diff options
376 files changed, 6237 insertions, 3238 deletions
diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore index c298bab3d320..7d1b30aae874 100644 --- a/.get_maintainer.ignore +++ b/.get_maintainer.ignore @@ -1,4 +1,5 @@ Alan Cox <[email protected]> Alan Cox <[email protected]> Christoph Hellwig <[email protected]> +Jeff Kirsher <[email protected]> Marc Gonzalez <[email protected]> diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues index 5bff64d256c2..84aa25e0d14d 100644 --- a/Documentation/ABI/testing/sysfs-class-net-queues +++ b/Documentation/ABI/testing/sysfs-class-net-queues @@ -96,3 +96,26 @@ Description: Indicates the absolute minimum limit of bytes allowed to be queued on this network device transmit queue. Default value is 0. + +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/stall_thrs +Date: Jan 2024 +KernelVersion: 6.9 +Contact: [email protected] +Description: + Tx completion stall detection threshold in ms. Kernel will + guarantee to detect all stalls longer than this threshold but + may also detect stalls longer than half of the threshold. + +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/stall_cnt +Date: Jan 2024 +KernelVersion: 6.9 +Contact: [email protected] +Description: + Number of detected Tx completion stalls. + +What: /sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/stall_max +Date: Jan 2024 +KernelVersion: 6.9 +Contact: [email protected] +Description: + Longest detected Tx completion stall. Write 0 to clear. diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml index 890f7858d0dc..de7ba7f345a9 100644 --- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml +++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml @@ -46,6 +46,7 @@ properties: - enum: - renesas,etheravb-r8a779a0 # R-Car V3U - renesas,etheravb-r8a779g0 # R-Car V4H + - renesas,etheravb-r8a779h0 # R-Car V4M - const: renesas,etheravb-rcar-gen4 # R-Car Gen4 - items: diff --git a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml index 475aff7714d6..ea35d19be829 100644 --- a/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ethertsn.yaml @@ -65,9 +65,11 @@ properties: rx-internal-delay-ps: enum: [0, 1800] + default: 0 tx-internal-delay-ps: enum: [0, 2000] + default: 0 '#address-cells': const: 1 diff --git a/Documentation/devicetree/bindings/net/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml index 8f23254c0458..784866ea392b 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83822.yaml +++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml @@ -84,10 +84,10 @@ properties: description: | If present, select the RMII operation mode. Two modes are available: - - RMII master, where the PHY operates from a 25MHz clock reference, - provided by a crystal or a CMOS-level oscillator - - RMII slave, where the PHY operates from a 50MHz clock reference, - provided by a CMOS-level oscillator + - RMII master, where the PHY outputs a 50MHz reference clock which can + be connected to the MAC. + - RMII slave, where the PHY expects a 50MHz reference clock input + shared with the MAC. The RMII operation mode can also be configured by its straps. If the strap pin is not set correctly or not set at all, then this can be used to configure it. diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index e3d593841aa7..ea8d16600e16 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -545,7 +545,7 @@ In such scenario, dpll device input signal shall be also configurable to drive dpll with signal recovered from the PHY netdevice. This is done by exposing a pin to the netdevice - attaching pin to the netdevice itself with -``netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``. +``dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)``. Exposed pin id handle ``DPLL_A_PIN_ID`` is then identifiable by the user as it is attached to rtnetlink respond to get ``RTM_NEWLINK`` command in nested attribute ``IFLA_DPLL_PIN``. diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index c58f7153fcf8..3ebd50d78820 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -126,8 +126,9 @@ properties: Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- type: string enum-name: - description: Name for the enum type of the attribute. - type: string + description: | + Name for the enum type of the attribute, if empty no name will be used. + type: [ string, "null" ] doc: description: Documentation of the space. type: string @@ -261,14 +262,16 @@ properties: the prefix with the upper case name of the command, with dashes replaced by underscores. type: string enum-name: - description: Name for the enum type with commands. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] async-prefix: description: Same as name-prefix but used to render notifications and events to separate enum. type: string async-enum: - description: Name for the enum type with notifications/events. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] list: description: List of commands type: array diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index 938703088306..1d3fe3637707 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -168,8 +168,9 @@ properties: Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- type: string enum-name: - description: Name for the enum type of the attribute. - type: string + description: | + Name for the enum type of the attribute, if empty no name will be used. + type: [ string, "null" ] doc: description: Documentation of the space. type: string @@ -304,14 +305,16 @@ properties: the prefix with the upper case name of the command, with dashes replaced by underscores. type: string enum-name: - description: Name for the enum type with commands. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] async-prefix: description: Same as name-prefix but used to render notifications and events to separate enum. type: string async-enum: - description: Name for the enum type with notifications/events. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] # Start genetlink-legacy fixed-header: &fixed-header description: | diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index ac4e05415f2f..40fc8ab1ee44 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -189,8 +189,9 @@ properties: Prefix for the C enum name of the attributes. Default family[name]-set[name]-a- type: string enum-name: - description: Name for the enum type of the attribute. - type: string + description: | + Name for the enum type of the attribute, if empty no name will be used. + type: [ string, "null" ] doc: description: Documentation of the space. type: string @@ -371,14 +372,16 @@ properties: the prefix with the upper case name of the command, with dashes replaced by underscores. type: string enum-name: - description: Name for the enum type with commands. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] async-prefix: description: Same as name-prefix but used to render notifications and events to separate enum. type: string async-enum: - description: Name for the enum type with notifications/events. - type: string + description: | + Name for the enum type with commands, if empty no name will be used. + type: [ string, "null" ] # Start genetlink-legacy fixed-header: &fixed-header description: | diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 8dc1df5cfae7..95b0eb1486bf 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -312,6 +312,7 @@ attribute-sets: - name: capabilities type: u32 + enum: pin-capabilities - name: parent-device type: nest diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index 3addac970680..76352dbd2be4 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -74,6 +74,10 @@ definitions: name: queue-type type: enum entries: [ rx, tx ] + - + name: qstats-scope + type: flags + entries: [ queue ] attribute-sets: - @@ -265,6 +269,73 @@ attribute-sets: doc: ID of the NAPI instance which services this queue. type: u32 + - + name: qstats + doc: | + Get device statistics, scoped to a device or a queue. + These statistics extend (and partially duplicate) statistics available + in struct rtnl_link_stats64. + Value of the `scope` attribute determines how statistics are + aggregated. When aggregated for the entire device the statistics + represent the total number of events since last explicit reset of + the device (i.e. not a reconfiguration like changing queue count). + When reported per-queue, however, the statistics may not add + up to the total number of events, will only be reported for currently + active objects, and will likely report the number of events since last + reconfiguration. + attributes: + - + name: ifindex + doc: ifindex of the netdevice to which stats belong. + type: u32 + checks: + min: 1 + - + name: queue-type + doc: Queue type as rx, tx, for queue-id. + type: u32 + enum: queue-type + - + name: queue-id + doc: Queue ID, if stats are scoped to a single queue instance. + type: u32 + - + name: scope + doc: | + What object type should be used to iterate over the stats. + type: uint + enum: qstats-scope + - + name: rx-packets + doc: | + Number of wire packets successfully received and passed to the stack. + For drivers supporting XDP, XDP is considered the first layer + of the stack, so packets consumed by XDP are still counted here. + type: uint + value: 8 # reserve some attr ids in case we need more metadata later + - + name: rx-bytes + doc: Successfully received bytes, see `rx-packets`. + type: uint + - + name: tx-packets + doc: | + Number of wire packets successfully sent. Packet is considered to be + successfully sent once it is in device memory (usually this means + the device has issued a DMA completion for the packet). + type: uint + - + name: tx-bytes + doc: Successfully sent bytes, see `tx-packets`. + type: uint + - + name: rx-alloc-fail + doc: | + Number of times skb or buffer allocation failed on the Rx datapath. + Allocation failure may, or may not result in a packet drop, depending + on driver implementation and whether system recovers quickly. + type: uint + operations: list: - @@ -405,6 +476,26 @@ operations: attributes: - ifindex reply: *napi-get-op + - + name: qstats-get + doc: | + Get / dump fine grained statistics. Which statistics are reported + depends on the device and the driver, and whether the driver stores + software counters per-queue. + attribute-set: qstats + dump: + request: + attributes: + - scope + reply: + attributes: + - ifindex + - queue-type + - queue-id + - rx-packets + - rx-bytes + - tx-packets + - tx-bytes mcast-groups: list: diff --git a/Documentation/netlink/specs/nlctrl.yaml b/Documentation/netlink/specs/nlctrl.yaml new file mode 100644 index 000000000000..b1632b95f725 --- /dev/null +++ b/Documentation/netlink/specs/nlctrl.yaml @@ -0,0 +1,206 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: nlctrl +protocol: genetlink-legacy +uapi-header: linux/genetlink.h + +doc: | + genetlink meta-family that exposes information about all genetlink + families registered in the kernel (including itself). + +definitions: + - + name: op-flags + type: flags + enum-name: + entries: + - admin-perm + - cmd-cap-do + - cmd-cap-dump + - cmd-cap-haspol + - uns-admin-perm + - + name: attr-type + enum-name: netlink-attribute-type + type: enum + entries: + - invalid + - flag + - u8 + - u16 + - u32 + - u64 + - s8 + - s16 + - s32 + - s64 + - binary + - string + - nul-string + - nested + - nested-array + - bitfield32 + - sint + - uint + +attribute-sets: + - + name: ctrl-attrs + name-prefix: ctrl-attr- + attributes: + - + name: family-id + type: u16 + - + name: family-name + type: string + - + name: version + type: u32 + - + name: hdrsize + type: u32 + - + name: maxattr + type: u32 + - + name: ops + type: array-nest + nested-attributes: op-attrs + - + name: mcast-groups + type: array-nest + nested-attributes: mcast-group-attrs + - + name: policy + type: nest-type-value + type-value: [ policy-id, attr-id ] + nested-attributes: policy-attrs + - + name: op-policy + type: nest-type-value + type-value: [ op-id ] + nested-attributes: op-policy-attrs + - + name: op + type: u32 + - + name: mcast-group-attrs + name-prefix: ctrl-attr-mcast-grp- + enum-name: + attributes: + - + name: name + type: string + - + name: id + type: u32 + - + name: op-attrs + name-prefix: ctrl-attr-op- + enum-name: + attributes: + - + name: id + type: u32 + - + name: flags + type: u32 + enum: op-flags + enum-as-flags: true + - + name: policy-attrs + name-prefix: nl-policy-type-attr- + enum-name: + attributes: + - + name: type + type: u32 + enum: attr-type + - + name: min-value-s + type: s64 + - + name: max-value-s + type: s64 + - + name: min-value-u + type: u64 + - + name: max-value-u + type: u64 + - + name: min-length + type: u32 + - + name: max-length + type: u32 + - + name: policy-idx + type: u32 + - + name: policy-maxtype + type: u32 + - + name: bitfield32-mask + type: u32 + - + name: mask + type: u64 + - + name: pad + type: pad + - + name: op-policy-attrs + name-prefix: ctrl-attr-policy- + enum-name: + attributes: + - + name: do + type: u32 + - + name: dump + type: u32 + +operations: + enum-model: directional + name-prefix: ctrl-cmd- + list: + - + name: getfamily + doc: Get / dump genetlink families + attribute-set: ctrl-attrs + do: + request: + value: 3 + attributes: + - family-name + reply: &all-attrs + value: 1 + attributes: + - family-id + - family-name + - hdrsize + - maxattr + - mcast-groups + - ops + - version + dump: + reply: *all-attrs + - + name: getpolicy + doc: Get / dump genetlink policies + attribute-set: ctrl-attrs + dump: + request: + value: 10 + attributes: + - family-name + - family-id + - op + reply: + value: 10 + attributes: + - family-id + - op-policy + - policy diff --git a/Documentation/networking/sfp-phylink.rst b/Documentation/networking/sfp-phylink.rst index 8054d33f449f..5bf285d73e8a 100644 --- a/Documentation/networking/sfp-phylink.rst +++ b/Documentation/networking/sfp-phylink.rst @@ -231,16 +231,136 @@ this documentation. For further information on these methods, please see the inline documentation in :c:type:`struct phylink_mac_ops <phylink_mac_ops>`. -9. Remove calls to of_parse_phandle() for the PHY, - of_phy_register_fixed_link() for fixed links etc. from the probe - function, and replace with: +9. Fill-in the :c:type:`struct phylink_config <phylink_config>` fields with + a reference to the :c:type:`struct device <device>` associated to your + :c:type:`struct net_device <net_device>`: .. code-block:: c - struct phylink *phylink; priv->phylink_config.dev = &dev.dev; priv->phylink_config.type = PHYLINK_NETDEV; + Fill-in the various speeds, pause and duplex modes your MAC can handle: + + .. code-block:: c + + priv->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_10 | MAC_100 | MAC_1000FD; + +10. Some Ethernet controllers work in pair with a PCS (Physical Coding Sublayer) + block, that can handle among other things the encoding/decoding, link + establishment detection and autonegotiation. While some MACs have internal + PCS whose operation is transparent, some other require dedicated PCS + configuration for the link to become functional. In that case, phylink + provides a PCS abstraction through :c:type:`struct phylink_pcs <phylink_pcs>`. + + Identify if your driver has one or more internal PCS blocks, and/or if + your controller can use an external PCS block that might be internally + connected to your controller. + + If your controller doesn't have any internal PCS, you can go to step 11. + + If your Ethernet controller contains one or several PCS blocks, create + one :c:type:`struct phylink_pcs <phylink_pcs>` instance per PCS block within + your driver's private data structure: + + .. code-block:: c + + struct phylink_pcs pcs; + + Populate the relevant :c:type:`struct phylink_pcs_ops <phylink_pcs_ops>` to + configure your PCS. Create a :c:func:`pcs_get_state` function that reports + the inband link state, a :c:func:`pcs_config` function to configure your + PCS according to phylink-provided parameters, and a :c:func:`pcs_validate` + function that report to phylink all accepted configuration parameters for + your PCS: + + .. code-block:: c + + struct phylink_pcs_ops foo_pcs_ops = { + .pcs_validate = foo_pcs_validate, + .pcs_get_state = foo_pcs_get_state, + .pcs_config = foo_pcs_config, + }; + + Arrange for PCS link state interrupts to be forwarded into + phylink, via: + + .. code-block:: c + + phylink_pcs_change(pcs, link_is_up); + + where ``link_is_up`` is true if the link is currently up or false + otherwise. If a PCS is unable to provide these interrupts, then + it should set ``pcs->pcs_poll = true;`` when creating the PCS. + +11. If your controller relies on, or accepts the presence of an external PCS + controlled through its own driver, add a pointer to a phylink_pcs instance + in your driver private data structure: + + .. code-block:: c + + struct phylink_pcs *pcs; + + The way of getting an instance of the actual PCS depends on the platform, + some PCS sit on an MDIO bus and are grabbed by passing a pointer to the + corresponding :c:type:`struct mii_bus <mii_bus>` and the PCS's address on + that bus. In this example, we assume the controller attaches to a Lynx PCS + instance: + + .. code-block:: c + + priv->pcs = lynx_pcs_create_mdiodev(bus, 0); + + Some PCS can be recovered based on firmware information: + + .. code-block:: c + + priv->pcs = lynx_pcs_create_fwnode(of_fwnode_handle(node)); + +12. Populate the :c:func:`mac_select_pcs` callback and add it to your + :c:type:`struct phylink_mac_ops <phylink_mac_ops>` set of ops. This function + must return a pointer to the relevant :c:type:`struct phylink_pcs <phylink_pcs>` + that will be used for the requested link configuration: + + .. code-block:: c + + static struct phylink_pcs *foo_select_pcs(struct phylink_config *config, + phy_interface_t interface) + { + struct foo_priv *priv = container_of(config, struct foo_priv, + phylink_config); + + if ( /* 'interface' needs a PCS to function */ ) + return priv->pcs; + + return NULL; + } + + See :c:func:`mvpp2_select_pcs` for an example of a driver that has multiple + internal PCS. + +13. Fill-in all the :c:type:`phy_interface_t <phy_interface_t>` (i.e. all MAC to + PHY link modes) that your MAC can output. The following example shows a + configuration for a MAC that can handle all RGMII modes, SGMII and 1000BaseX. + You must adjust these according to what your MAC and all PCS associated + with this MAC are capable of, and not just the interface you wish to use: + + .. code-block:: c + + phy_interface_set_rgmii(priv->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, + priv->phylink_config.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + priv->phylink_config.supported_interfaces); + +14. Remove calls to of_parse_phandle() for the PHY, + of_phy_register_fixed_link() for fixed links etc. from the probe + function, and replace with: + + .. code-block:: c + + struct phylink *phylink; + phylink = phylink_create(&priv->phylink_config, node, phy_mode, &phylink_ops); if (IS_ERR(phylink)) { err = PTR_ERR(phylink); @@ -249,14 +369,14 @@ this documentation. priv->phylink = phylink; - and arrange to destroy the phylink in the probe failure path as - appropriate and the removal path too by calling: + and arrange to destroy the phylink in the probe failure path as + appropriate and the removal path too by calling: - .. code-block:: c + .. code-block:: c phylink_destroy(priv->phylink); -10. Arrange for MAC link state interrupts to be forwarded into +15. Arrange for MAC link state interrupts to be forwarded into phylink, via: .. code-block:: c @@ -264,17 +384,16 @@ this documentation. phylink_mac_change(priv->phylink, link_is_up); where ``link_is_up`` is true if the link is currently up or false - otherwise. If a MAC is unable to provide these interrupts, then - it should set ``priv->phylink_config.pcs_poll = true;`` in step 9. + otherwise. -11. Verify that the driver does not call:: +16. Verify that the driver does not call:: netif_carrier_on() netif_carrier_off() - as these will interfere with phylink's tracking of the link state, - and cause phylink to omit calls via the :c:func:`mac_link_up` and - :c:func:`mac_link_down` methods. + as these will interfere with phylink's tracking of the link state, + and cause phylink to omit calls via the :c:func:`mac_link_up` and + :c:func:`mac_link_down` methods. Network drivers should call phylink_stop() and phylink_start() via their suspend/resume paths, which ensures that the appropriate diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst index 551b3cc29a41..75e017dfa825 100644 --- a/Documentation/networking/statistics.rst +++ b/Documentation/networking/statistics.rst @@ -41,6 +41,15 @@ If `-s` is specified once the detailed errors won't be shown. `ip` supports JSON formatting via the `-j` option. +Queue statistics +~~~~~~~~~~~~~~~~ + +Queue statistics are accessible via the netdev netlink family. + +Currently no widely distributed CLI exists to access those statistics. +Kernel development tools (ynl) can be used to experiment with them, +see `Documentation/userspace-api/netlink/intro-specs.rst`. + Protocol-specific statistics ---------------------------- @@ -147,6 +156,12 @@ Statistics are reported both in the responses to link information requests (`RTM_GETLINK`) and statistic requests (`RTM_GETSTATS`, when `IFLA_STATS_LINK_64` bit is set in the `.filter_mask` of the request). +netdev (netlink) +~~~~~~~~~~~~~~~~ + +`netdev` generic netlink family allows accessing page pool and per queue +statistics. + ethtool ------- diff --git a/Documentation/virt/hyperv/index.rst b/Documentation/virt/hyperv/index.rst index 4a7a1b738bbe..de447e11b4a5 100644 --- a/Documentation/virt/hyperv/index.rst +++ b/Documentation/virt/hyperv/index.rst @@ -10,3 +10,4 @@ Hyper-V Enlightenments overview vmbus clocks + vpci diff --git a/Documentation/virt/hyperv/vpci.rst b/Documentation/virt/hyperv/vpci.rst new file mode 100644 index 000000000000..b65b2126ede3 --- /dev/null +++ b/Documentation/virt/hyperv/vpci.rst @@ -0,0 +1,316 @@ +.. SPDX-License-Identifier: GPL-2.0 + +PCI pass-thru devices +========================= +In a Hyper-V guest VM, PCI pass-thru devices (also called +virtual PCI devices, or vPCI devices) are physical PCI devices +that are mapped directly into the VM's physical address space. +Guest device drivers can interact directly with the hardware +without intermediation by the host hypervisor. This approach +provides higher bandwidth access to the device with lower +latency, compared with devices that are virtualized by the +hypervisor. The device should appear to the guest just as it +would when running on bare metal, so no changes are required +to the Linux device drivers for the device. + +Hyper-V terminology for vPCI devices is "Discrete Device +Assignment" (DDA). Public documentation for Hyper-V DDA is +available here: `DDA`_ + +.. _DDA: https://learn.microsoft.com/en-us/windows-server/virtualization/hyper-v/plan/plan-for-deploying-devices-using-discrete-device-assignment + +DDA is typically used for storage controllers, such as NVMe, +and for GPUs. A similar mechanism for NICs is called SR-IOV +and produces the same benefits by allowing a guest device +driver to interact directly with the hardware. See Hyper-V +public documentation here: `SR-IOV`_ + +.. _SR-IOV: https://learn.microsoft.com/en-us/windows-hardware/drivers/network/overview-of-single-root-i-o-virtualization--sr-iov- + +This discussion of vPCI devices includes DDA and SR-IOV +devices. + +Device Presentation +------------------- +Hyper-V provides full PCI functionality for a vPCI device when +it is operating, so the Linux device driver for the device can +be used unchanged, provided it uses the correct Linux kernel +APIs for accessing PCI config space and for other integration +with Linux. But the initial detection of the PCI device and +its integration with the Linux PCI subsystem must use Hyper-V +specific mechanisms. Consequently, vPCI devices on Hyper-V +have a dual identity. They are initially presented to Linux +guests as VMBus devices via the standard VMBus "offer" +mechanism, so they have a VMBus identity and appear under +/sys/bus/vmbus/devices. The VMBus vPCI driver in Linux at +drivers/pci/controller/pci-hyperv.c handles a newly introduced +vPCI device by fabricating a PCI bus topology and creating all +the normal PCI device data structures in Linux that would +exist if the PCI device were discovered via ACPI on a bare- +metal system. Once those data structures are set up, the +device also has a normal PCI identity in Linux, and the normal +Linux device driver for the vPCI device can function as if it +were running in Linux on bare-metal. Because vPCI devices are +presented dynamically through the VMBus offer mechanism, they +do not appear in the Linux guest's ACPI tables. vPCI devices +may be added to a VM or removed from a VM at any time during +the life of the VM, and not just during initial boot. + +With this approach, the vPCI device is a VMBus device and a +PCI device at the same time. In response to the VMBus offer +message, the hv_pci_probe() function runs and establishes a +VMBus connection to the vPCI VSP on the Hyper-V host. That +connection has a single VMBus channel. The channel is used to +exchange messages with the vPCI VSP for the purpose of setting +up and configuring the vPCI device in Linux. Once the device +is fully configured in Linux as a PCI device, the VMBus +channel is used only if Linux changes the vCPU to be interrupted +in the guest, or if the vPCI device is removed from +the VM while the VM is running. The ongoing operation of the +device happens directly between the Linux device driver for +the device and the hardware, with VMBus and the VMBus channel +playing no role. + +PCI Device Setup +---------------- +PCI device setup follows a sequence that Hyper-V originally +created for Windows guests, and that can be ill-suited for +Linux guests due to differences in the overall structure of +the Linux PCI subsystem compared with Windows. Nonetheless, +with a bit of hackery in the Hyper-V virtual PCI driver for +Linux, the virtual PCI device is setup in Linux so that +generic Linux PCI subsystem code and the Linux driver for the +device "just work". + +Each vPCI device is set up in Linux to be in its own PCI +domain with a host bridge. The PCI domainID is derived from +bytes 4 and 5 of the instance GUID assigned to the VMBus vPCI +device. The Hyper-V host does not guarantee that these bytes +are unique, so hv_pci_probe() has an algorithm to resolve +collisions. The collision resolution is intended to be stable +across reboots of the same VM so that the PCI domainIDs don't +change, as the domainID appears in the user space +configuration of some devices. + +hv_pci_probe() allocates a guest MMIO range to be used as PCI +config space for the device. This MMIO range is communicated +to the Hyper-V host over the VMBus channel as part of telling +the host that the device is ready to enter d0. See +hv_pci_enter_d0(). When the guest subsequently accesses this +MMIO range, the Hyper-V host intercepts the accesses and maps +them to the physical device PCI config space. + +hv_pci_probe() also gets BAR information for the device from +the Hyper-V host, and uses this information to allocate MMIO +space for the BARs. That MMIO space is then setup to be +associated with the host bridge so that it works when generic +PCI subsystem code in Linux processes the BARs. + +Finally, hv_pci_probe() creates the root PCI bus. At this +point the Hyper-V virtual PCI driver hackery is done, and the +normal Linux PCI machinery for scanning the root bus works to +detect the device, to perform driver matching, and to +initialize the driver and device. + +PCI Device Removal +------------------ +A Hyper-V host may initiate removal of a vPCI device from a +guest VM at any time during the life of the VM. The removal +is instigated by an admin action taken on the Hyper-V host and +is not under the control of the guest OS. + +A guest VM is notified of the removal by an unsolicited +"Eject" message sent from the host to the guest over the VMBus +channel associated with the vPCI device. Upon receipt of such +a message, the Hyper-V virtual PCI driver in Linux +asynchronously invokes Linux kernel PCI subsystem calls to +shutdown and remove the device. When those calls are +complete, an "Ejection Complete" message is sent back to +Hyper-V over the VMBus channel indicating that the device has +been removed. At this point, Hyper-V sends a VMBus rescind +message to the Linux guest, which the VMBus driver in Linux +processes by removing the VMBus identity for the device. Once +that processing is complete, all vestiges of the device having +been present are gone from the Linux kernel. The rescind +message also indicates to the guest that Hyper-V has stopped +providing support for the vPCI device in the guest. If the +guest were to attempt to access that device's MMIO space, it +would be an invalid reference. Hypercalls affecting the device +return errors, and any further messages sent in the VMBus +channel are ignored. + +After sending the Eject message, Hyper-V allows the guest VM +60 seconds to cleanly shutdown the device and respond with +Ejection Complete before sending the VMBus rescind +message. If for any reason the Eject steps don't complete +within the allowed 60 seconds, the Hyper-V host forcibly +performs the rescind steps, which will likely result in +cascading errors in the guest because the device is now no +longer present from the guest standpoint and accessing the +device MMIO space will fail. + +Because ejection is asynchronous and can happen at any point +during the guest VM lifecycle, proper synchronization in the +Hyper-V virtual PCI driver is very tricky. Ejection has been +observed even before a newly offered vPCI device has been +fully setup. The Hyper-V virtual PCI driver has been updated +several times over the years to fix race conditions when +ejections happen at inopportune times. Care must be taken when +modifying this code to prevent re-introducing such problems. +See comments in the code. + +Interrupt Assignment +-------------------- +The Hyper-V virtual PCI driver supports vPCI devices using +MSI, multi-MSI, or MSI-X. Assigning the guest vCPU that will +receive the interrupt for a particular MSI or MSI-X message is +complex because of the way the Linux setup of IRQs maps onto +the Hyper-V interfaces. For the single-MSI and MSI-X cases, +Linux calls hv_compse_msi_msg() twice, with the first call +containing a dummy vCPU and the second call containing the +real vCPU. Furthermore, hv_irq_unmask() is finally called +(on x86) or the GICD registers are set (on arm64) to specify +the real vCPU again. Each of these three calls interact +with Hyper-V, which must decide which physical CPU should +receive the interrupt before it is forwarded to the guest VM. +Unfortunately, the Hyper-V decision-making process is a bit +limited, and can result in concentrating the physical +interrupts on a single CPU, causing a performance bottleneck. +See details about how this is resolved in the extensive +comment above the function hv_compose_msi_req_get_cpu(). + +The Hyper-V virtual PCI driver implements the +irq_chip.irq_compose_msi_msg function as hv_compose_msi_msg(). +Unfortunately, on Hyper-V the implementation requires sending +a VMBus message to the Hyper-V host and awaiting an interrupt +indicating receipt of a reply message. Since +irq_chip.irq_compose_msi_msg can be called with IRQ locks +held, it doesn't work to do the normal sleep until awakened by +the interrupt. Instead hv_compose_msi_msg() must send the +VMBus message, and then poll for the completion message. As +further complexity, the vPCI device could be ejected/rescinded +while the polling is in progress, so this scenario must be +detected as well. See comments in the code regarding this +very tricky area. + +Most of the code in the Hyper-V virtual PCI driver (pci- +hyperv.c) applies to Hyper-V and Linux guests running on x86 +and on arm64 architectures. But there are differences in how +interrupt assignments are managed. On x86, the Hyper-V +virtual PCI driver in the guest must make a hypercall to tell +Hyper-V which guest vCPU should be interrupted by each +MSI/MSI-X interrupt, and the x86 interrupt vector number that +the x86_vector IRQ domain has picked for the interrupt. This +hypercall is made by hv_arch_irq_unmask(). On arm64, the +Hyper-V virtual PCI driver manages the allocation of an SPI +for each MSI/MSI-X interrupt. The Hyper-V virtual PCI driver +stores the allocated SPI in the architectural GICD registers, +which Hyper-V emulates, so no hypercall is necessary as with +x86. Hyper-V does not support using LPIs for vPCI devices in +arm64 guest VMs because it does not emulate a GICv3 ITS. + +The Hyper-V virtual PCI driver in Linux supports vPCI devices +whose drivers create managed or unmanaged Linux IRQs. If the +smp_affinity for an unmanaged IRQ is updated via the /proc/irq +interface, the Hyper-V virtual PCI driver is called to tell +the Hyper-V host to change the interrupt targeting and +everything works properly. However, on x86 if the x86_vector +IRQ domain needs to reassign an interrupt vector due to +running out of vectors on a CPU, there's no path to inform the +Hyper-V host of the change, and things break. Fortunately, +guest VMs operate in a constrained device environment where +using all the vectors on a CPU doesn't happen. Since such a +problem is only a theoretical concern rather than a practical +concern, it has been left unaddressed. + +DMA +--- +By default, Hyper-V pins all guest VM memory in the host +when the VM is created, and programs the physical IOMMU to +allow the VM to have DMA access to all its memory. Hence +it is safe to assign PCI devices to the VM, and allow the +guest operating system to program the DMA transfers. The +physical IOMMU prevents a malicious guest from initiating +DMA to memory belonging to the host or to other VMs on the +host. From the Linux guest standpoint, such DMA transfers +are in "direct" mode since Hyper-V does not provide a virtual +IOMMU in the guest. + +Hyper-V assumes that physical PCI devices always perform +cache-coherent DMA. When running on x86, this behavior is +required by the architecture. When running on arm64, the +architecture allows for both cache-coherent and +non-cache-coherent devices, with the behavior of each device +specified in the ACPI DSDT. But when a PCI device is assigned +to a guest VM, that device does not appear in the DSDT, so the +Hyper-V VMBus driver propagates cache-coherency information +from the VMBus node in the ACPI DSDT to all VMBus devices, +including vPCI devices (since they have a dual identity as a VMBus +device and as a PCI device). See vmbus_dma_configure(). +Current Hyper-V versions always indicate that the VMBus is +cache coherent, so vPCI devices on arm64 always get marked as +cache coherent and the CPU does not perform any sync +operations as part of dma_map/unmap_*() calls. + +vPCI protocol versions +---------------------- +As previously described, during vPCI device setup and teardown +messages are passed over a VMBus channel between the Hyper-V +host and the Hyper-v vPCI driver in the Linux guest. Some +messages have been revised in newer versions of Hyper-V, so +the guest and host must agree on the vPCI protocol version to +be used. The version is negotiated when communication over +the VMBus channel is first established. See +hv_pci_protocol_negotiation(). Newer versions of the protocol +extend support to VMs with more than 64 vCPUs, and provide +additional information about the vPCI device, such as the +guest virtual NUMA node to which it is most closely affined in +the underlying hardware. + +Guest NUMA node affinity +------------------------ +When the vPCI protocol version provides it, the guest NUMA +node affinity of the vPCI device is stored as part of the Linux +device information for subsequent use by the Linux driver. See +hv_pci_assign_numa_node(). If the negotiated protocol version +does not support the host providing NUMA affinity information, +the Linux guest defaults the device NUMA node to 0. But even +when the negotiated protocol version includes NUMA affinity +information, the ability of the host to provide such +information depends on certain host configuration options. If +the guest receives NUMA node value "0", it could mean NUMA +node 0, or it could mean "no information is available". +Unfortunately it is not possible to distinguish the two cases +from the guest side. + +PCI config space access in a CoCo VM +------------------------------------ +Linux PCI device drivers access PCI config space using a +standard set of functions provided by the Linux PCI subsystem. +In Hyper-V guests these standard functions map to functions +hv_pcifront_read_config() and hv_pcifront_write_config() +in the Hyper-V virtual PCI driver. In normal VMs, +these hv_pcifront_*() functions directly access the PCI config +space, and the accesses trap to Hyper-V to be handled. +But in CoCo VMs, memory encryption prevents Hyper-V +from reading the guest instruction stream to emulate the +access, so the hv_pcifront_*() functions must invoke +hypercalls with explicit arguments describing the access to be +made. + +Config Block back-channel +------------------------- +The Hyper-V host and Hyper-V virtual PCI driver in Linux +together implement a non-standard back-channel communication +path between the host and guest. The back-channel path uses +messages sent over the VMBus channel associated with the vPCI +device. The functions hyperv_read_cfg_blk() and +hyperv_write_cfg_blk() are the primary interfaces provided to +other parts of the Linux kernel. As of this writing, these +interfaces are used only by the Mellanox mlx5 driver to pass +diagnostic data to a Hyper-V host running in the Azure public +cloud. The functions hyperv_read_cfg_blk() and +hyperv_write_cfg_blk() are implemented in a separate module +(pci-hyperv-intf.c, under CONFIG_PCI_HYPERV_INTERFACE) that +effectively stubs them out when running in non-Hyper-V +environments. diff --git a/MAINTAINERS b/MAINTAINERS index 04e5f7c20e30..90a58c73dbde 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1395,6 +1395,7 @@ F: drivers/hwmon/max31760.c ANALOGBITS PLL LIBRARIES M: Paul Walmsley <[email protected]> +M: Samuel Holland <[email protected]> S: Supported F: drivers/clk/analogbits/* F: include/linux/clk/analogbits* @@ -2156,7 +2157,7 @@ M: Shawn Guo <[email protected]> M: Sascha Hauer <[email protected]> R: Pengutronix Kernel Team <[email protected]> R: Fabio Estevam <[email protected]> -R: NXP Linux Team <[email protected]> L: [email protected] (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git @@ -8505,7 +8506,7 @@ FREESCALE IMX / MXC FEC DRIVER M: Wei Fang <[email protected]> R: Shenwei Wang <[email protected]> R: Clark Wang <[email protected]> -R: NXP Linux Team <[email protected]> S: Maintained F: Documentation/devicetree/bindings/net/fsl,fec.yaml @@ -8540,7 +8541,7 @@ F: drivers/i2c/busses/i2c-imx.c FREESCALE IMX LPI2C DRIVER M: Dong Aisheng <[email protected]> S: Maintained F: Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.yaml F: drivers/i2c/busses/i2c-imx-lpi2c.c @@ -15747,7 +15748,7 @@ F: drivers/iio/gyro/fxas21002c_spi.c NXP i.MX 7D/6SX/6UL/93 AND VF610 ADC DRIVER M: Haibo Chen <[email protected]> S: Maintained F: Documentation/devicetree/bindings/iio/adc/fsl,imx7d-adc.yaml F: Documentation/devicetree/bindings/iio/adc/fsl,vf610-adc.yaml @@ -15784,7 +15785,7 @@ F: drivers/gpu/drm/imx/dcss/ NXP i.MX 8QXP ADC DRIVER M: Cai Huoqing <[email protected]> M: Haibo Chen <[email protected]> S: Maintained F: Documentation/devicetree/bindings/iio/adc/nxp,imx8qxp-adc.yaml @@ -15792,7 +15793,7 @@ F: drivers/iio/adc/imx8qxp-adc.c NXP i.MX 8QXP/8QM JPEG V4L2 DRIVER M: Mirela Rabulea <[email protected]> -R: NXP Linux Team <[email protected]> S: Maintained F: Documentation/devicetree/bindings/media/nxp,imx8-jpeg.yaml @@ -15802,7 +15803,7 @@ NXP i.MX CLOCK DRIVERS M: Abel Vesa <[email protected]> R: Peng Fan <[email protected]> S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/abelvesa/linux.git clk/imx F: Documentation/devicetree/bindings/clock/imx* @@ -16763,6 +16764,7 @@ F: drivers/pci/controller/dwc/*layerscape* PCI DRIVER FOR FU740 M: Paul Walmsley <[email protected]> M: Greentime Hu <[email protected]> +M: Samuel Holland <[email protected]> S: Maintained F: Documentation/devicetree/bindings/pci/sifive,fu740-pcie.yaml @@ -19680,7 +19682,7 @@ F: drivers/mmc/host/sdhci-of-at91.c SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) NXP i.MX DRIVER M: Haibo Chen <[email protected]> S: Maintained F: drivers/mmc/host/sdhci-esdhc-imx.c @@ -20015,36 +20017,15 @@ S: Maintained F: drivers/watchdog/simatic-ipc-wdt.c SIFIVE DRIVERS -M: Palmer Dabbelt <[email protected]> M: Paul Walmsley <[email protected]> +M: Samuel Holland <[email protected]> S: Supported +F: drivers/dma/sf-pdma/ N: sifive +K: fu[57]40 K: [^@]sifive -SIFIVE CACHE DRIVER -M: Conor Dooley <[email protected]> -S: Maintained -F: Documentation/devicetree/bindings/cache/sifive,ccache0.yaml -F: drivers/cache/sifive_ccache.c - -SIFIVE FU540 SYSTEM-ON-CHIP -M: Paul Walmsley <[email protected]> -M: Palmer Dabbelt <[email protected]> -S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/pjw/sifive.git -N: fu540 -K: fu540 - -SIFIVE PDMA DRIVER -M: Green Wan <[email protected]> -S: Maintained -F: Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml -F: drivers/dma/sf-pdma/ - - SILEAD TOUCHSCREEN DRIVER M: Hans de Goede <[email protected]> @@ -20253,8 +20234,8 @@ F: Documentation/devicetree/bindings/net/socionext,uniphier-ave4.yaml F: drivers/net/ethernet/socionext/sni_ave.c SOCIONEXT (SNI) NETSEC NETWORK DRIVER -M: Jassi Brar <[email protected]> M: Ilias Apalodimas <[email protected]> +M: Masahisa Kojima <[email protected]> S: Maintained F: Documentation/devicetree/bindings/net/socionext,synquacer-netsec.yaml @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi index ebf7befcc11e..9c81c6baa2d3 100644 --- a/arch/arm/boot/dts/nxp/imx/imx7s.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imx7s.dtsi @@ -834,16 +834,6 @@ <&clks IMX7D_LCDIF_PIXEL_ROOT_CLK>; clock-names = "pix", "axi"; status = "disabled"; - - port { - #address-cells = <1>; - #size-cells = <0>; - - lcdif_out_mipi_dsi: endpoint@0 { - reg = <0>; - remote-endpoint = <&mipi_dsi_in_lcdif>; - }; - }; }; mipi_csi: mipi-csi@30750000 { @@ -895,22 +885,6 @@ samsung,esc-clock-frequency = <20000000>; samsung,pll-clock-frequency = <24000000>; status = "disabled"; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - #address-cells = <1>; - #size-cells = <0>; - - mipi_dsi_in_lcdif: endpoint@0 { - reg = <0>; - remote-endpoint = <&lcdif_out_mipi_dsi>; - }; - }; - }; }; }; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0a90583f9f01..8f9dbe8d9029 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -297,6 +297,7 @@ CONFIG_FB_MODE_HELPERS=y CONFIG_LCD_CLASS_DEVICE=y CONFIG_LCD_L4F00242T03=y CONFIG_LCD_PLATFORM=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_BACKLIGHT_PWM=y CONFIG_BACKLIGHT_GPIO=y CONFIG_FRAMEBUFFER_CONSOLE=y diff --git a/arch/arm64/boot/dts/allwinner/Makefile b/arch/arm64/boot/dts/allwinner/Makefile index 91d505b385de..1f1f8d865d0e 100644 --- a/arch/arm64/boot/dts/allwinner/Makefile +++ b/arch/arm64/boot/dts/allwinner/Makefile @@ -42,5 +42,6 @@ dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-cb1-manta.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-bigtreetech-pi.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-orangepi-zero2.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h616-x96-mate.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero2w.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-orangepi-zero3.dtb dtb-$(CONFIG_ARCH_SUNXI) += sun50i-h618-transpeed-8k618-t.dtb diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 4ae4fdab461e..43f1d45ccc96 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -255,7 +255,7 @@ <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>; assigned-clock-rates = <13000000>, <13000000>, <156000000>; - reset-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio4 1 GPIO_ACTIVE_HIGH>; status = "disabled"; ports { diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 76c73daf546b..39a550c1cd26 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -1820,7 +1820,7 @@ compatible = "fsl,imx8mp-ldb"; reg = <0x5c 0x4>, <0x128 0x4>; reg-names = "ldb", "lvds"; - clocks = <&clk IMX8MP_CLK_MEDIA_LDB>; + clocks = <&clk IMX8MP_CLK_MEDIA_LDB_ROOT>; clock-names = "ldb"; assigned-clocks = <&clk IMX8MP_CLK_MEDIA_LDB>; assigned-clock-parents = <&clk IMX8MP_VIDEO_PLL1_OUT>; diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts index ea13c4a7027c..81a82933e350 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra234-p3737-0000+p3701-0000.dts @@ -175,7 +175,7 @@ status = "okay"; phy-handle = <&mgbe0_phy>; - phy-mode = "usxgmii"; + phy-mode = "10gbase-r"; mdio { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi index 3f16595d099c..d1bd328892af 100644 --- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi @@ -1459,7 +1459,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBEAWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEA>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>; status = "disabled"; }; @@ -1493,7 +1493,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBEBWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF1>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEB>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>; status = "disabled"; }; @@ -1527,7 +1527,7 @@ <&mc TEGRA234_MEMORY_CLIENT_MGBECWR &emc>; interconnect-names = "dma-mem", "write"; iommus = <&smmu_niso0 TEGRA234_SID_MGBE_VF2>; - power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBEC>; + power-domains = <&bpmp TEGRA234_POWER_DOMAIN_MGBED>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 8d41ed261adf..ee6f87c828ae 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -457,25 +457,6 @@ }; }; - mpm: interrupt-controller { - compatible = "qcom,mpm"; - qcom,rpm-msg-ram = <&apss_mpm>; - interrupts = <GIC_SPI 171 IRQ_TYPE_EDGE_RISING>; - mboxes = <&apcs_glb 1>; - interrupt-controller; - #interrupt-cells = <2>; - #power-domain-cells = <0>; - interrupt-parent = <&intc>; - qcom,mpm-pin-count = <96>; - qcom,mpm-pin-map = <2 184>, /* TSENS1 upper_lower_int */ - <52 243>, /* DWC3_PRI ss_phy_irq */ - <79 347>, /* DWC3_PRI hs_phy_irq */ - <80 352>, /* DWC3_SEC hs_phy_irq */ - <81 347>, /* QUSB2_PHY_PRI DP+DM */ - <82 352>, /* QUSB2_PHY_SEC DP+DM */ - <87 326>; /* SPMI */ - }; - psci { compatible = "arm,psci-1.0"; method = "smc"; @@ -765,15 +746,8 @@ }; rpm_msg_ram: sram@68000 { - compatible = "qcom,rpm-msg-ram", "mmio-sram"; + compatible = "qcom,rpm-msg-ram"; reg = <0x00068000 0x6000>; - #address-cells = <1>; - #size-cells = <1>; - ranges = <0 0x00068000 0x7000>; - - apss_mpm: sram@1b8 { - reg = <0x1b8 0x48>; - }; }; qfprom@74000 { @@ -856,8 +830,8 @@ reg = <0x004ad000 0x1000>, /* TM */ <0x004ac000 0x1000>; /* SROT */ #qcom,sensors = <8>; - interrupts-extended = <&mpm 2 IRQ_TYPE_LEVEL_HIGH>, - <&intc GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "uplow", "critical"; #thermal-sensor-cells = <1>; }; @@ -1363,7 +1337,6 @@ interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>; gpio-controller; gpio-ranges = <&tlmm 0 0 150>; - wakeup-parent = <&mpm>; #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; @@ -1891,7 +1864,7 @@ <0x0400a000 0x002100>; reg-names = "core", "chnls", "obsrvr", "intr", "cnfg"; interrupt-names = "periph_irq"; - interrupts-extended = <&mpm 87 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 326 IRQ_TYPE_LEVEL_HIGH>; qcom,ee = <0>; qcom,channel = <0>; #address-cells = <2>; @@ -3052,8 +3025,8 @@ #size-cells = <1>; ranges; - interrupts-extended = <&mpm 79 IRQ_TYPE_LEVEL_HIGH>, - <&mpm 52 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 243 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "hs_phy_irq", "ss_phy_irq"; clocks = <&gcc GCC_SYS_NOC_USB3_AXI_CLK>, diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts index ffc4406422ae..41215567b3ae 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-crd.dts @@ -563,6 +563,8 @@ }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts index def3976bd5bb..eb657e544961 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts +++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts @@ -722,6 +722,8 @@ }; &pcie4 { + max-link-speed = <2>; + perst-gpios = <&tlmm 141 GPIO_ACTIVE_LOW>; wake-gpios = <&tlmm 139 GPIO_ACTIVE_LOW>; diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi index 160e098f1075..f9849b8befbf 100644 --- a/arch/arm64/boot/dts/qcom/sm6115.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi @@ -1304,6 +1304,9 @@ &config_noc SLAVE_QUP_0 RPM_ALWAYS_TAG>, <&system_noc MASTER_QUP_0 RPM_ALWAYS_TAG &bimc SLAVE_EBI_CH0 RPM_ALWAYS_TAG>; + interconnect-names = "qup-core", + "qup-config", + "qup-memory"; #address-cells = <1>; #size-cells = <0>; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts index 9d916edb1c73..be133a3d5cbe 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-mtp.dts @@ -622,7 +622,7 @@ &tlmm { /* Reserved I/Os for NFC */ - gpio-reserved-ranges = <32 8>; + gpio-reserved-ranges = <32 8>, <74 1>; disp0_reset_n_active: disp0-reset-n-active-state { pins = "gpio133"; diff --git a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts index 592a67a47c78..b9151c2ddf2e 100644 --- a/arch/arm64/boot/dts/qcom/sm8650-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8650-qrd.dts @@ -659,7 +659,7 @@ &tlmm { /* Reserved I/Os for NFC */ - gpio-reserved-ranges = <32 8>; + gpio-reserved-ranges = <32 8>, <74 1>; bt_default: bt-default-state { bt-en-pins { diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 9bb2210c8d44..065ffd1b2f8a 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -69,7 +69,7 @@ enum rtas_function_index { RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE, RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2, RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW, - RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS, + RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW, RTAS_FNIDX__IBM_SCAN_LOG_DUMP, RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR, RTAS_FNIDX__IBM_SET_EEH_OPTION, @@ -164,7 +164,7 @@ typedef struct { #define RTAS_FN_IBM_READ_SLOT_RESET_STATE rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE) #define RTAS_FN_IBM_READ_SLOT_RESET_STATE2 rtas_fn_handle(RTAS_FNIDX__IBM_READ_SLOT_RESET_STATE2) #define RTAS_FN_IBM_REMOVE_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW) -#define RTAS_FN_IBM_RESET_PE_DMA_WINDOWS rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS) +#define RTAS_FN_IBM_RESET_PE_DMA_WINDOW rtas_fn_handle(RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW) #define RTAS_FN_IBM_SCAN_LOG_DUMP rtas_fn_handle(RTAS_FNIDX__IBM_SCAN_LOG_DUMP) #define RTAS_FN_IBM_SET_DYNAMIC_INDICATOR rtas_fn_handle(RTAS_FNIDX__IBM_SET_DYNAMIC_INDICATOR) #define RTAS_FN_IBM_SET_EEH_OPTION rtas_fn_handle(RTAS_FNIDX__IBM_SET_EEH_OPTION) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 7e793b503e29..8064d9c3de86 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -375,8 +375,13 @@ static struct rtas_function rtas_function_table[] __ro_after_init = { [RTAS_FNIDX__IBM_REMOVE_PE_DMA_WINDOW] = { .name = "ibm,remove-pe-dma-window", }, - [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOWS] = { - .name = "ibm,reset-pe-dma-windows", + [RTAS_FNIDX__IBM_RESET_PE_DMA_WINDOW] = { + /* + * Note: PAPR+ v2.13 7.3.31.4.1 spells this as + * "ibm,reset-pe-dma-windows" (plural), but RTAS + * implementations use the singular form in practice. + */ + .name = "ibm,reset-pe-dma-window", }, [RTAS_FNIDX__IBM_SCAN_LOG_DUMP] = { .name = "ibm,scan-log-dump", diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 496e16c588aa..e8c4129697b1 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -574,29 +574,6 @@ static void iommu_table_setparms(struct pci_controller *phb, struct iommu_table_ops iommu_table_lpar_multi_ops; -/* - * iommu_table_setparms_lpar - * - * Function: On pSeries LPAR systems, return TCE table info, given a pci bus. - */ -static void iommu_table_setparms_lpar(struct pci_controller *phb, - struct device_node *dn, - struct iommu_table *tbl, - struct iommu_table_group *table_group, - const __be32 *dma_window) -{ - unsigned long offset, size, liobn; - - of_parse_dma_window(dn, dma_window, &liobn, &offset, &size); - - iommu_table_setparms_common(tbl, phb->bus->number, liobn, offset, size, IOMMU_PAGE_SHIFT_4K, NULL, - &iommu_table_lpar_multi_ops); - - - table_group->tce32_start = offset; - table_group->tce32_size = size; -} - struct iommu_table_ops iommu_table_pseries_ops = { .set = tce_build_pSeries, .clear = tce_free_pSeries, @@ -724,26 +701,71 @@ struct iommu_table_ops iommu_table_lpar_multi_ops = { * dynamic 64bit DMA window, walking up the device tree. */ static struct device_node *pci_dma_find(struct device_node *dn, - const __be32 **dma_window) + struct dynamic_dma_window_prop *prop) { - const __be32 *dw = NULL; + const __be32 *default_prop = NULL; + const __be32 *ddw_prop = NULL; + struct device_node *rdn = NULL; + bool default_win = false, ddw_win = false; for ( ; dn && PCI_DN(dn); dn = dn->parent) { - dw = of_get_property(dn, "ibm,dma-window", NULL); - if (dw) { - if (dma_window) - *dma_window = dw; - return dn; + default_prop = of_get_property(dn, "ibm,dma-window", NULL); + if (default_prop) { + rdn = dn; + default_win = true; + } + ddw_prop = of_get_property(dn, DIRECT64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; + } + ddw_prop = of_get_property(dn, DMA64_PROPNAME, NULL); + if (ddw_prop) { + rdn = dn; + ddw_win = true; + break; } - dw = of_get_property(dn, DIRECT64_PROPNAME, NULL); - if (dw) - return dn; - dw = of_get_property(dn, DMA64_PROPNAME, NULL); - if (dw) - return dn; + + /* At least found default window, which is the case for normal boot */ + if (default_win) + break; } - return NULL; + /* For PCI devices there will always be a DMA window, either on the device + * or parent bus + */ + WARN_ON(!(default_win | ddw_win)); + + /* caller doesn't want to get DMA window property */ + if (!prop) + return rdn; + + /* parse DMA window property. During normal system boot, only default + * DMA window is passed in OF. But, for kdump, a dedicated adapter might + * have both default and DDW in FDT. In this scenario, DDW takes precedence + * over default window. + */ + if (ddw_win) { + struct dynamic_dma_window_prop *p; + + p = (struct dynamic_dma_window_prop *)ddw_prop; + prop->liobn = p->liobn; + prop->dma_base = p->dma_base; + prop->tce_shift = p->tce_shift; + prop->window_shift = p->window_shift; + } else if (default_win) { + unsigned long offset, size, liobn; + + of_parse_dma_window(rdn, default_prop, &liobn, &offset, &size); + + prop->liobn = cpu_to_be32((u32)liobn); + prop->dma_base = cpu_to_be64(offset); + prop->tce_shift = cpu_to_be32(IOMMU_PAGE_SHIFT_4K); + prop->window_shift = cpu_to_be32(order_base_2(size)); + } + + return rdn; } static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) @@ -751,17 +773,20 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) struct iommu_table *tbl; struct device_node *dn, *pdn; struct pci_dn *ppci; - const __be32 *dma_window = NULL; + struct dynamic_dma_window_prop prop; dn = pci_bus_to_OF_node(bus); pr_debug("pci_dma_bus_setup_pSeriesLP: setting up bus %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); - if (dma_window == NULL) - pr_debug(" no ibm,dma-window property !\n"); + /* In PPC architecture, there will always be DMA window on bus or one of the + * parent bus. During reboot, there will be ibm,dma-window property to + * define DMA window. For kdump, there will at least be default window or DDW + * or both. + */ ppci = PCI_DN(pdn); @@ -771,13 +796,24 @@ static void pci_dma_bus_setup_pSeriesLP(struct pci_bus *bus) if (!ppci->table_group) { ppci->table_group = iommu_pseries_alloc_group(ppci->phb->node); tbl = ppci->table_group->tables[0]; - if (dma_window) { - iommu_table_setparms_lpar(ppci->phb, pdn, tbl, - ppci->table_group, dma_window); - if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) - panic("Failed to initialize iommu table"); - } + iommu_table_setparms_common(tbl, ppci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + ppci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + ppci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); + + if (!iommu_init_table(tbl, ppci->phb->node, 0, 0)) + panic("Failed to initialize iommu table"); + iommu_register_group(ppci->table_group, pci_domain_nr(bus), 0); pr_debug(" created table: %p\n", ppci->table_group); @@ -968,6 +1004,12 @@ static void find_existing_ddw_windows_named(const char *name) continue; } + /* If at the time of system initialization, there are DDWs in OF, + * it means this is during kexec. DDW could be direct or dynamic. + * We will just mark DDWs as "dynamic" since this is kdump path, + * no need to worry about perforance. ddw_list_new_entry() will + * set window->direct = false. + */ window = ddw_list_new_entry(pdn, dma64); if (!window) { of_node_put(pdn); @@ -1524,8 +1566,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) { struct device_node *pdn, *dn; struct iommu_table *tbl; - const __be32 *dma_window = NULL; struct pci_dn *pci; + struct dynamic_dma_window_prop prop; pr_debug("pci_dma_dev_setup_pSeriesLP: %s\n", pci_name(dev)); @@ -1538,7 +1580,7 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) dn = pci_device_to_OF_node(dev); pr_debug(" node is %pOF\n", dn); - pdn = pci_dma_find(dn, &dma_window); + pdn = pci_dma_find(dn, &prop); if (!pdn || !PCI_DN(pdn)) { printk(KERN_WARNING "pci_dma_dev_setup_pSeriesLP: " "no DMA window found for pci dev=%s dn=%pOF\n", @@ -1551,8 +1593,20 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev) if (!pci->table_group) { pci->table_group = iommu_pseries_alloc_group(pci->phb->node); tbl = pci->table_group->tables[0]; - iommu_table_setparms_lpar(pci->phb, pdn, tbl, - pci->table_group, dma_window); + + iommu_table_setparms_common(tbl, pci->phb->bus->number, + be32_to_cpu(prop.liobn), + be64_to_cpu(prop.dma_base), + 1ULL << be32_to_cpu(prop.window_shift), + be32_to_cpu(prop.tce_shift), NULL, + &iommu_table_lpar_multi_ops); + + /* Only for normal boot with default window. Doesn't matter even + * if we set these with DDW which is 64bit during kdump, since + * these will not be used during kdump. + */ + pci->table_group->tce32_start = be64_to_cpu(prop.dma_base); + pci->table_group->tce32_size = 1 << be32_to_cpu(prop.window_shift); iommu_init_table(tbl, pci->phb->node, 0, 0); iommu_register_group(pci->table_group, diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index bffbd869a068..e3142ce531a0 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -315,7 +315,6 @@ config AS_HAS_OPTION_ARCH # https://reviews.llvm.org/D123515 def_bool y depends on $(as-instr, .option arch$(comma) +m) - depends on !$(as-instr, .option arch$(comma) -i) source "arch/riscv/Kconfig.socs" source "arch/riscv/Kconfig.errata" diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 510014051f5d..2468c55933cd 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -424,6 +424,7 @@ # define CSR_STATUS CSR_MSTATUS # define CSR_IE CSR_MIE # define CSR_TVEC CSR_MTVEC +# define CSR_ENVCFG CSR_MENVCFG # define CSR_SCRATCH CSR_MSCRATCH # define CSR_EPC CSR_MEPC # define CSR_CAUSE CSR_MCAUSE @@ -448,6 +449,7 @@ # define CSR_STATUS CSR_SSTATUS # define CSR_IE CSR_SIE # define CSR_TVEC CSR_STVEC +# define CSR_ENVCFG CSR_SENVCFG # define CSR_SCRATCH CSR_SSCRATCH # define CSR_EPC CSR_SEPC # define CSR_CAUSE CSR_SCAUSE diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 329172122952..15055f9df4da 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -25,6 +25,11 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 #ifndef __ASSEMBLY__ + +extern void *return_address(unsigned int level); + +#define ftrace_return_address(n) return_address(n) + void MCOUNT_NAME(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) { diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h index 20f9c3ba2341..22deb7a2a6ec 100644 --- a/arch/riscv/include/asm/hugetlb.h +++ b/arch/riscv/include/asm/hugetlb.h @@ -11,8 +11,10 @@ static inline void arch_clear_hugepage_flags(struct page *page) } #define arch_clear_hugepage_flags arch_clear_hugepage_flags +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h); #define arch_hugetlb_migration_supported arch_hugetlb_migration_supported +#endif #ifdef CONFIG_RISCV_ISA_SVNAPOT #define __HAVE_ARCH_HUGE_PTE_CLEAR diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 5340f818746b..1f2d2599c655 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -81,6 +81,8 @@ #define RISCV_ISA_EXT_ZTSO 72 #define RISCV_ISA_EXT_ZACAS 73 +#define RISCV_ISA_EXT_XLINUXENVCFG 127 + #define RISCV_ISA_EXT_MAX 128 #define RISCV_ISA_EXT_INVALID U32_MAX diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index d169a4f41a2e..c80bb9990d32 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -95,7 +95,13 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) __pud_free(mm, pud); } -#define __pud_free_tlb(tlb, pud, addr) pud_free((tlb)->mm, pud) +#define __pud_free_tlb(tlb, pud, addr) \ +do { \ + if (pgtable_l4_enabled) { \ + pagetable_pud_dtor(virt_to_ptdesc(pud)); \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pud)); \ + } \ +} while (0) #define p4d_alloc_one p4d_alloc_one static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) @@ -124,7 +130,11 @@ static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) __p4d_free(mm, p4d); } -#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) +#define __p4d_free_tlb(tlb, p4d, addr) \ +do { \ + if (pgtable_l5_enabled) \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(p4d)); \ +} while (0) #endif /* __PAGETABLE_PMD_FOLDED */ static inline void sync_kernel_mappings(pgd_t *pgd) @@ -149,7 +159,11 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) #ifndef __PAGETABLE_PMD_FOLDED -#define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) +#define __pmd_free_tlb(tlb, pmd, addr) \ +do { \ + pagetable_pmd_dtor(virt_to_ptdesc(pmd)); \ + tlb_remove_page_ptdesc((tlb), virt_to_ptdesc(pmd)); \ +} while (0) #endif /* __PAGETABLE_PMD_FOLDED */ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h index b42017d76924..b99bd66107a6 100644 --- a/arch/riscv/include/asm/pgtable-64.h +++ b/arch/riscv/include/asm/pgtable-64.h @@ -136,7 +136,7 @@ enum napot_cont_order { * 10010 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable */ #define _PAGE_PMA_THEAD ((1UL << 62) | (1UL << 61) | (1UL << 60)) -#define _PAGE_NOCACHE_THEAD ((1UL < 61) | (1UL << 60)) +#define _PAGE_NOCACHE_THEAD ((1UL << 61) | (1UL << 60)) #define _PAGE_IO_THEAD ((1UL << 63) | (1UL << 60)) #define _PAGE_MTMASK_THEAD (_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 0c94260b5d0c..6066822e7396 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -84,7 +84,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START) +#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START @@ -439,6 +439,10 @@ static inline pte_t pte_mkhuge(pte_t pte) return pte; } +#define pte_leaf_size(pte) (pte_napot(pte) ? \ + napot_cont_size(napot_cont_order(pte)) :\ + PAGE_SIZE) + #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/asm-generic/pgtable.h diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h index 02f87867389a..491296a335d0 100644 --- a/arch/riscv/include/asm/suspend.h +++ b/arch/riscv/include/asm/suspend.h @@ -14,6 +14,7 @@ struct suspend_context { struct pt_regs regs; /* Saved and restored by high-level functions */ unsigned long scratch; + unsigned long envcfg; unsigned long tvec; unsigned long ie; #ifdef CONFIG_MMU diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h index 924d01b56c9a..51f6dfe19745 100644 --- a/arch/riscv/include/asm/vmalloc.h +++ b/arch/riscv/include/asm/vmalloc.h @@ -19,65 +19,6 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) return true; } -#ifdef CONFIG_RISCV_ISA_SVNAPOT -#include <linux/pgtable.h> +#endif -#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size -static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, - u64 pfn, unsigned int max_page_shift) -{ - unsigned long map_size = PAGE_SIZE; - unsigned long size, order; - - if (!has_svnapot()) - return map_size; - - for_each_napot_order_rev(order) { - if (napot_cont_shift(order) > max_page_shift) - continue; - - size = napot_cont_size(order); - if (end - addr < size) - continue; - - if (!IS_ALIGNED(addr, size)) - continue; - - if (!IS_ALIGNED(PFN_PHYS(pfn), size)) - continue; - - map_size = size; - break; - } - - return map_size; -} - -#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift -static inline int arch_vmap_pte_supported_shift(unsigned long size) -{ - int shift = PAGE_SHIFT; - unsigned long order; - - if (!has_svnapot()) - return shift; - - WARN_ON_ONCE(size >= PMD_SIZE); - - for_each_napot_order_rev(order) { - if (napot_cont_size(order) > size) - continue; - - if (!IS_ALIGNED(size, napot_cont_size(order))) - continue; - - shift = napot_cont_shift(order); - break; - } - - return shift; -} - -#endif /* CONFIG_RISCV_ISA_SVNAPOT */ -#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ #endif /* _ASM_RISCV_VMALLOC_H */ diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index f71910718053..604d6bf7e476 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -7,6 +7,7 @@ ifdef CONFIG_FTRACE CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,) @@ -46,6 +47,7 @@ obj-y += irq.o obj-y += process.o obj-y += ptrace.o obj-y += reset.o +obj-y += return_address.o obj-y += setup.o obj-y += signal.o obj-y += syscall_table.o diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index 89920f84d0a3..79a5a35fab96 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -24,6 +24,7 @@ #include <asm/hwprobe.h> #include <asm/patch.h> #include <asm/processor.h> +#include <asm/sbi.h> #include <asm/vector.h> #include "copy-unaligned.h" @@ -202,6 +203,16 @@ static const unsigned int riscv_zvbb_exts[] = { }; /* + * While the [ms]envcfg CSRs were not defined until version 1.12 of the RISC-V + * privileged ISA, the existence of the CSRs is implied by any extension which + * specifies [ms]envcfg bit(s). Hence, we define a custom ISA extension for the + * existence of the CSR, and treat it as a subset of those other extensions. + */ +static const unsigned int riscv_xlinuxenvcfg_exts[] = { + RISCV_ISA_EXT_XLINUXENVCFG +}; + +/* * The canonical order of ISA extension names in the ISA string is defined in * chapter 27 of the unprivileged specification. * @@ -250,8 +261,8 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c), __RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v), __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h), - __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), - __RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ), + __RISCV_ISA_EXT_SUPERSET(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts), + __RISCV_ISA_EXT_SUPERSET(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts), __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), __RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND), __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), @@ -539,6 +550,20 @@ static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) } /* + * "V" in ISA strings is ambiguous in practice: it should mean + * just the standard V-1.0 but vendors aren't well behaved. + * Many vendors with T-Head CPU cores which implement the 0.7.1 + * version of the vector specification put "v" into their DTs. + * CPU cores with the ratified spec will contain non-zero + * marchid. + */ + if (acpi_disabled && riscv_cached_mvendorid(cpu) == THEAD_VENDOR_ID && + riscv_cached_marchid(cpu) == 0x0) { + this_hwcap &= ~isa2hwcap[RISCV_ISA_EXT_v]; + clear_bit(RISCV_ISA_EXT_v, isainfo->isa); + } + + /* * All "okay" hart should have same isa. Set HWCAP based on * common capabilities of every "okay" hart, in case they don't * have. @@ -950,7 +975,7 @@ arch_initcall(check_unaligned_access_all_cpus); void riscv_user_isa_enable(void) { if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ)) - csr_set(CSR_SENVCFG, ENVCFG_CBZE); + csr_set(CSR_ENVCFG, ENVCFG_CBZE); } #ifdef CONFIG_RISCV_ALTERNATIVE diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c new file mode 100644 index 000000000000..c8115ec8fb30 --- /dev/null +++ b/arch/riscv/kernel/return_address.