desc *msi_desc = irq_data_get_msi_desc(data); struct hv_retarget_device_interrupt *params; @@ -713,6 +713,20 @@ out: dev_err(&hbus->hdev->device, "%s() failed: %#llx", __func__, res); } + +static void hv_arch_irq_unmask(struct irq_data *data) +{ + if (hv_root_partition()) + /* + * In case of the nested root partition, the nested hypervisor + * is taking care of interrupt remapping and thus the + * MAP_DEVICE_INTERRUPT hypercall is required instead of + * RETARGET_INTERRUPT. + */ + (void)hv_map_msi_interrupt(data, NULL); + else + hv_irq_retarget_interrupt(data); +} #elif defined(CONFIG_ARM64) /* * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit @@ -4200,6 +4214,9 @@ static int __init init_hv_pci_drv(void) if (!hv_is_hyperv_initialized()) return -ENODEV; + if (hv_root_partition() && !hv_nested) + return -ENODEV; + ret = hv_pci_irqchip_init(); if (ret) return ret; diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 8e2daea81666..04a5a34e7a95 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -994,7 +994,8 @@ struct phy *phy_create(struct device *dev, struct device_node *node, } device_initialize(&phy->dev); - mutex_init(&phy->mutex); + lockdep_register_key(&phy->lockdep_key); + mutex_init_with_key(&phy->mutex, &phy->lockdep_key); phy->dev.class = &phy_class; phy->dev.parent = dev; @@ -1259,6 +1260,8 @@ static void phy_release(struct device *dev) dev_vdbg(dev, "releasing '%s'\n", dev_name(dev)); debugfs_remove_recursive(phy->debugfs); regulator_put(phy->pwr); + mutex_destroy(&phy->mutex); + lockdep_unregister_key(&phy->lockdep_key); ida_free(&phy_ida, phy->id); kfree(phy); } diff --git a/drivers/phy/phy-snps-eusb2.c b/drivers/phy/phy-snps-eusb2.c index b73a1d7e57b3..751b6d8ba2be 100644 --- a/drivers/phy/phy-snps-eusb2.c +++ b/drivers/phy/phy-snps-eusb2.c @@ -567,9 +567,11 @@ static int snps_eusb2_hsphy_probe(struct platform_device *pdev) } } - if (IS_ERR_OR_NULL(phy->ref_clk)) - return dev_err_probe(dev, PTR_ERR(phy->ref_clk), + if (IS_ERR_OR_NULL(phy->ref_clk)) { + ret = phy->ref_clk ? PTR_ERR(phy->ref_clk) : -ENOENT; + return dev_err_probe(dev, ret, "failed to get ref clk\n"); + } num = ARRAY_SIZE(phy->vregs); for (i = 0; i < num; i++) diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c index 23a23f2d64e5..e818f6c3980e 100644 --- a/drivers/phy/tegra/xusb-tegra186.c +++ b/drivers/phy/tegra/xusb-tegra186.c @@ -648,14 +648,15 @@ static void tegra186_utmi_bias_pad_power_on(struct tegra_xusb_padctl *padctl) udelay(100); } - if (padctl->soc->trk_hw_mode) { - value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); - value |= USB2_TRK_HW_MODE; + value = padctl_readl(padctl, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); + if (padctl->soc->trk_update_on_idle) value &= ~CYA_TRK_CODE_UPDATE_ON_IDLE; - padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); - } else { + if (padctl->soc->trk_hw_mode) + value |= USB2_TRK_HW_MODE; + padctl_writel(padctl, value, XUSB_PADCTL_USB2_BIAS_PAD_CTL2); + + if (!padctl->soc->trk_hw_mode) clk_disable_unprepare(priv->usb2_trk_clk); - } } static void tegra186_utmi_bias_pad_power_off(struct tegra_xusb_padctl *padctl) @@ -782,13 +783,15 @@ static int tegra186_xusb_padctl_vbus_override(struct tegra_xusb_padctl *padctl, } static int tegra186_xusb_padctl_id_override(struct tegra_xusb_padctl *padctl, - bool status) + struct tegra_xusb_usb2_port *port, bool status) { - u32 value; + u32 value, id_override; + int err = 0; dev_dbg(padctl->dev, "%s id override\n", status ? "set" : "clear"); value = padctl_readl(padctl, USB2_VBUS_ID); + id_override = value & ID_OVERRIDE(~0); if (status) { if (value & VBUS_OVERRIDE) { @@ -799,15 +802,35 @@ static int tegra186_xusb_padctl_id_override(struct tegra_xusb_padctl *padctl, value = padctl_readl(padctl, USB2_VBUS_ID); } - value &= ~ID_OVERRIDE(~0); - value |= ID_OVERRIDE_GROUNDED; + if (id_override != ID_OVERRIDE_GROUNDED) { + value &= ~ID_OVERRIDE(~0); + value |= ID_OVERRIDE_GROUNDED; + padctl_writel(padctl, value, USB2_VBUS_ID); + + err = regulator_enable(port->supply); + if (err) { + dev_err(padctl->dev, "Failed to enable regulator: %d\n", err); + return err; + } + } } else { - value &= ~ID_OVERRIDE(~0); - value |= ID_OVERRIDE_FLOATING; + if (id_override == ID_OVERRIDE_GROUNDED) { + /* + * The regulator is disabled only when the role transitions + * from USB_ROLE_HOST to USB_ROLE_NONE. + */ + err = regulator_disable(port->supply); + if (err) { + dev_err(padctl->dev, "Failed to disable regulator: %d\n", err); + return err; + } + + value &= ~ID_OVERRIDE(~0); + value |= ID_OVERRIDE_FLOATING; + padctl_writel(padctl, value, USB2_VBUS_ID); + } } - padctl_writel(padctl, value, USB2_VBUS_ID); - return 0; } @@ -826,27 +849,20 @@ static int tegra186_utmi_phy_set_mode(struct phy *phy, enum phy_mode mode, if (mode == PHY_MODE_USB_OTG) { if (submode == USB_ROLE_HOST) { - tegra186_xusb_padctl_id_override(padctl, true); - - err = regulator_enable(port->supply); + err = tegra186_xusb_padctl_id_override(padctl, port, true); + if (err) + goto out; } else if (submode == USB_ROLE_DEVICE) { tegra186_xusb_padctl_vbus_override(padctl, true); } else if (submode == USB_ROLE_NONE) { - /* - * When port is peripheral only or role transitions to - * USB_ROLE_NONE from USB_ROLE_DEVICE, regulator is not - * enabled. - */ - if (regulator_is_enabled(port->supply)) - regulator_disable(port->supply); - - tegra186_xusb_padctl_id_override(padctl, false); + err = tegra186_xusb_padctl_id_override(padctl, port, false); + if (err) + goto out; tegra186_xusb_padctl_vbus_override(padctl, false); } } - +out: mutex_unlock(&padctl->lock); - return err; } @@ -1710,7 +1726,8 @@ const struct tegra_xusb_padctl_soc tegra234_xusb_padctl_soc = { .num_supplies = ARRAY_SIZE(tegra194_xusb_padctl_supply_names), .supports_gen2 = true, .poll_trk_completed = true, - .trk_hw_mode = true, + .trk_hw_mode = false, + .trk_update_on_idle = true, .supports_lp_cfg_en = true, }; EXPORT_SYMBOL_GPL(tegra234_xusb_padctl_soc); diff --git a/drivers/phy/tegra/xusb.h b/drivers/phy/tegra/xusb.h index 6e45d194c689..d2b5f9565132 100644 --- a/drivers/phy/tegra/xusb.h +++ b/drivers/phy/tegra/xusb.h @@ -434,6 +434,7 @@ struct tegra_xusb_padctl_soc { bool need_fake_usb3_port; bool poll_trk_completed; bool trk_hw_mode; + bool trk_update_on_idle; bool supports_lp_cfg_en; }; diff --git a/drivers/platform/arm64/huawei-gaokun-ec.c b/drivers/platform/arm64/huawei-gaokun-ec.c index 7e5aa7ca2403..7170f8eb76f7 100644 --- a/drivers/platform/arm64/huawei-gaokun-ec.c +++ b/drivers/platform/arm64/huawei-gaokun-ec.c @@ -662,6 +662,7 @@ static void gaokun_aux_release(struct device *dev) { struct auxiliary_device *adev = to_auxiliary_dev(dev); + of_node_put(dev->of_node); kfree(adev); } @@ -693,6 +694,7 @@ static int gaokun_aux_init(struct device *parent, const char *name, ret = auxiliary_device_init(adev); if (ret) { + of_node_put(adev->dev.of_node); kfree(adev); return ret; } diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c index a1c529f1ff1a..4776013e0764 100644 --- a/drivers/platform/mellanox/mlxbf-pmc.c +++ b/drivers/platform/mellanox/mlxbf-pmc.c @@ -15,6 +15,7 @@ #include <linux/hwmon.h> #include <linux/platform_device.h> #include <linux/string.h> +#include <linux/string_helpers.h> #include <uapi/linux/psci.h> #define MLXBF_PMC_WRITE_REG_32 0x82000009 @@ -1222,7 +1223,7 @@ static int mlxbf_pmc_get_event_num(const char *blk, const char *evt) return -ENODEV; } -/* Get the event number given the name */ +/* Get the event name given the number */ static char *mlxbf_pmc_get_event_name(const char *blk, u32 evt) { const struct mlxbf_pmc_events *events; @@ -1784,6 +1785,7 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev, attr, struct mlxbf_pmc_attribute, dev_attr); unsigned int blk_num, cnt_num; bool is_l3 = false; + char *evt_name; int evt_num; int err; @@ -1791,14 +1793,23 @@ static ssize_t mlxbf_pmc_event_store(struct device *dev, cnt_num = attr_event->index; if (isalpha(buf[0])) { + /* Remove the trailing newline character if present */ + evt_name = kstrdup_and_replace(buf, '\n', '\0', GFP_KERNEL); + if (!evt_name) + return -ENOMEM; + evt_num = mlxbf_pmc_get_event_num(pmc->block_name[blk_num], - buf); + evt_name); + kfree(evt_name); if (evt_num < 0) return -EINVAL; } else { err = kstrtouint(buf, 0, &evt_num); if (err < 0) return err; + + if (!mlxbf_pmc_get_event_name(pmc->block_name[blk_num], evt_num)) + return -EINVAL; } if (strstr(pmc->block_name[blk_num], "l3cache")) @@ -1879,13 +1890,14 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev, { struct mlxbf_pmc_attribute *attr_enable = container_of( attr, struct mlxbf_pmc_attribute, dev_attr); - unsigned int en, blk_num; + unsigned int blk_num; u32 word; int err; + bool en; blk_num = attr_enable->nr; - err = kstrtouint(buf, 0, &en); + err = kstrtobool(buf, &en); if (err < 0) return err; @@ -1905,14 +1917,11 @@ static ssize_t mlxbf_pmc_enable_store(struct device *dev, MLXBF_PMC_CRSPACE_PERFMON_CTL(pmc->block[blk_num].counters), MLXBF_PMC_WRITE_REG_32, word); } else { - if (en && en != 1) - return -EINVAL; - err = mlxbf_pmc_config_l3_counters(blk_num, false, !!en); if (err) return err; - if (en == 1) { + if (en) { err = mlxbf_pmc_config_l3_counters(blk_num, true, false); if (err) return err; diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index abbc2644ff6d..bea87a85ae75 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -58,6 +58,8 @@ obj-$(CONFIG_X86_PLATFORM_DRIVERS_HP) += hp/ # Hewlett Packard Enterprise obj-$(CONFIG_UV_SYSFS) += uv_sysfs.o +obj-$(CONFIG_FW_ATTR_CLASS) += firmware_attributes_class.o + # IBM Thinkpad and Lenovo obj-$(CONFIG_IBM_RTL) += ibm_rtl.o obj-$(CONFIG_IDEAPAD_LAPTOP) += ideapad-laptop.o @@ -128,7 +130,6 @@ obj-$(CONFIG_SYSTEM76_ACPI) += system76_acpi.o obj-$(CONFIG_TOPSTAR_LAPTOP) += topstar-laptop.o # Platform drivers -obj-$(CONFIG_FW_ATTR_CLASS) += firmware_attributes_class.o obj-$(CONFIG_SERIAL_MULTI_INSTANTIATE) += serial-multi-instantiate.o obj-$(CONFIG_TOUCHSCREEN_DMI) += touchscreen_dmi.o obj-$(CONFIG_WIRELESS_HOTKEY) += wireless-hotkey.o diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c index 20ec122a9fe0..b58cf74197f0 100644 --- a/drivers/platform/x86/dell/alienware-wmi-wmax.c +++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c @@ -90,6 +90,14 @@ static struct awcc_quirks empty_quirks; static const struct dmi_system_id awcc_dmi_table[] __initconst = { { + .ident = "Alienware Area-51m", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware Area-51m"), + }, + .driver_data = &generic_quirks, + }, + { .ident = "Alienware Area-51m R2", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -98,6 +106,14 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { .driver_data = &generic_quirks, }, { + .ident = "Alienware m15 R5", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), + DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m15 R5"), + }, + .driver_data = &generic_quirks, + }, + { .ident = "Alienware m15 R7", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Alienware"), @@ -233,6 +249,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = { }, .driver_data = &g_series_quirks, }, + {} }; enum AWCC_GET_FAN_SENSORS_OPERATIONS { diff --git a/drivers/platform/x86/dell/dell-lis3lv02d.c b/drivers/platform/x86/dell/dell-lis3lv02d.c index 0791118dd6b7..732de5f556f8 100644 --- a/drivers/platform/x86/dell/dell-lis3lv02d.c +++ b/drivers/platform/x86/dell/dell-lis3lv02d.c @@ -49,6 +49,7 @@ static const struct dmi_system_id lis3lv02d_devices[] __initconst = { DELL_LIS3LV02D_DMI_ENTRY("Latitude E6330", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Latitude E6430", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Precision 3540", 0x29), + DELL_LIS3LV02D_DMI_ENTRY("Precision 3551", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Precision M6800", 0x29), DELL_LIS3LV02D_DMI_ENTRY("Vostro V131", 0x1d), DELL_LIS3LV02D_DMI_ENTRY("Vostro 5568", 0x29), diff --git a/drivers/platform/x86/dell/dell-wmi-ddv.c b/drivers/platform/x86/dell/dell-wmi-ddv.c index 67f3d7158403..62e3d060f038 100644 --- a/drivers/platform/x86/dell/dell-wmi-ddv.c +++ b/drivers/platform/x86/dell/dell-wmi-ddv.c @@ -689,9 +689,13 @@ static int dell_wmi_ddv_battery_translate(struct dell_wmi_ddv_data *data, dev_dbg(&data->wdev->dev, "Translation cache miss\n"); - /* Perform a translation between a ACPI battery and a battery index */ - - ret = power_supply_get_property(battery, POWER_SUPPLY_PROP_SERIAL_NUMBER, &val); + /* + * Perform a translation between a ACPI battery and a battery index. + * We have to use power_supply_get_property_direct() here because this + * function will also get called from the callbacks of the power supply + * extension. + */ + ret = power_supply_get_property_direct(battery, POWER_SUPPLY_PROP_SERIAL_NUMBER, &val); if (ret < 0) return ret; diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index b5e4da6a6779..edb9d2fb02ec 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1669,7 +1669,7 @@ static int ideapad_kbd_bl_init(struct ideapad_private *priv) priv->kbd_bl.led.name = "platform::" LED_FUNCTION_KBD_BACKLIGHT; priv->kbd_bl.led.brightness_get = ideapad_kbd_bl_led_cdev_brightness_get; priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set; - priv->kbd_bl.led.flags = LED_BRIGHT_HW_CHANGED; + priv->kbd_bl.led.flags = LED_BRIGHT_HW_CHANGED | LED_RETAIN_AT_SHUTDOWN; err = led_classdev_register(&priv->platform_device->dev, &priv->kbd_bl.led); if (err) @@ -1728,7 +1728,7 @@ static int ideapad_fn_lock_led_init(struct ideapad_private *priv) priv->fn_lock.led.name = "platform::" LED_FUNCTION_FNLOCK; priv->fn_lock.led.brightness_get = ideapad_fn_lock_led_cdev_get; priv->fn_lock.led.brightness_set_blocking = ideapad_fn_lock_led_cdev_set; - priv->fn_lock.led.flags = LED_BRIGHT_HW_CHANGED; + priv->fn_lock.led.flags = LED_BRIGHT_HW_CHANGED | LED_RETAIN_AT_SHUTDOWN; err = led_classdev_register(&priv->platform_device->dev, &priv->fn_lock.led); if (err) diff --git a/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c b/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c index 89153afd7015..7b9bad1978ff 100644 --- a/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c +++ b/drivers/platform/x86/lenovo-wmi-hotkey-utilities.c @@ -122,26 +122,35 @@ static int lenovo_super_hotkey_wmi_led_init(enum mute_led_type led_type, struct return -EIO; union acpi_object *obj __free(kfree) = output.pointer; - if (obj && obj->type == ACPI_TYPE_INTEGER) - led_version = obj->integer.value; - else + if (!obj || obj->type != ACPI_TYPE_INTEGER) return -EIO; - wpriv->cdev[led_type].max_brightness = LED_ON; - wpriv->cdev[led_type].flags = LED_CORE_SUSPENDRESUME; + led_version = obj->integer.value; + + /* + * Output parameters define: 0 means mute LED is not supported, Non-zero means + * mute LED can be supported. + */ + if (led_version == 0) + return 0; + switch (led_type) { case MIC_MUTE: - if (led_version != WMI_LUD_SUPPORT_MICMUTE_LED_VER) - return -EIO; + if (led_version != WMI_LUD_SUPPORT_MICMUTE_LED_VER) { + pr_warn("The MIC_MUTE LED of this device isn't supported.\n"); + return 0; + } wpriv->cdev[led_type].name = "platform::micmute"; wpriv->cdev[led_type].brightness_set_blocking = &lsh_wmi_micmute_led_set; wpriv->cdev[led_type].default_trigger = "audio-micmute"; break; case AUDIO_MUTE: - if (led_version != WMI_LUD_SUPPORT_AUDIOMUTE_LED_VER) - return -EIO; + if (led_version != WMI_LUD_SUPPORT_AUDIOMUTE_LED_VER) { + pr_warn("The AUDIO_MUTE LED of this device isn't supported.\n"); + return 0; + } wpriv->cdev[led_type].name = "platform::mute"; wpriv->cdev[led_type].brightness_set_blocking = &lsh_wmi_audiomute_led_set; @@ -152,6 +161,9 @@ static int lenovo_super_hotkey_wmi_led_init(enum mute_led_type led_type, struct return -EINVAL; } + wpriv->cdev[led_type].max_brightness = LED_ON; + wpriv->cdev[led_type].flags = LED_CORE_SUSPENDRESUME; + err = devm_led_classdev_register(dev, &wpriv->cdev[led_type]); if (err < 0) { dev_err(dev, "Could not register mute LED %d : %d\n", led_type, err); diff --git a/drivers/pmdomain/governor.c b/drivers/pmdomain/governor.c index c1e148657c87..39359811a930 100644 --- a/drivers/pmdomain/governor.c +++ b/drivers/pmdomain/governor.c @@ -8,6 +8,7 @@ #include <linux/pm_domain.h> #include <linux/pm_qos.h> #include <linux/hrtimer.h> +#include <linux/cpu.h> #include <linux/cpuidle.h> #include <linux/cpumask.h> #include <linux/ktime.h> @@ -349,6 +350,8 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) struct cpuidle_device *dev; ktime_t domain_wakeup, next_hrtimer; ktime_t now = ktime_get(); + struct device *cpu_dev; + s64 cpu_constraint, global_constraint; s64 idle_duration_ns; int cpu, i; @@ -359,6 +362,7 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN)) return true; + global_constraint = cpu_latency_qos_limit(); /* * Find the next wakeup for any of the online CPUs within the PM domain * and its subdomains. Note, we only need the genpd->cpus, as it already @@ -372,8 +376,16 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) if (ktime_before(next_hrtimer, domain_wakeup)) domain_wakeup = next_hrtimer; } + + cpu_dev = get_cpu_device(cpu); + if (cpu_dev) { + cpu_constraint = dev_pm_qos_raw_resume_latency(cpu_dev); + if (cpu_constraint < global_constraint) + global_constraint = cpu_constraint; + } } + global_constraint *= NSEC_PER_USEC; /* The minimum idle duration is from now - until the next wakeup. */ idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, now)); if (idle_duration_ns <= 0) @@ -389,8 +401,10 @@ static bool cpu_power_down_ok(struct dev_pm_domain *pd) */ i = genpd->state_idx; do { - if (idle_duration_ns >= (genpd->states[i].residency_ns + - genpd->states[i].power_off_latency_ns)) { + if ((idle_duration_ns >= (genpd->states[i].residency_ns + + genpd->states[i].power_off_latency_ns)) && + (global_constraint >= (genpd->states[i].power_on_latency_ns + + genpd->states[i].power_off_latency_ns))) { genpd->state_idx = i; genpd->gd->last_enter = now; genpd->gd->reflect_residency = true; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 33a5bfce4604..cfb0e3e0d4aa 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1235,9 +1235,8 @@ bool power_supply_has_property(struct power_supply *psy, return false; } -int power_supply_get_property(struct power_supply *psy, - enum power_supply_property psp, - union power_supply_propval *val) +static int __power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val, bool use_extensions) { struct power_supply_ext_registration *reg; @@ -1247,10 +1246,14 @@ int power_supply_get_property(struct power_supply *psy, return -ENODEV; } - scoped_guard(rwsem_read, &psy->extensions_sem) { - power_supply_for_each_extension(reg, psy) { - if (power_supply_ext_has_property(reg->ext, psp)) + if (use_extensions) { + scoped_guard(rwsem_read, &psy->extensions_sem) { + power_supply_for_each_extension(reg, psy) { + if (!power_supply_ext_has_property(reg->ext, psp)) + continue; + return reg->ext->get_property(psy, reg->ext, reg->data, psp, val); + } } } @@ -1261,20 +1264,49 @@ int power_supply_get_property(struct power_supply *psy, else return -EINVAL; } + +int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val) +{ + return __power_supply_get_property(psy, psp, val, true); +} EXPORT_SYMBOL_GPL(power_supply_get_property); -int power_supply_set_property(struct power_supply *psy, - enum power_supply_property psp, - const union power_supply_propval *val) +/** + * power_supply_get_property_direct - Read a power supply property without checking for extensions + * @psy: The power supply + * @psp: The power supply property to read + * @val: The resulting value of the power supply property + * + * Read a power supply property without taking into account any power supply extensions registered + * on the given power supply. This is mostly useful for power supply extensions that want to access + * their own power supply as using power_supply_get_property() directly will result in a potential + * deadlock. + * + * Return: 0 on success or negative error code on failure. + */ +int power_supply_get_property_direct(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val) +{ + return __power_supply_get_property(psy, psp, val, false); +} +EXPORT_SYMBOL_GPL(power_supply_get_property_direct); + + +static int __power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val, bool use_extensions) { struct power_supply_ext_registration *reg; if (atomic_read(&psy->use_cnt) <= 0) return -ENODEV; - scoped_guard(rwsem_read, &psy->extensions_sem) { - power_supply_for_each_extension(reg, psy) { - if (power_supply_ext_has_property(reg->ext, psp)) { + if (use_extensions) { + scoped_guard(rwsem_read, &psy->extensions_sem) { + power_supply_for_each_extension(reg, psy) { + if (!power_supply_ext_has_property(reg->ext, psp)) + continue; + if (reg->ext->set_property) return reg->ext->set_property(psy, reg->ext, reg->data, psp, val); @@ -1289,8 +1321,34 @@ int power_supply_set_property(struct power_supply *psy, return psy->desc->set_property(psy, psp, val); } + +int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val) +{ + return __power_supply_set_property(psy, psp, val, true); +} EXPORT_SYMBOL_GPL(power_supply_set_property); +/** + * power_supply_set_property_direct - Write a power supply property without checking for extensions + * @psy: The power supply + * @psp: The power supply property to write + * @val: The value to write to the power supply property + * + * Write a power supply property without taking into account any power supply extensions registered + * on the given power supply. This is mostly useful for power supply extensions that want to access + * their own power supply as using power_supply_set_property() directly will result in a potential + * deadlock. + * + * Return: 0 on success or negative error code on failure. + */ +int power_supply_set_property_direct(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val) +{ + return __power_supply_set_property(psy, psp, val, false); +} +EXPORT_SYMBOL_GPL(power_supply_set_property_direct); + int power_supply_property_is_writeable(struct power_supply *psy, enum power_supply_property psp) { diff --git a/drivers/power/supply/test_power.c b/drivers/power/supply/test_power.c index 5bfdfcf6013b..2c0e9ad820c0 100644 --- a/drivers/power/supply/test_power.c +++ b/drivers/power/supply/test_power.c @@ -259,6 +259,7 @@ static const struct power_supply_config test_power_configs[] = { static int test_power_battery_extmanufacture_year = 1234; static int test_power_battery_exttemp_max = 1000; static const enum power_supply_property test_power_battery_extprops[] = { + POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW, POWER_SUPPLY_PROP_MANUFACTURE_YEAR, POWER_SUPPLY_PROP_TEMP_MAX, }; @@ -270,6 +271,9 @@ static int test_power_battery_extget_property(struct power_supply *psy, union power_supply_propval *val) { switch (psp) { + case POWER_SUPPLY_PROP_TIME_TO_EMPTY_NOW: + return power_supply_get_property_direct(psy, POWER_SUPPLY_PROP_TIME_TO_EMPTY_AVG, + val); case POWER_SUPPLY_PROP_MANUFACTURE_YEAR: val->intval = test_power_battery_extmanufacture_year; break; diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index b7f15f303ea2..967dc4f9eea8 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -130,6 +130,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd) struct ism_req_hdr *req = cmd; struct ism_resp_hdr *resp = cmd; + spin_lock(&ism->cmd_lock); __ism_write_cmd(ism, req + 1, sizeof(*req), req->len - sizeof(*req)); __ism_write_cmd(ism, req, 0, sizeof(*req)); @@ -143,6 +144,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd) } __ism_read_cmd(ism, resp + 1, sizeof(*resp), resp->len - sizeof(*resp)); out: + spin_unlock(&ism->cmd_lock); return resp->ret; } @@ -606,6 +608,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) return -ENOMEM; spin_lock_init(&ism->lock); + spin_lock_init(&ism->cmd_lock); dev_set_drvdata(&pdev->dev, ism); ism->pdev = pdev; ism->dev.parent = &pdev->dev; diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index eea93f8f106f..c0e4883be6d0 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -518,28 +518,32 @@ static ssize_t qeth_hw_trap_store(struct device *dev, if (qeth_card_hw_is_reachable(card)) state = 1; - if (sysfs_streq(buf, "arm") && !card->info.hwtrap) { - if (state) { + if (sysfs_streq(buf, "arm")) { + if (state && !card->info.hwtrap) { if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) { rc = qeth_hw_trap(card, QETH_DIAGS_TRAP_ARM); if (!rc) card->info.hwtrap = 1; - } else + } else { rc = -EINVAL; - } else + } + } else { card->info.hwtrap = 1; - } else if (sysfs_streq(buf, "disarm") && card->info.hwtrap) { - if (state) { + } + } else if (sysfs_streq(buf, "disarm")) { + if (state && card->info.hwtrap) { rc = qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM); if (!rc) card->info.hwtrap = 0; - } else + } else { card->info.hwtrap = 0; - } else if (sysfs_streq(buf, "trap") && state && card->info.hwtrap) + } + } else if (sysfs_streq(buf, "trap") && state && card->info.hwtrap) { rc = qeth_hw_trap(card, QETH_DIAGS_TRAP_CAPTURE); - else + } else { rc = -EINVAL; + } mutex_unlock(&card->conf_mutex); return rc ? rc : count; diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index a12c68b93b1c..7a671a786197 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -238,7 +238,7 @@ static u64 amd_sdw_send_cmd_get_resp(struct amd_sdw_manager *amd_manager, u32 lo if (sts & AMD_SDW_IMM_RES_VALID) { dev_err(amd_manager->dev, "SDW%x manager is in bad state\n", amd_manager->instance); - writel(0x00, amd_manager->mmio + ACP_SW_IMM_CMD_STS); + writel(AMD_SDW_IMM_RES_VALID, amd_manager->mmio + ACP_SW_IMM_CMD_STS); } writel(upper_data, amd_manager->mmio + ACP_SW_IMM_CMD_UPPER_WORD); writel(lower_data, amd_manager->mmio + ACP_SW_IMM_CMD_LOWER_QWORD); @@ -1209,6 +1209,7 @@ static int __maybe_unused amd_suspend(struct device *dev) } if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { + cancel_work_sync(&amd_manager->amd_sdw_work); amd_sdw_wake_enable(amd_manager, false); if (amd_manager->acp_rev >= ACP70_PCI_REV_ID) { ret = amd_sdw_host_wake_enable(amd_manager, false); @@ -1219,6 +1220,7 @@ static int __maybe_unused amd_suspend(struct device *dev) if (ret) return ret; } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { + cancel_work_sync(&amd_manager->amd_sdw_work); amd_sdw_wake_enable(amd_manager, false); if (amd_manager->acp_rev >= ACP70_PCI_REV_ID) { ret = amd_sdw_host_wake_enable(amd_manager, false); diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index 295a46dc2be7..0f45e3404756 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -156,7 +156,6 @@ struct qcom_swrm_port_config { u8 word_length; u8 blk_group_count; u8 lane_control; - u8 ch_mask; }; /* @@ -1049,13 +1048,9 @@ static int qcom_swrm_port_enable(struct sdw_bus *bus, { u32 reg = SWRM_DP_PORT_CTRL_BANK(enable_ch->port_num, bank); struct qcom_swrm_ctrl *ctrl = to_qcom_sdw(bus); - struct qcom_swrm_port_config *pcfg; u32 val; - pcfg = &ctrl->pconfig[enable_ch->port_num]; ctrl->reg_read(ctrl, reg, &val); - if (pcfg->ch_mask != SWR_INVALID_PARAM && pcfg->ch_mask != 0) - enable_ch->ch_mask = pcfg->ch_mask; if (enable_ch->enable) val |= (enable_ch->ch_mask << SWRM_DP_PORT_CTRL_EN_CHAN_SHFT); @@ -1275,26 +1270,6 @@ static void *qcom_swrm_get_sdw_stream(struct snd_soc_dai *dai, int direction) return ctrl->sruntime[dai->id]; } -static int qcom_swrm_set_channel_map(struct snd_soc_dai *dai, - unsigned int tx_num, const unsigned int *tx_slot, - unsigned int rx_num, const unsigned int *rx_slot) -{ - struct qcom_swrm_ctrl *ctrl = dev_get_drvdata(dai->dev); - int i; - - if (tx_slot) { - for (i = 0; i < tx_num; i++) - ctrl->pconfig[i].ch_mask = tx_slot[i]; - } - - if (rx_slot) { - for (i = 0; i < rx_num; i++) - ctrl->pconfig[i].ch_mask = rx_slot[i]; - } - - return 0; -} - static int qcom_swrm_startup(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { @@ -1331,7 +1306,6 @@ static const struct snd_soc_dai_ops qcom_swrm_pdm_dai_ops = { .shutdown = qcom_swrm_shutdown, .set_stream = qcom_swrm_set_sdw_stream, .get_stream = qcom_swrm_get_sdw_stream, - .set_channel_map = qcom_swrm_set_channel_map, }; static const struct snd_soc_component_driver qcom_swrm_dai_component = { diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 1bc0fdbb1bd7..0ffa3f9f2870 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -4138,10 +4138,13 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) xfer->tx_nbits != SPI_NBITS_OCTAL) return -EINVAL; if ((xfer->tx_nbits == SPI_NBITS_DUAL) && - !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD))) + !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD | SPI_TX_OCTAL))) return -EINVAL; if ((xfer->tx_nbits == SPI_NBITS_QUAD) && - !(spi->mode & SPI_TX_QUAD)) + !(spi->mode & (SPI_TX_QUAD | SPI_TX_OCTAL))) + return -EINVAL; + if ((xfer->tx_nbits == SPI_NBITS_OCTAL) && + !(spi->mode & SPI_TX_OCTAL)) return -EINVAL; } /* Check transfer rx_nbits */ @@ -4154,10 +4157,13 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message) xfer->rx_nbits != SPI_NBITS_OCTAL) return -EINVAL; if ((xfer->rx_nbits == SPI_NBITS_DUAL) && - !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD))) + !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD | SPI_RX_OCTAL))) return -EINVAL; if ((xfer->rx_nbits == SPI_NBITS_QUAD) && - !(spi->mode & SPI_RX_QUAD)) + !(spi->mode & (SPI_RX_QUAD | SPI_RX_OCTAL))) + return -EINVAL; + if ((xfer->rx_nbits == SPI_NBITS_OCTAL) && + !(spi->mode & SPI_RX_OCTAL)) return -EINVAL; } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index 5dbf8d53db09..721b15b7e13b 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -97,6 +97,13 @@ struct vchiq_arm_state { * tracked separately with the state. */ int peer_use_count; + + /* + * Flag to indicate that the first vchiq connect has made it through. + * This means that both sides should be fully ready, and we should + * be able to suspend after this point. + */ + int first_connect; }; static int @@ -273,6 +280,29 @@ static int vchiq_platform_init(struct platform_device *pdev, struct vchiq_state return 0; } +int +vchiq_platform_init_state(struct vchiq_state *state) +{ + struct vchiq_arm_state *platform_state; + + platform_state = devm_kzalloc(state->dev, sizeof(*platform_state), GFP_KERNEL); + if (!platform_state) + return -ENOMEM; + + rwlock_init(&platform_state->susp_res_lock); + + init_completion(&platform_state->ka_evt); + atomic_set(&platform_state->ka_use_count, 0); + atomic_set(&platform_state->ka_use_ack_count, 0); + atomic_set(&platform_state->ka_release_count, 0); + + platform_state->state = state; + + state->platform_state = (struct opaque_platform_state *)platform_state; + + return 0; +} + static struct vchiq_arm_state *vchiq_platform_get_arm_state(struct vchiq_state *state) { return (struct vchiq_arm_state *)state->platform_state; @@ -363,8 +393,7 @@ int vchiq_shutdown(struct vchiq_instance *instance) struct vchiq_state *state = instance->state; int ret = 0; - if (mutex_lock_killable(&state->mutex)) - return -EAGAIN; + mutex_lock(&state->mutex); /* Remove all services */ vchiq_shutdown_internal(state, instance); @@ -982,39 +1011,6 @@ exit: } int -vchiq_platform_init_state(struct vchiq_state *state) -{ - struct vchiq_arm_state *platform_state; - char threadname[16]; - - platform_state = devm_kzalloc(state->dev, sizeof(*platform_state), GFP_KERNEL); - if (!platform_state) - return -ENOMEM; - - snprintf(threadname, sizeof(threadname), "vchiq-keep/%d", - state->id); - platform_state->ka_thread = kthread_create(&vchiq_keepalive_thread_func, - (void *)state, threadname); - if (IS_ERR(platform_state->ka_thread)) { - dev_err(state->dev, "couldn't create thread %s\n", threadname); - return PTR_ERR(platform_state->ka_thread); - } - - rwlock_init(&platform_state->susp_res_lock); - - init_completion(&platform_state->ka_evt); - atomic_set(&platform_state->ka_use_count, 0); - atomic_set(&platform_state->ka_use_ack_count, 0); - atomic_set(&platform_state->ka_release_count, 0); - - platform_state->state = state; - - state->platform_state = (struct opaque_platform_state *)platform_state; - - return 0; -} - -int vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service, enum USE_TYPE_E use_type) { @@ -1329,19 +1325,37 @@ out: return ret; } -void vchiq_platform_connected(struct vchiq_state *state) -{ - struct vchiq_arm_state *arm_state = vchiq_platform_get_arm_state(state); - - wake_up_process(arm_state->ka_thread); -} - void vchiq_platform_conn_state_changed(struct vchiq_state *state, enum vchiq_connstate oldstate, enum vchiq_connstate newstate) { + struct vchiq_arm_state *arm_state = vchiq_platform_get_arm_state(state); + char threadname[16]; + dev_dbg(state->dev, "suspend: %d: %s->%s\n", state->id, get_conn_state_name(oldstate), get_conn_state_name(newstate)); + if (state->conn_state != VCHIQ_CONNSTATE_CONNECTED) + return; + + write_lock_bh(&arm_state->susp_res_lock); + if (arm_state->first_connect) { + write_unlock_bh(&arm_state->susp_res_lock); + return; + } + + arm_state->first_connect = 1; + write_unlock_bh(&arm_state->susp_res_lock); + snprintf(threadname, sizeof(threadname), "vchiq-keep/%d", + state->id); + arm_state->ka_thread = kthread_create(&vchiq_keepalive_thread_func, + (void *)state, + threadname); + if (IS_ERR(arm_state->ka_thread)) { + dev_err(state->dev, "suspend: Couldn't create thread %s\n", + threadname); + } else { + wake_up_process(arm_state->ka_thread); + } } static const struct of_device_id vchiq_of_match[] = { diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c index e7b0c800a205..e2cac0898b8f 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c @@ -3343,7 +3343,6 @@ vchiq_connect_internal(struct vchiq_state *state, struct vchiq_instance *instanc return -EAGAIN; vchiq_set_conn_state(state, VCHIQ_CONNSTATE_CONNECTED); - vchiq_platform_connected(state); complete(&state->connect); } diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h index 3b5c0618e567..9b4e766990a4 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.h @@ -575,8 +575,6 @@ int vchiq_send_remote_use(struct vchiq_state *state); int vchiq_send_remote_use_active(struct vchiq_state *state); -void vchiq_platform_connected(struct vchiq_state *state); - void vchiq_platform_conn_state_changed(struct vchiq_state *state, enum vchiq_connstate oldstate, enum vchiq_connstate newstate); diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 28febb95f8fa..b6c58a7e7b6a 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1450,7 +1450,7 @@ int tb_dp_port_set_hops(struct tb_port *port, unsigned int video, return ret; data[0] &= ~ADP_DP_CS_0_VIDEO_HOPID_MASK; - data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK; + data[1] &= ~ADP_DP_CS_1_AUX_TX_HOPID_MASK; data[1] &= ~ADP_DP_CS_1_AUX_RX_HOPID_MASK; data[0] |= (video << ADP_DP_CS_0_VIDEO_HOPID_SHIFT) & @@ -3437,7 +3437,7 @@ void tb_sw_set_unplugged(struct tb_switch *sw) } } -static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) +static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime) { if (flags) tb_sw_dbg(sw, "enabling wakeup: %#x\n", flags); @@ -3445,7 +3445,7 @@ static int tb_switch_set_wake(struct tb_switch *sw, unsigned int flags) tb_sw_dbg(sw, "disabling wakeup\n"); if (tb_switch_is_usb4(sw)) - return usb4_switch_set_wake(sw, flags); + return usb4_switch_set_wake(sw, flags, runtime); return tb_lc_set_wake(sw, flags); } @@ -3521,7 +3521,7 @@ int tb_switch_resume(struct tb_switch *sw, bool runtime) tb_switch_check_wakes(sw); /* Disable wakes */ - tb_switch_set_wake(sw, 0); + tb_switch_set_wake(sw, 0, true); err = tb_switch_tmu_init(sw); if (err) @@ -3603,7 +3603,7 @@ void tb_switch_suspend(struct tb_switch *sw, bool runtime) flags |= TB_WAKE_ON_USB4 | TB_WAKE_ON_USB3 | TB_WAKE_ON_PCIE; } - tb_switch_set_wake(sw, flags); + tb_switch_set_wake(sw, flags, runtime); if (tb_switch_is_usb4(sw)) usb4_switch_set_sleep(sw); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 87afd5a7c504..f503bad86413 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -1317,7 +1317,7 @@ int usb4_switch_read_uid(struct tb_switch *sw, u64 *uid); int usb4_switch_drom_read(struct tb_switch *sw, unsigned int address, void *buf, size_t size); bool usb4_switch_lane_bonding_possible(struct tb_switch *sw); -int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags); +int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime); int usb4_switch_set_sleep(struct tb_switch *sw); int usb4_switch_nvm_sector_size(struct tb_switch *sw); int usb4_switch_nvm_read(struct tb_switch *sw, unsigned int address, void *buf, diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index fce3c0f2354a..fdae76c8f728 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -403,12 +403,12 @@ bool usb4_switch_lane_bonding_possible(struct tb_switch *sw) * usb4_switch_set_wake() - Enabled/disable wake * @sw: USB4 router * @flags: Wakeup flags (%0 to disable) + * @runtime: Wake is being programmed during system runtime * * Enables/disables router to wake up from sleep. */ -int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags) +int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags, bool runtime) { - struct usb4_port *usb4; struct tb_port *port; u64 route = tb_route(sw); u32 val; @@ -438,13 +438,11 @@ int usb4_switch_set_wake(struct tb_switch *sw, unsigned int flags) val |= PORT_CS_19_WOU4; } else { bool configured = val & PORT_CS_19_PC; - usb4 = port->usb4; + bool wakeup = runtime || device_may_wakeup(&port->usb4->dev); - if (((flags & TB_WAKE_ON_CONNECT) && - device_may_wakeup(&usb4->dev)) && !configured) + if ((flags & TB_WAKE_ON_CONNECT) && wakeup && !configured) val |= PORT_CS_19_WOC; - if (((flags & TB_WAKE_ON_DISCONNECT) && - device_may_wakeup(&usb4->dev)) && configured) + if ((flags & TB_WAKE_ON_DISCONNECT) && wakeup && configured) val |= PORT_CS_19_WOD; if ((flags & TB_WAKE_ON_USB4) && configured) val |= PORT_CS_19_WOU4; diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 508e8c6f01d4..884fefbfd5a1 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -954,7 +954,7 @@ static unsigned int dma_handle_tx(struct eg20t_port *priv) __func__); return 0; } - dma_sync_sg_for_device(port->dev, priv->sg_tx_p, nent, DMA_TO_DEVICE); + dma_sync_sg_for_device(port->dev, priv->sg_tx_p, num, DMA_TO_DEVICE); priv->desc_tx = desc; desc->callback = pch_dma_tx_complete; desc->callback_param = priv; diff --git a/drivers/tty/serial/serial_base_bus.c b/drivers/tty/serial/serial_base_bus.c index cb3b127b06b6..22749ab0428a 100644 --- a/drivers/tty/serial/serial_base_bus.c +++ b/drivers/tty/serial/serial_base_bus.c @@ -13,6 +13,7 @@ #include <linux/device.h> #include <linux/idr.h> #include <linux/module.h> +#include <linux/of.h> #include <linux/serial_core.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -93,6 +94,7 @@ static void serial_base_ctrl_release(struct device *dev) { struct serial_ctrl_device *ctrl_dev = to_serial_base_ctrl_device(dev); + of_node_put(dev->of_node); kfree(ctrl_dev); } @@ -140,6 +142,7 @@ static void serial_base_port_release(struct device *dev) { struct serial_port_device *port_dev = to_serial_base_port_device(dev); + of_node_put(dev->of_node); kfree(port_dev); } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 3e1215f7a9a0..256fe8c86828 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5751,6 +5751,7 @@ static void port_event(struct usb_hub *hub, int port1) struct usb_device *hdev = hub->hdev; u16 portstatus, portchange; int i = 0; + int err; connect_change = test_bit(port1, hub->change_bits); clear_bit(port1, hub->event_bits); @@ -5847,8 +5848,11 @@ static void port_event(struct usb_hub *hub, int port1) } else if (!udev || !(portstatus & USB_PORT_STAT_CONNECTION) || udev->state == USB_STATE_NOTATTACHED) { dev_dbg(&port_dev->dev, "do warm reset, port only\n"); - if (hub_port_reset(hub, port1, NULL, - HUB_BH_RESET_TIME, true) < 0) + err = hub_port_reset(hub, port1, NULL, + HUB_BH_RESET_TIME, true); + if (!udev && err == -ENOTCONN) + connect_change = 0; + else if (err < 0) hub_port_disable(hub, port1, 1); } else { dev_dbg(&port_dev->dev, "do warm reset, full device\n"); diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index d5b622f78cf3..0637bfbc054e 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -5389,20 +5389,34 @@ int dwc2_gadget_enter_hibernation(struct dwc2_hsotg *hsotg) if (gusbcfg & GUSBCFG_ULPI_UTMI_SEL) { /* ULPI interface */ gpwrdn |= GPWRDN_ULPI_LATCH_EN_DURING_HIB_ENTRY; - } - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); - /* Suspend the Phy Clock */ - pcgcctl = dwc2_readl(hsotg, PCGCTL); - pcgcctl |= PCGCTL_STOPPCLK; - dwc2_writel(hsotg, pcgcctl, PCGCTL); - udelay(10); + /* Suspend the Phy Clock */ + pcgcctl = dwc2_readl(hsotg, PCGCTL); + pcgcctl |= PCGCTL_STOPPCLK; + dwc2_writel(hsotg, pcgcctl, PCGCTL); + udelay(10); - gpwrdn = dwc2_readl(hsotg, GPWRDN); - gpwrdn |= GPWRDN_PMUACTV; - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn |= GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } else { + /* UTMI+ Interface */ + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn |= GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + + pcgcctl = dwc2_readl(hsotg, PCGCTL); + pcgcctl |= PCGCTL_STOPPCLK; + dwc2_writel(hsotg, pcgcctl, PCGCTL); + udelay(10); + } /* Set flag to indicate that we are in hibernation */ hsotg->hibernated = 1; diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index 7334de85ad10..ca7e1c02773a 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -680,12 +680,12 @@ static int dwc3_qcom_probe(struct platform_device *pdev) ret = reset_control_deassert(qcom->resets); if (ret) { dev_err(&pdev->dev, "failed to deassert resets, err=%d\n", ret); - goto reset_assert; + return ret; } ret = clk_bulk_prepare_enable(qcom->num_clocks, qcom->clks); if (ret < 0) - goto reset_assert; + return ret; r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { @@ -755,8 +755,6 @@ remove_core: dwc3_core_remove(&qcom->dwc); clk_disable: clk_bulk_disable_unprepare(qcom->num_clocks, qcom->clks); -reset_assert: - reset_control_assert(qcom->resets); return ret; } @@ -771,7 +769,6 @@ static void dwc3_qcom_remove(struct platform_device *pdev) clk_bulk_disable_unprepare(qcom->num_clocks, qcom->clks); dwc3_qcom_interconnect_exit(qcom); - reset_control_assert(qcom->resets); } static int dwc3_qcom_pm_suspend(struct device *dev) diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index fba2a56dae97..f94ea196ce54 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1065,6 +1065,8 @@ static ssize_t webusb_landingPage_store(struct config_item *item, const char *pa unsigned int bytes_to_strip = 0; int l = len; + if (!len) + return len; if (page[l - 1] == '\n') { --l; ++bytes_to_strip; @@ -1188,6 +1190,8 @@ static ssize_t os_desc_qw_sign_store(struct config_item *item, const char *page, struct gadget_info *gi = os_desc_item_to_gadget_info(item); int res, l; + if (!len) + return len; l = min_t(int, len, OS_STRING_QW_SIGN_LEN >> 1); if (page[l - 1] == '\n') --l; diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index 6869c58367f2..caf4d4cd4b75 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -1913,6 +1913,7 @@ static int musb_gadget_stop(struct usb_gadget *g) * gadget driver here and have everything work; * that currently misbehaves. */ + usb_gadget_set_state(g, USB_STATE_NOTATTACHED); /* Force check of devctl register for PM runtime */ pm_runtime_mark_last_busy(musb->controller); @@ -2019,6 +2020,7 @@ void musb_g_disconnect(struct musb *musb) case OTG_STATE_B_PERIPHERAL: case OTG_STATE_B_IDLE: musb_set_state(musb, OTG_STATE_B_IDLE); + usb_gadget_set_state(&musb->g, USB_STATE_NOTATTACHED); break; case OTG_STATE_B_SRP_INIT: break; diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 6ac7a0a5cf07..abfcfca3f971 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -803,6 +803,8 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, { USB_DEVICE(FTDI_VID, FTDI_NDI_AURORA_SCU_PID), .