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code come from arch/arm64/kernel/return_address.c + * + * Copyright (C) 2023 SiFive. + */ + +#include <linux/export.h> +#include <linux/kprobes.h> +#include <linux/stacktrace.h> + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static bool save_return_addr(void *d, unsigned long pc) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)pc; + return false; + } + + --data->level; + + return true; +} +NOKPROBE_SYMBOL(save_return_addr); + +noinline void *return_address(unsigned int level) +{ + struct return_address_data data; + + data.level = level + 3; + data.addr = NULL; + + arch_stack_walk(save_return_addr, &data, current, NULL); + + if (!data.level) + return data.addr; + else + return NULL; + +} +EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c index 239509367e42..299795341e8a 100644 --- a/arch/riscv/kernel/suspend.c +++ b/arch/riscv/kernel/suspend.c @@ -15,6 +15,8 @@ void suspend_save_csrs(struct suspend_context *context) { context->scratch = csr_read(CSR_SCRATCH); + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + context->envcfg = csr_read(CSR_ENVCFG); context->tvec = csr_read(CSR_TVEC); context->ie = csr_read(CSR_IE); @@ -36,6 +38,8 @@ void suspend_save_csrs(struct suspend_context *context) void suspend_restore_csrs(struct suspend_context *context) { csr_write(CSR_SCRATCH, context->scratch); + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG)) + csr_write(CSR_ENVCFG, context->envcfg); csr_write(CSR_TVEC, context->tvec); csr_write(CSR_IE, context->ie); diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 29c7606414d2..5ef2a6891158 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -426,10 +426,12 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return __hugetlb_valid_size(size); } +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { return __hugetlb_valid_size(huge_page_size(h)); } +#endif #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 96e6c51515f5..cf1b78cb2d04 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -16,6 +16,11 @@ extern struct boot_params boot_params; static struct real_mode_header hv_vtl_real_mode_header; +static bool __init hv_vtl_msi_ext_dest_id(void) +{ + return true; +} + void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); @@ -38,6 +43,8 @@ void __init hv_vtl_init_platform(void) x86_platform.legacy.warm_reset = 0; x86_platform.legacy.reserve_bios_regions = 0; x86_platform.legacy.devices.pnpbios = 0; + + x86_init.hyper.msi_ext_dest_id = hv_vtl_msi_ext_dest_id; } static inline u64 hv_vtl_system_desc_base(struct ldttss_desc *desc) diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 7dcbf153ad72..768d73de0d09 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -15,6 +15,7 @@ #include <asm/io.h> #include <asm/coco.h> #include <asm/mem_encrypt.h> +#include <asm/set_memory.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/mtrr.h> @@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], } /* + * When transitioning memory between encrypted and decrypted, the caller + * of set_memory_encrypted() or set_memory_decrypted() is responsible for + * ensuring that the memory isn't in use and isn't referenced while the + * transition is in progress. The transition has multiple steps, and the + * memory is in an inconsistent state until all steps are complete. A + * reference while the state is inconsistent could result in an exception + * that can't be cleanly fixed up. + * + * But the Linux kernel load_unaligned_zeropad() mechanism could cause a + * stray reference that can't be prevented by the caller, so Linux has + * specific code to handle this case. But when the #VC and #VE exceptions + * routed to a paravisor, the specific code doesn't work. To avoid this + * problem, mark the pages as "not present" while the transition is in + * progress. If load_unaligned_zeropad() causes a stray reference, a normal + * page fault is generated instead of #VC or #VE, and the page-fault-based + * handlers for load_unaligned_zeropad() resolve the reference. When the + * transition is complete, hv_vtom_set_host_visibility() marks the pages + * as "present" again. + */ +static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc) +{ + return !set_memory_np(kbuffer, pagecount); +} + +/* * hv_vtom_set_host_visibility - Set specified memory visible to host. * * In Isolation VM, all guest memory is encrypted from host and guest @@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo enum hv_mem_host_visibility visibility = enc ? VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE; u64 *pfn_array; + phys_addr_t paddr; + void *vaddr; int ret = 0; bool result = true; int i, pfn; pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); - if (!pfn_array) - return false; + if (!pfn_array) { + result = false; + goto err_set_memory_p; + } for (i = 0, pfn = 0; i < pagecount; i++) { - pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE); + /* + * Use slow_virt_to_phys() because the PRESENT bit has been + * temporarily cleared in the PTEs. slow_virt_to_phys() works + * without the PRESENT bit while virt_to_hvpfn() or similar + * does not. + */ + vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE); + paddr = slow_virt_to_phys(vaddr); + pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT; pfn++; if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) { @@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo } } - err_free_pfn_array: +err_free_pfn_array: kfree(pfn_array); + +err_set_memory_p: + /* + * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present() + * did. Do this even if there is an error earlier in this function in + * order to avoid leaving the memory range in a "broken" state. Setting + * the PRESENT bits shouldn't fail, but return an error if it does. + */ + if (set_memory_p(kbuffer, pagecount)) + result = false; + return result; } static bool hv_vtom_tlb_flush_required(bool private) { - return true; + /* + * Since hv_vtom_clear_present() marks the PTEs as "not present" + * and flushes the TLB, they can't be in the TLB. That makes the + * flush controlled by this function redundant, so return "false". + */ + return false; } static bool hv_vtom_cache_flush_required(void) @@ -608,6 +662,7 @@ void __init hv_vtom_init(void) x86_platform.hyper.is_private_mmio = hv_is_private_mmio; x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required; x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required; + x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present; x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility; /* Set WB as the default cache mode. */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index a5e89641bd2d..9aee31862b4a 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); +int set_memory_p(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 0b97bcde70c6..fbc4e60d027c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1589,6 +1589,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) get_cpu_vendor(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); cpu_parse_early_param(); if (this_cpu->c_early_init) @@ -1601,10 +1602,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) this_cpu->c_bsp_init(c); } else { setup_clear_cpu_cap(X86_FEATURE_CPUID); + get_cpu_address_sizes(c); } - get_cpu_address_sizes(c); - setup_force_cpu_cap(X86_FEATURE_ALWAYS); cpu_set_bug_bits(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index a927a8fc9624..40dec9b56f87 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -184,6 +184,90 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) return false; } +#define MSR_IA32_TME_ACTIVATE 0x982 + +/* Helpers to access TME_ACTIVATE MSR */ +#define TME_ACTIVATE_LOCKED(x) (x & 0x1) +#define TME_ACTIVATE_ENABLED(x) (x & 0x2) + +#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ +#define TME_ACTIVATE_POLICY_AES_XTS_128 0 + +#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ + +#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ +#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 + +/* Values for mktme_status (SW only construct) */ +#define MKTME_ENABLED 0 +#define MKTME_DISABLED 1 +#define MKTME_UNINITIALIZED 2 +static int mktme_status = MKTME_UNINITIALIZED; + +static void detect_tme_early(struct cpuinfo_x86 *c) +{ + u64 tme_activate, tme_policy, tme_crypto_algs; + int keyid_bits = 0, nr_keyids = 0; + static u64 tme_activate_cpu0 = 0; + + rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); + + if (mktme_status != MKTME_UNINITIALIZED) { + if (tme_activate != tme_activate_cpu0) { + /* Broken BIOS? */ + pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); + pr_err_once("x86/tme: MKTME is not usable\n"); + mktme_status = MKTME_DISABLED; + + /* Proceed. We may need to exclude bits from x86_phys_bits. */ + } + } else { + tme_activate_cpu0 = tme_activate; + } + + if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { + pr_info_once("x86/tme: not enabled by BIOS\n"); + mktme_status = MKTME_DISABLED; + return; + } + + if (mktme_status != MKTME_UNINITIALIZED) + goto detect_keyid_bits; + + pr_info("x86/tme: enabled by BIOS\n"); + + tme_policy = TME_ACTIVATE_POLICY(tme_activate); + if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) + pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); + + tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); + if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { + pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", + tme_crypto_algs); + mktme_status = MKTME_DISABLED; + } +detect_keyid_bits: + keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); + nr_keyids = (1UL << keyid_bits) - 1; + if (nr_keyids) { + pr_info_once("x86/mktme: enabled by BIOS\n"); + pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); + } else { + pr_info_once("x86/mktme: disabled by BIOS\n"); + } + + if (mktme_status == MKTME_UNINITIALIZED) { + /* MKTME is usable */ + mktme_status = MKTME_ENABLED; + } + + /* + * KeyID bits effectively lower the number of physical address + * bits. Update cpuinfo_x86::x86_phys_bits accordingly. + */ + c->x86_phys_bits -= keyid_bits; +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -322,6 +406,13 @@ static void early_init_intel(struct cpuinfo_x86 *c) */ if (detect_extended_topology_early(c) < 0) detect_ht_early(c); + + /* + * Adjust the number of physical bits early because it affects the + * valid bits of the MTRR mask registers. + */ + if (cpu_has(c, X86_FEATURE_TME)) + detect_tme_early(c); } static void bsp_init_intel(struct cpuinfo_x86 *c) @@ -482,90 +573,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -#define MSR_IA32_TME_ACTIVATE 0x982 - -/* Helpers to access TME_ACTIVATE MSR */ -#define TME_ACTIVATE_LOCKED(x) (x & 0x1) -#define TME_ACTIVATE_ENABLED(x) (x & 0x2) - -#define TME_ACTIVATE_POLICY(x) ((x >> 4) & 0xf) /* Bits 7:4 */ -#define TME_ACTIVATE_POLICY_AES_XTS_128 0 - -#define TME_ACTIVATE_KEYID_BITS(x) ((x >> 32) & 0xf) /* Bits 35:32 */ - -#define TME_ACTIVATE_CRYPTO_ALGS(x) ((x >> 48) & 0xffff) /* Bits 63:48 */ -#define TME_ACTIVATE_CRYPTO_AES_XTS_128 1 - -/* Values for mktme_status (SW only construct) */ -#define MKTME_ENABLED 0 -#define MKTME_DISABLED 1 -#define MKTME_UNINITIALIZED 2 -static int mktme_status = MKTME_UNINITIALIZED; - -static void detect_tme(struct cpuinfo_x86 *c) -{ - u64 tme_activate, tme_policy, tme_crypto_algs; - int keyid_bits = 0, nr_keyids = 0; - static u64 tme_activate_cpu0 = 0; - - rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate); - - if (mktme_status != MKTME_UNINITIALIZED) { - if (tme_activate != tme_activate_cpu0) { - /* Broken BIOS? */ - pr_err_once("x86/tme: configuration is inconsistent between CPUs\n"); - pr_err_once("x86/tme: MKTME is not usable\n"); - mktme_status = MKTME_DISABLED; - - /* Proceed. We may need to exclude bits from x86_phys_bits. */ - } - } else { - tme_activate_cpu0 = tme_activate; - } - - if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) { - pr_info_once("x86/tme: not enabled by BIOS\n"); - mktme_status = MKTME_DISABLED; - return; - } - - if (mktme_status != MKTME_UNINITIALIZED) - goto detect_keyid_bits; - - pr_info("x86/tme: enabled by BIOS\n"); - - tme_policy = TME_ACTIVATE_POLICY(tme_activate); - if (tme_policy != TME_ACTIVATE_POLICY_AES_XTS_128) - pr_warn("x86/tme: Unknown policy is active: %#llx\n", tme_policy); - - tme_crypto_algs = TME_ACTIVATE_CRYPTO_ALGS(tme_activate); - if (!(tme_crypto_algs & TME_ACTIVATE_CRYPTO_AES_XTS_128)) { - pr_err("x86/mktme: No known encryption algorithm is supported: %#llx\n", - tme_crypto_algs); - mktme_status = MKTME_DISABLED; - } -detect_keyid_bits: - keyid_bits = TME_ACTIVATE_KEYID_BITS(tme_activate); - nr_keyids = (1UL << keyid_bits) - 1; - if (nr_keyids) { - pr_info_once("x86/mktme: enabled by BIOS\n"); - pr_info_once("x86/mktme: %d KeyIDs available\n", nr_keyids); - } else { - pr_info_once("x86/mktme: disabled by BIOS\n"); - } - - if (mktme_status == MKTME_UNINITIALIZED) { - /* MKTME is usable */ - mktme_status = MKTME_ENABLED; - } - - /* - * KeyID bits effectively lower the number of physical address - * bits. Update cpuinfo_x86::x86_phys_bits accordingly. - */ - c->x86_phys_bits -= keyid_bits; -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -702,9 +709,6 @@ static void init_intel(struct cpuinfo_x86 *c) init_ia32_feat_ctl(c); - if (cpu_has(c, X86_FEATURE_TME)) - detect_tme(c); - init_intel_misc_features(c); split_lock_init(); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index fb8cf953380d..b66f540de054 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1017,10 +1017,12 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* - * SETUP_EFI and SETUP_IMA are supplied by kexec and do not need - * to be reserved. + * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by + * kexec and do not need to be reserved. */ - if (data->type != SETUP_EFI && data->type != SETUP_IMA) + if (data->type != SETUP_EFI && + data->type != SETUP_IMA && + data->type != SETUP_RNG_SEED) e820__range_update_kexec(pa_data, sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index e9b448d1b1b7..102880404046 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address) * areas on 32-bit NUMA systems. The percpu areas can * end up in this kind of memory, for instance. * - * This could be optimized, but it is only intended to be - * used at initialization time, and keeping it - * unoptimized should increase the testing coverage for - * the more obscure platforms. + * Note that as long as the PTEs are well-formed with correct PFNs, this + * works without checking the PRESENT bit in the leaf PTE. This is unlike + * the similar vmalloc_to_page() and derivatives. Callers may depend on + * this behavior. + * + * This could be optimized, but it is only used in paths that are not perf + * sensitive, and keeping it unoptimized should increase the testing coverage + * for the more obscure platforms. */ phys_addr_t slow_virt_to_phys(void *__virt_addr) { @@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn) return rc; } -static int set_memory_p(unsigned long *addr, int numpages) -{ - return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0); -} - /* Restore full speculative operation to the pfn. */ int clear_mce_nospec(unsigned long pfn) { unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); - return set_memory_p(&addr, 1); + return set_memory_p(addr, 1); } EXPORT_SYMBOL_GPL(clear_mce_nospec); #endif /* CONFIG_X86_64 */ @@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages) CPA_NO_CHECK_ALIAS, NULL); } +int set_memory_p(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} + int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index 50d8ce20ae5b..9fb1575f8d88 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -2550,14 +2550,12 @@ static int fore200e_sba_probe(struct platform_device *op) return 0; } -static int fore200e_sba_remove(struct platform_device *op) +static void fore200e_sba_remove(struct platform_device *op) { struct fore200e *fore200e = dev_get_drvdata(&op->dev); fore200e_shutdown(fore200e); kfree(fore200e); - - return 0; } static const struct of_device_id fore200e_sba_match[] = { @@ -2574,7 +2572,7 @@ static struct platform_driver fore200e_sba_driver = { .of_match_table = fore200e_sba_match, }, .probe = fore200e_sba_probe, - .remove = fore200e_sba_remove, + .remove_new = fore200e_sba_remove, }; #endif diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c index 1262a7773ef3..de50c00ba218 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c @@ -299,22 +299,6 @@ theend: return err; } -static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) -{ - struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); - struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); - struct sun8i_ce_dev *ce = op->ce; - struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); - int flow, err; - - flow = rctx->flow; - err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); - local_bh_disable(); - crypto_finalize_skcipher_request(engine, breq, err); - local_bh_enable(); -} - static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, void *async_req) { @@ -360,6 +344,23 @@ static void sun8i_ce_cipher_unprepare(struct crypto_engine *engine, dma_unmap_single(ce->dev, rctx->addr_key, op->keylen, DMA_TO_DEVICE); } +static void sun8i_ce_cipher_run(struct crypto_engine *engine, void *areq) +{ + struct skcipher_request *breq = container_of(areq, struct skcipher_request, base); + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(breq); + struct sun8i_cipher_tfm_ctx *op = crypto_skcipher_ctx(tfm); + struct sun8i_ce_dev *ce = op->ce; + struct sun8i_cipher_req_ctx *rctx = skcipher_request_ctx(breq); + int flow, err; + + flow = rctx->flow; + err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(breq->base.tfm)); + sun8i_ce_cipher_unprepare(engine, areq); + local_bh_disable(); + crypto_finalize_skcipher_request(engine, breq, err); + local_bh_enable(); +} + int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) { int err = sun8i_ce_cipher_prepare(engine, areq); @@ -368,7 +369,6 @@ int sun8i_ce_cipher_do_one(struct crypto_engine *engine, void *areq) return err; sun8i_ce_cipher_run(engine, areq); - sun8i_ce_cipher_unprepare(engine, areq); return 0; } diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index 1b13b4aa16ec..a235e6c300f1 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -332,12 +332,12 @@ static int rk_hash_run(struct crypto_engine *engine, void *breq) theend: pm_runtime_put_autosuspend(rkc->dev); + rk_hash_unprepare(engine, breq); + local_bh_disable(); crypto_finalize_hash_request(engine, breq, err); local_bh_enable(); - rk_hash_unprepare(engine, breq); - return 0; } diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c index b38786f0ad79..b75fdaffad9a 100644 --- a/drivers/dma/dw-edma/dw-edma-v0-core.c +++ b/drivers/dma/dw-edma/dw-edma-v0-core.c @@ -346,6 +346,20 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk) dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr); } +static void dw_edma_v0_sync_ll_data(struct dw_edma_chunk *chunk) +{ + /* + * In case of remote eDMA engine setup, the DW PCIe RP/EP internal + * configuration registers and application memory are normally accessed + * over different buses. Ensure LL-data reaches the memory before the + * doorbell register is toggled by issuing the dummy-read from the remote + * LL memory in a hope that the MRd TLP will return only after the + * last MWr TLP is completed + */ + if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + readl(chunk->ll_region.vaddr.io); +} + static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) { struct dw_edma_chan *chan = chunk->chan; @@ -412,6 +426,9 @@ static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first) SET_CH_32(dw, chan->dir, chan->id, llp.msb, upper_32_bits(chunk->ll_region.paddr)); } + + dw_edma_v0_sync_ll_data(chunk); + /* Doorbell */ SET_RW_32(dw, chan->dir, doorbell, FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id)); diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c index 00b735a0202a..10e8f0715114 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-core.c +++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c @@ -65,18 +65,12 @@ static void dw_hdma_v0_core_off(struct dw_edma *dw) static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir) { - u32 num_ch = 0; - int id; - - for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) { - if (GET_CH_32(dw, id, dir, ch_en) & BIT(0)) - num_ch++; - } - - if (num_ch > HDMA_V0_MAX_NR_CH) - num_ch = HDMA_V0_MAX_NR_CH; - - return (u16)num_ch; + /* + * The HDMA IP have no way to know the number of hardware channels + * available, we set it to maximum channels and let the platform + * set the right number of channels. + */ + return HDMA_V0_MAX_NR_CH; } static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan) @@ -228,6 +222,20 @@ static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk) dw_hdma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr); } +static void dw_hdma_v0_sync_ll_data(struct dw_edma_chunk *chunk) +{ + /* + * In case of remote HDMA engine setup, the DW PCIe RP/EP internal + * configuration registers and application memory are normally accessed + * over different buses. Ensure LL-data reaches the memory before the + * doorbell register is toggled by issuing the dummy-read from the remote + * LL memory in a hope that the MRd TLP will return only after the + * last MWr TLP is completed + */ + if (!(chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + readl(chunk->ll_region.vaddr.io); +} + static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) { struct dw_edma_chan *chan = chunk->chan; @@ -242,7 +250,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) /* Interrupt enable&unmask - done, abort */ tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) | HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK | - HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN; + HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN; + if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL)) + tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN; SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp); /* Channel control */ SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN); @@ -256,6 +266,9 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first) /* Set consumer cycle */ SET_CH_32(dw, chan->dir, chan->id, cycle_sync, HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT); + + dw_hdma_v0_sync_ll_data(chunk); + /* Doorbell */ SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START); } diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h index a974abdf8aaf..eab5fd7177e5 100644 --- a/drivers/dma/dw-edma/dw-hdma-v0-regs.h +++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h @@ -15,7 +15,7 @@ #define HDMA_V0_LOCAL_ABORT_INT_EN BIT(6) #define HDMA_V0_REMOTE_ABORT_INT_EN BIT(5) #define HDMA_V0_LOCAL_STOP_INT_EN BIT(4) -#define HDMA_V0_REMOTEL_STOP_INT_EN BIT(3) +#define HDMA_V0_REMOTE_STOP_INT_EN BIT(3) #define HDMA_V0_ABORT_INT_MASK BIT(2) #define HDMA_V0_STOP_INT_MASK BIT(0) #define HDMA_V0_LINKLIST_EN BIT(0) diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index b53f46245c37..793f1a7ad5e3 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -503,7 +503,7 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan, if (fsl_chan->is_multi_fifo) { /* set mloff to support multiple fifo */ burst = cfg->direction == DMA_DEV_TO_MEM ? - cfg->src_addr_width : cfg->dst_addr_width; + cfg->src_maxburst : cfg->dst_maxburst; nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4)); /* enable DMLOE/SMLOE */ if (cfg->direction == DMA_MEM_TO_DEV) { diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index bb5221158a77..f5e216b157c7 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -30,8 +30,9 @@ #define EDMA_TCD_ATTR_SSIZE(x) (((x) & GENMASK(2, 0)) << 8) #define EDMA_TCD_ATTR_SMOD(x) (((x) & GENMASK(4, 0)) << 11) -#define EDMA_TCD_CITER_CITER(x) ((x) & GENMASK(14, 0)) -#define EDMA_TCD_BITER_BITER(x) ((x) & GENMASK(14, 0)) +#define EDMA_TCD_ITER_MASK GENMASK(14, 0) +#define EDMA_TCD_CITER_CITER(x) ((x) & EDMA_TCD_ITER_MASK) +#define EDMA_TCD_BITER_BITER(x) ((x) & EDMA_TCD_ITER_MASK) #define EDMA_TCD_CSR_START BIT(0) #define EDMA_TCD_CSR_INT_MAJOR BIT(1) diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 45cc419b1b4a..d36e28b9c767 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -10,6 +10,7 @@ */ #include <dt-bindings/dma/fsl-edma.h> +#include <linux/bitfield.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/clk.h> @@ -582,7 +583,8 @@ static int fsl_edma_probe(struct platform_device *pdev) DMAENGINE_ALIGN_32_BYTES; /* Per worst case 'nbytes = 1' take CITER as the max_seg_size */ - dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff); + dma_set_max_seg_size(fsl_edma->dma_dev.dev, + FIELD_GET(EDMA_TCD_ITER_MASK, EDMA_TCD_ITER_MASK)); fsl_edma->dma_dev.residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT; diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c index f405c77060ad..5005e138fc23 100644 --- a/drivers/dma/fsl-qdma.c +++ b/drivers/dma/fsl-qdma.c @@ -109,6 +109,7 @@ #define FSL_QDMA_CMD_WTHROTL_OFFSET 20 #define FSL_QDMA_CMD_DSEN_OFFSET 19 #define FSL_QDMA_CMD_LWC_OFFSET 16 +#define FSL_QDMA_CMD_PF BIT(17) /* Field definition for Descriptor status */ #define QDMA_CCDF_STATUS_RTE BIT(5) @@ -160,6 +161,10 @@ struct fsl_qdma_format { u8 __reserved1[2]; u8 cfg8b_w1; } __packed; + struct { + __le32 __reserved2; + __le32 cmd; + } __packed; __le64 data; }; } __packed; @@ -354,7 +359,6 @@ static void fsl_qdma_free_chan_resources(struct dma_chan *chan) static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, dma_addr_t dst, dma_addr_t src, u32 len) { - u32 cmd; struct fsl_qdma_format *sdf, *ddf; struct fsl_qdma_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest; @@ -383,14 +387,11 @@ static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp, /* This entry is the last entry. */ qdma_csgf_set_f(csgf_dest, len); /* Descriptor Buffer */ - cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); - sdf->data = QDMA_SDDF_CMD(cmd); - - cmd = cpu_to_le32(FSL_QDMA_CMD_RWTTYPE << - FSL_QDMA_CMD_RWTTYPE_OFFSET); - cmd |= cpu_to_le32(FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET); - ddf->data = QDMA_SDDF_CMD(cmd); + sdf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) | + FSL_QDMA_CMD_PF); + + ddf->cmd = cpu_to_le32((FSL_QDMA_CMD_RWTTYPE << FSL_QDMA_CMD_RWTTYPE_OFFSET) | + (FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET)); } /* @@ -624,7 +625,7 @@ static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma) static int fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma, - void *block, + __iomem void *block, int id) { bool duplicate; @@ -1196,10 +1197,6 @@ static int fsl_qdma_probe(struct platform_device *pdev) if (!fsl_qdma->queue) return -ENOMEM; - ret = fsl_qdma_irq_init(pdev, fsl_qdma); - if (ret) - return ret; - fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0"); if (fsl_qdma->irq_base < 0) return fsl_qdma->irq_base; @@ -1238,16 +1235,19 @@ static int fsl_qdma_probe(struct platform_device *pdev) platform_set_drvdata(pdev, fsl_qdma); - ret = dma_async_device_register(&fsl_qdma->dma_dev); + ret = fsl_qdma_reg_init(fsl_qdma); if (ret) { - dev_err(&pdev->dev, - "Can't register NXP Layerscape qDMA engine.\n"); + dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); return ret; } - ret = fsl_qdma_reg_init(fsl_qdma); + ret = fsl_qdma_irq_init(pdev, fsl_qdma); + if (ret) + return ret; + + ret = dma_async_device_register(&fsl_qdma->dma_dev); if (ret) { - dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n"); + dev_err(&pdev->dev, "Can't register NXP Layerscape qDMA engine.\n"); return ret; } diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 77f8885cf407..e5a94a93a3cc 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -345,7 +345,7 @@ static void idxd_cdev_evl_drain_pasid(struct idxd_wq *wq, u32 pasid) spin_lock(&evl->lock); status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = status.tail; - h = evl->head; + h = status.head; size = evl->size; while (h != t) { diff --git a/drivers/dma/idxd/debugfs.c b/drivers/dma/idxd/debugfs.c index 9cfbd9b14c4c..f3f25ee676f3 100644 --- a/drivers/dma/idxd/debugfs.c +++ b/drivers/dma/idxd/debugfs.c @@ -68,9 +68,9 @@ static int debugfs_evl_show(struct seq_file *s, void *d) spin_lock(&evl->lock); - h = evl->head; evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; + h = evl_status.head; evl_size = evl->size; seq_printf(s, "Event Log head %u tail %u interrupt pending %u\n\n", diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 47de3f93ff1e..d0f5db6cf1ed 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -300,7 +300,6 @@ struct idxd_evl { unsigned int log_size; /* The number of entries in the event log. */ u16 size; - u16 head; unsigned long *bmap; bool batch_fail[IDXD_MAX_BATCH_IDENT]; }; diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 14df1f1347a8..4954adc6bb60 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -343,7 +343,9 @@ static void idxd_cleanup_internals(struct idxd_device *idxd) static int idxd_init_evl(struct idxd_device *idxd) { struct device *dev = &idxd->pdev->dev; + unsigned int evl_cache_size; struct idxd_evl *evl; + const char *idxd_name; if (idxd->hw.gen_cap.evl_support == 0) return 0; @@ -355,9 +357,16 @@ static int idxd_init_evl(struct idxd_device *idxd) spin_lock_init(&evl->lock); evl->size = IDXD_EVL_SIZE_MIN; - idxd->evl_cache = kmem_cache_create(dev_name(idxd_confdev(idxd)), - sizeof(struct idxd_evl_fault) + evl_ent_size(idxd), - 0, 0, NULL); + idxd_name = dev_name(idxd_confdev(idxd)); + evl_cache_size = sizeof(struct idxd_evl_fault) + evl_ent_size(idxd); + /* + * Since completion record in evl_cache will be copied to user + * when handling completion record page fault, need to create + * the cache suitable for user copy. + */ + idxd->evl_cache = kmem_cache_create_usercopy(idxd_name, evl_cache_size, + 0, 0, 0, evl_cache_size, + NULL); if (!idxd->evl_cache) { kfree(evl); return -ENOMEM; diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index c8a0aa874b11..348aa21389a9 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -367,9 +367,9 @@ static void process_evl_entries(struct idxd_device *idxd) /* Clear interrupt pending bit */ iowrite32(evl_status.bits_upper32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET + sizeof(u32)); - h = evl->head; evl_status.bits = ioread64(idxd->reg_base + IDXD_EVLSTATUS_OFFSET); t = evl_status.tail; + h = evl_status.head; size = idxd->evl->size; while (h != t) { @@ -378,7 +378,6 @@ static void process_evl_entries(struct idxd_device *idxd) h = (h + 1) % size; } - evl->head = h; evl_status.head = h; iowrite32(evl_status.bits_lower32, idxd->reg_base + IDXD_EVLSTATUS_OFFSET); spin_unlock(&evl->lock); diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/ptdma/ptdma-dmaengine.c index 1aa65e5de0f3..f79240734807 100644 --- a/drivers/dma/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/ptdma/ptdma-dmaengine.c @@ -385,8 +385,6 @@ int pt_dmaengine_register(struct pt_device *pt) chan->vc.desc_free = pt_do_cleanup; vchan_init(&chan->vc, dma_dev); - dma_set_mask_and_coherent(pt->dev, DMA_BIT_MASK(64)); - ret = dma_async_device_register(dma_dev); if (ret) goto err_reg; diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c index 12fcd420396e..6b2a6236f5e3 100644 --- a/drivers/dpll/dpll_core.c +++ b/drivers/dpll/dpll_core.c @@ -44,11 +44,6 @@ struct dpll_pin_registration { void *priv; }; -struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) -{ - return rcu_dereference_rtnl(dev->dpll_pin); -} - struct dpll_device *dpll_device_get_by_id(int id) { if (xa_get_mark(&dpll_device_xa, id, DPLL_REGISTERED)) @@ -515,6 +510,26 @@ err_pin_prop: return ERR_PTR(ret); } +static void dpll_netdev_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) +{ + rtnl_lock(); + rcu_assign_pointer(dev->dpll_pin, dpll_pin); + rtnl_unlock(); +} + +void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) +{ + WARN_ON(!dpll_pin); + dpll_netdev_pin_assign(dev, dpll_pin); +} +EXPORT_SYMBOL(dpll_netdev_pin_set); + +void dpll_netdev_pin_clear(struct net_device *dev) +{ + dpll_netdev_pin_assign(dev, NULL); +} +EXPORT_SYMBOL(dpll_netdev_pin_clear); + /** * dpll_pin_get - find existing or create new dpll pin * @clock_id: clock_id of creator diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index 1419fd0d241c..98e6ad8528d3 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -8,6 +8,7 @@ */ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/netdevice.h> #include <net/genetlink.h> #include "dpll_core.h" #include "dpll_netlink.h" @@ -48,18 +49,6 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id) } /** - * dpll_msg_pin_handle_size - get size of pin handle attribute for given pin - * @pin: pin pointer - * - * Return: byte size of pin handle attribute for given pin. - */ -size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) -{ - return pin ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */ -} -EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size); - -/** * dpll_msg_add_pin_handle - attach pin handle attribute to a given message * @msg: pointer to sk_buff message to attach a pin handle * @pin: pin pointer @@ -68,7 +57,7 @@ EXPORT_SYMBOL_GPL(dpll_msg_pin_handle_size); * * 0 - success * * -EMSGSIZE - no space in message to attach pin handle */ -int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +static int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) { if (!pin) return 0; @@ -76,7 +65,28 @@ int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) return -EMSGSIZE; return 0; } -EXPORT_SYMBOL_GPL(dpll_msg_add_pin_handle); + +static struct dpll_pin *dpll_netdev_pin(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->dpll_pin); +} + +/** + * dpll_netdev_pin_handle_size - get size of pin handle attribute of a netdev + * @dev: netdev from which to get the pin + * + * Return: byte size of pin handle attribute, or 0 if @dev has no pin. + */ +size_t dpll_netdev_pin_handle_size(const struct net_device *dev) +{ + return dpll_netdev_pin(dev) ? nla_total_size(4) : 0; /* DPLL_A_PIN_ID */ +} + +int dpll_netdev_add_pin_handle(struct sk_buff *msg, + const struct net_device *dev) +{ + return dpll_msg_add_pin_handle(msg, dpll_netdev_pin(dev)); +} static int dpll_msg_add_mode(struct sk_buff *msg, struct dpll_device *dpll, diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c index 8aaa7fcb2630..401a77e3b5fa 100644 --- a/drivers/firewire/core-card.c +++ b/drivers/firewire/core-card.c @@ -500,7 +500,19 @@ static void bm_work(struct work_struct *work) fw_notice(card, "phy config: new root=%x, gap_count=%d\n", new_root_id, gap_count); fw_send_phy_config(card, new_root_id, generation, gap_count); - reset_bus(card, true); + /* + * Where possible, use a short bus reset to minimize + * disruption to isochronous transfers. But in the event + * of a gap count inconsistency, use a long bus reset. + * + * As noted in 1394a 8.4.6.2, nodes on a mixed 1394/1394a bus + * may set different gap counts after a bus reset. On a mixed + * 1394/1394a bus, a short bus reset can get doubled. Some + * nodes may treat the double reset as one bus reset and others + * may treat it as two, causing a gap count inconsistency + * again. Using a long bus reset prevents this. + */ + reset_bus(card, card->gap_count != 0); /* Will allocate broadcast channel after the reset. */ goto out; } diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index 3e8d4b51a814..97bafb5f7038 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -292,7 +292,7 @@ static int efi_capsule_open(struct inode *inode, struct file *file) return -ENOMEM; } - cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL); + cap_info->phys = kzalloc(sizeof(phys_addr_t), GFP_KERNEL); if (!cap_info->phys) { kfree(cap_info->pages); kfree(cap_info); diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c index 682e417be5a3..fbeeaee4ac85 100644 --- a/drivers/firmware/microchip/mpfs-auto-update.c +++ b/drivers/firmware/microchip/mpfs-auto-update.c @@ -384,7 +384,8 @@ static int mpfs_auto_update_available(struct mpfs_auto_update_priv *priv) u32 *response_msg; int ret; - response_msg = devm_kzalloc(priv->dev, AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(response_msg), + response_msg = devm_kzalloc(priv->dev, + AUTO_UPDATE_FEATURE_RESP_SIZE * sizeof(*response_msg), GFP_KERNEL); if (!response_msg) return -ENOMEM; diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c index e00c33310517..753e7be039e4 100644 --- a/drivers/gpio/gpio-74x164.c +++ b/drivers/gpio/gpio-74x164.c @@ -127,8 +127,6 @@ static int gen_74x164_probe(struct spi_device *spi) if (IS_ERR(chip->gpiod_oe)) return PTR_ERR(chip->gpiod_oe); - gpiod_set_value_cansleep(chip->gpiod_oe, 1); - spi_set_drvdata(spi, chip); chip->gpio_chip.label = spi->modalias; @@ -153,6 +151,8 @@ static int gen_74x164_probe(struct spi_device *spi) goto exit_destroy; } + gpiod_set_value_cansleep(chip->gpiod_oe, 1); + ret = gpiochip_add_data(&chip->gpio_chip, chip); if (!ret) return 0; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index e434e8cc1229..75be4a3ca7f8 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -968,11 +968,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, ret = gpiochip_irqchip_init_valid_mask(gc); if (ret) - goto err_remove_acpi_chip; + goto err_free_hogs; ret = gpiochip_irqchip_init_hw(gc); if (ret) - goto err_remove_acpi_chip; + goto err_remove_irqchip_mask; ret = gpiochip_add_irqchip(gc, lock_key, request_key); if (ret) @@ -997,13 +997,13 @@ err_remove_irqchip: gpiochip_irqchip_remove(gc); err_remove_irqchip_mask: gpiochip_irqchip_free_valid_mask(gc); -err_remove_acpi_chip: +err_free_hogs: + gpiochip_free_hogs(gc); acpi_gpiochip_remove(gc); + gpiochip_remove_pin_ranges(gc); err_remove_of_chip: - gpiochip_free_hogs(gc); of_gpiochip_remove(gc); err_free_gpiochip_mask: - gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); err_remove_from_list: spin_lock_irqsave(&gpio_lock, flags); diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 2520db0b776e..c7edba18a6f0 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -199,7 +199,7 @@ config DRM_TTM config DRM_TTM_KUNIT_TEST tristate "KUnit tests for TTM" if !KUNIT_ALL_TESTS default n - depends on DRM && KUNIT && MMU + depends on DRM && KUNIT && MMU && (UML || COMPILE_TEST) select DRM_TTM select DRM_EXPORT_FOR_TESTS if m select DRM_KUNIT_TEST_HELPERS @@ -207,7 +207,8 @@ config DRM_TTM_KUNIT_TEST help Enables unit tests for TTM, a GPU memory manager subsystem used to manage memory buffers. This option is mostly useful for kernel - developers. + developers. It depends on (UML || COMPILE_TEST) since no other driver + which uses TTM can be loaded while running the tests. If in doubt, say "N". diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index c64c01e2944a..1c614451dead 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -574,11 +574,34 @@ soc15_asic_reset_method(struct amdgpu_device *adev) return AMD_RESET_METHOD_MODE1; } +static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) +{ + u32 sol_reg; + + sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); + + /* Will reset for the following suspend abort cases. + * 1) Only reset limit on APU side, dGPU hasn't checked yet. + * 2) S3 suspend abort and TOS already launched. + */ + if (adev->flags & AMD_IS_APU && adev->in_s3 && + !adev->suspend_complete && + sol_reg) + return true; + + return false; +} + static int soc15_asic_reset(struct amdgpu_device *adev) { /* original raven doesn't have full asic reset */ - if ((adev->apu_flags & AMD_APU_IS_RAVEN) || - (adev->apu_flags & AMD_APU_IS_RAVEN2)) + /* On the latest Raven, the GPU reset can be performed + * successfully. So now, temporarily enable it for the + * S3 suspend abort case. + */ + if (((adev->apu_flags & AMD_APU_IS_RAVEN) || + (adev->apu_flags & AMD_APU_IS_RAVEN2)) && + !soc15_need_reset_on_resume(adev)) return 0; switch (soc15_asic_reset_method(adev)) { @@ -1298,24 +1321,6 @@ static int soc15_common_suspend(void *handle) return soc15_common_hw_fini(adev); } -static bool soc15_need_reset_on_resume(struct amdgpu_device *adev) -{ - u32 sol_reg; - - sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81); - - /* Will reset for the following suspend abort cases. - * 1) Only reset limit on APU side, dGPU hasn't checked yet. - * 2) S3 suspend abort and TOS already launched. - */ - if (adev->flags & AMD_IS_APU && adev->in_s3 && - !adev->suspend_complete && - sol_reg) - return true; - - return false; -} - static int soc15_common_resume(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 85b7f58a7f35..c27063305a13 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -67,6 +67,8 @@ static void apply_edid_quirks(struct edid *edid, struct dc_edid_caps *edid_caps) /* Workaround for some monitors that do not clear DPCD 0x317 if FreeSync is unsupported */ case drm_edid_encode_panel_id('A', 'U', 'O', 0xA7AB): case drm_edid_encode_panel_id('A', 'U', 'O', 0xE69B): + case drm_edid_encode_panel_id('B', 'O', 'E', 0x092A): + case drm_edid_encode_panel_id('L', 'G', 'D', 0x06D1): DRM_DEBUG_DRIVER("Clearing DPCD 0x317 on monitor with panel id %X\n", panel_id); edid_caps->panel_patch.remove_sink_ext_caps = true; break; @@ -120,6 +122,8 @@ enum dc_edid_status dm_helpers_parse_edid_caps( edid_caps->edid_hdmi = connector->display_info.is_hdmi; + apply_edid_quirks(edid_buf, edid_caps); + sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads); if (sad_count <= 0) return result; @@ -146,8 +150,6 @@ enum dc_edid_status dm_helpers_parse_edid_caps( else edid_caps->speaker_flags = DEFAULT_SPEAKER_LOCATION; - apply_edid_quirks(edid_buf, edid_caps); - kfree(sads); kfree(sadb); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c index 26307e599614..2a58a7687bdb 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_wrapper.c @@ -76,6 +76,11 @@ static void map_hw_resources(struct dml2_context *dml2, in_out_display_cfg->hw.DLGRefClkFreqMHz = 50; } for (j = 0; j < mode_support_info->DPPPerSurface[i]; j++) { + if (i >= __DML2_WRAPPER_MAX_STREAMS_PLANES__) { + dml_print("DML::%s: Index out of bounds: i=%d, __DML2_WRAPPER_MAX_STREAMS_PLANES__=%d\n", + __func__, i, __DML2_WRAPPER_MAX_STREAMS_PLANES__); + break; + } dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_stream_id[i]; dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_stream_id_valid[num_pipes] = true; dml2->v20.scratch.dml_to_dc_pipe_mapping.dml_pipe_idx_to_plane_id[num_pipes] = dml2->v20.scratch.dml_to_dc_pipe_mapping.disp_cfg_to_plane_id[i]; diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c index df4f20293c16..eb4da3666e05 100644 --- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c +++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c @@ -6925,6 +6925,23 @@ static int si_dpm_enable(struct amdgpu_device *adev) return 0; } +static int si_set_temperature_range(struct amdgpu_device *adev) +{ + int ret; + + ret = si_thermal_enable_alert(adev, false); + if (ret) + return ret; + ret = si_thermal_set_temperature_range(adev, R600_TEMP_RANGE_MIN, R600_TEMP_RANGE_MAX); + if (ret) + return ret; + ret = si_thermal_enable_alert(adev, true); + if (ret) + return ret; + + return ret; +} + static void si_dpm_disable(struct amdgpu_device *adev) { struct rv7xx_power_info *pi = rv770_get_pi(adev); @@ -7608,6 +7625,18 @@ static int si_dpm_process_interrupt(struct amdgpu_device *adev, static int si_dpm_late_init(void *handle) { + int ret; + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + + if (!adev->pm.dpm_enabled) + return 0; + + ret = si_set_temperature_range(adev); + if (ret) + return ret; +#if 0 //TODO ? + si_dpm_powergate_uvd(adev, true); +#endif return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 4cd43bbec910..bcad42534da4 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -1303,13 +1303,12 @@ static int arcturus_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 8d1d29ffb0f1..ed189a3878eb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -2357,13 +2357,12 @@ static int navi10_get_power_limit(struct smu_context *smu, *default_power_limit = power_limit; if (smu->od_enabled && - navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) { + navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 21fc033528fa..e2ad2b972ab0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -640,13 +640,12 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index a9954ffc02c5..9b80f18ea6c3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -2369,13 +2369,12 @@ static int smu_v13_0_0_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_0_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 0ffdb58af74e..3dc7b60cb075 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -2333,13 +2333,12 @@ static int smu_v13_0_7_get_power_limit(struct smu_context *smu, if (default_power_limit) *default_power_limit = power_limit; - if (smu->od_enabled) { + if (smu->od_enabled) od_percent_upper = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); - od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); - } else { + else od_percent_upper = 0; - od_percent_lower = 100; - } + + od_percent_lower = le32_to_cpu(powerplay_table->overdrive_table.min[SMU_13_0_7_ODSETTING_POWERPERCENTAGE]); dev_dbg(smu->adev->dev, "od percent upper:%d, od percent lower:%d (default power: %d)\n", od_percent_upper, od_percent_lower, power_limit); diff --git a/drivers/gpu/drm/bridge/aux-hpd-bridge.c b/drivers/gpu/drm/bridge/aux-hpd-bridge.c index bb55f697a181..6886db2d9e00 100644 --- a/drivers/gpu/drm/bridge/aux-hpd-bridge.c +++ b/drivers/gpu/drm/bridge/aux-hpd-bridge.c @@ -25,20 +25,18 @@ static void drm_aux_hpd_bridge_release(struct device *dev) ida_free(&drm_aux_hpd_bridge_ida, adev->id); of_node_put(adev->dev.platform_data); + of_node_put(adev->dev.of_node); kfree(adev); } -static void drm_aux_hpd_bridge_unregister_adev(void *_adev) +static void drm_aux_hpd_bridge_free_adev(void *_adev) { - struct auxiliary_device *adev = _adev; - - auxiliary_device_delete(adev); - auxiliary_device_uninit(adev); + auxiliary_device_uninit(_adev); } /** - * drm_dp_hpd_bridge_register - Create a simple HPD DisplayPort bridge + * devm_drm_dp_hpd_bridge_alloc - allocate a HPD DisplayPort bridge * @parent: device instance providing this bridge * @np: device node pointer corresponding to this bridge instance * @@ -46,11 +44,9 @@ static void drm_aux_hpd_bridge_unregister_adev(void *_adev) * DRM_MODE_CONNECTOR_DisplayPort, which terminates the bridge chain and is * able to send the HPD events. * - * Return: device instance that will handle created bridge or an error code - * encoded into the pointer. + * Return: bridge auxiliary device pointer or an error pointer */ -struct device *drm_dp_hpd_bridge_register(struct device *parent, - struct device_node *np) +struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np) { struct auxiliary_device *adev; int ret; @@ -74,18 +70,62 @@ struct device *drm_dp_hpd_bridge_register(struct device *parent, ret = auxiliary_device_init(adev); if (ret) { + of_node_put(adev->dev.platform_data); + of_node_put(adev->dev.of_node); ida_free(&drm_aux_hpd_bridge_ida, adev->id); kfree(adev); return ERR_PTR(ret); } - ret = auxiliary_device_add(adev); - if (ret) { - auxiliary_device_uninit(adev); + ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_free_adev, adev); + if (ret) return ERR_PTR(ret); - } - ret = devm_add_action_or_reset(parent, drm_aux_hpd_bridge_unregister_adev, adev); + return adev; +} +EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_alloc); + +static void drm_aux_hpd_bridge_del_adev(void *_adev) +{ + auxiliary_device_delete(_adev); +} + +/** + * devm_drm_dp_hpd_bridge_add - register a HDP DisplayPort bridge + * @dev: struct device to tie registration lifetime to + * @adev: bridge auxiliary device to be registered + * + * Returns: zero on success or a negative errno + */ +int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev) +{ + int ret; + + ret = auxiliary_device_add(adev); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, drm_aux_hpd_bridge_del_adev, adev); +} +EXPORT_SYMBOL_GPL(devm_drm_dp_hpd_bridge_add); + +/** + * drm_dp_hpd_bridge_register - allocate and register a HDP DisplayPort bridge + * @parent: device instance providing this bridge + * @np: device node pointer corresponding to this bridge instance + * + * Return: device instance that will handle created bridge or an error pointer + */ +struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np) +{ + struct auxiliary_device *adev; + int ret; + + adev = devm_drm_dp_hpd_bridge_alloc(parent, np); + if (IS_ERR(adev)) + return ERR_CAST(adev); + + ret = devm_drm_dp_hpd_bridge_add(parent, adev); if (ret) return ERR_PTR(ret); diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index c4222b886db7..5ebdd6f8f36e 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -332,6 +332,7 @@ alloc_range_bias(struct drm_buddy *mm, u64 start, u64 end, unsigned int order) { + u64 req_size = mm->chunk_size << order; struct drm_buddy_block *block; struct drm_buddy_block *buddy; LIST_HEAD(dfs); @@ -367,6 +368,15 @@ alloc_range_bias(struct drm_buddy *mm, if (drm_buddy_block_is_allocated(block)) continue; + if (block_start < start || block_end > end) { + u64 adjusted_start = max(block_start, start); + u64 adjusted_end = min(block_end, end); + + if (round_down(adjusted_end + 1, req_size) <= + round_up(adjusted_start, req_size)) + continue; + } + if (contains(start, end, block_start, block_end) && order == drm_buddy_block_order(block)) { /* @@ -761,8 +771,12 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm, return -EINVAL; /* Actual range allocation */ - if (start + size == end) + if (start + size == end) { + if (!IS_ALIGNED(start | end, min_block_size)) + return -EINVAL; + return __drm_buddy_alloc_range(mm, start, size, NULL, blocks); + } original_size = size; original_min_size = min_block_size; diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index d37d599aec27..4c72124ffb5d 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -329,10 +329,26 @@ static const struct component_ops dp_display_comp_ops = { .unbind = dp_display_unbind, }; +static void dp_display_send_hpd_event(struct msm_dp *dp_display) +{ + struct dp_display_private *dp; + struct drm_connector *connector; + + dp = container_of(dp_display, struct dp_display_private, dp_display); + + connector = dp->dp_display.connector; + drm_helper_hpd_irq_event(connector->dev); +} + static int dp_display_send_hpd_notification(struct dp_display_private *dp, bool hpd) { - struct drm_bridge *bridge = dp->dp_display.bridge; + if ((hpd && dp->dp_display.link_ready) || + (!hpd && !dp->dp_display.link_ready)) { + drm_dbg_dp(dp->drm_dev, "HPD already %s\n", + (hpd ? "on" : "off")); + return 0; + } /* reset video pattern flag on disconnect */ if (!hpd) { @@ -348,7 +364,7 @@ static int dp_display_send_hpd_notification(struct dp_display_private *dp, drm_dbg_dp(dp->drm_dev, "type=%d hpd=%d\n", dp->dp_display.connector_type, hpd); - drm_bridge_hpd_notify(bridge, dp->dp_display.link_ready); + dp_display_send_hpd_event(&dp->dp_display); return 0; } diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index cd14f993bdd1..80f74ee0fc78 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -269,7 +269,7 @@ nouveau_abi16_ioctl_getparam(ABI16_IOCTL_ARGS) break; case NOUVEAU_GETPARAM_VRAM_USED: { struct ttm_resource_manager *vram_mgr = ttm_manager_type(&drm->ttm.bdev, TTM_PL_VRAM); - getparam->value = (u64)ttm_resource_manager_usage(vram_mgr) << PAGE_SHIFT; + getparam->value = (u64)ttm_resource_manager_usage(vram_mgr); break; } default: diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index a64c81385682..a73a5b589790 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -1054,8 +1054,6 @@ r535_gsp_postinit(struct nvkm_gsp *gsp) /* Release the DMA buffers that were needed only for boot and init */ nvkm_gsp_mem_dtor(gsp, &gsp->boot.fw); nvkm_gsp_mem_dtor(gsp, &gsp->libos); - nvkm_gsp_mem_dtor(gsp, &gsp->rmargs); - nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta); return ret; } @@ -2163,6 +2161,8 @@ r535_gsp_dtor(struct nvkm_gsp *gsp) r535_gsp_dtor_fws(gsp); + nvkm_gsp_mem_dtor(gsp, &gsp->rmargs); + nvkm_gsp_mem_dtor(gsp, &gsp->wpr_meta); nvkm_gsp_mem_dtor(gsp, &gsp->shm.mem); nvkm_gsp_mem_dtor(gsp, &gsp->loginit); nvkm_gsp_mem_dtor(gsp, &gsp->logintr); diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index a73cff7a3070..03d1c76aec2d 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1243,9 +1243,26 @@ static int host1x_drm_probe(struct host1x_device *dev) drm_mode_config_reset(drm); - err = drm_aperture_remove_framebuffers(&tegra_drm_driver); - if (err < 0) - goto hub; + /* + * Only take over from a potential firmware framebuffer if any CRTCs + * have been registered. This must not be a fatal error because there + * are other accelerators that are exposed via this driver. + * + * Another case where this happens is on Tegra234 where the display + * hardware is no longer part of the host1x complex, so this driver + * will not expose any modesetting features. + */ + if (drm->mode_config.num_crtc > 0) { + err = drm_aperture_remove_framebuffers(&tegra_drm_driver); + if (err < 0) + goto hub; + } else { + /* + * Indicate to userspace that this doesn't expose any display + * capabilities. + */ + drm->driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); + } err = drm_dev_register(drm, 0); if (err < 0) diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index 2f32fb2f12e7..be2d9d7764be 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -14,11 +14,216 @@ #include "../lib/drm_random.h" +static unsigned int random_seed; + static inline u64 get_size(int order, u64 chunk_size) { return (1 << order) * chunk_size; } +static void drm_test_buddy_alloc_range_bias(struct kunit *test) +{ + u32 mm_size, ps, bias_size, bias_start, bias_end, bias_rem; + DRM_RND_STATE(prng, random_seed); + unsigned int i, count, *order; + struct drm_buddy mm; + LIST_HEAD(allocated); + + bias_size = SZ_1M; + ps = roundup_pow_of_two(prandom_u32_state(&prng) % bias_size); + ps = max(SZ_4K, ps); + mm_size = (SZ_8M-1) & ~(ps-1); /* Multiple roots */ + + kunit_info(test, "mm_size=%u, ps=%u\n", mm_size, ps); + + KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps), + "buddy_init failed\n"); + + count = mm_size / bias_size; + order = drm_random_order(count, &prng); + KUNIT_EXPECT_TRUE(test, order); + + /* + * Idea is to split the address space into uniform bias ranges, and then + * in some random order allocate within each bias, using various + * patterns within. This should detect if allocations leak out from a + * given bias, for example. + */ + + for (i = 0; i < count; i++) { + LIST_HEAD(tmp); + u32 size; + + bias_start = order[i] * bias_size; + bias_end = bias_start + bias_size; + bias_rem = bias_size; + + /* internal round_up too big */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_size + ps, bias_size, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_size, bias_size); + + /* size too big */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_size + ps, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_size + ps, ps); + + /* bias range too small for size */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start + ps, + bias_end, bias_size, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start + ps, bias_end, bias_size, ps); + + /* bias misaligned */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start + ps, + bias_end - ps, + bias_size >> 1, bias_size >> 1, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc h didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start + ps, bias_end - ps, bias_size >> 1, bias_size >> 1); + + /* single big page */ + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_size, bias_size, + &tmp, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc i failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_size, bias_size); + drm_buddy_free_list(&mm, &tmp); + + /* single page with internal round_up */ + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, ps, bias_size, + &tmp, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, ps, bias_size); + drm_buddy_free_list(&mm, &tmp); + + /* random size within */ + size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps); + if (size) + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, size, ps, + &tmp, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, size, ps); + + bias_rem -= size; + /* too big for current avail */ + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, bias_rem + ps, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, bias_rem + ps, ps); + + if (bias_rem) { + /* random fill of the remainder */ + size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps); + size = max(size, ps); + + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, size, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, size, ps); + /* + * Intentionally allow some space to be left + * unallocated, and ideally not always on the bias + * boundaries. + */ + drm_buddy_free_list(&mm, &tmp); + } else { + list_splice_tail(&tmp, &allocated); + } + } + + kfree(order); + drm_buddy_free_list(&mm, &allocated); + drm_buddy_fini(&mm); + + /* + * Something more free-form. Idea is to pick a random starting bias + * range within the address space and then start filling it up. Also + * randomly grow the bias range in both directions as we go along. This + * should give us bias start/end which is not always uniform like above, + * and in some cases will require the allocator to jump over already + * allocated nodes in the middle of the address space. + */ + + KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps), + "buddy_init failed\n"); + + bias_start = round_up(prandom_u32_state(&prng) % (mm_size - ps), ps); + bias_end = round_up(bias_start + prandom_u32_state(&prng) % (mm_size - bias_start), ps); + bias_end = max(bias_end, bias_start + ps); + bias_rem = bias_end - bias_start; + + do { + u32 size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps); + + KUNIT_ASSERT_FALSE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, + bias_end, size, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n", + bias_start, bias_end, size); + bias_rem -= size; + + /* + * Try to randomly grow the bias range in both directions, or + * only one, or perhaps don't grow at all. + */ + do { + u32 old_bias_start = bias_start; + u32 old_bias_end = bias_end; + + if (bias_start) + bias_start -= round_up(prandom_u32_state(&prng) % bias_start, ps); + if (bias_end != mm_size) + bias_end += round_up(prandom_u32_state(&prng) % (mm_size - bias_end), ps); + + bias_rem += old_bias_start - bias_start; + bias_rem += bias_end - old_bias_end; + } while (!bias_rem && (bias_start || bias_end != mm_size)); + } while (bias_rem); + + KUNIT_ASSERT_EQ(test, bias_start, 0); + KUNIT_ASSERT_EQ(test, bias_end, mm_size); + KUNIT_ASSERT_TRUE_MSG(test, + drm_buddy_alloc_blocks(&mm, bias_start, bias_end, + ps, ps, + &allocated, + DRM_BUDDY_RANGE_ALLOCATION), + "buddy_alloc passed with bias(%x-%x), size=%u\n", + bias_start, bias_end, ps); + + drm_buddy_free_list(&mm, &allocated); + drm_buddy_fini(&mm); +} + static void drm_test_buddy_alloc_contiguous(struct kunit *test) { const unsigned long ps = SZ_4K, mm_size = 16 * 3 * SZ_4K; @@ -362,17 +567,30 @@ static void drm_test_buddy_alloc_limit(struct kunit *test) drm_buddy_fini(&mm); } +static int drm_buddy_suite_init(struct kunit_suite *suite) +{ + while (!random_seed) + random_seed = get_random_u32(); + + kunit_info(suite, "Testing DRM buddy manager, with random_seed=0x%x\n", + random_seed); + + return 0; +} + static struct kunit_case drm_buddy_tests[] = { KUNIT_CASE(drm_test_buddy_alloc_limit), KUNIT_CASE(drm_test_buddy_alloc_optimistic), KUNIT_CASE(drm_test_buddy_alloc_pessimistic), KUNIT_CASE(drm_test_buddy_alloc_pathological), KUNIT_CASE(drm_test_buddy_alloc_contiguous), + KUNIT_CASE(drm_test_buddy_alloc_range_bias), {} }; static struct kunit_suite drm_buddy_test_suite = { .name = "drm_buddy", + .suite_init = drm_buddy_suite_init, .test_cases = drm_buddy_tests, }; diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 0b0e262e2166..4d3b80ec906d 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -28,6 +28,14 @@ #include "xe_ttm_stolen_mgr.h" #include "xe_vm.h" +const char *const xe_mem_type_to_name[TTM_NUM_MEM_TYPES] = { + [XE_PL_SYSTEM] = "system", + [XE_PL_TT] = "gtt", + [XE_PL_VRAM0] = "vram0", + [XE_PL_VRAM1] = "vram1", + [XE_PL_STOLEN] = "stolen" +}; + static const struct ttm_place sys_placement_flags = { .fpfn = 0, .lpfn = 0, @@ -713,8 +721,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, migrate = xe->tiles[0].migrate; xe_assert(xe, migrate); - - trace_xe_bo_move(bo); + trace_xe_bo_move(bo, new_mem->mem_type, old_mem_type, move_lacks_source); xe_device_mem_access_get(xe); if (xe_bo_is_pinned(bo) && !xe_bo_is_user(bo)) { diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 9b1279aca127..8be42ac6cd07 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -243,6 +243,7 @@ int xe_bo_evict_pinned(struct xe_bo *bo); int xe_bo_restore_pinned(struct xe_bo *bo); extern struct ttm_device_funcs xe_ttm_funcs; +extern const char *const xe_mem_type_to_name[]; int xe_gem_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file); diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 82d1305e831f..6040e4d22b28 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -131,14 +131,6 @@ static void bo_meminfo(struct xe_bo *bo, static void show_meminfo(struct drm_printer *p, struct drm_file *file) { - static const char *const mem_type_to_name[TTM_NUM_MEM_TYPES] = { - [XE_PL_SYSTEM] = "system", - [XE_PL_TT] = "gtt", - [XE_PL_VRAM0] = "vram0", - [XE_PL_VRAM1] = "vram1", - [4 ... 6] = NULL, - [XE_PL_STOLEN] = "stolen" - }; struct drm_memory_stats stats[TTM_NUM_MEM_TYPES] = {}; struct xe_file *xef = file->driver_priv; struct ttm_device *bdev = &xef->xe->ttm; @@ -171,7 +163,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) spin_unlock(&client->bos_lock); for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) { - if (!mem_type_to_name[mem_type]) + if (!xe_mem_type_to_name[mem_type]) continue; man = ttm_manager_type(bdev, mem_type); @@ -182,7 +174,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file) DRM_GEM_OBJECT_RESIDENT | (mem_type != XE_PL_SYSTEM ? 0 : DRM_GEM_OBJECT_PURGEABLE), - mem_type_to_name[mem_type]); + xe_mem_type_to_name[mem_type]); } } } diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c index 3acfd4f07666..49223026c89f 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue.c +++ b/drivers/gpu/drm/xe/xe_exec_queue.c @@ -309,85 +309,6 @@ static int exec_queue_set_timeslice(struct xe_device *xe, struct xe_exec_queue * return q->ops->set_timeslice(q, value); } -static int exec_queue_set_preemption_timeout(struct xe_device *xe, - struct xe_exec_queue *q, u64 value, - bool create) -{ - u32 min = 0, max = 0; - - xe_exec_queue_get_prop_minmax(q->hwe->eclass, - XE_EXEC_QUEUE_PREEMPT_TIMEOUT, &min, &max); - - if (xe_exec_queue_enforce_schedule_limit() && - !xe_hw_engine_timeout_in_range(value, min, max)) - return -EINVAL; - - return q->ops->set_preempt_timeout(q, value); -} - -static int exec_queue_set_job_timeout(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - u32 min = 0, max = 0; - - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - xe_exec_queue_get_prop_minmax(q->hwe->eclass, - XE_EXEC_QUEUE_JOB_TIMEOUT, &min, &max); - - if (xe_exec_queue_enforce_schedule_limit() && - !xe_hw_engine_timeout_in_range(value, min, max)) - return -EINVAL; - - return q->ops->set_job_timeout(q, value); -} - -static int exec_queue_set_acc_trigger(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - q->usm.acc_trigger = value; - - return 0; -} - -static int exec_queue_set_acc_notify(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - q->usm.acc_notify = value; - - return 0; -} - -static int exec_queue_set_acc_granularity(struct xe_device *xe, struct xe_exec_queue *q, - u64 value, bool create) -{ - if (XE_IOCTL_DBG(xe, !create)) - return -EINVAL; - - if (XE_IOCTL_DBG(xe, !xe->info.has_usm)) - return -EINVAL; - - if (value > DRM_XE_ACC_GRANULARITY_64M) - return -EINVAL; - - q->usm.acc_granularity = value; - - return 0; -} - typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe, struct xe_exec_queue *q, u64 value, bool create); @@ -395,11 +316,6 @@ typedef int (*xe_exec_queue_set_property_fn)(struct xe_device *xe, static const xe_exec_queue_set_property_fn exec_queue_set_property_funcs[] = { [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY] = exec_queue_set_priority, [DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE] = exec_queue_set_timeslice, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT] = exec_queue_set_preemption_timeout, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT] = exec_queue_set_job_timeout, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER] = exec_queue_set_acc_trigger, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY] = exec_queue_set_acc_notify, - [DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY] = exec_queue_set_acc_granularity, }; static int exec_queue_user_ext_set_property(struct xe_device *xe, @@ -418,7 +334,9 @@ static int exec_queue_user_ext_set_property(struct xe_device *xe, if (XE_IOCTL_DBG(xe, ext.property >= ARRAY_SIZE(exec_queue_set_property_funcs)) || - XE_IOCTL_DBG(xe, ext.pad)) + XE_IOCTL_DBG(xe, ext.pad) || + XE_IOCTL_DBG(xe, ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY && + ext.property != DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE)) return -EINVAL; idx = array_index_nospec(ext.property, ARRAY_SIZE(exec_queue_set_property_funcs)); diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h index 947bbc4b285d..36f4901d8d7e 100644 --- a/drivers/gpu/drm/xe/xe_exec_queue_types.h +++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h @@ -150,16 +150,6 @@ struct xe_exec_queue { spinlock_t lock; } compute; - /** @usm: unified shared memory state */ - struct { - /** @acc_trigger: access counter trigger */ - u32 acc_trigger; - /** @acc_notify: access counter notify */ - u32 acc_notify; - /** @acc_granularity: access counter granularity */ - u32 acc_granularity; - } usm; - /** @ops: submission backend exec queue operations */ const struct xe_exec_queue_ops *ops; diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c index 42d01bbbf7d0..acb4d9f38fd7 100644 --- a/drivers/gpu/drm/xe/xe_execlist.c +++ b/drivers/gpu/drm/xe/xe_execlist.c @@ -212,7 +212,7 @@ static void xe_execlist_port_wake_locked(struct xe_execlist_port *port, static void xe_execlist_make_active(struct xe_execlist_exec_queue *exl) { struct xe_execlist_port *port = exl->port; - enum xe_exec_queue_priority priority = exl->active_priority; + enum xe_exec_queue_priority priority = exl->q->sched_props.priority; XE_WARN_ON(priority == XE_EXEC_QUEUE_PRIORITY_UNSET); XE_WARN_ON(priority < 0); diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c index 7eef23a00d77..f4c485289dbe 100644 --- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c +++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c @@ -247,6 +247,14 @@ int xe_gt_tlb_invalidation_vma(struct xe_gt *gt, xe_gt_assert(gt, vma); + /* Execlists not supported */ + if (gt_to_xe(gt)->info.force_execlist) { + if (fence) + __invalidation_fence_signal(fence); + + return 0; + } + action[len++] = XE_GUC_ACTION_TLB_INVALIDATION; action[len++] = 0; /* seqno, replaced in send_tlb_invalidation */ if (!xe->info.has_range_tlb_invalidation) { @@ -317,6 +325,10 @@ int xe_gt_tlb_invalidation_wait(struct xe_gt *gt, int seqno) struct drm_printer p = drm_err_printer(__func__); int ret; + /* Execlists not supported */ + if (gt_to_xe(gt)->info.force_execlist) + return 0; + /* * XXX: See above, this algorithm only works if seqno are always in * order diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c index 0ec5ad2539f1..b38319d2801e 100644 --- a/drivers/gpu/drm/xe/xe_lrc.c +++ b/drivers/gpu/drm/xe/xe_lrc.c @@ -682,8 +682,6 @@ static void xe_lrc_set_ppgtt(struct xe_lrc *lrc, struct xe_vm *vm) #define PVC_CTX_ASID (0x2e + 1) #define PVC_CTX_ACC_CTR_THOLD (0x2a + 1) -#define ACC_GRANULARITY_S 20 -#define ACC_NOTIFY_S 16 int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, struct xe_exec_queue *q, struct xe_vm *vm, u32 ring_size) @@ -754,13 +752,7 @@ int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe, xe_lrc_write_ctx_reg(lrc, CTX_RING_CTL, RING_CTL_SIZE(lrc->ring.size) | RING_VALID); if (xe->info.has_asid && vm) - xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, - (q->usm.acc_granularity << - ACC_GRANULARITY_S) | vm->usm.asid); - if (xe->info.has_usm && vm) - xe_lrc_write_ctx_reg(lrc, PVC_CTX_ACC_CTR_THOLD, - (q->usm.acc_notify << ACC_NOTIFY_S) | - q->usm.acc_trigger); + xe_lrc_write_ctx_reg(lrc, PVC_CTX_ASID, vm->usm.asid); lrc->desc = LRC_VALID; lrc->desc |= LRC_LEGACY_64B_CONTEXT << LRC_ADDRESSING_MODE_SHIFT; diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c index 5f6b53ea5528..02f7808f28ca 100644 --- a/drivers/gpu/drm/xe/xe_mmio.c +++ b/drivers/gpu/drm/xe/xe_mmio.c @@ -105,7 +105,7 @@ static void xe_resize_vram_bar(struct xe_device *xe) pci_bus_for_each_resource(root, root_res, i) { if (root_res && root_res->flags & (IORESOURCE_MEM | IORESOURCE_MEM_64) && - root_res->start > 0x100000000ull) + (u64)root_res->start > 0x100000000ul) break; } diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index aab92bee1d7c..02c9577fe418 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -19,7 +19,7 @@ #include "xe_macros.h" #include "xe_sched_job_types.h" -struct user_fence { +struct xe_user_fence { struct xe_device *xe; struct kref refcount; struct dma_fence_cb cb; @@ -27,31 +27,32 @@ struct user_fence { struct mm_struct *mm; u64 __user *addr; u64 value; + int signalled; }; static void user_fence_destroy(struct kref *kref) { - struct user_fence *ufence = container_of(kref, struct user_fence, + struct xe_user_fence *ufence = container_of(kref, struct xe_user_fence, refcount); mmdrop(ufence->mm); kfree(ufence); } -static void user_fence_get(struct user_fence *ufence) +static void user_fence_get(struct xe_user_fence *ufence) { kref_get(&ufence->refcount); } -static void user_fence_put(struct user_fence *ufence) +static void user_fence_put(struct xe_user_fence *ufence) { kref_put(&ufence->refcount, user_fence_destroy); } -static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr, - u64 value) +static struct xe_user_fence *user_fence_create(struct xe_device *xe, u64 addr, + u64 value) { - struct user_fence *ufence; + struct xe_user_fence *ufence; ufence = kmalloc(sizeof(*ufence), GFP_KERNEL); if (!ufence) @@ -69,7 +70,7 @@ static struct user_fence *user_fence_create(struct xe_device *xe, u64 addr, static void user_fence_worker(struct work_struct *w) { - struct user_fence *ufence = container_of(w, struct user_fence, worker); + struct xe_user_fence *ufence = container_of(w, struct xe_user_fence, worker); if (mmget_not_zero(ufence->mm)) { kthread_use_mm(ufence->mm); @@ -80,10 +81,11 @@ static void user_fence_worker(struct work_struct *w) } wake_up_all(&ufence->xe->ufence_wq); + WRITE_ONCE(ufence->signalled, 1); user_fence_put(ufence); } -static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence) +static void kick_ufence(struct xe_user_fence *ufence, struct dma_fence *fence) { INIT_WORK(&ufence->worker, user_fence_worker); queue_work(ufence->xe->ordered_wq, &ufence->worker); @@ -92,7 +94,7 @@ static void kick_ufence(struct user_fence *ufence, struct dma_fence *fence) static void user_fence_cb(struct dma_fence *fence, struct dma_fence_cb *cb) { - struct user_fence *ufence = container_of(cb, struct user_fence, cb); + struct xe_user_fence *ufence = container_of(cb, struct xe_user_fence, cb); kick_ufence(ufence, fence); } @@ -340,3 +342,39 @@ err_out: return ERR_PTR(-ENOMEM); } + +/** + * xe_sync_ufence_get() - Get user fence from sync + * @sync: input sync + * + * Get a user fence reference from sync. + * + * Return: xe_user_fence pointer with reference + */ +struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync) +{ + user_fence_get(sync->ufence); + + return sync->ufence; +} + +/** + * xe_sync_ufence_put() - Put user fence reference + * @ufence: user fence reference + * + */ +void xe_sync_ufence_put(struct xe_user_fence *ufence) +{ + user_fence_put(ufence); +} + +/** + * xe_sync_ufence_get_status() - Get user fence status + * @ufence: user fence + * + * Return: 1 if signalled, 0 not signalled, <0 on error + */ +int xe_sync_ufence_get_status(struct xe_user_fence *ufence) +{ + return READ_ONCE(ufence->signalled); +} diff --git a/drivers/gpu/drm/xe/xe_sync.h b/drivers/gpu/drm/xe/xe_sync.h index f43cdcaca6c5..0fd0d51208e6 100644 --- a/drivers/gpu/drm/xe/xe_sync.h +++ b/drivers/gpu/drm/xe/xe_sync.h @@ -38,4 +38,8 @@ static inline bool xe_sync_is_ufence(struct xe_sync_entry *sync) return !!sync->ufence; } +struct xe_user_fence *xe_sync_ufence_get(struct xe_sync_entry *sync); +void xe_sync_ufence_put(struct xe_user_fence *ufence); +int xe_sync_ufence_get_status(struct xe_user_fence *ufence); + #endif diff --git a/drivers/gpu/drm/xe/xe_sync_types.h b/drivers/gpu/drm/xe/xe_sync_types.h index 852db5e7884f..30ac3f51993b 100644 --- a/drivers/gpu/drm/xe/xe_sync_types.h +++ b/drivers/gpu/drm/xe/xe_sync_types.h @@ -18,7 +18,7 @@ struct xe_sync_entry { struct drm_syncobj *syncobj; struct dma_fence *fence; struct dma_fence_chain *chain_fence; - struct user_fence *ufence; + struct xe_user_fence *ufence; u64 addr; u64 timeline_value; u32 type; diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h index 95163c303f3e..4ddc55527f9a 100644 --- a/drivers/gpu/drm/xe/xe_trace.h +++ b/drivers/gpu/drm/xe/xe_trace.h @@ -12,6 +12,7 @@ #include <linux/tracepoint.h> #include <linux/types.h> +#include "xe_bo.h" #include "xe_bo_types.h" #include "xe_exec_queue_types.h" #include "xe_gpu_scheduler_types.h" @@ -26,16 +27,16 @@ DECLARE_EVENT_CLASS(xe_gt_tlb_invalidation_fence, TP_ARGS(fence), TP_STRUCT__entry( - __field(u64, fence) + __field(struct xe_gt_tlb_invalidation_fence *, fence) __field(int, seqno) ), TP_fast_assign( - __entry->fence = (u64)fence; + __entry->fence = fence; __entry->seqno = fence->seqno; ), - TP_printk("fence=0x%016llx, seqno=%d", + TP_printk("fence=%p, seqno=%d", __entry->fence, __entry->seqno) ); @@ -82,16 +83,16 @@ DECLARE_EVENT_CLASS(xe_bo, TP_STRUCT__entry( __field(size_t, size) __field(u32, flags) - __field(u64, vm) + __field(struct xe_vm *, vm) ), TP_fast_assign( __entry->size = bo->size; __entry->flags = bo->flags; - __entry->vm = (unsigned long)bo->vm; + __entry->vm = bo->vm; ), - TP_printk("size=%zu, flags=0x%02x, vm=0x%016llx", + TP_printk("size=%zu, flags=0x%02x, vm=%p", __entry->size, __entry->flags, __entry->vm) ); @@ -100,9 +101,31 @@ DEFINE_EVENT(xe_bo, xe_bo_cpu_fault, TP_ARGS(bo) ); -DEFINE_EVENT(xe_bo, xe_bo_move, - TP_PROTO(struct xe_bo *bo), - TP_ARGS(bo) +TRACE_EVENT(xe_bo_move, + TP_PROTO(struct xe_bo *bo, uint32_t new_placement, uint32_t old_placement, + bool move_lacks_source), + TP_ARGS(bo, new_placement, old_placement, move_lacks_source), + TP_STRUCT__entry( + __field(struct xe_bo *, bo) + __field(size_t, size) + __field(u32, new_placement) + __field(u32, old_placement) + __array(char, device_id, 12) + __field(bool, move_lacks_source) + ), + + TP_fast_assign( + __entry->bo = bo; + __entry->size = bo->size; + __entry->new_placement = new_placement; + __entry->old_placement = old_placement; + strscpy(__entry->device_id, dev_name(xe_bo_device(__entry->bo)->drm.dev), 12); + __entry->move_lacks_source = move_lacks_source; + ), + TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s", + __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size, + xe_mem_type_to_name[__entry->old_placement], + xe_mem_type_to_name[__entry->new_placement], __entry->device_id) ); DECLARE_EVENT_CLASS(xe_exec_queue, @@ -327,16 +350,16 @@ DECLARE_EVENT_CLASS(xe_hw_fence, TP_STRUCT__entry( __field(u64, ctx) __field(u32, seqno) - __field(u64, fence) + __field(struct xe_hw_fence *, fence) ), TP_fast_assign( __entry->ctx = fence->dma.context; __entry->seqno = fence->dma.seqno; - __entry->fence = (unsigned long)fence; + __entry->fence = fence; ), - TP_printk("ctx=0x%016llx, fence=0x%016llx, seqno=%u", + TP_printk("ctx=0x%016llx, fence=%p, seqno=%u", __entry->ctx, __entry->fence, __entry->seqno) ); @@ -365,7 +388,7 @@ DECLARE_EVENT_CLASS(xe_vma, TP_ARGS(vma), TP_STRUCT__entry( - __field(u64, vma) + __field(struct xe_vma *, vma) __field(u32, asid) __field(u64, start) __field(u64, end) @@ -373,14 +396,14 @@ DECLARE_EVENT_CLASS(xe_vma, ), TP_fast_assign( - __entry->vma = (unsigned long)vma; + __entry->vma = vma; __entry->asid = xe_vma_vm(vma)->usm.asid; __entry->start = xe_vma_start(vma); __entry->end = xe_vma_end(vma) - 1; __entry->ptr = xe_vma_userptr(vma); ), - TP_printk("vma=0x%016llx, asid=0x%05x, start=0x%012llx, end=0x%012llx, ptr=0x%012llx,", + TP_printk("vma=%p, asid=0x%05x, start=0x%012llx, end=0x%012llx, userptr=0x%012llx,", __entry->vma, __entry->asid, __entry->start, __entry->end, __entry->ptr) ) @@ -465,16 +488,16 @@ DECLARE_EVENT_CLASS(xe_vm, TP_ARGS(vm), TP_STRUCT__entry( - __field(u64, vm) + __field(struct xe_vm *, vm) __field(u32, asid) ), TP_fast_assign( - __entry->vm = (unsigned long)vm; + __entry->vm = vm; __entry->asid = vm->usm.asid; ), - TP_printk("vm=0x%016llx, asid=0x%05x", __entry->vm, + TP_printk("vm=%p, asid=0x%05x", __entry->vm, __entry->asid) ); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index 921ca28d49dd..3b21afe5b488 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -897,6 +897,11 @@ static void xe_vma_destroy_late(struct xe_vma *vma) struct xe_device *xe = vm->xe; bool read_only = xe_vma_read_only(vma); + if (vma->ufence) { + xe_sync_ufence_put(vma->ufence); + vma->ufence = NULL; + } + if (xe_vma_is_userptr(vma)) { struct xe_userptr *userptr = &to_userptr_vma(vma)->userptr; @@ -1608,6 +1613,16 @@ xe_vm_unbind_vma(struct xe_vma *vma, struct xe_exec_queue *q, trace_xe_vma_unbind(vma); + if (vma->ufence) { + struct xe_user_fence * const f = vma->ufence; + + if (!xe_sync_ufence_get_status(f)) + return ERR_PTR(-EBUSY); + + vma->ufence = NULL; + xe_sync_ufence_put(f); + } + if (number_tiles > 1) { fences = kmalloc_array(number_tiles, sizeof(*fences), GFP_KERNEL); @@ -1741,6 +1756,21 @@ err_fences: return ERR_PTR(err); } +static struct xe_user_fence * +find_ufence_get(struct xe_sync_entry *syncs, u32 num_syncs) +{ + unsigned int i; + + for (i = 0; i < num_syncs; i++) { + struct xe_sync_entry *e = &syncs[i]; + + if (xe_sync_is_ufence(e)) + return xe_sync_ufence_get(e); + } + + return NULL; +} + static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma, struct xe_exec_queue *q, struct xe_sync_entry *syncs, u32 num_syncs, bool immediate, bool first_op, @@ -1748,9 +1778,16 @@ static int __xe_vm_bind(struct xe_vm *vm, struct xe_vma *vma, { struct dma_fence *fence; struct xe_exec_queue *wait_exec_queue = to_wait_exec_queue(vm, q); + struct xe_user_fence *ufence; xe_vm_assert_held(vm); + ufence = find_ufence_get(syncs, num_syncs); + if (vma->ufence && ufence) + xe_sync_ufence_put(vma->ufence); + + vma->ufence = ufence ?: vma->ufence; + if (immediate) { fence = xe_vm_bind_vma(vma, q, syncs, num_syncs, first_op, last_op); @@ -2117,10 +2154,6 @@ vm_bind_ioctl_ops_create(struct xe_vm *vm, struct xe_bo *bo, struct xe_vma_op *op = gpuva_op_to_vma_op(__op); if (__op->op == DRM_GPUVA_OP_MAP) { - op->map.immediate = - flags & DRM_XE_VM_BIND_FLAG_IMMEDIATE; - op->map.read_only = - flags & DRM_XE_VM_BIND_FLAG_READONLY; op->map.is_null = flags & DRM_XE_VM_BIND_FLAG_NULL; op->map.pat_index = pat_index; } else if (__op->op == DRM_GPUVA_OP_PREFETCH) { @@ -2313,8 +2346,6 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q, switch (op->base.op) { case DRM_GPUVA_OP_MAP: { - flags |= op->map.read_only ? - VMA_CREATE_FLAG_READ_ONLY : 0; flags |= op->map.is_null ? VMA_CREATE_FLAG_IS_NULL : 0; @@ -2445,7 +2476,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm, case DRM_GPUVA_OP_MAP: err = xe_vm_bind(vm, vma, op->q, xe_vma_bo(vma), op->syncs, op->num_syncs, - op->map.immediate || !xe_vm_in_fault_mode(vm), + !xe_vm_in_fault_mode(vm), op->flags & XE_VMA_OP_FIRST, op->flags & XE_VMA_OP_LAST); break; @@ -2720,14 +2751,11 @@ static int vm_bind_ioctl_ops_execute(struct xe_vm *vm, return 0; } -#define SUPPORTED_FLAGS \ - (DRM_XE_VM_BIND_FLAG_READONLY | \ - DRM_XE_VM_BIND_FLAG_IMMEDIATE | DRM_XE_VM_BIND_FLAG_NULL) +#define SUPPORTED_FLAGS (DRM_XE_VM_BIND_FLAG_NULL | \ + DRM_XE_VM_BIND_FLAG_DUMPABLE) #define XE_64K_PAGE_MASK 0xffffull #define ALL_DRM_XE_SYNCS_FLAGS (DRM_XE_SYNCS_FLAG_WAIT_FOR_OP) -#define MAX_BINDS 512 /* FIXME: Picking random upper limit */ - static int vm_bind_ioctl_check_args(struct xe_device *xe, struct drm_xe_vm_bind *args, struct drm_xe_vm_bind_op **bind_ops) @@ -2739,16 +2767,16 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, XE_IOCTL_DBG(xe, args->reserved[0] || args->reserved[1])) return -EINVAL; - if (XE_IOCTL_DBG(xe, args->extensions) || - XE_IOCTL_DBG(xe, args->num_binds > MAX_BINDS)) + if (XE_IOCTL_DBG(xe, args->extensions)) return -EINVAL; if (args->num_binds > 1) { u64 __user *bind_user = u64_to_user_ptr(args->vector_of_binds); - *bind_ops = kmalloc(sizeof(struct drm_xe_vm_bind_op) * - args->num_binds, GFP_KERNEL); + *bind_ops = kvmalloc_array(args->num_binds, + sizeof(struct drm_xe_vm_bind_op), + GFP_KERNEL | __GFP_ACCOUNT); if (!*bind_ops) return -ENOMEM; @@ -2838,7 +2866,7 @@ static int vm_bind_ioctl_check_args(struct xe_device *xe, free_bind_ops: if (args->num_binds > 1) - kfree(*bind_ops); + kvfree(*bind_ops); return err; } @@ -2926,13 +2954,15 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) } if (args->num_binds) { - bos = kcalloc(args->num_binds, sizeof(*bos), GFP_KERNEL); + bos = kvcalloc(args->num_binds, sizeof(*bos), + GFP_KERNEL | __GFP_ACCOUNT); if (!bos) { err = -ENOMEM; goto release_vm_lock; } - ops = kcalloc(args->num_binds, sizeof(*ops), GFP_KERNEL); + ops = kvcalloc(args->num_binds, sizeof(*ops), + GFP_KERNEL | __GFP_ACCOUNT); if (!ops) { err = -ENOMEM; goto release_vm_lock; @@ -3073,10 +3103,10 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) for (i = 0; bos && i < args->num_binds; ++i) xe_bo_put(bos[i]); - kfree(bos); - kfree(ops); + kvfree(bos); + kvfree(ops); if (args->num_binds > 1) - kfree(bind_ops); + kvfree(bind_ops); return err; @@ -3100,10 +3130,10 @@ put_exec_queue: if (q) xe_exec_queue_put(q); free_objs: - kfree(bos); - kfree(ops); + kvfree(bos); + kvfree(ops); if (args->num_binds > 1) - kfree(bind_ops); + kvfree(bind_ops); return err; } diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index a603cc2eb56b..7300eea5394b 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -19,6 +19,7 @@ struct xe_bo; struct xe_sync_entry; +struct xe_user_fence; struct xe_vm; #define XE_VMA_READ_ONLY DRM_GPUVA_USERBITS @@ -104,6 +105,12 @@ struct xe_vma { * @pat_index: The pat index to use when encoding the PTEs for this vma. */ u16 pat_index; + + /** + * @ufence: The user fence that was provided with MAP. + * Needs to be signalled before UNMAP can be processed. + */ + struct xe_user_fence *ufence; }; /** @@ -288,10 +295,6 @@ struct xe_vm { struct xe_vma_op_map { /** @vma: VMA to map */ struct xe_vma *vma; - /** @immediate: Immediate bind */ - bool immediate; - /** @read_only: Read only */ - bool read_only; /** @is_null: is NULL binding */ bool is_null; /** @pat_index: The pat index to use for this operation. */ diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 42fd504abbcd..89983d7d73ca 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -169,6 +169,7 @@ static const struct host1x_info host1x06_info = { .num_sid_entries = ARRAY_SIZE(tegra186_sid_table), .sid_table = tegra186_sid_table, .reserve_vblank_syncpts = false, + .skip_reset_assert = true, }; static const struct host1x_sid_entry tegra194_sid_table[] = { @@ -680,13 +681,15 @@ static int __maybe_unused host1x_runtime_suspend(struct device *dev) host1x_intr_stop(host); host1x_syncpt_save(host); - err = reset_control_bulk_assert(host->nresets, host->resets); - if (err) { - dev_err(dev, "failed to assert reset: %d\n", err); - goto resume_host1x; - } + if (!host->info->skip_reset_assert) { + err = reset_control_bulk_assert(host->nresets, host->resets); + if (err) { + dev_err(dev, "failed to assert reset: %d\n", err); + goto resume_host1x; + } - usleep_range(1000, 2000); + usleep_range(1000, 2000); + } clk_disable_unprepare(host->clk); reset_control_bulk_release(host->nresets, host->resets); diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index c8e302de7625..925a118db23f 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -116,6 +116,12 @@ struct host1x_info { * the display driver disables VBLANK increments. */ bool reserve_vblank_syncpts; + /* + * On Tegra186, secure world applications may require access to + * host1x during suspend/resume. To allow this, we need to leave + * host1x not in reset. + */ + bool skip_reset_assert; }; struct host1x { diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 56f7e06c673e..adbf674355b2 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -322,125 +322,89 @@ static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer, pagecount = hv_gpadl_size(type, size) >> HV_HYP_PAGE_SHIFT; - /* do we need a gpadl body msg */ pfnsize = MAX_SIZE_CHANNEL_MESSAGE - sizeof(struct vmbus_channel_gpadl_header) - sizeof(struct gpa_range); + pfncount = umin(pagecount, pfnsize / sizeof(u64)); + + msgsize = sizeof(struct vmbus_channel_msginfo) + + sizeof(struct vmbus_channel_gpadl_header) + + sizeof(struct gpa_range) + pfncount * sizeof(u64); + msgheader = kzalloc(msgsize, GFP_KERNEL); + if (!msgheader) + return -ENOMEM; + + INIT_LIST_HEAD(&msgheader->submsglist); + msgheader->msgsize = msgsize; + + gpadl_header = (struct vmbus_channel_gpadl_header *) + msgheader->msg; + gpadl_header->rangecount = 1; + gpadl_header->range_buflen = sizeof(struct gpa_range) + + pagecount * sizeof(u64); + gpadl_header->range[0].byte_offset = 0; + gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); + for (i = 0; i < pfncount; i++) + gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( + type, kbuffer, size, send_offset, i); + *msginfo = msgheader; + + pfnsum = pfncount; + pfnleft = pagecount - pfncount; + + /* how many pfns can we fit in a body message */ + pfnsize = MAX_SIZE_CHANNEL_MESSAGE - + sizeof(struct vmbus_channel_gpadl_body); pfncount = pfnsize / sizeof(u64); - if (pagecount > pfncount) { - /* we need a gpadl body */ - /* fill in the header */ + /* + * If pfnleft is zero, everything fits in the header and no body + * messages are needed + */ + while (pfnleft) { + pfncurr = umin(pfncount, pfnleft); msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pfncount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (!msgheader) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pfncount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - *msginfo = msgheader; - - pfnsum = pfncount; - pfnleft = pagecount - pfncount; - - /* how many pfns can we fit */ - pfnsize = MAX_SIZE_CHANNEL_MESSAGE - - sizeof(struct vmbus_channel_gpadl_body); - pfncount = pfnsize / sizeof(u64); - - /* fill in the body */ - while (pfnleft) { - if (pfnleft > pfncount) - pfncurr = pfncount; - else - pfncurr = pfnleft; - - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_body) + - pfncurr * sizeof(u64); - msgbody = kzalloc(msgsize, GFP_KERNEL); - - if (!msgbody) { - struct vmbus_channel_msginfo *pos = NULL; - struct vmbus_channel_msginfo *tmp = NULL; - /* - * Free up all the allocated messages. - */ - list_for_each_entry_safe(pos, tmp, - &msgheader->submsglist, - msglistentry) { - - list_del(&pos->msglistentry); - kfree(pos); - } - - goto nomem; - } - - msgbody->msgsize = msgsize; - gpadl_body = - (struct vmbus_channel_gpadl_body *)msgbody->msg; + sizeof(struct vmbus_channel_gpadl_body) + + pfncurr * sizeof(u64); + msgbody = kzalloc(msgsize, GFP_KERNEL); + if (!msgbody) { + struct vmbus_channel_msginfo *pos = NULL; + struct vmbus_channel_msginfo *tmp = NULL; /* - * Gpadl is u32 and we are using a pointer which could - * be 64-bit - * This is governed by the guest/host protocol and - * so the hypervisor guarantees that this is ok. + * Free up all the allocated messages. */ - for (i = 0; i < pfncurr; i++) - gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, - kbuffer, size, send_offset, pfnsum + i); - - /* add to msg header */ - list_add_tail(&msgbody->msglistentry, - &msgheader->submsglist); - pfnsum += pfncurr; - pfnleft -= pfncurr; + list_for_each_entry_safe(pos, tmp, + &msgheader->submsglist, + msglistentry) { + + list_del(&pos->msglistentry); + kfree(pos); + } + kfree(msgheader); + return -ENOMEM; } - } else { - /* everything fits in a header */ - msgsize = sizeof(struct vmbus_channel_msginfo) + - sizeof(struct vmbus_channel_gpadl_header) + - sizeof(struct gpa_range) + pagecount * sizeof(u64); - msgheader = kzalloc(msgsize, GFP_KERNEL); - if (msgheader == NULL) - goto nomem; - - INIT_LIST_HEAD(&msgheader->submsglist); - msgheader->msgsize = msgsize; - - gpadl_header = (struct vmbus_channel_gpadl_header *) - msgheader->msg; - gpadl_header->rangecount = 1; - gpadl_header->range_buflen = sizeof(struct gpa_range) + - pagecount * sizeof(u64); - gpadl_header->range[0].byte_offset = 0; - gpadl_header->range[0].byte_count = hv_gpadl_size(type, size); - for (i = 0; i < pagecount; i++) - gpadl_header->range[0].pfn_array[i] = hv_gpadl_hvpfn( - type, kbuffer, size, send_offset, i); - - *msginfo = msgheader; + + msgbody->msgsize = msgsize; + gpadl_body = (struct vmbus_channel_gpadl_body *)msgbody->msg; + + /* + * Gpadl is u32 and we are using a pointer which could + * be 64-bit + * This is governed by the guest/host protocol and + * so the hypervisor guarantees that this is ok. + */ + for (i = 0; i < pfncurr; i++) + gpadl_body->pfn[i] = hv_gpadl_hvpfn(type, + kbuffer, size, send_offset, pfnsum + i); + + /* add to msg header */ + list_add_tail(&msgbody->msglistentry, &msgheader->submsglist); + pfnsum += pfncurr; + pfnleft -= pfncurr; } return 0; -nomem: - kfree(msgheader); - kfree(msgbody); - return -ENOMEM; } /* diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 42aec2c5606a..9c97c4065fe7 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -296,6 +296,11 @@ static struct { spinlock_t lock; } host_ts; +static bool timesync_implicit; + +module_param(timesync_implicit, bool, 0644); +MODULE_PARM_DESC(timesync_implicit, "If set treat SAMPLE as SYNC when clock is behind"); + static inline u64 reftime_to_ns(u64 reftime) { return (reftime - WLTIMEDELTA) * 100; @@ -345,6 +350,29 @@ static void hv_set_host_time(struct work_struct *work) } /* + * Due to a bug on Hyper-V hosts, the sync flag may not always be sent on resume. + * Force a sync if the guest is behind. + */ +static inline bool hv_implicit_sync(u64 host_time) +{ + struct timespec64 new_ts; + struct timespec64 threshold_ts; + + new_ts = ns_to_timespec64(reftime_to_ns(host_time)); + ktime_get_real_ts64(&threshold_ts); + + threshold_ts.tv_sec += 5; + + /* + * If guest behind the host by 5 or more seconds. + */ + if (timespec64_compare(&new_ts, &threshold_ts) >= 0) + return true; + + return false; +} + +/* * Synchronize time with host after reboot, restore, etc. * * ICTIMESYNCFLAG_SYNC flag bit indicates reboot, restore events of the VM. @@ -384,7 +412,8 @@ static inline void adj_guesttime(u64 hosttime, u64 reftime, u8 adj_flags) spin_unlock_irqrestore(&host_ts.lock, flags); /* Schedule work to do do_settimeofday64() */ - if (adj_flags & ICTIMESYNCFLAG_SYNC) + if ((adj_flags & ICTIMESYNCFLAG_SYNC) || + (timesync_implicit && hv_implicit_sync(host_ts.host_time))) schedule_work(&adj_time_work); } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b33d5abd9beb..7f7965f3d187 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -988,7 +988,7 @@ static const struct dev_pm_ops vmbus_pm = { }; /* The one and only one */ -static struct bus_type hv_bus = { +static const struct bus_type hv_bus = { .name = "vmbus", .match = vmbus_match, .shutdown = vmbus_shutdown, diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 7f91c8d0064b..65814cbc8402 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -117,11 +117,11 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm if (ret) goto out_free_domain; domain->users = 1; - refcount_set(&handle->users, 1); list_add(&domain->next, &mm->iommu_mm->sva_domains); - list_add(&handle->handle_item, &mm->iommu_mm->sva_handles); out: + refcount_set(&handle->users, 1); + list_add(&handle->handle_item, &mm->iommu_mm->sva_handles); mutex_unlock(&iommu_sva_lock); handle->dev = dev; handle->domain = domain; diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 504ac1b01b2d..05fd9d3abf1b 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -1330,20 +1330,23 @@ out_unlock: int iopt_add_access(struct io_pagetable *iopt, struct iommufd_access *access) { + u32 new_id; int rc; down_write(&iopt->domains_rwsem); down_write(&iopt->iova_rwsem); - rc = xa_alloc(&iopt->access_list, &access->iopt_access_list_id, access, - xa_limit_16b, GFP_KERNEL_ACCOUNT); + rc = xa_alloc(&iopt->access_list, &new_id, access, xa_limit_16b, + GFP_KERNEL_ACCOUNT); + if (rc) goto out_unlock; rc = iopt_calculate_iova_alignment(iopt); if (rc) { - xa_erase(&iopt->access_list, access->iopt_access_list_id); + xa_erase(&iopt->access_list, new_id); goto out_unlock; } + access->iopt_access_list_id = new_id; out_unlock: up_write(&iopt->iova_rwsem); diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 8abf9747773e..7a2199470f31 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -36,7 +36,7 @@ static struct mock_bus_type iommufd_mock_bus_type = { }, }; -static atomic_t mock_dev_num; +static DEFINE_IDA(mock_dev_ida); enum { MOCK_DIRTY_TRACK = 1, @@ -63,8 +63,8 @@ enum { * In syzkaller mode the 64 bit IOVA is converted into an nth area and offset * value. This has a much smaller randomization space and syzkaller can hit it. */ -static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt, - u64 *iova) +static unsigned long __iommufd_test_syz_conv_iova(struct io_pagetable *iopt, + u64 *iova) { struct syz_layout { __u32 nth_area; @@ -88,6 +88,21 @@ static unsigned long iommufd_test_syz_conv_iova(struct io_pagetable *iopt, return 0; } +static unsigned long iommufd_test_syz_conv_iova(struct iommufd_access *access, + u64 *iova) +{ + unsigned long ret; + + mutex_lock(&access->ioas_lock); + if (!access->ioas) { + mutex_unlock(&access->ioas_lock); + return 0; + } + ret = __iommufd_test_syz_conv_iova(&access->ioas->iopt, iova); + mutex_unlock(&access->ioas_lock); + return ret; +} + void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd, unsigned int ioas_id, u64 *iova, u32 *flags) { @@ -100,7 +115,7 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd, ioas = iommufd_get_ioas(ucmd->ictx, ioas_id); if (IS_ERR(ioas)) return; - *iova = iommufd_test_syz_conv_iova(&ioas->iopt, iova); + *iova = __iommufd_test_syz_conv_iova(&ioas->iopt, iova); iommufd_put_object(ucmd->ictx, &ioas->obj); } @@ -123,6 +138,7 @@ enum selftest_obj_type { struct mock_dev { struct device dev; unsigned long flags; + int id; }; struct selftest_obj { @@ -430,20 +446,27 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain, /* * iommufd generates unmaps that must be a strict - * superset of the map's performend So every starting - * IOVA should have been an iova passed to map, and the + * superset of the map's performend So every + * starting/ending IOVA should have been an iova passed + * to map. * - * First IOVA must be present and have been a first IOVA - * passed to map_pages + * This simple logic doesn't work when the HUGE_PAGE is + * turned on since the core code will automatically + * switch between the two page sizes creating a break in + * the unmap calls. The break can land in the middle of + * contiguous IOVA. */ - if (first) { - WARN_ON(ent && !(xa_to_value(ent) & - MOCK_PFN_START_IOVA)); - first = false; + if (!(domain->pgsize_bitmap & MOCK_HUGE_PAGE_SIZE)) { + if (first) { + WARN_ON(ent && !(xa_to_value(ent) & + MOCK_PFN_START_IOVA)); + first = false; + } + if (pgcount == 1 && + cur + MOCK_IO_PAGE_SIZE == pgsize) + WARN_ON(ent && !(xa_to_value(ent) & + MOCK_PFN_LAST_IOVA)); } - if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize) - WARN_ON(ent && !(xa_to_value(ent) & - MOCK_PFN_LAST_IOVA)); iova += MOCK_IO_PAGE_SIZE; ret += MOCK_IO_PAGE_SIZE; @@ -631,7 +654,7 @@ static void mock_dev_release(struct device *dev) { struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); - atomic_dec(&mock_dev_num); + ida_free(&mock_dev_ida, mdev->id); kfree(mdev); } @@ -653,8 +676,12 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) mdev->dev.release = mock_dev_release; mdev->dev.bus = &iommufd_mock_bus_type.bus; - rc = dev_set_name(&mdev->dev, "iommufd_mock%u", - atomic_inc_return(&mock_dev_num)); + rc = ida_alloc(&mock_dev_ida, GFP_KERNEL); + if (rc < 0) + goto err_put; + mdev->id = rc; + + rc = dev_set_name(&mdev->dev, "iommufd_mock%u", mdev->id); if (rc) goto err_put; @@ -1156,7 +1183,7 @@ static int iommufd_test_access_pages(struct iommufd_ucmd *ucmd, } if (flags & MOCK_FLAGS_ACCESS_SYZ) - iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt, + iova = iommufd_test_syz_conv_iova(staccess->access, &cmd->access_pages.iova); npages = (ALIGN(iova + length, PAGE_SIZE) - @@ -1258,8 +1285,8 @@ static int iommufd_test_access_rw(struct iommufd_ucmd *ucmd, } if (flags & MOCK_FLAGS_ACCESS_SYZ) - iova = iommufd_test_syz_conv_iova(&staccess->access->ioas->iopt, - &cmd->access_rw.iova); + iova = iommufd_test_syz_conv_iova(staccess->access, + &cmd->access_rw.iova); rc = iommufd_access_rw(staccess->access, iova, tmp, length, flags); if (rc) diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c index 6e80d7bd3c4d..3ed257334562 100644 --- a/drivers/isdn/capi/capi.c +++ b/drivers/isdn/capi/capi.c @@ -49,7 +49,9 @@ MODULE_LICENSE("GPL"); /* -------- driver information -------------------------------------- */ static DEFINE_MUTEX(capi_mutex); -static struct class *capi_class; +static const struct class capi_class = { + .name = "capi", +}; static int capi_major = 68; /* allocated */ module_param_named(major, capi_major, uint, 0); @@ -1393,18 +1395,19 @@ static int __init capi_init(void) kcapi_exit(); return major_ret; } - capi_class = class_create("capi"); - if (IS_ERR(capi_class)) { + + ret = class_register(&capi_class); + if (ret) { unregister_chrdev(capi_major, "capi20"); kcapi_exit(); - return PTR_ERR(capi_class); + return ret; } - device_create(capi_class, NULL, MKDEV(capi_major, 0), NULL, "capi20"); + device_create(&capi_class, NULL, MKDEV(capi_major, 0), NULL, "capi20"); if (capinc_tty_init() < 0) { - device_destroy(capi_class, MKDEV(capi_major, 0)); - class_destroy(capi_class); + device_destroy(&capi_class, MKDEV(capi_major, 0)); + class_unregister(&capi_class); unregister_chrdev(capi_major, "capi20"); kcapi_exit(); return -ENOMEM; @@ -1427,8 +1430,8 @@ static void __exit capi_exit(void) { proc_exit(); - device_destroy(capi_class, MKDEV(capi_major, 0)); - class_destroy(capi_class); + device_destroy(&capi_class, MKDEV(capi_major, 0)); + class_unregister(&capi_class); unregister_chrdev(capi_major, "capi20"); capinc_tty_exit(); diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c index 09b72f14d4b7..b4ed0bb8ddfb 100644 --- a/drivers/isdn/mISDN/dsp_pipeline.c +++ b/drivers/isdn/mISDN/dsp_pipeline.c @@ -31,7 +31,9 @@ struct dsp_element_entry { static LIST_HEAD(dsp_elements); /* sysfs */ -static struct class *elements_class; +static const struct class elements_class = { + .name = "dsp_pipeline", +}; static ssize_t attr_show_args(struct device *dev, struct device_attribute *attr, char *buf) @@ -80,7 +82,7 @@ int mISDN_dsp_element_register(struct mISDN_dsp_element *elem) INIT_LIST_HEAD(&entry->list); entry->elem = elem; - entry->dev.class = elements_class; + entry->dev.class = &elements_class; entry->dev.release = mISDN_dsp_dev_release; dev_set_drvdata(&entry->dev, elem); dev_set_name(&entry->dev, "%s", elem->name); @@ -131,9 +133,11 @@ EXPORT_SYMBOL(mISDN_dsp_element_unregister); int dsp_pipeline_module_init(void) { - elements_class = class_create("dsp_pipeline"); - if (IS_ERR(elements_class)) - return PTR_ERR(elements_class); + int err; + + err = class_register(&elements_class); + if (err) + return err; dsp_hwec_init(); @@ -146,7 +150,7 @@ void dsp_pipeline_module_exit(void) dsp_hwec_exit(); - class_destroy(elements_class); + class_unregister(&elements_class); list_for_each_entry_safe(entry, n, &dsp_elements, list) { list_del(&entry->list); diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index f410bee50132..58ed7193a3ca 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1015,10 +1015,12 @@ static int mmc_select_bus_width(struct mmc_card *card) static unsigned ext_csd_bits[] = { EXT_CSD_BUS_WIDTH_8, EXT_CSD_BUS_WIDTH_4, + EXT_CSD_BUS_WIDTH_1, }; static unsigned bus_widths[] = { MMC_BUS_WIDTH_8, MMC_BUS_WIDTH_4, + MMC_BUS_WIDTH_1, }; struct mmc_host *host = card->host; unsigned idx, bus_width = 0; diff --git a/drivers/mmc/host/mmci_stm32_sdmmc.c b/drivers/mmc/host/mmci_stm32_sdmmc.c index 35067e1e6cd8..f5da7f9baa52 100644 --- a/drivers/mmc/host/mmci_stm32_sdmmc.c +++ b/drivers/mmc/host/mmci_stm32_sdmmc.c @@ -225,6 +225,8 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) struct scatterlist *sg; int i; + host->dma_in_progress = true; + if (!host->variant->dma_lli || data->sg_len == 1 || idma->use_bounce_buffer) { u32 dma_addr; @@ -263,9 +265,30 @@ static int sdmmc_idma_start(struct mmci_host *host, unsigned int *datactrl) return 0; } +static void sdmmc_idma_error(struct mmci_host *host) +{ + struct mmc_data *data = host->data; + struct sdmmc_idma *idma = host->dma_priv; + + if (!dma_inprogress(host)) + return; + + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; + data->host_cookie = 0; + + if (!idma->use_bounce_buffer) + dma_unmap_sg(mmc_dev(host->mmc), data->sg, data->sg_len, + mmc_get_dma_dir(data)); +} + static void sdmmc_idma_finalize(struct mmci_host *host, struct mmc_data *data) { + if (!dma_inprogress(host)) + return; + writel_relaxed(0, host->base + MMCI_STM32_IDMACTRLR); + host->dma_in_progress = false; if (!data->host_cookie) sdmmc_idma_unprep_data(host, data, 0); @@ -676,6 +699,7 @@ static struct mmci_host_ops sdmmc_variant_ops = { .dma_setup = sdmmc_idma_setup, .dma_start = sdmmc_idma_start, .dma_finalize = sdmmc_idma_finalize, + .dma_error = sdmmc_idma_error, .set_clkreg = mmci_sdmmc_set_clkreg, .set_pwrreg = mmci_sdmmc_set_pwrreg, .busy_complete = sdmmc_busy_complete, diff --git a/drivers/mmc/host/sdhci-xenon-phy.c b/drivers/mmc/host/sdhci-xenon-phy.c index 8cf3a375de65..cc9d28b75eb9 100644 --- a/drivers/mmc/host/sdhci-xenon-phy.c +++ b/drivers/mmc/host/sdhci-xenon-phy.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <linux/delay.h> #include <linux/ktime.h> +#include <linux/iopoll.h> #include <linux/of_address.h> #include "sdhci-pltfm.h" @@ -109,6 +110,8 @@ #define XENON_EMMC_PHY_LOGIC_TIMING_ADJUST (XENON_EMMC_PHY_REG_BASE + 0x18) #define XENON_LOGIC_TIMING_VALUE 0x00AA8977 +#define XENON_MAX_PHY_TIMEOUT_LOOPS 100 + /* * List offset of PHY registers and some special register values * in eMMC PHY 5.0 or eMMC PHY 5.1 @@ -216,6 +219,19 @@ static int xenon_alloc_emmc_phy(struct sdhci_host *host) return 0; } +static int xenon_check_stability_internal_clk(struct sdhci_host *host) +{ + u32 reg; + int err; + + err = read_poll_timeout(sdhci_readw, reg, reg & SDHCI_CLOCK_INT_STABLE, + 1100, 20000, false, host, SDHCI_CLOCK_CONTROL); + if (err) + dev_err(mmc_dev(host->mmc), "phy_init: Internal clock never stabilized.\n"); + + return err; +} + /* * eMMC 5.0/5.1 PHY init/re-init. * eMMC PHY init should be executed after: @@ -232,6 +248,11 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host); struct xenon_emmc_phy_regs *phy_regs = priv->emmc_phy_regs; + int ret = xenon_check_stability_internal_clk(host); + + if (ret) + return ret; + reg = sdhci_readl(host, phy_regs->timing_adj); reg |= XENON_PHY_INITIALIZAION; sdhci_writel(host, reg, phy_regs->timing_adj); @@ -259,18 +280,27 @@ static int xenon_emmc_phy_init(struct sdhci_host *host) /* get the wait time */ wait /= clock; wait++; - /* wait for host eMMC PHY init completes */ - udelay(wait); - reg = sdhci_readl(host, phy_regs->timing_adj); - reg &= XENON_PHY_INITIALIZAION; - if (reg) { + /* + * AC5X spec says bit must be polled until zero. + * We see cases in which timeout can take longer + * than the standard calculation on AC5X, which is + * expected following the spec comment above. + * According to the spec, we must wait as long as + * it takes for that bit to toggle on AC5X. + * Cap that with 100 delay loops so we won't get + * stuck here forever: + */ + + ret = read_poll_timeout(sdhci_readl, reg, + !(reg & XENON_PHY_INITIALIZAION), + wait, XENON_MAX_PHY_TIMEOUT_LOOPS * wait, + false, host, phy_regs->timing_adj); + if (ret) dev_err(mmc_dev(host->mmc), "eMMC PHY init cannot complete after %d us\n", - wait); - return -ETIMEDOUT; - } + wait * XENON_MAX_PHY_TIMEOUT_LOOPS); - return 0; + return ret; } #define ARMADA_3700_SOC_PAD_1_8V 0x1 diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ae1a561c4a0f..2c5ed0a7cb18 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1811,7 +1811,7 @@ void bond_xdp_set_features(struct net_device *bond_dev) ASSERT_RTNL(); - if (!bond_xdp_check(bond)) { + if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) { xdp_clear_features_flag(bond_dev); return; } diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 50351cef6ca5..14923535ca7e 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -49,9 +49,9 @@ static int ksz8_ind_write8(struct ksz_device *dev, u8 table, u16 addr, u8 data) mutex_lock(&dev->alu_mutex); ctrl_addr = IND_ACC_TABLE(table) | addr; - ret = ksz_write8(dev, regs[REG_IND_BYTE], data); + ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); if (!ret) - ret = ksz_write16(dev, regs[REG_IND_CTRL_0], ctrl_addr); + ret = ksz_write8(dev, regs[REG_IND_BYTE], data); mutex_unlock(&dev->alu_mutex); diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c index 4d677f836807..5a27d047a38e 100644 --- a/drivers/net/dsa/mv88e6xxx/pcs-6185.c +++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c @@ -95,7 +95,7 @@ static void mv88e6185_pcs_get_state(struct phylink_pcs *pcs, } } -static int mv88e6185_pcs_config(struct phylink_pcs *pcs, unsigned int mode, +static int mv88e6185_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, const unsigned long *advertising, bool permit_pause_to_mac) @@ -137,6 +137,7 @@ static int mv88e6185_pcs_init(struct mv88e6xxx_chip *chip, int port) mpcs->chip = chip; mpcs->port = port; mpcs->phylink_pcs.ops = &mv88e6185_phylink_pcs_ops; + mpcs->phylink_pcs.neg_mode = true; irq = mv88e6xxx_serdes_irq_mapping(chip, port); if (irq) { diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c index a3c79848a69a..2babea110991 100644 --- a/drivers/net/ethernet/amd/pds_core/auxbus.c +++ b/drivers/net/ethernet/amd/pds_core/auxbus.c @@ -160,23 +160,19 @@ static struct pds_auxiliary_dev *pdsc_auxbus_dev_register(struct pdsc *cf, if (err < 0) { dev_warn(cf->dev, "auxiliary_device_init of %s failed: %pe\n", name, ERR_PTR(err)); - goto err_out; + kfree(padev); + return ERR_PTR(err); } err = auxiliary_device_add(aux_dev); if (err) { dev_warn(cf->dev, "auxiliary_device_add of %s failed: %pe\n", name, ERR_PTR(err)); - goto err_out_uninit; + auxiliary_device_uninit(aux_dev); + return ERR_PTR(err); } return padev; - -err_out_uninit: - auxiliary_device_uninit(aux_dev); -err_out: - kfree(padev); - return ERR_PTR(err); } int pdsc_auxbus_dev_del(struct pdsc *cf, struct pdsc *pf) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a15e6d31fc22..493b724848c8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -14523,6 +14523,70 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_bridge_setlink = bnxt_bridge_setlink, }; +static void bnxt_get_queue_stats_rx(struct net_device *dev, int i, + struct netdev_queue_stats_rx *stats) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_cp_ring_info *cpr; + u64 *sw; + + cpr = &bp->bnapi[i]->cp_ring; + sw = cpr->stats.sw_stats; + + stats->packets = 0; + stats->packets += BNXT_GET_RING_STATS64(sw, rx_ucast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, rx_mcast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, rx_bcast_pkts); + + stats->bytes = 0; + stats->bytes += BNXT_GET_RING_STATS64(sw, rx_ucast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, rx_mcast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, rx_bcast_bytes); + + stats->alloc_fail = cpr->sw_stats.rx.rx_oom_discards; +} + +static void bnxt_get_queue_stats_tx(struct net_device *dev, int i, + struct netdev_queue_stats_tx *stats) +{ + struct bnxt *bp = netdev_priv(dev); + struct bnxt_napi *bnapi; + u64 *sw; + + bnapi = bp->tx_ring[bp->tx_ring_map[i]].bnapi; + sw = bnapi->cp_ring.stats.sw_stats; + + stats->packets = 0; + stats->packets += BNXT_GET_RING_STATS64(sw, tx_ucast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, tx_mcast_pkts); + stats->packets += BNXT_GET_RING_STATS64(sw, tx_bcast_pkts); + + stats->bytes = 0; + stats->bytes += BNXT_GET_RING_STATS64(sw, tx_ucast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, tx_mcast_bytes); + stats->bytes += BNXT_GET_RING_STATS64(sw, tx_bcast_bytes); +} + +static void bnxt_get_base_stats(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx) +{ + struct bnxt *bp = netdev_priv(dev); + + rx->packets = bp->net_stats_prev.rx_packets; + rx->bytes = bp->net_stats_prev.rx_bytes; + rx->alloc_fail = bp->ring_err_stats_prev.rx_total_oom_discards; + + tx->packets = bp->net_stats_prev.tx_packets; + tx->bytes = bp->net_stats_prev.tx_bytes; +} + +static const struct netdev_stat_ops bnxt_stat_ops = { + .get_queue_stats_rx = bnxt_get_queue_stats_rx, + .get_queue_stats_tx = bnxt_get_queue_stats_tx, + .get_base_stats = bnxt_get_base_stats, +}; + static void bnxt_remove_one(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); @@ -14970,6 +15034,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto init_err_free; dev->netdev_ops = &bnxt_netdev_ops; + dev->stat_ops = &bnxt_stat_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; pci_set_drvdata(pdev, dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index b5ff2e1a9975..49d5808b7d11 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -804,20 +804,6 @@ static inline unsigned int calc_tx_flits(const struct sk_buff *skb, } /** - * calc_tx_descs - calculate the number of Tx descriptors for a packet - * @skb: the packet - * @chip_ver: chip version - * - * Returns the number of Tx descriptors needed for the given Ethernet - * packet, including the needed WR and CPL headers. - */ -static inline unsigned int calc_tx_descs(const struct sk_buff *skb, - unsigned int chip_ver) -{ - return flits_to_desc(calc_tx_flits(skb, chip_ver)); -} - -/** * cxgb4_write_sgl - populate a scatter/gather list for a packet * @skb: the packet * @q: the Tx queue we are writing into diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index a2788fd5f8bb..19e450a5bd31 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2559,7 +2559,7 @@ void e1000_copy_rx_addrs_to_phy_ich8lan(struct e1000_hw *hw) hw->phy.ops.write_reg_page(hw, BM_RAR_H(i), (u16)(mac_reg & 0xFFFF)); hw->phy.ops.write_reg_page(hw, BM_RAR_CTRL(i), - FIELD_GET(E1000_RAH_AV, mac_reg)); + (u16)((mac_reg & E1000_RAH_AV) >> 16)); } e1000_disable_phy_wakeup_reg_access_bm(hw, &phy_reg); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 3fada49b8ae2..f86578857e8a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -13523,9 +13523,9 @@ int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) return err; i40e_queue_pair_disable_irq(vsi, queue_pair); + i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); - i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); i40e_queue_pair_clean_rings(vsi, queue_pair); i40e_queue_pair_reset_stats(vsi, queue_pair); diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index af4269330581..ce1f11b8ad65 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -567,8 +567,7 @@ static inline bool i40e_is_fw_ver_lt(struct i40e_hw *hw, u16 maj, u16 min) **/ static inline bool i40e_is_fw_ver_eq(struct i40e_hw *hw, u16 maj, u16 min) { - return (hw->aq.fw_maj_ver > maj || - (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min)); + return (hw->aq.fw_maj_ver == maj && hw->aq.fw_min_ver == min); } #endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index cca0e753f38f..7cee365cc7d1 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -2,6 +2,7 @@ /* Copyright (C) 2018-2020, Intel Corporation. */ #include "ice.h" +#include <net/rps.h> /** * ice_is_arfs_active - helper to check is aRFS is active diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 2bceee6d30f3..e92be6f130a3 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -1599,7 +1599,7 @@ static void ice_dpll_deinit_rclk_pin(struct ice_pf *pf) } if (WARN_ON_ONCE(!vsi || !vsi->netdev)) return; - netdev_dpll_pin_clear(vsi->netdev); + dpll_netdev_pin_clear(vsi->netdev); dpll_pin_put(rclk->pin); } @@ -1643,7 +1643,7 @@ ice_dpll_init_rclk_pins(struct ice_pf *pf, struct ice_dpll_pin *pin, } if (WARN_ON((!vsi || !vsi->netdev))) return -EINVAL; - netdev_dpll_pin_set(vsi->netdev, pf->dplls.rclk.pin); + dpll_netdev_pin_set(vsi->netdev, pf->dplls.rclk.pin); return 0; @@ -2122,6 +2122,7 @@ void ice_dpll_init(struct ice_pf *pf) struct ice_dplls *d = &pf->dplls; int err = 0; + mutex_init(&d->lock); err = ice_dpll_init_info(pf, cgu); if (err) goto err_exit; @@ -2134,7 +2135,6 @@ void ice_dpll_init(struct ice_pf *pf) err = ice_dpll_init_pins(pf, cgu); if (err) goto deinit_pps; - mutex_init(&d->lock); if (cgu) { err = ice_dpll_init_worker(pf); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 48e4c33a3550..71f061667980 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3008,7 +3008,7 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi) } } - tx_ring_stats = vsi_stat->rx_ring_stats; + tx_ring_stats = vsi_stat->tx_ring_stats; vsi_stat->tx_ring_stats = krealloc_array(vsi_stat->tx_ring_stats, req_txq, sizeof(*vsi_stat->tx_ring_stats), diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 062b4ea8e2c3..5d7660bc8846 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7998,6 +7998,8 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, pf_sw = pf->first_sw; /* find the attribute in the netlink message */ br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; nla_for_each_nested(attr, br_spec, rem) { __u16 mode; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index a2f8dbe3cb82..a958fcf3e6be 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1067,6 +1067,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) struct ice_pf *pf = pci_get_drvdata(pdev); u16 prev_msix, prev_queues, queues; bool needs_rebuild = false; + struct ice_vsi *vsi; struct ice_vf *vf; int id; @@ -1101,6 +1102,10 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (!vf) return -ENOENT; + vsi = ice_get_vf_vsi(vf); + if (!vsi) + return -ENOENT; + prev_msix = vf->num_msix; prev_queues = vf->num_vf_qs; @@ -1121,7 +1126,7 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) if (vf->first_vector_idx < 0) goto unroll; - if (ice_vf_reconfig_vsi(vf)) { + if (ice_vf_reconfig_vsi(vf) || ice_vf_init_host_cfg(vf, vsi)) { /* Try to rebuild with previous values */ needs_rebuild = true; goto unroll; @@ -1147,8 +1152,10 @@ unroll: if (vf->first_vector_idx < 0) return -EINVAL; - if (needs_rebuild) + if (needs_rebuild) { ice_vf_reconfig_vsi(vf); + ice_vf_init_host_cfg(vf, vsi); + } ice_ena_vf_mappings(vf); ice_put_vf(vf); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 6b88b9bfb51e..1ff9818b4c84 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -440,7 +440,6 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vf->driver_caps = *(u32 *)msg; else vf->driver_caps = VIRTCHNL_VF_OFFLOAD_L2 | - VIRTCHNL_VF_OFFLOAD_RSS_REG | VIRTCHNL_VF_OFFLOAD_VLAN; vfres->vf_cap_flags = VIRTCHNL_VF_OFFLOAD_L2; @@ -453,14 +452,8 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vf_cap_flags |= ice_vc_get_vlan_caps(hw, vf, vsi, vf->driver_caps); - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_PF) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_PF; - } else { - if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RSS_AQ) - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_AQ; - else - vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RSS_REG; - } if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index 5e19d48a05b4..d796dbd2a440 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -13,8 +13,6 @@ * - opcodes needed by VF when caps are activated * * Caps that don't use new opcodes (no opcodes should be allowed): - * - VIRTCHNL_VF_OFFLOAD_RSS_AQ - * - VIRTCHNL_VF_OFFLOAD_RSS_REG * - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR * - VIRTCHNL_VF_OFFLOAD_CRC * - VIRTCHNL_VF_OFFLOAD_RX_POLLING diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 8a051420fa19..1857220d27fe 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -179,6 +179,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) return -EBUSY; usleep_range(1000, 2000); } + + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + ice_qvec_toggle_napi(vsi, q_vector, false); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); ice_fill_txq_meta(vsi, tx_ring, &txq_meta); @@ -195,13 +199,10 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } - ice_qvec_dis_irq(vsi, rx_ring, q_vector); - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; - ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); @@ -245,11 +246,11 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx) if (err) return err; - clear_bit(ICE_CFG_BUSY, vsi->state); ice_qvec_toggle_napi(vsi, q_vector, true); ice_qvec_ena_irq(vsi, q_vector); netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + clear_bit(ICE_CFG_BUSY, vsi->state); return 0; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index a602ff8d74e0..a5f9b7a5effe 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -1978,8 +1978,10 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport) set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags); /* schedule the napi to receive all the marker packets */ + local_bh_disable(); for (i = 0; i < vport->num_q_vectors; i++) napi_schedule(&vport->q_vectors[i].napi); + local_bh_enable(); return idpf_wait_for_marker_event(vport); } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 34820f6a78b9..14924dd8a4b9 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6488,7 +6488,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, int cpu = smp_processor_id(); struct netdev_queue *nq; struct igc_ring *ring; - int i, drops; + int i, nxmit; if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; @@ -6504,16 +6504,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); - drops = 0; + nxmit = 0; for (i = 0; i < num_frames; i++) { int err; struct xdp_frame *xdpf = frames[i]; err = igc_xdp_init_tx_descriptor(ring, xdpf); - if (err) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err) + break; + nxmit++; } if (flags & XDP_XMIT_FLUSH) @@ -6521,7 +6520,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_unlock(nq); - return num_frames - drops; + return nxmit; } static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2e352bfcc401..f985252c8c8d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2969,8 +2969,8 @@ static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, u64 qmask) { - u32 mask; struct ixgbe_hw *hw = &adapter->hw; + u32 mask; switch (hw->mac.type) { case ixgbe_mac_82598EB: @@ -10555,6 +10555,44 @@ static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) } /** + * ixgbe_irq_disable_single - Disable single IRQ vector + * @adapter: adapter structure + * @ring: ring index + **/ +static void ixgbe_irq_disable_single(struct ixgbe_adapter *adapter, u32 ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 qmask = BIT_ULL(ring); + u32 mask; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + mask = qmask & IXGBE_EIMC_RTX_QUEUE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + synchronize_irq(adapter->msix_entries[ring].vector); + else + synchronize_irq(adapter->pdev->irq); +} + +/** * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings * @adapter: adapter structure * @ring: ring index @@ -10570,6 +10608,11 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; + ixgbe_irq_disable_single(adapter, ring); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + ixgbe_disable_txr(adapter, tx_ring); if (xdp_ring) ixgbe_disable_txr(adapter, xdp_ring); @@ -10578,9 +10621,6 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) if (xdp_ring) synchronize_rcu(); - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_disable(&rx_ring->q_vector->napi); - ixgbe_clean_tx_ring(tx_ring); if (xdp_ring) ixgbe_clean_tx_ring(xdp_ring); @@ -10608,9 +10648,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) tx_ring = adapter->tx_ring[ring]; xdp_ring = adapter->xdp_ring[ring]; - /* Rx/Tx/XDP Tx share the same napi context. */ - napi_enable(&rx_ring->q_vector->napi); - ixgbe_configure_tx_ring(adapter, tx_ring); if (xdp_ring) ixgbe_configure_tx_ring(adapter, xdp_ring); @@ -10619,6 +10656,11 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); if (xdp_ring) clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + ixgbe_irq_enable_queues(adapter, BIT_ULL(ring)); + IXGBE_WRITE_FLUSH(&adapter->hw); } /** diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index d5c4f810da61..61ab7f66f053 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -1556,6 +1556,7 @@ struct flow_msg { u32 mpls_lse[4]; u8 icmp_type; u8 icmp_code; + __be16 tcp_flags; }; struct npc_install_flow_req { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index 3e6de9d7dde3..d883157393ea 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -217,6 +217,7 @@ enum key_fields { NPC_MPLS4_TTL, NPC_TYPE_ICMP, NPC_CODE_ICMP, + NPC_TCP_FLAGS, NPC_HEADER_FIELDS_MAX, NPC_CHAN = NPC_HEADER_FIELDS_MAX, /* Valid when Rx */ NPC_PF_FUNC, /* Valid when Tx */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index e6d7914ce61c..2500f5ba4f5a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -2870,6 +2870,10 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s, seq_printf(s, "%d ", ntohs(rule->packet.dport)); seq_printf(s, "mask 0x%x\n", ntohs(rule->mask.dport)); break; + case NPC_TCP_FLAGS: + seq_printf(s, "%d ", rule->packet.tcp_flags); + seq_printf(s, "mask 0x%x\n", rule->mask.tcp_flags); + break; case NPC_IPSEC_SPI: seq_printf(s, "0x%x ", ntohl(rule->packet.spi)); seq_printf(s, "mask 0x%x\n", ntohl(rule->mask.spi)); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index c75669c8fde7..c181e7aa9eb6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -53,6 +53,7 @@ static const char * const npc_flow_names[] = { [NPC_MPLS4_TTL] = "lse depth 4", [NPC_TYPE_ICMP] = "icmp type", [NPC_CODE_ICMP] = "icmp code", + [NPC_TCP_FLAGS] = "tcp flags", [NPC_UNKNOWN] = "unknown", }; @@ -530,6 +531,7 @@ do { \ NPC_SCAN_HDR(NPC_DPORT_SCTP, NPC_LID_LD, NPC_LT_LD_SCTP, 2, 2); NPC_SCAN_HDR(NPC_TYPE_ICMP, NPC_LID_LD, NPC_LT_LD_ICMP, 0, 1); NPC_SCAN_HDR(NPC_CODE_ICMP, NPC_LID_LD, NPC_LT_LD_ICMP, 1, 1); + NPC_SCAN_HDR(NPC_TCP_FLAGS, NPC_LID_LD, NPC_LT_LD_TCP, 12, 2); NPC_SCAN_HDR(NPC_ETYPE_ETHER, NPC_LID_LA, NPC_LT_LA_ETHER, 12, 2); NPC_SCAN_HDR(NPC_ETYPE_TAG1, NPC_LID_LB, NPC_LT_LB_CTAG, 4, 2); NPC_SCAN_HDR(NPC_ETYPE_TAG2, NPC_LID_LB, NPC_LT_LB_STAG_QINQ, 8, 2); @@ -574,7 +576,8 @@ static void npc_set_features(struct rvu *rvu, int blkaddr, u8 intf) BIT_ULL(NPC_DPORT_TCP) | BIT_ULL(NPC_DPORT_UDP) | BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP) | BIT_ULL(NPC_SPORT_SCTP) | BIT_ULL(NPC_DPORT_SCTP) | - BIT_ULL(NPC_TYPE_ICMP) | BIT_ULL(NPC_CODE_ICMP); + BIT_ULL(NPC_TYPE_ICMP) | BIT_ULL(NPC_CODE_ICMP) | + BIT_ULL(NPC_TCP_FLAGS); /* for tcp/udp/sctp corresponding layer type should be in the key */ if (*features & proto_flags) { @@ -982,7 +985,8 @@ do { \ mask->icmp_type, 0); NPC_WRITE_FLOW(NPC_CODE_ICMP, icmp_code, pkt->icmp_code, 0, mask->icmp_code, 0); - + NPC_WRITE_FLOW(NPC_TCP_FLAGS, tcp_flags, ntohs(pkt->tcp_flags), 0, + ntohs(mask->tcp_flags), 0); NPC_WRITE_FLOW(NPC_IPSEC_SPI, spi, ntohl(pkt->spi), 0, ntohl(mask->spi), 0); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index 4fd44b6eecea..87bdb93cb066 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -638,6 +638,7 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, BIT(FLOW_DISSECTOR_KEY_IPSEC) | BIT_ULL(FLOW_DISSECTOR_KEY_MPLS) | BIT_ULL(FLOW_DISSECTOR_KEY_ICMP) | + BIT_ULL(FLOW_DISSECTOR_KEY_TCP) | BIT_ULL(FLOW_DISSECTOR_KEY_IP)))) { netdev_info(nic->netdev, "unsupported flow used key 0x%llx", dissector->used_keys); @@ -857,6 +858,16 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node, } } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp match; + + flow_rule_match_tcp(rule, &match); + + flow_spec->tcp_flags = match.key->flags; + flow_mask->tcp_flags = match.mask->flags; + req->features |= BIT_ULL(NPC_TCP_FLAGS); + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) { struct flow_match_mpls match; u8 bit; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index d7da62cda821..5d3fde63b273 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -42,6 +42,7 @@ #include <net/ip.h> #include <net/vxlan.h> #include <net/devlink.h> +#include <net/rps.h> #include <linux/mlx4/driver.h> #include <linux/mlx4/device.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 3e064234f6fe..98d4306929f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -157,6 +157,12 @@ static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change, return -EOPNOTSUPP; } + if (action == DEVLINK_RELOAD_ACTION_FW_ACTIVATE && + !dev->priv.fw_reset) { + NL_SET_ERR_MSG_MOD(extack, "FW activate is unsupported for this function"); + return -EOPNOTSUPP; + } + if (mlx5_core_is_pf(dev) && pci_num_vf(pdev)) NL_SET_ERR_MSG_MOD(extack, "reload while VFs are present is unfavorable"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c index c9c7fddb246f..904e08de852e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c @@ -285,7 +285,7 @@ static void mlx5_dpll_netdev_dpll_pin_set(struct mlx5_dpll *mdpll, { if (mdpll->tracking_netdev) return; - netdev_dpll_pin_set(netdev, mdpll->dpll_pin); + dpll_netdev_pin_set(netdev, mdpll->dpll_pin); mdpll->tracking_netdev = netdev; } @@ -293,7 +293,7 @@ static void mlx5_dpll_netdev_dpll_pin_clear(struct mlx5_dpll *mdpll) { if (!mdpll->tracking_netdev) return; - netdev_dpll_pin_clear(mdpll->tracking_netdev); + dpll_netdev_pin_clear(mdpll->tracking_netdev); mdpll->tracking_netdev = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index fd4ef6431142..a848a7fda66b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -42,9 +42,9 @@ mlx5e_ptp_port_ts_cqe_list_add(struct mlx5e_ptp_port_ts_cqe_list *list, u8 metad WARN_ON_ONCE(tracker->inuse); tracker->inuse = true; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_add_tail(&tracker->entry, &list->tracker_list_head); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } static void @@ -54,9 +54,9 @@ mlx5e_ptp_port_ts_cqe_list_remove(struct mlx5e_ptp_port_ts_cqe_list *list, u8 me WARN_ON_ONCE(!tracker->inuse); tracker->inuse = false; - spin_lock(&list->tracker_list_lock); + spin_lock_bh(&list->tracker_list_lock); list_del(&tracker->entry); - spin_unlock(&list->tracker_list_lock); + spin_unlock_bh(&list->tracker_list_lock); } void mlx5e_ptpsq_track_metadata(struct mlx5e_ptpsq *ptpsq, u8 metadata) @@ -155,7 +155,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, struct mlx5e_ptp_metadata_map *metadata_map = &ptpsq->metadata_map; struct mlx5e_ptp_port_ts_cqe_tracker *pos, *n; - spin_lock(&cqe_list->tracker_list_lock); + spin_lock_bh(&cqe_list->tracker_list_lock); list_for_each_entry_safe(pos, n, &cqe_list->tracker_list_head, entry) { struct sk_buff *skb = mlx5e_ptp_metadata_map_lookup(metadata_map, pos->metadata_id); @@ -170,7 +170,7 @@ static void mlx5e_ptpsq_mark_ts_cqes_undelivered(struct mlx5e_ptpsq *ptpsq, pos->inuse = false; list_del(&pos->entry); } - spin_unlock(&cqe_list->tracker_list_lock); + spin_unlock_bh(&cqe_list->tracker_list_lock); } #define PTP_WQE_CTR2IDX(val) ((val) & ptpsq->ts_cqe_ctr_mask) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c index 86bf007fd05b..b500cc2c9689 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_act.c @@ -37,7 +37,7 @@ mlx5e_tc_post_act_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, if (!MLX5_CAP_FLOWTABLE_TYPE(priv->mdev, ignore_flow_level, table_type)) { if (priv->mdev->coredev_type == MLX5_COREDEV_PF) - mlx5_core_warn(priv->mdev, "firmware level support is missing\n"); + mlx5_core_dbg(priv->mdev, "firmware flow level support is missing\n"); err = -EOPNOTSUPP; goto err_check; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index d4ebd8743114..b2cabd6ab86c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -310,9 +310,9 @@ static void mlx5e_macsec_destroy_object(struct mlx5_core_dev *mdev, u32 macsec_o mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); } -static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, - struct mlx5e_macsec_sa *sa, - bool is_tx, struct net_device *netdev, u32 fs_id) +static void mlx5e_macsec_cleanup_sa_fs(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) { int action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : MLX5_ACCEL_MACSEC_ACTION_DECRYPT; @@ -322,20 +322,49 @@ static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, mlx5_macsec_fs_del_rule(macsec->mdev->macsec_fs, sa->macsec_rule, action, netdev, fs_id); - mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); sa->macsec_rule = NULL; } +static void mlx5e_macsec_cleanup_sa(struct mlx5e_macsec *macsec, + struct mlx5e_macsec_sa *sa, bool is_tx, + struct net_device *netdev, u32 fs_id) +{ + mlx5e_macsec_cleanup_sa_fs(macsec, sa, is_tx, netdev, fs_id); + mlx5e_macsec_destroy_object(macsec->mdev, sa->macsec_obj_id); +} + +static int mlx5e_macsec_init_sa_fs(struct macsec_context *ctx, + struct mlx5e_macsec_sa *sa, bool encrypt, + bool is_tx, u32 *fs_id) +{ + struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); + struct mlx5_macsec_fs *macsec_fs = priv->mdev->macsec_fs; + struct mlx5_macsec_rule_attrs rule_attrs; + union mlx5_macsec_rule *macsec_rule; + + rule_attrs.macsec_obj_id = sa->macsec_obj_id; + rule_attrs.sci = sa->sci; + rule_attrs.assoc_num = sa->assoc_num; + rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : + MLX5_ACCEL_MACSEC_ACTION_DECRYPT; + + macsec_rule = mlx5_macsec_fs_add_rule(macsec_fs, ctx, &rule_attrs, fs_id); + if (!macsec_rule) + return -ENOMEM; + + sa->macsec_rule = macsec_rule; + + return 0; +} + static int mlx5e_macsec_init_sa(struct macsec_context *ctx, struct mlx5e_macsec_sa *sa, bool encrypt, bool is_tx, u32 *fs_id) { struct mlx5e_priv *priv = macsec_netdev_priv(ctx->netdev); struct mlx5e_macsec *macsec = priv->macsec; - struct mlx5_macsec_rule_attrs rule_attrs; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_macsec_obj_attrs obj_attrs; - union mlx5_macsec_rule *macsec_rule; int err; obj_attrs.next_pn = sa->next_pn; @@ -357,20 +386,12 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, if (err) return err; - rule_attrs.macsec_obj_id = sa->macsec_obj_id; - rule_attrs.sci = sa->sci; - rule_attrs.assoc_num = sa->assoc_num; - rule_attrs.action = (is_tx) ? MLX5_ACCEL_MACSEC_ACTION_ENCRYPT : - MLX5_ACCEL_MACSEC_ACTION_DECRYPT; - - macsec_rule = mlx5_macsec_fs_add_rule(mdev->macsec_fs, ctx, &rule_attrs, fs_id); - if (!macsec_rule) { - err = -ENOMEM; - goto destroy_macsec_object; + if (sa->active) { + err = mlx5e_macsec_init_sa_fs(ctx, sa, encrypt, is_tx, fs_id); + if (err) + goto destroy_macsec_object; } - sa->macsec_rule = macsec_rule; - return 0; destroy_macsec_object: @@ -526,9 +547,7 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx) goto destroy_sa; macsec_device->tx_sa[assoc_num] = tx_sa; - if (!secy->operational || - assoc_num != tx_sc->encoding_sa || - !tx_sa->active) + if (!secy->operational) goto out; err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); @@ -595,7 +614,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; if (ctx_tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } else { @@ -604,7 +623,7 @@ static int mlx5e_macsec_upd_txsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } out: mutex_unlock(&macsec->lock); @@ -1030,8 +1049,9 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx) goto out; } - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + if (rx_sa->active) + mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); mlx5_destroy_encryption_key(macsec->mdev, rx_sa->enc_key_id); kfree(rx_sa); rx_sc->rx_sa[assoc_num] = NULL; @@ -1112,8 +1132,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, if (!rx_sa || !rx_sa->macsec_rule) continue; - mlx5e_macsec_cleanup_sa(macsec, rx_sa, false, ctx->secy->netdev, - rx_sc->sc_xarray_element->fs_id); + mlx5e_macsec_cleanup_sa_fs(macsec, rx_sa, false, ctx->secy->netdev, + rx_sc->sc_xarray_element->fs_id); } } @@ -1124,8 +1144,8 @@ static int macsec_upd_secy_hw_address(struct macsec_context *ctx, continue; if (rx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, rx_sa, true, false, - &rx_sc->sc_xarray_element->fs_id); + err = mlx5e_macsec_init_sa_fs(ctx, rx_sa, true, false, + &rx_sc->sc_xarray_element->fs_id); if (err) goto out; } @@ -1178,7 +1198,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) if (!tx_sa) continue; - mlx5e_macsec_cleanup_sa(macsec, tx_sa, true, ctx->secy->netdev, 0); + mlx5e_macsec_cleanup_sa_fs(macsec, tx_sa, true, ctx->secy->netdev, 0); } for (i = 0; i < MACSEC_NUM_AN; ++i) { @@ -1187,7 +1207,7 @@ static int mlx5e_macsec_upd_secy(struct macsec_context *ctx) continue; if (tx_sa->assoc_num == tx_sc->encoding_sa && tx_sa->active) { - err = mlx5e_macsec_init_sa(ctx, tx_sa, tx_sc->encrypt, true, NULL); + err = mlx5e_macsec_init_sa_fs(ctx, tx_sa, tx_sc->encrypt, true, NULL); if (err) goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index e66f486faafe..c7f542d0b8f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -34,6 +34,7 @@ #include <linux/mlx5/fs.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <net/rps.h> #include "en.h" #define ARFS_HASH_SHIFT BITS_PER_BYTE diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 5c166d9d2dca..2fa076b23fbe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -401,6 +401,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, mlx5e_skb_cb_hwtstamp_init(skb); mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb, metadata_index); + /* ensure skb is put on metadata_map before tracking the index */ + wmb(); mlx5e_ptpsq_track_metadata(sq->ptpsq, metadata_index); if (!netif_tx_queue_stopped(sq->txq) && mlx5e_ptpsq_metadata_freelist_empty(sq->ptpsq)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 190f10aba170..5a0047bdcb51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -152,7 +152,7 @@ void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) xa_for_each(&esw->offloads.vport_reps, i, rep) { rpriv = rep->rep_data[REP_ETH].priv; - if (!rpriv || !rpriv->netdev || !atomic_read(&rpriv->tc_ht.nelems)) + if (!rpriv || !rpriv->netdev) continue; rhashtable_walk_enter(&rpriv->tc_ht, &iter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b0455134c98e..baaae628b0a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -535,21 +535,26 @@ esw_src_port_rewrite_supported(struct mlx5_eswitch *esw) } static bool -esw_dests_to_vf_pf_vports(struct mlx5_flow_destination *dests, int max_dest) +esw_dests_to_int_external(struct mlx5_flow_destination *dests, int max_dest) { - bool vf_dest = false, pf_dest = false; + bool internal_dest = false, external_dest = false; int i; for (i = 0; i < max_dest; i++) { - if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT) + if (dests[i].type != MLX5_FLOW_DESTINATION_TYPE_VPORT && + dests[i].type != MLX5_FLOW_DESTINATION_TYPE_UPLINK) continue; - if (dests[i].vport.num == MLX5_VPORT_UPLINK) - pf_dest = true; + /* Uplink dest is external, but considered as internal + * if there is reformat because firmware uses LB+hairpin to support it. + */ + if (dests[i].vport.num == MLX5_VPORT_UPLINK && + !