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, + { USB_DEVICE(FTDI_NDI_VID, FTDI_NDI_EMGUIDE_GEMINI_PID), + .driver_info = (kernel_ulong_t)&ftdi_NDI_device_quirk }, { USB_DEVICE(TELLDUS_VID, TELLDUS_TELLSTICK_PID) }, { USB_DEVICE(NOVITUS_VID, NOVITUS_BONO_E_PID) }, { USB_DEVICE(FTDI_VID, RTSYSTEMS_USB_VX8_PID) }, diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 9acb6f837327..4cc1fae8acb9 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -204,6 +204,9 @@ #define FTDI_NDI_FUTURE_3_PID 0xDA73 /* NDI future device #3 */ #define FTDI_NDI_AURORA_SCU_PID 0xDA74 /* NDI Aurora SCU */ +#define FTDI_NDI_VID 0x23F2 +#define FTDI_NDI_EMGUIDE_GEMINI_PID 0x0003 /* NDI Emguide Gemini */ + /* * ChamSys Limited (www.chamsys.co.uk) USB wing/interface product IDs */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 27879cc57536..147ca50c94be 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1415,6 +1415,9 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(5) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x60) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x30), /* Telit FE910C04 (ECM) */ + .driver_info = NCTRL(4) }, + { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10c7, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x30), /* Telit FN990B (MBIM) */ .driver_info = NCTRL(6) }, { USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x40) }, @@ -2343,6 +2346,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe145, 0xff), /* Foxconn T99W651 RNDIS */ .driver_info = RSVD(5) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(0x0489, 0xe167, 0xff), /* Foxconn T99W640 MBIM */ + .driver_info = RSVD(3) }, { USB_DEVICE(0x1508, 0x1001), /* Fibocom NL668 (IOT version) */ .driver_info = RSVD(4) | RSVD(5) | RSVD(6) }, { USB_DEVICE(0x1782, 0x4d10) }, /* Fibocom L610 (AT mode) */ diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index b375ad610acd..b58525ec7b4d 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -511,7 +511,8 @@ again: bch2_dev_usage_read_fast(ca, &req->usage); avail = dev_buckets_free(ca, req->usage, req->watermark); - if (req->usage.buckets[BCH_DATA_need_discard] > avail) + if (req->usage.buckets[BCH_DATA_need_discard] > + min(avail, ca->mi.nbuckets >> 7)) bch2_dev_do_discards(ca); if (req->usage.buckets[BCH_DATA_need_gc_gens] > avail) diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c index a4cc72986e36..590cd29f3e86 100644 --- a/fs/bcachefs/btree_io.c +++ b/fs/bcachefs/btree_io.c @@ -1295,9 +1295,6 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_bounce_free(c, btree_buf_bytes(b), used_mempool, sorted); - if (updated_range) - bch2_btree_node_drop_keys_outside_node(b); - i = &b->data->keys; for (k = i->start; k != vstruct_last(i);) { struct bkey tmp; @@ -1335,6 +1332,9 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, btree_node_reset_sib_u64s(b); + if (updated_range) + bch2_btree_node_drop_keys_outside_node(b); + /* * XXX: * diff --git a/fs/bcachefs/dirent.c b/fs/bcachefs/dirent.c index a18d0f78704d..28875c5c86ad 100644 --- a/fs/bcachefs/dirent.c +++ b/fs/bcachefs/dirent.c @@ -13,6 +13,7 @@ #include <linux/dcache.h> +#ifdef CONFIG_UNICODE int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info, const struct qstr *str, struct qstr *out_cf) { @@ -33,6 +34,7 @@ int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info, *out_cf = (struct qstr) QSTR_INIT(buf, ret); return 0; } +#endif static unsigned bch2_dirent_name_bytes(struct bkey_s_c_dirent d) { @@ -254,6 +256,7 @@ int bch2_dirent_init_name(struct bch_fs *c, if (!bch2_fs_casefold_enabled(c)) return -EOPNOTSUPP; +#ifdef CONFIG_UNICODE memcpy(&dirent->v.d_cf_name_block.d_names[0], name->name, name->len); char *cf_out = &dirent->v.d_cf_name_block.d_names[name->len]; @@ -279,6 +282,7 @@ int bch2_dirent_init_name(struct bch_fs *c, dirent->v.d_cf_name_block.d_cf_name_len = cpu_to_le16(cf_len); EBUG_ON(bch2_dirent_get_casefold_name(dirent_i_to_s_c(dirent)).len != cf_len); +#endif } unsigned u64s = dirent_val_u64s(name->len, cf_len); diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h index 1e17199cc5c7..0417608c18d5 100644 --- a/fs/bcachefs/dirent.h +++ b/fs/bcachefs/dirent.h @@ -23,8 +23,16 @@ struct bch_fs; struct bch_hash_info; struct bch_inode_info; +#ifdef CONFIG_UNICODE int bch2_casefold(struct btree_trans *, const struct bch_hash_info *, const struct qstr *, struct qstr *); +#else +static inline int bch2_casefold(struct btree_trans *trans, const struct bch_hash_info *info, + const struct qstr *str, struct qstr *out_cf) +{ + return -EOPNOTSUPP; +} +#endif static inline int bch2_maybe_casefold(struct btree_trans *trans, const struct bch_hash_info *info, diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c index cd184b219a65..e0874ad9a6cf 100644 --- a/fs/bcachefs/io_read.c +++ b/fs/bcachefs/io_read.c @@ -166,6 +166,7 @@ static noinline void promote_free(struct bch_read_bio *rbio) BUG_ON(ret); async_object_list_del(c, promote, op->list_idx); + async_object_list_del(c, rbio, rbio->list_idx); bch2_data_update_exit(&op->write); @@ -456,6 +457,10 @@ static void bch2_rbio_done(struct bch_read_bio *rbio) if (rbio->start_time) bch2_time_stats_update(&rbio->c->times[BCH_TIME_data_read], rbio->start_time); +#ifdef CONFIG_BCACHEFS_ASYNC_OBJECT_LISTS + if (rbio->list_idx) + async_object_list_del(rbio->c, rbio, rbio->list_idx); +#endif bio_endio(&rbio->bio); } diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index dd3f3434c1b0..9e028dbcc3d0 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -1767,6 +1767,7 @@ static CLOSURE_CALLBACK(journal_write_done) closure_wake_up(&c->freelist_wait); bch2_reset_alloc_cursors(c); + do_discards = true; } j->seq_ondisk = seq; diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index 27e68d470ad0..5e6de91a8763 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -71,7 +71,7 @@ static int bch2_bucket_is_movable(struct btree_trans *trans, if (ret) return ret; - struct bch_dev *ca = bch2_dev_tryget(c, k.k->p.inode); + struct bch_dev *ca = bch2_dev_bucket_tryget(c, k.k->p); if (!ca) goto out; diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index c08e4a66ac07..3e0576d9db1d 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -347,8 +347,6 @@ int __cachefiles_write(struct cachefiles_object *object, default: ki->was_async = false; cachefiles_write_complete(&ki->iocb, ret); - if (ret > 0) - ret = 0; break; } diff --git a/fs/cachefiles/ondemand.c b/fs/cachefiles/ondemand.c index d9bc67176128..a7ed86fa98bb 100644 --- a/fs/cachefiles/ondemand.c +++ b/fs/cachefiles/ondemand.c @@ -83,10 +83,8 @@ static ssize_t cachefiles_ondemand_fd_write_iter(struct kiocb *kiocb, trace_cachefiles_ondemand_fd_write(object, file_inode(file), pos, len); ret = __cachefiles_write(object, file, pos, iter, NULL, NULL); - if (!ret) { - ret = len; + if (ret > 0) kiocb->ki_pos += ret; - } out: fput(file); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index c900d98bf494..284d6dbba2ec 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -390,10 +390,16 @@ static int efivarfs_reconfigure(struct fs_context *fc) return 0; } +static void efivarfs_free(struct fs_context *fc) +{ + kfree(fc->s_fs_info); +} + static const struct fs_context_operations efivarfs_context_ops = { .get_tree = efivarfs_get_tree, .parse_param = efivarfs_parse_param, .reconfigure = efivarfs_reconfigure, + .free = efivarfs_free, }; static int efivarfs_check_missing(efi_char16_t *name16, efi_guid_t vendor, diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 3729391a18f3..fb4519158f3a 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -71,6 +71,9 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off, unsigned long flags; bool uptodate = true; + if (folio_test_uptodate(folio)) + return; + if (ifs) { spin_lock_irqsave(&ifs->state_lock, flags); uptodate = ifs_set_range_uptodate(folio, ifs, off, len); diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d5da9817df9b..33e6a620c103 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -1440,9 +1440,16 @@ static int isofs_read_inode(struct inode *inode, int relocated) inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); inode->i_data.a_ops = &isofs_symlink_aops; - } else + } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || + S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { /* XXX - parse_rock_ridge_inode() had already set i_rdev. */ init_special_inode(inode, inode->i_mode, inode->i_rdev); + } else { + printk(KERN_DEBUG "ISOFS: Invalid file type 0%04o for inode %lu.\n", + inode->i_mode, inode->i_ino); + ret = -EIO; + goto fail; + } ret = 0; out: diff --git a/fs/netfs/read_pgpriv2.c b/fs/netfs/read_pgpriv2.c index 5bbe906a551d..8097bc069c1d 100644 --- a/fs/netfs/read_pgpriv2.c +++ b/fs/netfs/read_pgpriv2.c @@ -110,6 +110,8 @@ static struct netfs_io_request *netfs_pgpriv2_begin_copy_to_cache( if (!creq->io_streams[1].avail) goto cancel_put; + __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &creq->flags); + trace_netfs_copy2cache(rreq, creq); trace_netfs_write(creq, netfs_write_trace_copy_to_cache); netfs_stat(&netfs_n_wh_copy_to_cache); rreq->copy_to_cache = creq; @@ -154,6 +156,9 @@ void netfs_pgpriv2_end_copy_to_cache(struct netfs_io_request *rreq) netfs_issue_write(creq, &creq->io_streams[1]); smp_wmb(); /* Write lists before ALL_QUEUED. */ set_bit(NETFS_RREQ_ALL_QUEUED, &creq->flags); + trace_netfs_rreq(rreq, netfs_rreq_trace_end_copy_to_cache); + if (list_empty_careful(&creq->io_streams[1].subrequests)) + netfs_wake_collector(creq); netfs_put_request(creq, netfs_rreq_trace_put_return); creq->copy_to_cache = NULL; diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index c4cdaf5fa7ed..9fb73bafd41d 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -308,6 +308,10 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } + error = file_f_owner_allocate(filp); + if (error) + goto out_err; + /* new fsnotify mark, we expect most fcntl calls to add a new mark */ new_dn_mark = kmem_cache_alloc(dnotify_mark_cache, GFP_KERNEL); if (!new_dn_mark) { @@ -315,10 +319,6 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg) goto out_err; } - error = file_f_owner_allocate(filp); - if (error) - goto out_err; - /* set up the new_fsn_mark and new_dn_mark */ new_fsn_mark = &new_dn_mark->fsn_mark; fsnotify_init_mark(new_fsn_mark, dnotify_group); diff --git a/fs/pidfs.c b/fs/pidfs.c index 69919be1c9d8..4625e097e3a0 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -319,7 +319,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg) if (!c) return -ESRCH; - if (!(kinfo.mask & PIDFD_INFO_COREDUMP)) { + if ((kinfo.mask & PIDFD_INFO_COREDUMP) && !(kinfo.coredump_mask)) { task_lock(task); if (task->mm) kinfo.coredump_mask = pidfs_coredump_mask(task->mm->flags); diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 1c6e5389c51f..5223edf6d11a 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -190,6 +190,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + struct cached_fid *parent_cfid = NULL; int rdwr_for_fscache = 0; __le32 lease_flags = 0; @@ -313,10 +314,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned if (!tcon->unix_ext && (mode & S_IWUGO) == 0) create_options |= CREATE_OPTION_READONLY; + retry_open: if (tcon->cfids && direntry->d_parent && server->dialect >= SMB30_PROT_ID) { - struct cached_fid *parent_cfid; - + parent_cfid = NULL; spin_lock(&tcon->cfids->cfid_list_lock); list_for_each_entry(parent_cfid, &tcon->cfids->entries, entry) { if (parent_cfid->dentry == direntry->d_parent) { @@ -327,6 +328,7 @@ retry_open: memcpy(fid->parent_lease_key, parent_cfid->fid.lease_key, SMB2_LEASE_KEY_SIZE); + parent_cfid->dirents.is_valid = false; } break; } diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index e9212da32f01..1421bde045c2 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -3088,7 +3088,8 @@ void cifs_oplock_break(struct work_struct *work) struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, oplock_break); struct inode *inode = d_inode(cfile->dentry); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct super_block *sb = inode->i_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifsInodeInfo *cinode = CIFS_I(inode); struct cifs_tcon *tcon; struct TCP_Server_Info *server; @@ -3098,6 +3099,12 @@ void cifs_oplock_break(struct work_struct *work) __u64 persistent_fid, volatile_fid; __u16 net_fid; + /* + * Hold a reference to the superblock to prevent it and its inodes from + * being freed while we are accessing cinode. Otherwise, _cifsFileInfo_put() + * may release the last reference to the sb and trigger inode eviction. + */ + cifs_sb_active(sb); wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE); @@ -3170,6 +3177,7 @@ oplock_break_ack: cifs_put_tlink(tlink); out: cifs_done_oplock_break(cinode); + cifs_sb_deactive(sb); } static int cifs_swap_activate(struct swap_info_struct *sis, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 2a3e46b8e15a..a11a2a693c51 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -1346,7 +1346,8 @@ struct inode *smb2_get_reparse_inode(struct cifs_open_info_data *data, * empty object on the server. */ if (!(le32_to_cpu(tcon->fsAttrInfo.Attributes) & FILE_SUPPORTS_REPARSE_POINTS)) - return ERR_PTR(-EOPNOTSUPP); + if (!tcon->posix_extensions) + return ERR_PTR(-EOPNOTSUPP); oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, SYNCHRONIZE | DELETE | diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 1468c16ea9b8..938a8a7c5d21 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -4316,6 +4316,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; u8 *iv; + DECLARE_CRYPTO_WAIT(wait); unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize); void *creq; size_t sensitive_size; @@ -4366,7 +4367,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, aead_request_set_crypt(req, sg, sg, crypt_len, iv); aead_request_set_ad(req, assoc_data_len); - rc = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req); + aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &wait); + + rc = crypto_wait_req(enc ? crypto_aead_encrypt(req) + : crypto_aead_decrypt(req), &wait); if (!rc && enc) memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE); @@ -5255,7 +5260,8 @@ static int smb2_make_node(unsigned int xid, struct inode *inode, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { rc = cifs_sfu_make_node(xid, inode, dentry, tcon, full_path, mode, dev); - } else if (le32_to_cpu(tcon->fsAttrInfo.Attributes) & FILE_SUPPORTS_REPARSE_POINTS) { + } else if ((le32_to_cpu(tcon->fsAttrInfo.Attributes) & FILE_SUPPORTS_REPARSE_POINTS) + || (tcon->posix_extensions)) { rc = smb2_mknod_reparse(xid, inode, dentry, tcon, full_path, mode, dev); } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 63d17cea2e95..fca92d1fea22 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -7847,7 +7847,7 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn, if (!ksmbd_find_netdev_name_iface_list(netdev->name)) continue; - flags = dev_get_flags(netdev); + flags = netif_get_flags(netdev); if (!(flags & IFF_RUNNING)) continue; ipv6_retry: diff --git a/fs/ufs/super.c b/fs/ufs/super.c index eea718ac66b4..6e4585169f94 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -397,7 +397,7 @@ static int ufs_parse_param(struct fs_context *fc, struct fs_parameter *param) pr_err("ufstype can't be changed during remount\n"); return -EINVAL; } - if (!ctx->flavour) { + if (ctx->flavour) { pr_err("conflicting ufstype options\n"); return -EINVAL; } diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c index e9d76bcdc820..20ad7c309489 100644 --- a/fs/xfs/libxfs/xfs_group.c +++ b/fs/xfs/libxfs/xfs_group.c @@ -163,7 +163,8 @@ xfs_group_free( xfs_defer_drain_free(&xg->xg_intents_drain); #ifdef __KERNEL__ - kfree(xg->xg_busy_extents); + if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type)) + kfree(xg->xg_busy_extents); #endif if (uninit) @@ -189,9 +190,11 @@ xfs_group_insert( xg->xg_type = type; #ifdef __KERNEL__ - xg->xg_busy_extents = xfs_extent_busy_alloc(); - if (!xg->xg_busy_extents) - return -ENOMEM; + if (xfs_group_has_extent_busy(mp, type)) { + xg->xg_busy_extents = xfs_extent_busy_alloc(); + if (!xg->xg_busy_extents) + return -ENOMEM; + } spin_lock_init(&xg->xg_state_lock); xfs_hooks_init(&xg->xg_rmap_update_hooks); #endif @@ -210,7 +213,8 @@ xfs_group_insert( out_drain: xfs_defer_drain_free(&xg->xg_intents_drain); #ifdef __KERNEL__ - kfree(xg->xg_busy_extents); + if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type)) + kfree(xg->xg_busy_extents); #endif return error; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index ba5bd6031ece..f9ef3b2a332a 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1683,7 +1683,7 @@ xfs_free_buftarg( fs_put_dax(btp->bt_daxdev, btp->bt_mount); /* the main block device is closed by kill_block_super */ if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev) - bdev_fput(btp->bt_bdev_file); + bdev_fput(btp->bt_file); kfree(btp); } @@ -1712,8 +1712,8 @@ xfs_configure_buftarg_atomic_writes( max_bytes = 0; } - btp->bt_bdev_awu_min = min_bytes; - btp->bt_bdev_awu_max = max_bytes; + btp->bt_awu_min = min_bytes; + btp->bt_awu_max = max_bytes; } /* Configure a buffer target that abstracts a block device. */ @@ -1738,14 +1738,9 @@ xfs_configure_buftarg( return -EINVAL; } - /* - * Flush the block device pagecache so our bios see anything dirtied - * before mount. - */ if (bdev_can_atomic_write(btp->bt_bdev)) xfs_configure_buftarg_atomic_writes(btp); - - return sync_blockdev(btp->bt_bdev); + return 0; } int @@ -1803,7 +1798,7 @@ xfs_alloc_buftarg( btp = kzalloc(sizeof(*btp), GFP_KERNEL | __GFP_NOFAIL); btp->bt_mount = mp; - btp->bt_bdev_file = bdev_file; + btp->bt_file = bdev_file; btp->bt_bdev = file_bdev(bdev_file); btp->bt_dev = btp->bt_bdev->bd_dev; btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off, diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 15fc56948346..b269e115d9ac 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -94,7 +94,6 @@ void xfs_buf_cache_destroy(struct xfs_buf_cache *bch); */ struct xfs_buftarg { dev_t bt_dev; - struct file *bt_bdev_file; struct block_device *bt_bdev; struct dax_device *bt_daxdev; struct file *bt_file; @@ -112,9 +111,9 @@ struct xfs_buftarg { struct percpu_counter bt_readahead_count; struct ratelimit_state bt_ioerror_rl; - /* Atomic write unit values, bytes */ - unsigned int bt_bdev_awu_min; - unsigned int bt_bdev_awu_max; + /* Hardware atomic write unit values, bytes */ + unsigned int bt_awu_min; + unsigned int bt_awu_max; /* built-in cache, if we're not using the perag one */ struct xfs_buf_cache bt_cache[]; @@ -375,7 +374,6 @@ extern void xfs_buftarg_wait(struct xfs_buftarg *); extern void xfs_buftarg_drain(struct xfs_buftarg *); int xfs_configure_buftarg(struct xfs_buftarg *btp, unsigned int sectorsize); -#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev) #define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev) int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops); diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index 94d0873bcd62..603d51365645 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -103,24 +103,6 @@ xfs_discard_endio( bio_put(bio); } -static inline struct block_device * -xfs_group_bdev( - const struct xfs_group *xg) -{ - struct xfs_mount *mp = xg->xg_mount; - - switch (xg->xg_type) { - case XG_TYPE_AG: - return mp->m_ddev_targp->bt_bdev; - case XG_TYPE_RTG: - return mp->m_rtdev_targp->bt_bdev; - default: - ASSERT(0); - break; - } - return NULL; -} - /* * Walk the discard list and issue discards on all the busy extents in the * list. We plug and chain the bios so that we only need a single completion @@ -138,11 +120,14 @@ xfs_discard_extents( blk_start_plug(&plug); list_for_each_entry(busyp, &extents->extent_list, list) { - trace_xfs_discard_extent(busyp->group, busyp->bno, - busyp->length); + struct xfs_group *xg = busyp->group; + struct xfs_buftarg *btp = + xfs_group_type_buftarg(xg->xg_mount, xg->xg_type); + + trace_xfs_discard_extent(xg, busyp->bno, busyp->length); - error = __blkdev_issue_discard(xfs_group_bdev(busyp->group), - xfs_gbno_to_daddr(busyp->group, busyp->bno), + error = __blkdev_issue_discard(btp->bt_bdev, + xfs_gbno_to_daddr(xg, busyp->bno), XFS_FSB_TO_BB(mp, busyp->length), GFP_KERNEL, &bio); if (error && error != -EOPNOTSUPP) { diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h index f069b04e8ea1..3e6e019b6146 100644 --- a/fs/xfs/xfs_extent_busy.h +++ b/fs/xfs/xfs_extent_busy.h @@ -68,4 +68,12 @@ static inline void xfs_extent_busy_sort(struct list_head *list) list_sort(NULL, list, xfs_extent_busy_ag_cmp); } +/* + * Zoned RTGs don't need to track busy extents, as the actual block freeing only + * happens by a zone reset, which forces out all transactions that touched the + * to be reset zone first. + */ +#define xfs_group_has_extent_busy(mp, type) \ + ((type) == XG_TYPE_AG || !xfs_has_zoned((mp))) + #endif /* __XFS_EXTENT_BUSY_H__ */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 0b41b18debf3..38e365b16348 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -752,7 +752,7 @@ xfs_file_dio_write_atomic( * HW offload should be faster, so try that first if it is already * known that the write length is not too large. */ - if (ocount > xfs_inode_buftarg(ip)->bt_bdev_awu_max) + if (ocount > xfs_inode_buftarg(ip)->bt_awu_max) dops = &xfs_atomic_write_cow_iomap_ops; else dops = &xfs_direct_write_iomap_ops; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index d7e2b902ef5c..07fbdcc4cbf5 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -358,7 +358,7 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip) static inline bool xfs_inode_can_hw_atomic_write(const struct xfs_inode *ip) { - return xfs_inode_buftarg(ip)->bt_bdev_awu_max > 0; + return xfs_inode_buftarg(ip)->bt_awu_max > 0; } /* diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index ff05e6b1b0bb..ec30b78bf5c4 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -827,7 +827,7 @@ xfs_bmap_hw_atomic_write_possible( /* * The ->iomap_begin caller should ensure this, but check anyway. */ - return len <= xfs_inode_buftarg(ip)->bt_bdev_awu_max; + return len <= xfs_inode_buftarg(ip)->bt_awu_max; } static int diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 8cddbb7c149b..01e597290eb5 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -665,7 +665,7 @@ xfs_get_atomic_write_max_opt( * less than our out of place write limit, but we don't want to exceed * the awu_max. */ - return min(awu_max, xfs_inode_buftarg(ip)->bt_bdev_awu_max); + return min(awu_max, xfs_inode_buftarg(ip)->bt_awu_max); } static void diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 29276fe60df9..0b690bc119d7 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -171,19 +171,16 @@ xfs_readsb( ASSERT(mp->m_ddev_targp != NULL); /* - * For the initial read, we must guess at the sector - * size based on the block device. It's enough to - * get the sb_sectsize out of the superblock and - * then reread with the proper length. - * We don't verify it yet, because it may not be complete. + * In the first pass, use the device sector size to just read enough + * of the superblock to extract the XFS sector size. + * + * The device sector size must be smaller than or equal to the XFS + * sector size and thus we can always read the superblock. Once we know + * the XFS sector size, re-read it and run the buffer verifier. */ - sector_size = xfs_getsize_buftarg(mp->m_ddev_targp); + sector_size = mp->m_ddev_targp->bt_logical_sectorsize; buf_ops = NULL; - /* - * Allocate a (locked) buffer to hold the superblock. This will be kept - * around at all times to optimize access to the superblock. - */ reread: error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size), &bp, buf_ops); @@ -247,6 +244,10 @@ reread: /* no need to be quiet anymore, so reset the buf ops */ bp->b_ops = &xfs_sb_buf_ops; + /* + * Keep a pointer of the sb buffer around instead of caching it in the + * buffer cache because we access it frequently. + */ mp->m_sb_bp = bp; xfs_buf_unlock(bp); return 0; @@ -678,68 +679,46 @@ static inline unsigned int max_pow_of_two_factor(const unsigned int nr) } /* - * If the data device advertises atomic write support, limit the size of data - * device atomic writes to the greatest power-of-two factor of the AG size so - * that every atomic write unit aligns with the start of every AG. This is - * required so that the per-AG allocations for an atomic write will always be + * If the underlying device advertises atomic write support, limit the size of + * atomic writes to the greatest power-of-two factor of the group size so + * that every atomic write unit aligns with the start of every group. This is + * required so that the allocations for an atomic write will always be * aligned compatibly with the alignment requirements of the storage. * - * If the data device doesn't advertise atomic writes, then there are no - * alignment restrictions and the largest out-of-place write we can do - * ourselves is the number of blocks that user files can allocate from any AG. - */ -static inline xfs_extlen_t xfs_calc_perag_awu_max(struct xfs_mount *mp) -{ - if (mp->m_ddev_targp->bt_bdev_awu_min > 0) - return max_pow_of_two_factor(mp->m_sb.sb_agblocks); - return rounddown_pow_of_two(mp->m_ag_max_usable); -} - -/* - * Reflink on the realtime device requires rtgroups, and atomic writes require - * reflink. - * - * If the realtime device advertises atomic write support, limit the size of - * data device atomic writes to the greatest power-of-two factor of the rtgroup - * size so that every atomic write unit aligns with the start of every rtgroup. - * This is required so that the per-rtgroup allocations for an atomic write - * will always be aligned compatibly with the alignment requirements of the - * storage. - * - * If the rt device doesn't advertise atomic writes, then there are no - * alignment restrictions and the largest out-of-place write we can do - * ourselves is the number of blocks that user files can allocate from any - * rtgroup. + * If the device doesn't advertise atomic writes, then there are no alignment + * restrictions and the largest out-of-place write we can do ourselves is the + * number of blocks that user files can allocate from any group. */ -static inline xfs_extlen_t xfs_calc_rtgroup_awu_max(struct xfs_mount *mp) +static xfs_extlen_t +xfs_calc_group_awu_max( + struct xfs_mount *mp, + enum xfs_group_type type) { - struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG]; + struct xfs_groups *g = &mp->m_groups[type]; + struct xfs_buftarg *btp = xfs_group_type_buftarg(mp, type); - if (rgs->blocks == 0) + if (g->blocks == 0) return 0; - if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev_awu_min > 0) - return max_pow_of_two_factor(rgs->blocks); - return rounddown_pow_of_two(rgs->blocks); + if (btp && btp->bt_awu_min > 0) + return max_pow_of_two_factor(g->blocks); + return rounddown_pow_of_two(g->blocks); } /* Compute the maximum atomic write unit size for each section. */ static inline void xfs_calc_atomic_write_unit_max( - struct xfs_mount *mp) + struct xfs_mount *mp, + enum xfs_group_type type) { - struct xfs_groups *ags = &mp->m_groups[XG_TYPE_AG]; - struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG]; + struct xfs_groups *g = &mp->m_groups[type]; const xfs_extlen_t max_write = xfs_calc_atomic_write_max(mp); const xfs_extlen_t max_ioend = xfs_reflink_max_atomic_cow(mp); - const xfs_extlen_t max_agsize = xfs_calc_perag_awu_max(mp); - const xfs_extlen_t max_rgsize = xfs_calc_rtgroup_awu_max(mp); - - ags->awu_max = min3(max_write, max_ioend, max_agsize); - rgs->awu_max = min3(max_write, max_ioend, max_rgsize); + const xfs_extlen_t max_gsize = xfs_calc_group_awu_max(mp, type); - trace_xfs_calc_atomic_write_unit_max(mp, max_write, max_ioend, - max_agsize, max_rgsize); + g->awu_max = min3(max_write, max_ioend, max_gsize); + trace_xfs_calc_atomic_write_unit_max(mp, type, max_write, max_ioend, + max_gsize, g->awu_max); } /* @@ -757,7 +736,8 @@ xfs_set_max_atomic_write_opt( max(mp->m_groups[XG_TYPE_AG].blocks, mp->m_groups[XG_TYPE_RTG].blocks); const xfs_extlen_t max_group_write = - max(xfs_calc_perag_awu_max(mp), xfs_calc_rtgroup_awu_max(mp)); + max(xfs_calc_group_awu_max(mp, XG_TYPE_AG), + xfs_calc_group_awu_max(mp, XG_TYPE_RTG)); int error; if (new_max_bytes == 0) @@ -813,7 +793,8 @@ set_limit: return error; } - xfs_calc_atomic_write_unit_max(mp); + xfs_calc_atomic_write_unit_max(mp, XG_TYPE_AG); + xfs_calc_atomic_write_unit_max(mp, XG_TYPE_RTG); mp->m_awu_max_bytes = new_max_bytes; return 0; } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index d85084f9f317..97de44c32272 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -802,4 +802,21 @@ static inline void xfs_mod_sb_delalloc(struct xfs_mount *mp, int64_t delta) int xfs_set_max_atomic_write_opt(struct xfs_mount *mp, unsigned long long new_max_bytes); +static inline struct xfs_buftarg * +xfs_group_type_buftarg( + struct xfs_mount *mp, + enum xfs_group_type type) +{ + switch (type) { + case XG_TYPE_AG: + return mp->m_ddev_targp; + case XG_TYPE_RTG: + return mp->m_rtdev_targp; + default: + ASSERT(0); + break; + } + return NULL; +} + #endif /* __XFS_MOUNT_H__ */ diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 3545dc1d953c..42e9c72b85c0 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -253,8 +253,7 @@ xfs_dax_notify_dev_failure( return -EOPNOTSUPP; } - error = xfs_dax_translate_range(type == XG_TYPE_RTG ? - mp->m_rtdev_targp : mp->m_ddev_targp, + error = xfs_dax_translate_range(xfs_group_type_buftarg(mp, type), offset, len, &daddr, &bblen); if (error) return error; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index ba45d801df1c..78be223b13b2 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -171,36 +171,33 @@ DEFINE_ATTR_LIST_EVENT(xfs_attr_leaf_list); DEFINE_ATTR_LIST_EVENT(xfs_attr_node_list); TRACE_EVENT(xfs_calc_atomic_write_unit_max, - TP_PROTO(struct xfs_mount *mp, unsigned int max_write, - unsigned int max_ioend, unsigned int max_agsize, - unsigned int max_rgsize), - TP_ARGS(mp, max_write, max_ioend, max_agsize, max_rgsize), + TP_PROTO(struct xfs_mount *mp, enum xfs_group_type type, + unsigned int max_write, unsigned int max_ioend, + unsigned int max_gsize, unsigned int awu_max), + TP_ARGS(mp, type, max_write, max_ioend, max_gsize, awu_max), TP_STRUCT__entry( __field(dev_t, dev) + __field(enum xfs_group_type, type) __field(unsigned int, max_write) __field(unsigned int, max_ioend) - __field(unsigned int, max_agsize) - __field(unsigned int, max_rgsize) - __field(unsigned int, data_awu_max) - __field(unsigned int, rt_awu_max) + __field(unsigned int, max_gsize) + __field(unsigned int, awu_max) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; + __entry->type = type; __entry->max_write = max_write; __entry->max_ioend = max_ioend; - __entry->max_agsize = max_agsize; - __entry->max_rgsize = max_rgsize; - __entry->data_awu_max = mp->m_groups[XG_TYPE_AG].awu_max; - __entry->rt_awu_max = mp->m_groups[XG_TYPE_RTG].awu_max; + __entry->max_gsize = max_gsize; + __entry->awu_max = awu_max; ), - TP_printk("dev %d:%d max_write %u max_ioend %u max_agsize %u max_rgsize %u data_awu_max %u rt_awu_max %u", + TP_printk("dev %d:%d %s max_write %u max_ioend %u max_gsize %u awu_max %u", MAJOR(__entry->dev), MINOR(__entry->dev), + __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->max_write, __entry->max_ioend, - __entry->max_agsize, - __entry->max_rgsize, - __entry->data_awu_max, - __entry->rt_awu_max) + __entry->max_gsize, + __entry->awu_max) ); TRACE_EVENT(xfs_calc_max_atomic_write_fsblocks, diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 0f641a9091ec..ac5cecec9aa1 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -243,7 +243,7 @@ __xfs_xattr_put_listent( offset = context->buffer + context->count; memcpy(offset, prefix, prefix_len); offset += prefix_len; - strncpy(offset, (char *)name, namelen); /* real name */ + memcpy(offset, (char *)name, namelen); /* real name */ offset += namelen; *offset = '\0'; diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h index 9689a7c5dd36..513837632b7d 100644 --- a/include/drm/drm_buddy.h +++ b/include/drm/drm_buddy.h @@ -160,6 +160,8 @@ int drm_buddy_block_trim(struct drm_buddy *mm, u64 new_size, struct list_head *blocks); +void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear); + void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block); void drm_buddy_free_list(struct drm_buddy *mm, diff --git a/include/linux/filter.h b/include/linux/filter.h index f5cf4d35d83e..4e82332afe03 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1073,10 +1073,20 @@ bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } -int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap, + enum skb_drop_reason *reason); + static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { - return sk_filter_trim_cap(sk, skb, 1); + enum skb_drop_reason ignore_reason; + + return sk_filter_trim_cap(sk, skb, 1, &ignore_reason); +} + +static inline int sk_filter_reason(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason) +{ + return sk_filter_trim_cap(sk, skb, 1, reason); } struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index 55cfebc658e6..8a2f652a05ff 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -119,6 +119,7 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw, struct icc_node *icc_node_create_dyn(void); struct icc_node *icc_node_create(int id); void icc_node_destroy(int id); +int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name); int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node); int icc_link_create(struct icc_node *node, const int dst_id); void icc_node_add(struct icc_node *node, struct icc_provider *provider); @@ -152,6 +153,12 @@ static inline void icc_node_destroy(int id) { } +static inline int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, + const char *name) +{ + return -EOPNOTSUPP; +} + static inline int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node) { return -EOPNOTSUPP; diff --git a/include/linux/ism.h b/include/linux/ism.h index 5428edd90982..8358b4cd7ba6 100644 --- a/include/linux/ism.h +++ b/include/linux/ism.h @@ -28,6 +28,7 @@ struct ism_dmb { struct ism_dev { spinlock_t lock; /* protects the ism device */ + spinlock_t cmd_lock; /* serializes cmds */ struct list_head list; struct pci_dev *pdev; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 639dd0b56655..ed4130e49c27 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -420,7 +420,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits { /* Table 2170 - Flow Table Fields Supported 2 Format */ struct mlx5_ifc_flow_table_fields_supported_2_bits { - u8 reserved_at_0[0x2]; + u8 inner_l4_type_ext[0x1]; + u8 outer_l4_type_ext[0x1]; u8 inner_l4_type[0x1]; u8 outer_l4_type[0x1]; u8 reserved_at_4[0xa]; @@ -429,7 +430,11 @@ struct mlx5_ifc_flow_table_fields_supported_2_bits { u8 tunnel_header_0_1[0x1]; u8 reserved_at_11[0xf]; - u8 reserved_at_20[0x60]; + u8 reserved_at_20[0xf]; + u8 ipsec_next_header[0x1]; + u8 reserved_at_30[0x10]; + + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_flow_table_prop_layout_bits { @@ -552,6 +557,13 @@ enum { MLX5_PACKET_L4_TYPE_UDP, }; +enum { + MLX5_PACKET_L4_TYPE_EXT_NONE, + MLX5_PACKET_L4_TYPE_EXT_TCP, + MLX5_PACKET_L4_TYPE_EXT_UDP, + MLX5_PACKET_L4_TYPE_EXT_ICMP, +}; + struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; @@ -578,10 +590,10 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_dport[0x10]; u8 l4_type[0x2]; - u8 reserved_at_c2[0xe]; + u8 l4_type_ext[0x4]; + u8 reserved_at_c6[0xa]; u8 ipv4_ihl[0x4]; - u8 reserved_at_c4[0x4]; - + u8 reserved_at_d4[0x4]; u8 ttl_hoplimit[0x8]; u8 udp_sport[0x10]; @@ -689,10 +701,9 @@ struct mlx5_ifc_fte_match_set_misc2_bits { u8 metadata_reg_a[0x20]; u8 reserved_at_1a0[0x8]; - u8 macsec_syndrome[0x8]; u8 ipsec_syndrome[0x8]; - u8 reserved_at_1b8[0x8]; + u8 ipsec_next_header[0x8]; u8 reserved_at_1c0[0x40]; }; @@ -9983,6 +9994,10 @@ struct mlx5_ifc_pude_reg_bits { u8 reserved_at_20[0x60]; }; +enum { + MLX5_PTYS_CONNECTOR_TYPE_PORT_DA = 0x7, +}; + struct mlx5_ifc_ptys_reg_bits { u8 reserved_at_0[0x1]; u8 an_disable_admin[0x1]; @@ -10019,7 +10034,8 @@ struct mlx5_ifc_ptys_reg_bits { u8 ib_link_width_oper[0x10]; u8 ib_proto_oper[0x10]; - u8 reserved_at_160[0x1c]; + u8 reserved_at_160[0x8]; + u8 lane_rate_oper[0x14]; u8 connector_type[0x4]; u8 eth_proto_lp_advertise[0x20]; @@ -10463,10 +10479,19 @@ struct mlx5_ifc_pifr_reg_bits { u8 port_filter_update_en[8][0x20]; }; +enum { + MLX5_BUF_OWNERSHIP_UNKNOWN = 0x0, + MLX5_BUF_OWNERSHIP_FW_OWNED = 0x1, + MLX5_BUF_OWNERSHIP_SW_OWNED = 0x2, +}; + struct mlx5_ifc_pfcc_reg_bits { - u8 reserved_at_0[0x8]; + u8 reserved_at_0[0x4]; + u8 buf_ownership[0x2]; + u8 reserved_at_6[0x2]; u8 local_port[0x8]; - u8 reserved_at_10[0xb]; + u8 reserved_at_10[0xa]; + u8 cable_length_mask[0x1]; u8 ppan_mask_n[0x1]; u8 minor_stall_mask[0x1]; u8 critical_stall_mask[0x1]; @@ -10495,7 +10520,10 @@ struct mlx5_ifc_pfcc_reg_bits { u8 device_stall_minor_watermark[0x10]; u8 device_stall_critical_watermark[0x10]; - u8 reserved_at_a0[0x60]; + u8 reserved_at_a0[0x18]; + u8 cable_length[0x8]; + + u8 reserved_at_c0[0x40]; }; struct mlx5_ifc_pelc_reg_bits { @@ -10596,11 +10624,15 @@ struct mlx5_ifc_mtutc_reg_bits { struct mlx5_ifc_pcam_enhanced_features_bits { u8 reserved_at_0[0x10]; u8 ppcnt_recovery_counters[0x1]; - u8 reserved_at_11[0xc]; + u8 reserved_at_11[0x7]; + u8 cable_length[0x1]; + u8 reserved_at_19[0x4]; u8 fec_200G_per_lane_in_pplm[0x1]; u8 reserved_at_1e[0x2a]; u8 fec_100G_per_lane_in_pplm[0x1]; - u8 reserved_at_49[0x1f]; + u8 reserved_at_49[0xa]; + u8 buffer_ownership[0x1]; + u8 resereved_at_54[0x14]; u8 fec_50G_per_lane_in_pplm[0x1]; u8 reserved_at_69[0x4]; u8 rx_icrc_encapsulated_counter[0x1]; diff --git a/include/linux/mm.h b/include/linux/mm.h index fa538feaa8d9..ae50c1641bed 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4178,12 +4178,12 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status); #define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL) #ifdef CONFIG_PAGE_POOL -static inline bool page_pool_page_is_pp(struct page *page) +static inline bool page_pool_page_is_pp(const struct page *page) { return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE; } #else -static inline bool page_pool_page_is_pp(struct page *page) +static inline bool page_pool_page_is_pp(const struct page *page) { return false; } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e49d8c98d284..5aee8d3895f4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -589,6 +589,7 @@ static inline bool napi_complete(struct napi_struct *n) return napi_complete_done(n, 0); } +int netif_set_threaded(struct net_device *dev, bool threaded); int dev_set_threaded(struct net_device *dev, bool threaded); void napi_disable(struct napi_struct *n); @@ -3342,7 +3343,7 @@ int netif_open(struct net_device *dev, struct netlink_ext_ack *extack); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void netif_close(struct net_device *dev); void dev_close(struct net_device *dev); -void dev_close_many(struct list_head *head, bool unlink); +void netif_close_many(struct list_head *head, bool unlink); void netif_disable_lro(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); @@ -4196,7 +4197,7 @@ int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); -unsigned int dev_get_flags(const struct net_device *); +unsigned int netif_get_flags(const struct net_device *dev); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int netif_change_flags(struct net_device *dev, unsigned int flags, @@ -4211,20 +4212,20 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, struct netlink_ext_ack *extack); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat); -int __dev_set_mtu(struct net_device *, int); +int __netif_set_mtu(struct net_device *dev, int new_mtu); int netif_set_mtu(struct net_device *dev, int new_mtu); int dev_set_mtu(struct net_device *, int); -int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, - struct netlink_ext_ack *extack); +int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr, + struct netlink_ext_ack *extack); int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack); -int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); -int dev_get_port_parent_id(struct net_device *dev, - struct netdev_phys_item_id *ppid, bool recurse); +int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); +int netif_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h index 437769e061b7..13add0c2c407 100644 --- a/include/linux/phy/phy.h +++ b/include/linux/phy/phy.h @@ -154,6 +154,7 @@ struct phy_attrs { * @id: id of the phy device * @ops: function pointers for performing phy operations * @mutex: mutex to protect phy_ops + * @lockdep_key: lockdep information for this mutex * @init_count: used to protect when the PHY is used by multiple consumers * @power_count: used to protect when the PHY is used by multiple consumers * @attrs: used to specify PHY specific attributes @@ -165,6 +166,7 @@ struct phy { int id; const struct phy_ops *ops; struct mutex mutex; + struct lock_class_key lockdep_key; int init_count; int power_count; struct phy_attrs attrs; diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 7803edaa8ff8..0cca01b5607b 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -888,15 +888,23 @@ static inline int power_supply_is_system_supplied(void) { return -ENOSYS; } extern int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp, union power_supply_propval *val); +int power_supply_get_property_direct(struct power_supply *psy, enum power_supply_property psp, + union power_supply_propval *val); #if IS_ENABLED(CONFIG_POWER_SUPPLY) extern int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val); +int power_supply_set_property_direct(struct power_supply *psy, enum power_supply_property psp, + const union power_supply_propval *val); #else static inline int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp, const union power_supply_propval *val) { return 0; } +static inline int power_supply_set_property_direct(struct power_supply *psy, + enum power_supply_property psp, + const union power_supply_propval *val) +{ return 0; } #endif extern void power_supply_external_power_changed(struct power_supply *psy); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1a5737b3753d..57e478bfaef2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -621,6 +621,7 @@ void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); int tcp_sock_set_user_timeout(struct sock *sk, int val); +int tcp_sock_set_maxseg(struct sock *sk, int val); static inline bool dst_tcp_usec_ts(const struct dst_entry *dst) { diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 2d207cb4837d..4ac082a63173 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -119,6 +119,7 @@ struct cdc_ncm_ctx { u32 timer_interval; u32 max_ndp_size; u8 is_ndp16; + u8 filtering_supported; union { struct usb_cdc_ncm_ndp16 *delayed_ndp16; struct usb_cdc_ncm_ndp32 *delayed_ndp32; diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h index 229bb1826f2a..d8ff24a33459 100644 --- a/include/net/dropreason-core.h +++ b/include/net/dropreason-core.h @@ -125,6 +125,8 @@ FN(CAN_RX_INVALID_FRAME) \ FN(CANFD_RX_INVALID_FRAME) \ FN(CANXL_RX_INVALID_FRAME) \ + FN(PFMEMALLOC) \ + FN(DUALPI2_STEP_DROP) \ FNe(MAX) /** @@ -599,6 +601,16 @@ enum skb_drop_reason { */ SKB_DROP_REASON_CANXL_RX_INVALID_FRAME, /** + * @SKB_DROP_REASON_PFMEMALLOC: packet allocated from memory reserve + * reached a path or socket not eligible for use of memory reserves + */ + SKB_DROP_REASON_PFMEMALLOC, + /** + * @SKB_DROP_REASON_DUALPI2_STEP_DROP: dropped by the step drop + * threshold of DualPI2 qdisc. + */ + SKB_DROP_REASON_DUALPI2_STEP_DROP, + /** * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which * shouldn't be used as a real 'reason' - only for tracing code gen */ diff --git a/include/net/libeth/xdp.h b/include/net/libeth/xdp.h index 6ce6aec6884c..f4880b50e804 100644 --- a/include/net/libeth/xdp.h +++ b/include/net/libeth/xdp.h @@ -1292,7 +1292,7 @@ static inline void libeth_xdp_prepare_buff(struct libeth_xdp_buff *xdp, xdp_init_buff(&xdp->base, fqe->truesize, xdp->base.rxq); #endif xdp_prepare_buff(&xdp->base, page_address(page) + fqe->offset, - page->pp->p.offset, len, true); + pp_page_to_nmdesc(page)->pp->p.offset, len, true); } /** diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 7e865b14749d..4a30bd458c5a 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -176,10 +176,14 @@ struct neigh_ops { }; struct pneigh_entry { - struct pneigh_entry *next; + struct pneigh_entry __rcu *next; possible_net_t net; struct net_device *dev; netdevice_tracker dev_tracker; + union { + struct list_head free_node; + struct rcu_head rcu; + }; u32 flags; u8 protocol; bool permanent; @@ -236,7 +240,8 @@ struct neigh_table { unsigned long last_rand; struct neigh_statistics __percpu *stats; struct neigh_hash_table __rcu *nht; - struct pneigh_entry **phash_buckets; + struct mutex phash_lock; + struct pneigh_entry __rcu **phash_buckets; }; static inline int neigh_parms_family(struct neigh_parms *p) @@ -376,10 +381,10 @@ unsigned long neigh_rand_reach_time(unsigned long base); void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb); struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, - const void *key, struct net_device *dev, - int creat); -struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net, - const void *key, struct net_device *dev); + const void *key, struct net_device *dev); +int pneigh_create(struct neigh_table *tbl, struct net *net, const void *key, + struct net_device *dev, u32 flags, u8 protocol, + bool permanent); int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); diff --git a/include/net/netmem.h b/include/net/netmem.h index de1d95f04076..f7dacc9e75fd 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -12,6 +12,50 @@ #include <linux/mm.h> #include <net/net_debug.h> +/* These fields in struct page are used by the page_pool and net stack: + * + * struct { + * unsigned long pp_magic; + * struct page_pool *pp; + * unsigned long _pp_mapping_pad; + * unsigned long dma_addr; + * atomic_long_t pp_ref_count; + * }; + * + * We mirror the page_pool fields here so the page_pool can access these + * fields without worrying whether the underlying fields belong to a + * page or netmem_desc. + * + * CAUTION: Do not update the fields in netmem_desc without also + * updating the anonymous aliasing union in struct net_iov. + */ +struct netmem_desc { + unsigned long _flags; + unsigned long pp_magic; + struct page_pool *pp; + unsigned long _pp_mapping_pad; + unsigned long dma_addr; + atomic_long_t pp_ref_count; +}; + +#define NETMEM_DESC_ASSERT_OFFSET(pg, desc) \ + static_assert(offsetof(struct page, pg) == \ + offsetof(struct netmem_desc, desc)) +NETMEM_DESC_ASSERT_OFFSET(flags, _flags); +NETMEM_DESC_ASSERT_OFFSET(pp_magic, pp_magic); +NETMEM_DESC_ASSERT_OFFSET(pp, pp); +NETMEM_DESC_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad); +NETMEM_DESC_ASSERT_OFFSET(dma_addr, dma_addr); +NETMEM_DESC_ASSERT_OFFSET(pp_ref_count, pp_ref_count); +#undef NETMEM_DESC_ASSERT_OFFSET + +/* + * Since struct netmem_desc uses the space in struct page, the size + * should be checked, until struct netmem_desc has its own instance from + * slab, to avoid conflicting with other members within struct page. + */ +static_assert(sizeof(struct netmem_desc) <= offsetof(struct page, _refcount)); + /* net_iov */ DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); @@ -30,13 +74,48 @@ enum net_iov_type { NET_IOV_MAX = ULONG_MAX }; +/* A memory descriptor representing abstract networking I/O vectors, + * generally for non-pages memory that doesn't have its corresponding + * struct page and needs to be explicitly allocated through slab. + * + * net_iovs are allocated and used by networking code, and the size of + * the chunk is PAGE_SIZE. + * + * This memory can be any form of non-struct paged memory. Examples + * include imported dmabuf memory and imported io_uring memory. See + * net_iov_type for all the supported types. + * + * @pp_magic: pp field, similar to the one in struct page/struct + * netmem_desc. + * @pp: the pp this net_iov belongs to, if any. + * @dma_addr: the dma addrs of the net_iov. Needed for the network + * card to send/receive this net_iov. + * @pp_ref_count: the pp ref count of this net_iov, exactly the same + * usage as struct page/struct netmem_desc. + * @owner: the net_iov_area this net_iov belongs to, if any. + * @type: the type of the memory. Different types of net_iovs are + * supported. + */ struct net_iov { - enum net_iov_type type; - unsigned long pp_magic; - struct page_pool *pp; + union { + struct netmem_desc desc; + + /* XXX: The following part should be removed once all + * the references to them are converted so as to be + * accessed via netmem_desc e.g. niov->desc.pp instead + * of niov->pp. + */ + struct { + unsigned long _flags; + unsigned long pp_magic; + struct page_pool *pp; + unsigned long _pp_mapping_pad; + unsigned long dma_addr; + atomic_long_t pp_ref_count; + }; + }; struct net_iov_area *owner; - unsigned long dma_addr; - atomic_long_t pp_ref_count; + enum net_iov_type type; }; struct net_iov_area { @@ -48,27 +127,22 @@ struct net_iov_area { unsigned long base_virtual; }; -/* These fields in struct page are used by the page_pool and net stack: - * - * struct { - * unsigned long pp_magic; - * struct page_pool *pp; - * unsigned long _pp_mapping_pad; - * unsigned long dma_addr; - * atomic_long_t pp_ref_count; - * }; - * - * We mirror the page_pool fields here so the page_pool can access these fields - * without worrying whether the underlying fields belong to a page or net_iov. +/* net_iov is union'ed with struct netmem_desc mirroring struct page, so + * the page_pool can access these fields without worrying whether the + * underlying fields are accessed via netmem_desc or directly via + * net_iov, until all the references to them are converted so as to be + * accessed via netmem_desc e.g. niov->desc.pp instead of niov->pp. * - * The non-net stack fields of struct page are private to the mm stack and must - * never be mirrored to net_iov. + * The non-net stack fields of struct page are private to the mm stack + * and must never be mirrored to net_iov. */ -#define NET_IOV_ASSERT_OFFSET(pg, iov) \ - static_assert(offsetof(struct page, pg) == \ +#define NET_IOV_ASSERT_OFFSET(desc, iov) \ + static_assert(offsetof(struct netmem_desc, desc) == \ offsetof(struct net_iov, iov)) +NET_IOV_ASSERT_OFFSET(_flags, _flags); NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic); NET_IOV_ASSERT_OFFSET(pp, pp); +NET_IOV_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad); NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr); NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count); #undef NET_IOV_ASSERT_OFFSET @@ -173,6 +247,24 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem) return page_to_pfn(netmem_to_page(netmem)); } +/** + * __netmem_to_nmdesc - unsafely get pointer to the &netmem_desc backing + * @netmem + * @netmem: netmem reference to convert + * + * Unsafe version that can be used only when @netmem is always backed by + * system memory, performs faster and generates smaller object code (no + * check for the LSB, no WARN). When @netmem points to IOV, provokes + * undefined behaviour. + * + * Return: pointer to the &netmem_desc (garbage if @netmem is not backed + * by system memory). + */ +static inline struct netmem_desc *__netmem_to_nmdesc(netmem_ref netmem) +{ + return (__force struct netmem_desc *)netmem; +} + /* __netmem_clear_lsb - convert netmem_ref to struct net_iov * for access to * common fields. * @netmem: netmem reference to extract as net_iov. @@ -193,6 +285,23 @@ static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); } +/* XXX: How to extract netmem_desc from page must be changed, once + * netmem_desc no longer overlays on page and will be allocated through + * slab. + */ +#define __pp_page_to_nmdesc(p) (_Generic((p), \ + const struct page * : (const struct netmem_desc *)(p), \ + struct page * : (struct netmem_desc *)(p))) + +/* CAUTION: Check if the page is a pp page before calling this helper or + * know it's a pp page. + */ +#define pp_page_to_nmdesc(p) \ +({ \ + DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p)); \ + __pp_page_to_nmdesc(p); \ +}) + /** * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem * @netmem: netmem reference to get the pointer from @@ -206,7 +315,7 @@ static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) */ static inline struct page_pool *__netmem_get_pp(netmem_ref netmem) { - return __netmem_to_page(netmem)->pp; + return __netmem_to_nmdesc(netmem)->pp; } static inline struct page_pool *netmem_get_pp(netmem_ref netmem) diff --git a/include/net/tcp.h b/include/net/tcp.h index bc08de49805c..b3815d104340 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1559,7 +1559,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); -int tcp_filter(struct sock *sk, struct sk_buff *skb); +int tcp_filter(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); int tcp_abort(struct sock *sk, int err); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index a21e276dbe44..f3014e4f54fc 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -441,7 +441,6 @@ int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_flush_gc(void); -void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { struct module *owner; @@ -474,7 +473,7 @@ struct xfrm_type_offload { int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); -void xfrm_set_type_offload(struct xfrm_state *x); +void xfrm_set_type_offload(struct xfrm_state *x, bool try_load); static inline void xfrm_unset_type_offload(struct xfrm_state *x) { if (!x->type_offload) @@ -916,7 +915,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *, bool); +void __xfrm_state_destroy(struct xfrm_state *); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -926,13 +925,7 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, false); -} - -static inline void xfrm_state_put_sync(struct xfrm_state *x) -{ - if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x, true); + __xfrm_state_destroy(x); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1770,7 +1763,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 73e96ccbe830..64a382fbc31a 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -55,6 +55,7 @@ EM(netfs_rreq_trace_copy, "COPY ") \ EM(netfs_rreq_trace_dirty, "DIRTY ") \ EM(netfs_rreq_trace_done, "DONE ") \ + EM(netfs_rreq_trace_end_copy_to_cache, "END-C2C") \ EM(netfs_rreq_trace_free, "FREE ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ @@ -559,6 +560,35 @@ TRACE_EVENT(netfs_write, __entry->start, __entry->start + __entry->len - 1) ); +TRACE_EVENT(netfs_copy2cache, + TP_PROTO(const struct netfs_io_request *rreq, + const struct netfs_io_request *creq), + + TP_ARGS(rreq, creq), + + TP_STRUCT__entry( + __field(unsigned int, rreq) + __field(unsigned int, creq) + __field(unsigned int, cookie) + __field(unsigned int, ino) + ), + + TP_fast_assign( + struct netfs_inode *__ctx = netfs_inode(rreq->inode); + struct fscache_cookie *__cookie = netfs_i_cookie(__ctx); + __entry->rreq = rreq->debug_id; + __entry->creq = creq->debug_id; + __entry->cookie = __cookie ? __cookie->debug_id : 0; + __entry->ino = rreq->inode->i_ino; + ), + + TP_printk("R=%08x CR=%08x c=%08x i=%x ", + __entry->rreq, + __entry->creq, + __entry->cookie, + __entry->ino) + ); + TRACE_EVENT(netfs_collect, TP_PROTO(const struct netfs_io_request *wreq), diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 54e60c6009e3..9d2c36c6a0ed 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -13,17 +13,11 @@ #include <linux/sock_diag.h> #include <net/rstreason.h> -/* - * tcp event with arguments sk and skb - * - * Note: this class requires a valid sk pointer; while skb pointer could - * be NULL. - */ -DECLARE_EVENT_CLASS(tcp_event_sk_skb, +TRACE_EVENT(tcp_retransmit_skb, - TP_PROTO(const struct sock *sk, const struct sk_buff *skb), + TP_PROTO(const struct sock *sk, const struct sk_buff *skb, int err), - TP_ARGS(sk, skb), + TP_ARGS(sk, skb, err), TP_STRUCT__entry( __field(const void *, skbaddr) @@ -36,6 +30,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) + __field(int, err) ), TP_fast_assign( @@ -58,21 +53,17 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); + + __entry->err = err; ), - TP_printk("skbaddr=%p skaddr=%p family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s", + TP_printk("skbaddr=%p skaddr=%p family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c state=%s err=%d", __entry->skbaddr, __entry->skaddr, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, - show_tcp_state_name(__entry->state)) -); - -DEFINE_EVENT(tcp_event_sk_skb, tcp_retransmit_skb, - - TP_PROTO(const struct sock *sk, const struct sk_buff *skb), - - TP_ARGS(sk, skb) + show_tcp_state_name(__entry->state), + __entry->err) ); #undef FN diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index e72bcc239afd..9fcb25a0f447 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -635,8 +635,6 @@ enum devlink_attr { DEVLINK_ATTR_REGION_DIRECT, /* flag */ DEVLINK_ATTR_RATE_TC_BWS, /* nested */ - DEVLINK_ATTR_RATE_TC_INDEX, /* u8 */ - DEVLINK_ATTR_RATE_TC_BW, /* u32 */ /* Add new attributes above here, update the spec in * Documentation/netlink/specs/devlink.yaml and re-generate @@ -647,6 +645,15 @@ enum devlink_attr { DEVLINK_ATTR_MAX = __DEVLINK_ATTR_MAX - 1 }; +enum devlink_rate_tc_attr { + DEVLINK_RATE_TC_ATTR_UNSPEC, + DEVLINK_RATE_TC_ATTR_INDEX, /* u8 */ + DEVLINK_RATE_TC_ATTR_BW, /* u32 */ + + __DEVLINK_RATE_TC_ATTR_MAX, + DEVLINK_RATE_TC_ATTR_MAX = __DEVLINK_RATE_TC_ATTR_MAX - 1 +}; + /* Mapping between internal resource described by the field and system * structure */ diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 96027e26ffba..e3b8813465d7 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -840,6 +840,9 @@ enum { ETHTOOL_MSG_PHY_GET, ETHTOOL_MSG_TSCONFIG_GET, ETHTOOL_MSG_TSCONFIG_SET, + ETHTOOL_MSG_RSS_SET, + ETHTOOL_MSG_RSS_CREATE_ACT, + ETHTOOL_MSG_RSS_DELETE_ACT, __ETHTOOL_MSG_USER_CNT, ETHTOOL_MSG_USER_MAX = (__ETHTOOL_MSG_USER_CNT - 1) @@ -897,6 +900,9 @@ enum { ETHTOOL_MSG_TSCONFIG_SET_REPLY, ETHTOOL_MSG_PSE_NTF, ETHTOOL_MSG_RSS_NTF, + ETHTOOL_MSG_RSS_CREATE_ACT_REPLY, + ETHTOOL_MSG_RSS_CREATE_NTF, + ETHTOOL_MSG_RSS_DELETE_NTF, __ETHTOOL_MSG_KERNEL_CNT, ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1) diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 3e41349f3fa2..c2da76e78bad 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1211,4 +1211,72 @@ enum { #define TCA_ETS_MAX (__TCA_ETS_MAX - 1) +/* DUALPI2 */ +enum tc_dualpi2_drop_overload { + TC_DUALPI2_DROP_OVERLOAD_OVERFLOW = 0, + TC_DUALPI2_DROP_OVERLOAD_DROP = 1, + __TCA_DUALPI2_DROP_OVERLOAD_MAX, +}; +#define TCA_DUALPI2_DROP_OVERLOAD_MAX (__TCA_DUALPI2_DROP_OVERLOAD_MAX - 1) + +enum tc_dualpi2_drop_early { + TC_DUALPI2_DROP_EARLY_DROP_DEQUEUE = 0, + TC_DUALPI2_DROP_EARLY_DROP_ENQUEUE = 1, + __TCA_DUALPI2_DROP_EARLY_MAX, +}; +#define TCA_DUALPI2_DROP_EARLY_MAX (__TCA_DUALPI2_DROP_EARLY_MAX - 1) + +enum tc_dualpi2_ecn_mask { + TC_DUALPI2_ECN_MASK_L4S_ECT = 1, + TC_DUALPI2_ECN_MASK_CLA_ECT = 2, + TC_DUALPI2_ECN_MASK_ANY_ECT = 3, + __TCA_DUALPI2_ECN_MASK_MAX, +}; +#define TCA_DUALPI2_ECN_MASK_MAX (__TCA_DUALPI2_ECN_MASK_MAX - 1) + +enum tc_dualpi2_split_gso { + TC_DUALPI2_SPLIT_GSO_NO_SPLIT_GSO = 0, + TC_DUALPI2_SPLIT_GSO_SPLIT_GSO = 1, + __TCA_DUALPI2_SPLIT_GSO_MAX, +}; +#define TCA_DUALPI2_SPLIT_GSO_MAX (__TCA_DUALPI2_SPLIT_GSO_MAX - 1) + +enum { + TCA_DUALPI2_UNSPEC, + TCA_DUALPI2_LIMIT, /* Packets */ + TCA_DUALPI2_MEMORY_LIMIT, /* Bytes */ + TCA_DUALPI2_TARGET, /* us */ + TCA_DUALPI2_TUPDATE, /* us */ + TCA_DUALPI2_ALPHA, /* Hz scaled up by 256 */ + TCA_DUALPI2_BETA, /* Hz scaled up by 256 */ + TCA_DUALPI2_STEP_THRESH_PKTS, /* Step threshold in packets */ + TCA_DUALPI2_STEP_THRESH_US, /* Step threshold in microseconds */ + TCA_DUALPI2_MIN_QLEN_STEP, /* Minimum qlen to apply STEP_THRESH */ + TCA_DUALPI2_COUPLING, /* Coupling factor between queues */ + TCA_DUALPI2_DROP_OVERLOAD, /* Whether to drop on overload */ + TCA_DUALPI2_DROP_EARLY, /* Whether to drop on enqueue */ + TCA_DUALPI2_C_PROTECTION, /* Percentage */ + TCA_DUALPI2_ECN_MASK, /* L4S queue classification mask */ + TCA_DUALPI2_SPLIT_GSO, /* Split GSO packets at enqueue */ + TCA_DUALPI2_PAD, + __TCA_DUALPI2_MAX +}; + +#define TCA_DUALPI2_MAX (__TCA_DUALPI2_MAX - 1) + +struct tc_dualpi2_xstats { + __u32 prob; /* current probability */ + __u32 delay_c; /* current delay in C queue */ + __u32 delay_l; /* current delay in L queue */ + __u32 packets_in_c; /* number of packets enqueued in C queue */ + __u32 packets_in_l; /* number of packets enqueued in L queue */ + __u32 maxq; /* maximum queue size */ + __u32 ecn_mark; /* packets marked with ecn*/ + __u32 step_marks; /* ECN marks due to the step AQM */ + __s32 credit; /* current c_protection credit */ + __u32 memory_used; /* Memory used by both queues */ + __u32 max_memory_used; /* Maximum used memory */ + __u32 memory_limit; /* Memory limit of both queues */ +}; + #endif diff --git a/io_uring/net.c b/io_uring/net.c index 43a43522f406..bec8c6ed0a93 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -1738,9 +1738,11 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - if (unlikely(req->flags & REQ_F_FAIL)) { - ret = -ECONNRESET; - goto out; + if (connect->in_progress) { + struct poll_table_struct pt = { ._key = EPOLLERR }; + + if (vfs_poll(req->file, &pt) & EPOLLERR) + goto get_sock_err; } file_flags = force_nonblock ? O_NONBLOCK : 0; @@ -1765,8 +1767,10 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) * which means the previous result is good. For both of these, * grab the sock_error() and use that for the completion. */ - if (ret == -EBADFD || ret == -EISCONN) + if (ret == -EBADFD || ret == -EISCONN) { +get_sock_err: ret = sock_error(sock_from_file(req->file)->sk); + } } if (ret == -ERESTARTSYS) ret = -EINTR; diff --git a/io_uring/poll.c b/io_uring/poll.c index 0526062e2f81..20e9b46a4adf 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -273,8 +273,6 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw) return IOU_POLL_REISSUE; } } - if (unlikely(req->cqe.res & EPOLLERR)) - req_set_fail(req); if (req->apoll_events & EPOLLONESHOT) return IOU_POLL_DONE; diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c index 00d0064b22a5..4a7011c799f0 100644 --- a/io_uring/zcrx.c +++ b/io_uring/zcrx.c @@ -76,6 +76,8 @@ static int io_import_dmabuf(struct io_zcrx_ifq *ifq, int dmabuf_fd = area_reg->dmabuf_fd; int i, ret; + if (off) + return -EINVAL; if (WARN_ON_ONCE(!ifq->dev)) return -EFAULT; if (!IS_ENABLED(CONFIG_DMA_SHARED_BUFFER)) @@ -106,7 +108,7 @@ static int io_import_dmabuf(struct io_zcrx_ifq *ifq, for_each_sgtable_dma_sg(mem->sgt, sg, i) total_size += sg_dma_len(sg); - if (total_size < off + len) { + if (total_size != len) { ret = -EINVAL; goto err; } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b71e428ad936..ad6df48b540c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -884,6 +884,13 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, if (fmt[i] == 'p') { sizeof_cur_arg = sizeof(long); + if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || + ispunct(fmt[i + 1])) { + if (tmp_buf) + cur_arg = raw_args[num_spec]; + goto nocopy_fmt; + } + if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') && fmt[i + 2] == 's') { fmt_ptype = fmt[i + 1]; @@ -891,11 +898,9 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, goto fmt_str; } - if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) || - ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' || + if (fmt[i + 1] == 'K' || fmt[i + 1] == 'x' || fmt[i + 1] == 's' || fmt[i + 1] == 'S') { - /* just kernel pointers */ if (tmp_buf) cur_arg = raw_args[num_spec]; i++; diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index 941d0d2427e3..8e61dc555415 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -21,7 +21,7 @@ static int btf_sysfs_vmlinux_mmap(struct file *filp, struct kobject *kobj, { unsigned long pages = PAGE_ALIGN(attr->size) >> PAGE_SHIFT; size_t vm_size = vma->vm_end - vma->vm_start; - phys_addr_t addr = virt_to_phys(__start_BTF); + phys_addr_t addr = __pa_symbol(__start_BTF); unsigned long pfn = addr >> PAGE_SHIFT; if (attr->private != __start_BTF || !PAGE_ALIGNED(addr)) diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c index 507b8f19a262..dd9417425d92 100644 --- a/kernel/cgroup/legacy_freezer.c +++ b/kernel/cgroup/legacy_freezer.c @@ -66,15 +66,9 @@ static struct freezer *parent_freezer(struct freezer *freezer) bool cgroup_freezing(struct task_struct *task) { bool ret; - unsigned int state; rcu_read_lock(); - /* Check if the cgroup is still FREEZING, but not FROZEN. The extra - * !FROZEN check is required, because the FREEZING bit is not cleared - * when the state FROZEN is reached. - */ - state = task_freezer(task)->state; - ret = (state & CGROUP_FREEZING) && !(state & CGROUP_FROZEN); + ret = task_freezer(task)->state & CGROUP_FREEZING; rcu_read_unlock(); return ret; diff --git a/kernel/freezer.c b/kernel/freezer.c index 8d530d0949ff..6a96149aede9 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -201,18 +201,9 @@ static int __restore_freezer_state(struct task_struct *p, void *arg) void __thaw_task(struct task_struct *p) { - unsigned long flags; - - spin_lock_irqsave(&freezer_lock, flags); - if (WARN_ON_ONCE(freezing(p))) - goto unlock; - - if (!frozen(p) || task_call_func(p, __restore_freezer_state, NULL)) - goto unlock; - - wake_up_state(p, TASK_FROZEN); -unlock: - spin_unlock_irqrestore(&freezer_lock, flags); + guard(spinlock_irqsave)(&freezer_lock); + if (frozen(p) && !task_call_func(p, __restore_freezer_state, NULL)) + wake_up_state(p, TASK_FROZEN); } /** diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index b498d867ba21..7dd5cbcb7a06 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1272,7 +1272,8 @@ static inline struct rq *scx_locked_rq(void) #define SCX_CALL_OP(sch, mask, op, rq, args...) \ do { \ - update_locked_rq(rq); \ + if (rq) \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ (sch)->ops.op(args); \ @@ -1280,14 +1281,16 @@ do { \ } else { \ (sch)->ops.op(args); \ } \ - update_locked_rq(NULL); \ + if (rq) \ + update_locked_rq(NULL); \ } while (0) #define SCX_CALL_OP_RET(sch, mask, op, rq, args...) \ ({ \ __typeof__((sch)->ops.op(args)) __ret; \ \ - update_locked_rq(rq); \ + if (rq) \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ __ret = (sch)->ops.op(args); \ @@ -1295,7 +1298,8 @@ do { \ } else { \ __ret = (sch)->ops.op(args); \ } \ - update_locked_rq(NULL); \ + if (rq) \ + update_locked_rq(NULL); \ __ret; \ }) diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index 6d29d3cbc670..001fb88a8481 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -903,7 +903,7 @@ s32 select_cpu_from_kfunc(struct task_struct *p, s32 prev_cpu, u64 wake_flags, * selection optimizations and simply check whether the previously * used CPU is idle and within the allowed cpumask. */ - if (p->nr_cpus_allowed == 1) { + if (p->nr_cpus_allowed == 1 || is_migration_disabled(p)) { if (cpumask_test_cpu(prev_cpu, allowed ?: p->cpus_ptr) && scx_idle_test_and_clear_cpu(prev_cpu)) cpu = prev_cpu; diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index c48900b856a2..52ca8e268cfc 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -80,7 +80,7 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) long nr_active, delta = 0; nr_active = this_rq->nr_running - adjust; - nr_active += (int)this_rq->nr_uninterruptible; + nr_active += (long)this_rq->nr_uninterruptible; if (nr_active != this_rq->calc_load_active) { delta = nr_active - this_rq->calc_load_active; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 475bb5998295..83e3aa917142 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1149,7 +1149,7 @@ struct rq { * one CPU and if it got migrated afterwards it may decrease * it on another CPU. Always updated under the runqueue lock: */ - unsigned int nr_uninterruptible; + unsigned long nr_uninterruptible; union { struct task_struct __rcu *donor; /* Scheduler context */ diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 120531268abf..d01e5c910ce1 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -3136,7 +3136,10 @@ __register_event(struct trace_event_call *call, struct module *mod) if (ret < 0) return ret; + down_write(&trace_event_sem); list_add(&call->list, &ftrace_events); + up_write(&trace_event_sem); + if (call->flags & TRACE_EVENT_FL_DYNAMIC) atomic_set(&call->refcnt, 0); else @@ -3750,6 +3753,8 @@ __trace_add_event_dirs(struct trace_array *tr) struct trace_event_call *call; int ret; + lockdep_assert_held(&trace_event_sem); + list_for_each_entry(call, &ftrace_events, list) { ret = __trace_add_new_event(call, tr); if (ret < 0) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 6819b93309ce..fd259da0aa64 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -637,8 +637,8 @@ __timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, u entry = ring_buffer_event_data(event); - memcpy(&entry->caller, fstack->calls, size); entry->size = fstack->nr_entries; + memcpy(&entry->caller, fstack->calls, size); trace_buffer_unlock_commit_nostack(buffer, event); } diff --git a/mm/secretmem.c b/mm/secretmem.c index 9a11a38a6770..e042a4a0bc0c 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -261,7 +261,15 @@ err_put_fd: static int secretmem_init_fs_context(struct fs_context *fc) { - return init_pseudo(fc, SECRETMEM_MAGIC) ? 0 : -ENOMEM; + struct pseudo_fs_context *ctx; + + ctx = init_pseudo(fc, SECRETMEM_MAGIC); + if (!ctx) + return -ENOMEM; + + fc->s_iflags |= SB_I_NOEXEC; + fc->s_iflags |= SB_I_NODEV; + return 0; } static struct file_system_type secretmem_fs = { @@ -279,9 +287,6 @@ static int __init secretmem_init(void) if (IS_ERR(secretmem_mnt)) return PTR_ERR(secretmem_mnt); - /* prevent secretmem mappings from ever getting PROT_EXEC */ - secretmem_mnt->mnt_flags |= MNT_NOEXEC; - return 0; } fs_initcall(secretmem_init); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 9a6df8c1daf9..fda3a80e9340 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -470,7 +470,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, list_add(&vlandev->close_list, &close_list); } - dev_close_many(&close_list, false); + netif_close_many(&close_list, false); list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { vlan_stacked_transfer_operstate(dev, vlandev, @@ -483,7 +483,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { - flgs = dev_get_flags(vlandev); + flgs = netif_get_flags(vlandev); if (flgs & IFF_UP) continue; @@ -765,3 +765,4 @@ module_exit(vlan_cleanup_module); MODULE_DESCRIPTION("802.1Q/802.1ad VLAN Protocol"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/net/Kconfig b/net/Kconfig index ebc80a98fc91..d5865cf19799 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -247,7 +247,7 @@ source "net/ipv4/netfilter/Kconfig" source "net/ipv6/netfilter/Kconfig" source "net/bridge/netfilter/Kconfig" -endif +endif # if NETFILTER source "net/sctp/Kconfig" source "net/rds/Kconfig" @@ -408,9 +408,9 @@ config NET_DROP_MONITOR just checking the various proc files and other utilities for drop statistics, say N here. -endmenu +endmenu # Network testing -endmenu +endmenu # Networking options source "net/ax25/Kconfig" source "net/can/Kconfig" diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 9c787e2e4b17..4744e3fd4544 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -35,6 +35,7 @@ #include <linux/seq_file.h> #include <linux/export.h> #include <linux/etherdevice.h> +#include <linux/refcount.h> int sysctl_aarp_expiry_time = AARP_EXPIRY_TIME; int sysctl_aarp_tick_time = AARP_TICK_TIME; @@ -44,6 +45,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; /* Lists of aarp entries */ /** * struct aarp_entry - AARP entry + * @refcnt: Reference count * @last_sent: Last time we xmitted the aarp request * @packet_queue: Queue of frames wait for resolution * @status: Used for proxy AARP @@ -55,6 +57,7 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; * @next: Next entry in chain */ struct aarp_entry { + refcount_t refcnt; /* These first two are only used for unresolved entries */ unsigned long last_sent; struct sk_buff_head packet_queue; @@ -79,6 +82,17 @@ static DEFINE_RWLOCK(aarp_lock); /* Used to walk the list and purge/kick entries. */ static struct timer_list aarp_timer; +static inline void aarp_entry_get(struct aarp_entry *a) +{ + refcount_inc(&a->refcnt); +} + +static inline void aarp_entry_put(struct aarp_entry *a) +{ + if (refcount_dec_and_test(&a->refcnt)) + kfree(a); +} + /* * Delete an aarp queue * @@ -87,7 +101,7 @@ static struct timer_list aarp_timer; static void __aarp_expire(struct aarp_entry *a) { skb_queue_purge(&a->packet_queue); - kfree(a); + aarp_entry_put(a); } /* @@ -380,9 +394,11 @@ static void aarp_purge(void) static struct aarp_entry *aarp_alloc(void) { struct aarp_entry *a = kmalloc(sizeof(*a), GFP_ATOMIC); + if (!a) + return NULL; - if (a) - skb_queue_head_init(&a->packet_queue); + refcount_set(&a->refcnt, 1); + skb_queue_head_init(&a->packet_queue); return a; } @@ -477,6 +493,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa) entry->dev = atif->dev; write_lock_bh(&aarp_lock); + aarp_entry_get(entry); hash = sa->s_node % (AARP_HASH_SIZE - 1); entry->next = proxies[hash]; @@ -502,6 +519,7 @@ int aarp_proxy_probe_network(struct atalk_iface *atif, struct atalk_addr *sa) retval = 1; } + aarp_entry_put(entry); write_unlock_bh(&aarp_lock); out: return retval; diff --git a/net/bridge/br.c b/net/bridge/br.c index 0adeafe11a36..1885d0c315f0 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -74,9 +74,9 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v if (br->dev->addr_assign_type == NET_ADDR_SET) break; prechaddr_info = ptr; - err = dev_pre_changeaddr_notify(br->dev, - prechaddr_info->dev_addr, - extack); + err = netif_pre_changeaddr_notify(br->dev, + prechaddr_info->dev_addr, + extack); if (err) return notifier_from_errno(err); break; @@ -484,3 +484,4 @@ MODULE_LICENSE("GPL"); MODULE_VERSION(BR_VERSION); MODULE_ALIAS_RTNL_LINK("bridge"); MODULE_DESCRIPTION("Ethernet bridge driver"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 2450690f98cf..98c5b9c3145f 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -668,7 +668,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, /* Ask for permission to use this MAC address now, even if we * don't end up choosing it below. */ - err = dev_pre_changeaddr_notify(br->dev, dev->dev_addr, extack); + err = netif_pre_changeaddr_notify(br->dev, dev->dev_addr, + extack); if (err) goto err6; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6e337937d0d7..4e2d53b27221 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -479,7 +479,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; - hdr->ifi_flags = dev_get_flags(dev); + hdr->ifi_flags = netif_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 9a910cf0256e..fe3f7bbe86ee 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -837,7 +837,7 @@ int br_switchdev_port_offload(struct net_bridge_port *p, struct netdev_phys_item_id ppid; int err; - err = dev_get_port_parent_id(dev, &ppid, false); + err = netif_get_port_parent_id(dev, &ppid, false); if (err) return err; diff --git a/net/core/dev.c b/net/core/dev.c index 621a639aeba1..354d3453b407 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1768,7 +1768,7 @@ static void __dev_close(struct net_device *dev) list_del(&single); } -void dev_close_many(struct list_head *head, bool unlink) +void netif_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; @@ -1786,7 +1786,7 @@ void dev_close_many(struct list_head *head, bool unlink) list_del_init(&dev->close_list); } } -EXPORT_SYMBOL(dev_close_many); +EXPORT_SYMBOL_NS_GPL(netif_close_many, "NETDEV_INTERNAL"); void netif_close(struct net_device *dev) { @@ -1794,7 +1794,7 @@ void netif_close(struct net_device *dev) LIST_HEAD(single); list_add(&dev->close_list, &single); - dev_close_many(&single, true); + netif_close_many(&single, true); list_del(&single); } } @@ -4798,7 +4798,7 @@ static inline void ____napi_schedule(struct softnet_data *sd, if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in - * napi_enable()/dev_set_threaded(). + * napi_enable()/netif_set_threaded(). * Use READ_ONCE() to guarantee a complete * read on napi->thread. Only call * wake_up_process() when it's not NULL. @@ -5749,6 +5749,7 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { + enum skb_drop_reason drop_reason = SKB_DROP_REASON_UNHANDLED_PROTO; struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct sk_buff *skb = *pskb; @@ -5840,8 +5841,10 @@ skip_taps: #endif skb_reset_redirect(skb); skip_classify: - if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) + if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) { + drop_reason = SKB_DROP_REASON_PFMEMALLOC; goto drop; + } if (skb_vlan_tag_present(skb)) { if (pt_prev) { @@ -5946,7 +5949,8 @@ drop: dev_core_stats_rx_dropped_inc(skb->dev); else dev_core_stats_rx_nohandler_inc(skb->dev); - kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO); + + kfree_skb_reason(skb, drop_reason); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ @@ -6986,7 +6990,7 @@ int napi_set_threaded(struct napi_struct *napi, bool threaded) return 0; } -int dev_set_threaded(struct net_device *dev, bool threaded) +int netif_set_threaded(struct net_device *dev, bool threaded) { struct napi_struct *napi; int err = 0; @@ -7027,7 +7031,7 @@ int dev_set_threaded(struct net_device *dev, bool threaded) return err; } -EXPORT_SYMBOL(dev_set_threaded); +EXPORT_SYMBOL(netif_set_threaded); /** * netif_queue_set_napi - Associate queue with the napi @@ -9450,12 +9454,12 @@ void dev_set_rx_mode(struct net_device *dev) } /** - * dev_get_flags - get flags reported to userspace - * @dev: device + * netif_get_flags() - get flags reported to userspace + * @dev: device * - * Get the combination of flag bits exported through APIs to userspace. + * Get the combination of flag bits exported through APIs to userspace. */ -unsigned int dev_get_flags(const struct net_device *dev) +unsigned int netif_get_flags(const struct net_device *dev) { unsigned int flags; @@ -9478,7 +9482,7 @@ unsigned int dev_get_flags(const struct net_device *dev) return flags; } -EXPORT_SYMBOL(dev_get_flags); +EXPORT_SYMBOL(netif_get_flags); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) @@ -9590,7 +9594,7 @@ int netif_change_flags(struct net_device *dev, unsigned int flags, return ret; } -int __dev_set_mtu(struct net_device *dev, int new_mtu) +int __netif_set_mtu(struct net_device *dev, int new_mtu) { const struct net_device_ops *ops = dev->netdev_ops; @@ -9601,7 +9605,7 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) WRITE_ONCE(dev->mtu, new_mtu); return 0; } -EXPORT_SYMBOL(__dev_set_mtu); +EXPORT_SYMBOL_NS_GPL(__netif_set_mtu, "NETDEV_INTERNAL"); int dev_validate_mtu(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) @@ -9620,18 +9624,22 @@ int dev_validate_mtu(struct net_device *dev, int new_mtu, } /** - * netif_set_mtu_ext - Change maximum transfer unit - * @dev: device - * @new_mtu: new transfer unit - * @extack: netlink extended ack + * netif_set_mtu_ext() - Change maximum transfer unit + * @dev: device + * @new_mtu: new transfer unit + * @extack: netlink extended ack * - * Change the maximum transfer size of the network device. + * Change the maximum transfer size of the network device. + * + * Return: 0 on success, -errno on failure. */ int netif_set_mtu_ext(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { int err, orig_mtu; + netdev_ops_assert_locked(dev); + if (new_mtu == dev->mtu) return 0; @@ -9648,7 +9656,7 @@ int netif_set_mtu_ext(struct net_device *dev, int new_mtu, return err; orig_mtu = dev->mtu; - err = __dev_set_mtu(dev, new_mtu); + err = __netif_set_mtu(dev, new_mtu); if (!err) { err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, @@ -9658,7 +9666,7 @@ int netif_set_mtu_ext(struct net_device *dev, int new_mtu, /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ - __dev_set_mtu(dev, orig_mtu); + __netif_set_mtu(dev, orig_mtu); call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, new_mtu); } @@ -9712,13 +9720,15 @@ void netif_set_group(struct net_device *dev, int new_group) } /** - * dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR. - * @dev: device - * @addr: new address - * @extack: netlink extended ack + * netif_pre_changeaddr_notify() - Call NETDEV_PRE_CHANGEADDR. + * @dev: device + * @addr: new address + * @extack: netlink extended ack + * + * Return: 0 on success, -errno on failure. */ -int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, - struct netlink_ext_ack *extack) +int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr, + struct netlink_ext_ack *extack) { struct netdev_notifier_pre_changeaddr_info info = { .info.dev = dev, @@ -9730,7 +9740,7 @@ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info); return notifier_to_errno(rc); } -EXPORT_SYMBOL(dev_pre_changeaddr_notify); +EXPORT_SYMBOL_NS_GPL(netif_pre_changeaddr_notify, "NETDEV_INTERNAL"); int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack) @@ -9744,7 +9754,7 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; - err = dev_pre_changeaddr_notify(dev, ss->__data, extack); + err = netif_pre_changeaddr_notify(dev, ss->__data, extack); if (err) return err; if (memcmp(dev->dev_addr, ss->__data, dev->addr_len)) { @@ -9761,7 +9771,7 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, DECLARE_RWSEM(dev_addr_sem); /* "sa" is a true struct sockaddr with limited "sa_data" member. */ -int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) +int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { size_t size = sizeof(sa->sa_data_min); struct net_device *dev; @@ -9787,7 +9797,7 @@ unlock: up_read(&dev_addr_sem); return ret; } -EXPORT_SYMBOL(dev_get_mac_address); +EXPORT_SYMBOL_NS_GPL(netif_get_mac_address, "NETDEV_INTERNAL"); int netif_change_carrier(struct net_device *dev, bool new_carrier) { @@ -9840,16 +9850,17 @@ int dev_get_phys_port_name(struct net_device *dev, } /** - * dev_get_port_parent_id - Get the device's port parent identifier - * @dev: network device - * @ppid: pointer to a storage for the port's parent identifier - * @recurse: allow/disallow recursion to lower devices + * netif_get_port_parent_id() - Get the device's port parent identifier + * @dev: network device + * @ppid: pointer to a storage for the port's parent identifier + * @recurse: allow/disallow recursion to lower devices + * + * Get the devices's port parent identifier. * - * Get the devices's port parent identifier + * Return: 0 on success, -errno on failure. */ -int dev_get_port_parent_id(struct net_device *dev, - struct netdev_phys_item_id *ppid, - bool recurse) +int netif_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, bool recurse) { const struct net_device_ops *ops = dev->netdev_ops; struct netdev_phys_item_id first = { }; @@ -9868,7 +9879,7 @@ int dev_get_port_parent_id(struct net_device *dev, return err; netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = dev_get_port_parent_id(lower_dev, ppid, true); + err = netif_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) @@ -9879,7 +9890,7 @@ int dev_get_port_parent_id(struct net_device *dev, return err; } -EXPORT_SYMBOL(dev_get_port_parent_id); +EXPORT_SYMBOL(netif_get_port_parent_id); /** * netdev_port_same_parent_id - Indicate if two network devices have @@ -9892,8 +9903,8 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) struct netdev_phys_item_id a_id = { }; struct netdev_phys_item_id b_id = { }; - if (dev_get_port_parent_id(a, &a_id, true) || - dev_get_port_parent_id(b, &b_id, true)) + if (netif_get_port_parent_id(a, &a_id, true) || + netif_get_port_parent_id(b, &b_id, true)) return false; return netdev_phys_item_id_same(&a_id, &b_id); @@ -12088,7 +12099,7 @@ void unregister_netdevice_many_notify(struct list_head *head, netdev_lock(dev); } } - dev_close_many(&close_head, true); + netif_close_many(&close_head, true); /* ... now unlock them and go over the rest. */ list_for_each_entry(dev, head, unreg_list) { if (netdev_need_ops_lock(dev)) @@ -12096,7 +12107,7 @@ void unregister_netdevice_many_notify(struct list_head *head, else list_add_tail(&dev->close_list, &close_head); } - dev_close_many(&close_head, true); + netif_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 90716bd736f3..76c91f224886 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -603,7 +603,7 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr, ASSERT_RTNL(); - err = dev_pre_changeaddr_notify(dev, addr, NULL); + err = netif_pre_changeaddr_notify(dev, addr, NULL); if (err) return err; err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type); diff --git a/net/core/dev_api.c b/net/core/dev_api.c index 1bf0153195f2..dd7f57013ce5 100644 --- a/net/core/dev_api.c +++ b/net/core/dev_api.c @@ -367,3 +367,15 @@ void netdev_state_change(struct net_device *dev) netdev_unlock_ops(dev); } EXPORT_SYMBOL(netdev_state_change); + +int dev_set_threaded(struct net_device *dev, bool threaded) +{ + int ret; + + netdev_lock(dev); + ret = netif_set_threaded(dev, threaded); + netdev_unlock(dev); + + return ret; +} +EXPORT_SYMBOL(dev_set_threaded); diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 616479e71466..9c0ad7f4b5d8 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -147,7 +147,7 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm switch (cmd) { case SIOCGIFFLAGS: /* Get interface flags */ - ifr->ifr_flags = (short) dev_get_flags(dev); + ifr->ifr_flags = (short)netif_get_flags(dev); return 0; case SIOCGIFMETRIC: /* Get the metric on the interface @@ -728,7 +728,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, switch (cmd) { case SIOCGIFHWADDR: dev_load(net, ifr->ifr_name); - ret = dev_get_mac_address(&ifr->ifr_hwaddr, net, ifr->ifr_name); + ret = netif_get_mac_address(&ifr->ifr_hwaddr, net, + ifr->ifr_name); if (colon) *colon = ':'; return ret; diff --git a/net/core/filter.c b/net/core/filter.c index 7a72f766aacf..2eb8947d8097 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -122,6 +122,7 @@ EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); * @sk: sock associated with &sk_buff * @skb: buffer to filter * @cap: limit on how short the eBPF program may trim the packet + * @reason: record drop reason on errors (negative return value) * * Run the eBPF program and then cut skb->data to correct size returned by * the program. If pkt_len is 0 we toss packet. If skb->len is smaller @@ -130,7 +131,8 @@ EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user); * be accepted or -EPERM if the packet should be tossed. * */ -int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) +int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, + unsigned int cap, enum skb_drop_reason *reason) { int err; struct sk_filter *filter; @@ -142,15 +144,20 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) */ if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); + *reason = SKB_DROP_REASON_PFMEMALLOC; return -ENOMEM; } err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb); - if (err) + if (err) { + *reason = SKB_DROP_REASON_SOCKET_FILTER; return err; + } err = security_sock_rcv_skb(sk, skb); - if (err) + if (err) { + *reason = SKB_DROP_REASON_SECURITY_HOOK; return err; + } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); @@ -162,6 +169,8 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) pkt_len = bpf_prog_run_save_cb(filter->prog, skb); skb->sk = save_sk; err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM; + if (err) + *reason = SKB_DROP_REASON_SOCKET_FILTER; } rcu_read_unlock(); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index d1de7f292eea..4316ca3d9872 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -28,6 +28,7 @@ #include <net/neighbour.h> #include <net/arp.h> #include <net/dst.h> +#include <net/ip.h> #include <net/sock.h> #include <net/netevent.h> #include <net/netlink.h> @@ -53,9 +54,8 @@ static void neigh_timer_handler(struct timer_list *t); static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid); static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid); -static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, - struct net_device *dev, - bool skip_perm); +static void pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev, + bool skip_perm); #ifdef CONFIG_PROC_FS static const struct seq_operations neigh_stat_seq_ops; @@ -436,7 +436,9 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); - pneigh_ifdown_and_unlock(tbl, dev, skip_perm); + write_unlock_bh(&tbl->lock); + + pneigh_ifdown(tbl, dev, skip_perm); pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL, tbl->family); if (skb_queue_empty_lockless(&tbl->proxy_queue)) @@ -719,54 +721,53 @@ static u32 pneigh_hash(const void *pkey, unsigned int key_len) return hash_val; } -static struct pneigh_entry *__pneigh_lookup_1(struct pneigh_entry *n, - struct net *net, - const void *pkey, - unsigned int key_len, - struct net_device *dev) +struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, + struct net *net, const void *pkey, + struct net_device *dev) { + struct pneigh_entry *n; + unsigned int key_len; + u32 hash_val; + + key_len = tbl->key_len; + hash_val = pneigh_hash(pkey, key_len); + n = rcu_dereference_check(tbl->phash_buckets[hash_val], + lockdep_is_held(&tbl->phash_lock)); + while (n) { if (!memcmp(n->key, pkey, key_len) && net_eq(pneigh_net(n), net) && (n->dev == dev || !n->dev)) return n; - n = n->next; - } - return NULL; -} -struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, - struct net *net, const void *pkey, struct net_device *dev) -{ - unsigned int key_len = tbl->key_len; - u32 hash_val = pneigh_hash(pkey, key_len); + n = rcu_dereference_check(n->next, lockdep_is_held(&tbl->phash_lock)); + } - return __pneigh_lookup_1(tbl->phash_buckets[hash_val], - net, pkey, key_len, dev); + return NULL; } -EXPORT_SYMBOL_GPL(__pneigh_lookup); +EXPORT_IPV6_MOD(pneigh_lookup); -struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, - struct net *net, const void *pkey, - struct net_device *dev, int creat) +int pneigh_create(struct neigh_table *tbl, struct net *net, + const void *pkey, struct net_device *dev, + u32 flags, u8 protocol, bool permanent) { struct pneigh_entry *n; - unsigned int key_len = tbl->key_len; - u32 hash_val = pneigh_hash(pkey, key_len); + unsigned int key_len; + u32 hash_val; + int err = 0; - read_lock_bh(&tbl->lock); - n = __pneigh_lookup_1(tbl->phash_buckets[hash_val], - net, pkey, key_len, dev); - read_unlock_bh(&tbl->lock); + mutex_lock(&tbl->phash_lock); - if (n || !creat) - goto out; - - ASSERT_RTNL(); + n = pneigh_lookup(tbl, net, pkey, dev); + if (n) + goto update; + key_len = tbl->key_len; n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL); - if (!n) + if (!n) { + err = -ENOBUFS; goto out; + } write_pnet(&n->net, net); memcpy(n->key, pkey, key_len); @@ -776,77 +777,98 @@ struct pneigh_entry * pneigh_lookup(struct neigh_table *tbl, if (tbl->pconstructor && tbl->pconstructor(n)) { netdev_put(dev, &n->dev_tracker); kfree(n); - n = NULL; + err = -ENOBUFS; goto out; } - write_lock_bh(&tbl->lock); + hash_val = pneigh_hash(pkey, key_len); n->next = tbl->phash_buckets[hash_val]; - tbl->phash_buckets[hash_val] = n; - write_unlock_bh(&tbl->lock); + rcu_assign_pointer(tbl->phash_buckets[hash_val], n); +update: + WRITE_ONCE(n->flags, flags); + n->permanent = permanent; + WRITE_ONCE(n->protocol, protocol); out: - return n; + mutex_unlock(&tbl->phash_lock); + return err; } -EXPORT_SYMBOL(pneigh_lookup); +static void pneigh_destroy(struct rcu_head *rcu) +{ + struct pneigh_entry *n = container_of(rcu, struct pneigh_entry, rcu); + + netdev_put(n->dev, &n->dev_tracker); + kfree(n); +} int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, struct net_device *dev) { - struct pneigh_entry *n, **np; - unsigned int key_len = tbl->key_len; - u32 hash_val = pneigh_hash(pkey, key_len); + struct pneigh_entry *n, __rcu **np; + unsigned int key_len; + u32 hash_val; - write_lock_bh(&tbl->lock); - for (np = &tbl->phash_buckets[hash_val]; (n = *np) != NULL; + key_len = tbl->key_len; + hash_val = pneigh_hash(pkey, key_len); + + mutex_lock(&tbl->phash_lock); + + for (np = &tbl->phash_buckets[hash_val]; + (n = rcu_dereference_protected(*np, 1)) != NULL; np = &n->next) { if (!memcmp(n->key, pkey, key_len) && n->dev == dev && net_eq(pneigh_net(n), net)) { - *np = n->next; - write_unlock_bh(&tbl->lock); + rcu_assign_pointer(*np, n->next); + + mutex_unlock(&tbl->phash_lock); + if (tbl->pdestructor) tbl->pdestructor(n); - netdev_put(n->dev, &n->dev_tracker); - kfree(n); + + call_rcu(&n->rcu, pneigh_destroy); return 0; } } - write_unlock_bh(&tbl->lock); + + mutex_unlock(&tbl->phash_lock); return -ENOENT; } -static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, - struct net_device *dev, - bool skip_perm) +static void pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev, + bool skip_perm) { - struct pneigh_entry *n, **np, *freelist = NULL; + struct pneigh_entry *n, __rcu **np; + LIST_HEAD(head); u32 h; + mutex_lock(&tbl->phash_lock); + for (h = 0; h <= PNEIGH_HASHMASK; h++) { np = &tbl->phash_buckets[h]; - while ((n = *np) != NULL) { + while ((n = rcu_dereference_protected(*np, 1)) != NULL) { if (skip_perm && n->permanent) goto skip; if (!dev || n->dev == dev) { - *np = n->next; - n->next = freelist; - freelist = n; + rcu_assign_pointer(*np, n->next); + list_add(&n->free_node, &head); continue; } skip: np = &n->next; } } - write_unlock_bh(&tbl->lock); - while ((n = freelist)) { - freelist = n->next; - n->next = NULL; + + mutex_unlock(&tbl->phash_lock); + + while (!list_empty(&head)) { + n = list_first_entry(&head, typeof(*n), free_node); + list_del(&n->free_node); + if (tbl->pdestructor) tbl->pdestructor(n); - netdev_put(n->dev, &n->dev_tracker); - kfree(n); + + call_rcu(&n->rcu, pneigh_destroy); } - return -ENOENT; } static inline void neigh_parms_put(struct neigh_parms *parms) @@ -1783,6 +1805,7 @@ void neigh_table_init(int index, struct neigh_table *tbl) WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); + mutex_init(&tbl->phash_lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, @@ -1999,22 +2022,13 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); if (ndm_flags & NTF_PROXY) { - struct pneigh_entry *pn; - if (ndm_flags & (NTF_MANAGED | NTF_EXT_VALIDATED)) { NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination"); goto out; } - err = -ENOBUFS; - pn = pneigh_lookup(tbl, net, dst, dev, 1); - if (pn) { - pn->flags = ndm_flags; - pn->permanent = !!(ndm->ndm_state & NUD_PERMANENT); - if (protocol) - pn->protocol = protocol; - err = 0; - } + err = pneigh_create(tbl, net, dst, dev, ndm_flags, protocol, + !!(ndm->ndm_state & NUD_PERMANENT)); goto out; } @@ -2643,13 +2657,15 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 neigh_flags, neigh_flags_ext; struct nlmsghdr *nlh; struct ndmsg *ndm; + u8 protocol; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; - neigh_flags_ext = pn->flags >> NTF_EXT_SHIFT; - neigh_flags = pn->flags & NTF_OLD_MASK; + neigh_flags = READ_ONCE(pn->flags); + neigh_flags_ext = neigh_flags >> NTF_EXT_SHIFT; + neigh_flags &= NTF_OLD_MASK; ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; @@ -2663,7 +2679,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nla_put(skb, NDA_DST, tbl->key_len, pn->key)) goto nla_put_failure; - if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) + protocol = READ_ONCE(pn->protocol); + if (protocol && nla_put_u8(skb, NDA_PROTOCOL, protocol)) goto nla_put_failure; if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) goto nla_put_failure; @@ -2770,12 +2787,12 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (filter->dev_idx || filter->master_idx) flags |= NLM_F_DUMP_FILTERED; - read_lock_bh(&tbl->lock); - for (h = s_h; h <= PNEIGH_HASHMASK; h++) { if (h > s_h) s_idx = 0; - for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { + for (n = rcu_dereference(tbl->phash_buckets[h]), idx = 0; + n; + n = rcu_dereference(n->next)) { if (idx < s_idx || pneigh_net(n) != net) goto next; if (neigh_ifindex_filtered(n->dev, filter->dev_idx) || @@ -2784,16 +2801,13 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, err = pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, flags, tbl); - if (err < 0) { - read_unlock_bh(&tbl->lock); + if (err < 0) goto out; - } next: idx++; } } - read_unlock_bh(&tbl->lock); out: cb->args[3] = h; cb->args[4] = idx; @@ -2910,64 +2924,58 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) return err; } -static int neigh_valid_get_req(const struct nlmsghdr *nlh, - struct neigh_table **tbl, - void **dst, int *dev_idx, u8 *ndm_flags, - struct netlink_ext_ack *extack) +static struct ndmsg *neigh_valid_get_req(const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) { - struct nlattr *tb[NDA_MAX + 1]; struct ndmsg *ndm; int err, i; ndm = nlmsg_payload(nlh, sizeof(*ndm)); if (!ndm) { NL_SET_ERR_MSG(extack, "Invalid header for neighbor get request"); - return -EINVAL; + return ERR_PTR(-EINVAL); } if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state || ndm->ndm_type) { NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor get request"); - return -EINVAL; + return ERR_PTR(-EINVAL); } if (ndm->ndm_flags & ~NTF_PROXY) { NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor get request"); - return -EINVAL; + return ERR_PTR(-EINVAL); + } + + if (!