(dests[i].vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)) + external_dest = true; else - vf_dest = true; + internal_dest = true; - if (vf_dest && pf_dest) + if (internal_dest && external_dest) return true; } @@ -695,9 +700,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, /* Header rewrite with combined wire+loopback in FDB is not allowed */ if ((flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) && - esw_dests_to_vf_pf_vports(dest, i)) { + esw_dests_to_int_external(dest, i)) { esw_warn(esw->dev, - "FDB: Header rewrite with forwarding to both PF and VF is not allowed\n"); + "FDB: Header rewrite with forwarding to both internal and external dests is not allowed\n"); rule = ERR_PTR(-EINVAL); goto err_esw_get; } @@ -3658,22 +3663,6 @@ static int esw_inline_mode_to_devlink(u8 mlx5_mode, u8 *mode) return 0; } -static bool esw_offloads_devlink_ns_eq_netdev_ns(struct devlink *devlink) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - struct net *devl_net, *netdev_net; - bool ret = false; - - mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); - if (dev->mlx5e_res.uplink_netdev) { - netdev_net = dev_net(dev->mlx5e_res.uplink_netdev); - devl_net = devlink_net(devlink); - ret = net_eq(devl_net, netdev_net); - } - mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); - return ret; -} - int mlx5_eswitch_block_mode(struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -3718,13 +3707,6 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && - !esw_offloads_devlink_ns_eq_netdev_ns(devlink)) { - NL_SET_ERR_MSG_MOD(extack, - "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's."); - return -EPERM; - } - mlx5_lag_disable_change(esw->dev); err = mlx5_esw_try_lock(esw); if (err < 0) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index f27eab6e4929..2911aa34a5be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -703,19 +703,30 @@ void mlx5_fw_reset_events_start(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + MLX5_NB_INIT(&fw_reset->nb, fw_reset_event_notifier, GENERAL_EVENT); mlx5_eq_notifier_register(dev, &fw_reset->nb); } void mlx5_fw_reset_events_stop(struct mlx5_core_dev *dev) { - mlx5_eq_notifier_unregister(dev, &dev->priv.fw_reset->nb); + struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + + if (!fw_reset) + return; + + mlx5_eq_notifier_unregister(dev, &fw_reset->nb); } void mlx5_drain_fw_reset(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + set_bit(MLX5_FW_RESET_FLAGS_DROP_NEW_REQUESTS, &fw_reset->reset_flags); cancel_work_sync(&fw_reset->fw_live_patch_work); cancel_work_sync(&fw_reset->reset_request_work); @@ -733,9 +744,13 @@ static const struct devlink_param mlx5_fw_reset_devlink_params[] = { int mlx5_fw_reset_init(struct mlx5_core_dev *dev) { - struct mlx5_fw_reset *fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); + struct mlx5_fw_reset *fw_reset; int err; + if (!MLX5_CAP_MCAM_REG(dev, mfrl)) + return 0; + + fw_reset = kzalloc(sizeof(*fw_reset), GFP_KERNEL); if (!fw_reset) return -ENOMEM; fw_reset->wq = create_singlethread_workqueue("mlx5_fw_reset_events"); @@ -771,6 +786,9 @@ void mlx5_fw_reset_cleanup(struct mlx5_core_dev *dev) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + if (!fw_reset) + return; + devl_params_unregister(priv_to_devlink(dev), mlx5_fw_reset_devlink_params, ARRAY_SIZE(mlx5_fw_reset_devlink_params)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 9463ede84d8d..ad38e31822df 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -452,10 +452,10 @@ mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct health_buffer __iomem *h = health->health; u8 synd = ioread8(&h->synd); + devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); if (!synd) return 0; - devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd)); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c index 253d7ad9b809..8b63968bbee9 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c @@ -124,6 +124,41 @@ static void mlxbf_gige_get_pauseparam(struct net_device *netdev, pause->tx_pause = 1; } +static bool mlxbf_gige_llu_counters_enabled(struct mlxbf_gige *priv) +{ + u32 data; + + if (priv->hw_version == MLXBF_GIGE_VERSION_BF2) { + data = readl(priv->llu_base + MLXBF_GIGE_BF2_LLU_GENERAL_CONFIG); + if (data & MLXBF_GIGE_BF2_LLU_COUNTERS_EN) + return true; + } else { + data = readl(priv->llu_base + MLXBF_GIGE_BF3_LLU_GENERAL_CONFIG); + if (data & MLXBF_GIGE_BF3_LLU_COUNTERS_EN) + return true; + } + + return false; +} + +static void mlxbf_gige_get_pause_stats(struct net_device *netdev, + struct ethtool_pause_stats *pause_stats) +{ + struct mlxbf_gige *priv = netdev_priv(netdev); + u64 data_lo, data_hi; + + /* Read LLU counters to provide stats only if counters are enabled */ + if (mlxbf_gige_llu_counters_enabled(priv)) { + data_lo = readl(priv->llu_base + MLXBF_GIGE_TX_PAUSE_CNT_LO); + data_hi = readl(priv->llu_base + MLXBF_GIGE_TX_PAUSE_CNT_HI); + pause_stats->tx_pause_frames = (data_hi << 32) | data_lo; + + data_lo = readl(priv->llu_base + MLXBF_GIGE_RX_PAUSE_CNT_LO); + data_hi = readl(priv->llu_base + MLXBF_GIGE_RX_PAUSE_CNT_HI); + pause_stats->rx_pause_frames = (data_hi << 32) | data_lo; + } +} + const struct ethtool_ops mlxbf_gige_ethtool_ops = { .get_link = ethtool_op_get_link, .get_ringparam = mlxbf_gige_get_ringparam, @@ -134,6 +169,7 @@ const struct ethtool_ops mlxbf_gige_ethtool_ops = { .get_ethtool_stats = mlxbf_gige_get_ethtool_stats, .nway_reset = phy_ethtool_nway_reset, .get_pauseparam = mlxbf_gige_get_pauseparam, + .get_pause_stats = mlxbf_gige_get_pause_stats, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, }; diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h index cd0973229c9b..98a8681c21b9 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h @@ -99,4 +99,34 @@ #define MLXBF_GIGE_100M_IPG_SIZE 119 #define MLXBF_GIGE_10M_IPG_SIZE 1199 +/* Offsets into OOB LLU block for pause frame counters */ +#define MLXBF_GIGE_BF2_TX_PAUSE_CNT_HI 0x33d8 +#define MLXBF_GIGE_BF2_TX_PAUSE_CNT_LO 0x33dc +#define MLXBF_GIGE_BF2_RX_PAUSE_CNT_HI 0x3210 +#define MLXBF_GIGE_BF2_RX_PAUSE_CNT_LO 0x3214 + +#define MLXBF_GIGE_BF3_TX_PAUSE_CNT_HI 0x3a88 +#define MLXBF_GIGE_BF3_TX_PAUSE_CNT_LO 0x3a8c +#define MLXBF_GIGE_BF3_RX_PAUSE_CNT_HI 0x38c0 +#define MLXBF_GIGE_BF3_RX_PAUSE_CNT_LO 0x38c4 + +#define MLXBF_GIGE_TX_PAUSE_CNT_HI ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_TX_PAUSE_CNT_HI : \ + MLXBF_GIGE_BF3_TX_PAUSE_CNT_HI) +#define MLXBF_GIGE_TX_PAUSE_CNT_LO ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_TX_PAUSE_CNT_LO : \ + MLXBF_GIGE_BF3_TX_PAUSE_CNT_LO) +#define MLXBF_GIGE_RX_PAUSE_CNT_HI ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_RX_PAUSE_CNT_HI : \ + MLXBF_GIGE_BF3_RX_PAUSE_CNT_HI) +#define MLXBF_GIGE_RX_PAUSE_CNT_LO ((priv->hw_version == MLXBF_GIGE_VERSION_BF2) ? \ + MLXBF_GIGE_BF2_RX_PAUSE_CNT_LO : \ + MLXBF_GIGE_BF3_RX_PAUSE_CNT_LO) + +#define MLXBF_GIGE_BF2_LLU_GENERAL_CONFIG 0x2110 +#define MLXBF_GIGE_BF3_LLU_GENERAL_CONFIG 0x2030 + +#define MLXBF_GIGE_BF2_LLU_COUNTERS_EN BIT(0) +#define MLXBF_GIGE_BF3_LLU_COUNTERS_EN BIT(4) + #endif /* !defined(__MLXBF_GIGE_REGS_H__) */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c index 4af285918ea2..75868b3f548e 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_mactable.c @@ -347,10 +347,10 @@ int sparx5_del_mact_entry(struct sparx5 *sparx5, list) { if ((vid == 0 || mact_entry->vid == vid) && ether_addr_equal(addr, mact_entry->mac)) { + sparx5_mact_forget(sparx5, addr, mact_entry->vid); + list_del(&mact_entry->list); devm_kfree(sparx5->dev, mact_entry); - - sparx5_mact_forget(sparx5, addr, mact_entry->vid); } } mutex_unlock(&sparx5->mact_lock); diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index fac227d372db..dcd901eccfc8 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -11,6 +11,7 @@ #include "net_driver.h" #include <linux/module.h> #include <linux/iommu.h> +#include <net/rps.h> #include "efx.h" #include "nic.h" #include "rx_common.h" diff --git a/drivers/net/ethernet/sfc/siena/rx_common.c b/drivers/net/ethernet/sfc/siena/rx_common.c index 4579f43484c3..219fb358a646 100644 --- a/drivers/net/ethernet/sfc/siena/rx_common.c +++ b/drivers/net/ethernet/sfc/siena/rx_common.c @@ -11,6 +11,7 @@ #include "net_driver.h" #include <linux/module.h> #include <linux/iommu.h> +#include <net/rps.h> #include "efx.h" #include "nic.h" #include "rx_common.h" diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 9d2f4ac783e4..2939a21ca74f 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -294,7 +294,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev, txqueue, netif_tx_queue_stopped(netif_txq), jiffies_to_msecs(jiffies - trans_start), - dql_avail(&netif_txq->dql), + netdev_queue_dql_avail(netif_txq), k3_cppi_desc_pool_avail(tx_chn->desc_pool)); if (netif_tx_queue_stopped(netif_txq)) { diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index e25e0a31126c..2f6739fe78af 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -221,7 +221,7 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, struct genevehdr *gnvh = geneve_hdr(skb); struct metadata_dst *tun_dst = NULL; unsigned int len; - int err = 0; + int nh, err = 0; void *oiph; if (ip_tunnel_collect_metadata() || gs->collect_md) { @@ -272,9 +272,23 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs, skb->pkt_type = PACKET_HOST; } - oiph = skb_network_header(skb); + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(geneve->dev, rx_length_errors); + DEV_STATS_INC(geneve->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + oiph = skb->head + nh; + if (geneve_get_sk_family(gs) == AF_INET) err = IP_ECN_decapsulate(oiph, skb); #if IS_ENABLED(CONFIG_IPV6) @@ -319,19 +333,12 @@ static int geneve_init(struct net_device *dev) struct geneve_dev *geneve = netdev_priv(dev); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&geneve->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL); if (err) { - free_percpu(dev->tstats); gro_cells_destroy(&geneve->gro_cells); return err; } @@ -345,7 +352,6 @@ static void geneve_uninit(struct net_device *dev) dst_cache_destroy(&geneve->cfg.info.dst_cache); gro_cells_destroy(&geneve->gro_cells); - free_percpu(dev->tstats); } /* Callback from net/ipv4/udp.c to receive packets */ @@ -1122,7 +1128,6 @@ static const struct net_device_ops geneve_netdev_ops = { .ndo_open = geneve_open, .ndo_stop = geneve_stop, .ndo_start_xmit = geneve_xmit, - .ndo_get_stats64 = dev_get_tstats64, .ndo_change_mtu = geneve_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, @@ -1189,6 +1194,7 @@ static void geneve_setup(struct net_device *dev) dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; /* MTU range: 68 - (something less than 65535) */ dev->min_mtu = ETH_MIN_MTU; /* The max_mtu calculation does not take account of GENEVE diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 2b46b7398ade..ba4704c2c640 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -711,25 +711,11 @@ static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb) return ret; } -static int gtp_dev_init(struct net_device *dev) -{ - struct gtp_dev *gtp = netdev_priv(dev); - - gtp->dev = dev; - - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - - return 0; -} - static void gtp_dev_uninit(struct net_device *dev) { struct gtp_dev *gtp = netdev_priv(dev); gtp_encap_disable(gtp); - free_percpu(dev->tstats); } static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx) @@ -942,10 +928,8 @@ tx_err: } static const struct net_device_ops gtp_netdev_ops = { - .ndo_init = gtp_dev_init, .ndo_uninit = gtp_dev_uninit, .ndo_start_xmit = gtp_dev_xmit, - .ndo_get_stats64 = dev_get_tstats64, }; static const struct device_type gtp_type = { @@ -957,6 +941,7 @@ static void gtp_link_setup(struct net_device *dev) unsigned int max_gtp_header_len = sizeof(struct iphdr) + sizeof(struct udphdr) + sizeof(struct gtp0_header); + struct gtp_dev *gtp = netdev_priv(dev); dev->netdev_ops = >p_netdev_ops; dev->needs_free_netdev = true; @@ -970,11 +955,13 @@ static void gtp_link_setup(struct net_device *dev) dev->type = ARPHRD_NONE; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->priv_flags |= IFF_NO_QUEUE; dev->features |= NETIF_F_LLTX; netif_keep_dst(dev); dev->needed_headroom = LL_MAX_HEADER + max_gtp_header_len; + gtp->dev = dev; } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 4b5513c9c2be..0206b84284ab 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3519,18 +3519,13 @@ static int macsec_dev_init(struct net_device *dev) struct net_device *real_dev = macsec->real_dev; int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&macsec->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } dev->features = real_dev->features & MACSEC_FEATURES; dev->features |= NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; macsec_set_head_tail_room(dev); @@ -3550,7 +3545,6 @@ static void macsec_dev_uninit(struct net_device *dev) struct macsec_dev *macsec = macsec_priv(dev); gro_cells_destroy(&macsec->gro_cells); - free_percpu(dev->tstats); } static netdev_features_t macsec_fix_features(struct net_device *dev, diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index d93f84fbb1fd..4bd66fdde367 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -183,7 +183,7 @@ static void miic_converter_enable(struct miic *miic, int port, int enable) miic_reg_rmw(miic, MIIC_CONVRST, MIIC_CONVRST_PHYIF_RST(port), val); } -static int miic_config(struct phylink_pcs *pcs, unsigned int mode, +static int miic_config(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, const unsigned long *advertising, bool permit) { @@ -234,7 +234,7 @@ static int miic_config(struct phylink_pcs *pcs, unsigned int mode, return 0; } -static void miic_link_up(struct phylink_pcs *pcs, unsigned int mode, +static void miic_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex) { struct miic_port *miic_port = phylink_pcs_to_miic_port(pcs); @@ -333,6 +333,7 @@ struct phylink_pcs *miic_create(struct device *dev, struct device_node *np) miic_port->miic = miic; miic_port->port = port - 1; miic_port->pcs.ops = &miic_phylink_ops; + miic_port->pcs.neg_mode = true; return &miic_port->pcs; } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 1faa22f58366..42ed013385bf 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -919,7 +919,10 @@ static int m88e1111_config_init_1000basex(struct phy_device *phydev) if (extsr < 0) return extsr; - /* If using copper mode, ensure 1000BaseX auto-negotiation is enabled */ + /* If using copper mode, ensure 1000BaseX auto-negotiation is enabled. + * FIXME: this does not actually enable 1000BaseX auto-negotiation if + * it was previously disabled in the Fiber BMCR! + */ mode = extsr & MII_M1111_HWCFG_MODE_MASK; if (mode == MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN) { err = phy_modify(phydev, MII_M1111_PHY_EXT_SR, diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 780c28e2e4aa..672c6929119a 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -732,24 +732,24 @@ static int qca807x_probe(struct phy_device *phydev) priv->dac_disable_bias_current_tweak = of_property_read_bool(node, "qcom,dac-disable-bias-current-tweak"); - if (IS_ENABLED(CONFIG_GPIOLIB)) { - /* Make sure we don't have mixed leds node and gpio-controller - * to prevent registering leds and having gpio-controller usage - * conflicting with them. - */ - if (of_find_property(node, "leds", NULL) && - of_find_property(node, "gpio-controller", NULL)) { - phydev_err(phydev, "Invalid property detected. LEDs and gpio-controller are mutually exclusive."); - return -EINVAL; - } +#if IS_ENABLED(CONFIG_GPIOLIB) + /* Make sure we don't have mixed leds node and gpio-controller + * to prevent registering leds and having gpio-controller usage + * conflicting with them. + */ + if (of_find_property(node, "leds", NULL) && + of_find_property(node, "gpio-controller", NULL)) { + phydev_err(phydev, "Invalid property detected. LEDs and gpio-controller are mutually exclusive."); + return -EINVAL; + } - /* Do not register a GPIO controller unless flagged for it */ - if (of_property_read_bool(node, "gpio-controller")) { - ret = qca807x_gpio(phydev); - if (ret) - return ret; - } + /* Do not register a GPIO controller unless flagged for it */ + if (of_property_read_bool(node, "gpio-controller")) { + ret = qca807x_gpio(phydev); + if (ret) + return ret; } +#endif /* Attach SFP bus on combo port*/ if (phy_read(phydev, QCA807X_CHIP_CONFIGURATION)) { diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 8d258e263f54..0b3f21cba552 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -78,6 +78,7 @@ #include <net/ax25.h> #include <net/rose.h> #include <net/6lowpan.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 3ff430198512..80ee4fcdfb36 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -3135,7 +3135,8 @@ static int lan78xx_open(struct net_device *net) done: mutex_unlock(&dev->dev_mutex); - usb_autopm_put_interface(dev->intf); + if (ret < 0) + usb_autopm_put_interface(dev->intf); return ret; } diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 143bd4ab160d..57947a5590cc 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -737,7 +737,9 @@ static int sr9800_bind(struct usbnet *dev, struct usb_interface *intf) data->eeprom_len = SR9800_EEPROM_LEN; - usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + goto out; /* LED Setting Rule : * AABB:CCDD diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index b21ebe24057f..e84efa661589 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1633,7 +1633,6 @@ void usbnet_disconnect (struct usb_interface *intf) usb_free_urb(dev->interrupt); kfree(dev->padding_pkt); - free_percpu(net->tstats); free_netdev(net); } EXPORT_SYMBOL_GPL(usbnet_disconnect); @@ -1645,7 +1644,6 @@ static const struct net_device_ops usbnet_netdev_ops = { .ndo_tx_timeout = usbnet_tx_timeout, .ndo_set_rx_mode = usbnet_set_rx_mode, .ndo_change_mtu = usbnet_change_mtu, - .ndo_get_stats64 = dev_get_tstats64, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, }; @@ -1710,10 +1708,6 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev->rx_speed = SPEED_UNSET; dev->tx_speed = SPEED_UNSET; - net->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!net->tstats) - goto out0; - dev->msg_enable = netif_msg_init (msg_level, NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK); init_waitqueue_head(&dev->wait); @@ -1743,6 +1737,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) net->netdev_ops = &usbnet_netdev_ops; net->watchdog_timeo = TX_TIMEOUT_JIFFIES; net->ethtool_ops = &usbnet_ethtool_ops; + net->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; // allow device-specific bind/init procedures // NOTE net->name still not usable ... @@ -1861,8 +1856,6 @@ out1: */ cancel_work_sync(&dev->kevent); del_timer_sync(&dev->delay); - free_percpu(net->tstats); -out0: free_netdev(net); out: return status; diff --git a/drivers/of/property.c b/drivers/of/property.c index b71267c6667c..fa8cd33be131 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1304,7 +1304,7 @@ static struct device_node *parse_remote_endpoint(struct device_node *np, int index) { /* Return NULL for index > 0 to signify end of remote-endpoints. */ - if (!index || strcmp(prop_name, "remote-endpoint")) + if (index > 0 || strcmp(prop_name, "remote-endpoint")) return NULL; return of_graph_get_remote_port_parent(np); diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index 0dda70e1ef90..c78a6fd6c57f 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -150,19 +150,11 @@ u64 riscv_pmu_ctr_get_width_mask(struct perf_event *event) struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; - if (!rvpmu->ctr_get_width) - /** - * If the pmu driver doesn't support counter width, set it to default - * maximum allowed by the specification. - */ - cwidth = 63; - else { - if (hwc->idx == -1) - /* Handle init case where idx is not initialized yet */ - cwidth = rvpmu->ctr_get_width(0); - else - cwidth = rvpmu->ctr_get_width(hwc->idx); - } + if (hwc->idx == -1) + /* Handle init case where idx is not initialized yet */ + cwidth = rvpmu->ctr_get_width(0); + else + cwidth = rvpmu->ctr_get_width(hwc->idx); return GENMASK_ULL(cwidth, 0); } diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 79fdd667922e..fa0bccf4edf2 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -37,6 +37,12 @@ static int pmu_legacy_event_map(struct perf_event *event, u64 *config) return pmu_legacy_ctr_get_idx(event); } +/* cycle & instret are always 64 bit, one bit less according to SBI spec */ +static int pmu_legacy_ctr_get_width(int idx) +{ + return 63; +} + static u64 pmu_legacy_read_ctr(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -111,12 +117,14 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) pmu->ctr_stop = NULL; pmu->event_map = pmu_legacy_event_map; pmu->ctr_get_idx = pmu_legacy_ctr_get_idx; - pmu->ctr_get_width = NULL; + pmu->ctr_get_width = pmu_legacy_ctr_get_width; pmu->ctr_clear_idx = NULL; pmu->ctr_read = pmu_legacy_read_ctr; pmu->event_mapped = pmu_legacy_event_mapped; pmu->event_unmapped = pmu_legacy_event_unmapped; pmu->csr_index = pmu_legacy_csr_index; + pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE; perf_pmu_register(&pmu->pmu, "cpu", PERF_TYPE_RAW); } diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 16acd4dcdb96..452aab49db1e 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -512,7 +512,7 @@ static void pmu_sbi_set_scounteren(void *arg) if (event->hw.idx != -1) csr_write(CSR_SCOUNTEREN, - csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event))); + csr_read(CSR_SCOUNTEREN) | BIT(pmu_sbi_csr_index(event))); } static void pmu_sbi_reset_scounteren(void *arg) @@ -521,7 +521,7 @@ static void pmu_sbi_reset_scounteren(void *arg) if (event->hw.idx != -1) csr_write(CSR_SCOUNTEREN, - csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event))); + csr_read(CSR_SCOUNTEREN) & ~BIT(pmu_sbi_csr_index(event))); } static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival) @@ -731,14 +731,14 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) /* compute hardware counter index */ hidx = info->csr - CSR_CYCLE; /* check if the corresponding bit is set in sscountovf */ - if (!(overflow & (1 << hidx))) + if (!(overflow & BIT(hidx))) continue; /* * Keep a track of overflowed counters so that they can be started * with updated initial value. */ - overflowed_ctrs |= 1 << lidx; + overflowed_ctrs |= BIT(lidx); hw_evt = &event->hw; riscv_pmu_event_update(event); perf_sample_data_init(&data, 0, hw_evt->last_period); diff --git a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c index e625b32889bf..0928a526e2ab 100644 --- a/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c +++ b/drivers/phy/freescale/phy-fsl-imx8-mipi-dphy.c @@ -706,7 +706,7 @@ static int mixel_dphy_probe(struct platform_device *pdev) return ret; } - priv->id = of_alias_get_id(np, "mipi_dphy"); + priv->id = of_alias_get_id(np, "mipi-dphy"); if (priv->id < 0) { dev_err(dev, "Failed to get phy node alias id: %d\n", priv->id); diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c index a623f092b11f..a43e20abb10d 100644 --- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c +++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c @@ -37,56 +37,28 @@ #define EUSB2_TUNE_EUSB_EQU 0x5A #define EUSB2_TUNE_EUSB_HS_COMP_CUR 0x5B -#define QCOM_EUSB2_REPEATER_INIT_CFG(r, v) \ - { \ - .reg = r, \ - .val = v, \ - } - -enum reg_fields { - F_TUNE_EUSB_HS_COMP_CUR, - F_TUNE_EUSB_EQU, - F_TUNE_EUSB_SLEW, - F_TUNE_USB2_HS_COMP_CUR, - F_TUNE_USB2_PREEM, - F_TUNE_USB2_EQU, - F_TUNE_USB2_SLEW, - F_TUNE_SQUELCH_U, - F_TUNE_HSDISC, - F_TUNE_RES_FSDIF, - F_TUNE_IUSB2, - F_TUNE_USB2_CROSSOVER, - F_NUM_TUNE_FIELDS, - - F_FORCE_VAL_5 = F_NUM_TUNE_FIELDS, - F_FORCE_EN_5, - - F_EN_CTL1, - - F_RPTR_STATUS, - F_NUM_FIELDS, -}; - -static struct reg_field eusb2_repeater_tune_reg_fields[F_NUM_FIELDS] = { - [F_TUNE_EUSB_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_EUSB_HS_COMP_CUR, 0, 1), - [F_TUNE_EUSB_EQU] = REG_FIELD(EUSB2_TUNE_EUSB_EQU, 0, 1), - [F_TUNE_EUSB_SLEW] = REG_FIELD(EUSB2_TUNE_EUSB_SLEW, 0, 1), - [F_TUNE_USB2_HS_COMP_CUR] = REG_FIELD(EUSB2_TUNE_USB2_HS_COMP_CUR, 0, 1), - [F_TUNE_USB2_PREEM] = REG_FIELD(EUSB2_TUNE_USB2_PREEM, 0, 2), - [F_TUNE_USB2_EQU] = REG_FIELD(EUSB2_TUNE_USB2_EQU, 0, 1), - [F_TUNE_USB2_SLEW] = REG_FIELD(EUSB2_TUNE_USB2_SLEW, 0, 1), - [F_TUNE_SQUELCH_U] = REG_FIELD(EUSB2_TUNE_SQUELCH_U, 0, 2), - [F_TUNE_HSDISC] = REG_FIELD(EUSB2_TUNE_HSDISC, 0, 2), - [F_TUNE_RES_FSDIF] = REG_FIELD(EUSB2_TUNE_RES_FSDIF, 0, 2), - [F_TUNE_IUSB2] = REG_FIELD(EUSB2_TUNE_IUSB2, 0, 3), - [F_TUNE_USB2_CROSSOVER] = REG_FIELD(EUSB2_TUNE_USB2_CROSSOVER, 0, 2), - - [F_FORCE_VAL_5] = REG_FIELD(EUSB2_FORCE_VAL_5, 0, 7), - [F_FORCE_EN_5] = REG_FIELD(EUSB2_FORCE_EN_5, 0, 7), - - [F_EN_CTL1] = REG_FIELD(EUSB2_EN_CTL1, 0, 7), - - [F_RPTR_STATUS] = REG_FIELD(EUSB2_RPTR_STATUS, 0, 7), +enum eusb2_reg_layout { + TUNE_EUSB_HS_COMP_CUR, + TUNE_EUSB_EQU, + TUNE_EUSB_SLEW, + TUNE_USB2_HS_COMP_CUR, + TUNE_USB2_PREEM, + TUNE_USB2_EQU, + TUNE_USB2_SLEW, + TUNE_SQUELCH_U, + TUNE_HSDISC, + TUNE_RES_FSDIF, + TUNE_IUSB2, + TUNE_USB2_CROSSOVER, + NUM_TUNE_FIELDS, + + FORCE_VAL_5 = NUM_TUNE_FIELDS, + FORCE_EN_5, + + EN_CTL1, + + RPTR_STATUS, + LAYOUT_SIZE, }; struct eusb2_repeater_cfg { @@ -98,10 +70,11 @@ struct eusb2_repeater_cfg { struct eusb2_repeater { struct device *dev; - struct regmap_field *regs[F_NUM_FIELDS]; + struct regmap *regmap; struct phy *phy; struct regulator_bulk_data *vregs; const struct eusb2_repeater_cfg *cfg; + u32 base; enum phy_mode mode; }; @@ -109,10 +82,10 @@ static const char * const pm8550b_vreg_l[] = { "vdd18", "vdd3", }; -static const u32 pm8550b_init_tbl[F_NUM_TUNE_FIELDS] = { - [F_TUNE_IUSB2] = 0x8, - [F_TUNE_SQUELCH_U] = 0x3, - [F_TUNE_USB2_PREEM] = 0x5, +static const u32 pm8550b_init_tbl[NUM_TUNE_FIELDS] = { + [TUNE_IUSB2] = 0x8, + [TUNE_SQUELCH_U] = 0x3, + [TUNE_USB2_PREEM] = 0x5, }; static const struct eusb2_repeater_cfg pm8550b_eusb2_cfg = { @@ -140,47 +113,42 @@ static int eusb2_repeater_init_vregs(struct eusb2_repeater *rptr) static int eusb2_repeater_init(struct phy *phy) { - struct reg_field *regfields = eusb2_repeater_tune_reg_fields; struct eusb2_repeater *rptr = phy_get_drvdata(phy); struct device_node *np = rptr->dev->of_node; - u32 init_tbl[F_NUM_TUNE_FIELDS] = { 0 }; - u8 override; + struct regmap *regmap = rptr->regmap; + const u32 *init_tbl = rptr->cfg->init_tbl; + u8 tune_usb2_preem = init_tbl[TUNE_USB2_PREEM]; + u8 tune_hsdisc = init_tbl[TUNE_HSDISC]; + u8 tune_iusb2 = init_tbl[TUNE_IUSB2]; + u32 base = rptr->base; u32 val; int ret; - int i; + + of_property_read_u8(np, "qcom,tune-usb2-amplitude", &tune_iusb2); + of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &tune_hsdisc); + of_property_read_u8(np, "qcom,tune-usb2-preem", &tune_usb2_preem); ret = regulator_bulk_enable(rptr->cfg->num_vregs, rptr->vregs); if (ret) return ret; - regmap_field_update_bits(rptr->regs[F_EN_CTL1], EUSB2_RPTR_EN, EUSB2_RPTR_EN); + regmap_write(regmap, base + EUSB2_EN_CTL1, EUSB2_RPTR_EN); - for (i = 0; i < F_NUM_TUNE_FIELDS; i++) { - if (init_tbl[i]) { - regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]); - } else { - /* Write 0 if there's no value set */ - u32 mask = GENMASK(regfields[i].msb, regfields[i].lsb); - - regmap_field_update_bits(rptr->regs[i], mask, 0); - } - } - memcpy(init_tbl, rptr->cfg->init_tbl, sizeof(init_tbl)); + regmap_write(regmap, base + EUSB2_TUNE_EUSB_HS_COMP_CUR, init_tbl[TUNE_EUSB_HS_COMP_CUR]); + regmap_write(regmap, base + EUSB2_TUNE_EUSB_EQU, init_tbl[TUNE_EUSB_EQU]); + regmap_write(regmap, base + EUSB2_TUNE_EUSB_SLEW, init_tbl[TUNE_EUSB_SLEW]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_HS_COMP_CUR, init_tbl[TUNE_USB2_HS_COMP_CUR]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_EQU, init_tbl[TUNE_USB2_EQU]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_SLEW, init_tbl[TUNE_USB2_SLEW]); + regmap_write(regmap, base + EUSB2_TUNE_SQUELCH_U, init_tbl[TUNE_SQUELCH_U]); + regmap_write(regmap, base + EUSB2_TUNE_RES_FSDIF, init_tbl[TUNE_RES_FSDIF]); + regmap_write(regmap, base + EUSB2_TUNE_USB2_CROSSOVER, init_tbl[TUNE_USB2_CROSSOVER]); - if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &override)) - init_tbl[F_TUNE_IUSB2] = override; + regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, tune_usb2_preem); + regmap_write(regmap, base + EUSB2_TUNE_HSDISC, tune_hsdisc); + regmap_write(regmap, base + EUSB2_TUNE_IUSB2, tune_iusb2); - if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &override)) - init_tbl[F_TUNE_HSDISC] = override; - - if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &override)) - init_tbl[F_TUNE_USB2_PREEM] = override; - - for (i = 0; i < F_NUM_TUNE_FIELDS; i++) - regmap_field_update_bits(rptr->regs[i], init_tbl[i], init_tbl[i]); - - ret = regmap_field_read_poll_timeout(rptr->regs[F_RPTR_STATUS], - val, val & RPTR_OK, 10, 5); + ret = regmap_read_poll_timeout(regmap, base + EUSB2_RPTR_STATUS, val, val & RPTR_OK, 10, 5); if (ret) dev_err(rptr->dev, "initialization timed-out\n"); @@ -191,6 +159,8 @@ static int eusb2_repeater_set_mode(struct phy *phy, enum phy_mode mode, int submode) { struct eusb2_repeater *rptr = phy_get_drvdata(phy); + struct regmap *regmap = rptr->regmap; + u32 base = rptr->base; switch (mode) { case PHY_MODE_USB_HOST: @@ -199,10 +169,8 @@ static int eusb2_repeater_set_mode(struct phy *phy, * per eUSB 1.2 Spec. Below implement software workaround until * PHY and controller is fixing seen observation. */ - regmap_field_update_bits(rptr->regs[F_FORCE_EN_5], - F_CLK_19P2M_EN, F_CLK_19P2M_EN); - regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5], - V_CLK_19P2M_EN, V_CLK_19P2M_EN); + regmap_write(regmap, base + EUSB2_FORCE_EN_5, F_CLK_19P2M_EN); + regmap_write(regmap, base + EUSB2_FORCE_VAL_5, V_CLK_19P2M_EN); break; case PHY_MODE_USB_DEVICE: /* @@ -211,10 +179,8 @@ static int eusb2_repeater_set_mode(struct phy *phy, * repeater doesn't clear previous value due to shared * regulators (say host <-> device mode switch). */ - regmap_field_update_bits(rptr->regs[F_FORCE_EN_5], - F_CLK_19P2M_EN, 0); - regmap_field_update_bits(rptr->regs[F_FORCE_VAL_5], - V_CLK_19P2M_EN, 0); + regmap_write(regmap, base + EUSB2_FORCE_EN_5, 0); + regmap_write(regmap, base + EUSB2_FORCE_VAL_5, 0); break; default: return -EINVAL; @@ -243,9 +209,8 @@ static int eusb2_repeater_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct phy_provider *phy_provider; struct device_node *np = dev->of_node; - struct regmap *regmap; - int i, ret; u32 res; + int ret; rptr = devm_kzalloc(dev, sizeof(*rptr), GFP_KERNEL); if (!rptr) @@ -258,22 +223,15 @@ static int eusb2_repeater_probe(struct platform_device *pdev) if (!rptr->cfg) return -EINVAL; - regmap = dev_get_regmap(dev->parent, NULL); - if (!regmap) + rptr->regmap = dev_get_regmap(dev->parent, NULL); + if (!rptr->regmap) return -ENODEV; ret = of_property_read_u32(np, "reg", &res); if (ret < 0) return ret; - for (i = 0; i < F_NUM_FIELDS; i++) - eusb2_repeater_tune_reg_fields[i].reg += res; - - ret = devm_regmap_field_bulk_alloc(dev, regmap, rptr->regs, - eusb2_repeater_tune_reg_fields, - F_NUM_FIELDS); - if (ret) - return ret; + rptr->base = res; ret = eusb2_repeater_init_vregs(rptr); if (ret < 0) { diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c index c2590579190a..03fb0d4b75d7 100644 --- a/drivers/phy/qualcomm/phy-qcom-m31.c +++ b/drivers/phy/qualcomm/phy-qcom-m31.c @@ -299,7 +299,7 @@ static int m31usb_phy_probe(struct platform_device *pdev) qphy->vreg = devm_regulator_get(dev, "vdda-phy"); if (IS_ERR(qphy->vreg)) - return dev_err_probe(dev, PTR_ERR(qphy->phy), + return dev_err_probe(dev, PTR_ERR(qphy->vreg), "failed to get vreg\n"); phy_set_drvdata(qphy->phy, qphy); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index 6621246e4ddf..5c003988c35d 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -1556,7 +1556,7 @@ static const char * const qmp_phy_vreg_l[] = { "vdda-phy", "vdda-pll", }; -static const struct qmp_usb_offsets qmp_usb_offsets_ipq8074 = { +static const struct qmp_usb_offsets qmp_usb_offsets_v3 = { .serdes = 0, .pcs = 0x800, .pcs_misc = 0x600, @@ -1572,7 +1572,7 @@ static const struct qmp_usb_offsets qmp_usb_offsets_ipq9574 = { .rx = 0x400, }; -static const struct qmp_usb_offsets qmp_usb_offsets_v3 = { +static const struct qmp_usb_offsets qmp_usb_offsets_v3_msm8996 = { .serdes = 0, .pcs = 0x600, .tx = 0x200, @@ -1624,7 +1624,7 @@ static const struct qmp_usb_offsets qmp_usb_offsets_v7 = { static const struct qmp_phy_cfg ipq6018_usb3phy_cfg = { .lanes = 1, - .offsets = &qmp_usb_offsets_ipq8074, + .offsets = &qmp_usb_offsets_v3, .serdes_tbl = ipq9574_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(ipq9574_usb3_serdes_tbl), @@ -1642,7 +1642,7 @@ static const struct qmp_phy_cfg ipq6018_usb3phy_cfg = { static const struct qmp_phy_cfg ipq8074_usb3phy_cfg = { .lanes = 1, - .offsets = &qmp_usb_offsets_ipq8074, + .offsets = &qmp_usb_offsets_v3, .serdes_tbl = ipq8074_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(ipq8074_usb3_serdes_tbl), @@ -1678,7 +1678,7 @@ static const struct qmp_phy_cfg ipq9574_usb3phy_cfg = { static const struct qmp_phy_cfg msm8996_usb3phy_cfg = { .lanes = 1, - .offsets = &qmp_usb_offsets_v3, + .offsets = &qmp_usb_offsets_v3_msm8996, .serdes_tbl = msm8996_usb3_serdes_tbl, .serdes_tbl_num = ARRAY_SIZE(msm8996_usb3_serdes_tbl), diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index 8527dca9cf56..dcbe8f85e122 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -458,8 +458,10 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev) amd_pmf_hex_dump_pb(dev); dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL); - if (!dev->prev_data) + if (!dev->prev_data) { + ret = -ENOMEM; goto error; + } ret = amd_pmf_start_policy_engine(dev); if (ret) diff --git a/drivers/platform/x86/p2sb.c b/drivers/platform/x86/p2sb.c index 6bd14d0132db..3d66e1d4eb1f 100644 --- a/drivers/platform/x86/p2sb.c +++ b/drivers/platform/x86/p2sb.c @@ -20,9 +20,11 @@ #define P2SBC_HIDE BIT(8) #define P2SB_DEVFN_DEFAULT PCI_DEVFN(31, 1) +#define P2SB_DEVFN_GOLDMONT PCI_DEVFN(13, 0) +#define SPI_DEVFN_GOLDMONT PCI_DEVFN(13, 2) static const struct x86_cpu_id p2sb_cpu_ids[] = { - X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, PCI_DEVFN(13, 0)), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT, P2SB_DEVFN_GOLDMONT), {} }; @@ -98,21 +100,12 @@ static void p2sb_scan_and_cache_devfn(struct pci_bus *bus, unsigned int devfn) static int p2sb_scan_and_cache(struct pci_bus *bus, unsigned int devfn) { - unsigned int slot, fn; - - if (PCI_FUNC(devfn) == 0) { - /* - * When function number of the P2SB device is zero, scan it and - * other function numbers, and if devices are available, cache - * their BAR0s. - */ - slot = PCI_SLOT(devfn); - for (fn = 0; fn < NR_P2SB_RES_CACHE; fn++) - p2sb_scan_and_cache_devfn(bus, PCI_DEVFN(slot, fn)); - } else { - /* Scan the P2SB device and cache its BAR0 */ - p2sb_scan_and_cache_devfn(bus, devfn); - } + /* Scan the P2SB device and cache its BAR0 */ + p2sb_scan_and_cache_devfn(bus, devfn); + + /* On Goldmont p2sb_bar() also gets called for the SPI controller */ + if (devfn == P2SB_DEVFN_GOLDMONT) + p2sb_scan_and_cache_devfn(bus, SPI_DEVFN_GOLDMONT); if (!p2sb_valid_resource(&p2sb_resources[PCI_FUNC(devfn)].res)) return -ENOENT; diff --git a/drivers/pmdomain/arm/scmi_perf_domain.c b/drivers/pmdomain/arm/scmi_perf_domain.c index 709bbc448fad..d7ef46ccd9b8 100644 --- a/drivers/pmdomain/arm/scmi_perf_domain.c +++ b/drivers/pmdomain/arm/scmi_perf_domain.c @@ -159,6 +159,9 @@ static void scmi_perf_domain_remove(struct scmi_device *sdev) struct genpd_onecell_data *scmi_pd_data = dev_get_drvdata(dev); int i; + if (!scmi_pd_data) + return; + of_genpd_del_provider(dev->of_node); for (i = 0; i < scmi_pd_data->num_domains; i++) diff --git a/drivers/pmdomain/qcom/rpmhpd.c b/drivers/pmdomain/qcom/rpmhpd.c index 3078896b1300..47df910645f6 100644 --- a/drivers/pmdomain/qcom/rpmhpd.c +++ b/drivers/pmdomain/qcom/rpmhpd.c @@ -692,6 +692,7 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner) unsigned int active_corner, sleep_corner; unsigned int this_active_corner = 0, this_sleep_corner = 0; unsigned int peer_active_corner = 0, peer_sleep_corner = 0; + unsigned int peer_enabled_corner; if (pd->state_synced) { to_active_sleep(pd, corner, &this_active_corner, &this_sleep_corner); @@ -701,9 +702,11 @@ static int rpmhpd_aggregate_corner(struct rpmhpd *pd, unsigned int corner) this_sleep_corner = pd->level_count - 1; } - if (peer && peer->enabled) - to_active_sleep(peer, peer->corner, &peer_active_corner, + if (peer && peer->enabled) { + peer_enabled_corner = max(peer->corner, peer->enable_corner); + to_active_sleep(peer, peer_enabled_corner, &peer_active_corner, &peer_sleep_corner); + } active_corner = max(this_active_corner, peer_active_corner); diff --git a/drivers/power/supply/Kconfig b/drivers/power/supply/Kconfig index f21cb05815ec..3e31375491d5 100644 --- a/drivers/power/supply/Kconfig +++ b/drivers/power/supply/Kconfig @@ -978,6 +978,7 @@ config CHARGER_QCOM_SMB2 config FUEL_GAUGE_MM8013 tristate "Mitsumi MM8013 fuel gauge driver" depends on I2C + select REGMAP_I2C help Say Y here to enable the Mitsumi MM8013 fuel gauge driver. It enables the monitoring of many battery parameters, including diff --git a/drivers/power/supply/bq27xxx_battery_i2c.c b/drivers/power/supply/bq27xxx_battery_i2c.c index 3a1798b0c1a7..9910c600743e 100644 --- a/drivers/power/supply/bq27xxx_battery_i2c.c +++ b/drivers/power/supply/bq27xxx_battery_i2c.c @@ -209,7 +209,9 @@ static void bq27xxx_battery_i2c_remove(struct i2c_client *client) { struct bq27xxx_device_info *di = i2c_get_clientdata(client); - free_irq(client->irq, di); + if (client->irq) + free_irq(client->irq, di); + bq27xxx_battery_teardown(di); mutex_lock(&battery_mutex); diff --git a/drivers/scsi/mpi3mr/mpi3mr_transport.c b/drivers/scsi/mpi3mr/mpi3mr_transport.c index c0c8ab586957..d32ad46318cb 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_transport.c +++ b/drivers/scsi/mpi3mr/mpi3mr_transport.c @@ -1671,7 +1671,7 @@ mpi3mr_update_mr_sas_port(struct mpi3mr_ioc *mrioc, struct host_port *h_port, void mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc) { - struct host_port h_port[64]; + struct host_port *h_port = NULL; int i, j, found, host_port_count = 0, port_idx; u16 sz, attached_handle, ioc_status; struct mpi3_sas_io_unit_page0 *sas_io_unit_pg0 = NULL; @@ -1685,6 +1685,10 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc) sas_io_unit_pg0 = kzalloc(sz, GFP_KERNEL); if (!sas_io_unit_pg0) return; + h_port = kcalloc(64, sizeof(struct host_port), GFP_KERNEL); + if (!h_port) + goto out; + if (mpi3mr_cfg_get_sas_io_unit_pg0(mrioc, sas_io_unit_pg0, sz)) { ioc_err(mrioc, "failure at %s:%d/%s()!\n", __FILE__, __LINE__, __func__); @@ -1814,6 +1818,7 @@ mpi3mr_refresh_sas_ports(struct mpi3mr_ioc *mrioc) } } out: + kfree(h_port); kfree(sas_io_unit_pg0); } diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 8761bc58d965..b8120ca93c79 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7378,7 +7378,9 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout) return -EFAULT; } - issue_diag_reset: + return 0; + +issue_diag_reset: rc = _base_diag_reset(ioc); return rc; } diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c index f4bfd24386f1..f913e9bd57ed 100644 --- a/drivers/soc/qcom/pmic_glink.c +++ b/drivers/soc/qcom/pmic_glink.c @@ -265,10 +265,17 @@ static int pmic_glink_probe(struct platform_device *pdev) pg->client_mask = *match_data; + pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg); + if (IS_ERR(pg->pdr)) { + ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr), + "failed to initialize pdr\n"); + return ret; + } + if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) { ret = pmic_glink_add_aux_device(pg, &pg->ucsi_aux, "ucsi"); if (ret) - return ret; + goto out_release_pdr_handle; } if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_ALTMODE)) { ret = pmic_glink_add_aux_device(pg, &pg->altmode_aux, "altmode"); @@ -281,17 +288,11 @@ static int pmic_glink_probe(struct platform_device *pdev) goto out_release_altmode_aux; } - pg->pdr = pdr_handle_alloc(pmic_glink_pdr_callback, pg); - if (IS_ERR(pg->pdr)) { - ret = dev_err_probe(&pdev->dev, PTR_ERR(pg->pdr), "failed to initialize pdr\n"); - goto out_release_aux_devices; - } - service = pdr_add_lookup(pg->pdr, "tms/servreg", "msm/adsp/charger_pd"); if (IS_ERR(service)) { ret = dev_err_probe(&pdev->dev, PTR_ERR(service), "failed adding pdr lookup for charger_pd\n"); - goto out_release_pdr_handle; + goto out_release_aux_devices; } mutex_lock(&__pmic_glink_lock); @@ -300,8 +301,6 @@ static int pmic_glink_probe(struct platform_device *pdev) return 0; -out_release_pdr_handle: - pdr_handle_release(pg->pdr); out_release_aux_devices: if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_BATT)) pmic_glink_del_aux_device(pg, &pg->ps_aux); @@ -311,6 +310,8 @@ out_release_altmode_aux: out_release_ucsi_aux: if (pg->client_mask & BIT(PMIC_GLINK_CLIENT_UCSI)) pmic_glink_del_aux_device(pg, &pg->ucsi_aux); +out_release_pdr_handle: + pdr_handle_release(pg->pdr); return ret; } diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c index 5fcd0fdd2faa..b3808fc24c69 100644 --- a/drivers/soc/qcom/pmic_glink_altmode.c +++ b/drivers/soc/qcom/pmic_glink_altmode.c @@ -76,7 +76,7 @@ struct pmic_glink_altmode_port { struct work_struct work; - struct device *bridge; + struct auxiliary_device *bridge; enum typec_orientation orientation; u16 svid; @@ -230,7 +230,7 @@ static void pmic_glink_altmode_worker(struct work_struct *work) else pmic_glink_altmode_enable_usb(altmode, alt_port); - drm_aux_hpd_bridge_notify(alt_port->bridge, + drm_aux_hpd_bridge_notify(&alt_port->bridge->dev, alt_port->hpd_state ? connector_status_connected : connector_status_disconnected); @@ -454,7 +454,7 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, alt_port->index = port; INIT_WORK(&alt_port->work, pmic_glink_altmode_worker); - alt_port->bridge = drm_dp_hpd_bridge_register(dev, to_of_node(fwnode)); + alt_port->bridge = devm_drm_dp_hpd_bridge_alloc(dev, to_of_node(fwnode)); if (IS_ERR(alt_port->bridge)) { fwnode_handle_put(fwnode); return PTR_ERR(alt_port->bridge); @@ -510,6 +510,16 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev, } } + for (port = 0; port < ARRAY_SIZE(altmode->ports); port++) { + alt_port = &altmode->ports[port]; + if (!alt_port->bridge) + continue; + + ret = devm_drm_dp_hpd_bridge_add(dev, alt_port->bridge); + if (ret) + return ret; + } + altmode->client = devm_pmic_glink_register_client(dev, altmode->owner_id, pmic_glink_altmode_callback, diff --git a/drivers/tee/optee/device.c b/drivers/tee/optee/device.c index 4b1092127694..1892e49a8e6a 100644 --- a/drivers/tee/optee/device.c +++ b/drivers/tee/optee/device.c @@ -90,13 +90,14 @@ static int optee_register_device(const uuid_t *device_uuid, u32 func) if (rc) { pr_err("device registration failed, err: %d\n", rc); put_device(&optee_device->dev); + return rc; } if (func == PTA_CMD_GET_DEVICES_SUPP) device_create_file(&optee_device->dev, &dev_attr_need_supplicant); - return rc; + return 0; } static int __optee_enumerate_devices(u32 func) diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 1183e7a871f8..46823c2e2ba1 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2399,11 +2399,9 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, struct fbcon_ops *ops = info->fbcon_par; struct fbcon_display *p = &fb_display[vc->vc_num]; int resize, ret, old_userfont, old_width, old_height, old_charcount; - char *old_data = NULL; + u8 *old_data = vc->vc_font.data; resize = (w != vc->vc_font.width) || (h != vc->vc_font.height); - if (p->userfont) - old_data = vc->vc_font.data; vc->vc_font.data = (void *)(p->fontdata = data); old_userfont = p->userfont; if ((p->userfont = userfont)) @@ -2437,13 +2435,13 @@ static int fbcon_do_set_font(struct vc_data *vc, int w, int h, int charcount, update_screen(vc); } - if (old_data && (--REFCOUNT(old_data) == 0)) + if (old_userfont && (--REFCOUNT(old_data) == 0)) kfree(old_data - FONT_EXTRA_WORDS * sizeof(int)); return 0; err_out: p->fontdata = old_data; - vc->vc_font.data = (void *)old_data; + vc->vc_font.data = old_data; if (userfont) { p->userfont = old_userfont; diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index c26ee6fd73c9..8fdccf033b2d 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1010,8 +1010,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) goto getmem_done; } pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n"); - } else { - goto err1; } /* diff --git a/fs/afs/dir.c b/fs/afs/dir.c index b5b8de521f99..8a67fc427e74 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -479,8 +479,10 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, dire->u.name[0] == '.' && ctx->actor != afs_lookup_filldir && ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) + memcmp(dire->u.name, ".__afs", 6) == 0) { + ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); continue; + } /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, @@ -589,8 +589,8 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; /* @@ -600,9 +600,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) if (!(iocb->ki_flags & IOCB_AIO_RW)) return; + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e71ef97d0a7c..c843563914ca 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1307,12 +1307,12 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) * * @objectid: root id * @anon_dev: preallocated anonymous block device number for new roots, - * pass 0 for new allocation. + * pass NULL for a new allocation. * @check_ref: whether to check root item references, If true, return -ENOENT * for orphan roots */ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev, + u64 objectid, dev_t *anon_dev, bool check_ref) { struct btrfs_root *root; @@ -1342,9 +1342,9 @@ again: * that common but still possible. In that case, we just need * to free the anon_dev. */ - if (unlikely(anon_dev)) { - free_anon_bdev(anon_dev); - anon_dev = 0; + if (unlikely(anon_dev && *anon_dev)) { + free_anon_bdev(*anon_dev); + *anon_dev = 0; } if (check_ref && btrfs_root_refs(&root->root_item) == 0) { @@ -1366,7 +1366,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root, anon_dev); + ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail; @@ -1402,7 +1402,7 @@ fail: * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() * and once again by our caller. */ - if (anon_dev) + if (anon_dev && *anon_dev) root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); @@ -1418,7 +1418,7 @@ fail: struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref) { - return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); + return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); } /* @@ -1426,11 +1426,11 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, * the anonymous block device id * * @objectid: tree objectid - * @anon_dev: if zero, allocate a new anonymous block device or use the - * parameter value + * @anon_dev: if NULL, allocate a new anonymous block device or use the + * parameter value if not NULL */ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev) + u64 objectid, dev_t *anon_dev) { return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 9413726b329b..eb3473d1c1ac 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -61,7 +61,7 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev); + u64 objectid, dev_t *anon_dev); struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 objectid); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3e19a2475ab3..8b4bef05e222 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2480,6 +2480,7 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, struct fiemap_cache *cache, u64 offset, u64 phys, u64 len, u32 flags) { + u64 cache_end; int ret = 0; /* Set at the end of extent_fiemap(). */ @@ -2489,15 +2490,102 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, goto assign; /* - * Sanity check, extent_fiemap() should have ensured that new - * fiemap extent won't overlap with cached one. - * Not recoverable. + * When iterating the extents of the inode, at extent_fiemap(), we may + * find an extent that starts at an offset behind the end offset of the + * previous extent we processed. This happens if fiemap is called + * without FIEMAP_FLAG_SYNC and there are ordered extents completing + * while we call btrfs_next_leaf() (through fiemap_next_leaf_item()). * - * NOTE: Physical address can overlap, due to compression + * For example we are in leaf X processing its last item, which is the + * file extent item for file range [512K, 1M[, and after + * btrfs_next_leaf() releases the path, there's an ordered extent that + * completes for the file range [768K, 2M[, and that results in trimming + * the file extent item so that it now corresponds to the file range + * [512K, 768K[ and a new file extent item is inserted for the file + * range [768K, 2M[, which may end up as the last item of leaf X or as + * the first item of the next leaf - in either case btrfs_next_leaf() + * will leave us with a path pointing to the new extent item, for the + * file range [768K, 2M[, since that's the first key that follows the + * last one we processed. So in order not to report overlapping extents + * to user space, we trim the length of the previously cached extent and + * emit it. + * + * Upon calling btrfs_next_leaf() we may also find an extent with an + * offset smaller than or equals to cache->offset, and this happens + * when we had a hole or prealloc extent with several delalloc ranges in + * it, but after btrfs_next_leaf() released the path, delalloc was + * flushed and the resulting ordered extents were completed, so we can + * now have found a file extent item for an offset that is smaller than + * or equals to what we have in cache->offset. We deal with this as + * described below. */ - if (cache->offset + cache->len > offset) { - WARN_ON(1); - return -EINVAL; + cache_end = cache->offset + cache->len; + if (cache_end > offset) { + if (offset == cache->offset) { + /* + * We cached a dealloc range (found in the io tree) for + * a hole or prealloc extent and we have now found a + * file extent item for the same offset. What we have + * now is more recent and up to date, so discard what + * we had in the cache and use what we have just found. + */ + goto assign; + } else if (offset > cache->offset) { + /* + * The extent range we previously found ends after the + * offset of the file extent item we found and that + * offset falls somewhere in the middle of that previous + * extent range. So adjust the range we previously found + * to end at the offset of the file extent item we have + * just found, since this extent is more up to date. + * Emit that adjusted range and cache the file extent + * item we have just found. This corresponds to the case + * where a previously found file extent item was split + * due to an ordered extent completing. + */ + cache->len = offset - cache->offset; + goto emit; + } else { + const u64 range_end = offset + len; + + /* + * The offset of the file extent item we have just found + * is behind the cached offset. This means we were + * processing a hole or prealloc extent for which we + * have found delalloc ranges (in the io tree), so what + * we have in the cache is the last delalloc range we + * found while the file extent item we found can be + * either for a whole delalloc range we previously + * emmitted or only a part of that range. + * + * We have two cases here: + * + * 1) The file extent item's range ends at or behind the + * cached extent's end. In this case just ignore the + * current file extent item because we don't want to + * overlap with previous ranges that may have been + * emmitted already; + * + * 2) The file extent item starts behind the currently + * cached extent but its end offset goes beyond the + * end offset of the cached extent. We don't want to + * overlap with a previous range that may have been + * emmitted already, so we emit the currently cached + * extent and then partially store the current file + * extent item's range in the cache, for the subrange + * going the cached extent's end to the end of the + * file extent item. + */ + if (range_end <= cache_end) + return 0; + + if (!(flags & (FIEMAP_EXTENT_ENCODED | FIEMAP_EXTENT_DELALLOC))) + phys += cache_end - offset; + + offset = cache_end; + len = range_end - cache_end; + goto emit; + } } /* @@ -2517,6 +2605,7 @@ static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, return 0; } +emit: /* Not mergeable, need to submit cached one */ ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, cache->len, cache->flags); @@ -2907,17 +2996,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, range_end = round_up(start + len, sectorsize); prev_extent_end = range_start; - btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); - ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end); if (ret < 0) - goto out_unlock; + goto out; btrfs_release_path(path); path->reada = READA_FORWARD; ret = fiemap_search_slot(inode, path, range_start); if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* * No file extent item found, but we may have delalloc between @@ -2964,7 +3051,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, backref_ctx, 0, 0, 0, prev_extent_end, hole_end); if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* fiemap_fill_next_extent() told us to stop. */ stopped = true; @@ -3020,7 +3107,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, extent_gen, backref_ctx); if (ret < 0) - goto out_unlock; + goto out; else if (ret > 0) flags |= FIEMAP_EXTENT_SHARED; } @@ -3031,7 +3118,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* fiemap_fill_next_extent() told us to stop. */ stopped = true; @@ -3042,12 +3129,12 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, next_item: if (fatal_signal_pending(current)) { ret = -EINTR; - goto out_unlock; + goto out; } ret = fiemap_next_leaf_item(inode, path); if (ret < 0) { - goto out_unlock; + goto out; } else if (ret > 0) { /* No more file extent items for this inode. */ break; @@ -3071,7 +3158,7 @@ check_eof_delalloc: &delalloc_cached_state, backref_ctx, 0, 0, 0, prev_extent_end, range_end - 1); if (ret < 0) - goto out_unlock; + goto out; prev_extent_end = range_end; } @@ -3109,9 +3196,6 @@ check_eof_delalloc: } ret = emit_last_fiemap_cache(fieinfo, &cache); - -out_unlock: - btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); out: free_extent_state(delalloc_cached_state); btrfs_free_backref_share_ctx(backref_ctx); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f88e0ca8331d..4795738d5785 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7835,6 +7835,7 @@ struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter, static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { + struct btrfs_inode *btrfs_inode = BTRFS_I(inode); int ret; ret = fiemap_prep(inode, fieinfo, start, &len, 0); @@ -7860,7 +7861,26 @@ static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return ret; } - return extent_fiemap(BTRFS_I(inode), fieinfo, start, len); + btrfs_inode_lock(btrfs_inode, BTRFS_ILOCK_SHARED); + + /* + * We did an initial flush to avoid holding the inode's lock while + * triggering writeback and waiting for the completion of IO and ordered + * extents. Now after we locked the inode we do it again, because it's + * possible a new write may have happened in between those two steps. + */ + if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) { + ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX); + if (ret) { + btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED); + return ret; + } + } + + ret = extent_fiemap(btrfs_inode, fieinfo, start, len); + btrfs_inode_unlock(btrfs_inode, BTRFS_ILOCK_SHARED); + + return ret; } static int btrfs_writepages(struct address_space *mapping, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ac3316e0d11c..9d1eac15e09e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -721,7 +721,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap, free_extent_buffer(leaf); leaf = NULL; - new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); + new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c52807d97efa..bf8e64c766b6 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1834,7 +1834,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); pending->snap = NULL; diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index fae97c25ce58..8109aba66e02 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -380,10 +380,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, ceph_decode_skip_8(p, end, bad_ext); /* required_client_features */ ceph_decode_skip_set(p, end, 64, bad_ext); + /* bal_rank_mask */ + ceph_decode_skip_string(p, end, bad_ext); + } + if (mdsmap_ev >= 18) { ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext); - } else { - /* This forces the usage of the (sync) SETXATTR Op */ - m->m_max_xattr_size = 0; } bad_ext: doutc(cl, "m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n", diff --git a/fs/ceph/mdsmap.h b/fs/ceph/mdsmap.h index 89f1931f1ba6..1f2171dd01bf 100644 --- a/fs/ceph/mdsmap.h +++ b/fs/ceph/mdsmap.h @@ -27,7 +27,11 @@ struct ceph_mdsmap { u32 m_session_timeout; /* seconds */ u32 m_session_autoclose; /* seconds */ u64 m_max_file_size; - u64 m_max_xattr_size; /* maximum size for xattrs blob */ + /* + * maximum size for xattrs blob. + * Zeroed by default to force the usage of the (sync) SETXATTR Op. + */ + u64 m_max_xattr_size; u32 m_max_mds; /* expected up:active mds number */ u32 m_num_active_mds; /* actual up:active mds number */ u32 possible_max_rank; /* possible max rank index */ diff --git a/fs/coredump.c b/fs/coredump.c index f258c17c1841..be6403b4b14b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -872,6 +872,9 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) loff_t pos; ssize_t n; + if (!page) + return 0; + if (cprm->to_skip) { if (!__dump_skip(cprm, cprm->to_skip)) return 0; @@ -884,7 +887,6 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) pos = file->f_pos; bvec_set_page(&bvec, page, PAGE_SIZE, 0); iov_iter_bvec(&iter, ITER_SOURCE, &bvec, 1, PAGE_SIZE); - iov_iter_set_copy_mc(&iter); n = __kernel_write_iter(cprm->file, &iter, &pos); if (n != PAGE_SIZE) return 0; @@ -895,10 +897,44 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) return 1; } +/* + * If we might get machine checks from kernel accesses during the + * core dump, let's get those errors early rather than during the + * IO. This is not performance-critical enough to warrant having + * all the machine check logic in the iovec paths. + */ +#ifdef copy_mc_to_kernel + +#define dump_page_alloc() alloc_page(GFP_KERNEL) +#define dump_page_free(x) __free_page(x) +static struct page *dump_page_copy(struct page *src, struct page *dst) +{ + void *buf = kmap_local_page(src); + size_t left = copy_mc_to_kernel(page_address(dst), buf, PAGE_SIZE); + kunmap_local(buf); + return left ? NULL : dst; +} + +#else + +/* We just want to return non-NULL; it's never used. */ +#define dump_page_alloc() ERR_PTR(-EINVAL) +#define dump_page_free(x) ((void)(x)) +static inline struct page *dump_page_copy(struct page *src, struct page *dst) +{ + return src; +} +#endif + int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len) { unsigned long addr; + struct page *dump_page; + + dump_page = dump_page_alloc(); + if (!dump_page) + return 0; for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page; @@ -912,14 +948,17 @@ int dump_user_range(struct coredump_params *cprm, unsigned long start, */ page = get_dump_page(addr); if (page) { - int stop = !dump_emit_page(cprm, page); + int stop = !dump_emit_page(cprm, dump_page_copy(page, dump_page)); put_page(page); - if (stop) + if (stop) { + dump_page_free(dump_page); return 0; + } } else { dump_skip(cprm, PAGE_SIZE); } } + dump_page_free(dump_page); return 1; } #endif diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index 169252e6dc46..f7206158ee81 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -38,7 +38,7 @@ struct efivar_entry { int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, struct list_head *), - void *data, bool duplicates, struct list_head *head); + void *data, struct list_head *head); int efivar_entry_add(struct efivar_entry *entry, struct list_head *head); void __efivar_entry_add(struct efivar_entry *entry, struct list_head *head); diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 6038dd39367a..bb14462f6d99 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -343,12 +343,7 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - err = efivar_init(efivarfs_callback, (void *)sb, true, - &sfi->efivarfs_list); - if (err) - efivar_entry_iter(efivarfs_destroy, &sfi->efivarfs_list, NULL); - - return err; + return efivar_init(efivarfs_callback, sb, &sfi->efivarfs_list); } static int efivarfs_get_tree(struct fs_context *fc) diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index 114ff0fd4e55..4d722af1014f 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -361,7 +361,6 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, * efivar_init - build the initial list of EFI variables * @func: callback function to invoke for every variable * @data: function-specific data to pass to @func - * @duplicates: error if we encounter duplicates on @head? * @head: initialised head of variable list * * Get every EFI variable from the firmware and invoke @func. @func @@ -371,9 +370,9 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, */ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, struct list_head *), - void *data, bool duplicates, struct list_head *head) + void *data, struct list_head *head) { - unsigned long variable_name_size = 1024; + unsigned long variable_name_size = 512; efi_char16_t *variable_name; efi_status_t status; efi_guid_t vendor_guid; @@ -390,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, goto free; /* - * Per EFI spec, the maximum storage allocated for both - * the variable name and variable data is 1024 bytes. + * A small set of old UEFI implementations reject sizes + * above a certain threshold, the lowest seen in the wild + * is 512. */ do { - variable_name_size = 1024; + variable_name_size = 512; status = efivar_get_next_variable(&variable_name_size, variable_name, @@ -413,8 +413,7 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, * we'll ever see a different variable name, * and may end up looping here forever. */ - if (duplicates && - variable_is_present(variable_name, &vendor_guid, + if (variable_is_present(variable_name, &vendor_guid, head)) { dup_variable_bug(variable_name, &vendor_guid, variable_name_size); @@ -432,9 +431,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *, break; case EFI_NOT_FOUND: break; + case EFI_BUFFER_TOO_SMALL: + pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n", + variable_name_size); + status = EFI_NOT_FOUND; + break; default: - printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n", - status); + pr_warn("efivars: get_next_variable: status=%lx\n", status); status = EFI_NOT_FOUND; break; } diff --git a/fs/exfat/file.c b/fs/exfat/file.c index d25a96a148af..cc00f1a7a1e1 100644 --- a/fs/exfat/file.c +++ b/fs/exfat/file.c @@ -35,13 +35,18 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) if (new_num_clusters == num_clusters) goto out; - exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags); - ret = exfat_find_last_cluster(sb, &clu, &last_clu); - if (ret) - return ret; + if (num_clusters) { + exfat_chain_set(&clu, ei->start_clu, num_clusters, ei->flags); + ret = exfat_find_last_cluster(sb, &clu, &last_clu); + if (ret) + return ret; + + clu.dir = last_clu + 1; + } else { + last_clu = EXFAT_EOF_CLUSTER; + clu.dir = EXFAT_EOF_CLUSTER; + } - clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ? - EXFAT_EOF_CLUSTER : last_clu + 1; clu.size = 0; clu.flags = ei->flags; @@ -51,17 +56,19 @@ static int exfat_cont_expand(struct inode *inode, loff_t size) return ret; /* Append new clusters to chain */ - if (clu.flags != ei->flags) { - exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters); - ei->flags = ALLOC_FAT_CHAIN; - } - if (clu.flags == ALLOC_FAT_CHAIN) - if (exfat_ent_set(sb, last_clu, clu.dir)) - goto free_clu; - - if (num_clusters == 0) + if (num_clusters) { + if (clu.flags != ei->flags) + if (exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters)) + goto free_clu; + + if (clu.flags == ALLOC_FAT_CHAIN) + if (exfat_ent_set(sb, last_clu, clu.dir)) + goto free_clu; + } else ei->start_clu = clu.dir; + ei->flags = clu.flags; + out: inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); /* Expanded range not zeroed, do not update valid_size */ diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 5a2512d20bd0..98401de832ee 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -350,7 +350,6 @@ xfs_setup_dax_always( return -EINVAL; } - xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); return 0; disable_dax: diff --git a/include/drm/bridge/aux-bridge.h b/include/drm/bridge/aux-bridge.h index c4c423e97f06..4453906105ca 100644 --- a/include/drm/bridge/aux-bridge.h +++ b/include/drm/bridge/aux-bridge.h @@ -9,6 +9,8 @@ #include <drm/drm_connector.h> +struct auxiliary_device; + #if IS_ENABLED(CONFIG_DRM_AUX_BRIDGE) int drm_aux_bridge_register(struct device *parent); #else @@ -19,10 +21,23 @@ static inline int drm_aux_bridge_register(struct device *parent) #endif #if IS_ENABLED(CONFIG_DRM_AUX_HPD_BRIDGE) +struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, struct device_node *np); +int devm_drm_dp_hpd_bridge_add(struct device *dev, struct auxiliary_device *adev); struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np); void drm_aux_hpd_bridge_notify(struct device *dev, enum drm_connector_status status); #else +static inline struct auxiliary_device *devm_drm_dp_hpd_bridge_alloc(struct device *parent, + struct device_node *np) +{ + return NULL; +} + +static inline int devm_drm_dp_hpd_bridge_add(struct auxiliary_device *adev) +{ + return 0; +} + static inline struct device *drm_dp_hpd_bridge_register(struct device *parent, struct device_node *np) { diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 555aae5448ae..bd1e361b351c 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -83,7 +83,7 @@ struct bvec_iter { unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ -} __packed; +} __packed __aligned(4); struct bvec_iter_all { struct bio_vec bv; diff --git a/include/linux/dpll.h b/include/linux/dpll.h index e3abde993244..d275736230b3 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -123,15 +123,24 @@ struct dpll_pin_properties { }; #if IS_ENABLED(CONFIG_DPLL) -size_t dpll_msg_pin_handle_size(struct dpll_pin *pin); -int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin); +void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); +void dpll_netdev_pin_clear(struct net_device *dev); + +size_t dpll_netdev_pin_handle_size(const struct net_device *dev); +int dpll_netdev_add_pin_handle(struct sk_buff *msg, + const struct net_device *dev); #else -static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) +static inline void +dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { } +static inline void dpll_netdev_pin_clear(struct net_device *dev) { } + +static inline size_t dpll_netdev_pin_handle_size(const struct net_device *dev) { return 0; } -static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +static inline int +dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev) { return 0; } @@ -170,13 +179,4 @@ int dpll_device_change_ntf(struct dpll_device *dpll); int dpll_pin_change_ntf(struct dpll_pin *pin); -#if !IS_ENABLED(CONFIG_DPLL) -static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) -{ - return NULL; -} -#else -struct dpll_pin *netdev_dpll_pin(const struct net_device *dev); -#endif - #endif diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h index 407c2f281b64..5693a4be0d9a 100644 --- a/include/linux/dynamic_queue_limits.h +++ b/include/linux/dynamic_queue_limits.h @@ -38,14 +38,22 @@ #ifdef __KERNEL__ +#include <linux/bitops.h> #include <asm/bug.h> +#define DQL_HIST_LEN 4 +#define DQL_HIST_ENT(dql, idx) ((dql)->history[(idx) % DQL_HIST_LEN]) + struct dql { /* Fields accessed in enqueue path (dql_queued) */ unsigned int num_queued; /* Total ever queued */ unsigned int adj_limit; /* limit + num_completed */ unsigned int last_obj_cnt; /* Count at last queuing */ + unsigned long history_head; /* top 58 bits of jiffies */ + /* stall entries, a bit per entry */ + unsigned long history[DQL_HIST_LEN]; + /* Fields accessed only by completion path (dql_completed) */ unsigned int limit ____cacheline_aligned_in_smp; /* Current limit */ @@ -62,6 +70,13 @@ struct dql { unsigned int max_limit; /* Max limit */ unsigned int min_limit; /* Minimum limit */ unsigned int slack_hold_time; /* Time to measure slack */ + + /* Stall threshold (in jiffies), defined by user */ + unsigned short stall_thrs; + /* Longest stall detected, reported to user */ + unsigned short stall_max; + unsigned long last_reap; /* Last reap (in jiffies) */ + unsigned long stall_cnt; /* Number of stalls */ }; /* Set some static maximums */ @@ -74,6 +89,8 @@ struct dql { */ static inline void dql_queued(struct dql *dql, unsigned int count) { + unsigned long map, now, now_hi, i; + BUG_ON(count > DQL_MAX_OBJECT); dql->last_obj_cnt = count; @@ -86,6 +103,34 @@ static inline void dql_queued(struct dql *dql, unsigned int count) barrier(); dql->num_queued += count; + + now = jiffies; + now_hi = now / BITS_PER_LONG; + + /* The following code set a bit in the ring buffer, where each + * bit trackes time the packet was queued. The dql->history buffer + * tracks DQL_HIST_LEN * BITS_PER_LONG time (jiffies) slot + */ + if (unlikely(now_hi != dql->history_head)) { + /* About to reuse slots, clear them */ + for (i = 0; i < DQL_HIST_LEN; i++) { + /* Multiplication masks high bits */ + if (now_hi * BITS_PER_LONG == + (dql->history_head + i) * BITS_PER_LONG) + break; + DQL_HIST_ENT(dql, dql->history_head + i + 1) = 0; + } + /* pairs with smp_rmb() in dql_check_stall() */ + smp_wmb(); + WRITE_ONCE(dql->history_head, now_hi); + } + + /* __set_bit() does not guarantee WRITE_ONCE() semantics */ + map = DQL_HIST_ENT(dql, now_hi); + + /* Populate the history with an entry (bit) per queued */ + if (!