(ndm->ndm_flags & NTF_PROXY) && !ndm->ndm_ifindex) { + NL_SET_ERR_MSG(extack, "No device specified"); + return ERR_PTR(-EINVAL); } err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX, nda_policy, extack); if (err < 0) - return err; - - *ndm_flags = ndm->ndm_flags; - *dev_idx = ndm->ndm_ifindex; - *tbl = neigh_find_table(ndm->ndm_family); - if (*tbl == NULL) { - NL_SET_ERR_MSG(extack, "Unsupported family in header for neighbor get request"); - return -EAFNOSUPPORT; - } + return ERR_PTR(err); for (i = 0; i <= NDA_MAX; ++i) { - if (!tb[i]) - continue; - switch (i) { case NDA_DST: - if (nla_len(tb[i]) != (int)(*tbl)->key_len) { - NL_SET_ERR_MSG(extack, "Invalid network address in neighbor get request"); - return -EINVAL; + if (!tb[i]) { + NL_SET_ERR_ATTR_MISS(extack, NULL, NDA_DST); + return ERR_PTR(-EINVAL); } - *dst = nla_data(tb[i]); break; default: + if (!tb[i]) + continue; + NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor get request"); - return -EINVAL; + return ERR_PTR(-EINVAL); } } - return 0; + return ndm; } static inline size_t neigh_nlmsg_size(void) @@ -2981,27 +2989,6 @@ static inline size_t neigh_nlmsg_size(void) + nla_total_size(1); /* NDA_PROTOCOL */ } -static int neigh_get_reply(struct net *net, struct neighbour *neigh, - u32 pid, u32 seq) -{ - struct sk_buff *skb; - int err = 0; - - skb = nlmsg_new(neigh_nlmsg_size(), GFP_KERNEL); - if (!skb) - return -ENOBUFS; - - err = neigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0); - if (err) { - kfree_skb(skb); - goto errout; - } - - err = rtnl_unicast(skb, net, pid); -errout: - return err; -} - static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) @@ -3010,85 +2997,91 @@ static inline size_t pneigh_nlmsg_size(void) + nla_total_size(1); /* NDA_PROTOCOL */ } -static int pneigh_get_reply(struct net *net, struct pneigh_entry *neigh, - u32 pid, u32 seq, struct neigh_table *tbl) +static int neigh_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) { + struct net *net = sock_net(in_skb->sk); + u32 pid = NETLINK_CB(in_skb).portid; + struct nlattr *tb[NDA_MAX + 1]; + struct net_device *dev = NULL; + u32 seq = nlh->nlmsg_seq; + struct neigh_table *tbl; + struct neighbour *neigh; struct sk_buff *skb; - int err = 0; + struct ndmsg *ndm; + void *dst; + int err; - skb = nlmsg_new(pneigh_nlmsg_size(), GFP_KERNEL); + ndm = neigh_valid_get_req(nlh, tb, extack); + if (IS_ERR(ndm)) + return PTR_ERR(ndm); + + if (ndm->ndm_flags & NTF_PROXY) + skb = nlmsg_new(neigh_nlmsg_size(), GFP_KERNEL); + else + skb = nlmsg_new(pneigh_nlmsg_size(), GFP_KERNEL); if (!skb) return -ENOBUFS; - err = pneigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0, tbl); - if (err) { - kfree_skb(skb); - goto errout; - } + rcu_read_lock(); - err = rtnl_unicast(skb, net, pid); -errout: - return err; -} + tbl = neigh_find_table(ndm->ndm_family); + if (!tbl) { + NL_SET_ERR_MSG(extack, "Unsupported family in header for neighbor get request"); + err = -EAFNOSUPPORT; + goto err_unlock; + } -static int neigh_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) -{ - struct net *net = sock_net(in_skb->sk); - struct net_device *dev = NULL; - struct neigh_table *tbl = NULL; - struct neighbour *neigh; - void *dst = NULL; - u8 ndm_flags = 0; - int dev_idx = 0; - int err; + if (nla_len(tb[NDA_DST]) != (int)tbl->key_len) { + NL_SET_ERR_MSG(extack, "Invalid network address in neighbor get request"); + err = -EINVAL; + goto err_unlock; + } - err = neigh_valid_get_req(nlh, &tbl, &dst, &dev_idx, &ndm_flags, - extack); - if (err < 0) - return err; + dst = nla_data(tb[NDA_DST]); - if (dev_idx) { - dev = __dev_get_by_index(net, dev_idx); + if (ndm->ndm_ifindex) { + dev = dev_get_by_index_rcu(net, ndm->ndm_ifindex); if (!dev) { NL_SET_ERR_MSG(extack, "Unknown device ifindex"); - return -ENODEV; + err = -ENODEV; + goto err_unlock; } } - if (!dst) { - NL_SET_ERR_MSG(extack, "Network address not specified"); - return -EINVAL; - } - - if (ndm_flags & NTF_PROXY) { + if (ndm->ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; - pn = pneigh_lookup(tbl, net, dst, dev, 0); + pn = pneigh_lookup(tbl, net, dst, dev); if (!pn) { NL_SET_ERR_MSG(extack, "Proxy neighbour entry not found"); - return -ENOENT; + err = -ENOENT; + goto err_unlock; } - return pneigh_get_reply(net, pn, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, tbl); - } - if (!dev) { - NL_SET_ERR_MSG(extack, "No device specified"); - return -EINVAL; - } + err = pneigh_fill_info(skb, pn, pid, seq, RTM_NEWNEIGH, 0, tbl); + if (err) + goto err_unlock; + } else { + neigh = neigh_lookup(tbl, dst, dev); + if (!neigh) { + NL_SET_ERR_MSG(extack, "Neighbour entry not found"); + err = -ENOENT; + goto err_unlock; + } - neigh = neigh_lookup(tbl, dst, dev); - if (!neigh) { - NL_SET_ERR_MSG(extack, "Neighbour entry not found"); - return -ENOENT; + err = neigh_fill_info(skb, neigh, pid, seq, RTM_NEWNEIGH, 0); + neigh_release(neigh); + if (err) + goto err_unlock; } - err = neigh_get_reply(net, neigh, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq); - - neigh_release(neigh); + rcu_read_unlock(); + return rtnl_unicast(skb, net, pid); +err_unlock: + rcu_read_unlock(); + kfree_skb(skb); return err; } @@ -3295,9 +3288,10 @@ static struct pneigh_entry *pneigh_get_first(struct seq_file *seq) state->flags |= NEIGH_SEQ_IS_PNEIGH; for (bucket = 0; bucket <= PNEIGH_HASHMASK; bucket++) { - pn = tbl->phash_buckets[bucket]; + pn = rcu_dereference(tbl->phash_buckets[bucket]); + while (pn && !net_eq(pneigh_net(pn), net)) - pn = pn->next; + pn = rcu_dereference(pn->next); if (pn) break; } @@ -3315,15 +3309,17 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq, struct neigh_table *tbl = state->tbl; do { - pn = pn->next; + pn = rcu_dereference(pn->next); } while (pn && !net_eq(pneigh_net(pn), net)); while (!pn) { if (++state->bucket > PNEIGH_HASHMASK) break; - pn = tbl->phash_buckets[state->bucket]; + + pn = rcu_dereference(tbl->phash_buckets[state->bucket]); + while (pn && !net_eq(pneigh_net(pn), net)) - pn = pn->next; + pn = rcu_dereference(pn->next); if (pn) break; } @@ -3887,7 +3883,7 @@ static const struct rtnl_msg_handler neigh_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWNEIGH, .doit = neigh_add}, {.msgtype = RTM_DELNEIGH, .doit = neigh_delete}, {.msgtype = RTM_GETNEIGH, .doit = neigh_get, .dumpit = neigh_dump_info, - .flags = RTNL_FLAG_DUMP_UNLOCKED}, + .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, {.msgtype = RTM_GETNEIGHTBL, .dumpit = neightbl_dump_info}, {.msgtype = RTM_SETNEIGHTBL, .doit = neightbl_set}, }; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 8f897e2c8b4f..c28cd6665444 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -256,7 +256,7 @@ static ssize_t name_assign_type_show(struct device *dev, } static DEVICE_ATTR_RO(name_assign_type); -/* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */ +/* use same locking rules as GIFHWADDR ioctl's (netif_get_mac_address()) */ static ssize_t address_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -687,7 +687,7 @@ static ssize_t phys_switch_id_show(struct device *dev, if (ret) return ret; - ret = dev_get_port_parent_id(netdev, &ppid, false); + ret = netif_get_port_parent_id(netdev, &ppid, false); if (!ret) ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id); @@ -757,7 +757,7 @@ static int modify_napi_threaded(struct net_device *dev, unsigned long val) if (val != 0 && val != 1) return -EOPNOTSUPP; - ret = dev_set_threaded(dev, val); + ret = netif_set_threaded(dev, val); return ret; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a9555bfc372f..094b085cff20 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1448,7 +1448,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) struct netdev_phys_item_id ppid = { }; int err; - err = dev_get_port_parent_id(dev, &ppid, false); + err = netif_get_port_parent_id(dev, &ppid, false); if (err) { if (err == -EOPNOTSUPP) return 0; @@ -2038,7 +2038,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, ifm->__ifi_pad = 0; ifm->ifi_type = READ_ONCE(dev->type); ifm->ifi_index = READ_ONCE(dev->ifindex); - ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_flags = netif_get_flags(dev); ifm->ifi_change = change; if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) @@ -5227,7 +5227,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, ifm->__ifi_pad = 0; ifm->ifi_type = dev->type; ifm->ifi_index = dev->ifindex; - ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_flags = netif_get_flags(dev); ifm->ifi_change = 0; diff --git a/net/core/selftests.c b/net/core/selftests.c index 406faf8e5f3f..3d79133a91a6 100644 --- a/net/core/selftests.c +++ b/net/core/selftests.c @@ -27,6 +27,7 @@ struct net_packet_attrs { int max_size; u8 id; u16 queue_mapping; + bool bad_csum; }; struct net_test_priv { @@ -165,6 +166,20 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev, thdr->check = ~tcp_v4_check(l4len, ihdr->saddr, ihdr->daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); + + if (attr->bad_csum) { + /* Force mangled checksum */ + if (skb_checksum_help(skb)) { + kfree_skb(skb); + return NULL; + } + + if (thdr->check != CSUM_MANGLED_0) + thdr->check = CSUM_MANGLED_0; + else + thdr->check = csum16_sub(thdr->check, + cpu_to_be16(1)); + } } else { udp4_hwcsum(skb, ihdr->saddr, ihdr->daddr); } @@ -239,7 +254,11 @@ static int net_test_loopback_validate(struct sk_buff *skb, if (tpriv->packet->id != shdr->id) goto out; - tpriv->ok = true; + if (tpriv->packet->bad_csum && skb->ip_summed == CHECKSUM_UNNECESSARY) + tpriv->ok = -EIO; + else + tpriv->ok = true; + complete(&tpriv->comp); out: kfree_skb(skb); @@ -285,7 +304,12 @@ static int __net_test_loopback(struct net_device *ndev, attr->timeout = NET_LB_TIMEOUT; wait_for_completion_timeout(&tpriv->comp, attr->timeout); - ret = tpriv->ok ? 0 : -ETIMEDOUT; + if (tpriv->ok < 0) + ret = tpriv->ok; + else if (!tpriv->ok) + ret = -ETIMEDOUT; + else + ret = 0; cleanup: dev_remove_pack(&tpriv->pt); @@ -345,6 +369,42 @@ static int net_test_phy_loopback_tcp(struct net_device *ndev) return __net_test_loopback(ndev, &attr); } +/** + * net_test_phy_loopback_tcp_bad_csum - PHY loopback test with a deliberately + * corrupted TCP checksum + * @ndev: the network device to test + * + * Builds the same minimal Ethernet/IPv4/TCP frame as + * net_test_phy_loopback_tcp(), then flips the least-significant bit of the TCP + * checksum so the resulting value is provably invalid (neither 0 nor 0xFFFF). + * The frame is transmitted through the device’s internal PHY loopback path: + * + * test code -> MAC driver -> MAC HW -> xMII -> PHY -> + * internal PHY loopback -> xMII -> MAC HW -> MAC driver -> test code + * + * Result interpretation + * --------------------- + * 0 The frame is delivered to the stack and the driver reports + * ip_summed as CHECKSUM_NONE or CHECKSUM_COMPLETE - both are + * valid ways to indicate “bad checksum, let the stack verify.” + * -ETIMEDOUT The MAC/PHY silently dropped the frame; hardware checksum + * verification filtered it out before the driver saw it. + * -EIO The driver returned the frame with ip_summed == + * CHECKSUM_UNNECESSARY, falsely claiming a valid checksum and + * indicating a serious RX-path defect. + * + * Return: 0 on success or a negative error code on failure. + */ +static int net_test_phy_loopback_tcp_bad_csum(struct net_device *ndev) +{ + struct net_packet_attrs attr = { }; + + attr.dst = ndev->dev_addr; + attr.tcp = true; + attr.bad_csum = true; + return __net_test_loopback(ndev, &attr); +} + static const struct net_test { char name[ETH_GSTRING_LEN]; int (*fn)(struct net_device *ndev); @@ -369,6 +429,9 @@ static const struct net_test { .name = "PHY internal loopback, TCP ", .fn = net_test_phy_loopback_tcp, }, { + .name = "PHY loopback, bad TCP csum ", + .fn = net_test_phy_loopback_tcp_bad_csum, + }, { /* This test should be done after all PHY loopback test */ .name = "PHY internal loopback, disable", .fn = net_test_phy_loopback_disable, diff --git a/net/core/sock.c b/net/core/sock.c index 8b7623c7d547..7c26ec8dce63 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -526,11 +526,10 @@ int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason drop_reason; int err; - err = sk_filter(sk, skb); - if (err) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + err = sk_filter_reason(sk, skb, &drop_reason); + if (err) goto out; - } + err = __sock_queue_rcv_skb(sk, skb); switch (err) { case -ENOMEM: @@ -553,15 +552,18 @@ EXPORT_SYMBOL(sock_queue_rcv_skb_reason); int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, const int nested, unsigned int trim_cap, bool refcounted) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; int rc = NET_RX_SUCCESS; + int err; - if (sk_filter_trim_cap(sk, skb, trim_cap)) + if (sk_filter_trim_cap(sk, skb, trim_cap, &reason)) goto discard_and_relse; skb->dev = NULL; if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) { atomic_inc(&sk->sk_drops); + reason = SKB_DROP_REASON_SOCKET_RCVBUFF; goto discard_and_relse; } if (nested) @@ -577,8 +579,12 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb, rc = sk_backlog_rcv(sk, skb); mutex_release(&sk->sk_lock.dep_map, _RET_IP_); - } else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) { + } else if ((err = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))) { bh_unlock_sock(sk); + if (err == -ENOMEM) + reason = SKB_DROP_REASON_PFMEMALLOC; + if (err == -ENOBUFS) + reason = SKB_DROP_REASON_SOCKET_BACKLOG; atomic_inc(&sk->sk_drops); goto discard_and_relse; } @@ -589,7 +595,7 @@ out: sock_put(sk); return rc; discard_and_relse: - kfree_skb(skb); + sk_skb_reason_drop(sk, skb, reason); goto out; } EXPORT_SYMBOL(__sk_receive_skb); diff --git a/net/core/stream.c b/net/core/stream.c index b16dfa568a2d..7a37e7dd2c43 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -23,9 +23,13 @@ /** * sk_stream_write_space - stream socket write_space callback. - * @sk: socket + * @sk: pointer to the socket structure * - * FIXME: write proper description + * This function is invoked when there's space available in the socket's + * send buffer for writing. It first checks if the socket is writable, + * clears the SOCK_NOSPACE flag indicating that memory for writing + * is now available, wakes up any processes waiting for write operations + * and sends asynchronous notifications if needed. */ void sk_stream_write_space(struct sock *sk) { diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index c50436433c18..d97c326a9045 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -45,9 +45,9 @@ const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_ [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(15), }; -const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_ATTR_RATE_TC_BW + 1] = { - [DEVLINK_ATTR_RATE_TC_INDEX] = NLA_POLICY_MAX(NLA_U8, DEVLINK_RATE_TC_INDEX_MAX), - [DEVLINK_ATTR_RATE_TC_BW] = { .type = NLA_U32, }, +const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_RATE_TC_ATTR_BW + 1] = { + [DEVLINK_RATE_TC_ATTR_INDEX] = NLA_POLICY_MAX(NLA_U8, DEVLINK_RATE_TC_INDEX_MAX), + [DEVLINK_RATE_TC_ATTR_BW] = { .type = NLA_U32, }, }; const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = { diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index fb733b5d4ff1..09cc6f264ccf 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -13,7 +13,7 @@ /* Common nested types */ extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1]; -extern const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_ATTR_RATE_TC_BW + 1]; +extern const struct nla_policy devlink_dl_rate_tc_bws_nl_policy[DEVLINK_RATE_TC_ATTR_BW + 1]; extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1]; /* Ops table for devlink */ diff --git a/net/devlink/rate.c b/net/devlink/rate.c index d39300a9b3d4..110b3fa8a0b1 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -90,8 +90,8 @@ static int devlink_rate_put_tc_bws(struct sk_buff *msg, u32 *tc_bw) if (!nla_tc_bw) return -EMSGSIZE; - if (nla_put_u8(msg, DEVLINK_ATTR_RATE_TC_INDEX, i) || - nla_put_u32(msg, DEVLINK_ATTR_RATE_TC_BW, tc_bw[i])) + if (nla_put_u8(msg, DEVLINK_RATE_TC_ATTR_INDEX, i) || + nla_put_u32(msg, DEVLINK_RATE_TC_ATTR_BW, tc_bw[i])) goto nla_put_failure; nla_nest_end(msg, nla_tc_bw); @@ -346,26 +346,26 @@ static int devlink_nl_rate_tc_bw_parse(struct nlattr *parent_nest, u32 *tc_bw, unsigned long *bitmap, struct netlink_ext_ack *extack) { - struct nlattr *tb[DEVLINK_ATTR_MAX + 1]; + struct nlattr *tb[DEVLINK_RATE_TC_ATTR_MAX + 1]; u8 tc_index; int err; - err = nla_parse_nested(tb, DEVLINK_ATTR_MAX, parent_nest, + err = nla_parse_nested(tb, DEVLINK_RATE_TC_ATTR_MAX, parent_nest, devlink_dl_rate_tc_bws_nl_policy, extack); if (err) return err; - if (!tb[DEVLINK_ATTR_RATE_TC_INDEX]) { + if (!tb[DEVLINK_RATE_TC_ATTR_INDEX]) { NL_SET_ERR_ATTR_MISS(extack, parent_nest, - DEVLINK_ATTR_RATE_TC_INDEX); + DEVLINK_RATE_TC_ATTR_INDEX); return -EINVAL; } - tc_index = nla_get_u8(tb[DEVLINK_ATTR_RATE_TC_INDEX]); + tc_index = nla_get_u8(tb[DEVLINK_RATE_TC_ATTR_INDEX]); - if (!tb[DEVLINK_ATTR_RATE_TC_BW]) { + if (!tb[DEVLINK_RATE_TC_ATTR_BW]) { NL_SET_ERR_ATTR_MISS(extack, parent_nest, - DEVLINK_ATTR_RATE_TC_BW); + DEVLINK_RATE_TC_ATTR_BW); return -EINVAL; } @@ -376,7 +376,7 @@ static int devlink_nl_rate_tc_bw_parse(struct nlattr *parent_nest, u32 *tc_bw, return -EINVAL; } - tc_bw[tc_index] = nla_get_u32(tb[DEVLINK_ATTR_RATE_TC_BW]); + tc_bw[tc_index] = nla_get_u32(tb[DEVLINK_RATE_TC_ATTR_BW]); return 0; } diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index 436a7e1b412a..5b01a0e43ebe 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -1621,7 +1621,7 @@ void dsa_switch_shutdown(struct dsa_switch *ds) dsa_switch_for_each_cpu_port(dp, ds) list_add(&dp->conduit->close_list, &close_list); - dev_close_many(&close_list, true); + netif_close_many(&close_list, true); dsa_switch_for_each_user_port(dp, ds) { conduit = dsa_port_to_conduit(dp); @@ -1829,3 +1829,4 @@ MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>"); MODULE_DESCRIPTION("Driver for Distributed Switch Architecture switch chips"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:dsa"); +MODULE_IMPORT_NS("NETDEV_INTERNAL"); diff --git a/net/dsa/user.c b/net/dsa/user.c index e9334520c54a..f59d66f0975d 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -3604,7 +3604,7 @@ static int dsa_user_netdevice_event(struct notifier_block *nb, list_add(&dp->user->close_list, &close_list); } - dev_close_many(&close_list, true); + netif_close_many(&close_list, true); return NOTIFY_OK; } diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 459cf25e763e..4f58648a27ad 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -806,6 +806,55 @@ out_free: return rc; } +struct ethtool_rxfh_context * +ethtool_rxfh_ctx_alloc(const struct ethtool_ops *ops, + u32 indir_size, u32 key_size) +{ + size_t indir_bytes, flex_len, key_off, size; + struct ethtool_rxfh_context *ctx; + u32 priv_bytes, indir_max; + u16 key_max; + + key_max = max(key_size, ops->rxfh_key_space); + indir_max = max(indir_size, ops->rxfh_indir_space); + + priv_bytes = ALIGN(ops->rxfh_priv_size, sizeof(u32)); + indir_bytes = array_size(indir_max, sizeof(u32)); + + key_off = size_add(priv_bytes, indir_bytes); + flex_len = size_add(key_off, key_max); + size = struct_size_t(struct ethtool_rxfh_context, data, flex_len); + + ctx = kzalloc(size, GFP_KERNEL_ACCOUNT); + if (!ctx) + return NULL; + + ctx->indir_size = indir_size; + ctx->key_size = key_size; + ctx->key_off = key_off; + ctx->priv_size = ops->rxfh_priv_size; + + ctx->hfunc = ETH_RSS_HASH_NO_CHANGE; + ctx->input_xfrm = RXH_XFRM_NO_CHANGE; + + return ctx; +} + +/* Check if fields configured for flow hash are symmetric - if src is included + * so is dst and vice versa. + */ +int ethtool_rxfh_config_is_sym(u64 rxfh) +{ + bool sym; + + sym = rxfh == (rxfh & (RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)); + sym &= !!(rxfh & RXH_IP_SRC) == !!(rxfh & RXH_IP_DST); + sym &= !!(rxfh & RXH_L4_B_0_1) == !!(rxfh & RXH_L4_B_2_3); + + return sym; +} + int ethtool_check_ops(const struct ethtool_ops *ops) { if (WARN_ON(ops->set_coalesce && !ops->supported_coalesce_params)) @@ -814,6 +863,10 @@ int ethtool_check_ops(const struct ethtool_ops *ops) return -EINVAL; if (WARN_ON(ops->supported_input_xfrm && !ops->get_rxfh_fields)) return -EINVAL; + if (WARN_ON(ops->supported_input_xfrm && + ops->rxfh_per_ctx_fields != ops->rxfh_per_ctx_key)) + return -EINVAL; + /* NOTE: sufficiently insane drivers may swap ethtool_ops at runtime, * the fact that ops are checked at registration time does not * mean the ops attached to a netdev later on are sane. @@ -1083,5 +1136,6 @@ void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id) netdev_err(dev, "device error, RSS context %d lost\n", context_id); ctx = xa_erase(&dev->ethtool->rss_ctx, context_id); kfree(ctx); + ethtool_rss_notify(dev, ETHTOOL_MSG_RSS_DELETE_NTF, context_id); } EXPORT_SYMBOL(ethtool_rxfh_context_lost); diff --git a/net/ethtool/common.h b/net/ethtool/common.h index c41db1595621..c4d084dde5bf 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -43,7 +43,11 @@ bool convert_legacy_settings_to_link_ksettings( int ethtool_check_max_channel(struct net_device *dev, struct ethtool_channels channels, struct genl_info *info); +struct ethtool_rxfh_context * +ethtool_rxfh_ctx_alloc(const struct ethtool_ops *ops, + u32 indir_size, u32 key_size); int ethtool_check_rss_ctx_busy(struct net_device *dev, u32 rss_context); +int ethtool_rxfh_config_is_sym(u64 rxfh); void ethtool_ringparam_get_cfg(struct net_device *dev, struct ethtool_ringparam *param, @@ -75,9 +79,10 @@ int ethtool_get_module_eeprom_call(struct net_device *dev, bool __ethtool_dev_mm_supported(struct net_device *dev); #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) -void ethtool_rss_notify(struct net_device *dev, u32 rss_context); +void ethtool_rss_notify(struct net_device *dev, u32 type, u32 rss_context); #else -static inline void ethtool_rss_notify(struct net_device *dev, u32 rss_context) +static inline void +ethtool_rss_notify(struct net_device *dev, u32 type, u32 rss_context) { } #endif diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 830623678cb3..43a7854e784e 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1027,9 +1027,7 @@ static int ethtool_check_xfrm_rxfh(u32 input_xfrm, u64 rxfh) */ if ((input_xfrm != RXH_XFRM_NO_CHANGE && input_xfrm & (RXH_XFRM_SYM_XOR | RXH_XFRM_SYM_OR_XOR)) && - ((rxfh & ~(RXH_IP_SRC | RXH_IP_DST | RXH_L4_B_0_1 | RXH_L4_B_2_3)) || - (!!(rxfh & RXH_IP_SRC) ^ !!(rxfh & RXH_IP_DST)) || - (!!(rxfh & RXH_L4_B_0_1) ^ !!(rxfh & RXH_L4_B_2_3)))) + !ethtool_rxfh_config_is_sym(rxfh)) return -EINVAL; return 0; @@ -1107,7 +1105,7 @@ exit_unlock: if (rc) return rc; - ethtool_rss_notify(dev, fields.rss_context); + ethtool_rss_notify(dev, ETHTOOL_MSG_RSS_NTF, fields.rss_context); return 0; } @@ -1475,40 +1473,6 @@ out: return ret; } -static struct ethtool_rxfh_context * -ethtool_rxfh_ctx_alloc(const struct ethtool_ops *ops, - u32 indir_size, u32 key_size) -{ - size_t indir_bytes, flex_len, key_off, size; - struct ethtool_rxfh_context *ctx; - u32 priv_bytes, indir_max; - u16 key_max; - - key_max = max(key_size, ops->rxfh_key_space); - indir_max = max(indir_size, ops->rxfh_indir_space); - - priv_bytes = ALIGN(ops->rxfh_priv_size, sizeof(u32)); - indir_bytes = array_size(indir_max, sizeof(u32)); - - key_off = size_add(priv_bytes, indir_bytes); - flex_len = size_add(key_off, key_max); - size = struct_size_t(struct ethtool_rxfh_context, data, flex_len); - - ctx = kzalloc(size, GFP_KERNEL_ACCOUNT); - if (!ctx) - return NULL; - - ctx->indir_size = indir_size; - ctx->key_size = key_size; - ctx->key_off = key_off; - ctx->priv_size = ops->rxfh_priv_size; - - ctx->hfunc = ETH_RSS_HASH_NO_CHANGE; - ctx->input_xfrm = RXH_XFRM_NO_CHANGE; - - return ctx; -} - static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, void __user *useraddr) { @@ -1522,8 +1486,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; bool create = false; - bool mod = false; u8 *rss_config; + int ntf = 0; int ret; if (!ops->get_rxnfc || !ops->set_rxfh) @@ -1673,20 +1637,25 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, rxfh_dev.input_xfrm = rxfh.input_xfrm; if (!rxfh.rss_context) { + ntf = ETHTOOL_MSG_RSS_NTF; ret = ops->set_rxfh(dev, &rxfh_dev, extack); } else if (create) { + ntf = ETHTOOL_MSG_RSS_CREATE_NTF; ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev, extack); /* Make sure driver populates defaults */ WARN_ON_ONCE(!ret && !rxfh_dev.key && ops->rxfh_per_ctx_key && !memchr_inv(ethtool_rxfh_context_key(ctx), 0, ctx->key_size)); } else if (rxfh_dev.rss_delete) { + ntf = ETHTOOL_MSG_RSS_DELETE_NTF; ret = ops->remove_rxfh_context(dev, ctx, rxfh.rss_context, extack); } else { + ntf = ETHTOOL_MSG_RSS_NTF; ret = ops->modify_rxfh_context(dev, ctx, &rxfh_dev, extack); } if (ret) { + ntf = 0; if (create) { /* failed to create, free our new tracking entry */ xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context); @@ -1694,7 +1663,6 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, } goto out_unlock; } - mod = !create && !rxfh_dev.rss_delete; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context), &rxfh_dev.rss_context, sizeof(rxfh_dev.rss_context))) @@ -1734,8 +1702,8 @@ out_unlock: mutex_unlock(&dev->ethtool->rss_lock); out_free: kfree(rss_config); - if (mod) - ethtool_rss_notify(dev, rxfh.rss_context); + if (ntf) + ethtool_rss_notify(dev, ntf, rxfh.rss_context); return ret; } diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index b1f8999c1adc..2f813f25f07e 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -81,6 +81,12 @@ static void ethnl_sock_priv_destroy(void *priv) } } +u32 ethnl_bcast_seq_next(void) +{ + ASSERT_RTNL(); + return ++ethnl_bcast_seq; +} + int ethnl_ops_begin(struct net_device *dev) { int ret; @@ -405,6 +411,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, [ETHTOOL_MSG_PSE_SET] = ðnl_pse_request_ops, [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, + [ETHTOOL_MSG_RSS_SET] = ðnl_rss_request_ops, [ETHTOOL_MSG_PLCA_GET_CFG] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_PLCA_SET_CFG] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_PLCA_GET_STATUS] = ðnl_plca_status_request_ops, @@ -953,6 +960,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_PLCA_NTF] = ðnl_plca_cfg_request_ops, [ETHTOOL_MSG_MM_NTF] = ðnl_mm_request_ops, [ETHTOOL_MSG_RSS_NTF] = ðnl_rss_request_ops, + [ETHTOOL_MSG_RSS_CREATE_NTF] = ðnl_rss_request_ops, }; /* default notification handler */ @@ -1060,6 +1068,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_PLCA_NTF] = ethnl_default_notify, [ETHTOOL_MSG_MM_NTF] = ethnl_default_notify, [ETHTOOL_MSG_RSS_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_RSS_CREATE_NTF] = ethnl_default_notify, }; void ethnl_notify(struct net_device *dev, unsigned int cmd, @@ -1504,6 +1513,27 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_tsconfig_set_policy, .maxattr = ARRAY_SIZE(ethnl_tsconfig_set_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_RSS_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_default_set_doit, + .policy = ethnl_rss_set_policy, + .maxattr = ARRAY_SIZE(ethnl_rss_set_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_RSS_CREATE_ACT, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_rss_create_doit, + .policy = ethnl_rss_create_policy, + .maxattr = ARRAY_SIZE(ethnl_rss_create_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_RSS_DELETE_ACT, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_rss_delete_doit, + .policy = ethnl_rss_delete_policy, + .maxattr = ARRAY_SIZE(ethnl_rss_delete_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 94a7eb402022..1d4f9ecb3d26 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -10,6 +10,7 @@ struct ethnl_req_info; +u32 ethnl_bcast_seq_next(void); int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info, const struct nlattr *nest, struct net *net, struct netlink_ext_ack *extack, @@ -484,6 +485,9 @@ extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MO extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_START_CONTEXT + 1]; +extern const struct nla_policy ethnl_rss_set_policy[ETHTOOL_A_RSS_FLOW_HASH + 1]; +extern const struct nla_policy ethnl_rss_create_policy[ETHTOOL_A_RSS_INPUT_XFRM + 1]; +extern const struct nla_policy ethnl_rss_delete_policy[ETHTOOL_A_RSS_CONTEXT + 1]; extern const struct nla_policy ethnl_plca_get_cfg_policy[ETHTOOL_A_PLCA_HEADER + 1]; extern const struct nla_policy ethnl_plca_set_cfg_policy[ETHTOOL_A_PLCA_MAX + 1]; extern const struct nla_policy ethnl_plca_get_status_policy[ETHTOOL_A_PLCA_HEADER + 1]; @@ -506,6 +510,8 @@ int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_tsinfo_start(struct netlink_callback *cb); int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_tsinfo_done(struct netlink_callback *cb); +int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info); +int ethnl_rss_delete_doit(struct sk_buff *skb, struct genl_info *info); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 41ab9fc67652..992e98abe9dd 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -113,21 +113,11 @@ rss_prepare_flow_hash(const struct rss_req_info *req, struct net_device *dev, } static int -rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, - struct rss_reply_data *data, const struct genl_info *info) +rss_get_data_alloc(struct net_device *dev, struct rss_reply_data *data) { - struct ethtool_rxfh_param rxfh = {}; - const struct ethtool_ops *ops; + const struct ethtool_ops *ops = dev->ethtool_ops; u32 total_size, indir_bytes; u8 *rss_config; - int ret; - - ops = dev->ethtool_ops; - - ret = ethnl_ops_begin(dev); - if (ret < 0) - return ret; - mutex_lock(&dev->ethtool->rss_lock); data->indir_size = 0; data->hkey_size = 0; @@ -139,16 +129,39 @@ rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, indir_bytes = data->indir_size * sizeof(u32); total_size = indir_bytes + data->hkey_size; rss_config = kzalloc(total_size, GFP_KERNEL); - if (!rss_config) { - ret = -ENOMEM; - goto out_unlock; - } + if (!rss_config) + return -ENOMEM; if (data->indir_size) data->indir_table = (u32 *)rss_config; if (data->hkey_size) data->hkey = rss_config + indir_bytes; + return 0; +} + +static void rss_get_data_free(const struct rss_reply_data *data) +{ + kfree(data->indir_table); +} + +static int +rss_prepare_get(const struct rss_req_info *request, struct net_device *dev, + struct rss_reply_data *data, const struct genl_info *info) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxfh_param rxfh = {}; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + mutex_lock(&dev->ethtool->rss_lock); + + ret = rss_get_data_alloc(dev, data); + if (ret) + goto out_unlock; + rxfh.indir_size = data->indir_size; rxfh.indir = data->indir_table; rxfh.key_size = data->hkey_size; @@ -166,6 +179,25 @@ out_unlock: return ret; } +static void +__rss_prepare_ctx(struct net_device *dev, struct rss_reply_data *data, + struct ethtool_rxfh_context *ctx) +{ + if (WARN_ON_ONCE(data->indir_size != ctx->indir_size || + data->hkey_size != ctx->key_size)) + return; + + data->no_key_fields = !dev->ethtool_ops->rxfh_per_ctx_key; + + data->hfunc = ctx->hfunc; + data->input_xfrm = ctx->input_xfrm; + memcpy(data->indir_table, ethtool_rxfh_context_indir(ctx), + data->indir_size * sizeof(u32)); + if (data->hkey_size) + memcpy(data->hkey, ethtool_rxfh_context_key(ctx), + data->hkey_size); +} + static int rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, struct rss_reply_data *data, const struct genl_info *info) @@ -175,8 +207,6 @@ rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, u8 *rss_config; int ret; - data->no_key_fields = !dev->ethtool_ops->rxfh_per_ctx_key; - mutex_lock(&dev->ethtool->rss_lock); ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context); if (!ctx) { @@ -186,8 +216,6 @@ rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, data->indir_size = ctx->indir_size; data->hkey_size = ctx->key_size; - data->hfunc = ctx->hfunc; - data->input_xfrm = ctx->input_xfrm; indir_bytes = data->indir_size * sizeof(u32); total_size = indir_bytes + data->hkey_size; @@ -198,13 +226,10 @@ rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, } data->indir_table = (u32 *)rss_config; - memcpy(data->indir_table, ethtool_rxfh_context_indir(ctx), indir_bytes); - - if (data->hkey_size) { + if (data->hkey_size) data->hkey = rss_config + indir_bytes; - memcpy(data->hkey, ethtool_rxfh_context_key(ctx), - data->hkey_size); - } + + __rss_prepare_ctx(dev, data, ctx); ret = 0; out_unlock: @@ -218,6 +243,10 @@ rss_prepare(const struct rss_req_info *request, struct net_device *dev, { rss_prepare_flow_hash(request, dev, data, info); + /* Coming from RSS_SET, driver may only have flow_hash_fields ops */ + if (!dev->ethtool_ops->get_rxfh) + return 0; + if (request->rss_context) return rss_prepare_ctx(request, dev, data, info); return rss_prepare_get(request, dev, data, info); @@ -314,7 +343,7 @@ static void rss_cleanup_data(struct ethnl_reply_data *reply_base) { const struct rss_reply_data *data = RSS_REPDATA(reply_base); - kfree(data->indir_table); + rss_get_data_free(data); } struct rss_nl_dump_ctx { @@ -457,13 +486,430 @@ int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb) /* RSS_NTF */ -void ethtool_rss_notify(struct net_device *dev, u32 rss_context) +static void ethnl_rss_delete_notify(struct net_device *dev, u32 rss_context) +{ + struct sk_buff *ntf; + size_t ntf_size; + void *hdr; + + ntf_size = ethnl_reply_header_size() + + nla_total_size(sizeof(u32)); /* _RSS_CONTEXT */ + + ntf = genlmsg_new(ntf_size, GFP_KERNEL); + if (!ntf) + goto out_warn; + + hdr = ethnl_bcastmsg_put(ntf, ETHTOOL_MSG_RSS_DELETE_NTF); + if (!hdr) + goto out_free_ntf; + + if (ethnl_fill_reply_header(ntf, dev, ETHTOOL_A_RSS_HEADER) || + nla_put_u32(ntf, ETHTOOL_A_RSS_CONTEXT, rss_context)) + goto out_free_ntf; + + genlmsg_end(ntf, hdr); + if (ethnl_multicast(ntf, dev)) + goto out_warn; + + return; + +out_free_ntf: + nlmsg_free(ntf); +out_warn: + pr_warn_once("Failed to send a RSS delete notification"); +} + +void ethtool_rss_notify(struct net_device *dev, u32 type, u32 rss_context) { struct rss_req_info req_info = { .rss_context = rss_context, }; - ethnl_notify(dev, ETHTOOL_MSG_RSS_NTF, &req_info.base); + if (type == ETHTOOL_MSG_RSS_DELETE_NTF) + ethnl_rss_delete_notify(dev, rss_context); + else + ethnl_notify(dev, type, &req_info.base); +} + +/* RSS_SET */ + +#define RFH_MASK (RXH_L2DA | RXH_VLAN | RXH_IP_SRC | RXH_IP_DST | \ + RXH_L3_PROTO | RXH_L4_B_0_1 | RXH_L4_B_2_3 | \ + RXH_GTP_TEID | RXH_DISCARD) + +static const struct nla_policy ethnl_rss_flows_policy[] = { + [ETHTOOL_A_FLOW_ETHER] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_IP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_IP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_TCP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_UDP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_SCTP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_AH_ESP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_TCP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_UDP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_SCTP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_AH_ESP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_AH4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_ESP4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_AH6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_ESP6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPC4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPC6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPC_TEID4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPC_TEID6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_EH4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_EH6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_UL4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_UL6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_DL4] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), + [ETHTOOL_A_FLOW_GTPU_DL6] = NLA_POLICY_MASK(NLA_UINT, RFH_MASK), +}; + +const struct nla_policy ethnl_rss_set_policy[ETHTOOL_A_RSS_FLOW_HASH + 1] = { + [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32, }, + [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RSS_INDIR] = { .type = NLA_BINARY, }, + [ETHTOOL_A_RSS_HKEY] = NLA_POLICY_MIN(NLA_BINARY, 1), + [ETHTOOL_A_RSS_INPUT_XFRM] = + NLA_POLICY_MAX(NLA_U32, RXH_XFRM_SYM_OR_XOR), + [ETHTOOL_A_RSS_FLOW_HASH] = NLA_POLICY_NESTED(ethnl_rss_flows_policy), +}; + +static int +ethnl_rss_set_validate(struct ethnl_req_info *req_info, struct genl_info *info) +{ + const struct ethtool_ops *ops = req_info->dev->ethtool_ops; + struct rss_req_info *request = RSS_REQINFO(req_info); + struct nlattr **tb = info->attrs; + struct nlattr *bad_attr = NULL; + u32 input_xfrm; + + if (request->rss_context && !ops->create_rxfh_context) + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_CONTEXT]; + + if (request->rss_context && !ops->rxfh_per_ctx_key) { + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_HFUNC]; + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_HKEY]; + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_INPUT_XFRM]; + } + + input_xfrm = nla_get_u32_default(tb[ETHTOOL_A_RSS_INPUT_XFRM], 0); + if (input_xfrm & ~ops->supported_input_xfrm) + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_INPUT_XFRM]; + + if (tb[ETHTOOL_A_RSS_FLOW_HASH] && !ops->set_rxfh_fields) + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_FLOW_HASH]; + if (request->rss_context && + tb[ETHTOOL_A_RSS_FLOW_HASH] && !ops->rxfh_per_ctx_fields) + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_FLOW_HASH]; + + if (bad_attr) { + NL_SET_BAD_ATTR(info->extack, bad_attr); + return -EOPNOTSUPP; + } + + return 1; +} + +static int +rss_set_prep_indir(struct net_device *dev, struct genl_info *info, + struct rss_reply_data *data, struct ethtool_rxfh_param *rxfh, + bool *reset, bool *mod) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct netlink_ext_ack *extack = info->extack; + struct nlattr **tb = info->attrs; + struct ethtool_rxnfc rx_rings; + size_t alloc_size; + u32 user_size; + int i, err; + + if (!tb[ETHTOOL_A_RSS_INDIR]) + return 0; + if (!data->indir_size || !ops->get_rxnfc) + return -EOPNOTSUPP; + + rx_rings.cmd = ETHTOOL_GRXRINGS; + err = ops->get_rxnfc(dev, &rx_rings, NULL); + if (err) + return err; + + if (nla_len(tb[ETHTOOL_A_RSS_INDIR]) % 4) { + NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_INDIR]); + return -EINVAL; + } + user_size = nla_len(tb[ETHTOOL_A_RSS_INDIR]) / 4; + if (!user_size) { + if (rxfh->rss_context) { + NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_RSS_INDIR], + "can't reset table for a context"); + return -EINVAL; + } + *reset = true; + } else if (data->indir_size % user_size) { + NL_SET_ERR_MSG_ATTR_FMT(extack, tb[ETHTOOL_A_RSS_INDIR], + "size (%d) mismatch with device indir table (%d)", + user_size, data->indir_size); + return -EINVAL; + } + + rxfh->indir_size = data->indir_size; + alloc_size = array_size(data->indir_size, sizeof(rxfh->indir[0])); + rxfh->indir = kzalloc(alloc_size, GFP_KERNEL); + if (!rxfh->indir) + return -ENOMEM; + + nla_memcpy(rxfh->indir, tb[ETHTOOL_A_RSS_INDIR], alloc_size); + for (i = 0; i < user_size; i++) { + if (rxfh->indir[i] < rx_rings.data) + continue; + + NL_SET_ERR_MSG_ATTR_FMT(extack, tb[ETHTOOL_A_RSS_INDIR], + "entry %d: queue out of range (%d)", + i, rxfh->indir[i]); + err = -EINVAL; + goto err_free; + } + + if (user_size) { + /* Replicate the user-provided table to fill the device table */ + for (i = user_size; i < data->indir_size; i++) + rxfh->indir[i] = rxfh->indir[i % user_size]; + } else { + for (i = 0; i < data->indir_size; i++) + rxfh->indir[i] = + ethtool_rxfh_indir_default(i, rx_rings.data); + } + + *mod |= memcmp(rxfh->indir, data->indir_table, data->indir_size); + + return 0; + +err_free: + kfree(rxfh->indir); + rxfh->indir = NULL; + return err; +} + +static int +rss_set_prep_hkey(struct net_device *dev, struct genl_info *info, + struct rss_reply_data *data, struct ethtool_rxfh_param *rxfh, + bool *mod) +{ + struct nlattr **tb = info->attrs; + + if (!tb[ETHTOOL_A_RSS_HKEY]) + return 0; + + if (nla_len(tb[ETHTOOL_A_RSS_HKEY]) != data->hkey_size) { + NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_HKEY]); + return -EINVAL; + } + + rxfh->key_size = data->hkey_size; + rxfh->key = kmemdup(data->hkey, data->hkey_size, GFP_KERNEL); + if (!rxfh->key) + return -ENOMEM; + + ethnl_update_binary(rxfh->key, rxfh->key_size, tb[ETHTOOL_A_RSS_HKEY], + mod); + return 0; +} + +static int +rss_check_rxfh_fields_sym(struct net_device *dev, struct genl_info *info, + struct rss_reply_data *data, bool xfrm_sym) +{ + struct nlattr **tb = info->attrs; + int i; + + if (!xfrm_sym) + return 0; + if (!data->has_flow_hash) { + NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_RSS_INPUT_XFRM], + "hash field config not reported"); + return -EINVAL; + } + + for (i = 1; i < __ETHTOOL_A_FLOW_CNT; i++) + if (data->flow_hash[i] >= 0 && + !ethtool_rxfh_config_is_sym(data->flow_hash[i])) { + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RSS_INPUT_XFRM], + "hash field config is not symmetric"); + return -EINVAL; + } + + return 0; +} + +static int +ethnl_set_rss_fields(struct net_device *dev, struct genl_info *info, + u32 rss_context, struct rss_reply_data *data, + bool xfrm_sym, bool *mod) +{ + struct nlattr *flow_nest = info->attrs[ETHTOOL_A_RSS_FLOW_HASH]; + struct nlattr *flows[ETHTOOL_A_FLOW_MAX + 1]; + const struct ethtool_ops *ops; + int i, ret; + + ops = dev->ethtool_ops; + + ret = rss_check_rxfh_fields_sym(dev, info, data, xfrm_sym); + if (ret) + return ret; + + if (!flow_nest) + return 0; + + ret = nla_parse_nested(flows, ARRAY_SIZE(ethnl_rss_flows_policy) - 1, + flow_nest, ethnl_rss_flows_policy, info->extack); + if (ret < 0) + return ret; + + for (i = 1; i < __ETHTOOL_A_FLOW_CNT; i++) { + struct ethtool_rxfh_fields fields = { + .flow_type = ethtool_rxfh_ft_nl2ioctl[i], + .rss_context = rss_context, + }; + + if (!flows[i]) + continue; + + fields.data = nla_get_u32(flows[i]); + if (data->has_flow_hash && data->flow_hash[i] == fields.data) + continue; + + if (xfrm_sym && !ethtool_rxfh_config_is_sym(fields.data)) { + NL_SET_ERR_MSG_ATTR(info->extack, flows[i], + "conflict with xfrm-input"); + return -EINVAL; + } + + ret = ops->set_rxfh_fields(dev, &fields, info->extack); + if (ret) + return ret; + + *mod = true; + } + + return 0; +} + +static void +rss_set_ctx_update(struct ethtool_rxfh_context *ctx, struct nlattr **tb, + struct rss_reply_data *data, struct ethtool_rxfh_param *rxfh) +{ + int i; + + if (rxfh->indir) { + for (i = 0; i < data->indir_size; i++) + ethtool_rxfh_context_indir(ctx)[i] = rxfh->indir[i]; + ctx->indir_configured = !!nla_len(tb[ETHTOOL_A_RSS_INDIR]); + } + if (rxfh->key) { + memcpy(ethtool_rxfh_context_key(ctx), rxfh->key, + data->hkey_size); + ctx->key_configured = !!rxfh->key_size; + } + if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE) + ctx->hfunc = rxfh->hfunc; + if (rxfh->input_xfrm != RXH_XFRM_NO_CHANGE) + ctx->input_xfrm = rxfh->input_xfrm; +} + +static int +ethnl_rss_set(struct ethnl_req_info *req_info, struct genl_info *info) +{ + bool indir_reset = false, indir_mod, xfrm_sym = false; + struct rss_req_info *request = RSS_REQINFO(req_info); + struct ethtool_rxfh_context *ctx = NULL; + struct net_device *dev = req_info->dev; + bool mod = false, fields_mod = false; + struct ethtool_rxfh_param rxfh = {}; + struct nlattr **tb = info->attrs; + struct rss_reply_data data = {}; + const struct ethtool_ops *ops; + int ret; + + ops = dev->ethtool_ops; + data.base.dev = dev; + + ret = rss_prepare(request, dev, &data, info); + if (ret) + return ret; + + rxfh.rss_context = request->rss_context; + + ret = rss_set_prep_indir(dev, info, &data, &rxfh, &indir_reset, &mod); + if (ret) + goto exit_clean_data; + indir_mod = !!tb[ETHTOOL_A_RSS_INDIR]; + + rxfh.hfunc = data.hfunc; + ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); + if (rxfh.hfunc == data.hfunc) + rxfh.hfunc = ETH_RSS_HASH_NO_CHANGE; + + ret = rss_set_prep_hkey(dev, info, &data, &rxfh, &mod); + if (ret) + goto exit_free_indir; + + rxfh.input_xfrm = data.input_xfrm; + ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); + /* For drivers which don't support input_xfrm it will be set to 0xff + * in the RSS context info. In all other case input_xfrm != 0 means + * symmetric hashing is requested. + */ + if (!request->rss_context || ops->rxfh_per_ctx_key) + xfrm_sym = rxfh.input_xfrm || data.input_xfrm; + if (rxfh.input_xfrm == data.input_xfrm) + rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; + + mutex_lock(&dev->ethtool->rss_lock); + if (request->rss_context) { + ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context); + if (!ctx) { + ret = -ENOENT; + goto exit_unlock; + } + } + + ret = ethnl_set_rss_fields(dev, info, request->rss_context, + &data, xfrm_sym, &fields_mod); + if (ret) + goto exit_unlock; + + if (!mod) + ret = 0; /* nothing to tell the driver */ + else if (!ops->set_rxfh) + ret = -EOPNOTSUPP; + else if (!rxfh.rss_context) + ret = ops->set_rxfh(dev, &rxfh, info->extack); + else + ret = ops->modify_rxfh_context(dev, ctx, &rxfh, info->extack); + if (ret) + goto exit_unlock; + + if (ctx) + rss_set_ctx_update(ctx, tb, &data, &rxfh); + else if (indir_reset) + dev->priv_flags &= ~IFF_RXFH_CONFIGURED; + else if (indir_mod) + dev->priv_flags |= IFF_RXFH_CONFIGURED; + +exit_unlock: + mutex_unlock(&dev->ethtool->rss_lock); + kfree(rxfh.key); +exit_free_indir: + kfree(rxfh.indir); +exit_clean_data: + rss_cleanup_data(&data.base); + + return ret ?: mod || fields_mod; } const struct ethnl_request_ops ethnl_rss_request_ops = { @@ -478,4 +924,282 @@ const struct ethnl_request_ops ethnl_rss_request_ops = { .reply_size = rss_reply_size, .fill_reply = rss_fill_reply, .cleanup_data = rss_cleanup_data, + + .set_validate = ethnl_rss_set_validate, + .set = ethnl_rss_set, + .set_ntf_cmd = ETHTOOL_MSG_RSS_NTF, +}; + +/* RSS_CREATE */ + +const struct nla_policy ethnl_rss_create_policy[ETHTOOL_A_RSS_INPUT_XFRM + 1] = { + [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_RSS_CONTEXT] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RSS_HFUNC] = NLA_POLICY_MIN(NLA_U32, 1), + [ETHTOOL_A_RSS_INDIR] = NLA_POLICY_MIN(NLA_BINARY, 1), + [ETHTOOL_A_RSS_HKEY] = NLA_POLICY_MIN(NLA_BINARY, 1), + [ETHTOOL_A_RSS_INPUT_XFRM] = + NLA_POLICY_MAX(NLA_U32, RXH_XFRM_SYM_OR_XOR), +}; + +static int +ethnl_rss_create_validate(struct net_device *dev, struct genl_info *info) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + struct nlattr **tb = info->attrs; + struct nlattr *bad_attr = NULL; + u32 rss_context, input_xfrm; + + if (!ops->create_rxfh_context) + return -EOPNOTSUPP; + + rss_context = nla_get_u32_default(tb[ETHTOOL_A_RSS_CONTEXT], 0); + if (ops->rxfh_max_num_contexts && + ops->rxfh_max_num_contexts <= rss_context) { + NL_SET_BAD_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT]); + return -ERANGE; + } + + if (!ops->rxfh_per_ctx_key) { + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_HFUNC]; + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_HKEY]; + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_INPUT_XFRM]; + } + + input_xfrm = nla_get_u32_default(tb[ETHTOOL_A_RSS_INPUT_XFRM], 0); + if (input_xfrm & ~ops->supported_input_xfrm) + bad_attr = bad_attr ?: tb[ETHTOOL_A_RSS_INPUT_XFRM]; + + if (bad_attr) { + NL_SET_BAD_ATTR(info->extack, bad_attr); + return -EOPNOTSUPP; + } + + return 0; +} + +static void +ethnl_rss_create_send_ntf(struct sk_buff *rsp, struct net_device *dev) +{ + struct nlmsghdr *nlh = (void *)rsp->data; + struct genlmsghdr *genl_hdr; + + /* Convert the reply into a notification */ + nlh->nlmsg_pid = 0; + nlh->nlmsg_seq = ethnl_bcast_seq_next(); + + genl_hdr = nlmsg_data(nlh); + genl_hdr->cmd = ETHTOOL_MSG_RSS_CREATE_NTF; + + ethnl_multicast(rsp, dev); +} + +int ethnl_rss_create_doit(struct sk_buff *skb, struct genl_info *info) +{ + bool indir_dflt = false, mod = false, ntf_fail = false; + struct ethtool_rxfh_param rxfh = {}; + struct ethtool_rxfh_context *ctx; + struct nlattr **tb = info->attrs; + struct rss_reply_data data = {}; + const struct ethtool_ops *ops; + struct rss_req_info req = {}; + struct net_device *dev; + struct sk_buff *rsp; + void *hdr; + u32 limit; + int ret; + + rsp = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + ret = ethnl_parse_header_dev_get(&req.base, tb[ETHTOOL_A_RSS_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + goto exit_free_rsp; + + dev = req.base.dev; + ops = dev->ethtool_ops; + + req.rss_context = nla_get_u32_default(tb[ETHTOOL_A_RSS_CONTEXT], 0); + + ret = ethnl_rss_create_validate(dev, info); + if (ret) + goto exit_free_dev; + + rtnl_lock(); + netdev_lock_ops(dev); + + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto exit_dev_unlock; + + ret = rss_get_data_alloc(dev, &data); + if (ret) + goto exit_ops; + + ret = rss_set_prep_indir(dev, info, &data, &rxfh, &indir_dflt, &mod); + if (ret) + goto exit_clean_data; + + ethnl_update_u8(&rxfh.hfunc, tb[ETHTOOL_A_RSS_HFUNC], &mod); + + ret = rss_set_prep_hkey(dev, info, &data, &rxfh, &mod); + if (ret) + goto exit_free_indir; + + rxfh.input_xfrm = RXH_XFRM_NO_CHANGE; + ethnl_update_u8(&rxfh.input_xfrm, tb[ETHTOOL_A_RSS_INPUT_XFRM], &mod); + + ctx = ethtool_rxfh_ctx_alloc(ops, data.indir_size, data.hkey_size); + if (!ctx) { + ret = -ENOMEM; + goto exit_free_hkey; + } + + mutex_lock(&dev->ethtool->rss_lock); + if (!req.rss_context) { + limit = ops->rxfh_max_num_contexts ?: U32_MAX; + ret = xa_alloc(&dev->ethtool->rss_ctx, &req.rss_context, ctx, + XA_LIMIT(1, limit - 1), GFP_KERNEL_ACCOUNT); + } else { + ret = xa_insert(&dev->ethtool->rss_ctx, + req.rss_context, ctx, GFP_KERNEL_ACCOUNT); + } + if (ret < 0) { + NL_SET_ERR_MSG_ATTR(info->extack, tb[ETHTOOL_A_RSS_CONTEXT], + "error allocating context ID"); + goto err_unlock_free_ctx; + } + rxfh.rss_context = req.rss_context; + + ret = ops->create_rxfh_context(dev, ctx, &rxfh, info->extack); + if (ret) + goto err_ctx_id_free; + + /* Make sure driver populates defaults */ + WARN_ON_ONCE(!rxfh.key && ops->rxfh_per_ctx_key && + !memchr_inv(ethtool_rxfh_context_key(ctx), 0, + ctx->key_size)); + + /* Store the config from rxfh to Xarray.. */ + rss_set_ctx_update(ctx, tb, &data, &rxfh); + /* .. copy from Xarray to data. */ + __rss_prepare_ctx(dev, &data, ctx); + + hdr = ethnl_unicast_put(rsp, info->snd_portid, info->snd_seq, + ETHTOOL_MSG_RSS_CREATE_ACT_REPLY); + ntf_fail = ethnl_fill_reply_header(rsp, dev, ETHTOOL_A_RSS_HEADER); + ntf_fail |= rss_fill_reply(rsp, &req.base, &data.base); + if (WARN_ON(!hdr || ntf_fail)) { + ret = -EMSGSIZE; + goto exit_unlock; + } + + genlmsg_end(rsp, hdr); + + /* Use the same skb for the response and the notification, + * genlmsg_reply() will copy the skb if it has elevated user count. + */ + skb_get(rsp); + ret = genlmsg_reply(rsp, info); + ethnl_rss_create_send_ntf(rsp, dev); + rsp = NULL; + +exit_unlock: + mutex_unlock(&dev->ethtool->rss_lock); +exit_free_hkey: + kfree(rxfh.key); +exit_free_indir: + kfree(rxfh.indir); +exit_clean_data: + rss_get_data_free(&data); +exit_ops: + ethnl_ops_complete(dev); +exit_dev_unlock: + netdev_unlock_ops(dev); + rtnl_unlock(); +exit_free_dev: + ethnl_parse_header_dev_put(&req.base); +exit_free_rsp: + nlmsg_free(rsp); + return ret; + +err_ctx_id_free: + xa_erase(&dev->ethtool->rss_ctx, req.rss_context); +err_unlock_free_ctx: + kfree(ctx); + goto exit_unlock; +} + +/* RSS_DELETE */ + +const struct nla_policy ethnl_rss_delete_policy[ETHTOOL_A_RSS_CONTEXT + 1] = { + [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_RSS_CONTEXT] = NLA_POLICY_MIN(NLA_U32, 1), }; + +int ethnl_rss_delete_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct ethtool_rxfh_context *ctx; + struct nlattr **tb = info->attrs; + struct ethnl_req_info req = {}; + const struct ethtool_ops *ops; + struct net_device *dev; + u32 rss_context; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, ETHTOOL_A_RSS_CONTEXT)) + return -EINVAL; + rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]); + + ret = ethnl_parse_header_dev_get(&req, tb[ETHTOOL_A_RSS_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + + dev = req.dev; + ops = dev->ethtool_ops; + + if (!ops->create_rxfh_context) + goto exit_free_dev; + + rtnl_lock(); + netdev_lock_ops(dev); + + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto exit_dev_unlock; + + mutex_lock(&dev->ethtool->rss_lock); + ret = ethtool_check_rss_ctx_busy(dev, rss_context); + if (ret) + goto exit_unlock; + + ctx = xa_load(&dev->ethtool->rss_ctx, rss_context); + if (!ctx) { + ret = -ENOENT; + goto exit_unlock; + } + + ret = ops->remove_rxfh_context(dev, ctx, rss_context, info->extack); + if (ret) + goto exit_unlock; + + WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rss_context) != ctx); + kfree(ctx); + + ethnl_rss_delete_notify(dev, rss_context); + +exit_unlock: + mutex_unlock(&dev->ethtool->rss_lock); + ethnl_ops_complete(dev); +exit_dev_unlock: + netdev_unlock_ops(dev); + rtnl_unlock(); +exit_free_dev: + ethnl_parse_header_dev_put(&req); + return ret; +} diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index c0440d61cf2f..5cfc1c939673 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -864,7 +864,7 @@ static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || (rt->dst.dev != dev && - pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))) { + pneigh_lookup(&arp_tbl, net, &tip, dev)))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); @@ -1089,9 +1089,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, if (mask) { __be32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1)) - return -ENOBUFS; - return 0; + return pneigh_create(&arp_tbl, net, &ip, dev, 0, 0, false); } return arp_req_set_proxy(net, dev, 1); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fd1e1507a224..6e1b94796f67 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1524,7 +1524,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_disable_ip(dev, event, false); break; case NETDEV_CHANGE: - flags = dev_get_flags(dev); + flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) fib_sync_up(dev, RTNH_F_LINKDOWN); else diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a2f04992f579..a5f3c8459758 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -2087,7 +2087,7 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags) return 0; if (nh_flags & RTNH_F_DEAD) { - unsigned int flags = dev_get_flags(dev); + unsigned int flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) nh_flags |= RTNH_F_LINKDOWN; diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 5a4fb2539b08..9a45aed508d1 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -54,6 +54,7 @@ static int ipcomp4_err(struct sk_buff *skb, u32 info) } /* We always hold one tunnel user reference to indicate a tunnel */ +static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -62,6 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) t = xfrm_state_alloc(net); if (!t) goto out; + lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPIP; t->id.spi = x->props.saddr.a4; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3a2044e6033d..e86a8a862c41 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -901,7 +901,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); - err = dev_get_port_parent_id(dev, &ppid, true); + err = netif_get_port_parent_id(dev, &ppid, true); if (err == 0) { memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); v->dev_parent_id.id_len = ppid.id_len; diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index e808801ab9b8..29118c43ebf5 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -3884,7 +3884,7 @@ static int nh_netdev_event(struct notifier_block *this, nexthop_flush_dev(dev, event); break; case NETDEV_CHANGE: - if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) + if (!(netif_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP))) nexthop_flush_dev(dev, event); break; case NETDEV_CHANGEMTU: diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 31149a0ac849..71a956fbfc55 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3751,6 +3751,19 @@ int tcp_set_window_clamp(struct sock *sk, int val) return 0; } +int tcp_sock_set_maxseg(struct sock *sk, int val) +{ + /* Values greater than interface MTU won't take effect. However + * at the point when this call is done we typically don't yet + * know which interface is going to be used + */ + if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) + return -EINVAL; + + tcp_sk(sk)->rx_opt.user_mss = val; + return 0; +} + /* * Socket option code for TCP. */ @@ -3883,15 +3896,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case TCP_MAXSEG: - /* Values greater than interface MTU won't take effect. However - * at the point when this call is done we typically don't yet - * know which interface is going to be used - */ - if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) { - err = -EINVAL; - break; - } - tp->rx_opt.user_mss = val; + err = tcp_sock_set_maxseg(sk, val); break; case TCP_NODELAY: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 672cbfbdcec1..71b76e98371a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5549,6 +5549,10 @@ static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb) { struct tcp_sock *tp = tcp_sk(sk); + /* Do nothing if our queues are empty. */ + if (!atomic_read(&sk->sk_rmem_alloc)) + return -1; + NET_INC_STATS(sock_net(sk), LINUX_MIB_PRUNECALLED); if (!tcp_can_ingest(sk, in_skb)) @@ -5911,7 +5915,11 @@ step1: if (!th->rst) { if (th->syn) goto syn_challenge; - NET_INC_STATS(sock_net(sk), LINUX_MIB_BEYOND_WINDOW); + + if (reason == SKB_DROP_REASON_TCP_INVALID_SEQUENCE || + reason == SKB_DROP_REASON_TCP_INVALID_END_SEQUENCE) + NET_INC_STATS(sock_net(sk), + LINUX_MIB_BEYOND_WINDOW); if (!tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDSEQ, &tp->last_oow_ack_time)) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a847d894ace3..84d3d556ed80 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -58,6 +58,7 @@ #include <linux/times.h> #include <linux/slab.h> #include <linux/sched.h> +#include <linux/sock_diag.h> #include <net/aligned_data.h> #include <net/net_namespace.h> @@ -2025,6 +2026,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, u32 gso_size; u64 limit; int delta; + int err; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), * we can fix skb->truesize to its real value to avoid future drops. @@ -2135,21 +2137,27 @@ no_coalesce: limit = min_t(u64, limit, UINT_MAX); - if (unlikely(sk_add_backlog(sk, skb, limit))) { + err = sk_add_backlog(sk, skb, limit); + if (unlikely(err)) { bh_unlock_sock(sk); - *reason = SKB_DROP_REASON_SOCKET_BACKLOG; - __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); + if (err == -ENOMEM) { + *reason = SKB_DROP_REASON_PFMEMALLOC; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP); + } else { + *reason = SKB_DROP_REASON_SOCKET_BACKLOG; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); + } return true; } return false; } EXPORT_IPV6_MOD(tcp_add_backlog); -int tcp_filter(struct sock *sk, struct sk_buff *skb) +int tcp_filter(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason) { struct tcphdr *th = (struct tcphdr *)skb->data; - return sk_filter_trim_cap(sk, skb, th->doff * 4); + return sk_filter_trim_cap(sk, skb, th->doff * 4, reason); } EXPORT_IPV6_MOD(tcp_filter); @@ -2276,14 +2284,12 @@ lookup: } refcounted = true; nsk = NULL; - if (!tcp_filter(sk, skb)) { + if (!tcp_filter(sk, skb, &drop_reason)) { th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen, &drop_reason); - } else { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); @@ -2339,10 +2345,9 @@ process: nf_reset_ct(skb); - if (tcp_filter(sk, skb)) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + if (tcp_filter(sk, skb, &drop_reason)) goto discard_and_relse; - } + th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); @@ -3014,13 +3019,17 @@ out: } #ifdef CONFIG_BPF_SYSCALL +union bpf_tcp_iter_batch_item { + struct sock *sk; + __u64 cookie; +}; + struct bpf_tcp_iter_state { struct tcp_iter_state state; unsigned int cur_sk; unsigned int end_sk; unsigned int max_sk; - struct sock **batch; - bool st_bucket_done; + union bpf_tcp_iter_batch_item *batch; }; struct bpf_iter__tcp { @@ -3043,21 +3052,32 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { - while (iter->cur_sk < iter->end_sk) - sock_gen_put(iter->batch[iter->cur_sk++]); + union bpf_tcp_iter_batch_item *item; + unsigned int cur_sk = iter->cur_sk; + __u64 cookie; + + /* Remember the cookies of the sockets we haven't seen yet, so we can + * pick up where we left off next time around. + */ + while (cur_sk < iter->end_sk) { + item = &iter->batch[cur_sk++]; + cookie = sock_gen_cookie(item->sk); + sock_gen_put(item->sk); + item->cookie = cookie; + } } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, - unsigned int new_batch_sz) + unsigned int new_batch_sz, gfp_t flags) { - struct sock **new_batch; + union bpf_tcp_iter_batch_item *new_batch; new_batch = kvmalloc(sizeof(*new_batch) * new_batch_sz, - GFP_USER | __GFP_NOWARN); + flags | __GFP_NOWARN); if (!new_batch) return -ENOMEM; - bpf_iter_tcp_put_batch(iter); + memcpy(new_batch, iter->batch, sizeof(*iter->batch) * iter->end_sk); kvfree(iter->batch); iter->batch = new_batch; iter->max_sk = new_batch_sz; @@ -3065,112 +3085,234 @@ static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, return 0; } -static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, - struct sock *start_sk) +static struct sock *bpf_iter_tcp_resume_bucket(struct sock *first_sk, + union bpf_tcp_iter_batch_item *cookies, + int n_cookies) +{ + struct hlist_nulls_node *node; + struct sock *sk; + int i; + + for (i = 0; i < n_cookies; i++) { + sk = first_sk; + sk_nulls_for_each_from(sk, node) + if (cookies[i].cookie == atomic64_read(&sk->sk_cookie)) + return sk; + } + + return NULL; +} + +static struct sock *bpf_iter_tcp_resume_listening(struct seq_file *seq) +{ + struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + unsigned int find_cookie = iter->cur_sk; + unsigned int end_cookie = iter->end_sk; + int resume_bucket = st->bucket; + struct sock *sk; + + if (end_cookie && find_cookie == end_cookie) + ++st->bucket; + + sk = listening_get_first(seq); + iter->cur_sk = 0; + iter->end_sk = 0; + + if (sk && st->bucket == resume_bucket && end_cookie) { + sk = bpf_iter_tcp_resume_bucket(sk, &iter->batch[find_cookie], + end_cookie - find_cookie); + if (!sk) { + spin_unlock(&hinfo->lhash2[st->bucket].lock); + ++st->bucket; + sk = listening_get_first(seq); + } + } + + return sk; +} + +static struct sock *bpf_iter_tcp_resume_established(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; + unsigned int find_cookie = iter->cur_sk; + unsigned int end_cookie = iter->end_sk; + int resume_bucket = st->bucket; + struct sock *sk; + + if (end_cookie && find_cookie == end_cookie) + ++st->bucket; + + sk = established_get_first(seq); + iter->cur_sk = 0; + iter->end_sk = 0; + + if (sk && st->bucket == resume_bucket && end_cookie) { + sk = bpf_iter_tcp_resume_bucket(sk, &iter->batch[find_cookie], + end_cookie - find_cookie); + if (!sk) { + spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); + ++st->bucket; + sk = established_get_first(seq); + } + } + + return sk; +} + +static struct sock *bpf_iter_tcp_resume(struct seq_file *seq) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + struct sock *sk = NULL; + + switch (st->state) { + case TCP_SEQ_STATE_LISTENING: + sk = bpf_iter_tcp_resume_listening(seq); + if (sk) + break; + st->bucket = 0; + st->state = TCP_SEQ_STATE_ESTABLISHED; + fallthrough; + case TCP_SEQ_STATE_ESTABLISHED: + sk = bpf_iter_tcp_resume_established(seq); + break; + } + + return sk; +} + +static unsigned int bpf_iter_tcp_listening_batch(struct seq_file *seq, + struct sock **start_sk) +{ + struct bpf_tcp_iter_state *iter = seq->private; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; - sock_hold(start_sk); - iter->batch[iter->end_sk++] = start_sk; + sock_hold(*start_sk); + iter->batch[iter->end_sk++].sk = *start_sk; - sk = sk_nulls_next(start_sk); + sk = sk_nulls_next(*start_sk); + *start_sk = NULL; sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); - iter->batch[iter->end_sk++] = sk; + iter->batch[iter->end_sk++].sk = sk; + } else if (!*start_sk) { + /* Remember where we left off. */ + *start_sk = sk; } expected++; } } - spin_unlock(&hinfo->lhash2[st->bucket].lock); return expected; } static unsigned int bpf_iter_tcp_established_batch(struct seq_file *seq, - struct sock *start_sk) + struct sock **start_sk) { - struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; - struct tcp_iter_state *st = &iter->state; struct hlist_nulls_node *node; unsigned int expected = 1; struct sock *sk; - sock_hold(start_sk); - iter->batch[iter->end_sk++] = start_sk; + sock_hold(*start_sk); + iter->batch[iter->end_sk++].sk = *start_sk; - sk = sk_nulls_next(start_sk); + sk = sk_nulls_next(*start_sk); + *start_sk = NULL; sk_nulls_for_each_from(sk, node) { if (seq_sk_match(seq, sk)) { if (iter->end_sk < iter->max_sk) { sock_hold(sk); - iter->batch[iter->end_sk++] = sk; + iter->batch[iter->end_sk++].sk = sk; + } else if (!*start_sk) { + /* Remember where we left off. */ + *start_sk = sk; } expected++; } } - spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); return expected; } -static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) +static unsigned int bpf_iter_fill_batch(struct seq_file *seq, + struct sock **start_sk) +{ + struct bpf_tcp_iter_state *iter = seq->private; + struct tcp_iter_state *st = &iter->state; + + if (st->state == TCP_SEQ_STATE_LISTENING) + return bpf_iter_tcp_listening_batch(seq, start_sk); + else + return bpf_iter_tcp_established_batch(seq, start_sk); +} + +static void bpf_iter_tcp_unlock_bucket(struct seq_file *seq) { struct inet_hashinfo *hinfo = seq_file_net(seq)->ipv4.tcp_death_row.hashinfo; struct bpf_tcp_iter_state *iter = seq->private; struct tcp_iter_state *st = &iter->state; + + if (st->state == TCP_SEQ_STATE_LISTENING) + spin_unlock(&hinfo->lhash2[st->bucket].lock); + else + spin_unlock_bh(inet_ehash_lockp(hinfo, st->bucket)); +} + +static struct sock *bpf_iter_tcp_batch(struct seq_file *seq) +{ + struct bpf_tcp_iter_state *iter = seq->private; unsigned int expected; - bool resized = false; struct sock *sk; + int err; - /* The st->bucket is done. Directly advance to the next - * bucket instead of having the tcp_seek_last_pos() to skip - * one by one in the current bucket and eventually find out - * it has to advance to the next bucket. - */ - if (iter->st_bucket_done) { - st->offset = 0; - st->bucket++; - if (st->state == TCP_SEQ_STATE_LISTENING && - st->bucket > hinfo->lhash2_mask) { - st->state = TCP_SEQ_STATE_ESTABLISHED; - st->bucket = 0; - } - } + sk = bpf_iter_tcp_resume(seq); + if (!sk) + return NULL; /* Done */ -again: - /* Get a new batch */ - iter->cur_sk = 0; - iter->end_sk = 0; - iter->st_bucket_done = false; + expected = bpf_iter_fill_batch(seq, &sk); + if (likely(iter->end_sk == expected)) + goto done; - sk = tcp_seek_last_pos(seq); + /* Batch size was too small. */ + bpf_iter_tcp_unlock_bucket(seq); + bpf_iter_tcp_put_batch(iter); + err = bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2, + GFP_USER); + if (err) + return ERR_PTR(err); + + sk = bpf_iter_tcp_resume(seq); if (!sk) return NULL; /* Done */ - if (st->state == TCP_SEQ_STATE_LISTENING) - expected = bpf_iter_tcp_listening_batch(seq, sk); - else - expected = bpf_iter_tcp_established_batch(seq, sk); - - if (iter->end_sk == expected) { - iter->st_bucket_done = true; - return sk; - } + expected = bpf_iter_fill_batch(seq, &sk); + if (likely(iter->end_sk == expected)) + goto done; - if (!resized && !bpf_iter_tcp_realloc_batch(iter, expected * 3 / 2)) { - resized = true; - goto again; + /* Batch size was still too small. Hold onto the lock while we try + * again with a larger batch to make sure the current bucket's size + * does not change in the meantime. + */ + err = bpf_iter_tcp_realloc_batch(iter, expected, GFP_NOWAIT); + if (err) { + bpf_iter_tcp_unlock_bucket(seq); + return ERR_PTR(err); } - return sk; + expected = bpf_iter_fill_batch(seq, &sk); + WARN_ON_ONCE(iter->end_sk != expected); +done: + bpf_iter_tcp_unlock_bucket(seq); + return iter->batch[0].sk; } static void *bpf_iter_tcp_seq_start(struct seq_file *seq, loff_t *pos) @@ -3200,16 +3342,11 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) * meta.seq_num is used instead. */ st->num++; - /* Move st->offset to the next sk in the bucket such that - * the future start() will resume at st->offset in - * st->bucket. See tcp_seek_last_pos(). - */ - st->offset++; - sock_gen_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++].sk); } if (iter->cur_sk < iter->end_sk) - sk = iter->batch[iter->cur_sk]; + sk = iter->batch[iter->cur_sk].sk; else sk = bpf_iter_tcp_batch(seq); @@ -3275,10 +3412,8 @@ static void bpf_iter_tcp_seq_stop(struct seq_file *seq, void *v) (void)tcp_prog_seq_show(prog, &meta, v, 0); } - if (iter->cur_sk < iter->end_sk) { + if (iter->cur_sk < iter->end_sk) bpf_iter_tcp_put_batch(iter); - iter->st_bucket_done = false; - } } static const struct seq_operations bpf_iter_tcp_seq_ops = { @@ -3596,7 +3731,7 @@ static int bpf_iter_init_tcp(void *priv_data, struct bpf_iter_aux_info *aux) if (err) return err; - err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ); + err = bpf_iter_tcp_realloc_batch(iter, INIT_BATCH_SZ, GFP_USER); if (err) { bpf_iter_fini_seq_net(priv_data); return err; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b616776e3354..caf11920a878 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3330,8 +3330,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; - if (skb_still_in_host_queue(sk, skb)) - return -EBUSY; + if (skb_still_in_host_queue(sk, skb)) { + err = -EBUSY; + goto out; + } start: if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { @@ -3342,14 +3344,19 @@ start: } if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); - return -EINVAL; + err = -EINVAL; + goto out; + } + if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) { + err = -ENOMEM; + goto out; } - if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) - return -ENOMEM; } - if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) - return -EHOSTUNREACH; /* Routing failure or similar. */ + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) { + err = -EHOSTUNREACH; /* Routing failure or similar. */ + goto out; + } cur_mss = tcp_current_mss(sk); avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; @@ -3360,8 +3367,10 @@ start: * our retransmit of one segment serves as a zero window probe. */ if (avail_wnd <= 0) { - if (TCP_SKB_CB(skb)->seq != tp->snd_una) - return -EAGAIN; + if (TCP_SKB_CB(skb)->seq != tp->snd_una) { + err = -EAGAIN; + goto out; + } avail_wnd = cur_mss; } @@ -3373,11 +3382,15 @@ start: } if (skb->len > len) { if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len, - cur_mss, GFP_ATOMIC)) - return -ENOMEM; /* We'll try again later. */ + cur_mss, GFP_ATOMIC)) { + err = -ENOMEM; /* We'll try again later. */ + goto out; + } } else { - if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) - return -ENOMEM; + if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) { + err = -ENOMEM; + goto out; + } diff = tcp_skb_pcount(skb); tcp_set_skb_tso_segs(skb, cur_mss); @@ -3431,17 +3444,16 @@ start: tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); - if (likely(!err)) { - trace_tcp_retransmit_skb(sk, skb); - } else if (err != -EBUSY) { + if (unlikely(err) && err != -EBUSY) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); - } /* To avoid taking spuriously low RTT samples based on a timestamp * for a transmit that never happened, always mark EVER_RETRANS */ TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; +out: + trace_tcp_retransmit_skb(sk, skb, err); return err; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 49f43c54cfb0..cc3ce0f762ec 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2347,7 +2347,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { - int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; + enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); int is_udplite = IS_UDPLITE(sk); @@ -2436,10 +2436,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason)) goto drop; - } udp_csum_pull_header(skb); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 0d31a8c108d4..f28cfd88eaf5 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -202,6 +202,9 @@ struct sk_buff *xfrm4_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out; + /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c85b1db74b1a..4f1d7d110302 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6072,7 +6072,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, hdr->ifi_type = dev->type; ifindex = READ_ONCE(dev->ifindex); hdr->ifi_index = ifindex; - hdr->ifi_flags = dev_get_flags(dev); + hdr->ifi_flags = netif_get_flags(dev); hdr->ifi_change = 0; iflink = dev_get_iflink(dev); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index a1210fd6404e..74d49dd6124d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -111,8 +111,32 @@ static u32 HASH_ADDR(const struct in6_addr *addr) #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] -/* Given src, dst and key, find appropriate for input tunnel. */ +static bool ip6gre_tunnel_match(struct ip6_tnl *t, int dev_type, int link, + int *cand_score, struct ip6_tnl **ret) +{ + int score = 0; + + if (t->dev->type != ARPHRD_IP6GRE && + t->dev->type != dev_type) + return false; + + if (t->parms.link != link) + score |= 1; + if (t->dev->type != dev_type) + score |= 2; + if (score == 0) { + *ret = t; + return true; + } + + if (score < *cand_score) { + *ret = t; + *cand_score = score; + } + return false; +} +/* Given src, dst and key, find appropriate for input tunnel. */ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, const struct in6_addr *remote, const struct in6_addr *local, __be32 key, __be16 gre_proto) @@ -127,8 +151,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, gre_proto == htons(ETH_P_ERSPAN) || gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; - int score, cand_score = 4; struct net_device *ndev; + int cand_score = 4; for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || @@ -137,22 +161,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, !(t->dev->flags & IFF_UP)) continue; - if (t->dev->type != ARPHRD_IP6GRE && - t->dev->type != dev_type) - continue; - - score = 0; - if (t->parms.link != link) - score |= 1; - if (t->dev->type != dev_type) - score |= 2; - if (score == 0) - return t; - - if (score < cand_score) { - cand = t; - cand_score = score; - } + if (ip6gre_tunnel_match(t, dev_type, link, &cand_score, &cand)) + return cand; } for_each_ip_tunnel_rcu(t, ign->tunnels_r[h0 ^ h1]) { @@ -161,22 +171,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, !(t->dev->flags & IFF_UP)) continue; - if (t->dev->type != ARPHRD_IP6GRE && - t->dev->type != dev_type) - continue; - - score = 0; - if (t->parms.link != link) - score |= 1; - if (t->dev->type != dev_type) - score |= 2; - if (score == 0) - return t; - - if (score < cand_score) { - cand = t; - cand_score = score; - } + if (ip6gre_tunnel_match(t, dev_type, link, &cand_score, &cand)) + return cand; } for_each_ip_tunnel_rcu(t, ign->tunnels_l[h1]) { @@ -187,22 +183,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, !(t->dev->flags & IFF_UP)) continue; - if (t->dev->type != ARPHRD_IP6GRE && - t->dev->type != dev_type) - continue; - - score = 0; - if (t->parms.link != link) - score |= 1; - if (t->dev->type != dev_type) - score |= 2; - if (score == 0) - return t; - - if (score < cand_score) { - cand = t; - cand_score = score; - } + if (ip6gre_tunnel_match(t, dev_type, link, &cand_score, &cand)) + return cand; } for_each_ip_tunnel_rcu(t, ign->tunnels_wc[h1]) { @@ -210,22 +192,8 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, !(t->dev->flags & IFF_UP)) continue; - if (t->dev->type != ARPHRD_IP6GRE && - t->dev->type != dev_type) - continue; - - score = 0; - if (t->parms.link != link) - score |= 1; - if (t->dev->type != dev_type) - score |= 2; - if (score == 0) - return t; - - if (score < cand_score) { - cand = t; - cand_score = score; - } + if (ip6gre_tunnel_match(t, dev_type, link, &cand_score, &cand)) + return cand; } if (cand) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index fcc20c7250eb..0412f8544695 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -563,7 +563,7 @@ int ip6_forward(struct sk_buff *skb) /* XXX: idev->cnf.proxy_ndp? */ if (READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && - pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { + pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { /* It's tempting to decrease the hop limit diff --git a/net/ipv6/ipcomp6.c b/net/ipv6/ipcomp6.c index 72d4858dec18..8607569de34f 100644 --- a/net/ipv6/ipcomp6.c +++ b/net/ipv6/ipcomp6.c @@ -71,6 +71,7 @@ static int ipcomp6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return 0; } +static struct lock_class_key xfrm_state_lock_key; static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -79,6 +80,7 @@ static struct xfrm_state *ipcomp6_tunnel_create(struct xfrm_state *x) t = xfrm_state_alloc(net); if (!t) goto out; + lockdep_set_class(&t->lock, &xfrm_state_lock_key); t->id.proto = IPPROTO_IPV6; t->id.spi = xfrm6_tunnel_alloc_spi(net, (xfrm_address_t *)&x->props.saddr); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d4c5876e1771..7d5abb3158ec 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -768,11 +768,9 @@ static int pndisc_is_router(const void *pkey, struct pneigh_entry *n; int ret = -1; - read_lock_bh(&nd_tbl.lock); - n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); + n = pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); if (n) - ret = !!(n->flags & NTF_ROUTER); - read_unlock_bh(&nd_tbl.lock); + ret = !!(READ_ONCE(n->flags) & NTF_ROUTER); return ret; } @@ -1100,7 +1098,7 @@ static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb) if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && READ_ONCE(net->ipv6.devconf_all->forwarding) && READ_ONCE(net->ipv6.devconf_all->proxy_ndp) && - pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { + pneigh_lookup(&nd_tbl, net, &msg->target, dev)) { /* XXX: idev->cnf.proxy_ndp */ goto out; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8f2c3cba1f1f..7577e7eb2c97 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1834,14 +1834,12 @@ lookup: } refcounted = true; nsk = NULL; - if (!tcp_filter(sk, skb)) { + if (!tcp_filter(sk, skb, &drop_reason)) { th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen, &drop_reason); - } else { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); @@ -1897,10 +1895,9 @@ process: nf_reset_ct(skb); - if (tcp_filter(sk, skb)) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + if (tcp_filter(sk, skb, &drop_reason)) goto discard_and_relse; - } + th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6bbdadbd5fec..6a68f77da44b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -894,10 +894,8 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { - drop_reason = SKB_DROP_REASON_SOCKET_FILTER; + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason)) goto drop; - } udp_csum_pull_header(skb); diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 841c81abaaf4..9005fc156a20 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -202,6 +202,9 @@ struct sk_buff *xfrm6_gro_udp_encap_rcv(struct sock *sk, struct list_head *head, if (len <= sizeof(struct ip_esp_hdr) || udpdata32[0] == 0) goto out; + /* set the transport header to ESP */ + skb_set_transport_header(skb, offset); + NAPI_GRO_CB(skb)->proto = IPPROTO_UDP; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index bf140ef781c1..5120a763da0d 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -334,8 +334,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); - xfrm_state_flush(net, 0, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 1f82f69acfde..2ebde0352245 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -1766,7 +1766,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true, false); + err = xfrm_state_flush(net, proto, true); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 47d7dfd9ad09..25c88cba5c48 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -706,7 +706,7 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, } else { unsigned int flags; - flags = dev_get_flags(dev); + flags = netif_get_flags(dev); if (!(flags & (IFF_RUNNING | IFF_LOWER_UP))) nh->nh_flags |= RTNH_F_LINKDOWN; } @@ -1616,14 +1616,14 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, return notifier_from_errno(err); break; case NETDEV_UP: - flags = dev_get_flags(dev); + flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); else mpls_ifup(dev, RTNH_F_DEAD); break; case NETDEV_CHANGE: - flags = dev_get_flags(dev); + flags = netif_get_flags(dev); if (flags & (IFF_RUNNING | IFF_LOWER_UP)) { mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); } else { diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 2ad1c41e963e..6c448a0be949 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1387,7 +1387,7 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) * - estimate the faster flow linger time * - use the above to estimate the amount of byte transferred * by the faster flow - * - check that the amount of queued data is greter than the above, + * - check that the amount of queued data is greater than the above, * otherwise do not use the picked, slower, subflow * We select the subflow with the shorter estimated time to flush * the queued mem, which basically ensure the above. We just need diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 6ec245fd2778..1a32edf6f343 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -326,6 +326,7 @@ struct mptcp_sock { int keepalive_cnt; int keepalive_idle; int keepalive_intvl; + int maxseg; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 3caa0a9d3b38..2c267aff95be 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -798,6 +798,23 @@ unlock: return ret; } +static int mptcp_setsockopt_all_sf(struct mptcp_sock *msk, int level, + int optname, sockptr_t optval, + unsigned int optlen) +{ + struct mptcp_subflow_context *subflow; + int ret = 0; + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ret = tcp_setsockopt(ssk, level, optname, optval, optlen); + if (ret) + break; + } + return ret; +} + static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, sockptr_t optval, unsigned int optlen) { @@ -859,6 +876,11 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, &msk->keepalive_cnt, val); break; + case TCP_MAXSEG: + msk->maxseg = val; + ret = mptcp_setsockopt_all_sf(msk, SOL_TCP, optname, optval, + optlen); + break; default: ret = -ENOPROTOOPT; } @@ -914,10 +936,8 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int lock_sock(sk); ssk = msk->first; - if (ssk) { - ret = tcp_getsockopt(ssk, level, optname, optval, optlen); - goto out; - } + if (ssk) + goto get; ssk = __mptcp_nmpc_sk(msk); if (IS_ERR(ssk)) { @@ -925,6 +945,7 @@ static int mptcp_getsockopt_first_sf_only(struct mptcp_sock *msk, int level, int goto out; } +get: ret = tcp_getsockopt(ssk, level, optname, optval, optlen); out: @@ -1407,6 +1428,9 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return mptcp_put_int_option(msk, optval, optlen, msk->notsent_lowat); case TCP_IS_MPTCP: return mptcp_put_int_option(msk, optval, optlen, 1); + case TCP_MAXSEG: + return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname, + optval, optlen); } return -EOPNOTSUPP; } @@ -1553,6 +1577,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) tcp_sock_set_keepidle_locked(ssk, msk->keepalive_idle); tcp_sock_set_keepintvl(ssk, msk->keepalive_intvl); tcp_sock_set_keepcnt(ssk, msk->keepalive_cnt); + tcp_sock_set_maxseg(ssk, msk->maxseg); inet_assign_bit(TRANSPARENT, ssk, inet_test_bit(TRANSPARENT, sk)); inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 4d67f36dce1b..3e99181e759f 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -101,6 +101,7 @@ static int rose_state2_machine(struct sock *sk, struct sk_buff *skb, int framety */ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype, int ns, int nr, int q, int d, int m) { + enum skb_drop_reason dr; /* ignored */ struct rose_sock *rose = rose_sk(sk); int queued = 0; @@ -162,7 +163,7 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety rose_frames_acked(sk, nr); if (ns == rose->vr) { rose_start_idletimer(sk); - if (sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN) == 0 && + if (!sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN, &dr) && __sock_queue_rcv_skb(sk, skb) == 0) { rose->vr = (rose->vr + 1) % ROSE_MODULUS; queued = 1; diff --git a/net/sched/Kconfig b/net/sched/Kconfig index ad914d2b2e22..6ddff028b81a 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -415,6 +415,18 @@ config NET_SCH_BPF If unsure, say N. +config NET_SCH_DUALPI2 + tristate "Dual Queue PI Square (DUALPI2) scheduler" + help + Say Y here if you want to use the Dual Queue Proportional Integral + Controller Improved with a Square scheduling algorithm. + For more information, please see https://tools.ietf.org/html/rfc9332 + + To compile this driver as a module, choose M here: the module + will be called sch_dualpi2. + + If unsure, say N. + menuconfig NET_SCH_DEFAULT bool "Allow override default queue discipline" help diff --git a/net/sched/Makefile b/net/sched/Makefile index 904d784902d1..5078ea84e6ad 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o obj-$(CONFIG_NET_SCH_BPF) += bpf_qdisc.o +obj-$(CONFIG_NET_SCH_DUALPI2) += sch_dualpi2.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c new file mode 100644 index 000000000000..845375ebd4ea --- /dev/null +++ b/net/sched/sch_dualpi2.c @@ -0,0 +1,1175 @@ +// SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +/* Copyright (C) 2024 Nokia + * + * Author: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com> + * Author: Olga Albisser <olga@albisser.org> + * Author: Henrik Steen <henrist@henrist.net> + * Author: Olivier Tilmans <olivier.tilmans@nokia.com> + * Author: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com> + * + * DualPI Improved with a Square (dualpi2): + * - Supports congestion controls that comply with the Prague requirements + * in RFC9331 (e.g. TCP-Prague) + * - Supports coupled dual-queue with PI2 as defined in RFC9332 + * - Supports ECN L4S-identifier (IP.ECN==0b*1) + * + * note: Although DCTCP and BBRv3 can use shallow-threshold ECN marks, + * they do not meet the 'Prague L4S Requirements' listed in RFC 9331 + * Section 4, so they can only be used with DualPI2 in a datacenter + * context. + * + * References: + * - RFC9332: https://datatracker.ietf.org/doc/html/rfc9332 + * - De Schepper, Koen, et al. "PI 2: A linearized AQM for both classic and + * scalable TCP." in proc. ACM CoNEXT'16, 2016. + */ + +#include <linux/errno.h> +#include <linux/hrtimer.h> +#include <linux/if_vlan.h> +#include <linux/kernel.h> +#include <linux/limits.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/types.h> + +#include <net/gso.h> +#include <net/inet_ecn.h> +#include <net/pkt_cls.h> +#include <net/pkt_sched.h> + +/* 32b enable to support flows with windows up to ~8.6 * 1e9 packets + * i.e., twice the maximal snd_cwnd. + * MAX_PROB must be consistent with the RNG in dualpi2_roll(). + */ +#define MAX_PROB U32_MAX + +/* alpha/beta values exchanged over netlink are in units of 256ns */ +#define ALPHA_BETA_SHIFT 8 + +/* Scaled values of alpha/beta must fit in 32b to avoid overflow in later + * computations. Consequently (see and dualpi2_scale_alpha_beta()), their + * netlink-provided values can use at most 31b, i.e. be at most (2^23)-1 + * (~4MHz) as those are given in 1/256th. This enable to tune alpha/beta to + * control flows whose maximal RTTs can be in usec up to few secs. + */ +#define ALPHA_BETA_MAX ((1U << 31) - 1) + +/* Internal alpha/beta are in units of 64ns. + * This enables to use all alpha/beta values in the allowed range without loss + * of precision due to rounding when scaling them internally, e.g., + * scale_alpha_beta(1) will not round down to 0. + */ +#define ALPHA_BETA_GRANULARITY 6 + +#define ALPHA_BETA_SCALING (ALPHA_BETA_SHIFT - ALPHA_BETA_GRANULARITY) + +/* We express the weights (wc, wl) in %, i.e., wc + wl = 100 */ +#define MAX_WC 100 + +struct dualpi2_sched_data { + struct Qdisc *l_queue; /* The L4S Low latency queue (L-queue) */ + struct Qdisc *sch; /* The Classic queue (C-queue) */ + + /* Registered tc filters */ + struct tcf_proto __rcu *tcf_filters; + struct tcf_block *tcf_block; + + /* PI2 parameters */ + u64 pi2_target; /* Target delay in nanoseconds */ + u32 pi2_tupdate; /* Timer frequency in nanoseconds */ + u32 pi2_prob; /* Base PI probability */ + u32 pi2_alpha; /* Gain factor for the integral rate response */ + u32 pi2_beta; /* Gain factor for the proportional response */ + struct hrtimer pi2_timer; /* prob update timer */ + + /* Step AQM (L-queue only) parameters */ + u32 step_thresh; /* Step threshold */ + bool step_in_packets; /* Step thresh in packets (1) or time (0) */ + + /* C-queue starvation protection */ + s32 c_protection_credit; /* Credit (sign indicates which queue) */ + s32 c_protection_init; /* Reset value of the credit */ + u8 c_protection_wc; /* C-queue weight (between 0 and MAX_WC) */ + u8 c_protection_wl; /* L-queue weight (MAX_WC - wc) */ + + /* General dualQ parameters */ + u32 memory_limit; /* Memory limit of both queues */ + u8 coupling_factor;/* Coupling factor (k) between both queues */ + u8 ecn_mask; /* Mask to match packets into L-queue */ + u32 min_qlen_step; /* Minimum queue length to apply step thresh */ + bool drop_early; /* Drop at enqueue (1) instead of dequeue (0) */ + bool drop_overload; /* Drop (1) on overload, or overflow (0) */ + bool split_gso; /* Split aggregated skb (1) or leave as is (0) */ + + /* Statistics */ + u64 c_head_ts; /* Enqueue timestamp of the C-queue head */ + u64 l_head_ts; /* Enqueue timestamp of the L-queue head */ + u64 last_qdelay; /* Q delay val at the last probability update */ + u32 packets_in_c; /* Enqueue packet counter of the C-queue */ + u32 packets_in_l; /* Enqueue packet counter of the L-queue */ + u32 maxq; /* Maximum queue size of the C-queue */ + u32 ecn_mark; /* ECN mark pkt counter due to PI probability */ + u32 step_marks; /* ECN mark pkt counter due to step AQM */ + u32 memory_used; /* Memory used of both queues */ + u32 max_memory_used;/* Maximum used memory */ + + /* Deferred drop statistics */ + u32 deferred_drops_cnt; /* Packets dropped */ + u32 deferred_drops_len; /* Bytes dropped */ +}; + +struct dualpi2_skb_cb { + u64 ts; /* Timestamp at enqueue */ + u8 apply_step:1, /* Can we apply the step threshold */ + classified:2, /* Packet classification results */ + ect:2; /* Packet ECT codepoint */ +}; + +enum dualpi2_classification_results { + DUALPI2_C_CLASSIC = 0, /* C-queue */ + DUALPI2_C_L4S = 1, /* L-queue (scale mark/classic drop) */ + DUALPI2_C_LLLL = 2, /* L-queue (no drops/marks) */ + __DUALPI2_C_MAX /* Keep last*/ +}; + +static struct dualpi2_skb_cb *dualpi2_skb_cb(struct sk_buff *skb) +{ + qdisc_cb_private_validate(skb, sizeof(struct dualpi2_skb_cb)); + return (struct dualpi2_skb_cb *)qdisc_skb_cb(skb)->data; +} + +static u64 dualpi2_sojourn_time(struct sk_buff *skb, u64 reference) +{ + return reference - dualpi2_skb_cb(skb)->ts; +} + +static u64 head_enqueue_time(struct Qdisc *q) +{ + struct sk_buff *skb = qdisc_peek_head(q); + + return skb ? dualpi2_skb_cb(skb)->ts : 0; +} + +static u32 dualpi2_scale_alpha_beta(u32 param) +{ + u64 tmp = ((u64)param * MAX_PROB >> ALPHA_BETA_SCALING); + + do_div(tmp, NSEC_PER_SEC); + return tmp; +} + +static u32 dualpi2_unscale_alpha_beta(u32 param) +{ + u64 tmp = ((u64)param * NSEC_PER_SEC << ALPHA_BETA_SCALING); + + do_div(tmp, MAX_PROB); + return tmp; +} + +static ktime_t next_pi2_timeout(struct dualpi2_sched_data *q) +{ + return ktime_add_ns(ktime_get_ns(), q->pi2_tupdate); +} + +static bool skb_is_l4s(struct sk_buff *skb) +{ + return dualpi2_skb_cb(skb)->classified == DUALPI2_C_L4S; +} + +static bool skb_in_l_queue(struct sk_buff *skb) +{ + return dualpi2_skb_cb(skb)->classified != DUALPI2_C_CLASSIC; +} + +static bool skb_apply_step(struct sk_buff *skb, struct dualpi2_sched_data *q) +{ + return skb_is_l4s(skb) && qdisc_qlen(q->l_queue) >= q->min_qlen_step; +} + +static bool dualpi2_mark(struct dualpi2_sched_data *q, struct sk_buff *skb) +{ + if (INET_ECN_set_ce(skb)) { + q->ecn_mark++; + return true; + } + return false; +} + +static void dualpi2_reset_c_protection(struct dualpi2_sched_data *q) +{ + q->c_protection_credit = q->c_protection_init; +} + +/* This computes the initial credit value and WRR weight for the L queue (wl) + * from the weight of the C queue (wc). + * If wl > wc, the scheduler will start with the L queue when reset. + */ +static void dualpi2_calculate_c_protection(struct Qdisc *sch, + struct dualpi2_sched_data *q, u32 wc) +{ + q->c_protection_wc = wc; + q->c_protection_wl = MAX_WC - wc; + q->c_protection_init = (s32)psched_mtu(qdisc_dev(sch)) * + ((int)q->c_protection_wc - (int)q->c_protection_wl); + dualpi2_reset_c_protection(q); +} + +static bool dualpi2_roll(u32 prob) +{ + return get_random_u32() <= prob; +} + +/* Packets in the C-queue are subject to a marking probability pC, which is the + * square of the internal PI probability (i.e., have an overall lower mark/drop + * probability). If the qdisc is overloaded, ignore ECT values and only drop. + * + * Note that this marking scheme is also applied to L4S packets during overload. + * Return true if packet dropping is required in C queue + */ +static bool dualpi2_classic_marking(struct dualpi2_sched_data *q, + struct sk_buff *skb, u32 prob, + bool overload) +{ + if (dualpi2_roll(prob) && dualpi2_roll(prob)) { + if (overload || dualpi2_skb_cb(skb)->ect == INET_ECN_NOT_ECT) + return true; + dualpi2_mark(q, skb); + } + return false; +} + +/* Packets in the L-queue are subject to a marking probability pL given by the + * internal PI probability scaled by the coupling factor. + * + * On overload (i.e., @local_l_prob is >= 100%): + * - if the qdisc is configured to trade losses to preserve latency (i.e., + * @q->drop_overload), apply classic drops first before marking. + * - otherwise, preserve the "no loss" property of ECN at the cost of queueing + * delay, eventually resulting in taildrop behavior once sch->limit is + * reached. + * Return true if packet dropping is required in L queue + */ +static bool dualpi2_scalable_marking(struct dualpi2_sched_data *q, + struct sk_buff *skb, + u64 local_l_prob, u32 prob, + bool overload) +{ + if (overload) { + /* Apply classic drop */ + if (!q->drop_overload || + !