(map & BIT_MASK(now))) + WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now)); } /* Returns how many objects can be queued, < 0 indicates over limit. */ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 2b00faf98017..6ef0557b4bff 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -164,8 +164,28 @@ struct hv_ring_buffer { u8 buffer[]; } __packed; + +/* + * If the requested ring buffer size is at least 8 times the size of the + * header, steal space from the ring buffer for the header. Otherwise, add + * space for the header so that is doesn't take too much of the ring buffer + * space. + * + * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a + * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring + * buffer size (such as 128 Kbytes) and so end up making a nearly twice as + * large allocation that will be almost half wasted. As a contrasting example, + * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the + * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring. + * In this latter case, we must add 64 Kbytes for the header and not worry + * about what's wasted. + */ +#define VMBUS_HEADER_ADJ(payload_sz) \ + ((payload_sz) >= 8 * sizeof(struct hv_ring_buffer) ? \ + 0 : sizeof(struct hv_ring_buffer)) + /* Calculate the proper size of a ringbuffer, it must be page-aligned */ -#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \ +#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \ (payload_sz)) struct hv_ring_buffer_info { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 628a3aa7a7e0..3a8a9e57a51d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10261,7 +10261,9 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_63_to_46[0x12]; u8 mrtc[0x1]; - u8 regs_44_to_32[0xd]; + u8 regs_44_to_41[0x4]; + u8 mfrl[0x1]; + u8 regs_39_to_32[0x8]; u8 regs_31_to_10[0x16]; u8 mtmp[0x1]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c41019f34179..4230c7f3b959 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -79,8 +79,6 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; -/* DPLL specific */ -struct dpll_pin; typedef u32 xdp_features_t; @@ -227,12 +225,6 @@ struct net_device_core_stats { #include <linux/cache.h> #include <linux/skbuff.h> -#ifdef CONFIG_RPS -#include <linux/static_key.h> -extern struct static_key_false rps_needed; -extern struct static_key_false rfs_needed; -#endif - struct neighbour; struct neigh_parms; struct sk_buff; @@ -732,86 +724,10 @@ static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node #endif } -#ifdef CONFIG_RPS -/* - * This structure holds an RPS map which can be of variable length. The - * map is an array of CPUs. - */ -struct rps_map { - unsigned int len; - struct rcu_head rcu; - u16 cpus[]; -}; -#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) - -/* - * The rps_dev_flow structure contains the mapping of a flow to a CPU, the - * tail pointer for that CPU's input queue at the time of last enqueue, and - * a hardware filter index. - */ -struct rps_dev_flow { - u16 cpu; - u16 filter; - unsigned int last_qtail; -}; -#define RPS_NO_FILTER 0xffff - -/* - * The rps_dev_flow_table structure contains a table of flow mappings. - */ -struct rps_dev_flow_table { - unsigned int mask; - struct rcu_head rcu; - struct rps_dev_flow flows[]; -}; -#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ - ((_num) * sizeof(struct rps_dev_flow))) - -/* - * The rps_sock_flow_table contains mappings of flows to the last CPU - * on which they were processed by the application (set in recvmsg). - * Each entry is a 32bit value. Upper part is the high-order bits - * of flow hash, lower part is CPU number. - * rps_cpu_mask is used to partition the space, depending on number of - * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 - * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, - * meaning we use 32-6=26 bits for the hash. - */ -struct rps_sock_flow_table { - u32 mask; - - u32 ents[] ____cacheline_aligned_in_smp; -}; -#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) - -#define RPS_NO_CPU 0xffff - -extern u32 rps_cpu_mask; -extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; - -static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, - u32 hash) -{ - if (table && hash) { - unsigned int index = hash & table->mask; - u32 val = hash & ~rps_cpu_mask; - - /* We only give a hint, preemption can change CPU under us */ - val |= raw_smp_processor_id(); - - /* The following WRITE_ONCE() is paired with the READ_ONCE() - * here, and another one in get_rps_cpu(). - */ - if (READ_ONCE(table->ents[index]) != val) - WRITE_ONCE(table->ents[index], val); - } -} - #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif -#endif /* CONFIG_RPS */ /* XPS map type and offset of the xps map within net_device->xps_maps[]. */ enum xps_map_type { @@ -2039,6 +1955,7 @@ enum netdev_reg_state { * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops + * @stat_ops: Optional ops for queue-aware statistics * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size @@ -2419,6 +2336,8 @@ struct net_device { const struct rtnl_link_ops *rtnl_link_ops; + const struct netdev_stat_ops *stat_ops; + /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u @@ -3500,6 +3419,16 @@ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue #endif } +static inline int netdev_queue_dql_avail(const struct netdev_queue *txq) +{ +#ifdef CONFIG_BQL + /* Non-BQL migrated drivers will return 0, too. */ + return dql_avail(&txq->dql); +#else + return 0; +#endif +} + /** * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue @@ -4033,8 +3962,6 @@ 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); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); -void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); -void netdev_dpll_pin_clear(struct net_device *dev); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -4787,11 +4714,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); -extern int netdev_max_backlog; -extern int dev_rx_weight; -extern int dev_tx_weight; -extern int gro_normal_batch; - enum { NESTED_SYNC_IMM_BIT, NESTED_SYNC_TODO_BIT, @@ -5301,7 +5223,6 @@ static inline const char *netdev_reg_state(const struct net_device *dev) #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) -extern struct list_head ptype_all __read_mostly; extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; extern struct net_device *blackhole_netdev; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 6ba411732a0d..9a57deefcb07 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -480,9 +480,6 @@ void pcs_disable(struct phylink_pcs *pcs); * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. - * - * When present, this overrides pcs_get_state() in &struct - * phylink_pcs_ops. */ void pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3013355b63f5..d0508f90bed5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1271,7 +1271,6 @@ static inline void consume_skb(struct sk_buff *skb) void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); -extern struct kmem_cache *skbuff_cache; void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, diff --git a/include/linux/uio.h b/include/linux/uio.h index bea9c89922d9..00cebe2b70de 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -40,7 +40,6 @@ struct iov_iter_state { struct iov_iter { u8 iter_type; - bool copy_mc; bool nofault; bool data_source; size_t iov_offset; @@ -248,22 +247,8 @@ size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i); #ifdef CONFIG_ARCH_HAS_COPY_MC size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); -static inline void iov_iter_set_copy_mc(struct iov_iter *i) -{ - i->copy_mc = true; -} - -static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) -{ - return i->copy_mc; -} #else #define _copy_mc_to_iter _copy_to_iter -static inline void iov_iter_set_copy_mc(struct iov_iter *i) { } -static inline bool iov_iter_is_copy_mc(const struct iov_iter *i) -{ - return false; -} #endif size_t iov_iter_zero(size_t bytes, struct iov_iter *); @@ -355,7 +340,6 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_UBUF, - .copy_mc = false, .data_source = direction, .ubuf = buf, .count = count, diff --git a/include/net/gro.h b/include/net/gro.h index 2b58671a6549..d6fc8fbd3730 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -9,6 +9,7 @@ #include <net/ip6_checksum.h> #include <linux/skbuff.h> #include <net/udp.h> +#include <net/hotdata.h> struct napi_gro_cb { union { @@ -446,7 +447,7 @@ static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, { list_add_tail(&skb->list, &napi->rx_list); napi->rx_count += segs; - if (napi->rx_count >= READ_ONCE(gro_normal_batch)) + if (napi->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch)) gro_normal_list(napi); } @@ -493,6 +494,4 @@ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int * #endif } -extern struct list_head offload_base; - #endif /* _NET_IPV6_GRO_H */ diff --git a/include/net/hotdata.h b/include/net/hotdata.h new file mode 100644 index 000000000000..003667a1efd6 --- /dev/null +++ b/include/net/hotdata.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_HOTDATA_H +#define _NET_HOTDATA_H + +#include <linux/types.h> +#include <linux/netdevice.h> +#include <net/protocol.h> + +/* Read mostly data used in network fast paths. */ +struct net_hotdata { +#if IS_ENABLED(CONFIG_INET) + struct packet_offload ip_packet_offload; + struct net_offload tcpv4_offload; + struct net_protocol tcp_protocol; + struct net_offload udpv4_offload; + struct net_protocol udp_protocol; + struct packet_offload ipv6_packet_offload; + struct net_offload tcpv6_offload; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_protocol tcpv6_protocol; + struct inet6_protocol udpv6_protocol; +#endif + struct net_offload udpv6_offload; +#endif + struct list_head offload_base; + struct list_head ptype_all; + struct kmem_cache *skbuff_cache; + struct kmem_cache *skbuff_fclone_cache; + struct kmem_cache *skb_small_head_cache; +#ifdef CONFIG_RPS + struct rps_sock_flow_table __rcu *rps_sock_flow_table; + u32 rps_cpu_mask; +#endif + int gro_normal_batch; + int netdev_budget; + int netdev_budget_usecs; + int tstamp_prequeue; + int max_backlog; + int dev_tx_weight; + int dev_rx_weight; +}; + +#define inet_ehash_secret net_hotdata.tcp_protocol.secret +#define udp_ehash_secret net_hotdata.udp_protocol.secret +#define inet6_ehash_secret net_hotdata.tcpv6_protocol.secret +#define tcp_ipv6_hash_secret net_hotdata.tcpv6_offload.secret +#define udp6_ehash_secret net_hotdata.udpv6_protocol.secret +#define udp_ipv6_hash_secret net_hotdata.udpv6_offload.secret + +extern struct net_hotdata net_hotdata; + +#endif /* _NET_HOTDATA_H */ diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h index 8b8ed4e13d74..1ec408585373 100644 --- a/include/net/netdev_queues.h +++ b/include/net/netdev_queues.h @@ -4,6 +4,62 @@ #include <linux/netdevice.h> +/* See the netdev.yaml spec for definition of each statistic */ +struct netdev_queue_stats_rx { + u64 bytes; + u64 packets; + u64 alloc_fail; +}; + +struct netdev_queue_stats_tx { + u64 bytes; + u64 packets; +}; + +/** + * struct netdev_stat_ops - netdev ops for fine grained stats + * @get_queue_stats_rx: get stats for a given Rx queue + * @get_queue_stats_tx: get stats for a given Tx queue + * @get_base_stats: get base stats (not belonging to any live instance) + * + * Query stats for a given object. The values of the statistics are undefined + * on entry (specifically they are *not* zero-initialized). Drivers should + * assign values only to the statistics they collect. Statistics which are not + * collected must be left undefined. + * + * Queue objects are not necessarily persistent, and only currently active + * queues are queried by the per-queue callbacks. This means that per-queue + * statistics will not generally add up to the total number of events for + * the device. The @get_base_stats callback allows filling in the delta + * between events for currently live queues and overall device history. + * When the statistics for the entire device are queried, first @get_base_stats + * is issued to collect the delta, and then a series of per-queue callbacks. + * Only statistics which are set in @get_base_stats will be reported + * at the device level, meaning that unlike in queue callbacks, setting + * a statistic to zero in @get_base_stats is a legitimate thing to do. + * This is because @get_base_stats has a second function of designating which + * statistics are in fact correct for the entire device (e.g. when history + * for some of the events is not maintained, and reliable "total" cannot + * be provided). + * + * Device drivers can assume that when collecting total device stats, + * the @get_base_stats and subsequent per-queue calls are performed + * "atomically" (without releasing the rtnl_lock). + * + * Device drivers are encouraged to reset the per-queue statistics when + * number of queues change. This is because the primary use case for + * per-queue statistics is currently to detect traffic imbalance. + */ +struct netdev_stat_ops { + void (*get_queue_stats_rx)(struct net_device *dev, int idx, + struct netdev_queue_stats_rx *stats); + void (*get_queue_stats_tx)(struct net_device *dev, int idx, + struct netdev_queue_stats_tx *stats); + void (*get_base_stats)(struct net_device *dev, + struct netdev_queue_stats_rx *rx, + struct netdev_queue_stats_tx *tx); +}; + /** * DOC: Lockless queue stopping / waking helpers. * diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 77e99cba60ad..7ec9cc80f11c 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -47,6 +47,8 @@ struct nh_config { bool nh_grp_res_has_idle_timer; bool nh_grp_res_has_unbalanced_timer; + bool nh_hw_stats; + struct nlattr *nh_encap; u16 nh_encap_type; @@ -95,8 +97,14 @@ struct nh_res_table { struct nh_res_bucket nh_buckets[] __counted_by(num_nh_buckets); }; +struct nh_grp_entry_stats { + u64_stats_t packets; + struct u64_stats_sync syncp; +}; + struct nh_grp_entry { struct nexthop *nh; + struct nh_grp_entry_stats __percpu *stats; u8 weight; union { @@ -114,6 +122,7 @@ struct nh_grp_entry { struct list_head nh_list; struct nexthop *nh_parent; /* nexthop of group with this entry */ + u64 packets_hw; }; struct nh_group { @@ -124,6 +133,7 @@ struct nh_group { bool resilient; bool fdb_nh; bool has_v4; + bool hw_stats; struct nh_res_table __rcu *res_table; struct nh_grp_entry nh_entries[] __counted_by(num_nh); @@ -157,6 +167,7 @@ enum nexthop_event_type { NEXTHOP_EVENT_REPLACE, NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE, NEXTHOP_EVENT_BUCKET_REPLACE, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, }; enum nh_notifier_info_type { @@ -164,6 +175,7 @@ enum nh_notifier_info_type { NH_NOTIFIER_INFO_TYPE_GRP, NH_NOTIFIER_INFO_TYPE_RES_TABLE, NH_NOTIFIER_INFO_TYPE_RES_BUCKET, + NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS, }; struct nh_notifier_single_info { @@ -187,6 +199,7 @@ struct nh_notifier_grp_entry_info { struct nh_notifier_grp_info { u16 num_nh; bool is_fdb; + bool hw_stats; struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh); }; @@ -200,9 +213,21 @@ struct nh_notifier_res_bucket_info { struct nh_notifier_res_table_info { u16 num_nh_buckets; + bool hw_stats; struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets); }; +struct nh_notifier_grp_hw_stats_entry_info { + u32 id; + u64 packets; +}; + +struct nh_notifier_grp_hw_stats_info { + u16 num_nh; + bool hw_stats_used; + struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh); +}; + struct nh_notifier_info { struct net *net; struct netlink_ext_ack *extack; @@ -213,6 +238,7 @@ struct nh_notifier_info { struct nh_notifier_grp_info *nh_grp; struct nh_notifier_res_table_info *nh_res_table; struct nh_notifier_res_bucket_info *nh_res_bucket; + struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats; }; }; @@ -225,6 +251,9 @@ void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index, bool offload, bool trap); void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets, unsigned long *activity); +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); diff --git a/include/net/protocol.h b/include/net/protocol.h index 6aef8cb11cc8..b2499f88f8f8 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -46,6 +46,7 @@ struct net_protocol { * socket lookup? */ icmp_strict_tag_validation:1; + u32 secret; }; #if IS_ENABLED(CONFIG_IPV6) @@ -59,6 +60,7 @@ struct inet6_protocol { __be32 info); unsigned int flags; /* INET6_PROTO_xxx */ + u32 secret; }; #define INET6_PROTO_NOPOLICY 0x1 @@ -68,6 +70,7 @@ struct inet6_protocol { struct net_offload { struct offload_callbacks callbacks; unsigned int flags; /* Flags used by IPv6 for now */ + u32 secret; }; /* This should be set for any extension header which is compatible with GSO. */ #define INET6_PROTO_GSO_EXTHDR 0x1 diff --git a/include/net/rps.h b/include/net/rps.h new file mode 100644 index 000000000000..7660243e905b --- /dev/null +++ b/include/net/rps.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _NET_RPS_H +#define _NET_RPS_H + +#include <linux/types.h> +#include <linux/static_key.h> +#include <net/sock.h> +#include <net/hotdata.h> + +#ifdef CONFIG_RPS + +extern struct static_key_false rps_needed; +extern struct static_key_false rfs_needed; + +/* + * This structure holds an RPS map which can be of variable length. The + * map is an array of CPUs. + */ +struct rps_map { + unsigned int len; + struct rcu_head rcu; + u16 cpus[]; +}; +#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16))) + +/* + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. + */ +struct rps_dev_flow { + u16 cpu; + u16 filter; + unsigned int last_qtail; +}; +#define RPS_NO_FILTER 0xffff + +/* + * The rps_dev_flow_table structure contains a table of flow mappings. + */ +struct rps_dev_flow_table { + unsigned int mask; + struct rcu_head rcu; + struct rps_dev_flow flows[]; +}; +#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \ + ((_num) * sizeof(struct rps_dev_flow))) + +/* + * The rps_sock_flow_table contains mappings of flows to the last CPU + * on which they were processed by the application (set in recvmsg). + * Each entry is a 32bit value. Upper part is the high-order bits + * of flow hash, lower part is CPU number. + * rps_cpu_mask is used to partition the space, depending on number of + * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1 + * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f, + * meaning we use 32-6=26 bits for the hash. + */ +struct rps_sock_flow_table { + u32 mask; + + u32 ents[] ____cacheline_aligned_in_smp; +}; +#define RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num])) + +#define RPS_NO_CPU 0xffff + +static inline void rps_record_sock_flow(struct rps_sock_flow_table *table, + u32 hash) +{ + unsigned int index = hash & table->mask; + u32 val = hash & ~net_hotdata.rps_cpu_mask; + + /* We only give a hint, preemption can change CPU under us */ + val |= raw_smp_processor_id(); + + /* The following WRITE_ONCE() is paired with the READ_ONCE() + * here, and another one in get_rps_cpu(). + */ + if (READ_ONCE(table->ents[index]) != val) + WRITE_ONCE(table->ents[index], val); +} + +#endif /* CONFIG_RPS */ + +static inline void sock_rps_record_flow_hash(__u32 hash) +{ +#ifdef CONFIG_RPS + struct rps_sock_flow_table *sock_flow_table; + + if (!hash) + return; + rcu_read_lock(); + sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); + if (sock_flow_table) + rps_record_sock_flow(sock_flow_table, hash); + rcu_read_unlock(); +#endif +} + +static inline void sock_rps_record_flow(const struct sock *sk) +{ +#ifdef CONFIG_RPS + if (static_branch_unlikely(&rfs_needed)) { + /* Reading sk->sk_rxhash might incur an expensive cache line + * miss. + * + * TCP_ESTABLISHED does cover almost all states where RFS + * might be useful, and is cheaper [1] than testing : + * IPv4: inet_sk(sk)->inet_daddr + * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) + * OR an additional socket flag + * [1] : sk_state and sk_prot are in the same cache line. + */ + if (sk->sk_state == TCP_ESTABLISHED) { + /* This READ_ONCE() is paired with the WRITE_ONCE() + * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). + */ + sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); + } + } +#endif +} + +#endif /* _NET_RPS_H */ diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 934fdb977551..cefe0c4bdae3 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -238,12 +238,7 @@ static inline bool qdisc_may_bulk(const struct Qdisc *qdisc) static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) { -#ifdef CONFIG_BQL - /* Non-BQL migrated drivers will return 0, too. */ - return dql_avail(&txq->dql); -#else - return 0; -#endif + return netdev_queue_dql_avail(txq); } struct Qdisc_class_ops { diff --git a/include/net/sock.h b/include/net/sock.h index 09a0cde8bf52..b5e00702acc1 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1117,41 +1117,6 @@ static inline void sk_incoming_cpu_update(struct sock *sk) WRITE_ONCE(sk->sk_incoming_cpu, cpu); } -static inline void sock_rps_record_flow_hash(__u32 hash) -{ -#ifdef CONFIG_RPS - struct rps_sock_flow_table *sock_flow_table; - - rcu_read_lock(); - sock_flow_table = rcu_dereference(rps_sock_flow_table); - rps_record_sock_flow(sock_flow_table, hash); - rcu_read_unlock(); -#endif -} - -static inline void sock_rps_record_flow(const struct sock *sk) -{ -#ifdef CONFIG_RPS - if (static_branch_unlikely(&rfs_needed)) { - /* Reading sk->sk_rxhash might incur an expensive cache line - * miss. - * - * TCP_ESTABLISHED does cover almost all states where RFS - * might be useful, and is cheaper [1] than testing : - * IPv4: inet_sk(sk)->inet_daddr - * IPv6: ipv6_addr_any(&sk->sk_v6_daddr) - * OR an additional socket flag - * [1] : sk_state and sk_prot are in the same cache line. - */ - if (sk->sk_state == TCP_ESTABLISHED) { - /* This READ_ONCE() is paired with the WRITE_ONCE() - * from sock_rps_save_rxhash() and sock_rps_reset_rxhash(). - */ - sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash)); - } - } -#endif -} static inline void sock_rps_save_rxhash(struct sock *sk, const struct sk_buff *skb) diff --git a/include/sound/soc-card.h b/include/sound/soc-card.h index ecc02e955279..1f4c39922d82 100644 --- a/include/sound/soc-card.h +++ b/include/sound/soc-card.h @@ -30,6 +30,8 @@ static inline void snd_soc_card_mutex_unlock(struct snd_soc_card *card) struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, const char *name); +struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card, + const char *name); int snd_soc_card_jack_new(struct snd_soc_card *card, const char *id, int type, struct snd_soc_jack *jack); int snd_soc_card_jack_new_pins(struct snd_soc_card *card, const char *id, diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h index 6678cf8b235b..dc03cf8e0369 100644 --- a/include/trace/events/napi.h +++ b/include/trace/events/napi.h @@ -36,6 +36,39 @@ TRACE_EVENT(napi_poll, __entry->work, __entry->budget) ); +TRACE_EVENT(dql_stall_detected, + + TP_PROTO(unsigned short thrs, unsigned int len, + unsigned long last_reap, unsigned long hist_head, + unsigned long now, unsigned long *hist), + + TP_ARGS(thrs, len, last_reap, hist_head, now, hist), + + TP_STRUCT__entry( + __field( unsigned short, thrs) + __field( unsigned int, len) + __field( unsigned long, last_reap) + __field( unsigned long, hist_head) + __field( unsigned long, now) + __array( unsigned long, hist, 4) + ), + + TP_fast_assign( + __entry->thrs = thrs; + __entry->len = len; + __entry->last_reap = last_reap; + __entry->hist_head = hist_head * BITS_PER_LONG; + __entry->now = now; + memcpy(__entry->hist, hist, sizeof(entry->hist)); + ), + + TP_printk("thrs %u len %u last_reap %lu hist_head %lu now %lu hist %016lx %016lx %016lx %016lx", + __entry->thrs, __entry->len, + __entry->last_reap, __entry->hist_head, __entry->now, + __entry->hist[0], __entry->hist[1], + __entry->hist[2], __entry->hist[3]) +); + #undef NO_DEV #endif /* _TRACE_NAPI_H */ diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h index a3995925cb05..1f4258308b96 100644 --- a/include/trace/events/qdisc.h +++ b/include/trace/events/qdisc.h @@ -81,14 +81,14 @@ TRACE_EVENT(qdisc_reset, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; @@ -106,14 +106,14 @@ TRACE_EVENT(qdisc_destroy, TP_ARGS(q), TP_STRUCT__entry( - __string( dev, qdisc_dev(q) ) - __string( kind, q->ops->id ) - __field( u32, parent ) - __field( u32, handle ) + __string( dev, qdisc_dev(q)->name ) + __string( kind, q->ops->id ) + __field( u32, parent ) + __field( u32, handle ) ), TP_fast_assign( - __assign_str(dev, qdisc_dev(q)); + __assign_str(dev, qdisc_dev(q)->name); __assign_str(kind, q->ops->id); __entry->parent = q->parent; __entry->handle = q->handle; diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 87b8de9b6c1c..a1b126a6b0d7 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -83,7 +83,7 @@ EM(rxrpc_badmsg_bad_abort, "bad-abort") \ EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \ EM(rxrpc_badmsg_short_ack, "short-ack") \ - EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \ + EM(rxrpc_badmsg_short_ack_trailer, "short-ack-trailer") \ EM(rxrpc_badmsg_short_hdr, "short-hdr") \ EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \ EM(rxrpc_badmsg_zero_call, "zero-call") \ @@ -119,6 +119,7 @@ EM(rxrpc_call_poke_complete, "Compl") \ EM(rxrpc_call_poke_error, "Error") \ EM(rxrpc_call_poke_idle, "Idle") \ + EM(rxrpc_call_poke_set_timeout, "Set-timo") \ EM(rxrpc_call_poke_start, "Start") \ EM(rxrpc_call_poke_timer, "Timer") \ E_(rxrpc_call_poke_timer_now, "Timer-now") @@ -340,35 +341,26 @@ E_(rxrpc_rtt_rx_requested_ack, "RACK") #define rxrpc_timer_traces \ - EM(rxrpc_timer_begin, "Begin ") \ - EM(rxrpc_timer_exp_ack, "ExpAck") \ - EM(rxrpc_timer_exp_hard, "ExpHrd") \ - EM(rxrpc_timer_exp_idle, "ExpIdl") \ - EM(rxrpc_timer_exp_keepalive, "ExpKA ") \ - EM(rxrpc_timer_exp_lost_ack, "ExpLoA") \ - EM(rxrpc_timer_exp_normal, "ExpNml") \ - EM(rxrpc_timer_exp_ping, "ExpPng") \ - EM(rxrpc_timer_exp_resend, "ExpRsn") \ - EM(rxrpc_timer_init_for_reply, "IniRpl") \ - EM(rxrpc_timer_init_for_send_reply, "SndRpl") \ - EM(rxrpc_timer_restart, "Restrt") \ - EM(rxrpc_timer_set_for_ack, "SetAck") \ - EM(rxrpc_timer_set_for_hard, "SetHrd") \ - EM(rxrpc_timer_set_for_idle, "SetIdl") \ - EM(rxrpc_timer_set_for_keepalive, "KeepAl") \ - EM(rxrpc_timer_set_for_lost_ack, "SetLoA") \ - EM(rxrpc_timer_set_for_normal, "SetNml") \ - EM(rxrpc_timer_set_for_ping, "SetPng") \ - EM(rxrpc_timer_set_for_resend, "SetRTx") \ - E_(rxrpc_timer_set_for_send, "SetSnd") + EM(rxrpc_timer_trace_delayed_ack, "DelayAck ") \ + EM(rxrpc_timer_trace_expect_rx, "ExpectRx ") \ + EM(rxrpc_timer_trace_hard, "HardLimit") \ + EM(rxrpc_timer_trace_idle, "IdleLimit") \ + EM(rxrpc_timer_trace_keepalive, "KeepAlive") \ + EM(rxrpc_timer_trace_lost_ack, "LostAck ") \ + EM(rxrpc_timer_trace_ping, "DelayPing") \ + EM(rxrpc_timer_trace_resend, "Resend ") \ + EM(rxrpc_timer_trace_resend_reset, "ResendRst") \ + E_(rxrpc_timer_trace_resend_tx, "ResendTx ") #define rxrpc_propose_ack_traces \ EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \ + EM(rxrpc_propose_ack_delayed_ack, "DlydAck") \ EM(rxrpc_propose_ack_input_data, "DataIn ") \ EM(rxrpc_propose_ack_input_data_hole, "DataInH") \ EM(rxrpc_propose_ack_ping_for_keepalive, "KeepAlv") \ EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \ EM(rxrpc_propose_ack_ping_for_lost_reply, "LostRpl") \ + EM(rxrpc_propose_ack_ping_for_0_retrans, "0-Retrn") \ EM(rxrpc_propose_ack_ping_for_old_rtt, "OldRtt ") \ EM(rxrpc_propose_ack_ping_for_params, "Params ") \ EM(rxrpc_propose_ack_ping_for_rtt, "Rtt ") \ @@ -1084,9 +1076,9 @@ TRACE_EVENT(rxrpc_tx_packet, TRACE_EVENT(rxrpc_tx_data, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, - rxrpc_serial_t serial, u8 flags, bool retrans, bool lose), + rxrpc_serial_t serial, unsigned int flags, bool lose), - TP_ARGS(call, seq, serial, flags, retrans, lose), + TP_ARGS(call, seq, serial, flags, lose), TP_STRUCT__entry( __field(unsigned int, call) @@ -1094,8 +1086,7 @@ TRACE_EVENT(rxrpc_tx_data, __field(rxrpc_serial_t, serial) __field(u32, cid) __field(u32, call_id) - __field(u8, flags) - __field(bool, retrans) + __field(u16, flags) __field(bool, lose) ), @@ -1106,7 +1097,6 @@ TRACE_EVENT(rxrpc_tx_data, __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; - __entry->retrans = retrans; __entry->lose = lose; ), @@ -1116,8 +1106,8 @@ TRACE_EVENT(rxrpc_tx_data, __entry->call_id, __entry->serial, __entry->seq, - __entry->flags, - __entry->retrans ? " *RETRANS*" : "", + __entry->flags & RXRPC_TXBUF_WIRE_FLAGS, + __entry->flags & RXRPC_TXBUF_RESENT ? " *RETRANS*" : "", __entry->lose ? " *LOSE*" : "") ); @@ -1314,90 +1304,112 @@ TRACE_EVENT(rxrpc_rtt_rx, __entry->rto) ); -TRACE_EVENT(rxrpc_timer, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_timer_trace why, - unsigned long now), +TRACE_EVENT(rxrpc_timer_set, + TP_PROTO(struct rxrpc_call *call, ktime_t delay, + enum rxrpc_timer_trace why), - TP_ARGS(call, why, now), + TP_ARGS(call, delay, why), TP_STRUCT__entry( __field(unsigned int, call) __field(enum rxrpc_timer_trace, why) - __field(long, now) - __field(long, ack_at) - __field(long, ack_lost_at) - __field(long, resend_at) - __field(long, ping_at) - __field(long, expect_rx_by) - __field(long, expect_req_by) - __field(long, expect_term_by) - __field(long, timer) + __field(ktime_t, delay) ), TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; - __entry->now = now; - __entry->ack_at = call->delay_ack_at; - __entry->ack_lost_at = call->ack_lost_at; - __entry->resend_at = call->resend_at; - __entry->expect_rx_by = call->expect_rx_by; - __entry->expect_req_by = call->expect_req_by; - __entry->expect_term_by = call->expect_term_by; - __entry->timer = call->timer.expires; + __entry->delay = delay; ), - TP_printk("c=%08x %s a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld", + TP_printk("c=%08x %s to=%lld", __entry->call, __print_symbolic(__entry->why, rxrpc_timer_traces), - __entry->ack_at - __entry->now, - __entry->ack_lost_at - __entry->now, - __entry->resend_at - __entry->now, - __entry->expect_rx_by - __entry->now, - __entry->expect_req_by - __entry->now, - __entry->expect_term_by - __entry->now, - __entry->timer - __entry->now) + ktime_to_us(__entry->delay)) + ); + +TRACE_EVENT(rxrpc_timer_exp, + TP_PROTO(struct rxrpc_call *call, ktime_t delay, + enum rxrpc_timer_trace why), + + TP_ARGS(call, delay, why), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(enum rxrpc_timer_trace, why) + __field(ktime_t, delay) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->delay = delay; + ), + + TP_printk("c=%08x %s to=%lld", + __entry->call, + __print_symbolic(__entry->why, rxrpc_timer_traces), + ktime_to_us(__entry->delay)) + ); + +TRACE_EVENT(rxrpc_timer_can, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_timer_trace why), + + TP_ARGS(call, why), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(enum rxrpc_timer_trace, why) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + ), + + TP_printk("c=%08x %s", + __entry->call, + __print_symbolic(__entry->why, rxrpc_timer_traces)) + ); + +TRACE_EVENT(rxrpc_timer_restart, + TP_PROTO(struct rxrpc_call *call, ktime_t delay, unsigned long delayj), + + TP_ARGS(call, delay, delayj), + + TP_STRUCT__entry( + __field(unsigned int, call) + __field(unsigned long, delayj) + __field(ktime_t, delay) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->delayj = delayj; + __entry->delay = delay; + ), + + TP_printk("c=%08x to=%lld j=%ld", + __entry->call, + ktime_to_us(__entry->delay), + __entry->delayj) ); TRACE_EVENT(rxrpc_timer_expired, - TP_PROTO(struct rxrpc_call *call, unsigned long now), + TP_PROTO(struct rxrpc_call *call), - TP_ARGS(call, now), + TP_ARGS(call), TP_STRUCT__entry( __field(unsigned int, call) - __field(long, now) - __field(long, ack_at) - __field(long, ack_lost_at) - __field(long, resend_at) - __field(long, ping_at) - __field(long, expect_rx_by) - __field(long, expect_req_by) - __field(long, expect_term_by) - __field(long, timer) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->now = now; - __entry->ack_at = call->delay_ack_at; - __entry->ack_lost_at = call->ack_lost_at; - __entry->resend_at = call->resend_at; - __entry->expect_rx_by = call->expect_rx_by; - __entry->expect_req_by = call->expect_req_by; - __entry->expect_term_by = call->expect_term_by; - __entry->timer = call->timer.expires; ), - TP_printk("c=%08x EXPIRED a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld", - __entry->call, - __entry->ack_at - __entry->now, - __entry->ack_lost_at - __entry->now, - __entry->resend_at - __entry->now, - __entry->expect_rx_by - __entry->now, - __entry->expect_req_by - __entry->now, - __entry->expect_term_by - __entry->now, - __entry->timer - __entry->now) + TP_printk("c=%08x EXPIRED", + __entry->call) ); TRACE_EVENT(rxrpc_rx_lose, @@ -1506,26 +1518,30 @@ TRACE_EVENT(rxrpc_drop_ack, ); TRACE_EVENT(rxrpc_retransmit, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, s64 expiry), + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, + rxrpc_serial_t serial, ktime_t expiry), - TP_ARGS(call, seq, expiry), + TP_ARGS(call, seq, serial, expiry), TP_STRUCT__entry( __field(unsigned int, call) __field(rxrpc_seq_t, seq) - __field(s64, expiry) + __field(rxrpc_serial_t, serial) + __field(ktime_t, expiry) ), TP_fast_assign( __entry->call = call->debug_id; __entry->seq = seq; + __entry->serial = serial; __entry->expiry = expiry; ), - TP_printk("c=%08x q=%x xp=%lld", + TP_printk("c=%08x q=%x r=%x xp=%lld", __entry->call, __entry->seq, - __entry->expiry) + __entry->serial, + ktime_to_us(__entry->expiry)) ); TRACE_EVENT(rxrpc_congest, diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 7b1ddffa3dfc..699dafd204ea 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -88,7 +88,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), - TP_printk("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", + __entry->skbaddr, __entry->skaddr, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, @@ -258,6 +259,8 @@ TRACE_EVENT(tcp_probe, __field(__u32, srtt) __field(__u32, rcv_wnd) __field(__u64, sock_cookie) + __field(const void *, skbaddr) + __field(const void *, skaddr) ), TP_fast_assign( @@ -285,14 +288,18 @@ TRACE_EVENT(tcp_probe, __entry->ssthresh = tcp_current_ssthresh(sk); __entry->srtt = tp->srtt_us >> 3; __entry->sock_cookie = sock_gen_cookie(sk); + + __entry->skbaddr = skb; + __entry->skaddr = sk; ), - TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx", + TP_printk("family=%s src=%pISpc dest=%pISpc mark=%#x data_len=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx skbaddr=%p skaddr=%p", show_family_name(__entry->family), __entry->saddr, __entry->daddr, __entry->mark, __entry->data_len, __entry->snd_nxt, __entry->snd_una, __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, - __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie) + __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie, + __entry->skbaddr, __entry->skaddr) ); #define TP_STORE_ADDR_PORTS_SKB_V4(__entry, skb) \ @@ -361,7 +368,8 @@ DECLARE_EVENT_CLASS(tcp_event_skb, TP_STORE_ADDR_PORTS_SKB(__entry, skb); ), - TP_printk("src=%pISpc dest=%pISpc", __entry->saddr, __entry->daddr) + TP_printk("skbaddr=%p src=%pISpc dest=%pISpc", + __entry->skbaddr, __entry->saddr, __entry->daddr) ); DEFINE_EVENT(tcp_event_skb, tcp_bad_csum, diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 6d11ee9e571a..bb0c8a994116 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -831,11 +831,6 @@ struct drm_xe_vm_destroy { * - %DRM_XE_VM_BIND_OP_PREFETCH * * and the @flags can be: - * - %DRM_XE_VM_BIND_FLAG_READONLY - * - %DRM_XE_VM_BIND_FLAG_ASYNC - * - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the - * MAP operation immediately rather than deferring the MAP to the page - * fault handler. * - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page * tables are setup with a special bit which indicates writes are * dropped and all reads return zero. In the future, the NULL flags @@ -928,9 +923,8 @@ struct drm_xe_vm_bind_op { /** @op: Bind operation to perform */ __u32 op; -#define DRM_XE_VM_BIND_FLAG_READONLY (1 << 0) -#define DRM_XE_VM_BIND_FLAG_IMMEDIATE (1 << 1) #define DRM_XE_VM_BIND_FLAG_NULL (1 << 2) +#define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) /** @flags: Bind flags */ __u32 flags; @@ -1045,19 +1039,6 @@ struct drm_xe_exec_queue_create { #define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY 0 #define DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE 1 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT 2 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT 4 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER 5 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY 6 -#define DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY 7 -/* Monitor 128KB contiguous region with 4K sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_128K 0 -/* Monitor 2MB contiguous region with 64KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_2M 1 -/* Monitor 16MB contiguous region with 512KB sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_16M 2 -/* Monitor 64MB contiguous region with 2M sub-granularity */ -#define DRM_XE_ACC_GRANULARITY_64M 3 /** @extensions: Pointer to the first extension struct, if any */ __u64 extensions; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 93cb411adf72..bb65ee840cda 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -133,6 +137,21 @@ enum { }; enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + NETDEV_A_QSTATS_RX_ALLOC_FAIL, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, @@ -144,6 +163,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/include/uapi/linux/nexthop.h b/include/uapi/linux/nexthop.h index d8ffa8c9ca78..dd8787f9cf39 100644 --- a/include/uapi/linux/nexthop.h +++ b/include/uapi/linux/nexthop.h @@ -30,6 +30,9 @@ enum { #define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1) +#define NHA_OP_FLAG_DUMP_STATS BIT(0) +#define NHA_OP_FLAG_DUMP_HW_STATS BIT(1) + enum { NHA_UNSPEC, NHA_ID, /* u32; id for nexthop. id == 0 means auto-assign */ @@ -60,6 +63,18 @@ enum { /* nested; nexthop bucket attributes */ NHA_RES_BUCKET, + /* u32; operation-specific flags */ + NHA_OP_FLAGS, + + /* nested; nexthop group stats */ + NHA_GROUP_STATS, + + /* u32; nexthop hardware stats enable */ + NHA_HW_STATS_ENABLE, + + /* u32; read-only; whether any driver collects HW stats */ + NHA_HW_STATS_USED, + __NHA_MAX, }; @@ -101,4 +116,34 @@ enum { #define NHA_RES_BUCKET_MAX (__NHA_RES_BUCKET_MAX - 1) +enum { + NHA_GROUP_STATS_UNSPEC, + + /* nested; nexthop group entry stats */ + NHA_GROUP_STATS_ENTRY, + + __NHA_GROUP_STATS_MAX, +}; + +#define NHA_GROUP_STATS_MAX (__NHA_GROUP_STATS_MAX - 1) + +enum { + NHA_GROUP_STATS_ENTRY_UNSPEC, + + /* u32; nexthop id of the nexthop group entry */ + NHA_GROUP_STATS_ENTRY_ID, + + /* uint; number of packets forwarded via the nexthop group entry */ + NHA_GROUP_STATS_ENTRY_PACKETS, + + /* uint; number of packets forwarded via the nexthop group entry in + * hardware + */ + NHA_GROUP_STATS_ENTRY_PACKETS_HW, + + __NHA_GROUP_STATS_ENTRY_MAX, +}; + +#define NHA_GROUP_STATS_ENTRY_MAX (__NHA_GROUP_STATS_ENTRY_MAX - 1) + #endif diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index d5b9cfbd9cea..628d46a0da92 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -142,7 +142,7 @@ struct snd_hwdep_dsp_image { * * *****************************************************************************/ -#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 16) +#define SNDRV_PCM_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 17) typedef unsigned long snd_pcm_uframes_t; typedef signed long snd_pcm_sframes_t; @@ -416,7 +416,7 @@ struct snd_pcm_hw_params { unsigned int rmask; /* W: requested masks */ unsigned int cmask; /* R: changed masks */ unsigned int info; /* R: Info flags for returned setup */ - unsigned int msbits; /* R: used most significant bits */ + unsigned int msbits; /* R: used most significant bits (in sample bit-width) */ unsigned int rate_num; /* R: rate numerator */ unsigned int rate_den; /* R: rate denominator */ snd_pcm_uframes_t fifo_size; /* R: chip FIFO size in frames */ diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8a0bb80fe48a..9ee8da477465 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -24,6 +24,7 @@ #include <linux/filter.h> #include <linux/ptr_ring.h> #include <net/xdp.h> +#include <net/hotdata.h> #include <linux/sched.h> #include <linux/workqueue.h> @@ -178,7 +179,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, void **frames, int n, struct xdp_cpumap_stats *stats) { - struct xdp_rxq_info rxq; + struct xdp_rxq_info rxq = {}; struct xdp_buff xdp; int i, nframes = 0; @@ -326,7 +327,8 @@ static int cpu_map_kthread_run(void *data) /* Support running another XDP prog on this CPU */ nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, skbs); + m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + gfp, nframes, skbs); if (unlikely(m == 0)) { for (i = 0; i < nframes; i++) skbs[i] = NULL; /* effect: xdp_return_frame */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 4dd84e13bbfe..21f80383f8b2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -16715,6 +16715,9 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat { int i; + if (old->callback_depth > cur->callback_depth) + return false; + for (i = 0; i < MAX_BPF_REG; i++) if (!regsafe(env, &old->regs[i], &cur->regs[i], &env->idmap_scratch, exact)) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ba36c073304a..927bef3a598a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2562,7 +2562,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, update_partition_sd_lb(cs, old_prs); out_free: free_cpumasks(NULL, &tmp); - return 0; + return retval; } /** @@ -2598,9 +2598,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus)) return 0; - if (alloc_cpumasks(NULL, &tmp)) - return -ENOMEM; - if (*buf) compute_effective_exclusive_cpumask(trialcs, NULL); @@ -2615,6 +2612,9 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (retval) return retval; + if (alloc_cpumasks(NULL, &tmp)) + return -ENOMEM; + if (old_prs) { if (cpumask_empty(trialcs->effective_xcpus)) { invalidate = true; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 6cd2a4e3afb8..9ff018245840 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -189,9 +189,6 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) { int size; - if (num <= 0) - return -EINVAL; - if (!fp->exit_handler) { fp->rethook = NULL; return 0; @@ -199,15 +196,16 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) /* Initialize rethook if needed */ if (fp->nr_maxactive) - size = fp->nr_maxactive; + num = fp->nr_maxactive; else - size = num * num_possible_cpus() * 2; - if (size <= 0) + num *= num_possible_cpus() * 2; + if (num <= 0) return -EINVAL; + size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size; + /* Initialize rethook */ - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, - sizeof(struct fprobe_rethook_node), size); + fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num); if (IS_ERR(fp->rethook)) return PTR_ERR(fp->rethook); diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c index fde0aa244148..a1389db1c30a 100644 --- a/lib/dynamic_queue_limits.c +++ b/lib/dynamic_queue_limits.c @@ -10,10 +10,77 @@ #include <linux/dynamic_queue_limits.h> #include <linux/compiler.h> #include <linux/export.h> +#include <trace/events/napi.h> #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) +static void dql_check_stall(struct dql *dql) +{ + unsigned short stall_thrs; + unsigned long now; + + stall_thrs = READ_ONCE(dql->stall_thrs); + if (!stall_thrs) + return; + + now = jiffies; + /* Check for a potential stall */ + if (time_after_eq(now, dql->last_reap + stall_thrs)) { + unsigned long hist_head, t, start, end; + + /* We are trying to detect a period of at least @stall_thrs + * jiffies without any Tx completions, but during first half + * of which some Tx was posted. + */ +dqs_again: + hist_head = READ_ONCE(dql->history_head); + /* pairs with smp_wmb() in dql_queued() */ + smp_rmb(); + + /* Get the previous entry in the ring buffer, which is the + * oldest sample. + */ + start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; + + /* Advance start to continue from the last reap time */ + if (time_before(start, dql->last_reap + 1)) + start = dql->last_reap + 1; + + /* Newest sample we should have already seen a completion for */ + end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); + + /* Shrink the search space to [start, (now - start_thrs/2)] if + * `end` is beyond the stall zone + */ + if (time_before(now, end + stall_thrs / 2)) + end = now - stall_thrs / 2; + + /* Search for the queued time in [t, end] */ + for (t = start; time_before_eq(t, end); t++) + if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), + dql->history)) + break; + + /* Variable t contains the time of the queue */ + if (!time_before_eq(t, end)) + goto no_stall; + + /* The ring buffer was modified in the meantime, retry */ + if (hist_head != READ_ONCE(dql->history_head)) + goto dqs_again; + + dql->stall_cnt++; + dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); + + trace_dql_stall_detected(dql->stall_thrs, now - t, + dql->last_reap, dql->history_head, + now, dql->history); + } +no_stall: + dql->last_reap = now; +} + /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { @@ -110,6 +177,8 @@ void dql_completed(struct dql *dql, unsigned int count) dql->prev_last_obj_cnt = dql->last_obj_cnt; dql->num_completed = completed; dql->prev_num_queued = num_queued; + + dql_check_stall(dql); } EXPORT_SYMBOL(dql_completed); @@ -125,6 +194,10 @@ void dql_reset(struct dql *dql) dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; + + dql->last_reap = jiffies; + dql->history_head = jiffies / BITS_PER_LONG; + memset(dql->history, 0, sizeof(dql->history)); } EXPORT_SYMBOL(dql_reset); @@ -133,6 +206,7 @@ void dql_init(struct dql *dql, unsigned int hold_time) dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; + dql->stall_thrs = 0; dql_reset(dql); } EXPORT_SYMBOL(dql_init); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index e0aa6b440ca5..cf2eb2b2f983 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -166,7 +166,6 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, - .copy_mc = false, .nofault = false, .data_source = direction, .__iov = iov, @@ -245,26 +244,8 @@ EXPORT_SYMBOL_GPL(_copy_mc_to_iter); #endif /* CONFIG_ARCH_HAS_COPY_MC */ static __always_inline -size_t memcpy_from_iter_mc(void *iter_from, size_t progress, - size_t len, void *to, void *priv2) -{ - return copy_mc_to_kernel(to + progress, iter_from, len); -} - -static size_t __copy_from_iter_mc(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(i->count < bytes)) - bytes = i->count; - if (unlikely(!bytes)) - return 0; - return iterate_bvec(i, bytes, addr, NULL, memcpy_from_iter_mc); -} - -static __always_inline size_t __copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { - if (unlikely(iov_iter_is_copy_mc(i))) - return __copy_from_iter_mc(addr, bytes, i); return iterate_and_advance(i, bytes, addr, copy_from_user_iter, memcpy_from_iter); } @@ -633,7 +614,6 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_KVEC, - .copy_mc = false, .data_source = direction, .kvec = kvec, .nr_segs = nr_segs, @@ -650,7 +630,6 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter){ .iter_type = ITER_BVEC, - .copy_mc = false, .data_source = direction, .bvec = bvec, .nr_segs = nr_segs, @@ -679,7 +658,6 @@ void iov_iter_xarray(struct iov_iter *i, unsigned int direction, BUG_ON(direction & ~1); *i = (struct iov_iter) { .iter_type = ITER_XARRAY, - .copy_mc = false, .data_source = direction, .xarray = xarray, .xarray_start = start, @@ -703,7 +681,6 @@ void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count) BUG_ON(direction != READ); *i = (struct iov_iter){ .iter_type = ITER_DISCARD, - .copy_mc = false, .data_source = false, .count = count, .iov_offset = 0 diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 5535f9adc658..61efeadaff8d 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -12,6 +12,7 @@ #include <linux/rcupdate_trace.h> #include <linux/sched/signal.h> #include <net/bpf_sk_storage.h> +#include <net/hotdata.h> #include <net/sock.h> #include <net/tcp.h> #include <net/net_namespace.h> @@ -254,7 +255,8 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, int i, n; LIST_HEAD(list); - n = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, (void **)skbs); + n = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, nframes, + (void **)skbs); if (unlikely(n == 0)) { for (i = 0; i < nframes; i++) xdp_return_frame(frames[i]); diff --git a/net/core/Makefile b/net/core/Makefile index 821aec06abf1..6e6548011fae 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -18,6 +18,7 @@ obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o obj-y += net-sysfs.o +obj-y += hotdata.o obj-$(CONFIG_PAGE_POOL) += page_pool.o page_pool_user.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o diff --git a/net/core/dev.c b/net/core/dev.c index fe054cbd41e9..0766a245816b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -155,13 +155,13 @@ #include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> +#include <net/rps.h> #include "dev.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; -struct list_head ptype_all __read_mostly; /* Taps */ static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, @@ -540,7 +540,7 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) - return pt->dev ? &pt->dev->ptype_all : &ptype_all; + return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all; else return pt->dev ? &pt->dev->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; @@ -2226,7 +2226,8 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) */ bool dev_nit_active(struct net_device *dev) { - return !list_empty(&ptype_all) || !list_empty(&dev->ptype_all); + return !list_empty(&net_hotdata.ptype_all) || + !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active); @@ -2237,10 +2238,9 @@ EXPORT_SYMBOL_GPL(dev_nit_active); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { - struct packet_type *ptype; + struct list_head *ptype_list = &net_hotdata.ptype_all; + struct packet_type *ptype, *pt_prev = NULL; struct sk_buff *skb2 = NULL; - struct packet_type *pt_prev = NULL; - struct list_head *ptype_list = &ptype_all; rcu_read_lock(); again: @@ -2286,7 +2286,7 @@ again: pt_prev = ptype; } - if (ptype_list == &ptype_all) { + if (ptype_list == &net_hotdata.ptype_all) { ptype_list = &dev->ptype_all; goto again; } @@ -4405,19 +4405,10 @@ EXPORT_SYMBOL(__dev_direct_xmit); * Receiver routines *************************************************************************/ -int netdev_max_backlog __read_mostly = 1000; -EXPORT_SYMBOL(netdev_max_backlog); - -int netdev_tstamp_prequeue __read_mostly = 1; unsigned int sysctl_skb_defer_max __read_mostly = 64; -int netdev_budget __read_mostly = 300; -/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ -unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ -int dev_rx_weight __read_mostly = 64; -int dev_tx_weight __read_mostly = 64; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -4459,12 +4450,6 @@ static inline void ____napi_schedule(struct softnet_data *sd, #ifdef CONFIG_RPS -/* One global table that all flow-based protocols share. */ -struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; -EXPORT_SYMBOL(rps_sock_flow_table); -u32 rps_cpu_mask __read_mostly; -EXPORT_SYMBOL(rps_cpu_mask); - struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; @@ -4556,7 +4541,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (!hash) goto done; - sock_flow_table = rcu_dereference(rps_sock_flow_table); + sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (flow_table && sock_flow_table) { struct rps_dev_flow *rflow; u32 next_cpu; @@ -4566,10 +4551,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); - if ((ident ^ hash) & ~rps_cpu_mask) + if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask) goto try_rps; - next_cpu = ident & rps_cpu_mask; + next_cpu = ident & net_hotdata.rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table @@ -4718,7 +4703,7 @@ static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) struct softnet_data *sd; unsigned int old_flow, new_flow; - if (qlen < (READ_ONCE(netdev_max_backlog) >> 1)) + if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); @@ -4766,7 +4751,8 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, if (!netif_running(skb->dev)) goto drop; qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= READ_ONCE(netdev_max_backlog) && !skb_flow_limit(skb, qlen)) { + if (qlen <= READ_ONCE(net_hotdata.max_backlog) && + !skb_flow_limit(skb, qlen)) { if (qlen) { enqueue: __skb_queue_tail(&sd->input_pkt_queue, skb); @@ -5055,7 +5041,7 @@ static int netif_rx_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_rx(skb); @@ -5347,7 +5333,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, int ret = NET_RX_DROP; __be16 type; - net_timestamp_check(!READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb); @@ -5391,7 +5377,7 @@ another_round: if (pfmemalloc) goto skip_taps; - list_for_each_entry_rcu(ptype, &ptype_all, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -5731,7 +5717,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; @@ -5761,7 +5747,8 @@ void netif_receive_skb_list_internal(struct list_head *head) INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { - net_timestamp_check(READ_ONCE(netdev_tstamp_prequeue), skb); + net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), + skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); @@ -5985,7 +5972,7 @@ static int process_backlog(struct napi_struct *napi, int quota) net_rps_action_and_irq_enable(sd); } - napi->weight = READ_ONCE(dev_rx_weight); + napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; @@ -6790,8 +6777,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + - usecs_to_jiffies(READ_ONCE(netdev_budget_usecs)); - int budget = READ_ONCE(netdev_budget); + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); + int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); @@ -9122,28 +9109,6 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) } EXPORT_SYMBOL(netdev_port_same_parent_id); -static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin) -{ -#if IS_ENABLED(CONFIG_DPLL) - rtnl_lock(); - rcu_assign_pointer(dev->dpll_pin, dpll_pin); - rtnl_unlock(); -#endif -} - -void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) -{ - WARN_ON(!dpll_pin); - netdev_dpll_pin_assign(dev, dpll_pin); -} -EXPORT_SYMBOL(netdev_dpll_pin_set); - -void netdev_dpll_pin_clear(struct net_device *dev) -{ - netdev_dpll_pin_assign(dev, NULL); -} -EXPORT_SYMBOL(netdev_dpll_pin_clear); - /** * dev_change_proto_down - set carrier according to proto_down. * @@ -11774,7 +11739,6 @@ static int __init net_dev_init(void) if (netdev_kobject_init()) goto out; - INIT_LIST_HEAD(&ptype_all); for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); diff --git a/net/core/dev.h b/net/core/dev.h index 45892267848d..2bcaf8eee50c 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -38,10 +38,7 @@ int dev_addr_init(struct net_device *dev); void dev_addr_check(struct net_device *dev); /* sysctls not referred to from outside net/core/ */ -extern int netdev_budget; -extern unsigned int netdev_budget_usecs; extern unsigned int sysctl_skb_defer_max; -extern int netdev_tstamp_prequeue; extern int netdev_unregister_timeout_secs; extern int weight_p; extern int dev_weight_rx_bias; diff --git a/net/core/gro.c b/net/core/gro.c index 6a0edbd826a1..ee30d4f0c038 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -10,9 +10,6 @@ #define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(offload_lock); -struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base); -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /** * dev_add_offload - register offload handlers @@ -31,7 +28,7 @@ void dev_add_offload(struct packet_offload *po) struct packet_offload *elem; spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { + list_for_each_entry(elem, &net_hotdata.offload_base, list) { if (po->priority < elem->priority) break; } @@ -55,7 +52,7 @@ EXPORT_SYMBOL(dev_add_offload); */ static void __dev_remove_offload(struct packet_offload *po) { - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *po1; spin_lock(&offload_lock); @@ -235,9 +232,9 @@ done: static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; - struct list_head *head = &offload_base; int err = -ENOENT; BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); @@ -444,7 +441,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff { u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); struct gro_list *gro_list = &napi->gro_hash[bucket]; - struct list_head *head = &offload_base; + struct list_head *head = &net_hotdata.offload_base; struct packet_offload *ptype; __be16 type = skb->protocol; struct sk_buff *pp = NULL; @@ -550,7 +547,7 @@ normal: struct packet_offload *gro_find_receive_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { @@ -564,7 +561,7 @@ EXPORT_SYMBOL(gro_find_receive_by_type); struct packet_offload *gro_find_complete_by_type(__be16 type) { - struct list_head *offload_head = &offload_base; + struct list_head *offload_head = &net_hotdata.offload_base; struct packet_offload *ptype; list_for_each_entry_rcu(ptype, offload_head, list) { diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c index ed5ec5de47f6..ff8e5b64bf6b 100644 --- a/net/core/gro_cells.c +++ b/net/core/gro_cells.c @@ -3,6 +3,7 @@ #include <linux/slab.h> #include <linux/netdevice.h> #include <net/gro_cells.h> +#include <net/hotdata.h> struct gro_cell { struct sk_buff_head napi_skbs; @@ -26,7 +27,7 @@ int gro_cells_receive(struct gro_cells *gcells, struct sk_buff *skb) cell = this_cpu_ptr(gcells->cells); - if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(netdev_max_backlog)) { + if (skb_queue_len(&cell->napi_skbs) > READ_ONCE(net_hotdata.max_backlog)) { drop: dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); diff --git a/net/core/gso.c b/net/core/gso.c index 9e1803bfc9c6..bcd156372f4d 100644 --- a/net/core/gso.c +++ b/net/core/gso.c @@ -17,7 +17,7 @@ struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, struct packet_offload *ptype; rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; @@ -48,7 +48,7 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, __skb_pull(skb, vlan_depth); rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { + list_for_each_entry_rcu(ptype, &net_hotdata.offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { segs = ptype->callbacks.gso_segment(skb, features); break; diff --git a/net/core/hotdata.c b/net/core/hotdata.c new file mode 100644 index 000000000000..c8a7a451c18a --- /dev/null +++ b/net/core/hotdata.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <net/hotdata.h> +#include <linux/cache.h> +#include <linux/jiffies.h> +#include <linux/list.h> + + +struct net_hotdata net_hotdata __cacheline_aligned = { + .offload_base = LIST_HEAD_INIT(net_hotdata.offload_base), + .ptype_all = LIST_HEAD_INIT(net_hotdata.ptype_all), + .gro_normal_batch = 8, + + .netdev_budget = 300, + /* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ + .netdev_budget_usecs = 2 * USEC_PER_SEC / HZ, + + .tstamp_prequeue = 1, + .max_backlog = 1000, + .dev_tx_weight = 64, + .dev_rx_weight = 64, +}; +EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 2e4e96d30ee1..a97eceb84e61 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -3,6 +3,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> +#include <net/hotdata.h> #include "dev.h" @@ -183,7 +184,7 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos) } } - list_for_each_entry_rcu(pt, &ptype_all, list) { + list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) { if (i == pos) return pt; ++i; @@ -231,13 +232,13 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) } } - nxt = ptype_all.next; + nxt = net_hotdata.ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: - if (nxt != &ptype_all) + if (nxt != &net_hotdata.ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index af238026ac3c..e3d7a8cfa20b 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -24,6 +24,7 @@ #include <linux/of_net.h> #include <linux/cpu.h> #include <net/netdev_rx_queue.h> +#include <net/rps.h> #include "dev.h" #include "net-sysfs.h" @@ -1414,6 +1415,65 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init = __ATTR(hold_time, 0644, bql_show_hold_time, bql_set_hold_time); +static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs)); +} + +static ssize_t bql_set_stall_thrs(struct netdev_queue *queue, + const char *buf, size_t len) +{ + struct dql *dql = &queue->dql; + unsigned int value; + int err; + + err = kstrtouint(buf, 10, &value); + if (err < 0) + return err; + + value = msecs_to_jiffies(value); + if (value && (value < 4 || value > 4 / 2 * BITS_PER_LONG)) + return -ERANGE; + + if (!dql->stall_thrs && value) + dql->last_reap = jiffies; + /* Force last_reap to be live */ + smp_wmb(); + dql->stall_thrs = value; + + return len; +} + +static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init = + __ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs); + +static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf) +{ + return sprintf(buf, "%u\n", READ_ONCE(queue->dql.stall_max)); +} + +static ssize_t bql_set_stall_max(struct netdev_queue *queue, + const char *buf, size_t len) +{ + WRITE_ONCE(queue->dql.stall_max, 0); + return len; +} + +static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init = + __ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max); + +static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf) +{ + struct dql *dql = &queue->dql; + + return sprintf(buf, "%lu\n", dql->stall_cnt); +} + +static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init = + __ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL); + static ssize_t bql_show_inflight(struct netdev_queue *queue, char *buf) { @@ -1452,6 +1512,9 @@ static struct attribute *dql_attrs[] __ro_after_init = { &bql_limit_min_attribute.attr, &bql_hold_time_attribute.attr, &bql_inflight_attribute.attr, + &bql_stall_thrs_attribute.attr, + &bql_stall_cnt_attribute.attr, + &bql_stall_max_attribute.attr, NULL }; diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index be7f2ebd61b2..8d8ace9ef87f 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -68,6 +68,11 @@ static const struct nla_policy netdev_napi_get_dump_nl_policy[NETDEV_A_NAPI_IFIN [NETDEV_A_NAPI_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), }; +/* NETDEV_CMD_QSTATS_GET - dump */ +static const struct nla_policy netdev_qstats_get_nl_policy[NETDEV_A_QSTATS_SCOPE + 1] = { + [NETDEV_A_QSTATS_SCOPE] = NLA_POLICY_MASK(NLA_UINT, 0x1), +}; + /* Ops table for netdev */ static const struct genl_split_ops netdev_nl_ops[] = { { @@ -138,6 +143,13 @@ static const struct genl_split_ops netdev_nl_ops[] = { .maxattr = NETDEV_A_NAPI_IFINDEX, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = NETDEV_CMD_QSTATS_GET, + .dumpit = netdev_nl_qstats_get_dumpit, + .policy = netdev_qstats_get_nl_policy, + .maxattr = NETDEV_A_QSTATS_SCOPE, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group netdev_nl_mcgrps[] = { diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h index a47f2bcbe4fa..4db40fd5b4a9 100644 --- a/net/core/netdev-genl-gen.h +++ b/net/core/netdev-genl-gen.h @@ -28,6 +28,8 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int netdev_nl_napi_get_doit(struct sk_buff *skb, struct genl_info *info); int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); enum { NETDEV_NLGRP_MGMT, diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c index 918b109e0cf4..7004b3399c2b 100644 --- a/net/core/netdev-genl.c +++ b/net/core/netdev-genl.c @@ -8,6 +8,7 @@ #include <net/xdp.h> #include <net/xdp_sock.h> #include <net/netdev_rx_queue.h> +#include <net/netdev_queues.h> #include <net/busy_poll.h> #include "netdev-genl-gen.h" @@ -460,6 +461,219 @@ int netdev_nl_queue_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) return err; } +#define NETDEV_STAT_NOT_SET (~0ULL) + +static void netdev_nl_stats_add(void *_sum, const void *_add, size_t size) +{ + const u64 *add = _add; + u64 *sum = _sum; + + while (size) { + if (*add != NETDEV_STAT_NOT_SET && *sum != NETDEV_STAT_NOT_SET) + *sum += *add; + sum++; + add++; + size -= 8; + } +} + +static int netdev_stat_put(struct sk_buff *rsp, unsigned int attr_id, u64 value) +{ + if (value == NETDEV_STAT_NOT_SET) + return 0; + return nla_put_uint(rsp, attr_id, value); +} + +static int +netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_PACKETS, rx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_BYTES, rx->bytes) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_write_tx(struct sk_buff *rsp, struct netdev_queue_stats_tx *tx) +{ + if (netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_PACKETS, tx->packets) || + netdev_stat_put(rsp, NETDEV_A_QSTATS_TX_BYTES, tx->bytes)) + return -EMSGSIZE; + return 0; +} + +static int +netdev_nl_stats_queue(struct net_device *netdev, struct sk_buff *rsp, + u32 q_type, int i, const struct genl_info *info) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + struct netdev_queue_stats_rx rx; + struct netdev_queue_stats_tx tx; + void *hdr; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_TYPE, q_type) || + nla_put_u32(rsp, NETDEV_A_QSTATS_QUEUE_ID, i)) + goto nla_put_failure; + + switch (q_type) { + case NETDEV_QUEUE_TYPE_RX: + memset(&rx, 0xff, sizeof(rx)); + ops->get_queue_stats_rx(netdev, i, &rx); + if (!memchr_inv(&rx, 0xff, sizeof(rx))) + goto nla_cancel; + if (netdev_nl_stats_write_rx(rsp, &rx)) + goto nla_put_failure; + break; + case NETDEV_QUEUE_TYPE_TX: + memset(&tx, 0xff, sizeof(tx)); + ops->get_queue_stats_tx(netdev, i, &tx); + if (!memchr_inv(&tx, 0xff, sizeof(tx))) + goto nla_cancel; + if (netdev_nl_stats_write_tx(rsp, &tx)) + goto nla_put_failure; + break; + } + + genlmsg_end(rsp, hdr); + return 0; + +nla_cancel: + genlmsg_cancel(rsp, hdr); + return 0; +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +static int +netdev_nl_stats_by_queue(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info, + struct netdev_nl_dump_ctx *ctx) +{ + const struct netdev_stat_ops *ops = netdev->stat_ops; + int i, err; + + if (!(netdev->flags & IFF_UP)) + return 0; + + i = ctx->rxq_idx; + while (ops->get_queue_stats_rx && i < netdev->real_num_rx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_RX, + i, info); + if (err) + return err; + ctx->rxq_idx = i++; + } + i = ctx->txq_idx; + while (ops->get_queue_stats_tx && i < netdev->real_num_tx_queues) { + err = netdev_nl_stats_queue(netdev, rsp, NETDEV_QUEUE_TYPE_TX, + i, info); + if (err) + return err; + ctx->txq_idx = i++; + } + + ctx->rxq_idx = 0; + ctx->txq_idx = 0; + return 0; +} + +static int +netdev_nl_stats_by_netdev(struct net_device *netdev, struct sk_buff *rsp, + const struct genl_info *info) +{ + struct netdev_queue_stats_rx rx_sum, rx; + struct netdev_queue_stats_tx tx_sum, tx; + const struct netdev_stat_ops *ops; + void *hdr; + int i; + + ops = netdev->stat_ops; + /* Netdev can't guarantee any complete counters */ + if (!ops->get_base_stats) + return 0; + + memset(&rx_sum, 0xff, sizeof(rx_sum)); + memset(&tx_sum, 0xff, sizeof(tx_sum)); + + ops->get_base_stats(netdev, &rx_sum, &tx_sum); + + /* The op was there, but nothing reported, don't bother */ + if (!memchr_inv(&rx_sum, 0xff, sizeof(rx_sum)) && + !memchr_inv(&tx_sum, 0xff, sizeof(tx_sum))) + return 0; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + if (nla_put_u32(rsp, NETDEV_A_QSTATS_IFINDEX, netdev->ifindex)) + goto nla_put_failure; + + for (i = 0; i < netdev->real_num_rx_queues; i++) { + memset(&rx, 0xff, sizeof(rx)); + if (ops->get_queue_stats_rx) + ops->get_queue_stats_rx(netdev, i, &rx); + netdev_nl_stats_add(&rx_sum, &rx, sizeof(rx)); + } + for (i = 0; i < netdev->real_num_tx_queues; i++) { + memset(&tx, 0xff, sizeof(tx)); + if (ops->get_queue_stats_tx) + ops->get_queue_stats_tx(netdev, i, &tx); + netdev_nl_stats_add(&tx_sum, &tx, sizeof(tx)); + } + + if (netdev_nl_stats_write_rx(rsp, &rx_sum) || + netdev_nl_stats_write_tx(rsp, &tx_sum)) + goto nla_put_failure; + + genlmsg_end(rsp, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int netdev_nl_qstats_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct netdev_nl_dump_ctx *ctx = netdev_dump_ctx(cb); + const struct genl_info *info = genl_info_dump(cb); + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + unsigned int scope; + int err = 0; + + scope = 0; + if (info->attrs[NETDEV_A_QSTATS_SCOPE]) + scope = nla_get_uint(info->attrs[NETDEV_A_QSTATS_SCOPE]); + + rtnl_lock(); + for_each_netdev_dump(net, netdev, ctx->ifindex) { + if (!netdev->stat_ops) + continue; + + switch (scope) { + case 0: + err = netdev_nl_stats_by_netdev(netdev, skb, info); + break; + case NETDEV_QSTATS_SCOPE_QUEUE: + err = netdev_nl_stats_by_queue(netdev, skb, info, ctx); + break; + } + if (err < 0) + break; + } + rtnl_unlock(); + + return err; +} + static int netdev_genl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 53ad96f71b63..3a3277ba167b 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -94,11 +94,12 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb, state->pp_id = pool->user.id; err = fill(skb, pool, info); if (err) - break; + goto out; } state->pp_id = 0; } +out: mutex_unlock(&page_pools_lock); rtnl_unlock(); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 780b330f8ef9..a3d7847ce69d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1056,7 +1056,7 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev) { size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */ - size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev)); + size += dpll_netdev_pin_handle_size(dev); return size; } @@ -1793,7 +1793,7 @@ static int rtnl_fill_dpll_pin(struct sk_buff *skb, if (!dpll_pin_nest) return -EMSGSIZE; - ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev)); + ret = dpll_netdev_add_pin_handle(skb, dev); if (ret < 0) goto nest_cancel; @@ -2267,11 +2267,8 @@ walk_entries: nlh->nlmsg_seq, 0, flags, ext_filter_mask, 0, NULL, 0, netnsid, GFP_KERNEL); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; + if (err < 0) break; - } } cb->seq = tgt_net->dev_base_seq; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 43d7fc150acc..766219011aea 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/sock.h> #include <net/checksum.h> #include <net/gso.h> +#include <net/hotdata.