(dualpi2_roll(prob) && dualpi2_roll(prob))) + goto mark; + return true; + } + + /* We can safely cut the upper 32b as overload==false */ + if (dualpi2_roll(local_l_prob)) { + /* Non-ECT packets could have classified as L4S by filters. */ + if (dualpi2_skb_cb(skb)->ect == INET_ECN_NOT_ECT) + return true; +mark: + dualpi2_mark(q, skb); + } + return false; +} + +/* Decide whether a given packet must be dropped (or marked if ECT), according + * to the PI2 probability. + * + * Never mark/drop if we have a standing queue of less than 2 MTUs. + */ +static bool must_drop(struct Qdisc *sch, struct dualpi2_sched_data *q, + struct sk_buff *skb) +{ + u64 local_l_prob; + bool overload; + u32 prob; + + if (sch->qstats.backlog < 2 * psched_mtu(qdisc_dev(sch))) + return false; + + prob = READ_ONCE(q->pi2_prob); + local_l_prob = (u64)prob * q->coupling_factor; + overload = local_l_prob > MAX_PROB; + + switch (dualpi2_skb_cb(skb)->classified) { + case DUALPI2_C_CLASSIC: + return dualpi2_classic_marking(q, skb, prob, overload); + case DUALPI2_C_L4S: + return dualpi2_scalable_marking(q, skb, local_l_prob, prob, + overload); + default: /* DUALPI2_C_LLLL */ + return false; + } +} + +static void dualpi2_read_ect(struct sk_buff *skb) +{ + struct dualpi2_skb_cb *cb = dualpi2_skb_cb(skb); + int wlen = skb_network_offset(skb); + + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): + wlen += sizeof(struct iphdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + goto not_ecn; + + cb->ect = ipv4_get_dsfield(ip_hdr(skb)) & INET_ECN_MASK; + break; + case htons(ETH_P_IPV6): + wlen += sizeof(struct ipv6hdr); + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + goto not_ecn; + + cb->ect = ipv6_get_dsfield(ipv6_hdr(skb)) & INET_ECN_MASK; + break; + default: + goto not_ecn; + } + return; + +not_ecn: + /* Non pullable/writable packets can only be dropped hence are + * classified as not ECT. + */ + cb->ect = INET_ECN_NOT_ECT; +} + +static int dualpi2_skb_classify(struct dualpi2_sched_data *q, + struct sk_buff *skb) +{ + struct dualpi2_skb_cb *cb = dualpi2_skb_cb(skb); + struct tcf_result res; + struct tcf_proto *fl; + int result; + + dualpi2_read_ect(skb); + if (cb->ect & q->ecn_mask) { + cb->classified = DUALPI2_C_L4S; + return NET_XMIT_SUCCESS; + } + + if (TC_H_MAJ(skb->priority) == q->sch->handle && + TC_H_MIN(skb->priority) < __DUALPI2_C_MAX) { + cb->classified = TC_H_MIN(skb->priority); + return NET_XMIT_SUCCESS; + } + + fl = rcu_dereference_bh(q->tcf_filters); + if (!fl) { + cb->classified = DUALPI2_C_CLASSIC; + return NET_XMIT_SUCCESS; + } + + result = tcf_classify(skb, NULL, fl, &res, false); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_TRAP: + return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + } +#endif + cb->classified = TC_H_MIN(res.classid) < __DUALPI2_C_MAX ? + TC_H_MIN(res.classid) : DUALPI2_C_CLASSIC; + } + return NET_XMIT_SUCCESS; +} + +static int dualpi2_enqueue_skb(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct dualpi2_skb_cb *cb; + + if (unlikely(qdisc_qlen(sch) >= sch->limit) || + unlikely((u64)q->memory_used + skb->truesize > q->memory_limit)) { + qdisc_qstats_overlimit(sch); + if (skb_in_l_queue(skb)) + qdisc_qstats_overlimit(q->l_queue); + return qdisc_drop_reason(skb, sch, to_free, + SKB_DROP_REASON_QDISC_OVERLIMIT); + } + + if (q->drop_early && must_drop(sch, q, skb)) { + qdisc_drop_reason(skb, sch, to_free, + SKB_DROP_REASON_QDISC_CONGESTED); + return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + } + + cb = dualpi2_skb_cb(skb); + cb->ts = ktime_get_ns(); + q->memory_used += skb->truesize; + if (q->memory_used > q->max_memory_used) + q->max_memory_used = q->memory_used; + + if (qdisc_qlen(sch) > q->maxq) + q->maxq = qdisc_qlen(sch); + + if (skb_in_l_queue(skb)) { + /* Apply step thresh if skb is L4S && L-queue len >= min_qlen */ + dualpi2_skb_cb(skb)->apply_step = skb_apply_step(skb, q); + + /* Keep the overall qdisc stats consistent */ + ++sch->q.qlen; + qdisc_qstats_backlog_inc(sch, skb); + ++q->packets_in_l; + if (!q->l_head_ts) + q->l_head_ts = cb->ts; + return qdisc_enqueue_tail(skb, q->l_queue); + } + ++q->packets_in_c; + if (!q->c_head_ts) + q->c_head_ts = cb->ts; + return qdisc_enqueue_tail(skb, sch); +} + +/* By default, dualpi2 will split GSO skbs into independent skbs and enqueue + * each of those individually. This yields the following benefits, at the + * expense of CPU usage: + * - Finer-grained AQM actions as the sub-packets of a burst no longer share the + * same fate (e.g., the random mark/drop probability is applied individually) + * - Improved precision of the starvation protection/WRR scheduler at dequeue, + * as the size of the dequeued packets will be smaller. + */ +static int dualpi2_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + int err; + + err = dualpi2_skb_classify(q, skb); + if (err != NET_XMIT_SUCCESS) { + if (err & __NET_XMIT_BYPASS) + qdisc_qstats_drop(sch); + __qdisc_drop(skb, to_free); + return err; + } + + if (q->split_gso && skb_is_gso(skb)) { + netdev_features_t features; + struct sk_buff *nskb, *next; + int cnt, byte_len, orig_len; + int err; + + features = netif_skb_features(skb); + nskb = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(nskb)) + return qdisc_drop(skb, sch, to_free); + + cnt = 1; + byte_len = 0; + orig_len = qdisc_pkt_len(skb); + skb_list_walk_safe(nskb, nskb, next) { + skb_mark_not_on_list(nskb); + + /* Iterate through GSO fragments of an skb: + * (1) Set pkt_len from the single GSO fragments + * (2) Copy classified and ect values of an skb + * (3) Enqueue fragment & set ts in dualpi2_enqueue_skb + */ + qdisc_skb_cb(nskb)->pkt_len = nskb->len; + dualpi2_skb_cb(nskb)->classified = + dualpi2_skb_cb(skb)->classified; + dualpi2_skb_cb(nskb)->ect = dualpi2_skb_cb(skb)->ect; + err = dualpi2_enqueue_skb(nskb, sch, to_free); + + if (err == NET_XMIT_SUCCESS) { + /* Compute the backlog adjustment that needs + * to be propagated in the qdisc tree to reflect + * all new skbs successfully enqueued. + */ + ++cnt; + byte_len += nskb->len; + } + } + if (cnt > 1) { + /* The caller will add the original skb stats to its + * backlog, compensate this if any nskb is enqueued. + */ + --cnt; + byte_len -= orig_len; + } + qdisc_tree_reduce_backlog(sch, -cnt, -byte_len); + consume_skb(skb); + return err; + } + return dualpi2_enqueue_skb(skb, sch, to_free); +} + +/* Select the queue from which the next packet can be dequeued, ensuring that + * neither queue can starve the other with a WRR scheduler. + * + * The sign of the WRR credit determines the next queue, while the size of + * the dequeued packet determines the magnitude of the WRR credit change. If + * either queue is empty, the WRR credit is kept unchanged. + * + * As the dequeued packet can be dropped later, the caller has to perform the + * qdisc_bstats_update() calls. + */ +static struct sk_buff *dequeue_packet(struct Qdisc *sch, + struct dualpi2_sched_data *q, + int *credit_change, + u64 now) +{ + struct sk_buff *skb = NULL; + int c_len; + + *credit_change = 0; + c_len = qdisc_qlen(sch) - qdisc_qlen(q->l_queue); + if (qdisc_qlen(q->l_queue) && (!c_len || q->c_protection_credit <= 0)) { + skb = __qdisc_dequeue_head(&q->l_queue->q); + WRITE_ONCE(q->l_head_ts, head_enqueue_time(q->l_queue)); + if (c_len) + *credit_change = q->c_protection_wc; + qdisc_qstats_backlog_dec(q->l_queue, skb); + + /* Keep the global queue size consistent */ + --sch->q.qlen; + q->memory_used -= skb->truesize; + } else if (c_len) { + skb = __qdisc_dequeue_head(&sch->q); + WRITE_ONCE(q->c_head_ts, head_enqueue_time(sch)); + if (qdisc_qlen(q->l_queue)) + *credit_change = ~((s32)q->c_protection_wl) + 1; + q->memory_used -= skb->truesize; + } else { + dualpi2_reset_c_protection(q); + return NULL; + } + *credit_change *= qdisc_pkt_len(skb); + qdisc_qstats_backlog_dec(sch, skb); + return skb; +} + +static int do_step_aqm(struct dualpi2_sched_data *q, struct sk_buff *skb, + u64 now) +{ + u64 qdelay = 0; + + if (q->step_in_packets) + qdelay = qdisc_qlen(q->l_queue); + else + qdelay = dualpi2_sojourn_time(skb, now); + + if (dualpi2_skb_cb(skb)->apply_step && qdelay > q->step_thresh) { + if (!dualpi2_skb_cb(skb)->ect) { + /* Drop this non-ECT packet */ + return 1; + } + + if (dualpi2_mark(q, skb)) + ++q->step_marks; + } + qdisc_bstats_update(q->l_queue, skb); + return 0; +} + +static void drop_and_retry(struct dualpi2_sched_data *q, struct sk_buff *skb, + struct Qdisc *sch, enum skb_drop_reason reason) +{ + ++q->deferred_drops_cnt; + q->deferred_drops_len += qdisc_pkt_len(skb); + kfree_skb_reason(skb, reason); + qdisc_qstats_drop(sch); +} + +static struct sk_buff *dualpi2_qdisc_dequeue(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct sk_buff *skb; + int credit_change; + u64 now; + + now = ktime_get_ns(); + + while ((skb = dequeue_packet(sch, q, &credit_change, now))) { + if (!q->drop_early && must_drop(sch, q, skb)) { + drop_and_retry(q, skb, sch, + SKB_DROP_REASON_QDISC_CONGESTED); + continue; + } + + if (skb_in_l_queue(skb) && do_step_aqm(q, skb, now)) { + qdisc_qstats_drop(q->l_queue); + drop_and_retry(q, skb, sch, + SKB_DROP_REASON_DUALPI2_STEP_DROP); + continue; + } + + q->c_protection_credit += credit_change; + qdisc_bstats_update(sch, skb); + break; + } + + if (q->deferred_drops_cnt) { + qdisc_tree_reduce_backlog(sch, q->deferred_drops_cnt, + q->deferred_drops_len); + q->deferred_drops_cnt = 0; + q->deferred_drops_len = 0; + } + return skb; +} + +static s64 __scale_delta(u64 diff) +{ + do_div(diff, 1 << ALPHA_BETA_GRANULARITY); + return diff; +} + +static void get_queue_delays(struct dualpi2_sched_data *q, u64 *qdelay_c, + u64 *qdelay_l) +{ + u64 now, qc, ql; + + now = ktime_get_ns(); + qc = READ_ONCE(q->c_head_ts); + ql = READ_ONCE(q->l_head_ts); + + *qdelay_c = qc ? now - qc : 0; + *qdelay_l = ql ? now - ql : 0; +} + +static u32 calculate_probability(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + u32 new_prob; + u64 qdelay_c; + u64 qdelay_l; + u64 qdelay; + s64 delta; + + get_queue_delays(q, &qdelay_c, &qdelay_l); + qdelay = max(qdelay_l, qdelay_c); + + /* Alpha and beta take at most 32b, i.e, the delay difference would + * overflow for queuing delay differences > ~4.2sec. + */ + delta = ((s64)qdelay - (s64)q->pi2_target) * q->pi2_alpha; + delta += ((s64)qdelay - (s64)q->last_qdelay) * q->pi2_beta; + q->last_qdelay = qdelay; + + /* Bound new_prob between 0 and MAX_PROB */ + if (delta > 0) { + new_prob = __scale_delta(delta) + q->pi2_prob; + if (new_prob < q->pi2_prob) + new_prob = MAX_PROB; + } else { + new_prob = q->pi2_prob - __scale_delta(~delta + 1); + if (new_prob > q->pi2_prob) + new_prob = 0; + } + + /* If we do not drop on overload, ensure we cap the L4S probability to + * 100% to keep window fairness when overflowing. + */ + if (!q->drop_overload) + return min_t(u32, new_prob, MAX_PROB / q->coupling_factor); + return new_prob; +} + +static u32 get_memory_limit(struct Qdisc *sch, u32 limit) +{ + /* Apply rule of thumb, i.e., doubling the packet length, + * to further include per packet overhead in memory_limit. + */ + u64 memlim = mul_u32_u32(limit, 2 * psched_mtu(qdisc_dev(sch))); + + if (upper_32_bits(memlim)) + return U32_MAX; + else + return lower_32_bits(memlim); +} + +static u32 convert_us_to_nsec(u32 us) +{ + u64 ns = mul_u32_u32(us, NSEC_PER_USEC); + + if (upper_32_bits(ns)) + return U32_MAX; + + return lower_32_bits(ns); +} + +static u32 convert_ns_to_usec(u64 ns) +{ + do_div(ns, NSEC_PER_USEC); + if (upper_32_bits(ns)) + return U32_MAX; + + return lower_32_bits(ns); +} + +static enum hrtimer_restart dualpi2_timer(struct hrtimer *timer) +{ + struct dualpi2_sched_data *q = timer_container_of(q, timer, pi2_timer); + struct Qdisc *sch = q->sch; + spinlock_t *root_lock; /* to lock qdisc for probability calculations */ + + rcu_read_lock(); + root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + spin_lock(root_lock); + + WRITE_ONCE(q->pi2_prob, calculate_probability(sch)); + hrtimer_set_expires(&q->pi2_timer, next_pi2_timeout(q)); + + spin_unlock(root_lock); + rcu_read_unlock(); + return HRTIMER_RESTART; +} + +static struct netlink_range_validation dualpi2_alpha_beta_range = { + .min = 1, + .max = ALPHA_BETA_MAX, +}; + +static const struct nla_policy dualpi2_policy[TCA_DUALPI2_MAX + 1] = { + [TCA_DUALPI2_LIMIT] = NLA_POLICY_MIN(NLA_U32, 1), + [TCA_DUALPI2_MEMORY_LIMIT] = NLA_POLICY_MIN(NLA_U32, 1), + [TCA_DUALPI2_TARGET] = { .type = NLA_U32 }, + [TCA_DUALPI2_TUPDATE] = NLA_POLICY_MIN(NLA_U32, 1), + [TCA_DUALPI2_ALPHA] = + NLA_POLICY_FULL_RANGE(NLA_U32, &dualpi2_alpha_beta_range), + [TCA_DUALPI2_BETA] = + NLA_POLICY_FULL_RANGE(NLA_U32, &dualpi2_alpha_beta_range), + [TCA_DUALPI2_STEP_THRESH_PKTS] = { .type = NLA_U32 }, + [TCA_DUALPI2_STEP_THRESH_US] = { .type = NLA_U32 }, + [TCA_DUALPI2_MIN_QLEN_STEP] = { .type = NLA_U32 }, + [TCA_DUALPI2_COUPLING] = NLA_POLICY_MIN(NLA_U8, 1), + [TCA_DUALPI2_DROP_OVERLOAD] = + NLA_POLICY_MAX(NLA_U8, TCA_DUALPI2_DROP_OVERLOAD_MAX), + [TCA_DUALPI2_DROP_EARLY] = + NLA_POLICY_MAX(NLA_U8, TCA_DUALPI2_DROP_EARLY_MAX), + [TCA_DUALPI2_C_PROTECTION] = + NLA_POLICY_RANGE(NLA_U8, 0, MAX_WC), + [TCA_DUALPI2_ECN_MASK] = + NLA_POLICY_RANGE(NLA_U8, TC_DUALPI2_ECN_MASK_L4S_ECT, + TCA_DUALPI2_ECN_MASK_MAX), + [TCA_DUALPI2_SPLIT_GSO] = + NLA_POLICY_MAX(NLA_U8, TCA_DUALPI2_SPLIT_GSO_MAX), +}; + +static int dualpi2_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_DUALPI2_MAX + 1]; + struct dualpi2_sched_data *q; + int old_backlog; + int old_qlen; + int err; + + if (!opt || !nla_len(opt)) { + NL_SET_ERR_MSG_MOD(extack, "Dualpi2 options are required"); + return -EINVAL; + } + err = nla_parse_nested(tb, TCA_DUALPI2_MAX, opt, dualpi2_policy, + extack); + if (err < 0) + return err; + if (tb[TCA_DUALPI2_STEP_THRESH_PKTS] && tb[TCA_DUALPI2_STEP_THRESH_US]) { + NL_SET_ERR_MSG_MOD(extack, "multiple step thresh attributes"); + return -EINVAL; + } + + q = qdisc_priv(sch); + sch_tree_lock(sch); + + if (tb[TCA_DUALPI2_LIMIT]) { + u32 limit = nla_get_u32(tb[TCA_DUALPI2_LIMIT]); + + WRITE_ONCE(sch->limit, limit); + WRITE_ONCE(q->memory_limit, get_memory_limit(sch, limit)); + } + + if (tb[TCA_DUALPI2_MEMORY_LIMIT]) + WRITE_ONCE(q->memory_limit, + nla_get_u32(tb[TCA_DUALPI2_MEMORY_LIMIT])); + + if (tb[TCA_DUALPI2_TARGET]) { + u64 target = nla_get_u32(tb[TCA_DUALPI2_TARGET]); + + WRITE_ONCE(q->pi2_target, target * NSEC_PER_USEC); + } + + if (tb[TCA_DUALPI2_TUPDATE]) { + u64 tupdate = nla_get_u32(tb[TCA_DUALPI2_TUPDATE]); + + WRITE_ONCE(q->pi2_tupdate, convert_us_to_nsec(tupdate)); + } + + if (tb[TCA_DUALPI2_ALPHA]) { + u32 alpha = nla_get_u32(tb[TCA_DUALPI2_ALPHA]); + + WRITE_ONCE(q->pi2_alpha, dualpi2_scale_alpha_beta(alpha)); + } + + if (tb[TCA_DUALPI2_BETA]) { + u32 beta = nla_get_u32(tb[TCA_DUALPI2_BETA]); + + WRITE_ONCE(q->pi2_beta, dualpi2_scale_alpha_beta(beta)); + } + + if (tb[TCA_DUALPI2_STEP_THRESH_PKTS]) { + u32 step_th = nla_get_u32(tb[TCA_DUALPI2_STEP_THRESH_PKTS]); + + WRITE_ONCE(q->step_in_packets, true); + WRITE_ONCE(q->step_thresh, step_th); + } else if (tb[TCA_DUALPI2_STEP_THRESH_US]) { + u32 step_th = nla_get_u32(tb[TCA_DUALPI2_STEP_THRESH_US]); + + WRITE_ONCE(q->step_in_packets, false); + WRITE_ONCE(q->step_thresh, convert_us_to_nsec(step_th)); + } + + if (tb[TCA_DUALPI2_MIN_QLEN_STEP]) + WRITE_ONCE(q->min_qlen_step, + nla_get_u32(tb[TCA_DUALPI2_MIN_QLEN_STEP])); + + if (tb[TCA_DUALPI2_COUPLING]) { + u8 coupling = nla_get_u8(tb[TCA_DUALPI2_COUPLING]); + + WRITE_ONCE(q->coupling_factor, coupling); + } + + if (tb[TCA_DUALPI2_DROP_OVERLOAD]) { + u8 drop_overload = nla_get_u8(tb[TCA_DUALPI2_DROP_OVERLOAD]); + + WRITE_ONCE(q->drop_overload, (bool)drop_overload); + } + + if (tb[TCA_DUALPI2_DROP_EARLY]) { + u8 drop_early = nla_get_u8(tb[TCA_DUALPI2_DROP_EARLY]); + + WRITE_ONCE(q->drop_early, (bool)drop_early); + } + + if (tb[TCA_DUALPI2_C_PROTECTION]) { + u8 wc = nla_get_u8(tb[TCA_DUALPI2_C_PROTECTION]); + + dualpi2_calculate_c_protection(sch, q, wc); + } + + if (tb[TCA_DUALPI2_ECN_MASK]) { + u8 ecn_mask = nla_get_u8(tb[TCA_DUALPI2_ECN_MASK]); + + WRITE_ONCE(q->ecn_mask, ecn_mask); + } + + if (tb[TCA_DUALPI2_SPLIT_GSO]) { + u8 split_gso = nla_get_u8(tb[TCA_DUALPI2_SPLIT_GSO]); + + WRITE_ONCE(q->split_gso, (bool)split_gso); + } + + old_qlen = qdisc_qlen(sch); + old_backlog = sch->qstats.backlog; + while (qdisc_qlen(sch) > sch->limit || + q->memory_used > q->memory_limit) { + struct sk_buff *skb = qdisc_dequeue_internal(sch, true); + + q->memory_used -= skb->truesize; + qdisc_qstats_backlog_dec(sch, skb); + rtnl_qdisc_drop(skb, sch); + } + qdisc_tree_reduce_backlog(sch, old_qlen - qdisc_qlen(sch), + old_backlog - sch->qstats.backlog); + + sch_tree_unlock(sch); + return 0; +} + +/* Default alpha/beta values give a 10dB stability margin with max_rtt=100ms. */ +static void dualpi2_reset_default(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + q->sch->limit = 10000; /* Max 125ms at 1Gbps */ + q->memory_limit = get_memory_limit(sch, q->sch->limit); + + q->pi2_target = 15 * NSEC_PER_MSEC; + q->pi2_tupdate = 16 * NSEC_PER_MSEC; + q->pi2_alpha = dualpi2_scale_alpha_beta(41); /* ~0.16 Hz * 256 */ + q->pi2_beta = dualpi2_scale_alpha_beta(819); /* ~3.20 Hz * 256 */ + + q->step_thresh = 1 * NSEC_PER_MSEC; + q->step_in_packets = false; + + dualpi2_calculate_c_protection(q->sch, q, 10); /* wc=10%, wl=90% */ + + q->ecn_mask = TC_DUALPI2_ECN_MASK_L4S_ECT; /* INET_ECN_ECT_1 */ + q->min_qlen_step = 0; /* Always apply step mark in L-queue */ + q->coupling_factor = 2; /* window fairness for equal RTTs */ + q->drop_overload = TC_DUALPI2_DROP_OVERLOAD_DROP; /* Drop overload */ + q->drop_early = TC_DUALPI2_DROP_EARLY_DROP_DEQUEUE; /* Drop dequeue */ + q->split_gso = TC_DUALPI2_SPLIT_GSO_SPLIT_GSO; /* Split GSO */ +} + +static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + int err; + + q->l_queue = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, 1), extack); + if (!q->l_queue) + return -ENOMEM; + + err = tcf_block_get(&q->tcf_block, &q->tcf_filters, sch, extack); + if (err) + return err; + + q->sch = sch; + dualpi2_reset_default(sch); + hrtimer_setup(&q->pi2_timer, dualpi2_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + + if (opt && nla_len(opt)) { + err = dualpi2_change(sch, opt, extack); + + if (err) + return err; + } + + hrtimer_start(&q->pi2_timer, next_pi2_timeout(q), + HRTIMER_MODE_ABS_PINNED); + return 0; +} + +static int dualpi2_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + bool step_in_pkts; + u32 step_th; + + step_in_pkts = READ_ONCE(q->step_in_packets); + step_th = READ_ONCE(q->step_thresh); + + opts = nla_nest_start_noflag(skb, TCA_OPTIONS); + if (!opts) + goto nla_put_failure; + + if (step_in_pkts && + (nla_put_u32(skb, TCA_DUALPI2_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_DUALPI2_MEMORY_LIMIT, + READ_ONCE(q->memory_limit)) || + nla_put_u32(skb, TCA_DUALPI2_TARGET, + convert_ns_to_usec(READ_ONCE(q->pi2_target))) || + nla_put_u32(skb, TCA_DUALPI2_TUPDATE, + convert_ns_to_usec(READ_ONCE(q->pi2_tupdate))) || + nla_put_u32(skb, TCA_DUALPI2_ALPHA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_alpha))) || + nla_put_u32(skb, TCA_DUALPI2_BETA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_beta))) || + nla_put_u32(skb, TCA_DUALPI2_STEP_THRESH_PKTS, step_th) || + nla_put_u32(skb, TCA_DUALPI2_MIN_QLEN_STEP, + READ_ONCE(q->min_qlen_step)) || + nla_put_u8(skb, TCA_DUALPI2_COUPLING, + READ_ONCE(q->coupling_factor)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_OVERLOAD, + READ_ONCE(q->drop_overload)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_EARLY, + READ_ONCE(q->drop_early)) || + nla_put_u8(skb, TCA_DUALPI2_C_PROTECTION, + READ_ONCE(q->c_protection_wc)) || + nla_put_u8(skb, TCA_DUALPI2_ECN_MASK, READ_ONCE(q->ecn_mask)) || + nla_put_u8(skb, TCA_DUALPI2_SPLIT_GSO, READ_ONCE(q->split_gso)))) + goto nla_put_failure; + + if (!step_in_pkts && + (nla_put_u32(skb, TCA_DUALPI2_LIMIT, READ_ONCE(sch->limit)) || + nla_put_u32(skb, TCA_DUALPI2_MEMORY_LIMIT, + READ_ONCE(q->memory_limit)) || + nla_put_u32(skb, TCA_DUALPI2_TARGET, + convert_ns_to_usec(READ_ONCE(q->pi2_target))) || + nla_put_u32(skb, TCA_DUALPI2_TUPDATE, + convert_ns_to_usec(READ_ONCE(q->pi2_tupdate))) || + nla_put_u32(skb, TCA_DUALPI2_ALPHA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_alpha))) || + nla_put_u32(skb, TCA_DUALPI2_BETA, + dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2_beta))) || + nla_put_u32(skb, TCA_DUALPI2_STEP_THRESH_US, + convert_ns_to_usec(step_th)) || + nla_put_u32(skb, TCA_DUALPI2_MIN_QLEN_STEP, + READ_ONCE(q->min_qlen_step)) || + nla_put_u8(skb, TCA_DUALPI2_COUPLING, + READ_ONCE(q->coupling_factor)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_OVERLOAD, + READ_ONCE(q->drop_overload)) || + nla_put_u8(skb, TCA_DUALPI2_DROP_EARLY, + READ_ONCE(q->drop_early)) || + nla_put_u8(skb, TCA_DUALPI2_C_PROTECTION, + READ_ONCE(q->c_protection_wc)) || + nla_put_u8(skb, TCA_DUALPI2_ECN_MASK, READ_ONCE(q->ecn_mask)) || + nla_put_u8(skb, TCA_DUALPI2_SPLIT_GSO, READ_ONCE(q->split_gso)))) + goto nla_put_failure; + + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -1; +} + +static int dualpi2_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + struct tc_dualpi2_xstats st = { + .prob = READ_ONCE(q->pi2_prob), + .packets_in_c = q->packets_in_c, + .packets_in_l = q->packets_in_l, + .maxq = q->maxq, + .ecn_mark = q->ecn_mark, + .credit = q->c_protection_credit, + .step_marks = q->step_marks, + .memory_used = q->memory_used, + .max_memory_used = q->max_memory_used, + .memory_limit = q->memory_limit, + }; + u64 qc, ql; + + get_queue_delays(q, &qc, &ql); + st.delay_l = convert_ns_to_usec(ql); + st.delay_c = convert_ns_to_usec(qc); + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +/* Reset both L-queue and C-queue, internal packet counters, PI probability, + * C-queue protection credit, and timestamps, while preserving current + * configuration of DUALPI2. + */ +static void dualpi2_reset(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + qdisc_reset_queue(sch); + qdisc_reset_queue(q->l_queue); + q->c_head_ts = 0; + q->l_head_ts = 0; + q->pi2_prob = 0; + q->packets_in_c = 0; + q->packets_in_l = 0; + q->maxq = 0; + q->ecn_mark = 0; + q->step_marks = 0; + q->memory_used = 0; + q->max_memory_used = 0; + dualpi2_reset_c_protection(q); +} + +static void dualpi2_destroy(struct Qdisc *sch) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + q->pi2_tupdate = 0; + hrtimer_cancel(&q->pi2_timer); + if (q->l_queue) + qdisc_put(q->l_queue); + tcf_block_put(q->tcf_block); +} + +static struct Qdisc *dualpi2_leaf(struct Qdisc *sch, unsigned long arg) +{ + return NULL; +} + +static unsigned long dualpi2_find(struct Qdisc *sch, u32 classid) +{ + return 0; +} + +static unsigned long dualpi2_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + +static void dualpi2_unbind(struct Qdisc *q, unsigned long cl) +{ +} + +static struct tcf_block *dualpi2_tcf_block(struct Qdisc *sch, unsigned long cl, + struct netlink_ext_ack *extack) +{ + struct dualpi2_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return q->tcf_block; +} + +static void dualpi2_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + unsigned int i; + + if (arg->stop) + return; + + /* We statically define only 2 queues */ + for (i = 0; i < 2; i++) { + if (arg->count < arg->skip) { + arg->count++; + continue; + } + if (arg->fn(sch, i + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +/* Minimal class support to handle tc filters */ +static const struct Qdisc_class_ops dualpi2_class_ops = { + .leaf = dualpi2_leaf, + .find = dualpi2_find, + .tcf_block = dualpi2_tcf_block, + .bind_tcf = dualpi2_bind, + .unbind_tcf = dualpi2_unbind, + .walk = dualpi2_walk, +}; + +static struct Qdisc_ops dualpi2_qdisc_ops __read_mostly = { + .id = "dualpi2", + .cl_ops = &dualpi2_class_ops, + .priv_size = sizeof(struct dualpi2_sched_data), + .enqueue = dualpi2_qdisc_enqueue, + .dequeue = dualpi2_qdisc_dequeue, + .peek = qdisc_peek_dequeued, + .init = dualpi2_init, + .destroy = dualpi2_destroy, + .reset = dualpi2_reset, + .change = dualpi2_change, + .dump = dualpi2_dump, + .dump_stats = dualpi2_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init dualpi2_module_init(void) +{ + return register_qdisc(&dualpi2_qdisc_ops); +} + +static void __exit dualpi2_module_exit(void) +{ + unregister_qdisc(&dualpi2_qdisc_ops); +} + +module_init(dualpi2_module_init); +module_exit(dualpi2_module_exit); + +MODULE_DESCRIPTION("Dual Queue with Proportional Integral controller Improved with a Square (dualpi2) scheduler"); +MODULE_AUTHOR("Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>"); +MODULE_AUTHOR("Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>"); +MODULE_AUTHOR("Olga Albisser <olga@albisser.org>"); +MODULE_AUTHOR("Henrik Steen <henrist@henrist.net>"); +MODULE_AUTHOR("Olivier Tilmans <olivier.tilmans@nokia.com>"); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_VERSION("1.0"); diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index f0eb70353744..2255355e51d3 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -536,9 +536,6 @@ destroy_class: static void qfq_destroy_class(struct Qdisc *sch, struct qfq_class *cl) { - struct qfq_sched *q = qdisc_priv(sch); - - qfq_rm_from_agg(q, cl); gen_kill_estimator(&cl->rate_est); qdisc_put(cl->qdisc); kfree(cl); @@ -559,10 +556,11 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg, qdisc_purge_queue(cl->qdisc); qdisc_class_hash_remove(&q->clhash, &cl->common); - qfq_destroy_class(sch, cl); + qfq_rm_from_agg(q, cl); sch_tree_unlock(sch); + qfq_destroy_class(sch, cl); return 0; } @@ -1503,6 +1501,7 @@ static void qfq_destroy_qdisc(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], common.hnode) { + qfq_rm_from_agg(q, cl); qfq_destroy_class(sch, cl); } } diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index bea70eb6f034..c32a7c6903d5 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -431,7 +431,7 @@ static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev, r->__ifi_pad = 0; r->ifi_type = dev->type; r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); + r->ifi_flags = netif_get_flags(dev); r->ifi_change = 0; /* Wireless changes don't affect those flags */ if (nla_put_string(skb, IFLA_IFNAME, dev->name)) diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 81fd486b5e56..d2819baea414 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -305,7 +305,6 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, return -EINVAL; } - xfrm_set_type_offload(x); if (!x->type_offload) { NL_SET_ERR_MSG(extack, "Type doesn't support offload"); dev_put(dev); diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 7e6a71b9d6a3..c9ddef869aa5 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -503,6 +503,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) /* An encap_type of -1 indicates async resumption. */ if (encap_type == -1) { async = 1; + dev_put(skb->dev); seq = XFRM_SKB_CB(skb)->seq.input.low; goto resume; } @@ -649,18 +650,18 @@ lock: XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; - dev_hold(skb->dev); - - if (crypto_done) + if (crypto_done) { nexthdr = x->type_offload->input_tail(x, skb); - else + } else { + dev_hold(skb->dev); + nexthdr = x->type->input(x, skb); + if (nexthdr == -EINPROGRESS) + return 0; - if (nexthdr == -EINPROGRESS) - return 0; + dev_put(skb->dev); + } resume: - dev_put(skb->dev); - spin_lock(&x->lock); if (nexthdr < 0) { if (nexthdr == -EBADMSG) { diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index cb1e12740c87..330a05286a56 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -875,7 +875,7 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], return -EINVAL; } - if (p.collect_md) { + if (p.collect_md || xi->p.collect_md) { NL_SET_ERR_MSG(extack, "collect_md can't be changed"); return -EINVAL; } @@ -886,11 +886,6 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], } else { if (xi->dev != dev) return -EEXIST; - if (xi->p.collect_md) { - NL_SET_ERR_MSG(extack, - "device can't be changed to collect_md"); - return -EINVAL; - } } return xfrmi_update(xi, &p); diff --git a/net/xfrm/xfrm_ipcomp.c b/net/xfrm/xfrm_ipcomp.c index 907c3ccb440d..43fdc6ed8dd1 100644 --- a/net/xfrm/xfrm_ipcomp.c +++ b/net/xfrm/xfrm_ipcomp.c @@ -97,7 +97,7 @@ static int ipcomp_input_done2(struct sk_buff *skb, int err) struct ip_comp_hdr *ipch = ip_comp_hdr(skb); const int plen = skb->len; - skb_reset_transport_header(skb); + skb->transport_header = skb->network_header + sizeof(*ipch); return ipcomp_post_acomp(skb, err, 0) ?: skb->len < (plen + sizeof(ip_comp_hdr)) ? -EINVAL : @@ -313,7 +313,6 @@ void ipcomp_destroy(struct xfrm_state *x) struct ipcomp_data *ipcd = x->data; if (!ipcd) return; - xfrm_state_delete_tunnel(x); ipcomp_free_data(ipcd); kfree(ipcd); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 77cc418ad69e..77db3b5fe4ac 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -424,11 +424,10 @@ void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, } EXPORT_SYMBOL(xfrm_unregister_type_offload); -void xfrm_set_type_offload(struct xfrm_state *x) +void xfrm_set_type_offload(struct xfrm_state *x, bool try_load) { const struct xfrm_type_offload *type = NULL; struct xfrm_state_afinfo *afinfo; - bool try_load = true; retry: afinfo = xfrm_state_get_afinfo(x->props.family); @@ -593,7 +592,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void ___xfrm_state_destroy(struct xfrm_state *x) +static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) x->mode_cbs->destroy_state(x); @@ -607,6 +606,7 @@ static void ___xfrm_state_destroy(struct xfrm_state *x) kfree(x->coaddr); kfree(x->replay_esn); kfree(x->preplay_esn); + xfrm_unset_type_offload(x); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); @@ -631,7 +631,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - ___xfrm_state_destroy(x); + xfrm_state_gc_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -780,8 +780,6 @@ void xfrm_dev_state_free(struct xfrm_state *x) struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); - xfrm_unset_type_offload(x); - if (dev && dev->xfrmdev_ops) { spin_lock_bh(&xfrm_state_dev_gc_lock); if (!hlist_unhashed(&x->dev_gclist)) @@ -797,22 +795,18 @@ void xfrm_dev_state_free(struct xfrm_state *x) } #endif -void __xfrm_state_destroy(struct xfrm_state *x, bool sync) +void __xfrm_state_destroy(struct xfrm_state *x) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - if (sync) { - synchronize_rcu(); - ___xfrm_state_destroy(x); - } else { - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); - } + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); +static void xfrm_state_delete_tunnel(struct xfrm_state *x); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -840,6 +834,8 @@ int __xfrm_state_delete(struct xfrm_state *x) xfrm_dev_state_delete(x); + xfrm_state_delete_tunnel(x); + /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. @@ -921,7 +917,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; @@ -943,10 +939,7 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - if (sync) - xfrm_state_put_sync(x); - else - xfrm_state_put(x); + xfrm_state_put(x); if (!err) cnt++; @@ -1307,14 +1300,8 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, - int *error) + int *error, unsigned int pcpu_id) { - /* We need the cpu id just as a lookup key, - * we don't require it to be stable. - */ - unsigned int pcpu_id = get_cpu(); - put_cpu(); - /* Resolution logic: * 1. There is a valid state with matching selector. Done. * 2. Valid state with inappropriate selector. Skip. @@ -1381,14 +1368,15 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, /* We need the cpu id just as a lookup key, * we don't require it to be stable. */ - pcpu_id = get_cpu(); - put_cpu(); + pcpu_id = raw_smp_processor_id(); to_put = NULL; sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); + xfrm_hash_ptrs_get(net, &state_ptrs); + hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && @@ -1400,7 +1388,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, encap_family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } if (best) @@ -1417,7 +1405,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } cached: @@ -1429,8 +1417,6 @@ cached: else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */ WARN_ON(1); - xfrm_hash_ptrs_get(net, &state_ptrs); - h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask); hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) { #ifdef CONFIG_XFRM_OFFLOAD @@ -1460,7 +1446,7 @@ cached: tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } if (best || acquire_in_progress) goto found; @@ -1495,7 +1481,7 @@ cached: tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, - &best, &acquire_in_progress, &error); + &best, &acquire_in_progress, &error, pcpu_id); } found: @@ -1711,6 +1697,26 @@ struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, } EXPORT_SYMBOL(xfrm_state_lookup_byspi); +static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 spi, u8 proto) +{ + struct xfrm_state *x; + unsigned int i; + + rcu_read_lock(); + for (i = 0; i <= net->xfrm.state_hmask; i++) { + hlist_for_each_entry_rcu(x, &net->xfrm.state_byspi[i], byspi) { + if (x->id.spi == spi && x->id.proto == proto) { + if (!xfrm_state_hold_rcu(x)) + continue; + rcu_read_unlock(); + return x; + } + } + } + rcu_read_unlock(); + return NULL; +} + static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); @@ -2262,7 +2268,12 @@ EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { - xfrm_dev_state_update_stats(x); + /* All counters which are needed to decide if state is expired + * are handled by SW for non-packet offload modes. Simply skip + * the following update and save extra boilerplate in drivers. + */ + if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) + xfrm_dev_state_update_stats(x); if (!READ_ONCE(x->curlft.use_time)) WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); @@ -2555,10 +2566,8 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, unsigned int h; struct xfrm_state *x0; int err = -ENOENT; - __be32 minspi = htonl(low); - __be32 maxspi = htonl(high); + u32 range = high - low + 1; __be32 newspi = 0; - u32 mark = x->mark.v & x->mark.m; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_DEAD) { @@ -2572,38 +2581,34 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, err = -ENOENT; - if (minspi == maxspi) { - x0 = xfrm_state_lookup(net, mark, &x->id.daddr, minspi, x->id.proto, x->props.family); - if (x0) { - NL_SET_ERR_MSG(extack, "Requested SPI is already in use"); - xfrm_state_put(x0); + for (h = 0; h < range; h++) { + u32 spi = (low == high) ? low : get_random_u32_inclusive(low, high); + newspi = htonl(spi); + + spin_lock_bh(&net->xfrm.xfrm_state_lock); + x0 = xfrm_state_lookup_spi_proto(net, newspi, x->id.proto); + if (!x0) { + x->id.spi = newspi; + h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family); + XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, x->xso.type); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + err = 0; goto unlock; } - newspi = minspi; - } else { - u32 spi = 0; - for (h = 0; h < high-low+1; h++) { - spi = get_random_u32_inclusive(low, high); - x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family); - if (x0 == NULL) { - newspi = htonl(spi); - break; - } - xfrm_state_put(x0); + xfrm_state_put(x0); + spin_unlock_bh(&net->xfrm.xfrm_state_lock); + + if (signal_pending(current)) { + err = -ERESTARTSYS; + goto unlock; } + + if (low == high) + break; } - if (newspi) { - spin_lock_bh(&net->xfrm.xfrm_state_lock); - x->id.spi = newspi; - h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); - XFRM_STATE_INSERT(byspi, &x->byspi, net->xfrm.state_byspi + h, - x->xso.type); - spin_unlock_bh(&net->xfrm.xfrm_state_lock); - err = 0; - } else { + if (err) NL_SET_ERR_MSG(extack, "No SPI available in the requested range"); - } unlock: spin_unlock_bh(&x->lock); @@ -3077,20 +3082,17 @@ void xfrm_flush_gc(void) } EXPORT_SYMBOL(xfrm_flush_gc); -/* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ -void xfrm_state_delete_tunnel(struct xfrm_state *x) +static void xfrm_state_delete_tunnel(struct xfrm_state *x) { if (x->tunnel) { struct xfrm_state *t = x->tunnel; - if (atomic_read(&t->tunnel_users) == 2) + if (atomic_dec_return(&t->tunnel_users) == 1) xfrm_state_delete(t); - atomic_dec(&t->tunnel_users); - xfrm_state_put_sync(t); + xfrm_state_put(t); x->tunnel = NULL; } } -EXPORT_SYMBOL(xfrm_state_delete_tunnel); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { @@ -3295,8 +3297,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); - xfrm_state_flush(net, 0, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 59f258daf830..684239018bec 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -977,6 +977,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, /* override default values from above */ xfrm_update_ae_params(x, attrs, 0); + xfrm_set_type_offload(x, attrs[XFRMA_OFFLOAD_DEV]); /* configure the hardware if offload is requested */ if (attrs[XFRMA_OFFLOAD_DEV]) { err = xfrm_dev_state_add(net, x, @@ -2634,7 +2635,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true, false); + err = xfrm_state_flush(net, p->proto, true); if (err) { if (err == -ESRCH) /* empty table */ return 0; diff --git a/rust/Makefile b/rust/Makefile index 27dec7904c3a..115b63b7d1e3 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -194,6 +194,7 @@ quiet_cmd_rustdoc_test = RUSTDOC T $< RUST_MODFILE=test.rs \ OBJTREE=$(abspath $(objtree)) \ $(RUSTDOC) --test $(rust_common_flags) \ + -Zcrate-attr='feature(used_with_arg)' \ @$(objtree)/include/generated/rustc_cfg \ $(rustc_target_flags) $(rustdoc_test_target_flags) \ $(rustdoc_test_quiet) \ diff --git a/rust/kernel/firmware.rs b/rust/kernel/firmware.rs index 2494c96e105f..4fe621f35716 100644 --- a/rust/kernel/firmware.rs +++ b/rust/kernel/firmware.rs @@ -202,7 +202,7 @@ macro_rules! module_firmware { }; #[link_section = ".modinfo"] - #[used] + #[used(compiler)] static __MODULE_FIRMWARE: [u8; $($builder)*::create(__MODULE_FIRMWARE_PREFIX) .build_length()] = $($builder)*::create(__MODULE_FIRMWARE_PREFIX).build(); }; diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 8d228c237954..21ef202ab0db 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -231,14 +231,14 @@ macro_rules! try_init { ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $crate::error::Error) }; ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { - ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $err) }; @@ -291,14 +291,14 @@ macro_rules! try_pin_init { ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }) => { - ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $crate::error::Error) }; ($(&$this:ident in)? $t:ident $(::<$($generics:ty),* $(,)?>)? { $($fields:tt)* }? $err:ty) => { - ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),* $(,)?>)? { + ::pin_init::try_pin_init!($(&$this in)? $t $(::<$($generics),*>)? { $($fields)* }? $err) }; diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 4b8cdcb21e77..b9e65905e121 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -302,7 +302,7 @@ macro_rules! kunit_unsafe_test_suite { is_init: false, }; - #[used] + #[used(compiler)] #[allow(unused_unsafe)] #[cfg_attr(not(target_os = "macos"), link_section = ".kunit_test_suites")] static mut KUNIT_TEST_SUITE_ENTRY: *const ::kernel::bindings::kunit_suite = diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 6b4774b2b1c3..e13d6ed88fa6 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -34,6 +34,9 @@ // Expected to become stable. #![feature(arbitrary_self_types)] // +// To be determined. +#![feature(used_with_arg)] +// // `feature(derive_coerce_pointee)` is expected to become stable. Before Rust // 1.84.0, it did not exist, so enable the predecessor features. #![cfg_attr(CONFIG_RUSTC_HAS_COERCE_POINTEE, feature(derive_coerce_pointee))] diff --git a/rust/macros/module.rs b/rust/macros/module.rs index 2ddd2eeb2852..75efc6eeeafc 100644 --- a/rust/macros/module.rs +++ b/rust/macros/module.rs @@ -57,7 +57,7 @@ impl<'a> ModInfoBuilder<'a> { {cfg} #[doc(hidden)] #[cfg_attr(not(target_os = \"macos\"), link_section = \".modinfo\")] - #[used] + #[used(compiler)] pub static __{module}_{counter}: [u8; {length}] = *{string}; ", cfg = if builtin { @@ -249,7 +249,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { // key or a new section. For the moment, keep it simple. #[cfg(MODULE)] #[doc(hidden)] - #[used] + #[used(compiler)] static __IS_RUST_MODULE: () = (); static mut __MOD: ::core::mem::MaybeUninit<{type_}> = @@ -273,7 +273,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { #[cfg(MODULE)] #[doc(hidden)] - #[used] + #[used(compiler)] #[link_section = \".init.data\"] static __UNIQUE_ID___addressable_init_module: unsafe extern \"C\" fn() -> i32 = init_module; @@ -293,7 +293,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { #[cfg(MODULE)] #[doc(hidden)] - #[used] + #[used(compiler)] #[link_section = \".exit.data\"] static __UNIQUE_ID___addressable_cleanup_module: extern \"C\" fn() = cleanup_module; @@ -303,7 +303,7 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream { #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] #[doc(hidden)] #[link_section = \"{initcall_section}\"] - #[used] + #[used(compiler)] pub static __{ident}_initcall: extern \"C\" fn() -> ::kernel::ffi::c_int = __{ident}_init; diff --git a/scripts/Makefile.build b/scripts/Makefile.build index a6461ea411f7..ba71b27aa363 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -312,10 +312,11 @@ $(obj)/%.lst: $(obj)/%.c FORCE # - Stable since Rust 1.82.0: `feature(asm_const)`, `feature(raw_ref_op)`. # - Stable since Rust 1.87.0: `feature(asm_goto)`. # - Expected to become stable: `feature(arbitrary_self_types)`. +# - To be determined: `feature(used_with_arg)`. # # Please see https://github.com/Rust-for-Linux/linux/issues/2 for details on # the unstable features in use. -rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,raw_ref_op +rust_allowed_features := asm_const,asm_goto,arbitrary_self_types,lint_reasons,raw_ref_op,used_with_arg # `--out-dir` is required to avoid temporaries being created by `rustc` in the # current working directory, which may be not accessible in the out-of-tree diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c index 840bb9cfe789..a66f258cafaa 100644 --- a/sound/core/compress_offload.c +++ b/sound/core/compress_offload.c @@ -1269,62 +1269,62 @@ static long snd_compr_ioctl(struct file *f, unsigned int cmd, unsigned long arg) stream = &data->stream; guard(mutex)(&stream->device->lock); - switch (_IOC_NR(cmd)) { - case _IOC_NR(SNDRV_COMPRESS_IOCTL_VERSION): + switch (cmd) { + case SNDRV_COMPRESS_IOCTL_VERSION: return put_user(SNDRV_COMPRESS_VERSION, (int __user *)arg) ? -EFAULT : 0; - case _IOC_NR(SNDRV_COMPRESS_GET_CAPS): + case SNDRV_COMPRESS_GET_CAPS: return snd_compr_get_caps(stream, arg); #ifndef COMPR_CODEC_CAPS_OVERFLOW - case _IOC_NR(SNDRV_COMPRESS_GET_CODEC_CAPS): + case SNDRV_COMPRESS_GET_CODEC_CAPS: return snd_compr_get_codec_caps(stream, arg); #endif - case _IOC_NR(SNDRV_COMPRESS_SET_PARAMS): + case SNDRV_COMPRESS_SET_PARAMS: return snd_compr_set_params(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_GET_PARAMS): + case SNDRV_COMPRESS_GET_PARAMS: return snd_compr_get_params(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_SET_METADATA): + case SNDRV_COMPRESS_SET_METADATA: return snd_compr_set_metadata(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_GET_METADATA): + case SNDRV_COMPRESS_GET_METADATA: return snd_compr_get_metadata(stream, arg); } if (stream->direction == SND_COMPRESS_ACCEL) { #if IS_ENABLED(CONFIG_SND_COMPRESS_ACCEL) - switch (_IOC_NR(cmd)) { - case _IOC_NR(SNDRV_COMPRESS_TASK_CREATE): + switch (cmd) { + case SNDRV_COMPRESS_TASK_CREATE: return snd_compr_task_create(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_TASK_FREE): + case SNDRV_COMPRESS_TASK_FREE: return snd_compr_task_seq(stream, arg, snd_compr_task_free_one); - case _IOC_NR(SNDRV_COMPRESS_TASK_START): + case SNDRV_COMPRESS_TASK_START: return snd_compr_task_start_ioctl(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_TASK_STOP): + case SNDRV_COMPRESS_TASK_STOP: return snd_compr_task_seq(stream, arg, snd_compr_task_stop_one); - case _IOC_NR(SNDRV_COMPRESS_TASK_STATUS): + case SNDRV_COMPRESS_TASK_STATUS: return snd_compr_task_status_ioctl(stream, arg); } #endif return -ENOTTY; } - switch (_IOC_NR(cmd)) { - case _IOC_NR(SNDRV_COMPRESS_TSTAMP): + switch (cmd) { + case SNDRV_COMPRESS_TSTAMP: return snd_compr_tstamp(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_AVAIL): + case SNDRV_COMPRESS_AVAIL: return snd_compr_ioctl_avail(stream, arg); - case _IOC_NR(SNDRV_COMPRESS_PAUSE): + case SNDRV_COMPRESS_PAUSE: return snd_compr_pause(stream); - case _IOC_NR(SNDRV_COMPRESS_RESUME): + case SNDRV_COMPRESS_RESUME: return snd_compr_resume(stream); - case _IOC_NR(SNDRV_COMPRESS_START): + case SNDRV_COMPRESS_START: return snd_compr_start(stream); - case _IOC_NR(SNDRV_COMPRESS_STOP): + case SNDRV_COMPRESS_STOP: return snd_compr_stop(stream); - case _IOC_NR(SNDRV_COMPRESS_DRAIN): + case SNDRV_COMPRESS_DRAIN: return snd_compr_drain(stream); - case _IOC_NR(SNDRV_COMPRESS_PARTIAL_DRAIN): + case SNDRV_COMPRESS_PARTIAL_DRAIN: return snd_compr_partial_drain(stream); - case _IOC_NR(SNDRV_COMPRESS_NEXT_TRACK): + case SNDRV_COMPRESS_NEXT_TRACK: return snd_compr_next_track(stream); } diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c index 3f2fd32f4ad9..886c53184fec 100644 --- a/sound/pci/hda/cs35l56_hda.c +++ b/sound/pci/hda/cs35l56_hda.c @@ -873,6 +873,52 @@ static int cs35l56_hda_system_resume(struct device *dev) return 0; } +static int cs35l56_hda_fixup_yoga9(struct cs35l56_hda *cs35l56, int *bus_addr) +{ + /* The cirrus,dev-index property has the wrong values */ + switch (*bus_addr) { + case 0x30: + cs35l56->index = 1; + return 0; + case 0x31: + cs35l56->index = 0; + return 0; + default: + /* There is a pseudo-address for broadcast to both amps - ignore it */ + dev_dbg(cs35l56->base.dev, "Ignoring I2C address %#x\n", *bus_addr); + return 0; + } +} + +static const struct { + const char *sub; + int (*fixup_fn)(struct cs35l56_hda *cs35l56, int *bus_addr); +} cs35l56_hda_fixups[] = { + { + .sub = "17AA390B", /* Lenovo Yoga Book 9i GenX */ + .fixup_fn = cs35l56_hda_fixup_yoga9, + }, +}; + +static int cs35l56_hda_apply_platform_fixups(struct cs35l56_hda *cs35l56, const char *sub, + int *bus_addr) +{ + int i; + + if (IS_ERR(sub)) + return 0; + + for (i = 0; i < ARRAY_SIZE(cs35l56_hda_fixups); i++) { + if (strcasecmp(cs35l56_hda_fixups[i].sub, sub) == 0) { + dev_dbg(cs35l56->base.dev, "Applying fixup for %s\n", + cs35l56_hda_fixups[i].sub); + return (cs35l56_hda_fixups[i].fixup_fn)(cs35l56, bus_addr); + } + } + + return 0; +} + static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) { u32 values[HDA_MAX_COMPONENTS]; @@ -897,39 +943,47 @@ static int cs35l56_hda_read_acpi(struct cs35l56_hda *cs35l56, int hid, int id) ACPI_COMPANION_SET(cs35l56->base.dev, adev); } - property = "cirrus,dev-index"; - ret = device_property_count_u32(cs35l56->base.dev, property); - if (ret <= 0) - goto err; - - if (ret > ARRAY_SIZE(values)) { - ret = -EINVAL; - goto err; - } - nval = ret; + /* Initialize things that could be overwritten by a fixup */ + cs35l56->index = -1; - ret = device_property_read_u32_array(cs35l56->base.dev, property, values, nval); + sub = acpi_get_subsystem_id(ACPI_HANDLE(cs35l56->base.dev)); + ret = cs35l56_hda_apply_platform_fixups(cs35l56, sub, &id); if (ret) - goto err; + return ret; - cs35l56->index = -1; - for (i = 0; i < nval; i++) { - if (values[i] == id) { - cs35l56->index = i; - break; - } - } - /* - * It's not an error for the ID to be missing: for I2C there can be - * an alias address that is not a real device. So reject silently. - */ if (cs35l56->index == -1) { - dev_dbg(cs35l56->base.dev, "No index found in %s\n", property); - ret = -ENODEV; - goto err; - } + property = "cirrus,dev-index"; + ret = device_property_count_u32(cs35l56->base.dev, property); + if (ret <= 0) + goto err; - sub = acpi_get_subsystem_id(ACPI_HANDLE(cs35l56->base.dev)); + if (ret > ARRAY_SIZE(values)) { + ret = -EINVAL; + goto err; + } + nval = ret; + + ret = device_property_read_u32_array(cs35l56->base.dev, property, values, nval); + if (ret) + goto err; + + for (i = 0; i < nval; i++) { + if (values[i] == id) { + cs35l56->index = i; + break; + } + } + + /* + * It's not an error for the ID to be missing: for I2C there can be + * an alias address that is not a real device. So reject silently. + */ + if (cs35l56->index == -1) { + dev_dbg(cs35l56->base.dev, "No index found in %s\n", property); + ret = -ENODEV; + goto err; + } + } if (IS_ERR(sub)) { dev_info(cs35l56->base.dev, diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 060db37eab83..d91aac06adde 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7497,6 +7497,9 @@ static void alc287_fixup_yoga9_14iap7_bass_spk_pin(struct hda_codec *codec, }; struct alc_spec *spec = codec->spec; + /* Support Audio mute LED and Mic mute LED on keyboard */ + hda_fixup_ideapad_acpi(codec, fix, action); + switch (action) { case HDA_FIXUP_ACT_PRE_PROBE: snd_hda_apply_pincfgs(codec, pincfgs); @@ -10814,6 +10817,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8bb3, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x8bb4, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x103c, 0x8bbe, "HP Victus 16-r0xxx (MB 8BBE)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bc8, "HP Victus 15-fa1xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bcd, "HP Omen 16-xd0xxx", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8bdd, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2), @@ -11006,6 +11010,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x1043, 0x1a8e, "ASUS G712LWS", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U_HEADSET_MIC), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 97e340140d0c..f210a253da9f 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -420,6 +420,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M6501RM"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "E1404FA"), } }, @@ -539,6 +546,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "Victus by HP Gaming Laptop 15-fb1xxx"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "Victus by HP Gaming Laptop 15-fb2xxx"), } }, @@ -588,6 +602,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "HP"), + DMI_MATCH(DMI_BOARD_NAME, "8A81"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "HP"), DMI_MATCH(DMI_BOARD_NAME, "8B27"), } }, diff --git a/sound/soc/codecs/rt5660.c b/sound/soc/codecs/rt5660.c index 82b92e83be4c..44c3a3b92f98 100644 --- a/sound/soc/codecs/rt5660.c +++ b/sound/soc/codecs/rt5660.c @@ -1315,14 +1315,17 @@ static int rt5660_i2c_probe(struct i2c_client *i2c) regmap_update_bits(rt5660->regmap, RT5660_GPIO_CTRL1, RT5660_GP1_PIN_MASK, RT5660_GP1_PIN_DMIC1_SCL); - if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_GPIO2) + if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_GPIO2) { regmap_update_bits(rt5660->regmap, RT5660_DMIC_CTRL1, RT5660_SEL_DMIC_DATA_MASK, RT5660_SEL_DMIC_DATA_GPIO2); - else