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> @@ -88,15 +89,10 @@ #include "dev.h" #include "sock_destructor.h" -struct kmem_cache *skbuff_cache __ro_after_init; -static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif - -static struct kmem_cache *skb_small_head_cache __ro_after_init; - #define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. @@ -349,7 +345,7 @@ static struct sk_buff *napi_skb_cache_get(void) struct sk_buff *skb; if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache, + nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); @@ -358,7 +354,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache)); + kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); return skb; } @@ -416,7 +412,7 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -467,7 +463,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -578,7 +574,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, obj_size = SKB_HEAD_ALIGN(*size); if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && !(flags & KMALLOC_NOT_NORMAL_BITS)) { - obj = kmem_cache_alloc_node(skb_small_head_cache, + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); *size = SKB_SMALL_HEAD_CACHE_SIZE; @@ -586,7 +582,7 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, goto out; /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmem_cache_alloc_node(skb_small_head_cache, flags, node); + obj = kmem_cache_alloc_node(net_hotdata.skb_small_head_cache, flags, node); goto out; } @@ -649,7 +645,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, u8 *data; cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_cache; + ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; @@ -1095,7 +1091,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb) static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) - kmem_cache_free(skb_small_head_cache, head); + kmem_cache_free(net_hotdata.skb_small_head_cache, head); else kfree(head); } @@ -1162,7 +1158,7 @@ static void kfree_skbmem(struct sk_buff *skb) switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); return; case SKB_FCLONE_ORIG: @@ -1183,7 +1179,7 @@ static void kfree_skbmem(struct sk_buff *skb) if (!refcount_dec_and_test(&fclones->fclone_ref)) return; fastpath: - kmem_cache_free(skbuff_fclone_cache, fclones); + kmem_cache_free(net_hotdata.skbuff_fclone_cache, fclones); } void skb_release_head_state(struct sk_buff *skb) @@ -1280,7 +1276,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { - kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE, + kmem_cache_free_bulk(net_hotdata.skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } @@ -1305,7 +1301,7 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) } if (sa.skb_count) - kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array); + kmem_cache_free_bulk(net_hotdata.skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); @@ -1467,9 +1463,9 @@ static void napi_skb_cache_put(struct sk_buff *skb) if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], - kmem_cache_size(skbuff_cache)); + kmem_cache_size(net_hotdata.skbuff_cache)); - kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, + kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } @@ -2066,7 +2062,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - n = kmem_cache_alloc(skbuff_cache, gfp_mask); + n = kmem_cache_alloc(net_hotdata.skbuff_cache, gfp_mask); if (!n) return NULL; @@ -5005,7 +5001,7 @@ static void skb_extensions_init(void) {} void __init skb_init(void) { - skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", + net_hotdata.skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC| @@ -5013,7 +5009,7 @@ void __init skb_init(void) offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); - skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", + net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, @@ -5022,7 +5018,7 @@ void __init skb_init(void) * struct skb_shared_info is located at the end of skb->head, * and should not be copied to/from user. */ - skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", + net_hotdata.skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", SKB_SMALL_HEAD_CACHE_SIZE, 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, @@ -5895,7 +5891,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); - kmem_cache_free(skbuff_cache, skb); + kmem_cache_free(net_hotdata.skbuff_cache, skb); } else { __kfree_skb(skb); } diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 986f15e5d6c4..6973dda3abda 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -23,6 +23,8 @@ #include <net/net_ratelimit.h> #include <net/busy_poll.h> #include <net/pkt_sched.h> +#include <net/hotdata.h> +#include <net/rps.h> #include "dev.h" @@ -138,7 +140,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, mutex_lock(&sock_flow_mutex); - orig_sock_table = rcu_dereference_protected(rps_sock_flow_table, + orig_sock_table = rcu_dereference_protected( + net_hotdata.rps_sock_flow_table, lockdep_is_held(&sock_flow_mutex)); size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; @@ -159,7 +162,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, mutex_unlock(&sock_flow_mutex); return -ENOMEM; } - rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1; + net_hotdata.rps_cpu_mask = + roundup_pow_of_two(nr_cpu_ids) - 1; sock_table->mask = size - 1; } else sock_table = orig_sock_table; @@ -170,7 +174,8 @@ static int rps_sock_flow_sysctl(struct ctl_table *table, int write, sock_table = NULL; if (sock_table != orig_sock_table) { - rcu_assign_pointer(rps_sock_flow_table, sock_table); + rcu_assign_pointer(net_hotdata.rps_sock_flow_table, + sock_table); if (sock_table) { static_branch_inc(&rps_needed); static_branch_inc(&rfs_needed); @@ -300,8 +305,8 @@ static int proc_do_dev_weight(struct ctl_table *table, int write, ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { weight = READ_ONCE(weight_p); - WRITE_ONCE(dev_rx_weight, weight * dev_weight_rx_bias); - WRITE_ONCE(dev_tx_weight, weight * dev_weight_tx_bias); + WRITE_ONCE(net_hotdata.dev_rx_weight, weight * dev_weight_rx_bias); + WRITE_ONCE(net_hotdata.dev_tx_weight, weight * dev_weight_tx_bias); } mutex_unlock(&dev_weight_mutex); @@ -439,7 +444,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "netdev_max_backlog", - .data = &netdev_max_backlog, + .data = &net_hotdata.max_backlog, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -498,7 +503,7 @@ static struct ctl_table net_core_table[] = { #endif { .procname = "netdev_tstamp_prequeue", - .data = &netdev_tstamp_prequeue, + .data = &net_hotdata.tstamp_prequeue, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -576,7 +581,7 @@ static struct ctl_table net_core_table[] = { #endif { .procname = "netdev_budget", - .data = &netdev_budget, + .data = &net_hotdata.netdev_budget, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -599,7 +604,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "netdev_budget_usecs", - .data = &netdev_budget_usecs, + .data = &net_hotdata.netdev_budget_usecs, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, @@ -632,7 +637,7 @@ static struct ctl_table net_core_table[] = { }, { .procname = "gro_normal_batch", - .data = &gro_normal_batch, + .data = &net_hotdata.gro_normal_batch, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec_minmax, diff --git a/net/core/xdp.c b/net/core/xdp.c index 0e3709a29175..41693154e426 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -16,6 +16,7 @@ #include <linux/bug.h> #include <net/page_pool/helpers.h> +#include <net/hotdata.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> @@ -589,7 +590,7 @@ EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { - n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs); + n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; @@ -658,7 +659,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(net_hotdata.skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; diff --git a/net/dsa/user.c b/net/dsa/user.c index 9c42a6edcdc8..16d395bb1a1f 100644 --- a/net/dsa/user.c +++ b/net/dsa/user.c @@ -2625,11 +2625,7 @@ int dsa_user_create(struct dsa_port *port) user_dev->vlan_features = conduit->vlan_features; p = netdev_priv(user_dev); - user_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!user_dev->tstats) { - free_netdev(user_dev); - return -ENOMEM; - } + user_dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; ret = gro_cells_init(&p->gcells, user_dev); if (ret) @@ -2695,7 +2691,6 @@ out_phy: out_gcells: gro_cells_destroy(&p->gcells); out_free: - free_percpu(user_dev->tstats); free_netdev(user_dev); port->user = NULL; return ret; @@ -2716,7 +2711,6 @@ void dsa_user_destroy(struct net_device *user_dev) dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); - free_percpu(user_dev->tstats); free_netdev(user_dev); } diff --git a/net/ethtool/common.c b/net/ethtool/common.c index ce486cec346c..6b2a360dcdf0 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -712,8 +712,3 @@ ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) } } EXPORT_SYMBOL_GPL(ethtool_forced_speed_maps_init); - -bool ethtool_eee_use_linkmodes(const struct ethtool_keee *eee) -{ - return !linkmode_empty(eee->supported); -} diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 0f2b5f7eacee..28b8aaaf9bcb 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -55,6 +55,5 @@ int ethtool_get_module_eeprom_call(struct net_device *dev, struct ethtool_eeprom *ee, u8 *data); bool __ethtool_dev_mm_supported(struct net_device *dev); -bool ethtool_eee_use_linkmodes(const struct ethtool_keee *eee); #endif /* _ETHTOOL_COMMON_H */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5daebdcbca32..55bd72997b31 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,6 +119,7 @@ #endif #include <net/l3mdev.h> #include <net/compat.h> +#include <net/rps.h> #include <trace/events/sock.h> @@ -1751,19 +1752,6 @@ static const struct net_protocol igmp_protocol = { }; #endif -static const struct net_protocol tcp_protocol = { - .handler = tcp_v4_rcv, - .err_handler = tcp_v4_err, - .no_policy = 1, - .icmp_strict_tag_validation = 1, -}; - -static const struct net_protocol udp_protocol = { - .handler = udp_rcv, - .err_handler = udp_err, - .no_policy = 1, -}; - static const struct net_protocol icmp_protocol = { .handler = icmp_rcv, .err_handler = icmp_err, @@ -1904,14 +1892,6 @@ static int ipv4_proc_init(void); * IP protocol layer initialiser */ -static struct packet_offload ip_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IP), - .callbacks = { - .gso_segment = inet_gso_segment, - .gro_receive = inet_gro_receive, - .gro_complete = inet_gro_complete, - }, -}; static const struct net_offload ipip_offload = { .callbacks = { @@ -1938,7 +1918,15 @@ static int __init ipv4_offload_init(void) if (ipip_offload_init() < 0) pr_crit("%s: Cannot add IPIP protocol offload\n", __func__); - dev_add_offload(&ip_packet_offload); + net_hotdata.ip_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IP), + .callbacks = { + .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ip_packet_offload); return 0; } @@ -1992,9 +1980,22 @@ static int __init inet_init(void) if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0) pr_crit("%s: Cannot add ICMP protocol\n", __func__); - if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0) + + net_hotdata.udp_protocol = (struct net_protocol) { + .handler = udp_rcv, + .err_handler = udp_err, + .no_policy = 1, + }; + if (inet_add_protocol(&net_hotdata.udp_protocol, IPPROTO_UDP) < 0) pr_crit("%s: Cannot add UDP protocol\n", __func__); - if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0) + + net_hotdata.tcp_protocol = (struct net_protocol) { + .handler = tcp_v4_rcv, + .err_handler = tcp_v4_err, + .no_policy = 1, + .icmp_strict_tag_validation = 1, + }; + if (inet_add_protocol(&net_hotdata.tcp_protocol, IPPROTO_TCP) < 0) pr_crit("%s: Cannot add TCP protocol\n", __func__); #ifdef CONFIG_IP_MULTICAST if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 4daa8124f247..7a437f0d4190 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1900,8 +1900,6 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) goto done; } done: - if (err < 0 && likely(skb->len)) - err = skb->len; if (fillargs.netnsid >= 0) put_net(tgt_net); rcu_read_unlock(); @@ -2312,8 +2310,6 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, ctx->all_default++; } done: - if (err < 0 && likely(skb->len)) - err = skb->len; rcu_read_unlock(); return err; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index bf3a2214fe29..48741352a88a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1026,8 +1026,6 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) goto unlock; } err = fib_table_dump(tb, skb, cb, &filter); - if (err < 0 && skb->len) - err = skb->len; goto unlock; } @@ -1045,11 +1043,8 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); err = fib_table_dump(tb, skb, cb, &filter); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; + if (err < 0) goto out; - } dumped = 1; next: e++; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 308ff34002ea..7498af320164 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -24,6 +24,7 @@ #include <net/inet6_hashtables.h> #endif #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/ip.h> #include <net/tcp.h> #include <net/sock_reuseport.h> @@ -32,8 +33,6 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 inet_ehash_secret __read_mostly; - net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 70509da4f080..e34466751d7b 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -26,6 +26,9 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHBITS 8 #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) +#define NHA_OP_FLAGS_DUMP_ALL (NHA_OP_FLAG_DUMP_STATS | \ + NHA_OP_FLAG_DUMP_HW_STATS) + static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, @@ -37,10 +40,17 @@ static const struct nla_policy rtm_nh_policy_new[] = { [NHA_ENCAP] = { .type = NLA_NESTED }, [NHA_FDB] = { .type = NLA_FLAG }, [NHA_RES_GROUP] = { .type = NLA_NESTED }, + [NHA_HW_STATS_ENABLE] = NLA_POLICY_MAX(NLA_U32, true), }; static const struct nla_policy rtm_nh_policy_get[] = { [NHA_ID] = { .type = NLA_U32 }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), +}; + +static const struct nla_policy rtm_nh_policy_del[] = { + [NHA_ID] = { .type = NLA_U32 }, }; static const struct nla_policy rtm_nh_policy_dump[] = { @@ -48,6 +58,8 @@ static const struct nla_policy rtm_nh_policy_dump[] = { [NHA_GROUPS] = { .type = NLA_FLAG }, [NHA_MASTER] = { .type = NLA_U32 }, [NHA_FDB] = { .type = NLA_FLAG }, + [NHA_OP_FLAGS] = NLA_POLICY_MASK(NLA_U32, + NHA_OP_FLAGS_DUMP_ALL), }; static const struct nla_policy rtm_nh_res_policy_new[] = { @@ -131,6 +143,7 @@ static int nh_notifier_mpath_info_init(struct nh_notifier_info *info, info->nh_grp->num_nh = num_nh; info->nh_grp->is_fdb = nhg->fdb_nh; + info->nh_grp->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh; i++) { struct nh_grp_entry *nhge = &nhg->nh_entries[i]; @@ -162,6 +175,7 @@ static int nh_notifier_res_table_info_init(struct nh_notifier_info *info, return -ENOMEM; info->nh_res_table->num_nh_buckets = num_nh_buckets; + info->nh_res_table->hw_stats = nhg->hw_stats; for (i = 0; i < num_nh_buckets; i++) { struct nh_res_bucket *bucket = &res_table->nh_buckets[i]; @@ -474,6 +488,7 @@ static void nexthop_free_group(struct nexthop *nh) struct nh_grp_entry *nhge = &nhg->nh_entries[i]; WARN_ON(!list_empty(&nhge->nh_list)); + free_percpu(nhge->stats); nexthop_put(nhge->nh); } @@ -654,8 +669,201 @@ nla_put_failure: return -EMSGSIZE; } -static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) +static void nh_grp_entry_stats_inc(struct nh_grp_entry *nhge) +{ + struct nh_grp_entry_stats *cpu_stats; + + cpu_stats = this_cpu_ptr(nhge->stats); + u64_stats_update_begin(&cpu_stats->syncp); + u64_stats_inc(&cpu_stats->packets); + u64_stats_update_end(&cpu_stats->syncp); +} + +static void nh_grp_entry_stats_read(struct nh_grp_entry *nhge, + u64 *ret_packets) +{ + int i; + + *ret_packets = 0; + + for_each_possible_cpu(i) { + struct nh_grp_entry_stats *cpu_stats; + unsigned int start; + u64 packets; + + cpu_stats = per_cpu_ptr(nhge->stats, i); + do { + start = u64_stats_fetch_begin(&cpu_stats->syncp); + packets = u64_stats_read(&cpu_stats->packets); + } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); + + *ret_packets += packets; + } +} + +static int nh_notifier_grp_hw_stats_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + info->id = nh->id; + info->type = NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS; + info->nh_grp_hw_stats = kzalloc(struct_size(info->nh_grp_hw_stats, + stats, nhg->num_nh), + GFP_KERNEL); + if (!info->nh_grp_hw_stats) + return -ENOMEM; + + info->nh_grp_hw_stats->num_nh = nhg->num_nh; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + info->nh_grp_hw_stats->stats[i].id = nhge->nh->id; + } + + return 0; +} + +static void nh_notifier_grp_hw_stats_fini(struct nh_notifier_info *info) +{ + kfree(info->nh_grp_hw_stats); +} + +void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info, + unsigned int nh_idx, + u64 delta_packets) +{ + info->hw_stats_used = true; + info->stats[nh_idx].packets += delta_packets; +} +EXPORT_SYMBOL(nh_grp_hw_stats_report_delta); + +static void nh_grp_hw_stats_apply_update(struct nexthop *nh, + struct nh_notifier_info *info) +{ + struct nh_group *nhg; + int i; + + ASSERT_RTNL(); + nhg = rtnl_dereference(nh->nh_grp); + + for (i = 0; i < nhg->num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + nhge->packets_hw += info->nh_grp_hw_stats->stats[i].packets; + } +} + +static int nh_grp_hw_stats_update(struct nexthop *nh, bool *hw_stats_used) +{ + struct nh_notifier_info info = { + .net = nh->net, + }; + struct net *net = nh->net; + int err; + + if (nexthop_notifiers_is_empty(net)) + return 0; + + err = nh_notifier_grp_hw_stats_init(&info, nh); + if (err) + return err; + + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, + NEXTHOP_EVENT_HW_STATS_REPORT_DELTA, + &info); + + /* Cache whatever we got, even if there was an error, otherwise the + * successful stats retrievals would get lost. + */ + nh_grp_hw_stats_apply_update(nh, &info); + *hw_stats_used = info.nh_grp_hw_stats->hw_stats_used; + + nh_notifier_grp_hw_stats_fini(&info); + return notifier_to_errno(err); +} + +static int nla_put_nh_group_stats_entry(struct sk_buff *skb, + struct nh_grp_entry *nhge, + u32 op_flags) +{ + struct nlattr *nest; + u64 packets; + + nh_grp_entry_stats_read(nhge, &packets); + + nest = nla_nest_start(skb, NHA_GROUP_STATS_ENTRY); + if (!nest) + return -EMSGSIZE; + + if (nla_put_u32(skb, NHA_GROUP_STATS_ENTRY_ID, nhge->nh->id) || + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS, + packets + nhge->packets_hw)) + goto nla_put_failure; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nla_put_uint(skb, NHA_GROUP_STATS_ENTRY_PACKETS_HW, + nhge->packets_hw)) + goto nla_put_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + +static int nla_put_nh_group_stats(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + struct nlattr *nest; + bool hw_stats_used; + int err; + int i; + + if (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats)) + goto err_out; + + if (op_flags & NHA_OP_FLAG_DUMP_HW_STATS && + nhg->hw_stats) { + err = nh_grp_hw_stats_update(nh, &hw_stats_used); + if (err) + goto out; + + if (nla_put_u32(skb, NHA_HW_STATS_USED, hw_stats_used)) + goto err_out; + } + + nest = nla_nest_start(skb, NHA_GROUP_STATS); + if (!nest) + goto err_out; + + for (i = 0; i < nhg->num_nh; i++) + if (nla_put_nh_group_stats_entry(skb, &nhg->nh_entries[i], + op_flags)) + goto cancel_out; + + nla_nest_end(skb, nest); + return 0; + +cancel_out: + nla_nest_cancel(skb, nest); +err_out: + err = -EMSGSIZE; +out: + return err; +} + +static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh, + u32 op_flags) { + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); struct nexthop_grp *p; size_t len = nhg->num_nh * sizeof(*p); struct nlattr *nla; @@ -684,6 +892,11 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg) if (nhg->resilient && nla_put_nh_group_res(skb, nhg)) goto nla_put_failure; + if (op_flags & NHA_OP_FLAG_DUMP_STATS && + (nla_put_u32(skb, NHA_HW_STATS_ENABLE, nhg->hw_stats) || + nla_put_nh_group_stats(skb, nh, op_flags))) + goto nla_put_failure; + return 0; nla_put_failure: @@ -691,7 +904,8 @@ nla_put_failure: } static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, - int event, u32 portid, u32 seq, unsigned int nlflags) + int event, u32 portid, u32 seq, unsigned int nlflags, + u32 op_flags) { struct fib6_nh *fib6_nh; struct fib_nh *fib_nh; @@ -718,7 +932,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, if (nhg->fdb_nh && nla_put_flag(skb, NHA_FDB)) goto nla_put_failure; - if (nla_put_nh_group(skb, nhg)) + if (nla_put_nh_group(skb, nh, op_flags)) goto nla_put_failure; goto out; } @@ -849,7 +1063,7 @@ static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info) if (!skb) goto errout; - err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags); + err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags, 0); if (err < 0) { /* -EMSGSIZE implies BUG in nh_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1104,6 +1318,7 @@ static int nh_check_attr_group(struct net *net, if (!tb[i]) continue; switch (i) { + case NHA_HW_STATS_ENABLE: case NHA_FDB: continue; case NHA_RES_GROUP: @@ -1176,6 +1391,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1185,7 +1401,7 @@ static struct nexthop *nexthop_select_path_fdb(struct nh_group *nhg, int hash) static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) { - struct nexthop *rc = NULL; + struct nh_grp_entry *nhge0 = NULL; int i; if (nhg->fdb_nh) @@ -1200,16 +1416,20 @@ static struct nexthop *nexthop_select_path_hthr(struct nh_group *nhg, int hash) if (!nexthop_is_good_nh(nhge->nh)) continue; - if (!rc) - rc = nhge->nh; + if (!nhge0) + nhge0 = nhge; if (hash > atomic_read(&nhge->hthr.upper_bound)) continue; + nh_grp_entry_stats_inc(nhge); return nhge->nh; } - return rc ? : nhg->nh_entries[0].nh; + if (!nhge0) + nhge0 = &nhg->nh_entries[0]; + nh_grp_entry_stats_inc(nhge0); + return nhge0->nh; } static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) @@ -1225,6 +1445,7 @@ static struct nexthop *nexthop_select_path_res(struct nh_group *nhg, int hash) bucket = &res_table->nh_buckets[bucket_index]; nh_res_bucket_set_busy(bucket); nhge = rcu_dereference(bucket->nh_entry); + nh_grp_entry_stats_inc(nhge); return nhge->nh; } @@ -1798,6 +2019,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, newg->has_v4 = true; list_del(&nhges[i].nh_list); + new_nhges[j].stats = nhges[i].stats; new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; new_nhges[j].weight = nhges[i].weight; @@ -1813,6 +2035,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, rcu_assign_pointer(nhp->nh_grp, newg); list_del(&nhge->nh_list); + free_percpu(nhge->stats); nexthop_put(nhge->nh); /* Removal of a NH from a resilient group is notified through @@ -2477,6 +2700,13 @@ static struct nexthop *nexthop_create_group(struct net *net, if (nhi->family == AF_INET) nhg->has_v4 = true; + nhg->nh_entries[i].stats = + netdev_alloc_pcpu_stats(struct nh_grp_entry_stats); + if (!nhg->nh_entries[i].stats) { + err = -ENOMEM; + nexthop_put(nhe); + goto out_no_nh; + } nhg->nh_entries[i].nh = nhe; nhg->nh_entries[i].weight = entry[i].weight + 1; list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list); @@ -2509,6 +2739,9 @@ static struct nexthop *nexthop_create_group(struct net *net, if (cfg->nh_fdb) nhg->fdb_nh = 1; + if (cfg->nh_hw_stats) + nhg->hw_stats = true; + rcu_assign_pointer(nh->nh_grp, nhg); return nh; @@ -2516,6 +2749,7 @@ static struct nexthop *nexthop_create_group(struct net *net, out_no_nh: for (i--; i >= 0; --i) { list_del(&nhg->nh_entries[i].nh_list); + free_percpu(nhg->nh_entries[i].stats); nexthop_put(nhg->nh_entries[i].nh); } @@ -2850,6 +3084,9 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, err = rtm_to_nh_config_grp_res(tb[NHA_RES_GROUP], cfg, extack); + if (tb[NHA_HW_STATS_ENABLE]) + cfg->nh_hw_stats = nla_get_u32(tb[NHA_HW_STATS_ENABLE]); + /* no other attributes should be set */ goto out; } @@ -2941,6 +3178,10 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb, goto out; } + if (tb[NHA_HW_STATS_ENABLE]) { + NL_SET_ERR_MSG(extack, "Cannot enable nexthop hardware statistics for non-group nexthops"); + goto out; + } err = 0; out: @@ -2966,9 +3207,9 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, return err; } -static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, - struct nlattr **tb, u32 *id, - struct netlink_ext_ack *extack) +static int nh_valid_get_del_req(const struct nlmsghdr *nlh, + struct nlattr **tb, u32 *id, u32 *op_flags, + struct netlink_ext_ack *extack) { struct nhmsg *nhm = nlmsg_data(nlh); @@ -2988,22 +3229,12 @@ static int __nh_valid_get_del_req(const struct nlmsghdr *nlh, return -EINVAL; } - return 0; -} - -static int nh_valid_get_del_req(const struct nlmsghdr *nlh, u32 *id, - struct netlink_ext_ack *extack) -{ - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get)]; - int err; - - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_get) - 1, - rtm_nh_policy_get, extack); - if (err < 0) - return err; + if (tb[NHA_OP_FLAGS]) + *op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + *op_flags = 0; - return __nh_valid_get_del_req(nlh, tb, id, extack); + return 0; } /* rtnl */ @@ -3011,16 +3242,23 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct nlattr *tb[NHA_MAX + 1]; struct nl_info nlinfo = { .nlh = nlh, .nl_net = net, .portid = NETLINK_CB(skb).portid, }; struct nexthop *nh; + u32 op_flags; int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, + rtm_nh_policy_del, extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3038,12 +3276,19 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); + struct nlattr *tb[NHA_MAX + 1]; struct sk_buff *skb = NULL; struct nexthop *nh; + u32 op_flags; int err; u32 id; - err = nh_valid_get_del_req(nlh, &id, extack); + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, + rtm_nh_policy_get, extack); + if (err < 0) + return err; + + err = nh_valid_get_del_req(nlh, tb, &id, &op_flags, extack); if (err) return err; @@ -3058,7 +3303,7 @@ static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_free; err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + nlh->nlmsg_seq, 0, op_flags); if (err < 0) { WARN_ON(err == -EMSGSIZE); goto errout_free; @@ -3079,6 +3324,7 @@ struct nh_dump_filter { bool group_filter; bool fdb_filter; u32 res_bucket_nh_id; + u32 op_flags; }; static bool nh_dump_filtered(struct nexthop *nh, @@ -3150,6 +3396,11 @@ static int __nh_valid_dump_req(const struct nlmsghdr *nlh, struct nlattr **tb, return -EINVAL; } + if (tb[NHA_OP_FLAGS]) + filter->op_flags = nla_get_u32(tb[NHA_OP_FLAGS]); + else + filter->op_flags = 0; + return 0; } @@ -3157,11 +3408,10 @@ static int nh_valid_dump_req(const struct nlmsghdr *nlh, struct nh_dump_filter *filter, struct netlink_callback *cb) { - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump)]; + struct nlattr *tb[NHA_MAX + 1]; int err; - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_dump) - 1, + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, rtm_nh_policy_dump, cb->extack); if (err < 0) return err; @@ -3223,7 +3473,7 @@ static int rtm_dump_nexthop_cb(struct sk_buff *skb, struct netlink_callback *cb, return nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); + cb->nlh->nlmsg_seq, NLM_F_MULTI, filter->op_flags); } /* rtnl */ @@ -3300,11 +3550,10 @@ static int nh_valid_dump_bucket_req(const struct nlmsghdr *nlh, struct netlink_callback *cb) { struct nlattr *res_tb[ARRAY_SIZE(rtm_nh_res_bucket_policy_dump)]; - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_dump_bucket)]; + struct nlattr *tb[NHA_MAX + 1]; int err; - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_dump_bucket) - 1, + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, rtm_nh_policy_dump_bucket, NULL); if (err < 0) return err; @@ -3474,16 +3723,16 @@ static int nh_valid_get_bucket_req(const struct nlmsghdr *nlh, u32 *id, u16 *bucket_index, struct netlink_ext_ack *extack) { - struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_get_bucket)]; + struct nlattr *tb[NHA_MAX + 1]; + u32 op_flags; int err; - err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, - ARRAY_SIZE(rtm_nh_policy_get_bucket) - 1, + err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb, NHA_MAX, rtm_nh_policy_get_bucket, extack); if (err < 0) return err; - err = __nh_valid_get_del_req(nlh, tb, id, extack); + err = nh_valid_get_del_req(nlh, tb, id, &op_flags, extack); if (err) return err; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7e1b848398d0..c5b83875411a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -279,6 +279,7 @@ #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/busy_poll.h> +#include <net/rps.h> /* Track pending CMSGs. */ enum { diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index b955ab3b236d..ebe4722bb020 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -345,15 +345,14 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff) return 0; } -static const struct net_offload tcpv4_offload = { - .callbacks = { - .gso_segment = tcp4_gso_segment, - .gro_receive = tcp4_gro_receive, - .gro_complete = tcp4_gro_complete, - }, -}; - int __init tcpv4_offload_init(void) { - return inet_add_offload(&tcpv4_offload, IPPROTO_TCP); + net_hotdata.tcpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp4_gso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.tcpv4_offload, IPPROTO_TCP); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a8acea17b4e5..2beabf5b2d86 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -411,8 +411,6 @@ INDIRECT_CALLABLE_SCOPE u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport) { - static u32 udp_ehash_secret __read_mostly; - net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); return __inet_ehashfn(laddr, lport, faddr, fport, diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 6c95d28d0c4a..b9880743765c 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -737,15 +737,14 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb); } -static const struct net_offload udpv4_offload = { - .callbacks = { - .gso_segment = udp4_ufo_fragment, - .gro_receive = udp4_gro_receive, - .gro_complete = udp4_gro_complete, - }, -}; - int __init udpv4_offload_init(void) { - return inet_add_offload(&udpv4_offload, IPPROTO_UDP); + net_hotdata.udpv4_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp4_ufo_fragment, + .gro_receive = udp4_gro_receive, + .gro_complete = udp4_gro_complete, + }, + }; + return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2f84e6ecf19f..247bd4d8ee45 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -717,7 +717,7 @@ errout: static u32 inet6_base_seq(const struct net *net) { u32 res = atomic_read(&net->ipv6.dev_addr_genid) + - net->dev_base_seq; + READ_ONCE(net->dev_base_seq); /* Must not return 0 (see nl_dump_check_consistent()). * Chose a value far away from 0. @@ -793,8 +793,6 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, ctx->all_default++; } done: - if (err < 0 && likely(skb->len)) - err = skb->len; rcu_read_unlock(); return err; } @@ -2730,7 +2728,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, if (update_lft) { ifp->valid_lft = valid_lft; ifp->prefered_lft = prefered_lft; - ifp->tstamp = now; + WRITE_ONCE(ifp->tstamp, now); flags = ifp->flags; ifp->flags &= ~IFA_F_DEPRECATED; spin_unlock_bh(&ifp->lock); @@ -4898,13 +4896,13 @@ static int inet6_addr_modify(struct net *net, struct inet6_ifaddr *ifp, IFA_F_HOMEADDRESS | IFA_F_MANAGETEMPADDR | IFA_F_NOPREFIXROUTE); ifp->flags |= cfg->ifa_flags; - ifp->tstamp = jiffies; - ifp->valid_lft = cfg->valid_lft; - ifp->prefered_lft = cfg->preferred_lft; - ifp->ifa_proto = cfg->ifa_proto; + WRITE_ONCE(ifp->tstamp, jiffies); + WRITE_ONCE(ifp->valid_lft, cfg->valid_lft); + WRITE_ONCE(ifp->prefered_lft, cfg->preferred_lft); + WRITE_ONCE(ifp->ifa_proto, cfg->ifa_proto); if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) - ifp->rt_priority = cfg->rt_priority; + WRITE_ONCE(ifp->rt_priority, cfg->rt_priority); if (new_peer) ifp->peer_addr = *cfg->peer_pfx; @@ -5125,17 +5123,21 @@ struct inet6_fill_args { enum addr_type_t type; }; -static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, +static int inet6_fill_ifaddr(struct sk_buff *skb, + const struct inet6_ifaddr *ifa, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; + struct nlmsghdr *nlh; u32 preferred, valid; + u32 flags, priority; + u8 proto; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + flags = READ_ONCE(ifa->flags); put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); @@ -5143,13 +5145,14 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto error; - spin_lock_bh(&ifa->lock); - if (!((ifa->flags&IFA_F_PERMANENT) && - (ifa->prefered_lft == INFINITY_LIFE_TIME))) { - preferred = ifa->prefered_lft; - valid = ifa->valid_lft; + preferred = READ_ONCE(ifa->prefered_lft); + valid = READ_ONCE(ifa->valid_lft); + + if (!((flags & IFA_F_PERMANENT) && + (preferred == INFINITY_LIFE_TIME))) { if (preferred != INFINITY_LIFE_TIME) { - long tval = (jiffies - ifa->tstamp)/HZ; + long tval = (jiffies - READ_ONCE(ifa->tstamp)) / HZ; + if (preferred > tval) preferred -= tval; else @@ -5165,28 +5168,29 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } - spin_unlock_bh(&ifa->lock); if (!ipv6_addr_any(&ifa->peer_addr)) { if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->peer_addr) < 0) goto error; - } else + } else { if (nla_put_in6_addr(skb, IFA_ADDRESS, &ifa->addr) < 0) goto error; + } - if (ifa->rt_priority && - nla_put_u32(skb, IFA_RT_PRIORITY, ifa->rt_priority)) + priority = READ_ONCE(ifa->rt_priority); + if (priority && nla_put_u32(skb, IFA_RT_PRIORITY, priority)) goto error; - if (put_cacheinfo(skb, ifa->cstamp, ifa->tstamp, preferred, valid) < 0) + if (put_cacheinfo(skb, ifa->cstamp, READ_ONCE(ifa->tstamp), + preferred, valid) < 0) goto error; - if (nla_put_u32(skb, IFA_FLAGS, ifa->flags) < 0) + if (nla_put_u32(skb, IFA_FLAGS, flags) < 0) goto error; - if (ifa->ifa_proto && - nla_put_u8(skb, IFA_PROTO, ifa->ifa_proto)) + proto = READ_ONCE(ifa->ifa_proto); + if (proto && nla_put_u8(skb, IFA_PROTO, proto)) goto error; nlmsg_end(skb, nlh); @@ -5197,12 +5201,13 @@ error: return -EMSGSIZE; } -static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, +static int inet6_fill_ifmcaddr(struct sk_buff *skb, + const struct ifmcaddr6 *ifmca, struct inet6_fill_args *args) { - struct nlmsghdr *nlh; - u8 scope = RT_SCOPE_UNIVERSE; int ifindex = ifmca->idev->dev->ifindex; + u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5220,7 +5225,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || - put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, + put_cacheinfo(skb, ifmca->mca_cstamp, READ_ONCE(ifmca->mca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5230,13 +5235,14 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, return 0; } -static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, +static int inet6_fill_ifacaddr(struct sk_buff *skb, + const struct ifacaddr6 *ifaca, struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; - struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; + struct nlmsghdr *nlh; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5254,7 +5260,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || - put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, + put_cacheinfo(skb, ifaca->aca_cstamp, READ_ONCE(ifaca->aca_tstamp), INFINITY_LIFE_TIME, INFINITY_LIFE_TIME) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; @@ -5265,24 +5271,23 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, } /* called with rcu_read_lock() */ -static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, - struct netlink_callback *cb, int s_ip_idx, +static int in6_dump_addrs(const struct inet6_dev *idev, struct sk_buff *skb, + struct netlink_callback *cb, int *s_ip_idx, struct inet6_fill_args *fillargs) { - struct ifmcaddr6 *ifmca; - struct ifacaddr6 *ifaca; + const struct ifmcaddr6 *ifmca; + const struct ifacaddr6 *ifaca; int ip_idx = 0; - int err = 1; + int err = 0; - read_lock_bh(&idev->lock); switch (fillargs->type) { case UNICAST_ADDR: { - struct inet6_ifaddr *ifa; + const struct inet6_ifaddr *ifa; fillargs->event = RTM_NEWADDR; /* unicast address incl. temp addr */ - list_for_each_entry(ifa, &idev->addr_list, if_list) { - if (ip_idx < s_ip_idx) + list_for_each_entry_rcu(ifa, &idev->addr_list, if_list) { + if (ip_idx < *s_ip_idx) goto next; err = inet6_fill_ifaddr(skb, ifa, fillargs); if (err < 0) @@ -5294,27 +5299,25 @@ next: break; } case MULTICAST_ADDR: - read_unlock_bh(&idev->lock); fillargs->event = RTM_GETMULTICAST; /* multicast address */ for (ifmca = rcu_dereference(idev->mc_list); ifmca; ifmca = rcu_dereference(ifmca->next), ip_idx++) { - if (ip_idx < s_ip_idx) + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, fillargs); if (err < 0) break; } - read_lock_bh(&idev->lock); break; case ANYCAST_ADDR: fillargs->event = RTM_GETANYCAST; /* anycast address */ for (ifaca = rcu_dereference(idev->ac_list); ifaca; ifaca = rcu_dereference(ifaca->aca_next), ip_idx++) { - if (ip_idx < s_ip_idx) + if (ip_idx < *s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, fillargs); if (err < 0) @@ -5324,8 +5327,7 @@ next: default: break; } - read_unlock_bh(&idev->lock); - cb->args[2] = ip_idx; + *s_ip_idx = err ? ip_idx : 0; return err; } @@ -5388,6 +5390,7 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh, static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { + struct net *tgt_net = sock_net(skb->sk); const struct nlmsghdr *nlh = cb->nlh; struct inet6_fill_args fillargs = { .portid = NETLINK_CB(cb->skb).portid, @@ -5396,72 +5399,52 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, .netnsid = -1, .type = type, }; - struct net *tgt_net = sock_net(skb->sk); - int idx, s_idx, s_ip_idx; - int h, s_h; + struct { + unsigned long ifindex; + int ip_idx; + } *ctx = (void *)cb->ctx; struct net_device *dev; struct inet6_dev *idev; - struct hlist_head *head; int err = 0; - s_h = cb->args[0]; - s_idx = idx = cb->args[1]; - s_ip_idx = cb->args[2]; - rcu_read_lock(); if (cb->strict_check) { err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net, skb->sk, cb); if (err < 0) - goto put_tgt_net; + goto done; err = 0; if (fillargs.ifindex) { - dev = __dev_get_by_index(tgt_net, fillargs.ifindex); - if (!dev) { - err = -ENODEV; - goto put_tgt_net; - } + err = -ENODEV; + dev = dev_get_by_index_rcu(tgt_net, fillargs.ifindex); + if (!dev) + goto done; idev = __in6_dev_get(dev); - if (idev) { - err = in6_dump_addrs(idev, skb, cb, s_ip_idx, + if (idev) + err = in6_dump_addrs(idev, skb, cb, + &ctx->ip_idx, &fillargs); - if (err > 0) - err = 0; - } - goto put_tgt_net; + goto done; } } cb->seq = inet6_base_seq(tgt_net); - for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { - idx = 0; - head = &tgt_net->dev_index_head[h]; - hlist_for_each_entry_rcu(dev, head, index_hlist) { - if (idx < s_idx) - goto cont; - if (h > s_h || idx > s_idx) - s_ip_idx = 0; - idev = __in6_dev_get(dev); - if (!idev) - goto cont; - - if (in6_dump_addrs(idev, skb, cb, s_ip_idx, - &fillargs) < 0) - goto done; -cont: - idx++; - } + for_each_netdev_dump(tgt_net, dev, ctx->ifindex) { + idev = __in6_dev_get(dev); + if (!idev) + continue; + err = in6_dump_addrs(idev, skb, cb, &ctx->ip_idx, + &fillargs); + if (err < 0) + goto done; } done: - cb->args[0] = h; - cb->args[1] = idx; -put_tgt_net: rcu_read_unlock(); if (fillargs.netnsid >= 0) put_net(tgt_net); - return skb->len ? : err; + return err; } static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) @@ -6158,11 +6141,8 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI); - if (err < 0) { - if (likely(skb->len)) - err = skb->len; + if (err < 0) break; - } } rcu_read_unlock(); @@ -7474,15 +7454,18 @@ int __init addrconf_init(void) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr, - RTNL_FLAG_DOIT_UNLOCKED); + RTNL_FLAG_DOIT_UNLOCKED | + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETMULTICAST, - NULL, inet6_dump_ifmcaddr, 0); + NULL, inet6_dump_ifmcaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETANYCAST, - NULL, inet6_dump_ifacaddr, 0); + NULL, inet6_dump_ifacaddr, + RTNL_FLAG_DUMP_UNLOCKED); if (err < 0) goto errout; err = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETNETCONF, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b90d46533cdc..8041dc181bd4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -64,6 +64,7 @@ #include <net/xfrm.h> #include <net/ioam6.h> #include <net/rawv6.h> +#include <net/rps.h> #include <linux/uaccess.h> #include <linux/mroute6.h> diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b0e8d278e8a9..2e81383b663b 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -14,6 +14,7 @@ #include <linux/random.h> #include <net/addrconf.h> +#include <net/hotdata.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> @@ -25,16 +26,13 @@ u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { - static u32 inet6_ehash_secret __read_mostly; - static u32 ipv6_hash_secret __read_mostly; - u32 lhash, fhash; net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); - net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); + net_get_random_once(&tcp_ipv6_hash_secret, sizeof(tcp_ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; - fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); + fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index cca64c7809be..b41e35af69ea 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -419,14 +419,6 @@ static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff) return inet_gro_complete(skb, nhoff); } -static struct packet_offload ipv6_packet_offload __read_mostly = { - .type = cpu_to_be16(ETH_P_IPV6), - .callbacks = { - .gso_segment = ipv6_gso_segment, - .gro_receive = ipv6_gro_receive, - .gro_complete = ipv6_gro_complete, - }, -}; static struct sk_buff *sit_gso_segment(struct sk_buff *skb, netdev_features_t features) @@ -486,7 +478,15 @@ static int __init ipv6_offload_init(void) if (ipv6_exthdrs_offload_init() < 0) pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__); - dev_add_offload(&ipv6_packet_offload); + net_hotdata.ipv6_packet_offload = (struct packet_offload) { + .type = cpu_to_be16(ETH_P_IPV6), + .callbacks = { + .gso_segment = ipv6_gso_segment, + .gro_receive = ipv6_gro_receive, + .gro_complete = ipv6_gro_complete, + }, + }; + dev_add_offload(&net_hotdata.ipv6_packet_offload); inet_add_offload(&sit_offload, IPPROTO_IPV6); inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2cecb1c5a58f..1f4b935a0e57 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5343,19 +5343,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); - fib6_info_release(nh->fib6_info); - - if (!err) { - /* save reference to last route successfully inserted */ - rt_last = nh->fib6_info; - - /* save reference to first route for notification */ - if (!rt_notif) - rt_notif = nh->fib6_info; - } - /* nh->fib6_info is used or freed at this point, reset to NULL*/ - nh->fib6_info = NULL; if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, @@ -5363,6 +5351,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = nh; goto add_errout; } + /* save reference to last route successfully inserted */ + rt_last = nh->fib6_info; + + /* save reference to first route for notification */ + if (!rt_notif) + rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, @@ -5423,8 +5417,7 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->fib6_info) - fib6_info_release(nh->fib6_info); + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f677f0fa5196..3f4cba49e9ee 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -58,6 +58,7 @@ #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> +#include <net/hotdata.h> #include <net/busy_poll.h> #include <linux/proc_fs.h> @@ -2367,11 +2368,6 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -static const struct inet6_protocol tcpv6_protocol = { - .handler = tcp_v6_rcv, - .err_handler = tcp_v6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; static struct inet_protosw tcpv6_protosw = { .type = SOCK_STREAM, @@ -2408,7 +2404,12 @@ int __init tcpv6_init(void) { int ret; - ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP); + net_hotdata.tcpv6_protocol = (struct inet6_protocol) { + .handler = tcp_v6_rcv, + .err_handler = tcp_v6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); if (ret) goto out; @@ -2433,7 +2434,7 @@ out_tcpv6_pernet_subsys: out_tcpv6_protosw: inet6_unregister_protosw(&tcpv6_protosw); out_tcpv6_protocol: - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); goto out; } @@ -2441,5 +2442,5 @@ void tcpv6_exit(void) { unregister_pernet_subsys(&tcpv6_net_ops); inet6_unregister_protosw(&tcpv6_protosw); - inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP); + inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP); } diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index bf0c957e4b5e..4b07d1e6c952 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -66,15 +66,15 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb, return tcp_gso_segment(skb, features); } -static const struct net_offload tcpv6_offload = { - .callbacks = { - .gso_segment = tcp6_gso_segment, - .gro_receive = tcp6_gro_receive, - .gro_complete = tcp6_gro_complete, - }, -}; int __init tcpv6_offload_init(void) { - return inet6_add_offload(&tcpv6_offload, IPPROTO_TCP); + net_hotdata.tcpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = tcp6_gso_segment, + .gro_receive = tcp6_gro_receive, + .gro_complete = tcp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.tcpv6_offload, IPPROTO_TCP); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3f2249b4cd5f..80ad8f436b17 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -79,9 +79,6 @@ u32 udp6_ehashfn(const struct net *net, const struct in6_addr *faddr, const __be16 fport) { - static u32 udp6_ehash_secret __read_mostly; - static u32 udp_ipv6_hash_secret __read_mostly; - u32 lhash, fhash; net_get_random_once(&udp6_ehash_secret, @@ -1702,11 +1699,6 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -static const struct inet6_protocol udpv6_protocol = { - .handler = udpv6_rcv, - .err_handler = udpv6_err, - .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, -}; /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS @@ -1803,7 +1795,12 @@ int __init udpv6_init(void) { int ret; - ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP); + net_hotdata.udpv6_protocol = (struct inet6_protocol) { + .handler = udpv6_rcv, + .err_handler = udpv6_err, + .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, + }; + ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); if (ret) goto out; @@ -1814,12 +1811,12 @@ out: return ret; out_udpv6_protocol: - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); goto out; } void udpv6_exit(void) { inet6_unregister_protosw(&udpv6_protosw); - inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP); + inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP); } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 6b95ba241ebe..312bcaeea96f 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -192,20 +192,19 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb); } -static const struct net_offload udpv6_offload = { - .callbacks = { - .gso_segment = udp6_ufo_fragment, - .gro_receive = udp6_gro_receive, - .gro_complete = udp6_gro_complete, - }, -}; - -int udpv6_offload_init(void) +int __init udpv6_offload_init(void) { - return inet6_add_offload(&udpv6_offload, IPPROTO_UDP); + net_hotdata.udpv6_offload = (struct net_offload) { + .callbacks = { + .gso_segment = udp6_ufo_fragment, + .gro_receive = udp6_gro_receive, + .gro_complete = udp6_gro_complete, + }, + }; + return inet6_add_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } int udpv6_offload_exit(void) { - return inet6_del_offload(&udpv6_offload, IPPROTO_UDP); + return inet6_del_offload(&net_hotdata.udpv6_offload, IPPROTO_UDP); } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f6cb94f82cc3..bf140ef781c1 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -355,10 +355,7 @@ static int __init xfrm6_tunnel_init(void) { int rv; - xfrm6_tunnel_spi_kmem = kmem_cache_create("xfrm6_tunnel_spi", - sizeof(struct xfrm6_tunnel_spi), - 0, SLAB_HWCACHE_ALIGN, - NULL); + xfrm6_tunnel_spi_kmem = KMEM_CACHE(xfrm6_tunnel_spi, SLAB_HWCACHE_ALIGN); if (!xfrm6_tunnel_spi_kmem) return -ENOMEM; rv = register_pernet_subsys(&xfrm6_tunnel_net_ops); diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index ef59e25dc482..8fc790f2a01b 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -55,8 +55,6 @@ static int mpls_xmit(struct sk_buff *skb) out_dev = dst->dev; net = dev_net(out_dev); - skb_orphan(skb); - if (!mpls_output_possible(out_dev) || !dst->lwtstate || skb_warn_if_lro(skb)) goto drop; diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 7017dd60659d..3ae46b545d2c 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -10,7 +10,6 @@ #include <linux/net.h> #include <linux/inet_diag.h> #include <net/netlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" static int subflow_get_info(struct sock *sk, struct sk_buff *skb) diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index bd8ff5950c8d..0566dd793810 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -10,7 +10,6 @@ #include <linux/net.h> #include <linux/inet_diag.h> #include <net/netlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index b4bdd92a5648..55406720c607 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -6,7 +6,6 @@ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/kernel.h> -#include <net/tcp.h> #include <net/mptcp.h> #include "protocol.h" @@ -457,13 +456,11 @@ int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) return mptcp_pm_nl_dump_addr(msg, cb); } -int mptcp_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup) +int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info) { - if (token) - return mptcp_userspace_pm_set_flags(net, token, loc, rem, bkup); - return mptcp_pm_nl_set_flags(net, loc, bkup); + if (info->attrs[MPTCP_PM_ATTR_TOKEN]) + return mptcp_userspace_pm_set_flags(skb, info); + return mptcp_pm_nl_set_flags(skb, info); } void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 16f8bd47f4b8..5c17d39146ea 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -8,12 +8,9 @@ #include <linux/inet.h> #include <linux/kernel.h> -#include <net/tcp.h> #include <net/inet_common.h> #include <net/netns/generic.h> #include <net/mptcp.h> -#include <net/genetlink.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" @@ -502,15 +499,12 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) } static struct mptcp_pm_addr_entry * -__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info, - bool lookup_by_id) +__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) { struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, &pernet->local_addr_list, list) { - if ((!lookup_by_id && - mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) || - (lookup_by_id && entry->addr.id == info->id)) + if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) return entry; } return NULL; @@ -540,7 +534,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) mptcp_local_address((struct sock_common *)msk->first, &mpc_addr); rcu_read_lock(); - entry = __lookup_addr(pernet, &mpc_addr, false); + entry = __lookup_addr(pernet, &mpc_addr); if (entry) { __clear_bit(entry->addr.id, msk->pm.id_avail_bitmap); msk->mpc_endpoint_id = entry->addr.id; @@ -1890,66 +1884,63 @@ next: return ret; } -int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup) +int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info) { - struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); + struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | MPTCP_PM_ADDR_FLAG_FULLMESH; + struct net *net = sock_net(skb->sk); struct mptcp_pm_addr_entry *entry; + struct pm_nl_pernet *pernet; u8 lookup_by_id = 0; + u8 bkup = 0; + int ret; + + pernet = pm_nl_get_pernet(net); - if (addr->addr.family == AF_UNSPEC) { + ret = mptcp_pm_parse_entry(attr, info, false, &addr); + if (ret < 0) + return ret; + + if (addr.addr.family == AF_UNSPEC) { lookup_by_id = 1; - if (!addr->addr.id) + if (!addr.addr.id) { + GENL_SET_ERR_MSG(info, "missing required inputs"); return -EOPNOTSUPP; + } } + if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; + spin_lock_bh(&pernet->lock); - entry = __lookup_addr(pernet, &addr->addr, lookup_by_id); + entry = lookup_by_id ? __lookup_addr_by_id(pernet, addr.addr.id) : + __lookup_addr(pernet, &addr.addr); if (!entry) { spin_unlock_bh(&pernet->lock); + GENL_SET_ERR_MSG(info, "address not found"); return -EINVAL; } - if ((addr->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && + if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { spin_unlock_bh(&pernet->lock); + GENL_SET_ERR_MSG(info, "invalid addr flags"); return -EINVAL; } - changed = (addr->flags ^ entry->flags) & mask; - entry->flags = (entry->flags & ~mask) | (addr->flags & mask); - *addr = *entry; + changed = (addr.flags ^ entry->flags) & mask; + entry->flags = (entry->flags & ~mask) | (addr.flags & mask); + addr = *entry; spin_unlock_bh(&pernet->lock); - mptcp_nl_set_flags(net, &addr->addr, bkup, changed); + mptcp_nl_set_flags(net, &addr.addr, bkup, changed); return 0; } int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { - struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; - struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; - struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; - struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct net *net = sock_net(skb->sk); - u8 bkup = 0; - int ret; - - ret = mptcp_pm_parse_entry(attr, info, false, &addr); - if (ret < 0) - return ret; - - if (attr_rem) { - ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote); - if (ret < 0) - return ret; - } - - if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) - bkup = 1; - - return mptcp_pm_set_flags(net, token, &addr, &remote, bkup); + return mptcp_pm_set_flags(skb, info); } static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index b9809d988693..9f5d422d5ef6 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -546,32 +546,57 @@ destroy_err: return err; } -int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup) +int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info) { + struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, }; + struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, }; + struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; + struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; + struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct net *net = sock_net(skb->sk); struct mptcp_sock *msk; int ret = -EINVAL; struct sock *sk; u32 token_val; + u8 bkup = 0; token_val = nla_get_u32(token); msk = mptcp_token_get_sock(net, token_val); - if (!msk) + if (!msk) { + NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token"); return ret; + } sk = (struct sock *)msk; - if (!mptcp_pm_is_userspace(msk)) + if (!mptcp_pm_is_userspace(msk)) { + GENL_SET_ERR_MSG(info, "userspace PM not selected"); + goto set_flags_err; + } + + ret = mptcp_pm_parse_entry(attr, info, false, &loc); + if (ret < 0) goto set_flags_err; - if (loc->addr.family == AF_UNSPEC || - rem->addr.family == AF_UNSPEC) + if (attr_rem) { + ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem); + if (ret < 0) + goto set_flags_err; + } + + if (loc.addr.family == AF_UNSPEC || + rem.addr.family == AF_UNSPEC) { + GENL_SET_ERR_MSG(info, "invalid address families"); + ret = -EINVAL; goto set_flags_err; + } + + if (loc.flags & MPTCP_PM_ADDR_FLAG_BACKUP) + bkup = 1; lock_sock(sk); - ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup); + ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup); release_sock(sk); set_flags_err: diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 99367c40de0d..3a1967bc7bad 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -15,7 +15,6 @@ #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> -#include <net/tcp.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index de9f0ff6dd30..f16edef6026a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -970,13 +970,9 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex); -int mptcp_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup); -int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup); -int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, - struct mptcp_pm_addr_entry *loc, - struct mptcp_pm_addr_entry *rem, u8 bkup); +int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info); +int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info); int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 6403c56f2902..1626dd20c68f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -15,13 +15,11 @@ #include <net/inet_common.h> #include <net/inet_hashtables.h> #include <net/protocol.h> -#include <net/tcp.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/ip6_route.h> #include <net/transp_v6.h> #endif #include <net/mptcp.h> -#include <uapi/linux/mptcp.h> #include "protocol.h" #include "mib.h" diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index e697a824b001..540d97715bd2 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Get fields bitmap */ if (nf_h323_error_boundary(bs, 0, f->sz)) return H323_ERROR_BOUND; + if (f->sz > 32) + return H323_ERROR_RANGE; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, bmp2_len = get_bits(bs, 7) + 1; if (nf_h323_error_boundary(bs, 0, bmp2_len)) return H323_ERROR_BOUND; + if (bmp2_len > 32) + return H323_ERROR_RANGE; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 224e5fb6a916..e93f905e60b6 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5008,6 +5008,12 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == + (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } desc.dtype = 0; @@ -5431,6 +5437,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index bfd3e5a14dab..255640013ab8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1256,14 +1256,13 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, switch (priv->l3num) { case NFPROTO_IPV4: case NFPROTO_IPV6: - if (priv->l3num != ctx->family) - return -EINVAL; + if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET) + break; - fallthrough; - case NFPROTO_INET: - break; + return -EINVAL; + case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */ default: - return -EOPNOTSUPP; + return -EAFNOSUPPORT; } priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 0eed00184adf..104a80b75477 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, nr_init_timers(sk); nr->t1 = - msecs_to_jiffies(sysctl_netrom_transport_timeout); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout)); nr->t2 = - msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay)); nr->n2 = - msecs_to_jiffies(sysctl_netrom_transport_maximum_tries); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries)); nr->t4 = - msecs_to_jiffies(sysctl_netrom_transport_busy_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay)); nr->idle = - msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout); - nr->window = sysctl_netrom_transport_requested_window_size; + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout)); + nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size); nr->bpqext = 1; nr->state = NR_STATE_0; @@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) * G8PZT's Xrouter which is sending packets with command type 7 * as an extension of the protocol. */ - if (sysctl_netrom_reset_circuit && + if (READ_ONCE(sysctl_netrom_reset_circuit) && (frametype != NR_RESET || flags != 0)) nr_transmit_reset(skb, 1); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 3aaac4a22b38..2c34389c3ce6 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev, buff[6] |= AX25_SSSID_SPARE; buff += AX25_ADDR_LEN; - *buff++ = sysctl_netrom_network_ttl_initialiser; + *buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); *buff++ = NR_PROTO_IP; *buff++ = NR_PROTO_IP; diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 2f084b6f69d7..97944db6b5ac 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -262,7 +262,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 44929657f5b7..5e531394a724 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (!nr_route_frame(skb, NULL)) { kfree_skb(skb); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index baea3cbd76ca..70480869ad1c 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->digipeat = NULL; nr_neigh->ax25 = NULL; nr_neigh->dev = dev; - nr_neigh->quality = sysctl_netrom_default_path_quality; + nr_neigh->quality = READ_ONCE(sysctl_netrom_default_path_quality); nr_neigh->locked = 0; nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; @@ -728,7 +728,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) nr_neigh->ax25 = NULL; ax25_cb_put(ax25); - if (++nr_neigh->failed < sysctl_netrom_link_fails_count) { + if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) { nr_neigh_put(nr_neigh); return; } @@ -766,7 +766,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (ax25 != NULL) { ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat, ax25->ax25_dev->dev, 0, - sysctl_netrom_obsolescence_count_initialiser); + READ_ONCE(sysctl_netrom_obsolescence_count_initialiser)); if (ret) return ret; } @@ -780,7 +780,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) return ret; } - if (!sysctl_netrom_routing_control && ax25 != NULL) + if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL) return 0; /* Its Time-To-Live has expired */ diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index e2d2af924cff..c3bbd5880850 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype) *dptr++ = nr->my_id; *dptr++ = frametype; *dptr++ = nr->window; - if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser; + if (nr->bpqext) + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); break; case NR_DISCREQ: @@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (mine) { *dptr++ = 0; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index fba82d36593a..a4e3c5de998b 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, kfree(sg); } ret = PTR_ERR(trans_private); + /* Trigger connection so that its ready for the next retry */ + if (ret == -ENODEV) + rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/rds/send.c b/net/rds/send.c index 5e57a1581dc6..2899def23865 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1313,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); - if (ret) { - /* Trigger connection so that its ready for the next retry */ - if (ret == -EAGAIN) - rds_conn_connect_if_down(conn); + if (ret) goto out; - } if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 465bfe5eb061..5222bc97d192 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -487,7 +487,7 @@ EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); * rxrpc_kernel_set_max_life - Set maximum lifespan on a call * @sock: The socket the call is on * @call: The call to configure - * @hard_timeout: The maximum lifespan of the call in jiffies + * @hard_timeout: The maximum lifespan of the call in ms * * Set the maximum lifespan of a call. The call will end with ETIME or * ETIMEDOUT if it takes longer than this. @@ -495,14 +495,14 @@ EXPORT_SYMBOL(rxrpc_kernel_new_call_notification); void rxrpc_kernel_set_max_life(struct socket *sock, struct rxrpc_call *call, unsigned long hard_timeout) { - unsigned long now; + ktime_t delay = ms_to_ktime(hard_timeout), expect_term_by; mutex_lock(&call->user_mutex); - now = jiffies; - hard_timeout += now; - WRITE_ONCE(call->expect_term_by, hard_timeout); - rxrpc_reduce_call_timer(call, hard_timeout, now, rxrpc_timer_set_for_hard); + expect_term_by = ktime_add(ktime_get_real(), delay); + WRITE_ONCE(call->expect_term_by, expect_term_by); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + rxrpc_poke_call(call, rxrpc_call_poke_set_timeout); mutex_unlock(&call->user_mutex); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7818aae1be8e..08c0a32db8c7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -198,8 +198,8 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ union { + struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ struct { u16 offset; /* Offset of data */ u16 len; /* Length of data */ @@ -208,9 +208,12 @@ struct rxrpc_skb_priv { }; struct { rxrpc_seq_t first_ack; /* First packet in acks table */ + rxrpc_seq_t prev_ack; /* Highest seq seen */ + rxrpc_serial_t acked_serial; /* Packet in response to (or 0) */ + u8 reason; /* Reason for ack */ u8 nr_acks; /* Number of acks+nacks */ u8 nr_nacks; /* Number of nacks */ - }; + } ack; }; struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; @@ -248,10 +251,9 @@ struct rxrpc_security { struct rxrpc_key_token *); /* Work out how much data we can store in a packet, given an estimate - * of the amount of data remaining. + * of the amount of data remaining and allocate a data buffer. */ - int (*how_much_data)(struct rxrpc_call *, size_t, - size_t *, size_t *, size_t *); + struct rxrpc_txbuf *(*alloc_txbuf)(struct rxrpc_call *call, size_t remaining, gfp_t gfp); /* impose security on a packet */ int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); @@ -292,6 +294,7 @@ struct rxrpc_local { struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ + struct page_frag_cache tx_alloc; /* Tx control packet allocation (I/O thread only) */ struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY struct sk_buff_head rx_delay_queue; /* Delay injection queue */ @@ -352,8 +355,8 @@ struct rxrpc_peer { u32 mdev_us; /* medium deviation */ u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ - u32 rto_j; /* Retransmission timeout in jiffies */ - u8 backoff; /* Backoff timeout */ + u32 rto_us; /* Retransmission timeout in usec */ + u8 backoff; /* Backoff timeout (as shift) */ u8 cong_ssthresh; /* Congestion slow-start threshold */ }; @@ -500,6 +503,8 @@ struct rxrpc_connection { struct list_head proc_link; /* link in procfs list */ struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ + struct page_frag_cache tx_data_alloc; /* Tx DATA packet allocation */ + struct mutex tx_data_alloc_lock; struct mutex security_lock; /* Lock for security management */ const struct rxrpc_security *security; /* applied security module */ @@ -618,17 +623,17 @@ struct rxrpc_call { const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ struct sockaddr_rxrpc dest_srx; /* Destination address */ - unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ - unsigned long ack_lost_at; /* When ACK is figured as lost */ - unsigned long resend_at; /* When next resend needs to happen */ - unsigned long ping_at; /* When next to send a ping */ - unsigned long keepalive_at; /* When next to send a keepalive ping */ - unsigned long expect_rx_by; /* When we expect to get a packet by */ - unsigned long expect_req_by; /* When we expect to get a request DATA packet by */ - unsigned long expect_term_by; /* When we expect call termination by */ - u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ - u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ - u32 hard_timo; /* Maximum lifetime or 0 (jif) */ + ktime_t delay_ack_at; /* When DELAY ACK needs to happen */ + ktime_t ack_lost_at; /* When ACK is figured as lost */ + ktime_t resend_at; /* When next resend needs to happen */ + ktime_t ping_at; /* When next to send a ping */ + ktime_t keepalive_at; /* When next to send a keepalive ping */ + ktime_t expect_rx_by; /* When we expect to get a packet by */ + ktime_t expect_req_by; /* When we expect to get a request DATA packet by */ + ktime_t expect_term_by; /* When we expect call termination by */ + u32 next_rx_timo; /* Timeout for next Rx packet (ms) */ + u32 next_req_timo; /* Timeout for next Rx request packet (ms) */ + u32 hard_timo; /* Maximum lifetime or 0 (s) */ struct timer_list timer; /* Combined event timer */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ @@ -673,7 +678,7 @@ struct rxrpc_call { rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_prepared; /* Highest Tx slot prepared. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ - u16 tx_backoff; /* Delay to insert due to Tx failure */ + u16 tx_backoff; /* Delay to insert due to Tx failure (ms) */ u8 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 ktime_t tx_last_sent; /* Last time a transmission occurred */ @@ -788,40 +793,30 @@ struct rxrpc_send_params { * Buffer of data to be output as a packet. */ struct rxrpc_txbuf { - struct rcu_head rcu; struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ ktime_t last_sent; /* Time at which last transmitted */ refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ + rxrpc_serial_t serial; /* Last serial number transmitted with */ unsigned int call_debug_id; unsigned int debug_id; unsigned int len; /* Amount of data in buffer */ unsigned int space; /* Remaining data space */ unsigned int offset; /* Offset of fill point */ - unsigned long flags; -#define RXRPC_TXBUF_LAST 0 /* Set if last packet in Tx phase */ -#define RXRPC_TXBUF_RESENT 1 /* Set if has been resent */ + unsigned int flags; +#define RXRPC_TXBUF_WIRE_FLAGS 0xff /* The wire protocol flags */ +#define RXRPC_TXBUF_RESENT 0x100 /* Set if has been resent */ + __be16 cksum; /* Checksum to go in header */ + unsigned short ack_rwind; /* ACK receive window */ u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ - struct { - /* The packet for encrypting and DMA'ing. We align it such - * that data[] aligns correctly for any crypto blocksize. - */ - u8 pad[64 - sizeof(struct rxrpc_wire_header)]; - struct rxrpc_wire_header wire; /* Network-ready header */ - union { - u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ - struct { - struct rxrpc_ackpacket ack; - DECLARE_FLEX_ARRAY(u8, acks); - }; - }; - } __aligned(64); + u8 nr_kvec; /* Amount of kvec[] used */ + struct kvec kvec[3]; }; static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) { - return txb->wire.flags & RXRPC_CLIENT_INITIATED; + return txb->flags & RXRPC_CLIENT_INITIATED; } static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) @@ -869,17 +864,11 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); */ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); -void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb); -void rxrpc_reduce_call_timer(struct rxrpc_call *call, - unsigned long expire_at, - unsigned long now, - enum rxrpc_timer_trace why); - bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); /* @@ -1160,9 +1149,9 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb); +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why); int rxrpc_send_abort_packet(struct rxrpc_call *); -int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); @@ -1223,7 +1212,7 @@ static inline int rxrpc_abort_eproto(struct rxrpc_call *call, */ void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, int, rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); -unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); +ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans); void rxrpc_peer_init_rtt(struct rxrpc_peer *); /* @@ -1295,8 +1284,9 @@ static inline void rxrpc_sysctl_exit(void) {} * txbuf.c */ extern atomic_t rxrpc_nr_txbuf; -struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, - gfp_t gfp); +struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, + size_t data_align, gfp_t gfp); +struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size); void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 0f78544d043b..7bbb68504766 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -23,14 +23,14 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why) { - unsigned long now = jiffies; - unsigned long ping_at = now + rxrpc_idle_ack_delay; - - if (time_before(ping_at, call->ping_at)) { - WRITE_ONCE(call->ping_at, ping_at); - rxrpc_reduce_call_timer(call, ping_at, now, - rxrpc_timer_set_for_ping); - trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); + ktime_t delay = ms_to_ktime(READ_ONCE(rxrpc_idle_ack_delay)); + ktime_t now = ktime_get_real(); + ktime_t ping_at = ktime_add(now, delay); + + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); + if (ktime_before(ping_at, call->ping_at)) { + call->ping_at = ping_at; + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_ping); } } @@ -40,62 +40,18 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) { - unsigned long expiry = rxrpc_soft_ack_delay; - unsigned long now = jiffies, ack_at; - - if (rxrpc_soft_ack_delay < expiry) - expiry = rxrpc_soft_ack_delay; - if (call->peer->srtt_us != 0) - ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); - else - ack_at = expiry; - - ack_at += READ_ONCE(call->tx_backoff); - ack_at += now; - if (time_before(ack_at, call->delay_ack_at)) { - WRITE_ONCE(call->delay_ack_at, ack_at); - rxrpc_reduce_call_timer(call, ack_at, now, - rxrpc_timer_set_for_ack); - } + ktime_t now = ktime_get_real(), delay; trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); -} - -/* - * Queue an ACK for immediate transmission. - */ -void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, - rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) -{ - struct rxrpc_txbuf *txb; - - if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - return; - - rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK, - rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS); - if (!txb) { - kleave(" = -ENOMEM"); - return; - } + if (call->peer->srtt_us) + delay = (call->peer->srtt_us >> 3) * NSEC_PER_USEC; + else + delay = ms_to_ktime(READ_ONCE(rxrpc_soft_ack_delay)); + ktime_add_ms(delay, call->tx_backoff); - txb->ack_why = why; - txb->wire.seq = 0; - txb->wire.type = RXRPC_PACKET_TYPE_ACK; - txb->wire.flags |= RXRPC_SLOW_START_OK; - txb->ack.bufferSpace = 0; - txb->ack.maxSkew = 0; - txb->ack.firstPacket = 0; - txb->ack.previousPacket = 0; - txb->ack.serial = htonl(serial); - txb->ack.reason = ack_reason; - txb->ack.nAcks = 0; - - trace_rxrpc_send_ack(call, why, ack_reason, serial); - rxrpc_send_ack_packet(call, txb); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + call->delay_ack_at = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_delayed_ack); } /* @@ -114,25 +70,19 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) struct rxrpc_ackpacket *ack = NULL; struct rxrpc_skb_priv *sp; struct rxrpc_txbuf *txb; - unsigned long resend_at; - rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); - ktime_t now, max_age, oldest, ack_ts; - bool unacked = false; + rxrpc_seq_t transmitted = call->tx_transmitted; + ktime_t next_resend = KTIME_MAX, rto = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); + ktime_t resend_at = KTIME_MAX, now, delay; + bool unacked = false, did_send = false; unsigned int i; - LIST_HEAD(retrans_queue); _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); - max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); - oldest = now; if (list_empty(&call->tx_buffer)) goto no_resend; - if (list_empty(&call->tx_buffer)) - goto no_further_resend; - trace_rxrpc_resend(call, ack_skb); txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); @@ -143,12 +93,12 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) sp = rxrpc_skb(ack_skb); ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { rxrpc_seq_t seq; if (ack->acks[i] & 1) continue; - seq = sp->first_ack + i; + seq = sp->ack.first_ack + i; if (after(txb->seq, transmitted)) break; if (after(txb->seq, seq)) @@ -160,19 +110,23 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) goto no_further_resend; found_txb: - if (after(ntohl(txb->wire.serial), call->acks_highest_serial)) + resend_at = ktime_add(txb->last_sent, rto); + if (after(txb->serial, call->acks_highest_serial)) { + if (ktime_after(resend_at, now) && + ktime_before(resend_at, next_resend)) + next_resend = resend_at; continue; /* Ack point not yet reached */ + } rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); - if (list_empty(&txb->tx_link)) { - list_add_tail(&txb->tx_link, &retrans_queue); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - } + trace_rxrpc_retransmit(call, txb->seq, txb->serial, + ktime_sub(resend_at, now)); - trace_rxrpc_retransmit(call, txb->seq, - ktime_to_ns(ktime_sub(txb->last_sent, - max_age))); + txb->flags |= RXRPC_TXBUF_RESENT; + rxrpc_transmit_one(call, txb); + did_send = true; + now = ktime_get_real(); if (list_is_last(&txb->call_link, &call->tx_buffer)) goto no_further_resend; @@ -184,43 +138,46 @@ void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) * seen. Anything between the soft-ACK table and that point will get * ACK'd or NACK'd in due course, so don't worry about it here; here we * need to consider retransmitting anything beyond that point. - * - * Note that ACK for a packet can beat the update of tx_transmitted. */ - if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted))) + if (after_eq(call->acks_prev_seq, call->tx_transmitted)) goto no_further_resend; list_for_each_entry_from(txb, &call->tx_buffer, call_link) { - if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq))) + resend_at = ktime_add(txb->last_sent, rto); + + if (before_eq(txb->seq, call->acks_prev_seq)) continue; - if (after(txb->seq, READ_ONCE(call->tx_transmitted))) + if (after(txb->seq, call->tx_transmitted)) break; /* Not transmitted yet */ if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && - before(ntohl(txb->wire.serial), ntohl(ack->serial))) + before(txb->serial, ntohl(ack->serial))) goto do_resend; /* Wasn't accounted for by a more recent ping. */ - if (ktime_after(txb->last_sent, max_age)) { - if (ktime_before(txb->last_sent, oldest)) - oldest = txb->last_sent; + if (ktime_after(resend_at, now)) { + if (ktime_before(resend_at, next_resend)) + next_resend = resend_at; continue; } do_resend: unacked = true; - if (list_empty(&txb->tx_link)) { - list_add_tail(&txb->tx_link, &retrans_queue); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); - } + + txb->flags |= RXRPC_TXBUF_RESENT; + rxrpc_transmit_one(call, txb); + did_send = true; + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + now = ktime_get_real(); } no_further_resend: no_resend: - resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, - !list_empty(&retrans_queue)); - WRITE_ONCE(call->resend_at, resend_at); + if (resend_at < KTIME_MAX) { + delay = rxrpc_get_rto_backoff(call->peer, did_send); + resend_at = ktime_add(resend_at, delay); + trace_rxrpc_timer_set(call, resend_at - now, rxrpc_timer_trace_resend_reset); + } + call->resend_at = resend_at; if (unacked) rxrpc_congestion_timeout(call); @@ -229,25 +186,15 @@ no_resend: * that an ACK got lost somewhere. Send a ping to find out instead of * retransmitting data. */ - if (list_empty(&retrans_queue)) { - rxrpc_reduce_call_timer(call, resend_at, jiffies, - rxrpc_timer_set_for_resend); - ack_ts = ktime_sub(now, call->acks_latest_ts); - if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) - goto out; - rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, - rxrpc_propose_ack_ping_for_lost_ack); - goto out; - } + if (!did_send) { + ktime_t next_ping = ktime_add_us(call->acks_latest_ts, + call->peer->srtt_us >> 3); - /* Retransmit the queue */ - while ((txb = list_first_entry_or_null(&retrans_queue, - struct rxrpc_txbuf, tx_link))) { - list_del_init(&txb->tx_link); - rxrpc_transmit_one(call, txb); + if (ktime_sub(next_ping, now) <= 0) + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_0_retrans); } -out: _leave(""); } @@ -257,13 +204,11 @@ out: */ static void rxrpc_begin_service_reply(struct rxrpc_call *call) { - unsigned long now = jiffies; - rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY); - WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); if (call->ackr_reason == RXRPC_ACK_DELAY) call->ackr_reason = 0; - trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); + call->delay_ack_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack); } /* @@ -320,7 +265,7 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) call->tx_top = txb->seq; list_add_tail(&txb->call_link, &call->tx_buffer); - if (txb->wire.flags & RXRPC_LAST_PACKET) + if (txb->flags & RXRPC_LAST_PACKET) rxrpc_close_tx_phase(call); rxrpc_transmit_one(call, txb); @@ -372,8 +317,8 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call) */ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { - unsigned long now, next, t; - bool resend = false, expired = false; + ktime_t now, t; + bool resend = false; s32 abort_code; rxrpc_see_call(call, rxrpc_call_see_input); @@ -397,70 +342,73 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) goto out; + if (skb) + rxrpc_input_call_packet(call, skb); + /* If we see our async-event poke, check for timeout trippage. */ - now = jiffies; - t = READ_ONCE(call->expect_rx_by); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now); - expired = true; + now = ktime_get_real(); + t = ktime_sub(call->expect_rx_by, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_expect_rx); + goto expired; } - t = READ_ONCE(call->expect_req_by); - if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST && - time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now); - expired = true; + t = ktime_sub(call->expect_req_by, now); + if (t <= 0) { + call->expect_req_by = KTIME_MAX; + if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_idle); + goto expired; + } } - t = READ_ONCE(call->expect_term_by); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now); - expired = true; + t = ktime_sub(READ_ONCE(call->expect_term_by), now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_hard); + goto expired; } - t = READ_ONCE(call->delay_ack_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); - cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->delay_ack_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_delayed_ack); + call->delay_ack_at = KTIME_MAX; rxrpc_send_ACK(call, RXRPC_ACK_DELAY, 0, - rxrpc_propose_ack_ping_for_lost_ack); + rxrpc_propose_ack_delayed_ack); } - t = READ_ONCE(call->ack_lost_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_lost_ack, now); - cmpxchg(&call->ack_lost_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->ack_lost_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_lost_ack); + call->ack_lost_at = KTIME_MAX; set_bit(RXRPC_CALL_EV_ACK_LOST, &call->events); } - t = READ_ONCE(call->keepalive_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); - cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->ping_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_ping); + call->ping_at = KTIME_MAX; rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_keepalive); } - t = READ_ONCE(call->ping_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now); - cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, - rxrpc_propose_ack_ping_for_keepalive); - } - - t = READ_ONCE(call->resend_at); - if (time_after_eq(now, t)) { - trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now); - cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET); + t = ktime_sub(call->resend_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_resend); + call->resend_at = KTIME_MAX; resend = true; } - if (skb) - rxrpc_input_call_packet(call, skb); - rxrpc_transmit_some_data(call); + now = ktime_get_real(); + t = ktime_sub(call->keepalive_at, now); + if (t <= 0) { + trace_rxrpc_timer_exp(call, t, rxrpc_timer_trace_keepalive); + call->keepalive_at = KTIME_MAX; + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); + } + if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -472,24 +420,13 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_send_initial_ping(call); /* Process events */ - if (expired) { - if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && - (int)call->conn->hi_serial - (int)call->rx_serial > 0) { - trace_rxrpc_call_reset(call); - rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, - rxrpc_abort_call_reset); - } else { - rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, - rxrpc_abort_call_timeout); - } - goto out; - } - if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY) + if (resend && + __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY && + !test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) rxrpc_resend(call, NULL); if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) @@ -511,23 +448,33 @@ bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) /* Make sure the timer is restarted */ if (!__rxrpc_call_is_complete(call)) { - next = call->expect_rx_by; + ktime_t next = READ_ONCE(call->expect_term_by), delay; -#define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } +#define set(T) { ktime_t _t = (T); if (ktime_before(_t, next)) next = _t; } set(call->expect_req_by); - set(call->expect_term_by); + set(call->expect_rx_by); set(call->delay_ack_at); set(call->ack_lost_at); set(call->resend_at); set(call->keepalive_at); set(call->ping_at); - now = jiffies; - if (time_after_eq(now, next)) + now = ktime_get_real(); + delay = ktime_sub(next, now); + if (delay <= 0) { rxrpc_poke_call(call, rxrpc_call_poke_timer_now); - - rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); + } else { + unsigned long nowj = jiffies, delayj, nextj; + + delayj = max(nsecs_to_jiffies(delay), 1); + nextj = nowj + delayj; + if (time_before(nextj, call->timer.expires) || + !timer_pending(&call->timer)) { + trace_rxrpc_timer_restart(call, delay, delayj); + timer_reduce(&call->timer, nextj); + } + } } out: @@ -542,4 +489,16 @@ out: rxrpc_shrink_call_tx_buffer(call); _leave(""); return true; + +expired: + if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && + (int)call->conn->hi_serial - (int)call->rx_serial > 0) { + trace_rxrpc_call_reset(call); + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_reset); + } else { + rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, + rxrpc_abort_call_timeout); + } + goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 9fc9a6c3f685..01fa71e8b1f7 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -70,20 +70,11 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); if (!__rxrpc_call_is_complete(call)) { - trace_rxrpc_timer_expired(call, jiffies); + trace_rxrpc_timer_expired(call); rxrpc_poke_call(call, rxrpc_call_poke_timer); } } -void rxrpc_reduce_call_timer(struct rxrpc_call *call, - unsigned long expire_at, - unsigned long now, - enum rxrpc_timer_trace why) -{ - trace_rxrpc_timer(call, why, now); - timer_reduce(&call->timer, expire_at); -} - static struct lock_class_key rxrpc_call_user_mutex_lock_class_key; static void rxrpc_destroy_call(struct work_struct *); @@ -163,12 +154,20 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); refcount_set(&call->ref, 1); - call->debug_id = debug_id; - call->tx_total_len = -1; - call->next_rx_timo = 20 * HZ; - call->next_req_timo = 1 * HZ; - call->ackr_window = 1; - call->ackr_wtop = 1; + call->debug_id = debug_id; + call->tx_total_len = -1; + call->next_rx_timo = 20 * HZ; + call->next_req_timo = 1 * HZ; + call->ackr_window = 1; + call->ackr_wtop = 1; + call->delay_ack_at = KTIME_MAX; + call->ack_lost_at = KTIME_MAX; + call->resend_at = KTIME_MAX; + call->ping_at = KTIME_MAX; + call->keepalive_at = KTIME_MAX; + call->expect_rx_by = KTIME_MAX; + call->expect_req_by = KTIME_MAX; + call->expect_term_by = KTIME_MAX; memset(&call->sock_node, 0xed, sizeof(call->sock_node)); @@ -226,11 +225,11 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, __set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); if (p->timeouts.normal) - call->next_rx_timo = min(msecs_to_jiffies(p->timeouts.normal), 1UL); + call->next_rx_timo = min(p->timeouts.normal, 1); if (p->timeouts.idle) - call->next_req_timo = min(msecs_to_jiffies(p->timeouts.idle), 1UL); + call->next_req_timo = min(p->timeouts.idle, 1); if (p->timeouts.hard) - call->hard_timo = p->timeouts.hard * HZ; + call->hard_timo = p->timeouts.hard; ret = rxrpc_init_client_call_security(call); if (ret < 0) { @@ -253,18 +252,13 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, */ void rxrpc_start_call_timer(struct rxrpc_call *call) { - unsigned long now = jiffies; - unsigned long j = now + MAX_JIFFY_OFFSET; - - call->delay_ack_at = j; - call->ack_lost_at = j; - call->resend_at = j; - call->ping_at = j; - call->keepalive_at = j; - call->expect_rx_by = j; - call->expect_req_by = j; - call->expect_term_by = j + call->hard_timo; - call->timer.expires = now; + if (call->hard_timo) { + ktime_t delay = ms_to_ktime(call->hard_timo * 1000); + + call->expect_term_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + } + call->timer.expires = jiffies; } /* diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3b9b267a4431..d25bf1cf3670 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -636,7 +636,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { unsigned long final_ack_at = jiffies + 2; - WRITE_ONCE(chan->final_ack_at, final_ack_at); + chan->final_ack_at = final_ack_at; smp_wmb(); /* vs rxrpc_process_delayed_final_acks() */ set_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); rxrpc_reduce_conn_timer(conn, final_ack_at); @@ -770,7 +770,7 @@ next: conn_expires_at = conn->idle_timestamp + expiry; - now = READ_ONCE(jiffies); + now = jiffies; if (time_after(conn_expires_at, now)) goto not_yet_expired; } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 1f251d758cb9..598b4ee389fc 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -88,7 +88,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct rxrpc_ackpacket ack; }; } __attribute__((packed)) pkt; - struct rxrpc_ackinfo ack_info; + struct rxrpc_acktrailer trailer; size_t len; int ret, ioc; u32 serial, mtu, call_id, padding; @@ -122,8 +122,8 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[0].iov_len = sizeof(pkt.whdr); iov[1].iov_base = &padding; iov[1].iov_len = 3; - iov[2].iov_base = &ack_info; - iov[2].iov_len = sizeof(ack_info); + iov[2].iov_base = &trailer; + iov[2].iov_len = sizeof(trailer); serial = rxrpc_get_next_serial(conn); @@ -158,14 +158,14 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, pkt.ack.serial = htonl(skb ? sp->hdr.serial : 0); pkt.ack.reason = skb ? RXRPC_ACK_DUPLICATE : RXRPC_ACK_IDLE; pkt.ack.nAcks = 0; - ack_info.rxMTU = htonl(rxrpc_rx_mtu); - ack_info.maxMTU = htonl(mtu); - ack_info.rwind = htonl(rxrpc_rx_window_size); - ack_info.jumbo_max = htonl(rxrpc_rx_jumbo_max); + trailer.maxMTU = htonl(rxrpc_rx_mtu); + trailer.ifMTU = htonl(mtu); + trailer.rwind = htonl(rxrpc_rx_window_size); + trailer.jumbo_max = htonl(rxrpc_rx_jumbo_max); pkt.whdr.flags |= RXRPC_SLOW_START_OK; padding = 0; iov[0].iov_len += sizeof(pkt.ack); - len += sizeof(pkt.ack) + 3 + sizeof(ack_info); + len += sizeof(pkt.ack) + 3 + sizeof(trailer); ioc = 3; trace_rxrpc_tx_ack(chan->call_debug_id, serial, diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index df8a271948a1..0af4642aeec4 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -68,6 +68,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); mutex_init(&conn->security_lock); + mutex_init(&conn->tx_data_alloc_lock); skb_queue_head_init(&conn->rx_queue); conn->rxnet = rxnet; conn->security = &rxrpc_no_security; @@ -341,6 +342,9 @@ static void rxrpc_clean_up_connection(struct work_struct *work) */ rxrpc_purge_queue(&conn->rx_queue); + if (conn->tx_data_alloc.va) + __page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va), + conn->tx_data_alloc.pagecnt_bias); call_rcu(&conn->rcu, rxrpc_rcu_free_connection); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 9691de00ade7..3dedb8c0618c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -212,7 +212,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { if (before_eq(txb->seq, call->acks_hard_ack)) continue; - if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { + if (txb->flags & RXRPC_LAST_PACKET) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } @@ -252,6 +252,9 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, { ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); + call->resend_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_resend); + if (unlikely(call->cong_last_nack)) { rxrpc_free_skb(call->cong_last_nack, rxrpc_skb_put_last_nack); call->cong_last_nack = NULL; @@ -288,15 +291,11 @@ static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, static bool rxrpc_receiving_reply(struct rxrpc_call *call) { struct rxrpc_ack_summary summary = { 0 }; - unsigned long now, timo; rxrpc_seq_t top = READ_ONCE(call->tx_top); if (call->ackr_reason) { - now = jiffies; - timo = now + MAX_JIFFY_OFFSET; - - WRITE_ONCE(call->delay_ack_at, timo); - trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); + call->delay_ack_at = KTIME_MAX; + trace_rxrpc_timer_can(call, rxrpc_timer_trace_delayed_ack); } if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { @@ -329,7 +328,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) case RXRPC_CALL_SERVER_RECV_REQUEST: rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST); - call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; + call->expect_req_by = KTIME_MAX; rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op); break; @@ -589,14 +588,12 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_SERVER_RECV_REQUEST: { unsigned long timo = READ_ONCE(call->next_req_timo); - unsigned long now, expect_req_by; if (timo) { - now = jiffies; - expect_req_by = now + timo; - WRITE_ONCE(call->expect_req_by, expect_req_by); - rxrpc_reduce_call_timer(call, expect_req_by, now, - rxrpc_timer_set_for_idle); + ktime_t delay = ms_to_ktime(timo); + + call->expect_req_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_idle); } break; } @@ -670,14 +667,14 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, /* * Process the extra information that may be appended to an ACK packet */ -static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, - struct rxrpc_ackinfo *ackinfo) +static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb, + struct rxrpc_acktrailer *trailer) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; unsigned int mtu; bool wake = false; - u32 rwind = ntohl(ackinfo->rwind); + u32 rwind = ntohl(trailer->rwind); if (rwind > RXRPC_TX_MAX_WINDOW) rwind = RXRPC_TX_MAX_WINDOW; @@ -691,7 +688,7 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, if (call->cong_ssthresh > rwind) call->cong_ssthresh = rwind; - mtu = min(ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU)); + mtu = min(ntohl(trailer->maxMTU), ntohl(trailer->ifMTU)); peer = call->peer; if (mtu < peer->maxdata) { @@ -713,20 +710,19 @@ static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, rxrpc_seq_t seq) { struct sk_buff *skb = call->cong_last_nack; - struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int i, new_acks = 0, retained_nacks = 0; - rxrpc_seq_t old_seq = sp->first_ack; - u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(ack); + rxrpc_seq_t old_seq = sp->ack.first_ack; + u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - if (after_eq(seq, old_seq + sp->nr_acks)) { - summary->nr_new_acks += sp->nr_nacks; - summary->nr_new_acks += seq - (old_seq + sp->nr_acks); + if (after_eq(seq, old_seq + sp->ack.nr_acks)) { + summary->nr_new_acks += sp->ack.nr_nacks; + summary->nr_new_acks += seq - (old_seq + sp->ack.nr_acks); summary->nr_retained_nacks = 0; } else if (seq == old_seq) { - summary->nr_retained_nacks = sp->nr_nacks; + summary->nr_retained_nacks = sp->ack.nr_nacks; } else { - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { if (acks[i] == RXRPC_ACK_TYPE_NACK) { if (before(old_seq + i, seq)) new_acks++; @@ -739,7 +735,7 @@ static rxrpc_seq_t rxrpc_input_check_prev_ack(struct rxrpc_call *call, summary->nr_retained_nacks = retained_nacks; } - return old_seq + sp->nr_acks; + return old_seq + sp->ack.nr_acks; } /* @@ -759,10 +755,10 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned int i, old_nacks = 0; - rxrpc_seq_t lowest_nak = seq + sp->nr_acks; + rxrpc_seq_t lowest_nak = seq + sp->ack.nr_acks; u8 *acks = skb->data + sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); - for (i = 0; i < sp->nr_acks; i++) { + for (i = 0; i < sp->ack.nr_acks; i++) { if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; if (after_eq(seq, since)) @@ -774,7 +770,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, old_nacks++; } else { summary->nr_new_nacks++; - sp->nr_nacks++; + sp->ack.nr_nacks++; } if (before(seq, lowest_nak)) @@ -835,38 +831,32 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; - struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_ackinfo info; + struct rxrpc_acktrailer trailer; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt, since; int nr_acks, offset, ioffset; _enter(""); - offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) - return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack); - offset += sizeof(ack); - - ack_serial = sp->hdr.serial; - acked_serial = ntohl(ack.serial); - first_soft_ack = ntohl(ack.firstPacket); - prev_pkt = ntohl(ack.previousPacket); - hard_ack = first_soft_ack - 1; - nr_acks = ack.nAcks; - sp->first_ack = first_soft_ack; - sp->nr_acks = nr_acks; - summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? - ack.reason : RXRPC_ACK__INVALID); + offset = sizeof(struct rxrpc_wire_header) + sizeof(struct rxrpc_ackpacket); + + ack_serial = sp->hdr.serial; + acked_serial = sp->ack.acked_serial; + first_soft_ack = sp->ack.first_ack; + prev_pkt = sp->ack.prev_ack; + nr_acks = sp->ack.nr_acks; + hard_ack = first_soft_ack - 1; + summary.ack_reason = (sp->ack.reason < RXRPC_ACK__INVALID ? + sp->ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[summary.ack_reason]); if (acked_serial != 0) { - switch (ack.reason) { + switch (summary.ack_reason) { case RXRPC_ACK_PING_RESPONSE: rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, rxrpc_rtt_rx_ping_response); @@ -886,7 +876,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ - if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && + if (unlikely(summary.ack_reason == RXRPC_ACK_EXCEEDS_WINDOW) && first_soft_ack == 1 && prev_pkt == 0 && rxrpc_is_client_call(call)) { @@ -899,7 +889,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicate a change of address. However, we can retransmit the call * if we still have it buffered to the beginning. */ - if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + if (unlikely(summary.ack_reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && call->acks_hard_ack == 0 && @@ -917,11 +907,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto send_response; } - info.rxMTU = 0; + trailer.maxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(info) && - skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) - return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info); + if (skb->len >= ioffset + sizeof(trailer) && + skb_copy_bits(skb, ioffset, &trailer, sizeof(trailer)) < 0) + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_trailer); if (nr_acks > 0) skb_condense(skb); @@ -940,7 +930,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; - switch (ack.reason) { + switch (summary.ack_reason) { case RXRPC_ACK_PING: break; default: @@ -950,8 +940,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } /* Parse rwind and mtu sizes if provided. */ - if (info.rxMTU) - rxrpc_input_ackinfo(call, skb, &info); + if (trailer.maxMTU) + rxrpc_input_ack_trailer(call, skb, &trailer); if (first_soft_ack == 0) return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); @@ -997,7 +987,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_congestion_management(call, skb, &summary, acked_serial); send_response: - if (ack.reason == RXRPC_ACK_PING) + if (summary.ack_reason == RXRPC_ACK_PING) rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, rxrpc_propose_ack_respond_to_ping); else if (sp->hdr.flags & RXRPC_REQUEST_ACK) @@ -1048,12 +1038,10 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) timo = READ_ONCE(call->next_rx_timo); if (timo) { - unsigned long now = jiffies, expect_rx_by; + ktime_t delay = ms_to_ktime(timo); - expect_rx_by = now + timo; - WRITE_ONCE(call->expect_rx_by, expect_rx_by); - rxrpc_reduce_call_timer(call, expect_rx_by, now, - rxrpc_timer_set_for_normal); + call->expect_rx_by = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); } switch (sp->hdr.type) { diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 34353b6e584b..f2701068ed9e 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -15,14 +15,11 @@ static int none_init_connection_security(struct rxrpc_connection *conn, } /* - * Work out how much data we can put in an unsecured packet. + * Allocate an appropriately sized buffer for the amount of data remaining. */ -static int none_how_much_data(struct rxrpc_call *call, size_t remain, - size_t *_buf_size, size_t *_data_size, size_t *_offset) +static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - *_buf_size = *_data_size = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - *_offset = 0; - return 0; + return rxrpc_alloc_data_txbuf(call, min_t(size_t, remain, RXRPC_JUMBO_DATALEN), 0, gfp); } static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) @@ -79,7 +76,7 @@ const struct rxrpc_security rxrpc_no_security = { .exit = none_exit, .init_connection_security = none_init_connection_security, .free_call_crypto = none_free_call_crypto, - .how_much_data = none_how_much_data, + .alloc_txbuf = none_alloc_txbuf, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, .respond_to_challenge = none_respond_to_challenge, diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 4a3a08a0e2cd..0300baa9afcd 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -124,6 +124,7 @@ static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) { struct rxrpc_wire_header whdr; + struct rxrpc_ackpacket ack; /* dig out the RxRPC connection details */ if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) @@ -141,6 +142,16 @@ static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, sp->hdr.securityIndex = whdr.securityIndex; sp->hdr._rsvd = ntohs(whdr._rsvd); sp->hdr.serviceId = ntohs(whdr.serviceId); + + if (sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(whdr), &ack, sizeof(ack)) < 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_short_ack); + sp->ack.first_ack = ntohl(ack.firstPacket); + sp->ack.prev_ack = ntohl(ack.previousPacket); + sp->ack.acked_serial = ntohl(ack.serial); + sp->ack.reason = ack.reason; + sp->ack.nr_acks = ack.nAcks; + } return true; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 34d307368135..504453c688d7 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -452,6 +452,9 @@ void rxrpc_destroy_local(struct rxrpc_local *local) #endif rxrpc_purge_queue(&local->rx_queue); rxrpc_purge_client_connections(local); + if (local->tx_alloc.va) + __page_frag_cache_drain(virt_to_page(local->tx_alloc.va), + local->tx_alloc.pagecnt_bias); } /* diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 825b81183046..657cf35089a6 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -17,22 +17,22 @@ unsigned int rxrpc_max_backlog __read_mostly = 10; /* - * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). + * How long to wait before scheduling an ACK with subtype DELAY (in ms). * * We use this when we've received new data packets. If those packets aren't * all consumed within this time we will send a DELAY ACK if an ACK was not * requested to let the sender know it doesn't need to resend. */ -unsigned long rxrpc_soft_ack_delay = HZ; +unsigned long rxrpc_soft_ack_delay = 1000; /* - * How long to wait before scheduling an ACK with subtype IDLE (in jiffies). + * How long to wait before scheduling an ACK with subtype IDLE (in ms). * * We use this when we've consumed some previously soft-ACK'd packets when * further packets aren't immediately received to decide when to send an IDLE * ACK let the other end know that it can free up its Tx buffer space. */ -unsigned long rxrpc_idle_ack_delay = HZ / 2; +unsigned long rxrpc_idle_ack_delay = 500; /* * Receive window size in packets. This indicates the maximum number of diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 4a292f860ae3..5ea9601efd05 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -48,12 +48,10 @@ static const char rxrpc_keepalive_string[] = ""; static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) { if (ret < 0) { - u16 tx_backoff = READ_ONCE(call->tx_backoff); - - if (tx_backoff < HZ) - WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + if (call->tx_backoff < 1000) + call->tx_backoff += 100; } else { - WRITE_ONCE(call->tx_backoff, 0); + call->tx_backoff = 0; } } @@ -65,84 +63,92 @@ static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) * Receiving a response to the ping will prevent the ->expect_rx_by timer from * expiring. */ -static void rxrpc_set_keepalive(struct rxrpc_call *call) +static void rxrpc_set_keepalive(struct rxrpc_call *call, ktime_t now) { - unsigned long now = jiffies, keepalive_at = call->next_rx_timo / 6; + ktime_t delay = ms_to_ktime(READ_ONCE(call->next_rx_timo) / 6); - keepalive_at += now; - WRITE_ONCE(call->keepalive_at, keepalive_at); - rxrpc_reduce_call_timer(call, keepalive_at, now, - rxrpc_timer_set_for_keepalive); + call->keepalive_at = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_keepalive); } /* * Fill out an ACK packet. */ -static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, - struct rxrpc_call *call, - struct rxrpc_txbuf *txb, - u16 *_rwind) +static void rxrpc_fill_out_ack(struct rxrpc_call *call, + struct rxrpc_txbuf *txb, + u8 ack_reason, + rxrpc_serial_t serial) { - struct rxrpc_ackinfo ackinfo; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxrpc_acktrailer *trailer = txb->kvec[2].iov_base + 3; + struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); unsigned int qsize, sack, wrap, to; rxrpc_seq_t window, wtop; int rsize; u32 mtu, jmax; - u8 *ackp = txb->acks; + u8 *filler = txb->kvec[2].iov_base; + u8 *sackp = txb->kvec[1].iov_base; - call->ackr_nr_unacked = 0; - atomic_set(&call->ackr_nr_consumed, 0); rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); - clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); window = call->ackr_window; wtop = call->ackr_wtop; sack = call->ackr_sack_base % RXRPC_SACK_SIZE; - txb->ack.firstPacket = htonl(window); - txb->ack.nAcks = wtop - window; + + whdr->seq = 0; + whdr->type = RXRPC_PACKET_TYPE_ACK; + txb->flags |= RXRPC_SLOW_START_OK; + ack->bufferSpace = 0; + ack->maxSkew = 0; + ack->firstPacket = htonl(window); + ack->previousPacket = htonl(call->rx_highest_seq); + ack->serial = htonl(serial); + ack->reason = ack_reason; + ack->nAcks = wtop - window; + filler[0] = 0; + filler[1] = 0; + filler[2] = 0; + + if (ack_reason == RXRPC_ACK_PING) + txb->flags |= RXRPC_REQUEST_ACK; if (after(wtop, window)) { + txb->len += ack->nAcks; + txb->kvec[1].iov_base = sackp; + txb->kvec[1].iov_len = ack->nAcks; + wrap = RXRPC_SACK_SIZE - sack; - to = min_t(unsigned int, txb->ack.nAcks, RXRPC_SACK_SIZE); + to = min_t(unsigned int, ack->nAcks, RXRPC_SACK_SIZE); - if (sack + txb->ack.nAcks <= RXRPC_SACK_SIZE) { - memcpy(txb->acks, call->ackr_sack_table + sack, txb->ack.nAcks); + if (sack + ack->nAcks <= RXRPC_SACK_SIZE) { + memcpy(sackp, call->ackr_sack_table + sack, ack->nAcks); } else { - memcpy(txb->acks, call->ackr_sack_table + sack, wrap); - memcpy(txb->acks + wrap, call->ackr_sack_table, - to - wrap); + memcpy(sackp, call->ackr_sack_table + sack, wrap); + memcpy(sackp + wrap, call->ackr_sack_table, to - wrap); } - - ackp += to; } else if (before(wtop, window)) { pr_warn("ack window backward %x %x", window, wtop); - } else if (txb->ack.reason == RXRPC_ACK_DELAY) { - txb->ack.reason = RXRPC_ACK_IDLE; + } else if (ack->reason == RXRPC_ACK_DELAY) { + ack->reason = RXRPC_ACK_IDLE; } - mtu = conn->peer->if_mtu; - mtu -= conn->peer->hdrsize; + mtu = call->peer->if_mtu; + mtu -= call->peer->hdrsize; jmax = rxrpc_rx_jumbo_max; qsize = (window - 1) - call->rx_consumed; rsize = max_t(int, call->rx_winsize - qsize, 0); - *_rwind = rsize; - ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(rsize); - ackinfo.jumbo_max = htonl(jmax); - - *ackp++ = 0; - *ackp++ = 0; - *ackp++ = 0; - memcpy(ackp, &ackinfo, sizeof(ackinfo)); - return txb->ack.nAcks + 3 + sizeof(ackinfo); + txb->ack_rwind = rsize; + trailer->maxMTU = htonl(rxrpc_rx_mtu); + trailer->ifMTU = htonl(mtu); + trailer->rwind = htonl(rsize); + trailer->jumbo_max = htonl(jmax); } /* * Record the beginning of an RTT probe. */ -static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, - enum rxrpc_rtt_tx_trace why) +static void rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, + ktime_t now, enum rxrpc_rtt_tx_trace why) { unsigned long avail = call->rtt_avail; int rtt_slot = 9; @@ -155,47 +161,31 @@ static int rxrpc_begin_rtt_probe(struct rxrpc_call *call, rxrpc_serial_t serial, goto no_slot; call->rtt_serial[rtt_slot] = serial; - call->rtt_sent_at[rtt_slot] = ktime_get_real(); + call->rtt_sent_at[rtt_slot] = now; smp_wmb(); /* Write data before avail bit */ set_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); trace_rxrpc_rtt_tx(call, why, rtt_slot, serial); - return rtt_slot; + return; no_slot: trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_no_slot, rtt_slot, serial); - return -1; -} - -/* - * Cancel an RTT probe. - */ -static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, - rxrpc_serial_t serial, int rtt_slot) -{ - if (rtt_slot != -1) { - clear_bit(rtt_slot + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); - smp_wmb(); /* Clear pending bit before setting slot */ - set_bit(rtt_slot, &call->rtt_avail); - trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_cancel, rtt_slot, serial); - } } /* * Transmit an ACK packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static void rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; struct rxrpc_connection *conn; + struct rxrpc_ackpacket *ack = (struct rxrpc_ackpacket *)(whdr + 1); struct msghdr msg; - struct kvec iov[1]; - rxrpc_serial_t serial; - size_t len, n; - int ret, rtt_slot = -1; - u16 rwind; + ktime_t now; + int ret; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - return -ECONNRESET; + return; conn = call->conn; @@ -203,55 +193,68 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) msg.msg_namelen = call->peer->srx.transport_len; msg.msg_control = NULL; msg.msg_controllen = 0; - msg.msg_flags = 0; - - if (txb->ack.reason == RXRPC_ACK_PING) - txb->wire.flags |= RXRPC_REQUEST_ACK; - - n = rxrpc_fill_out_ack(conn, call, txb, &rwind); - if (n == 0) - return 0; - - iov[0].iov_base = &txb->wire; - iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; - len = iov[0].iov_len; + msg.msg_flags = MSG_SPLICE_PAGES; - serial = rxrpc_get_next_serial(conn); - txb->wire.serial = htonl(serial); - trace_rxrpc_tx_ack(call->debug_id, serial, - ntohl(txb->ack.firstPacket), - ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks, - rwind); + whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; - if (txb->ack.reason == RXRPC_ACK_PING) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); + txb->serial = rxrpc_get_next_serial(conn); + whdr->serial = htonl(txb->serial); + trace_rxrpc_tx_ack(call->debug_id, txb->serial, + ntohl(ack->firstPacket), + ntohl(ack->serial), ack->reason, ack->nAcks, + txb->ack_rwind); rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); - /* Grab the highest received seq as late as possible */ - txb->ack.previousPacket = htonl(call->rx_highest_seq); - - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); - ret = do_udp_sendmsg(conn->local->socket, &msg, len); + iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, txb->len); + rxrpc_local_dont_fragment(conn->local, false); + ret = do_udp_sendmsg(conn->local->socket, &msg, txb->len); call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) { - trace_rxrpc_tx_fail(call->debug_id, serial, ret, + trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, rxrpc_tx_point_call_ack); } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, + trace_rxrpc_tx_packet(call->debug_id, whdr, rxrpc_tx_point_call_ack); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - call->peer->rtt_last_req = ktime_get_real(); + now = ktime_get_real(); + if (ack->reason == RXRPC_ACK_PING) + rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_ping); + if (txb->flags & RXRPC_REQUEST_ACK) + call->peer->rtt_last_req = now; + rxrpc_set_keepalive(call, now); } rxrpc_tx_backoff(call, ret); +} - if (!__rxrpc_call_is_complete(call)) { - if (ret < 0) - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - rxrpc_set_keepalive(call); +/* + * Queue an ACK for immediate transmission. + */ +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) +{ + struct rxrpc_txbuf *txb; + + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + return; + + rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); + + txb = rxrpc_alloc_ack_txbuf(call, call->ackr_wtop - call->ackr_window); + if (!txb) { + kleave(" = -ENOMEM"); + return; } - return ret; + txb->ack_why = why; + + rxrpc_fill_out_ack(call, txb, ack_reason, serial); + call->ackr_nr_unacked = 0; + atomic_set(&call->ackr_nr_consumed, 0); + clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); + + trace_rxrpc_send_ack(call, why, ack_reason, serial); + rxrpc_send_ack_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); } /* @@ -319,38 +322,22 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) } /* - * send a packet through the transport endpoint + * Prepare a (sub)packet for transmission. */ -int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +static void rxrpc_prepare_data_subpacket(struct rxrpc_call *call, struct rxrpc_txbuf *txb, + rxrpc_serial_t serial) { + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct msghdr msg; - struct kvec iov[1]; - rxrpc_serial_t serial; - size_t len; - int ret, rtt_slot = -1; _enter("%x,{%d}", txb->seq, txb->len); - /* Each transmission of a Tx packet needs a new serial number */ - serial = rxrpc_get_next_serial(conn); - txb->wire.serial = htonl(serial); + txb->serial = serial; if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && txb->seq == 1) - txb->wire.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; - - iov[0].iov_base = &txb->wire; - iov[0].iov_len = sizeof(txb->wire) + txb->len; - len = iov[0].iov_len; - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); - - msg.msg_name = &call->peer->srx.transport; - msg.msg_namelen = call->peer->srx.transport_len; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; + whdr->userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. @@ -359,13 +346,13 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (txb->wire.flags & RXRPC_REQUEST_ACK) + if (txb->flags & RXRPC_REQUEST_ACK) why = rxrpc_reqack_already_on; - else if (test_bit(RXRPC_TXBUF_LAST, &txb->flags) && rxrpc_sending_to_client(txb)) + else if ((txb->flags & RXRPC_LAST_PACKET) && rxrpc_sending_to_client(txb)) why = rxrpc_reqack_no_srv_last; else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) why = rxrpc_reqack_ack_lost; - else if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) + else if (txb->flags & RXRPC_TXBUF_RESENT) why = rxrpc_reqack_retrans; else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) why = rxrpc_reqack_slow_start; @@ -381,42 +368,116 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); trace_rxrpc_req_ack(call->debug_id, txb->seq, why); if (why != rxrpc_reqack_no_srv_last) - txb->wire.flags |= RXRPC_REQUEST_ACK; + txb->flags |= RXRPC_REQUEST_ACK; dont_set_request_ack: + whdr->flags = txb->flags & RXRPC_TXBUF_WIRE_FLAGS; + whdr->serial = htonl(txb->serial); + whdr->cksum = txb->cksum; + + trace_rxrpc_tx_data(call, txb->seq, txb->serial, txb->flags, false); +} + +/* + * Prepare a packet for transmission. + */ +static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + rxrpc_serial_t serial; + + /* Each transmission of a Tx packet needs a new serial number */ + serial = rxrpc_get_next_serial(call->conn); + + rxrpc_prepare_data_subpacket(call, txb, serial); + + return txb->len; +} + +/* + * Set timeouts after transmitting a packet. + */ +static void rxrpc_tstamp_data_packets(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + ktime_t now = ktime_get_real(); + bool ack_requested = txb->flags & RXRPC_REQUEST_ACK; + + call->tx_last_sent = now; + txb->last_sent = now; + + if (ack_requested) { + rxrpc_begin_rtt_probe(call, txb->serial, now, rxrpc_rtt_tx_data); + + call->peer->rtt_last_req = now; + if (call->peer->rtt_count > 1) { + ktime_t delay = rxrpc_get_rto_backoff(call->peer, false); + + call->ack_lost_at = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_lost_ack); + } + } + + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { + ktime_t delay = ms_to_ktime(READ_ONCE(call->next_rx_timo)); + + call->expect_rx_by = ktime_add(now, delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_expect_rx); + } + + rxrpc_set_keepalive(call, now); +} + +/* + * send a packet through the transport endpoint + */ +static int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxrpc_connection *conn = call->conn; + enum rxrpc_tx_point frag; + struct msghdr msg; + size_t len; + int ret; + + _enter("%x,{%d}", txb->seq, txb->len); + + len = rxrpc_prepare_data_packet(call, txb); + if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { ret = 0; - trace_rxrpc_tx_data(call, txb->seq, serial, - txb->wire.flags, - test_bit(RXRPC_TXBUF_RESENT, &txb->flags), - true); + trace_rxrpc_tx_data(call, txb->seq, txb->serial, + txb->flags, true); goto done; } } - trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, - test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + iov_iter_kvec(&msg.msg_iter, WRITE, txb->kvec, txb->nr_kvec, len); + + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = MSG_SPLICE_PAGES; /* Track what we've attempted to transmit at least once so that the * retransmission algorithm doesn't try to resend what we haven't sent - * yet. However, this can race as we can receive an ACK before we get - * to this point. But, OTOH, if we won't get an ACK mentioning this - * packet unless the far side received it (though it could have - * discarded it anyway and NAK'd it). + * yet. */ - cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); + if (txb->seq == call->tx_transmitted + 1) + call->tx_transmitted = txb->seq; /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (txb->len >= call->peer->maxdata) - goto send_fragmentable; - - txb->last_sent = ktime_get_real(); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); + if (txb->len >= call->peer->maxdata) { + rxrpc_local_dont_fragment(conn->local, false); + frag = rxrpc_tx_point_call_data_frag; + } else { + rxrpc_local_dont_fragment(conn->local, true); + frag = rxrpc_tx_point_call_data_nofrag; + } +retry: /* send the packet by UDP * - returns -EMSGSIZE if UDP would have to fragment the packet * to go out of the interface @@ -429,46 +490,21 @@ dont_set_request_ack: if (ret < 0) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_point_call_data_nofrag); + trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, frag); } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, - rxrpc_tx_point_call_data_nofrag); + trace_rxrpc_tx_packet(call->debug_id, whdr, frag); } rxrpc_tx_backoff(call, ret); - if (ret == -EMSGSIZE) - goto send_fragmentable; + if (ret == -EMSGSIZE && frag == rxrpc_tx_point_call_data_frag) { + rxrpc_local_dont_fragment(conn->local, false); + frag = rxrpc_tx_point_call_data_frag; + goto retry; + } done: if (ret >= 0) { - call->tx_last_sent = txb->last_sent; - if (txb->wire.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = txb->last_sent; - if (call->peer->rtt_count > 1) { - unsigned long nowj = jiffies, ack_lost_at; - - ack_lost_at = rxrpc_get_rto_backoff(call->peer, false); - ack_lost_at += nowj; - WRITE_ONCE(call->ack_lost_at, ack_lost_at); - rxrpc_reduce_call_timer(call, ack_lost_at, nowj, - rxrpc_timer_set_for_lost_ack); - } - } - - if (txb->seq == 1 && - !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, - &call->flags)) { - unsigned long nowj = jiffies, expect_rx_by; - - expect_rx_by = nowj + call->next_rx_timo; - WRITE_ONCE(call->expect_rx_by, expect_rx_by); - rxrpc_reduce_call_timer(call, expect_rx_by, nowj, - rxrpc_timer_set_for_normal); - } - - rxrpc_set_keepalive(call); + rxrpc_tstamp_data_packets(call, txb); } else { /* Cancel the call if the initial transmission fails, * particularly if that's due to network routing issues that @@ -482,41 +518,6 @@ done: _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; - -send_fragmentable: - /* attempt to send this message with fragmentation enabled */ - _debug("send fragment"); - - txb->last_sent = ktime_get_real(); - if (txb->wire.flags & RXRPC_REQUEST_ACK) - rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); - - switch (conn->local->srx.transport.family) { - case AF_INET6: - case AF_INET: - rxrpc_local_dont_fragment(conn->local, false); - rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); - ret = do_udp_sendmsg(conn->local->socket, &msg, len); - conn->peer->last_tx_at = ktime_get_seconds(); - - rxrpc_local_dont_fragment(conn->local, true); - break; - - default: - BUG(); - } - - if (ret < 0) { - rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); - rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - trace_rxrpc_tx_fail(call->debug_id, serial, ret, - rxrpc_tx_point_call_data_frag); - } else { - trace_rxrpc_tx_packet(call->debug_id, &txb->wire, - rxrpc_tx_point_call_data_frag); - } - rxrpc_tx_backoff(call, ret); - goto done; } /* @@ -723,11 +724,9 @@ void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_instant_resend(call, txb); } } else { - unsigned long now = jiffies; - unsigned long resend_at = now + call->peer->rto_j; + ktime_t delay = ns_to_ktime(call->peer->rto_us * NSEC_PER_USEC); - WRITE_ONCE(call->resend_at, resend_at); - rxrpc_reduce_call_timer(call, resend_at, now, - rxrpc_timer_set_for_send); + call->resend_at = ktime_add(ktime_get_real(), delay); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_resend_tx); } } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 26dc2f26d92d..263a2251e3d2 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -52,9 +52,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); enum rxrpc_call_state state; - unsigned long timeout = 0; rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; + long timeout = 0; if (v == &rxnet->calls) { seq_puts(seq, @@ -76,10 +76,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) sprintf(rbuff, "%pISpc", &call->dest_srx.transport); state = rxrpc_call_state(call); - if (state != RXRPC_CALL_SERVER_PREALLOC) { - timeout = READ_ONCE(call->expect_rx_by); - timeout -= jiffies; - } + if (state != RXRPC_CALL_SERVER_PREALLOC) + timeout = ktime_ms_delta(READ_ONCE(call->expect_rx_by), ktime_get_real()); acks_hard_ack = READ_ONCE(call->acks_hard_ack); seq_printf(seq, @@ -309,7 +307,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) peer->mtu, now - peer->last_tx_at, peer->srtt_us >> 3, - jiffies_to_usecs(peer->rto_j)); + peer->rto_us); return 0; } diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index e8ee4af43ca8..4fe6b4d20ada 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -135,9 +135,9 @@ struct rxrpc_ackpacket { /* * ACK packets can have a further piece of information tagged on the end */ -struct rxrpc_ackinfo { - __be32 rxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ - __be32 maxMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ +struct rxrpc_acktrailer { + __be32 maxMTU; /* maximum Rx MTU size (bytes) [AFS 3.3] */ + __be32 ifMTU; /* maximum interface MTU size (bytes) [AFS 3.3] */ __be32 rwind; /* Rx window size (packets) [AFS 3.4] */ __be32 jumbo_max; /* max packets to stick into a jumbo packet [AFS 3.5] */ }; diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c index be61d6f5be8d..cdab7b7d08a0 100644 --- a/net/rxrpc/rtt.c +++ b/net/rxrpc/rtt.c @@ -11,8 +11,8 @@ #include <linux/net.h> #include "ar-internal.h" -#define RXRPC_RTO_MAX ((unsigned)(120 * HZ)) -#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ +#define RXRPC_RTO_MAX (120 * USEC_PER_SEC) +#define RXRPC_TIMEOUT_INIT ((unsigned int)(1 * MSEC_PER_SEC)) /* RFC6298 2.1 initial RTO value */ #define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) @@ -22,7 +22,7 @@ static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer) { - return usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us); + return (peer->srtt_us >> 3) + peer->rttvar_us; } static u32 rxrpc_bound_rto(u32 rto) @@ -124,7 +124,7 @@ static void rxrpc_set_rto(struct rxrpc_peer *peer) /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo * guarantees that rto is higher. */ - peer->rto_j = rxrpc_bound_rto(rto); + peer->rto_us = rxrpc_bound_rto(rto); } static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) @@ -163,33 +163,33 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, spin_unlock(&peer->rtt_input_lock); trace_rxrpc_rtt_rx(call, why, rtt_slot, send_serial, resp_serial, - peer->srtt_us >> 3, peer->rto_j); + peer->srtt_us >> 3, peer->rto_us); } /* - * Get the retransmission timeout to set in jiffies, backing it off each time - * we retransmit. + * Get the retransmission timeout to set in nanoseconds, backing it off each + * time we retransmit. */ -unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) +ktime_t rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) { - u64 timo_j; - u8 backoff = READ_ONCE(peer->backoff); + u64 timo_us; + u32 backoff = READ_ONCE(peer->backoff); - timo_j = peer->rto_j; - timo_j <<= backoff; - if (retrans && timo_j * 2 <= RXRPC_RTO_MAX) + timo_us = peer->rto_us; + timo_us <<= backoff; + if (retrans && timo_us * 2 <= RXRPC_RTO_MAX) WRITE_ONCE(peer->backoff, backoff + 1); - if (timo_j < 1) - timo_j = 1; + if (timo_us < 1) + timo_us = 1; - return timo_j; + return ns_to_ktime(timo_us * NSEC_PER_USEC); } void rxrpc_peer_init_rtt(struct rxrpc_peer *peer) { - peer->rto_j = RXRPC_TIMEOUT_INIT; - peer->mdev_us = jiffies_to_usecs(RXRPC_TIMEOUT_INIT); + peer->rto_us = RXRPC_TIMEOUT_INIT; + peer->mdev_us = RXRPC_TIMEOUT_INIT; peer->backoff = 0; //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 6b32d61d4cdc..f1a68270862d 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -145,16 +145,17 @@ error: /* * Work out how much data we can put in a packet. */ -static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain, - size_t *_buf_size, size_t *_data_size, size_t *_offset) +static struct rxrpc_txbuf *rxkad_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp) { - size_t shdr, buf_size, chunk; + struct rxrpc_txbuf *txb; + size_t shdr, space; + + remain = min(remain, 65535 - sizeof(struct rxrpc_wire_header)); switch (call->conn->security_level) { default: - buf_size = chunk = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); - shdr = 0; - goto out; + space = min_t(size_t, remain, RXRPC_JUMBO_DATALEN); + return rxrpc_alloc_data_txbuf(call, space, 0, gfp); case RXRPC_SECURITY_AUTH: shdr = sizeof(struct rxkad_level1_hdr); break; @@ -163,17 +164,16 @@ static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain, break; } - buf_size = round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN); + space = min_t(size_t, round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN), remain + shdr); + space = round_up(space, RXKAD_ALIGN); - chunk = buf_size - shdr; - if (remain < chunk) - buf_size = round_up(shdr + remain, RXKAD_ALIGN); + txb = rxrpc_alloc_data_txbuf(call, space, RXKAD_ALIGN, gfp); + if (!txb) + return NULL; -out: - *_buf_size = buf_size; - *_data_size = chunk; - *_offset = shdr; - return 0; + txb->offset += shdr; + txb->space -= shdr; + return txb; } /* @@ -251,7 +251,8 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxkad_level1_hdr *hdr = (void *)txb->data; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxkad_level1_hdr *hdr = (void *)(whdr + 1); struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -259,7 +260,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = txb->seq ^ ntohl(txb->wire.callNumber); + check = txb->seq ^ call->call_id; hdr->data_size = htonl((u32)check << 16 | txb->len); txb->len += sizeof(struct rxkad_level1_hdr); @@ -267,14 +268,14 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { - memset(txb->data + txb->offset, 0, pad); + memset(txb->kvec[0].iov_base + txb->offset, 0, pad); txb->len += pad; } /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg, txb->data, 8); + sg_init_one(&sg, hdr, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); @@ -293,7 +294,8 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr *rxkhdr = (void *)txb->data; + struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; + struct rxkad_level2_hdr *rxkhdr = (void *)(whdr + 1); struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -302,7 +304,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, _enter(""); - check = txb->seq ^ ntohl(txb->wire.callNumber); + check = txb->seq ^ call->call_id; rxkhdr->data_size = htonl(txb->len | (u32)check << 16); rxkhdr->checksum = 0; @@ -312,7 +314,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { - memset(txb->data + txb->offset, 0, pad); + memset(txb->kvec[0].iov_base + txb->offset, 0, pad); txb->len += pad; } @@ -320,7 +322,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, token = call->conn->key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg, txb->data, txb->len); + sg_init_one(&sg, rxkhdr, txb->len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); @@ -362,9 +364,9 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = (ntohl(txb->wire.cid) & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); + x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); x |= txb->seq & 0x3fffffff; - crypto.buf[0] = txb->wire.callNumber; + crypto.buf[0] = htonl(call->call_id); crypto.buf[1] = htonl(x); sg_init_one(&sg, crypto.buf, 8); @@ -378,7 +380,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ - txb->wire.cksum = htons(y); + txb->cksum = htons(y); switch (call->conn->security_level) { case RXRPC_SECURITY_PLAIN: @@ -726,7 +728,6 @@ static int rxkad_send_response(struct rxrpc_connection *conn, rxrpc_local_dont_fragment(conn->local, false); ret = kernel_sendmsg(conn->local->socket, &msg, iov, 3, len); - rxrpc_local_dont_fragment(conn->local, true); if (ret < 0) { trace_rxrpc_tx_fail(conn->debug_id, serial, ret, rxrpc_tx_point_rxkad_response); @@ -1256,7 +1257,7 @@ const struct rxrpc_security rxkad = { .free_preparse_server_key = rxkad_free_preparse_server_key, .destroy_server_key = rxkad_destroy_server_key, .init_connection_security = rxkad_init_connection_security, - .how_much_data = rxkad_how_much_data, + .alloc_txbuf = rxkad_alloc_txbuf, .