if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_IN1P) + regmap_update_bits(rt5660->regmap, RT5660_GPIO_CTRL1, + RT5660_GP2_PIN_MASK, RT5660_GP2_PIN_DMIC1_SDA); + } else if (rt5660->pdata.dmic1_data_pin == RT5660_DMIC1_DATA_IN1P) { regmap_update_bits(rt5660->regmap, RT5660_DMIC_CTRL1, RT5660_SEL_DMIC_DATA_MASK, RT5660_SEL_DMIC_DATA_IN1P); + } } return devm_snd_soc_register_component(&i2c->dev, diff --git a/sound/soc/intel/avs/pcm.c b/sound/soc/intel/avs/pcm.c index ccf90428126d..0efe490024b0 100644 --- a/sound/soc/intel/avs/pcm.c +++ b/sound/soc/intel/avs/pcm.c @@ -1570,11 +1570,13 @@ static void avs_component_hda_unregister_dais(struct snd_soc_component *componen { struct snd_soc_acpi_mach *mach; struct snd_soc_dai *dai, *save; + struct avs_mach_pdata *pdata; struct hda_codec *codec; char name[32]; mach = dev_get_platdata(component->card->dev); - codec = mach->pdata; + pdata = mach->pdata; + codec = pdata->codec; snprintf(name, sizeof(name), "%s-cpu", dev_name(&codec->core.dev)); for_each_component_dais_safe(component, dai, save) { diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig index 128b6876af83..c23fdb6aad4c 100644 --- a/sound/soc/intel/boards/Kconfig +++ b/sound/soc/intel/boards/Kconfig @@ -11,7 +11,7 @@ menuconfig SND_SOC_INTEL_MACH kernel: saying N will just cause the configurator to skip all the questions about Intel ASoC machine drivers. -if SND_SOC_INTEL_MACH +if SND_SOC_INTEL_MACH && (SND_SOC_SOF_INTEL_COMMON || !SND_SOC_SOF_INTEL_COMMON) config SND_SOC_INTEL_USER_FRIENDLY_LONG_NAMES bool "Use more user friendly long card names" diff --git a/sound/soc/intel/common/soc-acpi-intel-arl-match.c b/sound/soc/intel/common/soc-acpi-intel-arl-match.c index 1ad704ca2c5f..6bf7a6250ddc 100644 --- a/sound/soc/intel/common/soc-acpi-intel-arl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-arl-match.c @@ -238,6 +238,15 @@ static const struct snd_soc_acpi_adr_device rt722_0_single_adr[] = { } }; +static const struct snd_soc_acpi_adr_device rt1316_3_single_adr[] = { + { + .adr = 0x000330025D131601ull, + .num_endpoints = 1, + .endpoints = &single_endpoint, + .name_prefix = "rt1316-1" + } +}; + static const struct snd_soc_acpi_adr_device rt1320_2_single_adr[] = { { .adr = 0x000230025D132001ull, @@ -368,6 +377,20 @@ static const struct snd_soc_acpi_link_adr arl_sdca_rvp[] = { {} }; +static const struct snd_soc_acpi_link_adr arl_rt711_l0_rt1316_l3[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt711_sdca_0_adr), + .adr_d = rt711_sdca_0_adr, + }, + { + .mask = BIT(3), + .num_adr = ARRAY_SIZE(rt1316_3_single_adr), + .adr_d = rt1316_3_single_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr arl_rt722_l0_rt1320_l2[] = { { .mask = BIT(0), @@ -482,6 +505,12 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_arl_sdw_machines[] = { .get_function_tplg_files = sof_sdw_get_tplg_files, }, { + .link_mask = BIT(0) | BIT(3), + .links = arl_rt711_l0_rt1316_l3, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-arl-rt711-l0-rt1316-l3.tplg", + }, + { .link_mask = 0x1, /* link0 required */ .links = arl_rvp, .drv_name = "sof_sdw", diff --git a/tools/hv/hv_fcopy_uio_daemon.c b/tools/hv/hv_fcopy_uio_daemon.c index 0198321d14a2..92e8307b2a46 100644 --- a/tools/hv/hv_fcopy_uio_daemon.c +++ b/tools/hv/hv_fcopy_uio_daemon.c @@ -35,7 +35,10 @@ #define WIN8_SRV_MINOR 1 #define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) -#define FCOPY_UIO "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/uio" +#define FCOPY_DEVICE_PATH(subdir) \ + "/sys/bus/vmbus/devices/eb765408-105f-49b6-b4aa-c123b64d17d4/" #subdir +#define FCOPY_UIO_PATH FCOPY_DEVICE_PATH(uio) +#define FCOPY_CHANNELS_PATH FCOPY_DEVICE_PATH(channels) #define FCOPY_VER_COUNT 1 static const int fcopy_versions[] = { @@ -47,9 +50,62 @@ static const int fw_versions[] = { UTIL_FW_VERSION }; -#define HV_RING_SIZE 0x4000 /* 16KB ring buffer size */ +static uint32_t get_ring_buffer_size(void) +{ + char ring_path[PATH_MAX]; + DIR *dir; + struct dirent *entry; + struct stat st; + uint32_t ring_size = 0; + int retry_count = 0; + + /* Find the channel directory */ + dir = opendir(FCOPY_CHANNELS_PATH); + if (!dir) { + usleep(100 * 1000); /* Avoid race with kernel, wait 100ms and retry once */ + dir = opendir(FCOPY_CHANNELS_PATH); + if (!dir) { + syslog(LOG_ERR, "Failed to open channels directory: %s", strerror(errno)); + return 0; + } + } + +retry_once: + while ((entry = readdir(dir)) != NULL) { + if (entry->d_type == DT_DIR && strcmp(entry->d_name, ".") != 0 && + strcmp(entry->d_name, "..") != 0) { + snprintf(ring_path, sizeof(ring_path), "%s/%s/ring", + FCOPY_CHANNELS_PATH, entry->d_name); + + if (stat(ring_path, &st) == 0) { + /* + * stat returns size of Tx, Rx rings combined, + * so take half of it for individual ring size. + */ + ring_size = (uint32_t)st.st_size / 2; + syslog(LOG_INFO, "Ring buffer size from %s: %u bytes", + ring_path, ring_size); + break; + } + } + } + + if (!ring_size && retry_count == 0) { + retry_count = 1; + rewinddir(dir); + usleep(100 * 1000); /* Wait 100ms and retry once */ + goto retry_once; + } + + closedir(dir); -static unsigned char desc[HV_RING_SIZE]; + if (!ring_size) + syslog(LOG_ERR, "Could not determine ring size"); + + return ring_size; +} + +static unsigned char *desc; static int target_fd; static char target_fname[PATH_MAX]; @@ -62,8 +118,11 @@ static int hv_fcopy_create_file(char *file_name, char *path_name, __u32 flags) filesize = 0; p = path_name; - snprintf(target_fname, sizeof(target_fname), "%s/%s", - path_name, file_name); + if (snprintf(target_fname, sizeof(target_fname), "%s/%s", + path_name, file_name) >= sizeof(target_fname)) { + syslog(LOG_ERR, "target file name is too long: %s/%s", path_name, file_name); + goto done; + } /* * Check to see if the path is already in place; if not, @@ -270,7 +329,7 @@ static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size) { size_t len = 0; - while (len < dest_size) { + while (len < dest_size && *src) { if (src[len] < 0x80) dest[len++] = (char)(*src++); else @@ -282,27 +341,15 @@ static void wcstoutf8(char *dest, const __u16 *src, size_t dest_size) static int hv_fcopy_start(struct hv_start_fcopy *smsg_in) { - setlocale(LC_ALL, "en_US.utf8"); - size_t file_size, path_size; - char *file_name, *path_name; - char *in_file_name = (char *)smsg_in->file_name; - char *in_path_name = (char *)smsg_in->path_name; - - file_size = wcstombs(NULL, (const wchar_t *restrict)in_file_name, 0) + 1; - path_size = wcstombs(NULL, (const wchar_t *restrict)in_path_name, 0) + 1; - - file_name = (char *)malloc(file_size * sizeof(char)); - path_name = (char *)malloc(path_size * sizeof(char)); - - if (!file_name || !path_name) { - free(file_name); - free(path_name); - syslog(LOG_ERR, "Can't allocate memory for file name and/or path name"); - return HV_E_FAIL; - } + /* + * file_name and path_name should have same length with appropriate + * member of hv_start_fcopy. + */ + char file_name[W_MAX_PATH], path_name[W_MAX_PATH]; - wcstoutf8(file_name, (__u16 *)in_file_name, file_size); - wcstoutf8(path_name, (__u16 *)in_path_name, path_size); + setlocale(LC_ALL, "en_US.utf8"); + wcstoutf8(file_name, smsg_in->file_name, W_MAX_PATH - 1); + wcstoutf8(path_name, smsg_in->path_name, W_MAX_PATH - 1); return hv_fcopy_create_file(file_name, path_name, smsg_in->copy_flags); } @@ -406,7 +453,7 @@ int main(int argc, char *argv[]) int daemonize = 1, long_index = 0, opt, ret = -EINVAL; struct vmbus_br txbr, rxbr; void *ring; - uint32_t len = HV_RING_SIZE; + uint32_t ring_size, len; char uio_name[NAME_MAX] = {0}; char uio_dev_path[PATH_MAX] = {0}; @@ -437,7 +484,20 @@ int main(int argc, char *argv[]) openlog("HV_UIO_FCOPY", 0, LOG_USER); syslog(LOG_INFO, "starting; pid is:%d", getpid()); - fcopy_get_first_folder(FCOPY_UIO, uio_name); + ring_size = get_ring_buffer_size(); + if (!ring_size) { + ret = -ENODEV; + goto exit; + } + + desc = malloc(ring_size * sizeof(unsigned char)); + if (!desc) { + syslog(LOG_ERR, "malloc failed for desc buffer"); + ret = -ENOMEM; + goto exit; + } + + fcopy_get_first_folder(FCOPY_UIO_PATH, uio_name); snprintf(uio_dev_path, sizeof(uio_dev_path), "/dev/%s", uio_name); fcopy_fd = open(uio_dev_path, O_RDWR); @@ -445,17 +505,17 @@ int main(int argc, char *argv[]) syslog(LOG_ERR, "open %s failed; error: %d %s", uio_dev_path, errno, strerror(errno)); ret = fcopy_fd; - goto exit; + goto free_desc; } - ring = vmbus_uio_map(&fcopy_fd, HV_RING_SIZE); + ring = vmbus_uio_map(&fcopy_fd, ring_size); if (!ring) { ret = errno; syslog(LOG_ERR, "mmap ringbuffer failed; error: %d %s", ret, strerror(ret)); goto close; } - vmbus_br_setup(&txbr, ring, HV_RING_SIZE); - vmbus_br_setup(&rxbr, (char *)ring + HV_RING_SIZE, HV_RING_SIZE); + vmbus_br_setup(&txbr, ring, ring_size); + vmbus_br_setup(&rxbr, (char *)ring + ring_size, ring_size); rxbr.vbr->imask = 0; @@ -472,7 +532,7 @@ int main(int argc, char *argv[]) goto close; } - len = HV_RING_SIZE; + len = ring_size; ret = rte_vmbus_chan_recv_raw(&rxbr, desc, &len); if (unlikely(ret <= 0)) { /* This indicates a failure to communicate (or worse) */ @@ -492,6 +552,8 @@ int main(int argc, char *argv[]) } close: close(fcopy_fd); +free_desc: + free(desc); exit: return ret; } diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 52e353368f58..d41ee26b9443 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -735,7 +735,7 @@ struct bpf_object { struct usdt_manager *usdt_man; - struct bpf_map *arena_map; + int arena_map_idx; void *arena_data; size_t arena_data_sz; @@ -1517,6 +1517,7 @@ static struct bpf_object *bpf_object__new(const char *path, obj->efile.obj_buf_sz = obj_buf_sz; obj->efile.btf_maps_shndx = -1; obj->kconfig_map_idx = -1; + obj->arena_map_idx = -1; obj->kern_version = get_kernel_version(); obj->state = OBJ_OPEN; @@ -2964,7 +2965,7 @@ static int init_arena_map_data(struct bpf_object *obj, struct bpf_map *map, const long page_sz = sysconf(_SC_PAGE_SIZE); size_t mmap_sz; - mmap_sz = bpf_map_mmap_sz(obj->arena_map); + mmap_sz = bpf_map_mmap_sz(map); if (roundup(data_sz, page_sz) > mmap_sz) { pr_warn("elf: sec '%s': declared ARENA map size (%zu) is too small to hold global __arena variables of size %zu\n", sec_name, mmap_sz, data_sz); @@ -3038,12 +3039,12 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, if (map->def.type != BPF_MAP_TYPE_ARENA) continue; - if (obj->arena_map) { + if (obj->arena_map_idx >= 0) { pr_warn("map '%s': only single ARENA map is supported (map '%s' is also ARENA)\n", - map->name, obj->arena_map->name); + map->name, obj->maps[obj->arena_map_idx].name); return -EINVAL; } - obj->arena_map = map; + obj->arena_map_idx = i; if (obj->efile.arena_data) { err = init_arena_map_data(obj, map, ARENA_SEC, obj->efile.arena_data_shndx, @@ -3053,7 +3054,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, return err; } } - if (obj->efile.arena_data && !obj->arena_map) { + if (obj->efile.arena_data && obj->arena_map_idx < 0) { pr_warn("elf: sec '%s': to use global __arena variables the ARENA map should be explicitly declared in SEC(\".maps\")\n", ARENA_SEC); return -ENOENT; @@ -4583,8 +4584,13 @@ static int bpf_program__record_reloc(struct bpf_program *prog, if (shdr_idx == obj->efile.arena_data_shndx) { reloc_desc->type = RELO_DATA; reloc_desc->insn_idx = insn_idx; - reloc_desc->map_idx = obj->arena_map - obj->maps; + reloc_desc->map_idx = obj->arena_map_idx; reloc_desc->sym_off = sym->st_value; + + map = &obj->maps[obj->arena_map_idx]; + pr_debug("prog '%s': found arena map %d (%s, sec %d, off %zu) for insn %u\n", + prog->name, obj->arena_map_idx, map->name, map->sec_idx, + map->sec_offset, insn_idx); return 0; } diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 006b359294a4..8244a5f440b2 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -575,7 +575,9 @@ class YnlFamily(SpecFamily): elif attr["type"] == 'string': attr_payload = str(value).encode('ascii') + b'\x00' elif attr["type"] == 'binary': - if isinstance(value, bytes): + if value is None: + attr_payload = b'' + elif isinstance(value, bytes): attr_payload = value elif isinstance(value, str): if attr.display_hint: @@ -584,6 +586,9 @@ class YnlFamily(SpecFamily): attr_payload = bytes.fromhex(value) elif isinstance(value, dict) and attr.struct_name: attr_payload = self._encode_struct(attr.struct_name, value) + elif isinstance(value, list) and attr.sub_type in NlAttr.type_formats: + format = NlAttr.get_format(attr.sub_type) + attr_payload = b''.join([format.pack(x) for x in value]) else: raise Exception(f'Unknown type for binary attribute, value: {value}') elif attr['type'] in NlAttr.type_formats or attr.is_auto_scalar: diff --git a/tools/objtool/check.c b/tools/objtool/check.c index d967ac001498..67d76f3a1dce 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -224,6 +224,7 @@ static bool is_rust_noreturn(const struct symbol *func) str_ends_with(func->name, "_4core9panicking14panic_explicit") || str_ends_with(func->name, "_4core9panicking14panic_nounwind") || str_ends_with(func->name, "_4core9panicking18panic_bounds_check") || + str_ends_with(func->name, "_4core9panicking18panic_nounwind_fmt") || str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || str_ends_with(func->name, "_4core9panicking30panic_null_pointer_dereference") || str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || diff --git a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c index 8100509e561b..0ffa01d54ce2 100644 --- a/tools/testing/selftests/bpf/prog_tests/recursive_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/recursive_attach.c @@ -149,3 +149,70 @@ close_prog: fentry_recursive_target__destroy(target_skel); fentry_recursive__destroy(tracing_skel); } + +static void *fentry_target_test_run(void *arg) +{ + for (;;) { + int prog_fd = __atomic_load_n((int *)arg, __ATOMIC_SEQ_CST); + LIBBPF_OPTS(bpf_test_run_opts, topts); + int err; + + if (prog_fd == -1) + break; + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "fentry_target test_run")) + break; + } + + return NULL; +} + +void test_fentry_attach_stress(void) +{ + struct fentry_recursive_target *target_skel = NULL; + struct fentry_recursive *tracing_skel = NULL; + struct bpf_program *prog; + int err, i, tgt_prog_fd; + pthread_t thread; + + target_skel = fentry_recursive_target__open_and_load(); + if (!ASSERT_OK_PTR(target_skel, + "fentry_recursive_target__open_and_load")) + goto close_prog; + tgt_prog_fd = bpf_program__fd(target_skel->progs.fentry_target); + err = pthread_create(&thread, NULL, + fentry_target_test_run, &tgt_prog_fd); + if (!ASSERT_OK(err, "bpf_program__set_attach_target")) + goto close_prog; + + for (i = 0; i < 1000; i++) { + tracing_skel = fentry_recursive__open(); + if (!ASSERT_OK_PTR(tracing_skel, "fentry_recursive__open")) + goto stop_thread; + + prog = tracing_skel->progs.recursive_attach; + err = bpf_program__set_attach_target(prog, tgt_prog_fd, + "fentry_target"); + if (!ASSERT_OK(err, "bpf_program__set_attach_target")) + goto stop_thread; + + err = fentry_recursive__load(tracing_skel); + if (!ASSERT_OK(err, "fentry_recursive__load")) + goto stop_thread; + + err = fentry_recursive__attach(tracing_skel); + if (!ASSERT_OK(err, "fentry_recursive__attach")) + goto stop_thread; + + fentry_recursive__destroy(tracing_skel); + tracing_skel = NULL; + } + +stop_thread: + __atomic_store_n(&tgt_prog_fd, -1, __ATOMIC_SEQ_CST); + err = pthread_join(thread, NULL); + ASSERT_OK(err, "pthread_join"); +close_prog: + fentry_recursive__destroy(tracing_skel); + fentry_recursive_target__destroy(target_skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c index 4be6fdb78c6a..594441acb707 100644 --- a/tools/testing/selftests/bpf/prog_tests/snprintf.c +++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c @@ -116,6 +116,8 @@ static void test_snprintf_negative(void) ASSERT_ERR(load_single_snprintf("%llc"), "invalid specifier 7"); ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character"); ASSERT_ERR(load_single_snprintf("\x1"), "non printable character"); + ASSERT_ERR(load_single_snprintf("%p%"), "invalid specifier 8"); + ASSERT_ERR(load_single_snprintf("%s%"), "invalid specifier 9"); } void test_snprintf(void) diff --git a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c index a4517bee34d5..27781df8f2fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/prog_tests/sock_iter_batch.c @@ -1,11 +1,13 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2024 Meta +#include <poll.h> #include <test_progs.h> #include "network_helpers.h" #include "sock_iter_batch.skel.h" #define TEST_NS "sock_iter_batch_netns" +#define TEST_CHILD_NS "sock_iter_batch_child_netns" static const int init_batch_size = 16; static const int nr_soreuse = 4; @@ -118,6 +120,45 @@ done: return nth_sock_idx; } +static void destroy(int fd) +{ + struct sock_iter_batch *skel = NULL; + __u64 cookie = socket_cookie(fd); + struct bpf_link *link = NULL; + int iter_fd = -1; + int nread; + __u64 out; + + skel = sock_iter_batch__open(); + if (!ASSERT_OK_PTR(skel, "sock_iter_batch__open")) + goto done; + + skel->rodata->destroy_cookie = cookie; + + if (!ASSERT_OK(sock_iter_batch__load(skel), "sock_iter_batch__load")) + goto done; + + link = bpf_program__attach_iter(skel->progs.iter_tcp_destroy, NULL); + if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter")) + goto done; + + iter_fd = bpf_iter_create(bpf_link__fd(link)); + if (!ASSERT_OK_FD(iter_fd, "bpf_iter_create")) + goto done; + + /* Delete matching socket. */ + nread = read(iter_fd, &out, sizeof(out)); + ASSERT_GE(nread, 0, "nread"); + if (nread) + ASSERT_EQ(out, cookie, "cookie matches"); +done: + if (iter_fd >= 0) + close(iter_fd); + bpf_link__destroy(link); + sock_iter_batch__destroy(skel); + close(fd); +} + static int get_seen_count(int fd, struct sock_count counts[], int n) { __u64 cookie = socket_cookie(fd); @@ -152,8 +193,71 @@ static void check_n_were_seen_once(int *fds, int fds_len, int n, ASSERT_EQ(seen_once, n, "seen_once"); } +static int accept_from_one(struct pollfd *server_poll_fds, + int server_poll_fds_len) +{ + static const int poll_timeout_ms = 5000; /* 5s */ + int ret; + int i; + + ret = poll(server_poll_fds, server_poll_fds_len, poll_timeout_ms); + if (!ASSERT_EQ(ret, 1, "poll")) + return -1; + + for (i = 0; i < server_poll_fds_len; i++) + if (server_poll_fds[i].revents & POLLIN) + return accept(server_poll_fds[i].fd, NULL, NULL); + + return -1; +} + +static int *connect_to_server(int family, int sock_type, const char *addr, + __u16 port, int nr_connects, int *server_fds, + int server_fds_len) +{ + struct pollfd *server_poll_fds = NULL; + int *established_socks = NULL; + int i; + + server_poll_fds = calloc(server_fds_len, sizeof(*server_poll_fds)); + if (!ASSERT_OK_PTR(server_poll_fds, "server_poll_fds")) + return NULL; + + for (i = 0; i < server_fds_len; i++) { + server_poll_fds[i].fd = server_fds[i]; + server_poll_fds[i].events = POLLIN; + } + + i = 0; + + established_socks = malloc(sizeof(*established_socks) * nr_connects*2); + if (!ASSERT_OK_PTR(established_socks, "established_socks")) + goto error; + + while (nr_connects--) { + established_socks[i] = connect_to_addr_str(family, sock_type, + addr, port, NULL); + if (!ASSERT_OK_FD(established_socks[i], "connect_to_addr_str")) + goto error; + i++; + established_socks[i] = accept_from_one(server_poll_fds, + server_fds_len); + if (!ASSERT_OK_FD(established_socks[i], "accept_from_one")) + goto error; + i++; + } + + free(server_poll_fds); + return established_socks; +error: + free_fds(established_socks, i); + free(server_poll_fds); + return NULL; +} + static void remove_seen(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int close_idx; @@ -182,8 +286,46 @@ static void remove_seen(int family, int sock_type, const char *addr, __u16 port, counts_len); } +static void remove_seen_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Leave one established socket. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Close a socket we've already seen to remove it from the bucket. */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the last socket wasn't skipped and that there were no + * repeats. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_unseen(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -214,8 +356,54 @@ static void remove_unseen(int family, int sock_type, const char *addr, counts_len); } +static void remove_unseen_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int close_idx; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close what would be the next socket in the bucket to exercise the + * condition where we need to skip past the first cookie we remembered. + */ + close_idx = get_nth_socket(established_socks, established_socks_len, + link, listen_socks_len + 1); + if (!ASSERT_GE(close_idx, 0, "close_idx")) + return; + + destroy(established_socks[close_idx]); + established_socks[close_idx] = -1; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure the remaining sockets were seen exactly once and that we + * didn't repeat the socket that was already seen. + */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); +} + static void remove_all(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -242,8 +430,57 @@ static void remove_all(int family, int sock_type, const char *addr, ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); } +static void remove_all_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + int *close_idx = NULL; + int i; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established socket. */ + read_n(iter_fd, 1, counts, counts_len); + + /* Make sure we saw one established socks. */ + check_n_were_seen_once(established_socks, established_socks_len, 1, + counts, counts_len); + + /* Close all remaining sockets to exhaust the list of saved cookies and + * exit without putting any sockets into the batch on the next read. + */ + close_idx = malloc(sizeof(int) * (established_socks_len - 1)); + if (!ASSERT_OK_PTR(close_idx, "close_idx malloc")) + return; + for (i = 0; i < established_socks_len - 1; i++) { + close_idx[i] = get_nth_socket(established_socks, + established_socks_len, link, + listen_socks_len + i); + if (!ASSERT_GE(close_idx[i], 0, "close_idx")) + return; + } + + for (i = 0; i < established_socks_len - 1; i++) { + destroy(established_socks[close_idx[i]]); + established_socks[close_idx[i]] = -1; + } + + /* Make sure there are no more sockets returned */ + ASSERT_EQ(read_n(iter_fd, -1, counts, counts_len), 0, "read_n"); + free(close_idx); +} + static void add_some(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { int *new_socks = NULL; @@ -271,8 +508,52 @@ done: free_fds(new_socks, socks_len); } +static void add_some_established(int family, int sock_type, const char *addr, + __u16 port, int *listen_socks, + int listen_socks_len, int *established_socks, + int established_socks_len, + struct sock_count *counts, + int counts_len, struct bpf_link *link, + int iter_fd) +{ + int *new_socks = NULL; + + /* Iterate through all listening sockets. */ + read_n(iter_fd, listen_socks_len, counts, counts_len); + + /* Make sure we saw all listening sockets exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + + /* Iterate through the first established_socks_len - 1 sockets. */ + read_n(iter_fd, established_socks_len - 1, counts, counts_len); + + /* Make sure we saw established_socks_len - 1 sockets exactly once. */ + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len - 1, counts, counts_len); + + /* Double the number of established sockets in the bucket. */ + new_socks = connect_to_server(family, sock_type, addr, port, + established_socks_len / 2, listen_socks, + listen_socks_len); + if (!ASSERT_OK_PTR(new_socks, "connect_to_server")) + goto done; + + /* Iterate through the rest of the sockets. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each of the original sockets was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +done: + free_fds(new_socks, established_socks_len); +} + static void force_realloc(int family, int sock_type, const char *addr, __u16 port, int *socks, int socks_len, + int *established_socks, int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd) { @@ -299,11 +580,32 @@ done: free_fds(new_socks, socks_len); } +static void force_realloc_established(int family, int sock_type, + const char *addr, __u16 port, + int *listen_socks, int listen_socks_len, + int *established_socks, + int established_socks_len, + struct sock_count *counts, int counts_len, + struct bpf_link *link, int iter_fd) +{ + /* Iterate through all sockets to trigger a realloc. */ + read_n(iter_fd, -1, counts, counts_len); + + /* Make sure each socket was seen exactly once. */ + check_n_were_seen_once(listen_socks, listen_socks_len, listen_socks_len, + counts, counts_len); + check_n_were_seen_once(established_socks, established_socks_len, + established_socks_len, counts, counts_len); +} + struct test_case { void (*test)(int family, int sock_type, const char *addr, __u16 port, - int *socks, int socks_len, struct sock_count *counts, + int *socks, int socks_len, int *established_socks, + int established_socks_len, struct sock_count *counts, int counts_len, struct bpf_link *link, int iter_fd); const char *description; + int ehash_buckets; + int connections; int init_socks; int max_socks; int sock_type; @@ -358,18 +660,140 @@ static struct test_case resume_tests[] = { .family = AF_INET6, .test = force_realloc, }, + { + .description = "tcp: resume after removing a seen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen, + }, + { + .description = "tcp: resume after removing one unseen socket (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen, + }, + { + .description = "tcp: resume after removing all unseen sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all, + }, + { + .description = "tcp: resume after adding a few sockets (listening)", + .init_socks = nr_soreuse, + .max_socks = nr_soreuse, + .sock_type = SOCK_STREAM, + /* Use AF_INET so that new sockets are added to the head of the + * bucket's list. + */ + .family = AF_INET, + .test = add_some, + }, + { + .description = "tcp: force a realloc to occur (listening)", + .init_socks = init_batch_size, + .max_socks = init_batch_size * 2, + .sock_type = SOCK_STREAM, + /* Use AF_INET6 so that new sockets are added to the tail of the + * bucket's list, needing to be added to the next batch to force + * a realloc. + */ + .family = AF_INET6, + .test = force_realloc, + }, + { + .description = "tcp: resume after removing a seen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_seen_established, + }, + { + .description = "tcp: resume after removing one unseen socket (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_unseen_established, + }, + { + .description = "tcp: resume after removing all unseen sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = remove_all_established, + }, + { + .description = "tcp: resume after adding a few sockets (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + .connections = nr_soreuse, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse * 3, + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = add_some_established, + }, + { + .description = "tcp: force a realloc to occur (established)", + /* Force all established sockets into one bucket */ + .ehash_buckets = 1, + /* Bucket size will need to double when going from listening to + * established sockets. + */ + .connections = init_batch_size, + .init_socks = nr_soreuse, + /* Room for connect()ed and accept()ed sockets */ + .max_socks = nr_soreuse + (init_batch_size * 2), + .sock_type = SOCK_STREAM, + .family = AF_INET6, + .test = force_realloc_established, + }, }; static void do_resume_test(struct test_case *tc) { struct sock_iter_batch *skel = NULL; + struct sock_count *counts = NULL; static const __u16 port = 10001; + struct nstoken *nstoken = NULL; struct bpf_link *link = NULL; - struct sock_count *counts; + int *established_fds = NULL; int err, iter_fd = -1; const char *addr; int *fds = NULL; - int local_port; + + if (tc->ehash_buckets) { + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS(done, "sysctl -wq net.ipv4.tcp_child_ehash_entries=%d", + tc->ehash_buckets); + SYS(done, "ip netns add %s", TEST_CHILD_NS); + SYS(done, "ip -net %s link set dev lo up", TEST_CHILD_NS); + nstoken = open_netns(TEST_CHILD_NS); + if (!ASSERT_OK_PTR(nstoken, "open_child_netns")) + goto done; + } counts = calloc(tc->max_socks, sizeof(*counts)); if (!ASSERT_OK_PTR(counts, "counts")) @@ -384,11 +808,18 @@ static void do_resume_test(struct test_case *tc) tc->init_socks); if (!ASSERT_OK_PTR(fds, "start_reuseport_server")) goto done; - local_port = get_socket_local_port(*fds); - if (!ASSERT_GE(local_port, 0, "get_socket_local_port")) - goto done; - skel->rodata->ports[0] = ntohs(local_port); + if (tc->connections) { + established_fds = connect_to_server(tc->family, tc->sock_type, + addr, port, + tc->connections, fds, + tc->init_socks); + if (!ASSERT_OK_PTR(established_fds, "connect_to_server")) + goto done; + } + skel->rodata->ports[0] = 0; + skel->rodata->ports[1] = 0; skel->rodata->sf = tc->family; + skel->rodata->ss = 0; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) @@ -406,10 +837,15 @@ static void do_resume_test(struct test_case *tc) goto done; tc->test(tc->family, tc->sock_type, addr, port, fds, tc->init_socks, - counts, tc->max_socks, link, iter_fd); + established_fds, tc->connections*2, counts, tc->max_socks, + link, iter_fd); done: + close_netns(nstoken); + SYS_NOFAIL("ip netns del " TEST_CHILD_NS); + SYS_NOFAIL("sysctl -w net.ipv4.tcp_child_ehash_entries=0"); free(counts); free_fds(fds, tc->init_socks); + free_fds(established_fds, tc->connections*2); if (iter_fd >= 0) close(iter_fd); bpf_link__destroy(link); @@ -454,6 +890,8 @@ static void do_test(int sock_type, bool onebyone) skel->rodata->ports[i] = ntohs(local_port); } skel->rodata->sf = AF_INET6; + if (sock_type == SOCK_STREAM) + skel->rodata->ss = TCP_LISTEN; err = sock_iter_batch__load(skel); if (!ASSERT_OK(err, "sock_iter_batch__load")) diff --git a/tools/testing/selftests/bpf/progs/sock_iter_batch.c b/tools/testing/selftests/bpf/progs/sock_iter_batch.c index 8f483337e103..77966ded5467 100644 --- a/tools/testing/selftests/bpf/progs/sock_iter_batch.c +++ b/tools/testing/selftests/bpf/progs/sock_iter_batch.c @@ -23,6 +23,7 @@ static bool ipv4_addr_loopback(__be32 a) } volatile const unsigned int sf; +volatile const unsigned int ss; volatile const __u16 ports[2]; unsigned int bucket[2]; @@ -42,16 +43,18 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_state != TCP_LISTEN || - sk->sk_family == AF_INET6 ? + (ss && sk->sk_state != ss) || + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; @@ -67,6 +70,27 @@ int iter_tcp_soreuse(struct bpf_iter__tcp *ctx) return 0; } +volatile const __u64 destroy_cookie; + +SEC("iter/tcp") +int iter_tcp_destroy(struct bpf_iter__tcp *ctx) +{ + struct sock_common *sk_common = (struct sock_common *)ctx->sk_common; + __u64 sock_cookie; + + if (!sk_common) + return 0; + + sock_cookie = bpf_get_socket_cookie(sk_common); + if (sock_cookie != destroy_cookie) + return 0; + + bpf_sock_destroy(sk_common); + bpf_seq_write(ctx->meta->seq, &sock_cookie, sizeof(sock_cookie)); + + return 0; +} + #define udp_sk(ptr) container_of(ptr, struct udp_sock, inet.sk) SEC("iter/udp") @@ -83,15 +107,17 @@ int iter_udp_soreuse(struct bpf_iter__udp *ctx) sock_cookie = bpf_get_socket_cookie(sk); sk = bpf_core_cast(sk, struct sock); if (sk->sk_family != sf || - sk->sk_family == AF_INET6 ? + (sk->sk_family == AF_INET6 ? !ipv6_addr_loopback(&sk->sk_v6_rcv_saddr) : - !ipv4_addr_loopback(sk->sk_rcv_saddr)) + !ipv4_addr_loopback(sk->sk_rcv_saddr))) return 0; if (sk->sk_num == ports[0]) idx = 0; else if (sk->sk_num == ports[1]) idx = 1; + else if (!ports[0] && !ports[1]) + idx = 0; else return 0; diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 9bd84d6b542e..3556f3563e08 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -22,6 +22,7 @@ TEST_PROGS := \ stats.py \ shaper.py \ hds.py \ + xdp.py \ # end of TEST_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py index 820d8a03becc..835c357919a8 100755 --- a/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py +++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py @@ -208,14 +208,14 @@ def setup_devlink_rate(cfg): "port-index": port_index, "rate-tx-max": 125000000, "rate-tc-bws": [ - {"rate-tc-index": 0, "rate-tc-bw": 0}, - {"rate-tc-index": 1, "rate-tc-bw": 0}, - {"rate-tc-index": 2, "rate-tc-bw": 0}, - {"rate-tc-index": 3, "rate-tc-bw": 20}, - {"rate-tc-index": 4, "rate-tc-bw": 80}, - {"rate-tc-index": 5, "rate-tc-bw": 0}, - {"rate-tc-index": 6, "rate-tc-bw": 0}, - {"rate-tc-index": 7, "rate-tc-bw": 0}, + {"index": 0, "bw": 0}, + {"index": 1, "bw": 0}, + {"index": 2, "bw": 0}, + {"index": 3, "bw": 20}, + {"index": 4, "bw": 80}, + {"index": 5, "bw": 0}, + {"index": 6, "bw": 0}, + {"index": 7, "bw": 0}, ] }) except NlError as exc: diff --git a/tools/testing/selftests/drivers/net/hw/rss_api.py b/tools/testing/selftests/drivers/net/hw/rss_api.py index 6ae908bed1a4..19847f3d4a00 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_api.py +++ b/tools/testing/selftests/drivers/net/hw/rss_api.py @@ -5,14 +5,23 @@ API level tests for RSS (mostly Netlink vs IOCTL). """ +import errno import glob -from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_is, ksft_ne +import random +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_is, ksft_ne, ksft_raises from lib.py import KsftSkipEx, KsftFailEx -from lib.py import defer, ethtool -from lib.py import EthtoolFamily +from lib.py import defer, ethtool, CmdExitFailure +from lib.py import EthtoolFamily, NlError from lib.py import NetDrvEnv +def _require_2qs(cfg): + qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*")) + if qcnt < 2: + raise KsftSkipEx(f"Local has only {qcnt} queues") + return qcnt + + def _ethtool_create(cfg, act, opts): output = ethtool(f"{act} {cfg.ifname} {opts}").stdout # Output will be something like: "New RSS context is 1" or @@ -52,15 +61,101 @@ def _ethtool_get_cfg(cfg, fl_type, to_nl=False): return ret +def test_rxfh_nl_set_fail(cfg): + """ + Test error path of Netlink SET. + """ + _require_2qs(cfg) + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + with ksft_raises(NlError): + ethnl.rss_set({"header": {"dev-name": "lo"}, + "indir": None}) + + with ksft_raises(NlError): + ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [100000]}) + ntf = next(ethnl.poll_ntf(duration=0.2), None) + ksft_is(ntf, None) + + +def test_rxfh_nl_set_indir(cfg): + """ + Test setting indirection table via Netlink. + """ + qcnt = _require_2qs(cfg) + + # Test some SETs with a value + reset = defer(cfg.ethnl.rss_set, + {"header": {"dev-index": cfg.ifindex}, "indir": None}) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), {1}) + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [0, 1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + # Make sure we can't set the queue count below max queue used + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 0 rx 1") + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 1 rx 0") + + # Test reset back to default + reset.exec() + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(set(rss.get("indir", [-1])), set(range(qcnt))) + + +def test_rxfh_nl_set_indir_ctx(cfg): + """ + Test setting indirection table for a custom context via Netlink. + """ + _require_2qs(cfg) + + # Get setting for ctx 0, we'll make sure they don't get clobbered + dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + + # Create context + ctx_id = _ethtool_create(cfg, "-X", "context new") + defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id, "indir": [1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id}) + ksft_eq(set(rss.get("indir", [-1])), {1}) + + ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(ctx0, dflt) + + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id, "indir": [0, 1]}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}, + "context": ctx_id}) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(ctx0, dflt) + + # Make sure we can't set the queue count below max queue used + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 0 rx 1") + with ksft_raises(CmdExitFailure): + ethtool(f"-L {cfg.ifname} combined 1 rx 0") + + def test_rxfh_indir_ntf(cfg): """ Check that Netlink notifications are generated when RSS indirection table was modified. """ - - qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*")) - if qcnt < 2: - raise KsftSkipEx(f"Local has only {qcnt} queues") + _require_2qs(cfg) ethnl = EthtoolFamily() ethnl.ntf_subscribe("monitor") @@ -88,10 +183,7 @@ def test_rxfh_indir_ctx_ntf(cfg): Check that Netlink notifications are generated when RSS indirection table was modified on an additional RSS context. """ - - qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*")) - if qcnt < 2: - raise KsftSkipEx(f"Local has only {qcnt} queues") + _require_2qs(cfg) ctx_id = _ethtool_create(cfg, "-X", "context new") defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") @@ -109,6 +201,38 @@ def test_rxfh_indir_ctx_ntf(cfg): ksft_eq(set(ntf["msg"]["indir"]), {1}) +def test_rxfh_nl_set_key(cfg): + """ + Test setting hashing key via Netlink. + """ + + dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + defer(cfg.ethnl.rss_set, + {"header": {"dev-index": cfg.ifindex}, + "hkey": dflt["hkey"], "indir": None}) + + # Empty key should error out + with ksft_raises(NlError) as cm: + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hkey": None}) + ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.hkey') + + # Set key to random + mod = random.randbytes(len(dflt["hkey"])) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "hkey": mod}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(rss.get("hkey", [-1]), mod) + + # Set key to random and indir tbl to something at once + mod = random.randbytes(len(dflt["hkey"])) + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "indir": [0, 1], "hkey": mod}) + rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(rss.get("hkey", [-1]), mod) + ksft_eq(set(rss.get("indir", [-1])), {0, 1}) + + def test_rxfh_fields(cfg): """ Test reading Rx Flow Hash over Netlink. @@ -124,10 +248,226 @@ def test_rxfh_fields(cfg): comment="Config for " + fl_type) +def test_rxfh_fields_set(cfg): + """ Test configuring Rx Flow Hash over Netlink. """ + + flow_types = ["tcp4", "tcp6", "udp4", "udp6"] + + # Collect current settings + cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # symmetric hashing is config-order-sensitive make sure we leave + # symmetric mode, or make the flow-hash sym-compatible first + changes = [{"flow-hash": cfg_old["flow-hash"],}, + {"input-xfrm": cfg_old.get("input-xfrm", {}),}] + if cfg_old.get("input-xfrm"): + changes = list(reversed(changes)) + for old in changes: + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old) + + # symmetric hashing prevents some of the configs below + if cfg_old.get("input-xfrm"): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "input-xfrm": {}}) + + for fl_type in flow_types: + cur = _ethtool_get_cfg(cfg, fl_type) + if cur == "sdfn": + change_nl = {"ip-src", "ip-dst"} + change_ic = "sd" + else: + change_nl = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"} + change_ic = "sdfn" + + cfg.ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {fl_type: change_nl} + }) + reset = defer(ethtool, f"--disable-netlink -N {cfg.ifname} " + f"rx-flow-hash {fl_type} {cur}") + + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(change_nl, cfg_nl["flow-hash"][fl_type], + comment=f"Config for {fl_type} over Netlink") + cfg_ic = _ethtool_get_cfg(cfg, fl_type) + ksft_eq(change_ic, cfg_ic, + comment=f"Config for {fl_type} over IOCTL") + + reset.exec() + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + ksft_eq(cfg_old["flow-hash"][fl_type], cfg_nl["flow-hash"][fl_type], + comment=f"Un-config for {fl_type} over Netlink") + cfg_ic = _ethtool_get_cfg(cfg, fl_type) + ksft_eq(cur, cfg_ic, comment=f"Un-config for {fl_type} over IOCTL") + + # Try to set multiple at once, the defer was already installed at the start + change = {"ip-src"} + if change == cfg_old["flow-hash"]["tcp4"]: + change = {"ip-dst"} + cfg.ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {x: change for x in flow_types} + }) + + cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + for fl_type in flow_types: + ksft_eq(change, cfg_nl["flow-hash"][fl_type], + comment=f"multi-config for {fl_type} over Netlink") + + +def test_rxfh_fields_set_xfrm(cfg): + """ Test changing Rx Flow Hash vs xfrm_input at once. """ + + def set_rss(cfg, xfrm, fh): + cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex}, + "input-xfrm": xfrm, "flow-hash": fh}) + + # Install the reset handler + cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}}) + # symmetric hashing is config-order-sensitive make sure we leave + # symmetric mode, or make the flow-hash sym-compatible first + changes = [{"flow-hash": cfg_old["flow-hash"],}, + {"input-xfrm": cfg_old.get("input-xfrm", {}),}] + if cfg_old.get("input-xfrm"): + changes = list(reversed(changes)) + for old in changes: + defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old) + + # Make sure we start with input-xfrm off, and tcp4 config non-sym + set_rss(cfg, {}, {}) + set_rss(cfg, {}, {"tcp4": {"ip-src"}}) + + # Setting sym and fixing tcp4 config not expected to pass right now + with ksft_raises(NlError): + set_rss(cfg, {"sym-xor"}, {"tcp4": {"ip-src", "ip-dst"}}) + # One at a time should work, hopefully + set_rss(cfg, 0, {"tcp4": {"ip-src", "ip-dst"}}) + no_support = False + try: + set_rss(cfg, {"sym-xor"}, {}) + except NlError: + try: + set_rss(cfg, {"sym-or-xor"}, {}) + except NlError: + no_support = True + if no_support: + raise KsftSkipEx("no input-xfrm supported") + # Disabling two at once should not work either without kernel changes + with ksft_raises(NlError): + set_rss(cfg, {}, {"tcp4": {"ip-src"}}) + + +def test_rxfh_fields_ntf(cfg): + """ Test Rx Flow Hash notifications. """ + + cur = _ethtool_get_cfg(cfg, "tcp4") + if cur == "sdfn": + change = {"ip-src", "ip-dst"} + else: + change = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"} + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + ethnl.rss_set({ + "header": {"dev-index": cfg.ifindex}, + "flow-hash": {"tcp4": change} + }) + reset = defer(ethtool, + f"--disable-netlink -N {cfg.ifname} rx-flow-hash tcp4 {cur}") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after IOCTL change") + ksft_eq(ntf["name"], "rss-ntf") + ksft_eq(ntf["msg"]["flow-hash"]["tcp4"], change) + ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None) + + reset.exec() + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("No notification received after Netlink change") + ksft_eq(ntf["name"], "rss-ntf") + ksft_ne(ntf["msg"]["flow-hash"]["tcp4"], change) + ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None) + + +def test_rss_ctx_add(cfg): + """ Test creating an additional RSS context via Netlink """ + + _require_2qs(cfg) + + # Test basic creation + ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}}) + d = defer(ethtool, f"-X {cfg.ifname} context {ctx.get('context')} delete") + ksft_ne(ctx.get("context", 0), 0) + ksft_ne(set(ctx.get("indir", [0])), {0}, + comment="Driver should init the indirection table") + + # Try requesting the ID we just got allocated + with ksft_raises(NlError) as cm: + ctx = cfg.ethnl.rss_create_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx.get("context"), + }) + ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete") + d.exec() + ksft_eq(cm.exception.nl_msg.error, -errno.EBUSY) + + # Test creating with a specified RSS table, and context ID + ctx_id = ctx.get("context") + ctx = cfg.ethnl.rss_create_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx_id, + "indir": [1], + }) + ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete") + ksft_eq(ctx.get("context"), ctx_id) + ksft_eq(set(ctx.get("indir", [0])), {1}) + + +def test_rss_ctx_ntf(cfg): + """ Test notifications for creating additional RSS contexts """ + + ethnl = EthtoolFamily() + ethnl.ntf_subscribe("monitor") + + # Create / delete via Netlink + ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}}) + cfg.ethnl.rss_delete_act({ + "header": {"dev-index": cfg.ifindex}, + "context": ctx["context"], + }) + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[NL] No notification after context creation") + ksft_eq(ntf["name"], "rss-create-ntf") + ksft_eq(ctx, ntf["msg"]) + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[NL] No notification after context deletion") + ksft_eq(ntf["name"], "rss-delete-ntf") + + # Create / deleve via IOCTL + ctx_id = _ethtool_create(cfg, "--disable-netlink -X", "context new") + ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} delete") + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[IOCTL] No notification after context creation") + ksft_eq(ntf["name"], "rss-create-ntf") + + ntf = next(ethnl.poll_ntf(duration=0.2), None) + if ntf is None: + raise KsftFailEx("[IOCTL] No notification after context deletion") + ksft_eq(ntf["name"], "rss-delete-ntf") + + def main() -> None: """ Ksft boiler plate main """ with NetDrvEnv(__file__, nsim_test=False) as cfg: + cfg.ethnl = EthtoolFamily() ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, )) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py index 648ff50bc1c3..6e90fb290564 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py +++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py @@ -37,11 +37,11 @@ def test_rss_input_xfrm(cfg, ipver): if not hasattr(socket, "SO_INCOMING_CPU"): raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11") - input_xfrm = cfg.ethnl.rss_get( - {'header': {'dev-name': cfg.ifname}}).get('input-xfrm') + rss = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}}) + input_xfrm = set(filter(lambda x: 'sym' in x, rss.get('input-xfrm', {}))) # Check for symmetric xor/or-xor - if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2): + if not input_xfrm: raise KsftSkipEx("Symmetric RSS hash not requested") cpus = set() diff --git a/tools/testing/selftests/drivers/net/lib/py/load.py b/tools/testing/selftests/drivers/net/lib/py/load.py index d9c10613ae67..44151b7b1a24 100644 --- a/tools/testing/selftests/drivers/net/lib/py/load.py +++ b/tools/testing/selftests/drivers/net/lib/py/load.py @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 +import re import time from lib.py import ksft_pr, cmd, ip, rand_port, wait_port_listen @@ -10,12 +11,11 @@ class GenerateTraffic: self.env = env - if port is None: - port = rand_port() - self._iperf_server = cmd(f"iperf3 -s -1 -p {port}", background=True) - wait_port_listen(port) + self.port = rand_port() if port is None else port + self._iperf_server = cmd(f"iperf3 -s -1 -p {self.port}", background=True) + wait_port_listen(self.port) time.sleep(0.1) - self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {port} -t 86400", + self._iperf_client = cmd(f"iperf3 -c {env.addr} -P 16 -p {self.port} -t 86400", background=True, host=env.remote) # Wait for traffic to ramp up @@ -56,3 +56,16 @@ class GenerateTraffic: ksft_pr(">> Server:") ksft_pr(self._iperf_server.stdout) ksft_pr(self._iperf_server.stderr) + self._wait_client_stopped() + + def _wait_client_stopped(self, sleep=0.005, timeout=5): + end = time.monotonic() + timeout + + live_port_pattern = re.compile(fr":{self.port:04X} 0[^6] ") + + while time.monotonic() < end: + data = cmd("cat /proc/net/tcp*", host=self.env.remote).stdout + if not live_port_pattern.search(data): + return + time.sleep(sleep) + raise Exception(f"Waiting for client to stop timed out after {timeout}s") diff --git a/tools/testing/selftests/drivers/net/napi_id.py b/tools/testing/selftests/drivers/net/napi_id.py index 356bac46ba04..d05eddcad539 100755 --- a/tools/testing/selftests/drivers/net/napi_id.py +++ b/tools/testing/selftests/drivers/net/napi_id.py @@ -7,10 +7,10 @@ from lib.py import bkg, cmd, rand_port, NetNSEnter def test_napi_id(cfg) -> None: port = rand_port() - listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr_v['4']} {port}" + listen_cmd = f"{cfg.test_dir}/napi_id_helper {cfg.addr} {port}" with bkg(listen_cmd, ksft_wait=3) as server: - cmd(f"echo a | socat - TCP:{cfg.addr_v['4']}:{port}", host=cfg.remote, shell=True) + cmd(f"echo a | socat - TCP:{cfg.baddr}:{port}", host=cfg.remote, shell=True) ksft_eq(0, server.ret) diff --git a/tools/testing/selftests/drivers/net/napi_id_helper.c b/tools/testing/selftests/drivers/net/napi_id_helper.c index eecd610c2109..7f49ca6c8637 100644 --- a/tools/testing/selftests/drivers/net/napi_id_helper.c +++ b/tools/testing/selftests/drivers/net/napi_id_helper.c @@ -7,41 +7,58 @@ #include <unistd.h> #include <arpa/inet.h> #include <sys/socket.h> +#include <netdb.h> #include "../../net/lib/ksft.h" int main(int argc, char *argv[]) { - struct sockaddr_in address; + struct sockaddr_storage address; + struct addrinfo *result; + struct addrinfo hints; unsigned int napi_id; - unsigned int port; + socklen_t addr_len; socklen_t optlen; char buf[1024]; int opt = 1; + int family; int server; int client; int ret; - server = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + memset(&hints, 0, sizeof(hints)); + hints.ai_family = AF_UNSPEC; + hints.ai_socktype = SOCK_STREAM; + hints.ai_flags = AI_PASSIVE; + + ret = getaddrinfo(argv[1], argv[2], &hints, &result); + if (ret != 0) { + fprintf(stderr, "getaddrinfo: %s\n", gai_strerror(ret)); + return 1; + } + + family = result->ai_family; + addr_len = result->ai_addrlen; + + server = socket(family, SOCK_STREAM, IPPROTO_TCP); if (server < 0) { perror("socket creation failed"); + freeaddrinfo(result); if (errno == EAFNOSUPPORT) return -1; return 1; } - port = atoi(argv[2]); - if (setsockopt(server, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt))) { perror("setsockopt"); + freeaddrinfo(result); return 1; } - address.sin_family = AF_INET; - inet_pton(AF_INET, argv[1], &address.sin_addr); - address.sin_port = htons(port); + memcpy(&address, result->ai_addr, result->ai_addrlen); + freeaddrinfo(result); - if (bind(server, (struct sockaddr *)&address, sizeof(address)) < 0) { + if (bind(server, (struct sockaddr *)&address, addr_len) < 0) { perror("bind failed"); return 1; } diff --git a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh index a102803ff74f..030762b203d7 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/devlink.