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 5677d5690a02..6f765768c49c 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -240,7 +240,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_notify_end_tx_t notify_end_tx) { rxrpc_seq_t seq = txb->seq; - bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; + bool poke, last = txb->flags & RXRPC_LAST_PACKET; rxrpc_inc_stat(call->rxnet, stat_tx_data); @@ -336,7 +336,7 @@ reload: do { if (!txb) { - size_t remain, bufsize, chunk, offset; + size_t remain; _debug("alloc"); @@ -348,23 +348,11 @@ reload: * region (enc blocksize), but the trailer is not. */ remain = more ? INT_MAX : msg_data_left(msg); - ret = call->conn->security->how_much_data(call, remain, - &bufsize, &chunk, &offset); - if (ret < 0) + txb = call->conn->security->alloc_txbuf(call, remain, sk->sk_allocation); + if (IS_ERR(txb)) { + ret = PTR_ERR(txb); goto maybe_error; - - _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); - - /* create a buffer that we can retain until it's ACK'd */ - ret = -ENOMEM; - txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, - GFP_KERNEL); - if (!txb) - goto maybe_error; - - txb->offset = offset; - txb->space -= offset; - txb->space = min_t(size_t, chunk, txb->space); + } } _debug("append"); @@ -374,8 +362,8 @@ reload: size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); _debug("add %zu", copy); - if (!copy_from_iter_full(txb->data + txb->offset, copy, - &msg->msg_iter)) + if (!copy_from_iter_full(txb->kvec[0].iov_base + txb->offset, + copy, &msg->msg_iter)) goto efault; _debug("added"); txb->space -= copy; @@ -394,18 +382,18 @@ reload: /* add the packet to the send queue if it's now full */ if (!txb->space || (msg_data_left(msg) == 0 && !more)) { - if (msg_data_left(msg) == 0 && !more) { - txb->wire.flags |= RXRPC_LAST_PACKET; - __set_bit(RXRPC_TXBUF_LAST, &txb->flags); - } + if (msg_data_left(msg) == 0 && !more) + txb->flags |= RXRPC_LAST_PACKET; else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) - txb->wire.flags |= RXRPC_MORE_PACKETS; + txb->flags |= RXRPC_MORE_PACKETS; ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; + txb->kvec[0].iov_len += txb->len; + txb->len = txb->kvec[0].iov_len; rxrpc_queue_packet(rx, call, txb, notify_end_tx); txb = NULL; } @@ -621,7 +609,6 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { struct rxrpc_call *call; - unsigned long now, j; bool dropped_lock = false; int ret; @@ -699,25 +686,21 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) switch (p.call.nr_timeouts) { case 3: - j = msecs_to_jiffies(p.call.timeouts.normal); - if (p.call.timeouts.normal > 0 && j == 0) - j = 1; - WRITE_ONCE(call->next_rx_timo, j); + WRITE_ONCE(call->next_rx_timo, p.call.timeouts.normal); fallthrough; case 2: - j = msecs_to_jiffies(p.call.timeouts.idle); - if (p.call.timeouts.idle > 0 && j == 0) - j = 1; - WRITE_ONCE(call->next_req_timo, j); + WRITE_ONCE(call->next_req_timo, p.call.timeouts.idle); fallthrough; case 1: if (p.call.timeouts.hard > 0) { - j = p.call.timeouts.hard * HZ; - now = jiffies; - j += now; - WRITE_ONCE(call->expect_term_by, j); - rxrpc_reduce_call_timer(call, j, now, - rxrpc_timer_set_for_hard); + ktime_t delay = ms_to_ktime(p.call.timeouts.hard * MSEC_PER_SEC); + + WRITE_ONCE(call->expect_term_by, + ktime_add(p.call.timeouts.hard, + ktime_get_real())); + trace_rxrpc_timer_set(call, delay, rxrpc_timer_trace_hard); + rxrpc_poke_call(call, rxrpc_call_poke_set_timeout); + } break; } diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index ecaeb4ecfb58..c9bedd0e2d86 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -15,6 +15,8 @@ static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; static const unsigned int n_max_acks = 255; +static const unsigned long one_ms = 1; +static const unsigned long max_ms = 1000; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; #ifdef CONFIG_AF_RXRPC_INJECT_RX_DELAY @@ -28,24 +30,24 @@ static const unsigned long max_500 = 500; * information on the individual parameters. */ static struct ctl_table rxrpc_sysctl_table[] = { - /* Values measured in milliseconds but used in jiffies */ + /* Values measured in milliseconds */ { .procname = "soft_ack_delay", .data = &rxrpc_soft_ack_delay, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, + .proc_handler = proc_doulongvec_minmax, + .extra1 = (void *)&one_ms, + .extra2 = (void *)&max_ms, }, { .procname = "idle_ack_delay", .data = &rxrpc_idle_ack_delay, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, + .proc_handler = proc_doulongvec_minmax, + .extra1 = (void *)&one_ms, + .extra2 = (void *)&max_ms, }, { .procname = "idle_conn_expiry", diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index d43be8512386..b2a82ab756c2 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -14,45 +14,146 @@ static atomic_t rxrpc_txbuf_debug_ids; atomic_t rxrpc_nr_txbuf; /* - * Allocate and partially initialise an I/O request structure. + * Allocate and partially initialise a data transmission buffer. */ -struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, - gfp_t gfp) +struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, + size_t data_align, gfp_t gfp) { + struct rxrpc_wire_header *whdr; struct rxrpc_txbuf *txb; + size_t total, hoff = 0; + void *buf; txb = kmalloc(sizeof(*txb), gfp); - if (txb) { - INIT_LIST_HEAD(&txb->call_link); - INIT_LIST_HEAD(&txb->tx_link); - refcount_set(&txb->ref, 1); - txb->call_debug_id = call->debug_id; - txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); - txb->space = sizeof(txb->data); - txb->len = 0; - txb->offset = 0; - txb->flags = 0; - txb->ack_why = 0; - txb->seq = call->tx_prepared + 1; - txb->wire.epoch = htonl(call->conn->proto.epoch); - txb->wire.cid = htonl(call->cid); - txb->wire.callNumber = htonl(call->call_id); - txb->wire.seq = htonl(txb->seq); - txb->wire.type = packet_type; - txb->wire.flags = call->conn->out_clientflag; - txb->wire.userStatus = 0; - txb->wire.securityIndex = call->security_ix; - txb->wire._rsvd = 0; - txb->wire.serviceId = htons(call->dest_srx.srx_service); - - trace_rxrpc_txbuf(txb->debug_id, - txb->call_debug_id, txb->seq, 1, - packet_type == RXRPC_PACKET_TYPE_DATA ? - rxrpc_txbuf_alloc_data : - rxrpc_txbuf_alloc_ack); - atomic_inc(&rxrpc_nr_txbuf); + if (!txb) + return NULL; + + if (data_align) + hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr); + total = hoff + sizeof(*whdr) + data_size; + + mutex_lock(&call->conn->tx_data_alloc_lock); + buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp, + ~(data_align - 1) & ~(L1_CACHE_BYTES - 1)); + mutex_unlock(&call->conn->tx_data_alloc_lock); + if (!buf) { + kfree(txb); + return NULL; + } + + whdr = buf + hoff; + + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->last_sent = KTIME_MIN; + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = data_size; + txb->len = 0; + txb->offset = sizeof(*whdr); + txb->flags = call->conn->out_clientflag; + txb->ack_why = 0; + txb->seq = call->tx_prepared + 1; + txb->serial = 0; + txb->cksum = 0; + txb->nr_kvec = 1; + txb->kvec[0].iov_base = whdr; + txb->kvec[0].iov_len = sizeof(*whdr); + + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->seq = htonl(txb->seq); + whdr->type = RXRPC_PACKET_TYPE_DATA; + whdr->flags = 0; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->dest_srx.srx_service); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, + rxrpc_txbuf_alloc_data); + + atomic_inc(&rxrpc_nr_txbuf); + return txb; +} + +/* + * Allocate and partially initialise an ACK packet. + */ +struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_size) +{ + struct rxrpc_wire_header *whdr; + struct rxrpc_acktrailer *trailer; + struct rxrpc_ackpacket *ack; + struct rxrpc_txbuf *txb; + gfp_t gfp = rcu_read_lock_held() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS; + void *buf, *buf2 = NULL; + u8 *filler; + + txb = kmalloc(sizeof(*txb), gfp); + if (!txb) + return NULL; + + buf = page_frag_alloc(&call->local->tx_alloc, + sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp); + if (!buf) { + kfree(txb); + return NULL; + } + + if (sack_size) { + buf2 = page_frag_alloc(&call->local->tx_alloc, sack_size, gfp); + if (!buf2) { + page_frag_free(buf); + kfree(txb); + return NULL; + } } + whdr = buf; + ack = buf + sizeof(*whdr); + filler = buf + sizeof(*whdr) + sizeof(*ack) + 1; + trailer = buf + sizeof(*whdr) + sizeof(*ack) + 1 + 3; + + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = 0; + txb->len = sizeof(*whdr) + sizeof(*ack) + 3 + sizeof(*trailer); + txb->offset = 0; + txb->flags = call->conn->out_clientflag; + txb->ack_rwind = 0; + txb->seq = 0; + txb->serial = 0; + txb->cksum = 0; + txb->nr_kvec = 3; + txb->kvec[0].iov_base = whdr; + txb->kvec[0].iov_len = sizeof(*whdr) + sizeof(*ack); + txb->kvec[1].iov_base = buf2; + txb->kvec[1].iov_len = sack_size; + txb->kvec[2].iov_base = filler; + txb->kvec[2].iov_len = 3 + sizeof(*trailer); + + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->seq = 0; + whdr->type = RXRPC_PACKET_TYPE_ACK; + whdr->flags = 0; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->dest_srx.srx_service); + + get_page(virt_to_head_page(trailer)); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, + rxrpc_txbuf_alloc_ack); + atomic_inc(&rxrpc_nr_txbuf); return txb; } @@ -71,12 +172,15 @@ void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r, what); } -static void rxrpc_free_txbuf(struct rcu_head *rcu) +static void rxrpc_free_txbuf(struct rxrpc_txbuf *txb) { - struct rxrpc_txbuf *txb = container_of(rcu, struct rxrpc_txbuf, rcu); + int i; trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, rxrpc_txbuf_free); + for (i = 0; i < txb->nr_kvec; i++) + if (txb->kvec[i].iov_base) + page_frag_free(txb->kvec[i].iov_base); kfree(txb); atomic_dec(&rxrpc_nr_txbuf); } @@ -95,7 +199,7 @@ void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) dead = __refcount_dec_and_test(&txb->ref, &r); trace_rxrpc_txbuf(debug_id, call_debug_id, seq, r - 1, what); if (dead) - call_rcu(&txb->rcu, rxrpc_free_txbuf); + rxrpc_free_txbuf(txb); } } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 9b3e9262040b..ff5336493777 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -27,6 +27,7 @@ #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> +#include <net/hotdata.h> #include <trace/events/qdisc.h> #include <trace/events/net.h> #include <net/xfrm.h> @@ -409,7 +410,7 @@ static inline bool qdisc_restart(struct Qdisc *q, int *packets) void __qdisc_run(struct Qdisc *q) { - int quota = READ_ONCE(dev_tx_weight); + int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6b9fcdb0952a..c67679a41044 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -67,6 +67,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <net/rps.h> /* Forward declarations for internal helper functions. */ static bool sctp_writeable(const struct sock *sk); diff --git a/net/x25/Kconfig b/net/x25/Kconfig index 68729aa3a5d5..dc72302cbd07 100644 --- a/net/x25/Kconfig +++ b/net/x25/Kconfig @@ -17,8 +17,6 @@ config X25 if you want that) and the lower level data link layer protocol LAPB (say Y to "LAPB Data Link Driver" below if you want that). - You can read more about X.25 at <https://www.sangoma.com/tutorials/x25/> and - <http://docwiki.cisco.com/wiki/X.25>. Information about X.25 for Linux is contained in the files <file:Documentation/networking/x25.rst> and <file:Documentation/networking/x25-iface.rst>. diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index d3b3f9e720b3..fe82e2d07300 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -10,6 +10,7 @@ #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6_stubs.h> #endif +#include <net/hotdata.h> static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, struct sock *sk) @@ -169,7 +170,8 @@ int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) { struct espintcp_ctx *ctx = espintcp_getctx(sk); - if (skb_queue_len(&ctx->out_queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&ctx->out_queue) >= + READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; __skb_queue_tail(&ctx->out_queue, skb); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 3784534c9185..653e51ae3964 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -407,7 +407,7 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct net_device *dev = x->xso.dev; - if (!x->type_offload || x->encap) + if (!x->type_offload) return false; if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET || diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index bd4ce21d76d7..161f535c8b94 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -21,6 +21,7 @@ #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h> #include <net/dst_metadata.h> +#include <net/hotdata.h> #include "xfrm_inout.h" @@ -764,7 +765,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, trans = this_cpu_ptr(&xfrm_trans_tasklet); - if (skb_queue_len(&trans->queue) >= READ_ONCE(netdev_max_backlog)) + if (skb_queue_len(&trans->queue) >= READ_ONCE(net_hotdata.max_backlog)) return -ENOBUFS; BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 717855b9acf1..4df5c06e3ece 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -240,7 +240,6 @@ static void xfrmi_dev_free(struct net_device *dev) struct xfrm_if *xi = netdev_priv(dev); gro_cells_destroy(&xi->gro_cells); - free_percpu(dev->tstats); } static int xfrmi_create(struct net_device *dev) @@ -749,6 +748,7 @@ static void xfrmi_dev_setup(struct net_device *dev) dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); eth_broadcast_addr(dev->broadcast); @@ -765,15 +765,9 @@ static int xfrmi_dev_init(struct net_device *dev) struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link); int err; - dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!dev->tstats) - return -ENOMEM; - err = gro_cells_init(&xi->gro_cells, dev); - if (err) { - free_percpu(dev->tstats); + if (err) return err; - } dev->features |= NETIF_F_LLTX; dev->features |= XFRMI_FEATURES; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 662c83beb345..e5722c95b8bb 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -704,9 +704,13 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) { struct net *net = dev_net(skb_dst(skb)->dev); struct xfrm_state *x = skb_dst(skb)->xfrm; + int family; int err; - switch (x->outer_mode.family) { + family = (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) ? x->outer_mode.family + : skb_dst(skb)->ops->family; + + switch (family) { case AF_INET: memset(IPCB(skb), 0, sizeof(*IPCB(skb))); IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 1b7e75159727..6affe5cd85d8 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -29,6 +29,7 @@ #include <linux/audit.h> #include <linux/rhashtable.h> #include <linux/if_tunnel.h> +#include <linux/icmp.h> #include <net/dst.h> #include <net/flow.h> #include <net/inet_ecn.h> @@ -2694,7 +2695,9 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); - family = xfrm[i]->props.family; + if (xfrm[i]->xso.type != XFRM_DEV_OFFLOAD_PACKET) + family = xfrm[i]->props.family; + oif = fl->flowi_oif ? : fl->flowi_l3mdev; dst = xfrm_dst_lookup(xfrm[i], tos, oif, &saddr, &daddr, family, mark); @@ -3416,7 +3419,7 @@ decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reve } fl4->flowi4_proto = flkeys->basic.ip_proto; - fl4->flowi4_tos = flkeys->ip.tos; + fl4->flowi4_tos = flkeys->ip.tos & ~INET_ECN_MASK; } #if IS_ENABLED(CONFIG_IPV6) @@ -3503,6 +3506,128 @@ static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int return 0; } +static bool icmp_err_packet(const struct flowi *fl, unsigned short family) +{ + const struct flowi4 *fl4 = &fl->u.ip4; + + if (family == AF_INET && + fl4->flowi4_proto == IPPROTO_ICMP && + (fl4->fl4_icmp_type == ICMP_DEST_UNREACH || + fl4->fl4_icmp_type == ICMP_TIME_EXCEEDED)) + return true; + +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) { + const struct flowi6 *fl6 = &fl->u.ip6; + + if (fl6->flowi6_proto == IPPROTO_ICMPV6 && + (fl6->fl6_icmp_type == ICMPV6_DEST_UNREACH || + fl6->fl6_icmp_type == ICMPV6_PKT_TOOBIG || + fl6->fl6_icmp_type == ICMPV6_TIME_EXCEED)) + return true; + } +#endif + return false; +} + +static bool xfrm_icmp_flow_decode(struct sk_buff *skb, unsigned short family, + const struct flowi *fl, struct flowi *fl1) +{ + bool ret = true; + struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); + int hl = family == AF_INET ? (sizeof(struct iphdr) + sizeof(struct icmphdr)) : + (sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr)); + + if (!newskb) + return true; + + if (!pskb_pull(newskb, hl)) + goto out; + + skb_reset_network_header(newskb); + + if (xfrm_decode_session_reverse(dev_net(skb->dev), newskb, fl1, family) < 0) + goto out; + + fl1->flowi_oif = fl->flowi_oif; + fl1->flowi_mark = fl->flowi_mark; + fl1->flowi_tos = fl->flowi_tos; + nf_nat_decode_session(newskb, fl1, family); + ret = false; + +out: + consume_skb(newskb); + return ret; +} + +static bool xfrm_selector_inner_icmp_match(struct sk_buff *skb, unsigned short family, + const struct xfrm_selector *sel, + const struct flowi *fl) +{ + bool ret = false; + + if (icmp_err_packet(fl, family)) { + struct flowi fl1; + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return ret; + + ret = xfrm_selector_match(sel, &fl1, family); + } + + return ret; +} + +static inline struct +xfrm_policy *xfrm_in_fwd_icmp(struct sk_buff *skb, + const struct flowi *fl, unsigned short family, + u32 if_id) +{ + struct xfrm_policy *pol = NULL; + + if (icmp_err_packet(fl, family)) { + struct flowi fl1; + struct net *net = dev_net(skb->dev); + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return pol; + + pol = xfrm_policy_lookup(net, &fl1, family, XFRM_POLICY_FWD, if_id); + } + + return pol; +} + +static inline struct +dst_entry *xfrm_out_fwd_icmp(struct sk_buff *skb, struct flowi *fl, + unsigned short family, struct dst_entry *dst) +{ + if (icmp_err_packet(fl, family)) { + struct net *net = dev_net(skb->dev); + struct dst_entry *dst2; + struct flowi fl1; + + if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) + return dst; + + dst_hold(dst); + + dst2 = xfrm_lookup(net, dst, &fl1, NULL, (XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_ICMP)); + + if (IS_ERR(dst2)) + return dst; + + if (dst2->xfrm) { + dst_release(dst); + dst = dst2; + } else { + dst_release(dst2); + } + } + + return dst; +} + int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { @@ -3549,9 +3674,17 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, for (i = sp->len - 1; i >= 0; i--) { struct xfrm_state *x = sp->xvec[i]; + int ret = 0; + if (!xfrm_selector_match(&x->sel, &fl, family)) { - XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); - return 0; + ret = 1; + if (x->props.flags & XFRM_STATE_ICMP && + xfrm_selector_inner_icmp_match(skb, family, &x->sel, &fl)) + ret = 0; + if (ret) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); + return 0; + } } } } @@ -3574,6 +3707,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 0; } + if (!pol && dir == XFRM_POLICY_FWD) + pol = xfrm_in_fwd_icmp(skb, &fl, family, if_id); + if (!pol) { if (net->xfrm.policy_default[dir] == XFRM_USERPOLICY_BLOCK) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); @@ -3707,6 +3843,10 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) res = 0; dst = NULL; } + + if (dst && !dst->xfrm) + dst = xfrm_out_fwd_icmp(skb, &fl, family, dst); + skb_dst_set(skb, dst); return res; } @@ -4025,10 +4165,7 @@ static int __net_init xfrm_policy_init(struct net *net) int dir, err; if (net_eq(net, &init_net)) { - xfrm_dst_cache = kmem_cache_create("xfrm_dst_cache", - sizeof(struct xfrm_dst), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, - NULL); + xfrm_dst_cache = KMEM_CACHE(xfrm_dst, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = rhashtable_init(&xfrm_policy_inexact_table, &xfrm_pol_inexact_params); BUG_ON(err); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a5232dcfea46..810b520493f3 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2017,6 +2017,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index 5a84b6443875..3ee8ecfb8c04 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -33,7 +33,7 @@ ld-option = $(success,$(LD) -v $(1)) # $(as-instr,<instr>) # Return y if the assembler supports <instr>, n otherwise -as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler-with-cpp -o /dev/null -) +as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -) # check if $(CC) and $(LD) exist $(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found) diff --git a/scripts/Makefile.compiler b/scripts/Makefile.compiler index 8fcb427405a6..92be0c9a13ee 100644 --- a/scripts/Makefile.compiler +++ b/scripts/Makefile.compiler @@ -38,7 +38,7 @@ as-option = $(call try-run,\ # Usage: aflags-y += $(call as-instr,instr,option1,option2) as-instr = $(call try-run,\ - printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3)) + printf "%b\n" "$(1)" | $(CC) -Werror $(CLANG_FLAGS) $(KBUILD_AFLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o "$$TMP" -,$(2),$(3)) # __cc-option # Usage: MY_CFLAGS += $(call __cc-option,$(CC),$(MY_CFLAGS),-march=winchip-c6,-march=i586) diff --git a/security/integrity/digsig.c b/security/integrity/digsig.c index df387de29bfa..45c3e5dda355 100644 --- a/security/integrity/digsig.c +++ b/security/integrity/digsig.c @@ -179,7 +179,8 @@ static int __init integrity_add_key(const unsigned int id, const void *data, KEY_ALLOC_NOT_IN_QUOTA); if (IS_ERR(key)) { rc = PTR_ERR(key); - pr_err("Problem loading X.509 certificate %d\n", rc); + if (id != INTEGRITY_KEYRING_MACHINE) + pr_err("Problem loading X.509 certificate %d\n", rc); } else { pr_notice("Loaded X.509 cert '%s'\n", key_ref_to_ptr(key)->description); diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index 57ee70ae50f2..ea3140d510ec 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -2649,13 +2649,14 @@ ssize_t tomoyo_write_control(struct tomoyo_io_buffer *head, { int error = buffer_len; size_t avail_len = buffer_len; - char *cp0 = head->write_buf; + char *cp0; int idx; if (!head->write) return -EINVAL; if (mutex_lock_interruptible(&head->io_sem)) return -EINTR; + cp0 = head->write_buf; head->read_user_buf_avail = 0; idx = tomoyo_read_lock(); /* Read a line and dispatch it to the policy handler. */ diff --git a/sound/core/Makefile b/sound/core/Makefile index a6b444ee2832..f6526b337137 100644 --- a/sound/core/Makefile +++ b/sound/core/Makefile @@ -32,7 +32,6 @@ snd-ump-objs := ump.o snd-ump-$(CONFIG_SND_UMP_LEGACY_RAWMIDI) += ump_convert.o snd-timer-objs := timer.o snd-hrtimer-objs := hrtimer.o -snd-rtctimer-objs := rtctimer.o snd-hwdep-objs := hwdep.o snd-seq-device-objs := seq_device.o diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index f5ff00f99788..21baf6bf7e25 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -486,6 +486,11 @@ static int fixup_unreferenced_params(struct snd_pcm_substream *substream, i = hw_param_interval_c(params, SNDRV_PCM_HW_PARAM_SAMPLE_BITS); if (snd_interval_single(i)) params->msbits = snd_interval_value(i); + m = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT); + if (snd_mask_single(m)) { + snd_pcm_format_t format = (__force snd_pcm_format_t)snd_mask_min(m); + params->msbits = snd_pcm_format_width(format); + } } if (params->msbits) { diff --git a/sound/core/ump.c b/sound/core/ump.c index 3bef1944e955..fe7911498cc4 100644 --- a/sound/core/ump.c +++ b/sound/core/ump.c @@ -985,7 +985,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream) struct snd_ump_endpoint *ump = substream->rmidi->private_data; int dir = substream->stream; int group = ump->legacy_mapping[substream->number]; - int err; + int err = 0; mutex_lock(&ump->open_mutex); if (ump->legacy_substreams[dir][group]) { @@ -1009,7 +1009,7 @@ static int snd_ump_legacy_open(struct snd_rawmidi_substream *substream) spin_unlock_irq(&ump->legacy_locks[dir]); unlock: mutex_unlock(&ump->open_mutex); - return 0; + return err; } static int snd_ump_legacy_close(struct snd_rawmidi_substream *substream) diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index a13c0b408aad..7be17bca257f 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -951,7 +951,7 @@ static int generate_tx_packet_descs(struct amdtp_stream *s, struct pkt_desc *des // to the reason. unsigned int safe_cycle = increment_ohci_cycle_count(next_cycle, IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES); - lost = (compare_ohci_cycle_count(safe_cycle, cycle) > 0); + lost = (compare_ohci_cycle_count(safe_cycle, cycle) < 0); } if (lost) { dev_err(&s->unit->device, "Detect discontinuity of cycle: %d %d\n", diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 0ec1312bffd5..62701197a019 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3684,6 +3684,7 @@ static void alc285_hp_init(struct hda_codec *codec) int i, val; int coef38, coef0d, coef36; + alc_write_coefex_idx(codec, 0x58, 0x00, 0x1888); /* write default value */ alc_update_coef_idx(codec, 0x4a, 1<<15, 1<<15); /* Reset HP JD */ coef38 = alc_read_coef_idx(codec, 0x38); /* Amp control */ coef0d = alc_read_coef_idx(codec, 0x0d); /* Digital Misc control */ @@ -7444,6 +7445,7 @@ enum { ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE, ALC287_FIXUP_YOGA7_14ITL_SPEAKERS, ALC298_FIXUP_LENOVO_C940_DUET7, + ALC287_FIXUP_LENOVO_14IRP8_DUETITL, ALC287_FIXUP_13S_GEN2_SPEAKERS, ALC256_FIXUP_SET_COEF_DEFAULTS, ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE, @@ -7495,6 +7497,26 @@ static void alc298_fixup_lenovo_c940_duet7(struct hda_codec *codec, __snd_hda_apply_fixup(codec, id, action, 0); } +/* A special fixup for Lenovo Slim/Yoga Pro 9 14IRP8 and Yoga DuetITL 2021; + * 14IRP8 PCI SSID will mistakenly be matched with the DuetITL codec SSID, + * so we need to apply a different fixup in this case. The only DuetITL codec + * SSID reported so far is the 17aa:3802 while the 14IRP8 has the 17aa:38be + * and 17aa:38bf. If it weren't for the PCI SSID, the 14IRP8 models would + * have matched correctly by their codecs. + */ +static void alc287_fixup_lenovo_14irp8_duetitl(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + int id; + + if (codec->core.subsystem_id == 0x17aa3802) + id = ALC287_FIXUP_YOGA7_14ITL_SPEAKERS; /* DuetITL */ + else + id = ALC287_FIXUP_TAS2781_I2C; /* 14IRP8 */ + __snd_hda_apply_fixup(codec, id, action, 0); +} + static const struct hda_fixup alc269_fixups[] = { [ALC269_FIXUP_GPIO2] = { .type = HDA_FIXUP_FUNC, @@ -9379,6 +9401,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc298_fixup_lenovo_c940_duet7, }, + [ALC287_FIXUP_LENOVO_14IRP8_DUETITL] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc287_fixup_lenovo_14irp8_duetitl, + }, [ALC287_FIXUP_13S_GEN2_SPEAKERS] = { .type = HDA_FIXUP_VERBS, .v.verbs = (const struct hda_verb[]) { @@ -9585,7 +9611,7 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = tas2781_fixup_i2c, .chained = true, - .chain_id = ALC269_FIXUP_THINKPAD_ACPI, + .chain_id = ALC285_FIXUP_THINKPAD_HEADSET_JACK, }, [ALC287_FIXUP_YOGA7_14ARB7_I2C] = { .type = HDA_FIXUP_FUNC, @@ -9746,6 +9772,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0c1c, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1d, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1e, "Dell Precision 3540", ALC236_FIXUP_DELL_DUAL_CODECS), + SND_PCI_QUIRK(0x1028, 0x0c28, "Dell Inspiron 16 Plus 7630", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0c4d, "Dell", ALC287_FIXUP_CS35L41_I2C_4), SND_PCI_QUIRK(0x1028, 0x0cbd, "Dell Oasis 13 CS MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), SND_PCI_QUIRK(0x1028, 0x0cbe, "Dell Oasis 13 2-IN-1 MTL-U", ALC289_FIXUP_DELL_CS35L41_SPI_2), @@ -9902,6 +9929,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8973, "HP EliteBook 860 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8974, "HP EliteBook 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8975, "HP EliteBook x360 840 Aero G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x897d, "HP mt440 Mobile Thin Client U74", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8981, "HP Elite Dragonfly G3", ALC245_FIXUP_CS35L41_SPI_4), SND_PCI_QUIRK(0x103c, 0x898e, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x103c, 0x898f, "HP EliteBook 835 G9", ALC287_FIXUP_CS35L41_I2C_2), @@ -9927,11 +9955,13 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8aa3, "HP ProBook 450 G9 (MB 8AA1)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aa8, "HP EliteBook 640 G9 (MB 8AA6)", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8aab, "HP EliteBook 650 G9 (MB 8AA9)", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ab9, "HP EliteBook 840 G8 (MB 8AB8)", ALC285_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b0f, "HP Elite mt645 G7 Mobile Thin Client U81", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), + SND_PCI_QUIRK(0x103c, 0x8b3f, "HP mt440 Mobile Thin Client U91", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -10247,7 +10277,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340), SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), - SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS), + SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga Pro 9 14IRP8 / DuetITL 2021", ALC287_FIXUP_LENOVO_14IRP8_DUETITL), SND_PCI_QUIRK(0x17aa, 0x3813, "Legion 7i 15IMHG05", ALC287_FIXUP_LEGION_15IMHG05_SPEAKERS), SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940 / Yoga Duet 7", ALC298_FIXUP_LENOVO_C940_DUET7), SND_PCI_QUIRK(0x17aa, 0x3819, "Lenovo 13s Gen2 ITL", ALC287_FIXUP_13S_GEN2_SPEAKERS), diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index cc231185d72c..abb9589b8477 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -203,6 +203,20 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { .driver_data = &acp6x_card, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21J2"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "21J0"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), DMI_MATCH(DMI_PRODUCT_NAME, "21J5"), } }, diff --git a/sound/soc/amd/yc/pci-acp6x.c b/sound/soc/amd/yc/pci-acp6x.c index 7af6a349b1d4..694b8e313902 100644 --- a/sound/soc/amd/yc/pci-acp6x.c +++ b/sound/soc/amd/yc/pci-acp6x.c @@ -162,6 +162,7 @@ static int snd_acp6x_probe(struct pci_dev *pci, /* Yellow Carp device check */ switch (pci->revision) { case 0x60: + case 0x63: case 0x6f: break; default: diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c index 44c221745c3b..2392c6effed8 100644 --- a/sound/soc/codecs/cs35l45.c +++ b/sound/soc/codecs/cs35l45.c @@ -184,7 +184,7 @@ static int cs35l45_activate_ctl(struct snd_soc_component *component, else snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s", ctl_name); - kcontrol = snd_soc_card_get_kcontrol(component->card, name); + kcontrol = snd_soc_card_get_kcontrol_locked(component->card, name); if (!kcontrol) { dev_err(component->dev, "Can't find kcontrol %s\n", name); return -EINVAL; diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c index 995d979b6d87..cb4e83126b08 100644 --- a/sound/soc/codecs/cs35l56-shared.c +++ b/sound/soc/codecs/cs35l56-shared.c @@ -335,6 +335,7 @@ void cs35l56_wait_min_reset_pulse(void) EXPORT_SYMBOL_NS_GPL(cs35l56_wait_min_reset_pulse, SND_SOC_CS35L56_SHARED); static const struct reg_sequence cs35l56_system_reset_seq[] = { + REG_SEQ0(CS35L56_DSP1_HALO_STATE, 0), REG_SEQ0(CS35L56_DSP_VIRTUAL1_MBOX_1, CS35L56_MBOX_CMD_SYSTEM_RESET), }; diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index 2c1313e34cce..6dd0319bc843 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -114,7 +114,7 @@ static int cs35l56_sync_asp1_mixer_widgets_with_firmware(struct cs35l56_private name = full_name; } - kcontrol = snd_soc_card_get_kcontrol(dapm->card, name); + kcontrol = snd_soc_card_get_kcontrol_locked(dapm->card, name); if (!kcontrol) { dev_warn(cs35l56->base.dev, "Could not find control %s\n", name); continue; diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c index f0fb33d719c2..c46f64557a7f 100644 --- a/sound/soc/fsl/fsl_xcvr.c +++ b/sound/soc/fsl/fsl_xcvr.c @@ -174,7 +174,9 @@ static int fsl_xcvr_activate_ctl(struct snd_soc_dai *dai, const char *name, struct snd_kcontrol *kctl; bool enabled; - kctl = snd_soc_card_get_kcontrol(card, name); + lockdep_assert_held(&card->snd_card->controls_rwsem); + + kctl = snd_soc_card_get_kcontrol_locked(card, name); if (kctl == NULL) return -ENOENT; @@ -576,10 +578,14 @@ static int fsl_xcvr_startup(struct snd_pcm_substream *substream, xcvr->streams |= BIT(substream->stream); if (!xcvr->soc_data->spdif_only) { + struct snd_soc_card *card = dai->component->card; + /* Disable XCVR controls if there is stream started */ + down_read(&card->snd_card->controls_rwsem); fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, false); fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name, false); fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name, false); + up_read(&card->snd_card->controls_rwsem); } return 0; @@ -598,11 +604,15 @@ static void fsl_xcvr_shutdown(struct snd_pcm_substream *substream, /* Enable XCVR controls if there is no stream started */ if (!xcvr->streams) { if (!xcvr->soc_data->spdif_only) { + struct snd_soc_card *card = dai->component->card; + + down_read(&card->snd_card->controls_rwsem); fsl_xcvr_activate_ctl(dai, fsl_xcvr_mode_kctl.name, true); fsl_xcvr_activate_ctl(dai, fsl_xcvr_arc_mode_kctl.name, (xcvr->mode == FSL_XCVR_MODE_ARC)); fsl_xcvr_activate_ctl(dai, fsl_xcvr_earc_capds_kctl.name, (xcvr->mode == FSL_XCVR_MODE_EARC)); + up_read(&card->snd_card->controls_rwsem); } ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_IER0, FSL_XCVR_IRQ_EARC_ALL, 0); diff --git a/sound/soc/qcom/lpass-cdc-dma.c b/sound/soc/qcom/lpass-cdc-dma.c index 48b03e60e3a3..8106c586f68a 100644 --- a/sound/soc/qcom/lpass-cdc-dma.c +++ b/sound/soc/qcom/lpass-cdc-dma.c @@ -259,7 +259,7 @@ static int lpass_cdc_dma_daiops_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { struct snd_soc_pcm_runtime *soc_runtime = snd_soc_substream_to_rtd(substream); - struct lpaif_dmactl *dmactl; + struct lpaif_dmactl *dmactl = NULL; int ret = 0, id; switch (cmd) { diff --git a/sound/soc/soc-card.c b/sound/soc/soc-card.c index 285ab4c9c716..8a2f163da6bc 100644 --- a/sound/soc/soc-card.c +++ b/sound/soc/soc-card.c @@ -5,6 +5,9 @@ // Copyright (C) 2019 Renesas Electronics Corp. // Kuninori Morimoto <[email protected]> // + +#include <linux/lockdep.h> +#include <linux/rwsem.h> #include <sound/soc.h> #include <sound/jack.h> @@ -26,12 +29,15 @@ static inline int _soc_card_ret(struct snd_soc_card *card, return ret; } -struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, - const char *name) +struct snd_kcontrol *snd_soc_card_get_kcontrol_locked(struct snd_soc_card *soc_card, + const char *name) { struct snd_card *card = soc_card->snd_card; struct snd_kcontrol *kctl; + /* must be held read or write */ + lockdep_assert_held(&card->controls_rwsem); + if (unlikely(!name)) return NULL; @@ -40,6 +46,20 @@ struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, return kctl; return NULL; } +EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol_locked); + +struct snd_kcontrol *snd_soc_card_get_kcontrol(struct snd_soc_card *soc_card, + const char *name) +{ + struct snd_card *card = soc_card->snd_card; + struct snd_kcontrol *kctl; + + down_read(&card->controls_rwsem); + kctl = snd_soc_card_get_kcontrol_locked(soc_card, name); + up_read(&card->controls_rwsem); + + return kctl; +} EXPORT_SYMBOL_GPL(snd_soc_card_get_kcontrol); static int jack_new(struct snd_soc_card *card, const char *id, int type, diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 93cb411adf72..bb65ee840cda 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -70,6 +70,10 @@ enum netdev_queue_type { NETDEV_QUEUE_TYPE_TX, }; +enum netdev_qstats_scope { + NETDEV_QSTATS_SCOPE_QUEUE = 1, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, @@ -133,6 +137,21 @@ enum { }; enum { + NETDEV_A_QSTATS_IFINDEX = 1, + NETDEV_A_QSTATS_QUEUE_TYPE, + NETDEV_A_QSTATS_QUEUE_ID, + NETDEV_A_QSTATS_SCOPE, + NETDEV_A_QSTATS_RX_PACKETS = 8, + NETDEV_A_QSTATS_RX_BYTES, + NETDEV_A_QSTATS_TX_PACKETS, + NETDEV_A_QSTATS_TX_BYTES, + NETDEV_A_QSTATS_RX_ALLOC_FAIL, + + __NETDEV_A_QSTATS_MAX, + NETDEV_A_QSTATS_MAX = (__NETDEV_A_QSTATS_MAX - 1) +}; + +enum { NETDEV_CMD_DEV_GET = 1, NETDEV_CMD_DEV_ADD_NTF, NETDEV_CMD_DEV_DEL_NTF, @@ -144,6 +163,7 @@ enum { NETDEV_CMD_PAGE_POOL_STATS_GET, NETDEV_CMD_QUEUE_GET, NETDEV_CMD_NAPI_GET, + NETDEV_CMD_QSTATS_GET, __NETDEV_CMD_MAX, NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) diff --git a/tools/net/ynl/cli.py b/tools/net/ynl/cli.py index e8a65fbc3698..f131e33ac3ee 100755 --- a/tools/net/ynl/cli.py +++ b/tools/net/ynl/cli.py @@ -6,7 +6,7 @@ import json import pprint import time -from lib import YnlFamily, Netlink +from lib import YnlFamily, Netlink, NlError class YnlEncoder(json.JSONEncoder): @@ -66,12 +66,16 @@ def main(): if args.sleep: time.sleep(args.sleep) - if args.do: - reply = ynl.do(args.do, attrs, args.flags) - output(reply) - if args.dump: - reply = ynl.dump(args.dump, attrs) - output(reply) + try: + if args.do: + reply = ynl.do(args.do, attrs, args.flags) + output(reply) + if args.dump: + reply = ynl.dump(args.dump, attrs) + output(reply) + except NlError as e: + print(e) + exit(1) if args.ntf: ynl.check_ntf() diff --git a/tools/net/ynl/lib/__init__.py b/tools/net/ynl/lib/__init__.py index f7eaa07783e7..9137b83e580a 100644 --- a/tools/net/ynl/lib/__init__.py +++ b/tools/net/ynl/lib/__init__.py @@ -2,7 +2,7 @@ from .nlspec import SpecAttr, SpecAttrSet, SpecEnumEntry, SpecEnumSet, \ SpecFamily, SpecOperation -from .ynl import YnlFamily, Netlink +from .ynl import YnlFamily, Netlink, NlError __all__ = ["SpecAttr", "SpecAttrSet", "SpecEnumEntry", "SpecEnumSet", - "SpecFamily", "SpecOperation", "YnlFamily", "Netlink"] + "SpecFamily", "SpecOperation", "YnlFamily", "Netlink", "NlError"] diff --git a/tools/net/ynl/lib/ynl-priv.h b/tools/net/ynl/lib/ynl-priv.h index a8099fab035d..6cf890080dc0 100644 --- a/tools/net/ynl/lib/ynl-priv.h +++ b/tools/net/ynl/lib/ynl-priv.h @@ -135,6 +135,8 @@ int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); /* Netlink message handling helpers */ +#define YNL_MSG_OVERFLOW 1 + static inline struct nlmsghdr *ynl_nlmsg_put_header(void *buf) { struct nlmsghdr *nlh = buf; @@ -239,11 +241,29 @@ ynl_attr_first(const void *start, size_t len, size_t skip) return ynl_attr_if_good(start + len, attr); } +static inline bool +__ynl_attr_put_overflow(struct nlmsghdr *nlh, size_t size) +{ + bool o; + + /* ynl_msg_start() stashed buffer length in nlmsg_pid. */ + o = nlh->nlmsg_len + NLA_HDRLEN + NLMSG_ALIGN(size) > nlh->nlmsg_pid; + if (o) + /* YNL_MSG_OVERFLOW is < NLMSG_HDRLEN, all subsequent checks + * are guaranteed to fail. + */ + nlh->nlmsg_pid = YNL_MSG_OVERFLOW; + return o; +} + static inline struct nlattr * ynl_attr_nest_start(struct nlmsghdr *nlh, unsigned int attr_type) { struct nlattr *attr; + if (__ynl_attr_put_overflow(nlh, 0)) + return ynl_nlmsg_end_addr(nlh) - NLA_HDRLEN; + attr = ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type | NLA_F_NESTED; nlh->nlmsg_len += NLA_HDRLEN; @@ -263,6 +283,9 @@ ynl_attr_put(struct nlmsghdr *nlh, unsigned int attr_type, { struct nlattr *attr; + if (__ynl_attr_put_overflow(nlh, size)) + return; + attr = ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; attr->nla_len = NLA_HDRLEN + size; @@ -276,14 +299,17 @@ static inline void ynl_attr_put_str(struct nlmsghdr *nlh, unsigned int attr_type, const char *str) { struct nlattr *attr; - const char *end; + size_t len; + + len = strlen(str); + if (__ynl_attr_put_overflow(nlh, len)) + return; attr = ynl_nlmsg_end_addr(nlh); attr->nla_type = attr_type; - end = stpcpy(ynl_attr_data(attr), str); - attr->nla_len = - NLA_HDRLEN + NLA_ALIGN(end - (char *)ynl_attr_data(attr)); + strcpy(ynl_attr_data(attr), str); + attr->nla_len = NLA_HDRLEN + NLA_ALIGN(len); nlh->nlmsg_len += NLMSG_ALIGN(attr->nla_len); } diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index 484070492b17..b9e77af5af5f 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -404,9 +404,33 @@ struct nlmsghdr *ynl_msg_start(struct ynl_sock *ys, __u32 id, __u16 flags) nlh->nlmsg_flags = flags; nlh->nlmsg_seq = ++ys->seq; + /* This is a local YNL hack for length checking, we put the buffer + * length in nlmsg_pid, since messages sent to the kernel always use + * PID 0. Message needs to be terminated with ynl_msg_end(). + */ + nlh->nlmsg_pid = YNL_SOCKET_BUFFER_SIZE; + return nlh; } +static int ynl_msg_end(struct ynl_sock *ys, struct nlmsghdr *nlh) +{ + /* We stash buffer length in nlmsg_pid. */ + if (nlh->nlmsg_pid == 0) { + yerr(ys, YNL_ERROR_INPUT_INVALID, + "Unknown input buffer length"); + return -EINVAL; + } + if (nlh->nlmsg_pid == YNL_MSG_OVERFLOW) { + yerr(ys, YNL_ERROR_INPUT_TOO_BIG, + "Constructred message longer than internal buffer"); + return -EMSGSIZE; + } + + nlh->nlmsg_pid = 0; + return 0; +} + struct nlmsghdr * ynl_gemsg_start(struct ynl_sock *ys, __u32 id, __u16 flags, __u8 cmd, __u8 version) @@ -607,6 +631,10 @@ static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name) nlh = ynl_gemsg_start_req(ys, GENL_ID_CTRL, CTRL_CMD_GETFAMILY, 1); ynl_attr_put_str(nlh, CTRL_ATTR_FAMILY_NAME, family_name); + err = ynl_msg_end(ys, nlh); + if (err < 0) + return err; + err = send(ys->socket, nlh, nlh->nlmsg_len, 0); if (err < 0) { perr(ys, "failed to request socket family info"); @@ -868,6 +896,10 @@ int ynl_exec(struct ynl_sock *ys, struct nlmsghdr *req_nlh, { int err; + err = ynl_msg_end(ys, req_nlh); + if (err < 0) + return err; + err = send(ys->socket, req_nlh, req_nlh->nlmsg_len, 0); if (err < 0) return err; @@ -921,6 +953,10 @@ int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, { int err; + err = ynl_msg_end(ys, req_nlh); + if (err < 0) + return err; + err = send(ys->socket, req_nlh, req_nlh->nlmsg_len, 0); if (err < 0) return err; diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h index dbeeef8ce91a..9842e85a8c57 100644 --- a/tools/net/ynl/lib/ynl.h +++ b/tools/net/ynl/lib/ynl.h @@ -20,6 +20,8 @@ enum ynl_error_code { YNL_ERROR_ATTR_INVALID, YNL_ERROR_UNKNOWN_NTF, YNL_ERROR_INV_RESP, + YNL_ERROR_INPUT_INVALID, + YNL_ERROR_INPUT_TOO_BIG, }; /** diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 239e22b7a85f..2d7fdd903d9e 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -353,6 +353,9 @@ class NetlinkProtocol: raise Exception(f'Multicast group "{mcast_name}" not present in the spec') return mcast_groups[mcast_name].value + def msghdr_size(self): + return 16 + class GenlProtocol(NetlinkProtocol): def __init__(self, family_name): @@ -378,6 +381,8 @@ class GenlProtocol(NetlinkProtocol): raise Exception(f'Multicast group "{mcast_name}" not present in the family') return self.genl_family['mcast'][mcast_name] + def msghdr_size(self): + return super().msghdr_size() + 4 class SpaceAttrs: @@ -590,6 +595,16 @@ class YnlFamily(SpecFamily): decoded.append({ item.type: subattrs }) return decoded + def _decode_nest_type_value(self, attr, attr_spec): + decoded = {} + value = attr + for name in attr_spec['type-value']: + value = NlAttr(value.raw, 0) + decoded[name] = value.type + subattrs = self._decode(NlAttrs(value.raw), attr_spec['nested-attributes']) + decoded.update(subattrs) + return decoded + def _decode_unknown(self, attr): if attr.is_nest: return self._decode(NlAttrs(attr.raw), None) @@ -681,6 +696,8 @@ class YnlFamily(SpecFamily): decoded = {"value": value, "selector": selector} elif attr_spec["type"] == 'sub-message': decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) + elif attr_spec["type"] == 'nest-type-value': + decoded = self._decode_nest_type_value(attr, attr_spec) else: if not self.process_unknown: raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') @@ -721,7 +738,7 @@ class YnlFamily(SpecFamily): return msg = self.nlproto.decode(self, NlMsg(request, 0, op.attr_set)) - offset = 20 + self._struct_size(op.fixed_header) + offset = self.nlproto.msghdr_size() + self._struct_size(op.fixed_header) path = self._decode_extack_path(msg.raw_attrs, op.attr_set, offset, extack['bad-attr-offs']) if path: diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 2f5febfe66a1..67bfaff05154 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -1667,7 +1667,7 @@ def _multi_parse(ri, struct, init_lines, local_vars): aspec = struct[anest] ri.cw.block_start(line=f"if (n_{aspec.c_name})") - ri.cw.p(f"dst->{aspec.c_name} = calloc({aspec.c_name}, sizeof(*dst->{aspec.c_name}));") + ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));") ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};") ri.cw.p('i = 0;') ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;") diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index c3b45745cbcc..6d8b54124cb3 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -511,7 +511,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons) if (!ASSERT_OK(err, "bond bpf_xdp_query")) goto out; - if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + if (!ASSERT_EQ(query_opts.feature_flags, 0, "bond query_opts.feature_flags")) goto out; @@ -601,7 +601,7 @@ static void test_xdp_bonding_features(struct skeletons *skeletons) if (!ASSERT_OK(err, "bond bpf_xdp_query")) goto out; - ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_MASK, + ASSERT_EQ(query_opts.feature_flags, 0, "bond query_opts.feature_flags"); out: bpf_link__destroy(link); diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c index 5905e036e0ea..a955a6358206 100644 --- a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -239,4 +239,74 @@ int bpf_loop_iter_limit_nested(void *unused) return 1000 * a + b + c; } +struct iter_limit_bug_ctx { + __u64 a; + __u64 b; + __u64 c; +}; + +static __naked void iter_limit_bug_cb(void) +{ + /* This is the same as C code below, but written + * in assembly to control which branches are fall-through. + * + * switch (bpf_get_prandom_u32()) { + * case 1: ctx->a = 42; break; + * case 2: ctx->b = 42; break; + * default: ctx->c = 42; break; + * } + */ + asm volatile ( + "r9 = r2;" + "call %[bpf_get_prandom_u32];" + "r1 = r0;" + "r2 = 42;" + "r0 = 0;" + "if r1 == 0x1 goto 1f;" + "if r1 == 0x2 goto 2f;" + "*(u64 *)(r9 + 16) = r2;" + "exit;" + "1: *(u64 *)(r9 + 0) = r2;" + "exit;" + "2: *(u64 *)(r9 + 8) = r2;" + "exit;" + : + : __imm(bpf_get_prandom_u32) + : __clobber_all + ); +} + +SEC("tc") +__failure +__flag(BPF_F_TEST_STATE_FREQ) +int iter_limit_bug(struct __sk_buff *skb) +{ + struct iter_limit_bug_ctx ctx = { 7, 7, 7 }; + + bpf_loop(2, iter_limit_bug_cb, &ctx, 0); + + /* This is the same as C code below, + * written in assembly to guarantee checks order. + * + * if (ctx.a == 42 && ctx.b == 42 && ctx.c == 7) + * asm volatile("r1 /= 0;":::"r1"); + */ + asm volatile ( + "r1 = *(u64 *)%[ctx_a];" + "if r1 != 42 goto 1f;" + "r1 = *(u64 *)%[ctx_b];" + "if r1 != 42 goto 1f;" + "r1 = *(u64 *)%[ctx_c];" + "if r1 != 7 goto 1f;" + "r1 /= 0;" + "1:" + : + : [ctx_a]"m"(ctx.a), + [ctx_b]"m"(ctx.b), + [ctx_c]"m"(ctx.c) + : "r1" + ); + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 634be793ad58..4fd735e48ee7 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -382,29 +382,33 @@ /* fixture data is alloced, setup, and torn down per call. */ \ FIXTURE_DATA(fixture_name) self; \ pid_t child = 1; \ + int status = 0; \ memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \ if (setjmp(_metadata->env) == 0) { \ - fixture_name##_setup(_metadata, &self, variant->data); \ - /* Let setup failure terminate early. */ \ - if (_metadata->exit_code) \ - return; \ - _metadata->setup_completed = true; \ /* Use the same _metadata. */ \ child = vfork(); \ if (child == 0) { \ + fixture_name##_setup(_metadata, &self, variant->data); \ + /* Let setup failure terminate early. */ \ + if (_metadata->exit_code) \ + _exit(0); \ + _metadata->setup_completed = true; \ fixture_name##_##test_name(_metadata, &self, variant->data); \ - _exit(0); \ - } \ - if (child < 0) { \ + } else if (child < 0 || child != waitpid(child, &status, 0)) { \ ksft_print_msg("ERROR SPAWNING TEST GRANDCHILD\n"); \ _metadata->exit_code = KSFT_FAIL; \ } \ } \ - if (child == 0) \ - /* Child failed and updated the shared _metadata. */ \ + if (child == 0) { \ + if (_metadata->setup_completed && !_metadata->teardown_parent) \ + fixture_name##_teardown(_metadata, &self, variant->data); \ _exit(0); \ - if (_metadata->setup_completed) \ + } \ + if (_metadata->setup_completed && _metadata->teardown_parent) \ fixture_name##_teardown(_metadata, &self, variant->data); \ + if (!WIFEXITED(status) && WIFSIGNALED(status)) \ + /* Forward signal to __wait_for_test(). */ \ + kill(getpid(), WTERMSIG(status)); \ __test_check_assert(_metadata); \ } \ static struct __test_metadata \ @@ -414,6 +418,7 @@ .fixture = &_##fixture_name##_fixture_object, \ .termsig = signal, \ .timeout = tmout, \ + .teardown_parent = false, \ }; \ static void __attribute__((constructor)) \ _register_##fixture_name##_##test_name(void) \ @@ -873,6 +878,7 @@ struct __test_metadata { bool timed_out; /* did this test timeout instead of exiting? */ bool aborted; /* stopped test due to failed ASSERT */ bool setup_completed; /* did setup finish? */ + bool teardown_parent; /* run teardown in a parent process */ jmp_buf env; /* for exiting out of test early */ struct __test_results *results; struct __test_metadata *prev, *next; diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 98817a14c91b..9a6036fbf289 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -285,6 +285,8 @@ static void prepare_layout_opt(struct __test_metadata *const _metadata, static void prepare_layout(struct __test_metadata *const _metadata) { + _metadata->teardown_parent = true; + prepare_layout_opt(_metadata, &mnt_tmp); } @@ -3861,9 +3863,7 @@ FIXTURE_SETUP(layout1_bind) FIXTURE_TEARDOWN(layout1_bind) { - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(dir_s2d2)); - clear_cap(_metadata, CAP_SYS_ADMIN); + /* umount(dir_s2d2)) is handled by namespace lifetime. */ remove_layout1(_metadata); @@ -4276,9 +4276,8 @@ FIXTURE_TEARDOWN(layout2_overlay) EXPECT_EQ(0, remove_path(lower_fl1)); EXPECT_EQ(0, remove_path(lower_do1_fo2)); EXPECT_EQ(0, remove_path(lower_fo1)); - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(LOWER_BASE)); - clear_cap(_metadata, CAP_SYS_ADMIN); + + /* umount(LOWER_BASE)) is handled by namespace lifetime. */ EXPECT_EQ(0, remove_path(LOWER_BASE)); EXPECT_EQ(0, remove_path(upper_do1_fu3)); @@ -4287,14 +4286,11 @@ FIXTURE_TEARDOWN(layout2_overlay) EXPECT_EQ(0, remove_path(upper_do1_fo2)); EXPECT_EQ(0, remove_path(upper_fo1)); EXPECT_EQ(0, remove_path(UPPER_WORK "/work")); - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(UPPER_BASE)); - clear_cap(_metadata, CAP_SYS_ADMIN); + + /* umount(UPPER_BASE)) is handled by namespace lifetime. */ EXPECT_EQ(0, remove_path(UPPER_BASE)); - set_cap(_metadata, CAP_SYS_ADMIN); - EXPECT_EQ(0, umount(MERGE_DATA)); - clear_cap(_metadata, CAP_SYS_ADMIN); + /* umount(MERGE_DATA)) is handled by namespace lifetime. */ EXPECT_EQ(0, remove_path(MERGE_DATA)); cleanup_layout(_metadata); @@ -4691,6 +4687,8 @@ FIXTURE_SETUP(layout3_fs) SKIP(return, "this filesystem is not supported (setup)"); } + _metadata->teardown_parent = true; + slash = strrchr(variant->file_path, '/'); ASSERT_NE(slash, NULL); dir_len = (size_t)slash - (size_t)variant->file_path; diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 3ec1050e47a2..73895711cdf4 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -789,6 +789,7 @@ fib6_gc_test() set -e EXPIRE=5 + GC_WAIT_TIME=$((EXPIRE * 2 + 2)) # Check expiration of routes every $EXPIRE seconds (GC) $NS_EXEC sysctl -wq net.ipv6.route.gc_interval=$EXPIRE @@ -805,7 +806,7 @@ fib6_gc_test() $IP -6 route add 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - sleep $(($EXPIRE * 2 + 1)) + sleep $GC_WAIT_TIME $NS_EXEC sysctl -wq net.ipv6.route.flush=1 check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection" @@ -823,7 +824,8 @@ fib6_gc_test() $IP -6 route add 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - sleep $(($EXPIRE * 2 + 1)) + # Wait for GC + sleep $GC_WAIT_TIME check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection (with permanent routes)" @@ -840,10 +842,8 @@ fib6_gc_test() $IP -6 route replace 2001:20::$i \ via 2001:10::2 dev dummy_10 expires $EXPIRE done - check_rt_num_clean 5 $($IP -6 route list |grep expires|wc -l) || return # Wait for GC - sleep $(($EXPIRE * 2 + 1)) - $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + sleep $GC_WAIT_TIME check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection (replace with expires)" @@ -863,8 +863,7 @@ fib6_gc_test() check_rt_num_clean 0 $($IP -6 route list |grep expires|wc -l) || return # Wait for GC - sleep $(($EXPIRE * 2 + 1)) - + sleep $GC_WAIT_TIME check_rt_num 5 $($IP -6 route list |grep -v expires|grep 2001:20::|wc -l) log_test $ret 0 "ipv6 route garbage collection (replace with permanent)" @@ -901,9 +900,7 @@ fib6_gc_test() check_rt_num_clean 1 $($IP -6 route list|grep expires|wc -l) || return # Wait for GC - sleep $(($EXPIRE * 2 + 1)) - - $NS_EXEC sysctl -wq net.ipv6.route.flush=1 + sleep $GC_WAIT_TIME check_rt_num 0 $($IP -6 route list |grep expires|wc -l) log_test $ret 0 "ipv6 route garbage collection (RA message)" diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index e87cf76b3e4a..afe862895946 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -1,12 +1,14 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns="ns1-$rndh" -ksft_skip=4 +ns="" test_cnt=1 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) @@ -26,25 +28,17 @@ flush_pids() done } +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null - ip netns del $ns + mptcp_lib_ns_exit "${ns}" } mptcp_lib_check_mptcp - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi -ss -h | grep -q MPTCP -if [ $? -ne 0 ];then - echo "SKIP: ss tool does not support MPTCP" - exit $ksft_skip -fi +mptcp_lib_check_tools ip ss get_msk_inuse() { @@ -69,7 +63,7 @@ __chk_nr() else echo "[ fail ] expected $expected found $nr" mptcp_lib_result_fail "${msg}" - ret=$test_cnt + ret=${KSFT_FAIL} fi else echo "[ ok ]" @@ -96,8 +90,8 @@ chk_listener_nr() local expected=$1 local msg="$2" - __chk_nr "ss -inmlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0 - __chk_nr "ss -inmlHtON $ns | wc -l" "$expected" "$msg - subflows" + __chk_nr "ss -nlHMON $ns | wc -l" "$expected" "$msg - mptcp" 0 + __chk_nr "ss -nlHtON $ns | wc -l" "$expected" "$msg - subflows" } wait_msk_nr() @@ -124,11 +118,11 @@ wait_msk_nr() if [ $i -ge $timeout ]; then echo "[ fail ] timeout while expecting $expected max $max last $nr" mptcp_lib_result_fail "${msg} # timeout" - ret=$test_cnt + ret=${KSFT_FAIL} elif [ $nr != $expected ]; then echo "[ fail ] expected $expected found $nr" mptcp_lib_result_fail "${msg} # unexpected result" - ret=$test_cnt + ret=${KSFT_FAIL} else echo "[ ok ]" mptcp_lib_result_pass "${msg}" @@ -186,7 +180,7 @@ chk_msk_inuse() expected=$((expected + listen_nr)) for _ in $(seq 10); do - if [ $(get_msk_inuse) -eq $expected ];then + if [ "$(get_msk_inuse)" -eq $expected ]; then break fi sleep 0.1 @@ -224,8 +218,7 @@ wait_connected() } trap cleanup EXIT -ip netns add $ns -ip -n $ns link set dev lo up +mptcp_lib_ns_init ns echo "a" | \ timeout ${timeout_test} \ @@ -273,7 +266,7 @@ chk_msk_inuse 0 "1->0" chk_msk_cestab 0 "1->0" NR_CLIENTS=100 -for I in `seq 1 $NR_CLIENTS`; do +for I in $(seq 1 $NR_CLIENTS); do echo "a" | \ timeout ${timeout_test} \ ip netns exec $ns \ @@ -282,7 +275,7 @@ for I in `seq 1 $NR_CLIENTS`; do done mptcp_lib_wait_local_port_listen $ns $((NR_CLIENTS + 10001)) -for I in `seq 1 $NR_CLIENTS`; do +for I in $(seq 1 $NR_CLIENTS); do echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ @@ -304,10 +297,7 @@ for I in $(seq 1 $NR_SERVERS); do ip netns exec $ns ./mptcp_connect -p $((I + 20001)) \ -t ${timeout_poll} -l 0.0.0.0 >/dev/null 2>&1 & done - -for I in $(seq 1 $NR_SERVERS); do - mptcp_lib_wait_local_port_listen $ns $((I + 20001)) -done +mptcp_lib_wait_local_port_listen $ns $((NR_SERVERS + 20001)) chk_listener_nr $NR_SERVERS "many listener sockets" diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 7898d62fce0b..0ca2960c9099 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" time_start=$(date +%s) @@ -13,7 +18,6 @@ sout="" cin_disconnect="" cin="" cout="" -ksft_skip=4 capture=false timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) @@ -121,16 +125,16 @@ while getopts "$optstring" option;do esac done -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" -ns3="ns3-$rndh" -ns4="ns4-$rndh" +ns1="" +ns2="" +ns3="" +ns4="" TEST_COUNT=0 TEST_GROUP="" +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { rm -f "$cin_disconnect" "$cout_disconnect" @@ -138,21 +142,12 @@ cleanup() rm -f "$sin" "$sout" rm -f "$capout" - local netns - for netns in "$ns1" "$ns2" "$ns3" "$ns4";do - ip netns del $netns - rm -f /tmp/$netns.{nstat,out} - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns3}" "${ns4}" } mptcp_lib_check_mptcp mptcp_lib_check_kallsyms - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip sin=$(mktemp) sout=$(mktemp) @@ -163,10 +158,7 @@ cin_disconnect="$cin".disconnect cout_disconnect="$cout".disconnect trap cleanup EXIT -for i in "$ns1" "$ns2" "$ns3" "$ns4";do - ip netns add $i || exit $ksft_skip - ip -net $i link set lo up -done +mptcp_lib_ns_init ns1 ns2 ns3 ns4 # "$ns1" ns2 ns3 ns4 # ns1eth2 ns2eth1 ns2eth3 ns3eth2 ns3eth4 ns4eth3 @@ -225,8 +217,9 @@ set_ethtool_flags() { local dev="$2" local flags="$3" - ip netns exec $ns ethtool -K $dev $flags 2>/dev/null - [ $? -eq 0 ] && echo "INFO: set $ns dev $dev: ethtool -K $flags" + if ip netns exec $ns ethtool -K $dev $flags 2>/dev/null; then + echo "INFO: set $ns dev $dev: ethtool -K $flags" + fi } set_random_ethtool_flags() { @@ -256,8 +249,8 @@ fi check_mptcp_disabled() { - local disabled_ns="ns_disabled-$rndh" - ip netns add ${disabled_ns} || exit $ksft_skip + local disabled_ns + mptcp_lib_ns_init disabled_ns # net.mptcp.enabled should be enabled by default if [ "$(ip netns exec ${disabled_ns} sysctl net.mptcp.enabled | awk '{ print $3 }')" -ne 1 ]; then @@ -271,7 +264,7 @@ check_mptcp_disabled() local err=0 LC_ALL=C ip netns exec ${disabled_ns} ./mptcp_connect -p 10000 -s MPTCP 127.0.0.1 < "$cin" 2>&1 | \ grep -q "^socket: Protocol not available$" && err=1 - ip netns delete ${disabled_ns} + mptcp_lib_ns_exit "${disabled_ns}" if [ ${err} -eq 0 ]; then echo -e "New MPTCP socket cannot be blocked via sysctl\t\t[ FAIL ]" @@ -321,7 +314,7 @@ do_transfer() local extra_args="$7" local port - port=$((10000+$TEST_COUNT)) + port=$((10000+TEST_COUNT)) TEST_COUNT=$((TEST_COUNT+1)) if [ "$rcvbuf" -gt 0 ]; then @@ -353,6 +346,7 @@ do_transfer() if $capture; then local capuser + local rndh="${connector_ns:4}" if [ -z $SUDO_USER ] ; then capuser="" else @@ -378,12 +372,18 @@ do_transfer() nstat -n fi - local stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local stat_synrx_last_l + local stat_ackrx_last_l + local stat_cookietx_last + local stat_cookierx_last + local stat_csum_err_s + local stat_csum_err_c + stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") timeout ${timeout_test} \ ip netns exec ${listener_ns} \ @@ -446,11 +446,16 @@ do_transfer() mptcp_lib_check_transfer $cin $sout "file received by server" rets=$? - local stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - local stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - local stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - local stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - local stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + local stat_synrx_now_l + local stat_ackrx_now_l + local stat_cookietx_now + local stat_cookierx_now + local stat_ooo_now + stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") expect_synrx=$((stat_synrx_last_l)) expect_ackrx=$((stat_ackrx_last_l)) @@ -459,8 +464,8 @@ do_transfer() cookies=${cookies##*=} if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then - expect_synrx=$((stat_synrx_last_l+$connect_per_transfer)) - expect_ackrx=$((stat_ackrx_last_l+$connect_per_transfer)) + expect_synrx=$((stat_synrx_last_l+connect_per_transfer)) + expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer)) fi if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then @@ -468,7 +473,7 @@ do_transfer() "${stat_synrx_now_l}" "${expect_synrx}" 1>&2 retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} -a ${stat_ooo_now} -eq 0 ]; then + if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ] && [ ${stat_ooo_now} -eq 0 ]; then if [ ${stat_ooo_now} -eq 0 ]; then printf "[ FAIL ] lower MPC ACK rx (%d) than expected (%d)\n" \ "${stat_ackrx_now_l}" "${expect_ackrx}" 1>&2 @@ -479,18 +484,20 @@ do_transfer() fi if $checksum; then - local csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - local csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") + local csum_err_s + local csum_err_c + csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") + csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) if [ $csum_err_s_nr -gt 0 ]; then - printf "[ FAIL ]\nserver got $csum_err_s_nr data checksum error[s]" + printf "[ FAIL ]\nserver got %d data checksum error[s]" ${csum_err_s_nr} rets=1 fi local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) if [ $csum_err_c_nr -gt 0 ]; then - printf "[ FAIL ]\nclient got $csum_err_c_nr data checksum error[s]" + printf "[ FAIL ]\nclient got %d data checksum error[s]" ${csum_err_c_nr} retc=1 fi fi @@ -658,7 +665,7 @@ run_test_transparent() return fi -ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" + if ! ip netns exec "$listener_ns" nft -f /dev/stdin <<"EOF" flush ruleset table inet mangle { chain divert { @@ -669,7 +676,7 @@ table inet mangle { } } EOF - if [ $? -ne 0 ]; then + then echo "SKIP: $msg, could not load nft ruleset" mptcp_lib_fail_if_expected_feature "nft rules" mptcp_lib_result_skip "${TEST_GROUP}" @@ -684,8 +691,7 @@ EOF local_addr="0.0.0.0" fi - ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100 - if [ $? -ne 0 ]; then + if ! ip -net "$listener_ns" $r6flag rule add fwmark 1 lookup 100; then ip netns exec "$listener_ns" nft flush ruleset echo "SKIP: $msg, ip $r6flag rule failed" mptcp_lib_fail_if_expected_feature "ip rule" @@ -693,8 +699,7 @@ EOF return fi - ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100 - if [ $? -ne 0 ]; then + if ! ip -net "$listener_ns" route add local $local_addr/0 dev lo table 100; then ip netns exec "$listener_ns" nft flush ruleset ip -net "$listener_ns" $r6flag rule del fwmark 1 lookup 100 echo "SKIP: $msg, ip route add local $local_addr failed" @@ -857,7 +862,7 @@ stop_if_error "Could not even run ping tests" echo -n "INFO: Using loss of $tc_loss " test "$tc_delay" -gt 0 && echo -n "delay $tc_delay ms " -reorder_delay=$(($tc_delay / 4)) +reorder_delay=$((tc_delay / 4)) if [ -z "${tc_reorder}" ]; then reorder1=$((RANDOM%10)) diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 955ee651dcd5..1df2d24979a0 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -86,21 +86,11 @@ init_partial() { capout=$(mktemp) - local sec rndh - sec=$(date +%s) - rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) - - ns1="ns1-$rndh" - ns2="ns2-$rndh" + mptcp_lib_ns_init ns1 ns2 local netns for netns in "$ns1" "$ns2"; do - ip netns add $netns || exit $ksft_skip - ip -net $netns link set lo up - ip netns exec $netns sysctl -q net.mptcp.enabled=1 ip netns exec $netns sysctl -q net.mptcp.pm_type=0 2>/dev/null || true - ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 - ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 if $checksum; then ip netns exec $netns sysctl -q net.mptcp.checksum_enabled=1 fi @@ -145,45 +135,15 @@ cleanup_partial() { rm -f "$capout" - local netns - for netns in "$ns1" "$ns2"; do - ip netns del $netns - rm -f /tmp/$netns.{nstat,out} - done -} - -check_tools() -{ - mptcp_lib_check_mptcp - mptcp_lib_check_kallsyms - - if ! ip -Version &> /dev/null; then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip - fi - - if ! ss -h | grep -q MPTCP; then - echo "SKIP: ss tool does not support MPTCP" - exit $ksft_skip - fi - - # Use the legacy version if available to support old kernel versions - if iptables-legacy -V &> /dev/null; then - iptables="iptables-legacy" - ip6tables="ip6tables-legacy" - elif ! iptables -V &> /dev/null; then - echo "SKIP: Could not run all tests without iptables tool" - exit $ksft_skip - elif ! ip6tables -V &> /dev/null; then - echo "SKIP: Could not run all tests without ip6tables tool" - exit $ksft_skip - fi + mptcp_lib_ns_exit "${ns1}" "${ns2}" } init() { init=1 - check_tools + mptcp_lib_check_mptcp + mptcp_lib_check_kallsyms + mptcp_lib_check_tools ip ss "${iptables}" "${ip6tables}" sin=$(mktemp) sout=$(mktemp) @@ -470,12 +430,8 @@ reset_with_events() { reset "${1}" || return 1 - :> "$evts_ns1" - :> "$evts_ns2" - ip netns exec $ns1 ./pm_nl_ctl events >> "$evts_ns1" 2>&1 & - evts_ns1_pid=$! - ip netns exec $ns2 ./pm_nl_ctl events >> "$evts_ns2" 2>&1 & - evts_ns2_pid=$! + mptcp_lib_events "${ns1}" "${evts_ns1}" evts_ns1_pid + mptcp_lib_events "${ns2}" "${evts_ns2}" evts_ns2_pid } reset_with_tcp_filter() @@ -648,7 +604,9 @@ wait_mpj() kill_events_pids() { mptcp_lib_kill_wait $evts_ns1_pid + evts_ns1_pid=0 mptcp_lib_kill_wait $evts_ns2_pid + evts_ns2_pid=0 } pm_nl_set_limits() diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 438f557aac90..5d071b6eb780 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -342,3 +342,71 @@ mptcp_lib_check_output() { return 1 fi } + +mptcp_lib_check_tools() { + local tool + + for tool in "${@}"; do + case "${tool}" in + "ip") + if ! ip -Version &> /dev/null; then + mptcp_lib_print_warn "SKIP: Could not run test without ip tool" + exit ${KSFT_SKIP} + fi + ;; + "ss") + if ! ss -h | grep -q MPTCP; then + mptcp_lib_print_warn "SKIP: ss tool does not support MPTCP" + exit ${KSFT_SKIP} + fi + ;; + "iptables"* | "ip6tables"*) + if ! "${tool}" -V &> /dev/null; then + mptcp_lib_print_warn "SKIP: Could not run all tests without ${tool}" + exit ${KSFT_SKIP} + fi + ;; + *) + mptcp_lib_print_err "Internal error: unsupported tool: ${tool}" + exit ${KSFT_FAIL} + ;; + esac + done +} +mptcp_lib_ns_init() { + local sec rndh + + sec=$(date +%s) + rndh=$(printf %x "${sec}")-$(mktemp -u XXXXXX) + + local netns + for netns in "${@}"; do + eval "${netns}=${netns}-${rndh}" + + ip netns add "${!netns}" || exit ${KSFT_SKIP} + ip -net "${!netns}" link set lo up + ip netns exec "${!netns}" sysctl -q net.mptcp.enabled=1 + ip netns exec "${!netns}" sysctl -q net.ipv4.conf.all.rp_filter=0 + ip netns exec "${!netns}" sysctl -q net.ipv4.conf.default.rp_filter=0 + done +} + +mptcp_lib_ns_exit() { + local netns + for netns in "${@}"; do + ip netns del "${netns}" + rm -f /tmp/"${netns}".{nstat,out} + done +} + +mptcp_lib_events() { + local ns="${1}" + local evts="${2}" + declare -n pid="${3}" + + :>"${evts}" + + mptcp_lib_kill_wait "${pid:-0}" + ip netns exec "${ns}" ./pm_nl_ctl events >> "${evts}" 2>&1 & + pid=$! +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index c643872ddf47..6ed4aa32222f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" ret=0 @@ -8,17 +13,14 @@ sin="" sout="" cin="" cout="" -ksft_skip=4 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) iptables="iptables" ip6tables="ip6tables" -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" -ns_sbox="ns_sbox-$rndh" +ns1="" +ns2="" +ns_sbox="" add_mark_rules() { @@ -40,17 +42,10 @@ add_mark_rules() init() { - local netns - for netns in "$ns1" "$ns2" "$ns_sbox";do - ip netns add $netns || exit $ksft_skip - ip -net $netns link set lo up - ip netns exec $netns sysctl -q net.mptcp.enabled=1 - ip netns exec $netns sysctl -q net.ipv4.conf.all.rp_filter=0 - ip netns exec $netns sysctl -q net.ipv4.conf.default.rp_filter=0 - done + mptcp_lib_ns_init ns1 ns2 ns_sbox local i - for i in `seq 1 4`; do + for i in $(seq 1 4); do ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2" ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad @@ -77,36 +72,18 @@ init() add_mark_rules $ns2 2 } +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { - local netns - for netns in "$ns1" "$ns2" "$ns_sbox"; do - ip netns del $netns - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}" rm -f "$cin" "$cout" rm -f "$sin" "$sout" } mptcp_lib_check_mptcp mptcp_lib_check_kallsyms - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -# Use the legacy version if available to support old kernel versions -if iptables-legacy -V &> /dev/null; then - iptables="iptables-legacy" - ip6tables="ip6tables-legacy" -elif ! iptables -V &> /dev/null; then - echo "SKIP: Could not run all tests without iptables tool" - exit $ksft_skip -elif ! ip6tables -V &> /dev/null; then - echo "SKIP: Could not run all tests without ip6tables tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip "${iptables}" "${ip6tables}" check_mark() { @@ -286,12 +263,12 @@ do_tcpinq_test() local lret=$? if [ $lret -ne 0 ];then ret=$lret - echo "FAIL: mptcp_inq $@" 1>&2 + echo "FAIL: mptcp_inq $*" 1>&2 mptcp_lib_result_fail "TCP_INQ: $*" return $lret fi - echo "PASS: TCP_INQ cmsg/ioctl $@" + echo "PASS: TCP_INQ cmsg/ioctl $*" mptcp_lib_result_pass "TCP_INQ: $*" return $lret } diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 705106d60db5..427fc5c70b3c 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -1,16 +1,20 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" -ksft_skip=4 ret=0 usage() { echo "Usage: $0 [ -h ]" } - +optstring=h while getopts "$optstring" option;do case "$option" in "h") @@ -24,30 +28,23 @@ while getopts "$optstring" option;do esac done -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" +ns1="" err=$(mktemp) +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { rm -f $err - ip netns del $ns1 + mptcp_lib_ns_exit "${ns1}" } mptcp_lib_check_mptcp - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip trap cleanup EXIT -ip netns add $ns1 || exit $ksft_skip -ip -net $ns1 link set lo up -ip netns exec $ns1 sysctl -q net.mptcp.enabled=1 +mptcp_lib_ns_init ns1 check() { @@ -100,14 +97,14 @@ check "ip netns exec $ns1 ./pm_nl_ctl get 4" "" "duplicate addr" ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.4 flags signal check "ip netns exec $ns1 ./pm_nl_ctl get 4" "id 4 flags signal 10.0.1.4" "id addr increment" -for i in `seq 5 9`; do +for i in $(seq 5 9); do ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.$i flags signal >/dev/null 2>&1 done check "ip netns exec $ns1 ./pm_nl_ctl get 9" "id 9 flags signal 10.0.1.9" "hard addr limit" check "ip netns exec $ns1 ./pm_nl_ctl get 10" "" "above hard addr limit" ip netns exec $ns1 ./pm_nl_ctl del 9 -for i in `seq 10 255`; do +for i in $(seq 10 255); do ip netns exec $ns1 ./pm_nl_ctl add 10.0.0.9 id $i ip netns exec $ns1 ./pm_nl_ctl del $i done diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index ed0165c15a24..365fb3d6ef55 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -1,15 +1,17 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + . "$(dirname "${0}")/mptcp_lib.sh" -sec=$(date +%s) -rndh=$(printf %x $sec)-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" -ns3="ns3-$rndh" +ns1="" +ns2="" +ns3="" capture=false -ksft_skip=4 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) test_cnt=1 @@ -30,25 +32,19 @@ usage() { echo -e "\t-d: debug this script" } +# This function is used in the cleanup trap +#shellcheck disable=SC2317 cleanup() { rm -f "$cout" "$sout" rm -f "$large" "$small" rm -f "$capout" - local netns - for netns in "$ns1" "$ns2" "$ns3";do - ip netns del $netns - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns3}" } mptcp_lib_check_mptcp - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi +mptcp_lib_check_tools ip # "$ns1" ns2 ns3 # ns1eth1 ns2eth1 ns2eth3 ns3eth1 @@ -70,12 +66,7 @@ setup() trap cleanup EXIT - for i in "$ns1" "$ns2" "$ns3";do - ip netns add $i || exit $ksft_skip - ip -net $i link set lo up - ip netns exec $i sysctl -q net.ipv4.conf.all.rp_filter=0 - ip netns exec $i sysctl -q net.ipv4.conf.default.rp_filter=0 - done + mptcp_lib_ns_init ns1 ns2 ns3 ip link add ns1eth1 netns "$ns1" type veth peer name ns2eth1 netns "$ns2" ip link add ns1eth2 netns "$ns1" type veth peer name ns2eth2 netns "$ns2" @@ -135,7 +126,7 @@ do_transfer() local sin=$2 local max_time=$3 local port - port=$((10000+$test_cnt)) + port=$((10000+test_cnt)) test_cnt=$((test_cnt+1)) :> "$cout" @@ -144,6 +135,7 @@ do_transfer() if $capture; then local capuser + local rndh="${ns1:4}" if [ -z $SUDO_USER ] ; then capuser="" else diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 1b94a75604fe..b0cce8f065d8 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -17,11 +17,7 @@ if ! mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then echo "userspace pm tests are not supported by the kernel: SKIP" exit ${KSFT_SKIP} fi - -if ! ip -Version &> /dev/null; then - echo "SKIP: Cannot not run test without ip tool" - exit ${KSFT_SKIP} -fi +mptcp_lib_check_tools ip ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED REMOVED=7 # MPTCP_EVENT_REMOVED @@ -54,10 +50,8 @@ app6_port=50004 client_addr_id=${RANDOM:0:2} server_addr_id=${RANDOM:0:2} -sec=$(date +%s) -rndh=$(printf %x "$sec")-$(mktemp -u XXXXXX) -ns1="ns1-$rndh" -ns2="ns2-$rndh" +ns1="" +ns2="" ret=0 test_name="" @@ -122,10 +116,7 @@ cleanup() mptcp_lib_kill_wait $pid done - local netns - for netns in "$ns1" "$ns2" ;do - ip netns del "$netns" - done + mptcp_lib_ns_exit "${ns1}" "${ns2}" rm -rf $file $client_evts $server_evts @@ -135,10 +126,8 @@ cleanup() trap cleanup EXIT # Create and configure network namespaces for testing +mptcp_lib_ns_init ns1 ns2 for i in "$ns1" "$ns2" ;do - ip netns add "$i" || exit 1 - ip -net "$i" link set lo up - ip netns exec "$i" sysctl -q net.mptcp.enabled=1 ip netns exec "$i" sysctl -q net.mptcp.pm_type=1 done @@ -160,17 +149,23 @@ ip -net "$ns2" addr add dead:beef:1::2/64 dev ns2eth1 nodad ip -net "$ns2" addr add dead:beef:2::2/64 dev ns2eth1 nodad ip -net "$ns2" link set ns2eth1 up +file=$(mktemp) +mptcp_lib_make_file "$file" 2 1 + +# Capture netlink events over the two network namespaces running +# the MPTCP client and server +client_evts=$(mktemp) +mptcp_lib_events "${ns2}" "${client_evts}" client_evts_pid +server_evts=$(mktemp) +mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid +sleep 0.5 + print_title "Init" print_test "Created network namespaces ns1, ns2" test_pass make_connection() { - if [ -z "$file" ]; then - file=$(mktemp) - fi - mptcp_lib_make_file "$file" 2 1 - local is_v6=$1 local app_port=$app4_port local connect_addr="10.0.1.1" @@ -184,27 +179,8 @@ make_connection() is_v6="v4" fi - # Capture netlink events over the two network namespaces running - # the MPTCP client and server - if [ -z "$client_evts" ]; then - client_evts=$(mktemp) - fi :>"$client_evts" - if [ $client_evts_pid -ne 0 ]; then - mptcp_lib_kill_wait $client_evts_pid - fi - ip netns exec "$ns2" ./pm_nl_ctl events >> "$client_evts" 2>&1 & - client_evts_pid=$! - if [ -z "$server_evts" ]; then - server_evts=$(mktemp) - fi :>"$server_evts" - if [ $server_evts_pid -ne 0 ]; then - mptcp_lib_kill_wait $server_evts_pid - fi - ip netns exec "$ns1" ./pm_nl_ctl events >> "$server_evts" 2>&1 & - server_evts_pid=$! - sleep 0.5 # Run the server ip netns exec "$ns1" \ diff --git a/tools/testing/selftests/powerpc/math/fpu_signal.c b/tools/testing/selftests/powerpc/math/fpu_signal.c index 7b1addd50420..8a64f63e37ce 100644 --- a/tools/testing/selftests/powerpc/math/fpu_signal.c +++ b/tools/testing/selftests/powerpc/math/fpu_signal.c @@ -18,6 +18,7 @@ #include <pthread.h> #include "utils.h" +#include "fpu.h" /* Number of times each thread should receive the signal */ #define ITERATIONS 10 @@ -27,9 +28,7 @@ */ #define THREAD_FACTOR 8 -__thread double darray[] = {0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0, - 1.1, 1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.8, 1.9, 2.0, - 2.1}; +__thread double darray[32]; bool bad_context; int threads_starting; @@ -43,9 +42,9 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context) ucontext_t *uc = context; mcontext_t *mc = &uc->uc_mcontext; - /* Only the non volatiles were loaded up */ - for (i = 14; i < 32; i++) { - if (mc->fp_regs[i] != darray[i - 14]) { + // Don't check f30/f31, they're used as scratches in check_all_fprs() + for (i = 0; i < 30; i++) { + if (mc->fp_regs[i] != darray[i]) { bad_context = true; break; } @@ -54,7 +53,6 @@ void signal_fpu_sig(int sig, siginfo_t *info, void *context) void *signal_fpu_c(void *p) { - int i; long rc; struct sigaction act; act.sa_sigaction = signal_fpu_sig; @@ -64,9 +62,7 @@ void *signal_fpu_c(void *p) return p; srand(pthread_self()); - for (i = 0; i < 21; i++) - darray[i] = rand(); - + randomise_darray(darray, ARRAY_SIZE(darray)); rc = preempt_fpu(darray, &threads_starting, &running); return (void *) rc; |