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/devlink.sh @@ -40,6 +40,8 @@ fw_flash_test() return fi + echo "10"> $DEBUGFS_DIR/fw_update_flash_chunk_time_ms + devlink dev flash $DL_HANDLE file $DUMMYFILE check_err $? "Failed to flash with status updates on" diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py new file mode 100755 index 000000000000..887d662ad128 --- /dev/null +++ b/tools/testing/selftests/drivers/net/xdp.py @@ -0,0 +1,656 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +This file contains tests to verify native XDP support in network drivers. +The tests utilize the BPF program `xdp_native.bpf.o` from the `selftests.net.lib` +directory, with each test focusing on a specific aspect of XDP functionality. +""" +import random +import string +from dataclasses import dataclass +from enum import Enum + +from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ne, ksft_pr +from lib.py import KsftFailEx, NetDrvEpEnv, EthtoolFamily, NlError +from lib.py import bkg, cmd, rand_port +from lib.py import ip, bpftool, defer + + +class TestConfig(Enum): + """Enum for XDP configuration options.""" + MODE = 0 # Configures the BPF program for a specific test + PORT = 1 # Port configuration to communicate with the remote host + ADJST_OFFSET = 2 # Tail/Head adjustment offset for extension/shrinking + ADJST_TAG = 3 # Adjustment tag to annotate the start and end of extension + + +class XDPAction(Enum): + """Enum for XDP actions.""" + PASS = 0 # Pass the packet up to the stack + DROP = 1 # Drop the packet + TX = 2 # Route the packet to the remote host + TAIL_ADJST = 3 # Adjust the tail of the packet + HEAD_ADJST = 4 # Adjust the head of the packet + + +class XDPStats(Enum): + """Enum for XDP statistics.""" + RX = 0 # Count of valid packets received for testing + PASS = 1 # Count of packets passed up to the stack + DROP = 2 # Count of packets dropped + TX = 3 # Count of incoming packets routed to the remote host + ABORT = 4 # Count of packets that were aborted + + +@dataclass +class BPFProgInfo: + """Data class to store information about a BPF program.""" + name: str # Name of the BPF program + file: str # BPF program object file + xdp_sec: str = "xdp" # XDP section name (e.g., "xdp" or "xdp.frags") + mtu: int = 1500 # Maximum Transmission Unit, default is 1500 + + +def _exchg_udp(cfg, port, test_string): + """ + Exchanges UDP packets between a local and remote host using the socat tool. + + Args: + cfg: Configuration object containing network settings. + port: Port number to use for the UDP communication. + test_string: String that the remote host will send. + + Returns: + The string received by the test host. + """ + cfg.require_cmd("socat", remote=True) + + rx_udp_cmd = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT" + tx_udp_cmd = f"echo -n {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}" + + with bkg(rx_udp_cmd, exit_wait=True) as nc: + cmd(tx_udp_cmd, host=cfg.remote, shell=True) + + return nc.stdout.strip() + + +def _test_udp(cfg, port, size=256): + """ + Tests UDP packet exchange between a local and remote host. + + Args: + cfg: Configuration object containing network settings. + port: Port number to use for the UDP communication. + size: The length of the test string to be exchanged, default is 256 characters. + + Returns: + bool: True if the received string matches the sent string, False otherwise. + """ + test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(size)) + recvd_str = _exchg_udp(cfg, port, test_str) + + return recvd_str == test_str + + +def _load_xdp_prog(cfg, bpf_info): + """ + Loads an XDP program onto a network interface. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + + Returns: + dict: A dictionary containing the XDP program ID, name, and associated map IDs. + """ + abs_path = cfg.net_lib_dir / bpf_info.file + prog_info = {} + + cmd(f"ip link set dev {cfg.remote_ifname} mtu {bpf_info.mtu}", shell=True, host=cfg.remote) + defer(ip, f"link set dev {cfg.remote_ifname} mtu 1500", host=cfg.remote) + + cmd( + f"ip link set dev {cfg.ifname} mtu {bpf_info.mtu} xdp obj {abs_path} sec {bpf_info.xdp_sec}", + shell=True + ) + defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off") + + xdp_info = ip(f"-d link show dev {cfg.ifname}", json=True)[0] + prog_info["id"] = xdp_info["xdp"]["prog"]["id"] + prog_info["name"] = xdp_info["xdp"]["prog"]["name"] + prog_id = prog_info["id"] + + map_ids = bpftool(f"prog show id {prog_id}", json=True)["map_ids"] + prog_info["maps"] = {} + for map_id in map_ids: + name = bpftool(f"map show id {map_id}", json=True)["name"] + prog_info["maps"][name] = map_id + + return prog_info + + +def format_hex_bytes(value): + """ + Helper function that converts an integer into a formatted hexadecimal byte string. + + Args: + value: An integer representing the number to be converted. + + Returns: + A string representing hexadecimal equivalent of value, with bytes separated by spaces. + """ + hex_str = value.to_bytes(4, byteorder='little', signed=True) + return ' '.join(f'{byte:02x}' for byte in hex_str) + + +def _set_xdp_map(map_name, key, value): + """ + Updates an XDP map with a given key-value pair using bpftool. + + Args: + map_name: The name of the XDP map to update. + key: The key to update in the map, formatted as a hexadecimal string. + value: The value to associate with the key, formatted as a hexadecimal string. + """ + key_formatted = format_hex_bytes(key) + value_formatted = format_hex_bytes(value) + bpftool( + f"map update name {map_name} key hex {key_formatted} value hex {value_formatted}" + ) + + +def _get_stats(xdp_map_id): + """ + Retrieves and formats statistics from an XDP map. + + Args: + xdp_map_id: The ID of the XDP map from which to retrieve statistics. + + Returns: + A dictionary containing formatted packet statistics for various XDP actions. + The keys are based on the XDPStats Enum values. + + Raises: + KsftFailEx: If the stats retrieval fails. + """ + stats_dump = bpftool(f"map dump id {xdp_map_id}", json=True) + if not stats_dump: + raise KsftFailEx(f"Failed to get stats for map {xdp_map_id}") + + stats_formatted = {} + for key in range(0, 5): + val = stats_dump[key]["formatted"]["value"] + if stats_dump[key]["formatted"]["key"] == XDPStats.RX.value: + stats_formatted[XDPStats.RX.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.PASS.value: + stats_formatted[XDPStats.PASS.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.DROP.value: + stats_formatted[XDPStats.DROP.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.TX.value: + stats_formatted[XDPStats.TX.value] = val + elif stats_dump[key]["formatted"]["key"] == XDPStats.ABORT.value: + stats_formatted[XDPStats.ABORT.value] = val + + return stats_formatted + + +def _test_pass(cfg, bpf_info, msg_sz): + """ + Tests the XDP_PASS action by exchanging UDP packets. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + msg_sz: Size of the test message to send. + """ + + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.PASS.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + ksft_eq(_test_udp(cfg, port, msg_sz), True, "UDP packet exchange failed") + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should not be zero") + ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.PASS.value], "RX and PASS stats mismatch") + + +def test_xdp_native_pass_sb(cfg): + """ + Tests the XDP_PASS action for single buffer case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) + + _test_pass(cfg, bpf_info, 256) + + +def test_xdp_native_pass_mb(cfg): + """ + Tests the XDP_PASS action for a multi-buff size. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + _test_pass(cfg, bpf_info, 8000) + + +def _test_drop(cfg, bpf_info, msg_sz): + """ + Tests the XDP_DROP action by exchanging UDP packets. + + Args: + cfg: Configuration object containing network settings. + bpf_info: BPFProgInfo object containing information about the BPF program. + msg_sz: Size of the test message to send. + """ + + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.DROP.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + ksft_eq(_test_udp(cfg, port, msg_sz), False, "UDP packet exchange should fail") + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + ksft_ne(stats[XDPStats.RX.value], 0, "RX stats should be zero") + ksft_eq(stats[XDPStats.RX.value], stats[XDPStats.DROP.value], "RX and DROP stats mismatch") + + +def test_xdp_native_drop_sb(cfg): + """ + Tests the XDP_DROP action for a signle-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog", "xdp_native.bpf.o", "xdp", 1500) + + _test_drop(cfg, bpf_info, 256) + + +def test_xdp_native_drop_mb(cfg): + """ + Tests the XDP_DROP action for a multi-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + _test_drop(cfg, bpf_info, 8000) + + +def test_xdp_native_tx_mb(cfg): + """ + Tests the XDP_TX action for a multi-buff case. + + Args: + cfg: Configuration object containing network settings. + """ + cfg.require_cmd("socat", remote=True) + + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + prog_info = _load_xdp_prog(cfg, bpf_info) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TX.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(8000)) + rx_udp = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT" + tx_udp = f"echo {test_string} | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}" + + with bkg(rx_udp, host=cfg.remote, exit_wait=True) as rnc: + cmd(tx_udp, host=cfg.remote, shell=True) + + stats = _get_stats(prog_info['maps']['map_xdp_stats']) + + ksft_eq(rnc.stdout.strip(), test_string, "UDP packet exchange failed") + ksft_eq(stats[XDPStats.TX.value], 1, "TX stats mismatch") + + +def _validate_res(res, offset_lst, pkt_sz_lst): + """ + Validates the result of a test. + + Args: + res: The result of the test, which should be a dictionary with a "status" key. + + Raises: + KsftFailEx: If the test fails to pass any combination of offset and packet size. + """ + if "status" not in res: + raise KsftFailEx("Missing 'status' key in result dictionary") + + # Validate that not a single case was successful + if res["status"] == "fail": + if res["offset"] == offset_lst[0] and res["pkt_sz"] == pkt_sz_lst[0]: + raise KsftFailEx(f"{res['reason']}") + + # Get the previous offset and packet size to report the successful run + tmp_idx = offset_lst.index(res["offset"]) + prev_offset = offset_lst[tmp_idx - 1] + if tmp_idx == 0: + tmp_idx = pkt_sz_lst.index(res["pkt_sz"]) + prev_pkt_sz = pkt_sz_lst[tmp_idx - 1] + else: + prev_pkt_sz = res["pkt_sz"] + + # Use these values for error reporting + ksft_pr( + f"Failed run: pkt_sz {res['pkt_sz']}, offset {res['offset']}. " + f"Last successful run: pkt_sz {prev_pkt_sz}, offset {prev_offset}. " + f"Reason: {res['reason']}" + ) + + +def _check_for_failures(recvd_str, stats): + """ + Checks for common failures while adjusting headroom or tailroom. + + Args: + recvd_str: The string received from the remote host after sending a test string. + stats: A dictionary containing formatted packet statistics for various XDP actions. + + Returns: + str: A string describing the failure reason if a failure is detected, otherwise None. + """ + + # Any adjustment failure result in an abort hence, we track this counter + if stats[XDPStats.ABORT.value] != 0: + return "Adjustment failed" + + # Since we are using aggregate stats for a single test across all offsets and packet sizes + # we can't use RX stats only to track data exchange failure without taking a previous + # snapshot. An easier way is to simply check for non-zero length of received string. + if len(recvd_str) == 0: + return "Data exchange failed" + + # Check for RX and PASS stats mismatch. Ideally, they should be equal for a successful run + if stats[XDPStats.RX.value] != stats[XDPStats.PASS.value]: + return "RX stats mismatch" + + return None + + +def _test_xdp_native_tail_adjst(cfg, pkt_sz_lst, offset_lst): + """ + Tests the XDP tail adjustment functionality. + + This function loads the appropriate XDP program based on the provided + program name and configures the XDP map for tail adjustment. It then + validates the tail adjustment by sending and receiving UDP packets + with specified packet sizes and offsets. + + Args: + cfg: Configuration object containing network settings. + prog: Name of the XDP program to load. + pkt_sz_lst: List of packet sizes to test. + offset_lst: List of offsets to validate support for tail adjustment. + + Returns: + dict: A dictionary with test status and failure details if applicable. + """ + port = rand_port() + bpf_info = BPFProgInfo("xdp_prog_frags", "xdp_native.bpf.o", "xdp.frags", 9000) + + prog_info = _load_xdp_prog(cfg, bpf_info) + + # Configure the XDP map for tail adjustment + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.TAIL_ADJST.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + for offset in offset_lst: + tag = format(random.randint(65, 90), "02x") + + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset) + if offset > 0: + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16)) + + for pkt_sz in pkt_sz_lst: + test_str = "".join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz)) + recvd_str = _exchg_udp(cfg, port, test_str) + stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) + + failure = _check_for_failures(recvd_str, stats) + if failure is not None: + return { + "status": "fail", + "reason": failure, + "offset": offset, + "pkt_sz": pkt_sz, + } + + # Validate data content based on offset direction + expected_data = None + if offset > 0: + expected_data = test_str + (offset * chr(int(tag, 16))) + else: + expected_data = test_str[0:pkt_sz + offset] + + if recvd_str != expected_data: + return { + "status": "fail", + "reason": "Data mismatch", + "offset": offset, + "pkt_sz": pkt_sz, + } + + return {"status": "pass"} + + +def test_xdp_native_adjst_tail_grow_data(cfg): + """ + Tests the XDP tail adjustment by growing packet data. + + Args: + cfg: Configuration object containing network settings. + """ + pkt_sz_lst = [512, 1024, 2048] + offset_lst = [1, 16, 32, 64, 128, 256] + res = _test_xdp_native_tail_adjst( + cfg, + pkt_sz_lst, + offset_lst, + ) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def test_xdp_native_adjst_tail_shrnk_data(cfg): + """ + Tests the XDP tail adjustment by shrinking packet data. + + Args: + cfg: Configuration object containing network settings. + """ + pkt_sz_lst = [512, 1024, 2048] + offset_lst = [-16, -32, -64, -128, -256] + res = _test_xdp_native_tail_adjst( + cfg, + pkt_sz_lst, + offset_lst, + ) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def get_hds_thresh(cfg): + """ + Retrieves the header data split (HDS) threshold for a network interface. + + Args: + cfg: Configuration object containing network settings. + + Returns: + The HDS threshold value. If the threshold is not supported or an error occurs, + a default value of 1500 is returned. + """ + netnl = cfg.netnl + hds_thresh = 1500 + + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + if 'hds-thresh' not in rings: + ksft_pr(f'hds-thresh not supported. Using default: {hds_thresh}') + return hds_thresh + hds_thresh = rings['hds-thresh'] + except NlError as e: + ksft_pr(f"Failed to get rings: {e}. Using default: {hds_thresh}") + + return hds_thresh + + +def _test_xdp_native_head_adjst(cfg, prog, pkt_sz_lst, offset_lst): + """ + Tests the XDP head adjustment action for a multi-buffer case. + + Args: + cfg: Configuration object containing network settings. + netnl: Network namespace or link object (not used in this function). + + This function sets up the packet size and offset lists, then performs + the head adjustment test by sending and receiving UDP packets. + """ + cfg.require_cmd("socat", remote=True) + + prog_info = _load_xdp_prog(cfg, BPFProgInfo(prog, "xdp_native.bpf.o", "xdp.frags", 9000)) + port = rand_port() + + _set_xdp_map("map_xdp_setup", TestConfig.MODE.value, XDPAction.HEAD_ADJST.value) + _set_xdp_map("map_xdp_setup", TestConfig.PORT.value, port) + + hds_thresh = get_hds_thresh(cfg) + for offset in offset_lst: + for pkt_sz in pkt_sz_lst: + # The "head" buffer must contain at least the Ethernet header + # after we eat into it. We send large-enough packets, but if HDS + # is enabled head will only contain headers. Don't try to eat + # more than 28 bytes (UDPv4 + eth hdr left: (14 + 20 + 8) - 14) + l2_cut_off = 28 if cfg.addr_ipver == 4 else 48 + if pkt_sz > hds_thresh and offset > l2_cut_off: + ksft_pr( + f"Failed run: pkt_sz ({pkt_sz}) > HDS threshold ({hds_thresh}) and " + f"offset {offset} > {l2_cut_off}" + ) + return {"status": "pass"} + + test_str = ''.join(random.choice(string.ascii_lowercase) for _ in range(pkt_sz)) + tag = format(random.randint(65, 90), '02x') + + _set_xdp_map("map_xdp_setup", + TestConfig.ADJST_OFFSET.value, + offset) + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_TAG.value, int(tag, 16)) + _set_xdp_map("map_xdp_setup", TestConfig.ADJST_OFFSET.value, offset) + + recvd_str = _exchg_udp(cfg, port, test_str) + + # Check for failures around adjustment and data exchange + failure = _check_for_failures(recvd_str, _get_stats(prog_info['maps']['map_xdp_stats'])) + if failure is not None: + return { + "status": "fail", + "reason": failure, + "offset": offset, + "pkt_sz": pkt_sz + } + + # Validate data content based on offset direction + expected_data = None + if offset < 0: + expected_data = chr(int(tag, 16)) * (0 - offset) + test_str + else: + expected_data = test_str[offset:] + + if recvd_str != expected_data: + return { + "status": "fail", + "reason": "Data mismatch", + "offset": offset, + "pkt_sz": pkt_sz + } + + return {"status": "pass"} + + +def test_xdp_native_adjst_head_grow_data(cfg): + """ + Tests the XDP headroom growth support. + + Args: + cfg: Configuration object containing network settings. + + This function sets up the packet size and offset lists, then calls the + _test_xdp_native_head_adjst_mb function to perform the actual test. The + test is passed if the headroom is successfully extended for given packet + sizes and offsets. + """ + pkt_sz_lst = [512, 1024, 2048] + + # Negative values result in headroom shrinking, resulting in growing of payload + offset_lst = [-16, -32, -64, -128, -256] + res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def test_xdp_native_adjst_head_shrnk_data(cfg): + """ + Tests the XDP headroom shrinking support. + + Args: + cfg: Configuration object containing network settings. + + This function sets up the packet size and offset lists, then calls the + _test_xdp_native_head_adjst_mb function to perform the actual test. The + test is passed if the headroom is successfully shrunk for given packet + sizes and offsets. + """ + pkt_sz_lst = [512, 1024, 2048] + + # Positive values result in headroom growing, resulting in shrinking of payload + offset_lst = [16, 32, 64, 128, 256] + res = _test_xdp_native_head_adjst(cfg, "xdp_prog_frags", pkt_sz_lst, offset_lst) + + _validate_res(res, offset_lst, pkt_sz_lst) + + +def main(): + """ + Main function to execute the XDP tests. + + This function runs a series of tests to validate the XDP support for + both the single and multi-buffer. It uses the NetDrvEpEnv context + manager to manage the network driver environment and the ksft_run + function to execute the tests. + """ + with NetDrvEpEnv(__file__) as cfg: + cfg.netnl = EthtoolFamily() + ksft_run( + [ + test_xdp_native_pass_sb, + test_xdp_native_pass_mb, + test_xdp_native_drop_sb, + test_xdp_native_drop_mb, + test_xdp_native_tx_mb, + test_xdp_native_adjst_tail_grow_data, + test_xdp_native_adjst_tail_shrnk_data, + test_xdp_native_adjst_head_grow_data, + test_xdp_native_adjst_head_shrnk_data, + ], + args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/futex/include/futex2test.h b/tools/testing/selftests/futex/include/futex2test.h index ea79662405bc..1f625b39948a 100644 --- a/tools/testing/selftests/futex/include/futex2test.h +++ b/tools/testing/selftests/futex/include/futex2test.h @@ -4,6 +4,7 @@ * * Copyright 2021 Collabora Ltd. */ +#include <linux/time_types.h> #include <stdint.h> #define u64_to_ptr(x) ((void *)(uintptr_t)(x)) @@ -65,7 +66,12 @@ struct futex32_numa { static inline int futex_waitv(volatile struct futex_waitv *waiters, unsigned long nr_waiters, unsigned long flags, struct timespec *timo, clockid_t clockid) { - return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, timo, clockid); + struct __kernel_timespec ts = { + .tv_sec = timo->tv_sec, + .tv_nsec = timo->tv_nsec, + }; + + return syscall(__NR_futex_waitv, waiters, nr_waiters, flags, &ts, clockid); } /* diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 9308b2f77fed..890b3374dacd 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -142,6 +142,20 @@ check_tc_version() fi } +check_tc_erspan_support() +{ + local dev=$1; shift + + tc filter add dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null + if [[ $? -ne 0 ]]; then + echo "SKIP: iproute2 too old; tc is missing erspan support" + return $ksft_skip + fi + tc filter del dev $dev ingress pref 1 handle 1 flower \ + erspan_opts 1:0:0:0 &> /dev/null +} + # Old versions of tc don't understand "mpls_uc" check_tc_mpls_support() { diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index b1daad19b01e..b58909a93112 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -6,7 +6,7 @@ ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ match_ip_tos_test match_indev_test match_ip_ttl_test match_mpls_label_test \ match_mpls_tc_test match_mpls_bos_test match_mpls_ttl_test \ - match_mpls_lse_test" + match_mpls_lse_test match_erspan_opts_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -676,6 +676,56 @@ match_mpls_lse_test() log_test "mpls lse match ($tcflags)" } +match_erspan_opts_test() +{ + RET=0 + + check_tc_erspan_support $h2 || return 0 + + # h1 erspan setup + tunnel_create erspan1 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1001 \ + tos C ttl 64 erspan_ver 1 erspan 6789 # ERSPAN Type II + tunnel_create erspan2 erspan 192.0.2.1 192.0.2.2 dev $h1 seq key 1002 \ + tos C ttl 64 erspan_ver 2 erspan_dir egress erspan_hwid 63 \ + # ERSPAN Type III + ip link set dev erspan1 master v$h1 + ip link set dev erspan2 master v$h1 + # h2 erspan setup + ip link add ep-ex type erspan ttl 64 external # To collect tunnel info + ip link set ep-ex up + ip link set dev ep-ex master v$h2 + tc qdisc add dev ep-ex clsact + + # ERSPAN Type II [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 101 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1001 erspan_opts 1:6789:0:0 \ + action drop + # ERSPAN Type III [decap direction] + tc filter add dev ep-ex ingress protocol ip handle 102 flower \ + $tcflags enc_src_ip 192.0.2.1 enc_dst_ip 192.0.2.2 \ + enc_key_id 1002 erspan_opts 2:0:1:63 action drop + + ep1mac=$(mac_get erspan1) + $MZ erspan1 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 101 1 + check_err $? "ERSPAN Type II" + + ep2mac=$(mac_get erspan2) + $MZ erspan2 -c 1 -p 64 -a $ep1mac -b $h2mac -t ip -q + tc_check_packets "dev ep-ex ingress" 102 1 + check_err $? "ERSPAN Type III" + + # h2 erspan cleanup + tc qdisc del dev ep-ex clsact + tunnel_destroy ep-ex + # h1 erspan cleanup + tunnel_destroy erspan2 # ERSPAN Type III + tunnel_destroy erspan1 # ERSPAN Type II + + log_test "erspan_opts match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py index 61287c203b6e..8e35ed12ed9e 100644 --- a/tools/testing/selftests/net/lib/py/ksft.py +++ b/tools/testing/selftests/net/lib/py/ksft.py @@ -32,6 +32,7 @@ class KsftTerminate(KeyboardInterrupt): def ksft_pr(*objs, **kwargs): + kwargs["flush"] = True print("#", *objs, **kwargs) @@ -139,7 +140,7 @@ def ktap_result(ok, cnt=1, case="", comment=""): res += "." + str(case.__name__) if comment: res += " # " + comment - print(res) + print(res, flush=True) def ksft_flush_defer(): @@ -227,8 +228,8 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()): totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0} - print("TAP version 13") - print("1.." + str(len(cases))) + print("TAP version 13", flush=True) + print("1.." + str(len(cases)), flush=True) global KSFT_RESULT cnt = 0 diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c new file mode 100644 index 000000000000..521ba38f2ddd --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/udp.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_helpers.h> + +#define MAX_ADJST_OFFSET 256 +#define MAX_PAYLOAD_LEN 5000 +#define MAX_HDR_LEN 64 + +enum { + XDP_MODE = 0, + XDP_PORT = 1, + XDP_ADJST_OFFSET = 2, + XDP_ADJST_TAG = 3, +} xdp_map_setup_keys; + +enum { + XDP_MODE_PASS = 0, + XDP_MODE_DROP = 1, + XDP_MODE_TX = 2, + XDP_MODE_TAIL_ADJST = 3, + XDP_MODE_HEAD_ADJST = 4, +} xdp_map_modes; + +enum { + STATS_RX = 0, + STATS_PASS = 1, + STATS_DROP = 2, + STATS_TX = 3, + STATS_ABORT = 4, +} xdp_stats; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __s32); +} map_xdp_setup SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 5); + __type(key, __u32); + __type(value, __u64); +} map_xdp_stats SEC(".maps"); + +static __u32 min(__u32 a, __u32 b) +{ + return a < b ? a : b; +} + +static void record_stats(struct xdp_md *ctx, __u32 stat_type) +{ + __u64 *count; + + count = bpf_map_lookup_elem(&map_xdp_stats, &stat_type); + + if (count) + __sync_fetch_and_add(count, 1); +} + +static struct udphdr *filter_udphdr(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + } else { + return NULL; + } + + if (udph + 1 > (struct udphdr *)data_end) + return NULL; + + if (udph->dest != bpf_htons(port)) + return NULL; + + record_stats(ctx, STATS_RX); + + return udph; +} + +static int xdp_mode_pass(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_PASS); + + return XDP_PASS; +} + +static int xdp_mode_drop_handler(struct xdp_md *ctx, __u16 port) +{ + struct udphdr *udph = NULL; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + record_stats(ctx, STATS_DROP); + + return XDP_DROP; +} + +static void swap_machdr(void *data) +{ + struct ethhdr *eth = data; + __u8 tmp_mac[ETH_ALEN]; + + __builtin_memcpy(tmp_mac, eth->h_source, ETH_ALEN); + __builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN); + __builtin_memcpy(eth->h_dest, tmp_mac, ETH_ALEN); +} + +static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + + if (data + sizeof(*eth) > data_end) + return XDP_PASS; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __be32 tmp_ip = iph->saddr; + + if (iph + 1 > (struct iphdr *)data_end || + iph->protocol != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*iph) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + iph->saddr = iph->daddr; + iph->daddr = tmp_ip; + + record_stats(ctx, STATS_TX); + + return XDP_TX; + + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + struct in6_addr tmp_ipv6; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end || + ipv6h->nexthdr != IPPROTO_UDP) + return XDP_PASS; + + udph = data + sizeof(*ipv6h) + sizeof(*eth); + + if (udph + 1 > (struct udphdr *)data_end) + return XDP_PASS; + if (udph->dest != bpf_htons(port)) + return XDP_PASS; + + record_stats(ctx, STATS_RX); + swap_machdr((void *)eth); + + __builtin_memcpy(&tmp_ipv6, &ipv6h->saddr, sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->saddr, &ipv6h->daddr, + sizeof(tmp_ipv6)); + __builtin_memcpy(&ipv6h->daddr, &tmp_ipv6, sizeof(tmp_ipv6)); + + record_stats(ctx, STATS_TX); + + return XDP_TX; + } + + return XDP_PASS; +} + +static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + struct ethhdr *eth = data; + __u32 len, len_new; + + if (data + sizeof(*eth) > data_end) + return NULL; + + if (eth->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *iph = data + sizeof(*eth); + __u16 total_len; + + if (iph + 1 > (struct iphdr *)data_end) + return NULL; + + iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset); + + udph = (void *)eth + sizeof(*iph) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { + struct ipv6hdr *ipv6h = data + sizeof(*eth); + __u16 payload_len; + + if (ipv6h + 1 > (struct ipv6hdr *)data_end) + return NULL; + + udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth); + if (!udph || udph + 1 > (struct udphdr *)data_end) + return NULL; + + *udp_csum = ~((__u32)udph->check); + + len = ipv6h->payload_len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + ipv6h->payload_len = len_new; + + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + + len = udph->len; + len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + } else { + return NULL; + } + + udph->len = len_new; + + return udph; +} + +static __u16 csum_fold_helper(__u32 csum) +{ + return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff; +} + +static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, + __u32 hdr_len) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + struct udphdr *udph = NULL; + __u32 buff_len; + + udph = update_pkt(ctx, 0 - offset, &udp_csum); + if (!udph) + return -1; + + buff_len = bpf_xdp_get_buff_len(ctx); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + /* Make sure we have enough data to avoid eating the header */ + if (buff_len - offset < hdr_len) + return -1; + + buff_pos = buff_len - offset; + if (bpf_xdp_load_bytes(ctx, buff_pos, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + __u32 buff_pos, udp_csum = 0; + __u32 buff_len, hdr_len, key; + struct udphdr *udph; + __s32 *val; + __u8 tag; + + /* Proceed to update the packet headers before attempting to adjuste + * the tail. Once the tail is adjusted we lose access to the offset + * amount of data at the end of the packet which is crucial to update + * the checksum. + * Since any failure beyond this would abort the packet, we should + * not worry about passing a packet up the stack with wrong headers + */ + udph = update_pkt(ctx, offset, &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&tmp_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + buff_len = bpf_xdp_get_buff_len(ctx); + + if (bpf_xdp_adjust_tail(ctx, offset) < 0) { + bpf_printk("Failed to adjust tail\n"); + return -1; + } + + if (bpf_xdp_store_bytes(ctx, buff_len, tmp_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) +{ + void *data = (void *)(long)ctx->data; + struct udphdr *udph = NULL; + __s32 *adjust_offset, *val; + __u32 key, hdr_len; + void *offset_ptr; + __u8 tag; + int ret; + + udph = filter_udphdr(ctx, port); + if (!udph) + return XDP_PASS; + + hdr_len = (void *)udph - data + sizeof(struct udphdr); + key = XDP_ADJST_OFFSET; + adjust_offset = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!adjust_offset) + return XDP_PASS; + + if (*adjust_offset < 0) + ret = xdp_adjst_tail_shrnk_data(ctx, + (__u16)(0 - *adjust_offset), + hdr_len); + else + ret = xdp_adjst_tail_grow_data(ctx, (__u16)(*adjust_offset)); + if (ret) + goto abort_pkt; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort_pkt: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char tmp_buff[MAX_ADJST_OFFSET]; + struct udphdr *udph; + void *offset_ptr; + __u32 udp_csum = 0; + + /* Update the length information in the IP and UDP headers before + * adjusting the headroom. This simplifies accessing the relevant + * fields in the IP and UDP headers for fragmented packets. Any + * failure beyond this point will result in the packet being aborted, + * so we don't need to worry about incorrect length information for + * passed packets. + */ + udph = update_pkt(ctx, (__s16)(0 - offset), &udp_csum); + if (!udph) + return -1; + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, hdr_len, tmp_buff, offset) < 0) + return -1; + + udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); + + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0) + return -1; + + if (bpf_xdp_adjust_head(ctx, offset) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, tmp_buff, hdr_len) < 0) + return -1; + + return 0; +} + +static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len, + __u32 offset) +{ + char hdr_buff[MAX_HDR_LEN]; + char data_buff[MAX_ADJST_OFFSET]; + void *offset_ptr; + __s32 *val; + __u32 key; + __u8 tag; + __u32 udp_csum = 0; + struct udphdr *udph; + + udph = update_pkt(ctx, (__s16)(offset), &udp_csum); + if (!udph) + return -1; + + key = XDP_ADJST_TAG; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return -1; + + tag = (__u8)(*val); + for (int i = 0; i < MAX_ADJST_OFFSET; i++) + __builtin_memcpy(&data_buff[i], &tag, 1); + + offset = (offset & 0x1ff) >= MAX_ADJST_OFFSET ? MAX_ADJST_OFFSET : + offset & 0xff; + if (offset == 0) + return -1; + + udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum); + udph->check = (__u16)csum_fold_helper(udp_csum); + + if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) + return -1; + + /* Added here to handle clang complain about negative value */ + hdr_len = hdr_len & 0xff; + + if (hdr_len == 0) + return -1; + + if (bpf_xdp_load_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (offset > MAX_ADJST_OFFSET) + return -1; + + if (bpf_xdp_adjust_head(ctx, 0 - offset) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, 0, hdr_buff, hdr_len) < 0) + return -1; + + if (bpf_xdp_store_bytes(ctx, hdr_len, data_buff, offset) < 0) + return -1; + + return 0; +} + +static int xdp_head_adjst(struct xdp_md *ctx, __u16 port) +{ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + struct udphdr *udph_ptr = NULL; + __u32 key, size, hdr_len; + __s32 *val; + int res; + + /* Filter packets based on UDP port */ + udph_ptr = filter_udphdr(ctx, port); + if (!udph_ptr) + return XDP_PASS; + + hdr_len = (void *)udph_ptr - data + sizeof(struct udphdr); + + key = XDP_ADJST_OFFSET; + val = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!val) + return XDP_PASS; + + switch (*val) { + case -16: + case 16: + size = 16; + break; + case -32: + case 32: + size = 32; + break; + case -64: + case 64: + size = 64; + break; + case -128: + case 128: + size = 128; + break; + case -256: + case 256: + size = 256; + break; + default: + bpf_printk("Invalid adjustment offset: %d\n", *val); + goto abort; + } + + if (*val < 0) + res = xdp_adjst_head_grow_data(ctx, hdr_len, size); + else + res = xdp_adjst_head_shrnk_data(ctx, hdr_len, size); + + if (res) + goto abort; + + record_stats(ctx, STATS_PASS); + return XDP_PASS; + +abort: + record_stats(ctx, STATS_ABORT); + return XDP_ABORTED; +} + +static int xdp_prog_common(struct xdp_md *ctx) +{ + __u32 key, *port; + __s32 *mode; + + key = XDP_MODE; + mode = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!mode) + return XDP_PASS; + + key = XDP_PORT; + port = bpf_map_lookup_elem(&map_xdp_setup, &key); + if (!port) + return XDP_PASS; + + switch (*mode) { + case XDP_MODE_PASS: + return xdp_mode_pass(ctx, (__u16)(*port)); + case XDP_MODE_DROP: + return xdp_mode_drop_handler(ctx, (__u16)(*port)); + case XDP_MODE_TX: + return xdp_mode_tx_handler(ctx, (__u16)(*port)); + case XDP_MODE_TAIL_ADJST: + return xdp_adjst_tail(ctx, (__u16)(*port)); + case XDP_MODE_HEAD_ADJST: + return xdp_head_adjst(ctx, (__u16)(*port)); + } + + /* Default action is to simple pass */ + return XDP_PASS; +} + +SEC("xdp") +int xdp_prog(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +SEC("xdp.frags") +int xdp_prog_frags(struct xdp_md *ctx) +{ + return xdp_prog_common(ctx); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index e47788bfa671..4c7e51336ab2 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -4,7 +4,8 @@ top_srcdir = ../../../../.. CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) -TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ +TEST_PROGS := mptcp_connect.sh mptcp_connect_mmap.sh mptcp_connect_sendfile.sh \ + mptcp_connect_checksum.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh new file mode 100755 index 000000000000..ce93ec2f107f --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_checksum.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -C "${@}" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh new file mode 100755 index 000000000000..5dd30f9394af --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_mmap.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m mmap "${@}" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh new file mode 100755 index 000000000000..1d16fb1cc9bb --- /dev/null +++ b/tools/testing/selftests/net/mptcp/mptcp_connect_sendfile.sh @@ -0,0 +1,5 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +MPTCP_LIB_KSFT_TEST="$(basename "${0}" .sh)" \ + "$(dirname "${0}")/mptcp_connect.sh" -m sendfile "${@}" diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh index 3712c1b9b38b..606a43a60f73 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -93,32 +93,28 @@ ping_test() run_one_clash_test() { local ns="$1" - local daddr="$2" - local dport="$3" + local ctns="$2" + local daddr="$3" + local dport="$4" local entries local cre if ! ip netns exec "$ns" ./udpclash $daddr $dport;then - echo "FAIL: did not receive expected number of replies for $daddr:$dport" - ret=1 - return 1 + echo "INFO: did not receive expected number of replies for $daddr:$dport" + ip netns exec "$ctns" conntrack -S + # don't fail: check if clash resolution triggered after all. fi - entries=$(conntrack -S | wc -l) - cre=$(conntrack -S | grep -v "clash_resolve=0" | wc -l) + entries=$(ip netns exec "$ctns" conntrack -S | wc -l) + cre=$(ip netns exec "$ctns" conntrack -S | grep "clash_resolve=0" | wc -l) - if [ "$cre" -ne "$entries" ] ;then + if [ "$cre" -ne "$entries" ];then clash_resolution_active=1 return 0 fi - # 1 cpu -> parallel insertion impossible - if [ "$entries" -eq 1 ]; then - return 0 - fi - - # not a failure: clash resolution logic did not trigger, but all replies - # were received. With right timing, xmit completed sequentially and + # not a failure: clash resolution logic did not trigger. + # With right timing, xmit completed sequentially and # no parallel insertion occurs. return $ksft_skip } @@ -126,20 +122,23 @@ run_one_clash_test() run_clash_test() { local ns="$1" - local daddr="$2" - local dport="$3" + local ctns="$2" + local daddr="$3" + local dport="$4" + local softerr=0 for i in $(seq 1 10);do - run_one_clash_test "$ns" "$daddr" "$dport" + run_one_clash_test "$ns" "$ctns" "$daddr" "$dport" local rv=$? if [ $rv -eq 0 ];then echo "PASS: clash resolution test for $daddr:$dport on attempt $i" return 0 - elif [ $rv -eq 1 ];then - echo "FAIL: clash resolution test for $daddr:$dport on attempt $i" - return 1 + elif [ $rv -eq $ksft_skip ]; then + softerr=1 fi done + + [ $softerr -eq 1 ] && echo "SKIP: clash resolution for $daddr:$dport did not trigger" } ip link add veth0 netns "$nsclient1" type veth peer name veth0 netns "$nsrouter" @@ -161,11 +160,11 @@ spawn_servers "$nsclient2" # exercise clash resolution with nat: # nsrouter is supposed to dnat to 10.0.2.1:900{0,1,2,3}. -run_clash_test "$nsclient1" 10.0.1.99 "$dport" +run_clash_test "$nsclient1" "$nsrouter" 10.0.1.99 "$dport" # exercise clash resolution without nat. load_simple_ruleset "$nsclient2" -run_clash_test "$nsclient2" 127.0.0.1 9001 +run_clash_test "$nsclient2" "$nsclient2" 127.0.0.1 9001 if [ $clash_resolution_active -eq 0 ];then [ "$ret" -eq 0 ] && ret=$ksft_skip diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 49141254065c..441b17947230 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -30,6 +30,7 @@ ALL_TESTS=" kci_test_address_proto kci_test_enslave_bonding kci_test_mngtmpaddr + kci_test_operstate " devdummy="test-dummy0" @@ -1344,6 +1345,39 @@ kci_test_mngtmpaddr() return $ret } +kci_test_operstate() +{ + local ret=0 + + # Check that it is possible to set operational state during device + # creation and that it is preserved when the administrative state of + # the device is toggled. + run_cmd ip link add name vx0 up state up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UP" ip link show dev vx0 + run_cmd ip link set dev vx0 down + run_cmd_grep "state DOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + # Check that it is possible to set the operational state of the device + # after creation. + run_cmd ip link add name vx0 up type vxlan id 10010 dstport 4789 + run_cmd_grep "state UNKNOWN" ip link show dev vx0 + run_cmd ip link set dev vx0 state up + run_cmd_grep "state UP" ip link show dev vx0 + + run_cmd ip link del dev vx0 + + if [ "$ret" -ne 0 ]; then + end_test "FAIL: operstate" + return 1 + fi + + end_test "PASS: operstate" +} + kci_test_rtnl() { local current_test diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index 9451782689de..ee25824b1cbe 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -22,6 +22,14 @@ static enum scx_test_status run(void *ctx) struct bpf_link *link; char buf[16]; + /* + * On single-CPU systems, ops.select_cpu() is never + * invoked, so skip this test to avoid getting stuck + * indefinitely. + */ + if (tc == EXIT_SELECT_CPU && libbpf_num_possible_cpus() == 1) + continue; + skel = exit__open(); SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 8e902f7f1a18..c20aa16b1d63 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -31,6 +31,7 @@ CONFIG_NET_SCH_CBS=m CONFIG_NET_SCH_CHOKE=m CONFIG_NET_SCH_CODEL=m CONFIG_NET_SCH_DRR=m +CONFIG_NET_SCH_DUALPI2=m CONFIG_NET_SCH_ETF=m CONFIG_NET_SCH_FQ=m CONFIG_NET_SCH_FQ_CODEL=m diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json new file mode 100644 index 000000000000..cd1f2ee8f354 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json @@ -0,0 +1,254 @@ +[ + { + "id": "a4c7", + "name": "Create DualPI2 with default setting", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* step_thresh 1ms min_qlen_step 0p coupling_factor 2 drop_on_overload drop_dequeue classic_protection 10% l4s_ect split_gso", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "1ea4", + "name": "Create DualPI2 with memlimit", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 memlimit 20000000", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* memlimit 20000000B", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "2130", + "name": "Create DualPI2 with typical_rtt and max_rtt", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 typical_rtt 20ms max_rtt 200ms", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 20ms tupdate 20ms alpha 0.042969 beta 1.496094", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "90c1", + "name": "Create DualPI2 with max_rtt", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 max_rtt 300ms", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 50ms tupdate 50ms alpha 0.050781 beta 0.996094", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "7b3c", + "name": "Create DualPI2 with any_ect option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 any_ect", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* any_ect", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "49a3", + "name": "Create DualPI2 with overflow option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 overflow", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* overflow", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "d0a1", + "name": "Create DualPI2 with drop_enqueue option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 drop_enqueue", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* drop_enqueue", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "f051", + "name": "Create DualPI2 with no_split_gso option", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 no_split_gso", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* no_split_gso", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "456b", + "name": "Create DualPI2 with packet step_thresh", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 step_thresh 3p", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* step_thresh 3p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "610c", + "name": "Create DualPI2 with packet min_qlen_step", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 min_qlen_step 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* min_qlen_step 1p", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "b4fa", + "name": "Create DualPI2 with packet coupling_factor", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 coupling_factor 1", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* coupling_factor 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + }, + { + "id": "37f1", + "name": "Create DualPI2 with packet classic_protection", + "category": [ + "qdisc", + "dualpi2" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + ], + "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 classic_protection 0", + "expExitCode": "0", + "verifyCmd": "$TC qdisc show dev $DUMMY", + "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* classic_protection 0%", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] + } +] diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh index 589b18ed758a..dae19687912d 100755 --- a/tools/testing/selftests/tc-testing/tdc.sh +++ b/tools/testing/selftests/tc-testing/tdc.sh @@ -4,8 +4,7 @@ # If a module is required and was not compiled # the test that requires it will fail anyways try_modprobe() { - modprobe -q -R "$1" - if [ $? -ne 0 ]; then + if ! modprobe -q -R "$1"; then echo "Module $1 not found... skipping." else modprobe "$1" @@ -67,4 +66,5 @@ try_modprobe sch_hfsc try_modprobe sch_hhf try_modprobe sch_htb try_modprobe sch_teql -./tdc.py -J`nproc` +try_modprobe sch_dualpi2 +./tdc.py -J"$(nproc)" |